sweeplog

wandb: Agent Starting Run: rxx2sygy with config:
wandb: 	accumulate_grad_batches: 7
wandb: 	epochs: 1
wandb: 	gradient_clip_val: 0.92372930002197
wandb: 	init_lora_weights: pissa_niter_32
wandb: 	lora_alpha: 32
wandb: 	lora_dropout: 0.0794528890442868
wandb: 	lora_rank: 16
wandb: 	lr: 0.0004051653419029888
wandb: 	model_name: tiiuae/falcon-7b-instruct
wandb: Currently logged in as: j0ntendo (j0ntendo-yonsei-university). Use `wandb login --relogin` to force relogin
wandb: WARNING Ignored wandb.init() arg project when running a sweep.
wandb: Tracking run with wandb version 0.17.5
wandb: Run data is saved locally in /user/jonathan/wandb/run-20240806_134906-rxx2sygy
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run usual-sweep-1
wandb: ⭐️ View project at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: 🧹 View sweep at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/sweeps/4ik6ex9z
wandb: 🚀 View run at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/rxx2sygy
Unused kwargs: ['bnb_8bit_quant_type', 'bnb_8bit_compute_dtype']. These kwargs are not used in <class 'transformers.utils.quantization_config.BitsAndBytesConfig'>.
Repo card metadata block was not found. Setting CardData to empty.


                    ####
                ###########
             ####################
         ############################
    #####################################
##############################################
#########################  ###################
#######################    ###################
####################      ####################
##################       #####################
################        ######################
#####################        #################
######################     ###################
#####################    #####################
####################   #######################
###################  #########################
##############################################
    #####################################
         ############################
             ####################
                  ##########
                     ####


Create sweep with ID: 4ik6ex9z
Sweep URL: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/sweeps/4ik6ex9z
[2024-08-06 13:49:20,008] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
/user/jonathan/jonathan/lib/python3.10/site-packages/deepspeed/runtime/zero/linear.py:49: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
  def forward(ctx, input, weight, bias=None):
/user/jonathan/jonathan/lib/python3.10/site-packages/deepspeed/runtime/zero/linear.py:67: FutureWarning: `torch.cuda.amp.custom_bwd(args...)` is deprecated. Please use `torch.amp.custom_bwd(args..., device_type='cuda')` instead.
  def backward(ctx, grad_output):
GPU available: True (cuda), used: True
TPU available: False, using: 0 TPU cores
HPU available: False, using: 0 HPUs
You are using a CUDA device ('NVIDIA A100-SXM4-80GB') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision
initializing deepspeed distributed: GLOBAL_RANK: 0, MEMBER: 1/1
/user/jonathan/jonathan/lib/python3.10/site-packages/lightning/pytorch/loggers/wandb.py:396: There is a wandb run already in progress and newly created instances of `WandbLogger` will reuse this run. If this is not desired, call `wandb.finish()` before instantiating `WandbLogger`.
2024-08-06 13:49:24.254273: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-08-06 13:49:27.865117: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
/user/jonathan/jonathan/lib/python3.10/site-packages/lightning/pytorch/callbacks/model_checkpoint.py:652: Checkpoint directory /user/jonathan/checkpoint exists and is not empty.
Enabling DeepSpeed BF16. Model parameters and inputs will be cast to `bfloat16`.
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]
Warning: The default cache directory for DeepSpeed Triton autotune, /user/jonathan/.triton/autotune, appears to be on an NFS system. While this is generally acceptable, if you experience slowdowns or hanging when DeepSpeed exits, it is recommended to set the TRITON_CACHE_DIR environment variable to a non-NFS path.
 [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
 [WARNING]  async_io: please install the libaio-dev package with apt
 [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
 [WARNING]  Please specify the CUTLASS repo directory as environment variable $CUTLASS_PATH
 [WARNING]  sparse_attn requires a torch version >= 1.5 and < 2.0 but detected 2.4
 [WARNING]  using untested triton version (3.0.0), only 1.0.0 is known to be compatible
[2024-08-06 13:49:37,199] [WARNING] [engine.py:1179:_do_optimizer_sanity_check] **** You are using ZeRO with an untested optimizer, proceed with caution *****

  | Name  | Type                 | Params | Mode 
-------------------------------------------------------
0 | model | PeftModelForCausalLM | 1.5 B  | train
-------------------------------------------------------
2.2 M     Trainable params
1.5 B     Non-trainable params
1.5 B     Total params
6,192.290 Total estimated model params size (MB)

Sanity Checking: |          | 0/? [00:00<?, ?it/s]/user/jonathan/jonathan/lib/python3.10/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:424: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=127` in the `DataLoader` to improve performance.

Sanity Checking:   0%|          | 0/2 [00:00<?, ?it/s]
Sanity Checking DataLoader 0:   0%|          | 0/2 [00:00<?, ?it/s]We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co/docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)

Sanity Checking DataLoader 0: 100%|██████████| 2/2 [00:00<00:00,  2.01it/s]
                                                                           /user/jonathan/jonathan/lib/python3.10/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:424: The 'train_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=127` in the `DataLoader` to improve performance.


Training: |          | 0/? [00:00<?, ?it/s]
Training:   0%|          | 0/192 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/192 [00:00<?, ?it/s] 
Epoch 0:   3%|▎         | 5/192 [00:01<01:01,  3.02it/s]
Epoch 0:   3%|▎         | 5/192 [00:01<01:01,  3.02it/s, v_num=gy_1, train_loss_step=5.450, train_rouge1_fmeasure_step=0.00117, train_rouge1_precision_step=0.000589, train_rouge1_recall_step=0.100, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.00117, train_rougeL_precision_step=0.000589, train_rougeL_recall_step=0.100, train_rougeLsum_fmeasure_step=0.00117, train_rougeLsum_precision_step=0.000589, train_rougeLsum_recall_step=0.100]
Epoch 0:   5%|▌         | 10/192 [00:03<01:01,  2.98it/s, v_num=gy_1, train_loss_step=5.450, train_rouge1_fmeasure_step=0.00117, train_rouge1_precision_step=0.000589, train_rouge1_recall_step=0.100, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.00117, train_rougeL_precision_step=0.000589, train_rougeL_recall_step=0.100, train_rougeLsum_fmeasure_step=0.00117, train_rougeLsum_precision_step=0.000589, train_rougeLsum_recall_step=0.100]
Epoch 0:   5%|▌         | 10/192 [00:03<01:01,  2.98it/s, v_num=gy_1, train_loss_step=5.730, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]               
Epoch 0:   8%|▊         | 15/192 [00:04<00:58,  3.02it/s, v_num=gy_1, train_loss_step=5.730, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:   8%|▊         | 15/192 [00:04<00:58,  3.02it/s, v_num=gy_1, train_loss_step=4.770, train_rouge1_fmeasure_step=0.00123, train_rouge1_precision_step=0.000627, train_rouge1_recall_step=0.0385, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.00123, train_rougeL_precision_step=0.000627, train_rougeL_recall_step=0.0385, train_rougeLsum_fmeasure_step=0.00123, train_rougeLsum_precision_step=0.000627, train_rougeLsum_recall_step=0.0385]
Epoch 0:  10%|█         | 20/192 [00:06<00:57,  3.02it/s, v_num=gy_1, train_loss_step=4.770, train_rouge1_fmeasure_step=0.00123, train_rouge1_precision_step=0.000627, train_rouge1_recall_step=0.0385, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.00123, train_rougeL_precision_step=0.000627, train_rougeL_recall_step=0.0385, train_rougeLsum_fmeasure_step=0.00123, train_rougeLsum_precision_step=0.000627, train_rougeLsum_recall_step=0.0385]
Epoch 0:  10%|█         | 20/192 [00:06<00:57,  3.02it/s, v_num=gy_1, train_loss_step=4.780, train_rouge1_fmeasure_step=0.00145, train_rouge1_precision_step=0.000733, train_rouge1_recall_step=0.0714, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.00145, train_rougeL_precision_step=0.000733, train_rougeL_recall_step=0.0714, train_rougeLsum_fmeasure_step=0.00145, train_rougeLsum_precision_step=0.000733, train_rougeLsum_recall_step=0.0714]
Epoch 0:  13%|█▎        | 25/192 [00:08<00:55,  3.03it/s, v_num=gy_1, train_loss_step=4.780, train_rouge1_fmeasure_step=0.00145, train_rouge1_precision_step=0.000733, train_rouge1_recall_step=0.0714, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.00145, train_rougeL_precision_step=0.000733, train_rougeL_recall_step=0.0714, train_rougeLsum_fmeasure_step=0.00145, train_rougeLsum_precision_step=0.000733, train_rougeLsum_recall_step=0.0714]
Epoch 0:  13%|█▎        | 25/192 [00:08<00:55,  3.03it/s, v_num=gy_1, train_loss_step=3.640, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]                  
Epoch 0:  16%|█▌        | 30/192 [00:09<00:52,  3.06it/s, v_num=gy_1, train_loss_step=3.640, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  16%|█▌        | 30/192 [00:09<00:52,  3.06it/s, v_num=gy_1, train_loss_step=2.730, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  18%|█▊        | 35/192 [00:11<00:51,  3.08it/s, v_num=gy_1, train_loss_step=2.730, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  18%|█▊        | 35/192 [00:11<00:51,  3.08it/s, v_num=gy_1, train_loss_step=3.600, train_rouge1_fmeasure_step=0.0455, train_rouge1_precision_step=0.0446, train_rouge1_recall_step=0.0464, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0455, train_rougeL_precision_step=0.0446, train_rougeL_recall_step=0.0464, train_rougeLsum_fmeasure_step=0.0455, train_rougeLsum_precision_step=0.0446, train_rougeLsum_recall_step=0.0464]
Epoch 0:  21%|██        | 40/192 [00:12<00:49,  3.09it/s, v_num=gy_1, train_loss_step=3.600, train_rouge1_fmeasure_step=0.0455, train_rouge1_precision_step=0.0446, train_rouge1_recall_step=0.0464, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0455, train_rougeL_precision_step=0.0446, train_rougeL_recall_step=0.0464, train_rougeLsum_fmeasure_step=0.0455, train_rougeLsum_precision_step=0.0446, train_rougeLsum_recall_step=0.0464]
Epoch 0:  21%|██        | 40/192 [00:12<00:49,  3.09it/s, v_num=gy_1, train_loss_step=3.160, train_rouge1_fmeasure_step=0.0432, train_rouge1_precision_step=0.0323, train_rouge1_recall_step=0.0652, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0288, train_rougeL_precision_step=0.0215, train_rougeL_recall_step=0.0435, train_rougeLsum_fmeasure_step=0.0432, train_rougeLsum_precision_step=0.0323, train_rougeLsum_recall_step=0.0652]
Epoch 0:  23%|██▎       | 45/192 [00:14<00:47,  3.10it/s, v_num=gy_1, train_loss_step=3.160, train_rouge1_fmeasure_step=0.0432, train_rouge1_precision_step=0.0323, train_rouge1_recall_step=0.0652, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0288, train_rougeL_precision_step=0.0215, train_rougeL_recall_step=0.0435, train_rougeLsum_fmeasure_step=0.0432, train_rougeLsum_precision_step=0.0323, train_rougeLsum_recall_step=0.0652]
Epoch 0:  23%|██▎       | 45/192 [00:14<00:47,  3.10it/s, v_num=gy_1, train_loss_step=1.630, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]         
Epoch 0:  26%|██▌       | 50/192 [00:16<00:45,  3.11it/s, v_num=gy_1, train_loss_step=1.630, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  26%|██▌       | 50/192 [00:16<00:45,  3.11it/s, v_num=gy_1, train_loss_step=2.280, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  29%|██▊       | 55/192 [00:17<00:44,  3.11it/s, v_num=gy_1, train_loss_step=2.280, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  29%|██▊       | 55/192 [00:17<00:44,  3.11it/s, v_num=gy_1, train_loss_step=2.930, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  31%|███▏      | 60/192 [00:19<00:42,  3.12it/s, v_num=gy_1, train_loss_step=2.930, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  31%|███▏      | 60/192 [00:19<00:42,  3.12it/s, v_num=gy_1, train_loss_step=2.600, train_rouge1_fmeasure_step=0.0259, train_rouge1_precision_step=0.014, train_rouge1_recall_step=0.174, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0194, train_rougeL_precision_step=0.0105, train_rougeL_recall_step=0.130, train_rougeLsum_fmeasure_step=0.0259, train_rougeLsum_precision_step=0.014, train_rougeLsum_recall_step=0.174]
Epoch 0:  34%|███▍      | 65/192 [00:20<00:40,  3.12it/s, v_num=gy_1, train_loss_step=2.600, train_rouge1_fmeasure_step=0.0259, train_rouge1_precision_step=0.014, train_rouge1_recall_step=0.174, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0194, train_rougeL_precision_step=0.0105, train_rougeL_recall_step=0.130, train_rougeLsum_fmeasure_step=0.0259, train_rougeLsum_precision_step=0.014, train_rougeLsum_recall_step=0.174]
Epoch 0:  34%|███▍      | 65/192 [00:20<00:40,  3.12it/s, v_num=gy_1, train_loss_step=2.680, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]    
Epoch 0:  36%|███▋      | 70/192 [00:22<00:39,  3.13it/s, v_num=gy_1, train_loss_step=2.680, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  36%|███▋      | 70/192 [00:22<00:39,  3.13it/s, v_num=gy_1, train_loss_step=2.780, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  39%|███▉      | 75/192 [00:23<00:37,  3.13it/s, v_num=gy_1, train_loss_step=2.780, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  39%|███▉      | 75/192 [00:23<00:37,  3.13it/s, v_num=gy_1, train_loss_step=5.300, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  42%|████▏     | 80/192 [00:25<00:35,  3.13it/s, v_num=gy_1, train_loss_step=5.300, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  42%|████▏     | 80/192 [00:25<00:35,  3.13it/s, v_num=gy_1, train_loss_step=1.990, train_rouge1_fmeasure_step=0.0674, train_rouge1_precision_step=0.0938, train_rouge1_recall_step=0.0526, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0562, train_rougeL_precision_step=0.0781, train_rougeL_recall_step=0.0439, train_rougeLsum_fmeasure_step=0.0562, train_rougeLsum_precision_step=0.0781, train_rougeLsum_recall_step=0.0439]
Epoch 0:  44%|████▍     | 85/192 [00:27<00:34,  3.14it/s, v_num=gy_1, train_loss_step=1.990, train_rouge1_fmeasure_step=0.0674, train_rouge1_precision_step=0.0938, train_rouge1_recall_step=0.0526, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0562, train_rougeL_precision_step=0.0781, train_rougeL_recall_step=0.0439, train_rougeLsum_fmeasure_step=0.0562, train_rougeLsum_precision_step=0.0781, train_rougeLsum_recall_step=0.0439]
Epoch 0:  44%|████▍     | 85/192 [00:27<00:34,  3.14it/s, v_num=gy_1, train_loss_step=0.776, train_rouge1_fmeasure_step=0.0154, train_rouge1_precision_step=0.0106, train_rouge1_recall_step=0.0278, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0154, train_rougeL_precision_step=0.0106, train_rougeL_recall_step=0.0278, train_rougeLsum_fmeasure_step=0.0154, train_rougeLsum_precision_step=0.0106, train_rougeLsum_recall_step=0.0278]
Epoch 0:  47%|████▋     | 90/192 [00:28<00:32,  3.14it/s, v_num=gy_1, train_loss_step=0.776, train_rouge1_fmeasure_step=0.0154, train_rouge1_precision_step=0.0106, train_rouge1_recall_step=0.0278, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0154, train_rougeL_precision_step=0.0106, train_rougeL_recall_step=0.0278, train_rougeLsum_fmeasure_step=0.0154, train_rougeLsum_precision_step=0.0106, train_rougeLsum_recall_step=0.0278]
Epoch 0:  47%|████▋     | 90/192 [00:28<00:32,  3.14it/s, v_num=gy_1, train_loss_step=5.700, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]         
Epoch 0:  49%|████▉     | 95/192 [00:30<00:30,  3.15it/s, v_num=gy_1, train_loss_step=5.700, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  49%|████▉     | 95/192 [00:30<00:30,  3.15it/s, v_num=gy_1, train_loss_step=0.772, train_rouge1_fmeasure_step=0.0755, train_rouge1_precision_step=0.0444, train_rouge1_recall_step=0.250, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0755, train_rougeL_precision_step=0.0444, train_rougeL_recall_step=0.250, train_rougeLsum_fmeasure_step=0.0755, train_rougeLsum_precision_step=0.0444, train_rougeLsum_recall_step=0.250]
Epoch 0:  52%|█████▏    | 100/192 [00:31<00:29,  3.15it/s, v_num=gy_1, train_loss_step=0.772, train_rouge1_fmeasure_step=0.0755, train_rouge1_precision_step=0.0444, train_rouge1_recall_step=0.250, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0755, train_rougeL_precision_step=0.0444, train_rougeL_recall_step=0.250, train_rougeLsum_fmeasure_step=0.0755, train_rougeLsum_precision_step=0.0444, train_rougeLsum_recall_step=0.250]
Epoch 0:  52%|█████▏    | 100/192 [00:31<00:29,  3.15it/s, v_num=gy_1, train_loss_step=1.070, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]      
Epoch 0:  55%|█████▍    | 105/192 [00:33<00:27,  3.15it/s, v_num=gy_1, train_loss_step=1.070, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  55%|█████▍    | 105/192 [00:33<00:27,  3.15it/s, v_num=gy_1, train_loss_step=0.380, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  57%|█████▋    | 110/192 [00:34<00:26,  3.15it/s, v_num=gy_1, train_loss_step=0.380, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  57%|█████▋    | 110/192 [00:34<00:26,  3.15it/s, v_num=gy_1, train_loss_step=0.360, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  60%|█████▉    | 115/192 [00:36<00:24,  3.15it/s, v_num=gy_1, train_loss_step=0.360, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  60%|█████▉    | 115/192 [00:36<00:24,  3.15it/s, v_num=gy_1, train_loss_step=5.230, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  62%|██████▎   | 120/192 [00:38<00:22,  3.16it/s, v_num=gy_1, train_loss_step=5.230, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  62%|██████▎   | 120/192 [00:38<00:22,  3.16it/s, v_num=gy_1, train_loss_step=0.338, train_rouge1_fmeasure_step=0.0571, train_rouge1_precision_step=0.0625, train_rouge1_recall_step=0.0526, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0571, train_rougeL_precision_step=0.0625, train_rougeL_recall_step=0.0526, train_rougeLsum_fmeasure_step=0.0571, train_rougeLsum_precision_step=0.0625, train_rougeLsum_recall_step=0.0526]
Epoch 0:  65%|██████▌   | 125/192 [00:39<00:21,  3.16it/s, v_num=gy_1, train_loss_step=0.338, train_rouge1_fmeasure_step=0.0571, train_rouge1_precision_step=0.0625, train_rouge1_recall_step=0.0526, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0571, train_rougeL_precision_step=0.0625, train_rougeL_recall_step=0.0526, train_rougeLsum_fmeasure_step=0.0571, train_rougeLsum_precision_step=0.0625, train_rougeLsum_recall_step=0.0526]
Epoch 0:  65%|██████▌   | 125/192 [00:39<00:21,  3.16it/s, v_num=gy_1, train_loss_step=0.180, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]         
Epoch 0:  68%|██████▊   | 130/192 [00:41<00:19,  3.16it/s, v_num=gy_1, train_loss_step=0.180, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  68%|██████▊   | 130/192 [00:41<00:19,  3.16it/s, v_num=gy_1, train_loss_step=1.770, train_rouge1_fmeasure_step=0.0707, train_rouge1_precision_step=0.152, train_rouge1_recall_step=0.0461, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0505, train_rougeL_precision_step=0.109, train_rougeL_recall_step=0.0329, train_rougeLsum_fmeasure_step=0.0505, train_rougeLsum_precision_step=0.109, train_rougeLsum_recall_step=0.0329]
Epoch 0:  70%|███████   | 135/192 [00:42<00:18,  3.16it/s, v_num=gy_1, train_loss_step=1.770, train_rouge1_fmeasure_step=0.0707, train_rouge1_precision_step=0.152, train_rouge1_recall_step=0.0461, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0505, train_rougeL_precision_step=0.109, train_rougeL_recall_step=0.0329, train_rougeLsum_fmeasure_step=0.0505, train_rougeLsum_precision_step=0.109, train_rougeLsum_recall_step=0.0329]
Epoch 0:  70%|███████   | 135/192 [00:42<00:18,  3.16it/s, v_num=gy_1, train_loss_step=1.910, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]      
Epoch 0:  73%|███████▎  | 140/192 [00:44<00:16,  3.16it/s, v_num=gy_1, train_loss_step=1.910, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  73%|███████▎  | 140/192 [00:44<00:16,  3.16it/s, v_num=gy_1, train_loss_step=3.720, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  76%|███████▌  | 145/192 [00:45<00:14,  3.16it/s, v_num=gy_1, train_loss_step=3.720, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  76%|███████▌  | 145/192 [00:45<00:14,  3.16it/s, v_num=gy_1, train_loss_step=0.154, train_rouge1_fmeasure_step=0.0833, train_rouge1_precision_step=0.0667, train_rouge1_recall_step=0.111, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0833, train_rougeL_precision_step=0.0667, train_rougeL_recall_step=0.111, train_rougeLsum_fmeasure_step=0.0833, train_rougeLsum_precision_step=0.0667, train_rougeLsum_recall_step=0.111]
Epoch 0:  78%|███████▊  | 150/192 [00:47<00:13,  3.16it/s, v_num=gy_1, train_loss_step=0.154, train_rouge1_fmeasure_step=0.0833, train_rouge1_precision_step=0.0667, train_rouge1_recall_step=0.111, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0833, train_rougeL_precision_step=0.0667, train_rougeL_recall_step=0.111, train_rougeLsum_fmeasure_step=0.0833, train_rougeLsum_precision_step=0.0667, train_rougeLsum_recall_step=0.111]
Epoch 0:  78%|███████▊  | 150/192 [00:47<00:13,  3.16it/s, v_num=gy_1, train_loss_step=2.160, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]      
Epoch 0:  81%|████████  | 155/192 [00:48<00:11,  3.17it/s, v_num=gy_1, train_loss_step=2.160, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  81%|████████  | 155/192 [00:48<00:11,  3.17it/s, v_num=gy_1, train_loss_step=1.150, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  83%|████████▎ | 160/192 [00:50<00:10,  3.17it/s, v_num=gy_1, train_loss_step=1.150, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  83%|████████▎ | 160/192 [00:50<00:10,  3.17it/s, v_num=gy_1, train_loss_step=0.596, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  86%|████████▌ | 165/192 [00:52<00:08,  3.17it/s, v_num=gy_1, train_loss_step=0.596, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  86%|████████▌ | 165/192 [00:52<00:08,  3.17it/s, v_num=gy_1, train_loss_step=2.700, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  89%|████████▊ | 170/192 [00:53<00:06,  3.17it/s, v_num=gy_1, train_loss_step=2.700, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  89%|████████▊ | 170/192 [00:53<00:06,  3.17it/s, v_num=gy_1, train_loss_step=0.307, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  91%|█████████ | 175/192 [00:55<00:05,  3.17it/s, v_num=gy_1, train_loss_step=0.307, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  91%|█████████ | 175/192 [00:55<00:05,  3.17it/s, v_num=gy_1, train_loss_step=0.288, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  94%|█████████▍| 180/192 [00:56<00:03,  3.17it/s, v_num=gy_1, train_loss_step=0.288, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  94%|█████████▍| 180/192 [00:56<00:03,  3.17it/s, v_num=gy_1, train_loss_step=0.577, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  96%|█████████▋| 185/192 [00:58<00:02,  3.17it/s, v_num=gy_1, train_loss_step=0.577, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  96%|█████████▋| 185/192 [00:58<00:02,  3.17it/s, v_num=gy_1, train_loss_step=6.880, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  99%|█████████▉| 190/192 [00:59<00:00,  3.18it/s, v_num=gy_1, train_loss_step=6.880, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  99%|█████████▉| 190/192 [00:59<00:00,  3.17it/s, v_num=gy_1, train_loss_step=0.681, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0: 100%|██████████| 192/192 [01:00<00:00,  3.18it/s, v_num=gy_1, train_loss_step=0.681, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0: 100%|██████████| 192/192 [01:00<00:00,  3.18it/s, v_num=gy_1, train_loss_step=0.763, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]

Validation: |          | 0/? [00:00<?, ?it/s]

Validation:   0%|          | 0/12 [00:00<?, ?it/s]

Validation DataLoader 0:   0%|          | 0/12 [00:00<?, ?it/s]

Validation DataLoader 0:  42%|████▏     | 5/12 [00:00<00:01,  5.39it/s]

Validation DataLoader 0:  83%|████████▎ | 10/12 [00:01<00:00,  5.37it/s]

Validation DataLoader 0: 100%|██████████| 12/12 [00:02<00:00,  5.36it/s]

                                                                        
Epoch 0: 100%|██████████| 192/192 [01:02<00:00,  3.06it/s, v_num=gy_1, train_loss_step=0.763, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000, val_loss_step=6.070, val_rouge1_fmeasure_step=0.000, val_rouge1_precision_step=0.000, val_rouge1_recall_step=0.000, val_rouge2_fmeasure_step=0.000, val_rouge2_precision_step=0.000, val_rouge2_recall_step=0.000, val_rougeL_fmeasure_step=0.000, val_rougeL_precision_step=0.000, val_rougeL_recall_step=0.000, val_rougeLsum_fmeasure_step=0.000, val_rougeLsum_precision_step=0.000, val_rougeLsum_recall_step=0.000, val_loss_epoch=1.350, val_rouge1_fmeasure_epoch=0.0144, val_rouge1_precision_epoch=0.0261, val_rouge1_recall_epoch=0.0113, val_rouge2_fmeasure_epoch=0.000, val_rouge2_precision_epoch=0.000, val_rouge2_recall_epoch=0.000, val_rougeL_fmeasure_epoch=0.0129, val_rougeL_precision_epoch=0.0233, val_rougeL_recall_epoch=0.010, val_rougeLsum_fmeasure_epoch=0.0144, val_rougeLsum_precision_epoch=0.0261, val_rougeLsum_recall_epoch=0.0113]
Epoch 0: 100%|██████████| 192/192 [01:02<00:00,  3.06it/s, v_num=gy_1, train_loss_step=0.763, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000, val_loss_step=6.070, val_rouge1_fmeasure_step=0.000, val_rouge1_precision_step=0.000, val_rouge1_recall_step=0.000, val_rouge2_fmeasure_step=0.000, val_rouge2_precision_step=0.000, val_rouge2_recall_step=0.000, val_rougeL_fmeasure_step=0.000, val_rougeL_precision_step=0.000, val_rougeL_recall_step=0.000, val_rougeLsum_fmeasure_step=0.000, val_rougeLsum_precision_step=0.000, val_rougeLsum_recall_step=0.000, val_loss_epoch=1.350, val_rouge1_fmeasure_epoch=0.0144, val_rouge1_precision_epoch=0.0261, val_rouge1_recall_epoch=0.0113, val_rouge2_fmeasure_epoch=0.000, val_rouge2_precision_epoch=0.000, val_rouge2_recall_epoch=0.000, val_rougeL_fmeasure_epoch=0.0129, val_rougeL_precision_epoch=0.0233, val_rougeL_recall_epoch=0.010, val_rougeLsum_fmeasure_epoch=0.0144, val_rougeLsum_precision_epoch=0.0261, val_rougeLsum_recall_epoch=0.0113, train_loss_epoch=2.300, train_rouge1_fmeasure_epoch=0.0101, train_rouge1_precision_epoch=0.013, train_rouge1_recall_epoch=0.026, train_rouge2_fmeasure_epoch=0.000, train_rouge2_precision_epoch=0.000, train_rouge2_recall_epoch=0.000, train_rougeL_fmeasure_epoch=0.00923, train_rougeL_precision_epoch=0.0117, train_rougeL_recall_epoch=0.0238, train_rougeLsum_fmeasure_epoch=0.00992, train_rougeLsum_precision_epoch=0.0126, train_rougeLsum_recall_epoch=0.0258]`Trainer.fit` stopped: `max_epochs=1` reached.

Epoch 0: 100%|██████████| 192/192 [01:27<00:00,  2.20it/s, v_num=gy_1, train_loss_step=0.763, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000, val_loss_step=6.070, val_rouge1_fmeasure_step=0.000, val_rouge1_precision_step=0.000, val_rouge1_recall_step=0.000, val_rouge2_fmeasure_step=0.000, val_rouge2_precision_step=0.000, val_rouge2_recall_step=0.000, val_rougeL_fmeasure_step=0.000, val_rougeL_precision_step=0.000, val_rougeL_recall_step=0.000, val_rougeLsum_fmeasure_step=0.000, val_rougeLsum_precision_step=0.000, val_rougeLsum_recall_step=0.000, val_loss_epoch=1.350, val_rouge1_fmeasure_epoch=0.0144, val_rouge1_precision_epoch=0.0261, val_rouge1_recall_epoch=0.0113, val_rouge2_fmeasure_epoch=0.000, val_rouge2_precision_epoch=0.000, val_rouge2_recall_epoch=0.000, val_rougeL_fmeasure_epoch=0.0129, val_rougeL_precision_epoch=0.0233, val_rougeL_recall_epoch=0.010, val_rougeLsum_fmeasure_epoch=0.0144, val_rougeLsum_precision_epoch=0.0261, val_rougeLsum_recall_epoch=0.0113, train_loss_epoch=2.300, train_rouge1_fmeasure_epoch=0.0101, train_rouge1_precision_epoch=0.013, train_rouge1_recall_epoch=0.026, train_rouge2_fmeasure_epoch=0.000, train_rouge2_precision_epoch=0.000, train_rouge2_recall_epoch=0.000, train_rougeL_fmeasure_epoch=0.00923, train_rougeL_precision_epoch=0.0117, train_rougeL_recall_epoch=0.0238, train_rougeLsum_fmeasure_epoch=0.00992, train_rougeLsum_precision_epoch=0.0126, train_rougeLsum_recall_epoch=0.0258]wandb: - 0.014 MB of 0.014 MB uploaded
wandb: \ 0.014 MB of 0.014 MB uploaded
wandb: | 0.014 MB of 0.014 MB uploaded
wandb: / 0.014 MB of 0.014 MB uploaded
wandb: - 0.014 MB of 0.020 MB uploaded
wandb: \ 0.014 MB of 0.020 MB uploaded
wandb: | 0.027 MB of 0.027 MB uploaded
wandb:                                                                                
wandb: 
wandb: Run history:
wandb:                           epoch ▁▁
wandb:                train_loss_epoch ▁
wandb:     train_rouge1_fmeasure_epoch ▁
wandb:    train_rouge1_precision_epoch ▁
wandb:       train_rouge1_recall_epoch ▁
wandb:     train_rouge2_fmeasure_epoch ▁
wandb:    train_rouge2_precision_epoch ▁
wandb:       train_rouge2_recall_epoch ▁
wandb:     train_rougeL_fmeasure_epoch ▁
wandb:    train_rougeL_precision_epoch ▁
wandb:       train_rougeL_recall_epoch ▁
wandb:  train_rougeLsum_fmeasure_epoch ▁
wandb: train_rougeLsum_precision_epoch ▁
wandb:    train_rougeLsum_recall_epoch ▁
wandb:             trainer/global_step ▁▁▂▂▂▂▃▃▃▃▄▄██
wandb:                  val_loss_epoch ▁
wandb:                   val_loss_step ▂▁▁▁▁▃▄▁▂▂▃█
wandb:       val_rouge1_fmeasure_epoch ▁
wandb:        val_rouge1_fmeasure_step ▂▁▅█▃▄▁▁▁▁▁▁
wandb:      val_rouge1_precision_epoch ▁
wandb:       val_rouge1_precision_step ▃▁▆▆▃█▁▁▁▁▁▁
wandb:         val_rouge1_recall_epoch ▁
wandb:          val_rouge1_recall_step ▂▁▄█▂▃▁▁▁▁▁▁
wandb:       val_rouge2_fmeasure_epoch ▁
wandb:        val_rouge2_fmeasure_step ▁▁▁▁▁▁▁▁▁▁▁▁
wandb:      val_rouge2_precision_epoch ▁
wandb:       val_rouge2_precision_step ▁▁▁▁▁▁▁▁▁▁▁▁
wandb:         val_rouge2_recall_epoch ▁
wandb:          val_rouge2_recall_step ▁▁▁▁▁▁▁▁▁▁▁▁
wandb:       val_rougeL_fmeasure_epoch ▁
wandb:        val_rougeL_fmeasure_step ▃▁▇█▃▅▁▁▁▁▁▁
wandb:      val_rougeL_precision_epoch ▁
wandb:       val_rougeL_precision_step ▄▁▇▆▃█▁▁▁▁▁▁
wandb:         val_rougeL_recall_epoch ▁
wandb:          val_rougeL_recall_step ▂▁▅█▂▃▁▁▁▁▁▁
wandb:    val_rougeLsum_fmeasure_epoch ▁
wandb:     val_rougeLsum_fmeasure_step ▂▁▅█▃▄▁▁▁▁▁▁
wandb:   val_rougeLsum_precision_epoch ▁
wandb:    val_rougeLsum_precision_step ▃▁▆▆▃█▁▁▁▁▁▁
wandb:      val_rougeLsum_recall_epoch ▁
wandb:       val_rougeLsum_recall_step ▂▁▄█▂▃▁▁▁▁▁▁
wandb: 
wandb: Run summary:
wandb:                           epoch 0
wandb:                train_loss_epoch 2.29987
wandb:     train_rouge1_fmeasure_epoch 0.01015
wandb:    train_rouge1_precision_epoch 0.01305
wandb:       train_rouge1_recall_epoch 0.02602
wandb:     train_rouge2_fmeasure_epoch 0.0
wandb:    train_rouge2_precision_epoch 0.0
wandb:       train_rouge2_recall_epoch 0.0
wandb:     train_rougeL_fmeasure_epoch 0.00923
wandb:    train_rougeL_precision_epoch 0.0117
wandb:       train_rougeL_recall_epoch 0.02379
wandb:  train_rougeLsum_fmeasure_epoch 0.00992
wandb: train_rougeLsum_precision_epoch 0.01263
wandb:    train_rougeLsum_recall_epoch 0.02581
wandb:             trainer/global_step 26
wandb:                  val_loss_epoch 1.35165
wandb:                   val_loss_step 6.06906
wandb:       val_rouge1_fmeasure_epoch 0.01442
wandb:        val_rouge1_fmeasure_step 0.0
wandb:      val_rouge1_precision_epoch 0.02607
wandb:       val_rouge1_precision_step 0.0
wandb:         val_rouge1_recall_epoch 0.01127
wandb:          val_rouge1_recall_step 0.0
wandb:       val_rouge2_fmeasure_epoch 0.0
wandb:        val_rouge2_fmeasure_step 0.0
wandb:      val_rouge2_precision_epoch 0.0
wandb:       val_rouge2_precision_step 0.0
wandb:         val_rouge2_recall_epoch 0.0
wandb:          val_rouge2_recall_step 0.0
wandb:       val_rougeL_fmeasure_epoch 0.01289
wandb:        val_rougeL_fmeasure_step 0.0
wandb:      val_rougeL_precision_epoch 0.02329
wandb:       val_rougeL_precision_step 0.0
wandb:         val_rougeL_recall_epoch 0.01003
wandb:          val_rougeL_recall_step 0.0
wandb:    val_rougeLsum_fmeasure_epoch 0.01442
wandb:     val_rougeLsum_fmeasure_step 0.0
wandb:   val_rougeLsum_precision_epoch 0.02607
wandb:    val_rougeLsum_precision_step 0.0
wandb:      val_rougeLsum_recall_epoch 0.01127
wandb:       val_rougeLsum_recall_step 0.0
wandb: 
wandb: 🚀 View run usual-sweep-1 at: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/rxx2sygy
wandb: ⭐️ View project at: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)
wandb: Find logs at: ./wandb/run-20240806_134906-rxx2sygy/logs
wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information.
wandb: Agent Starting Run: rwwzlqym with config:
wandb: 	accumulate_grad_batches: 1
wandb: 	epochs: 1
wandb: 	gradient_clip_val: 0.167332531520484
wandb: 	init_lora_weights: pissa_niter_16
wandb: 	lora_alpha: 32
wandb: 	lora_dropout: 0.09360935034869836
wandb: 	lora_rank: 8
wandb: 	lr: 0.0004243323255909761
wandb: 	model_name: MLP-KTLim/llama-3-Korean-Bllossom-8B
wandb: WARNING Ignored wandb.init() arg project when running a sweep.
wandb: Tracking run with wandb version 0.17.5
wandb: Run data is saved locally in /user/jonathan/wandb/run-20240806_135122-rwwzlqym
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run peach-sweep-2
wandb: ⭐️ View project at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: 🧹 View sweep at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/sweeps/4ik6ex9z
wandb: 🚀 View run at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/rwwzlqym
Unused kwargs: ['bnb_8bit_quant_type', 'bnb_8bit_compute_dtype']. These kwargs are not used in <class 'transformers.utils.quantization_config.BitsAndBytesConfig'>.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Repo card metadata block was not found. Setting CardData to empty.


Map:   0%|          | 0/960 [00:00<?, ? examples/s]Asking to truncate to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no truncation.

Map: 100%|██████████| 960/960 [00:00<00:00, 7297.63 examples/s]
Map: 100%|██████████| 960/960 [00:00<00:00, 6496.33 examples/s]
GPU available: True (cuda), used: True
TPU available: False, using: 0 TPU cores
HPU available: False, using: 0 HPUs
initializing deepspeed distributed: GLOBAL_RANK: 0, MEMBER: 1/1
Enabling DeepSpeed BF16. Model parameters and inputs will be cast to `bfloat16`.
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]
[2024-08-06 13:54:29,819] [WARNING] [engine.py:1179:_do_optimizer_sanity_check] **** You are using ZeRO with an untested optimizer, proceed with caution *****

  | Name  | Type                 | Params | Mode 
-------------------------------------------------------
0 | model | PeftModelForCausalLM | 1.5 B  | train
-------------------------------------------------------
1.1 M     Trainable params
1.5 B     Non-trainable params
1.5 B     Total params
6,183.574 Total estimated model params size (MB)

Sanity Checking: |          | 0/? [00:00<?, ?it/s]
Sanity Checking:   0%|          | 0/2 [00:00<?, ?it/s]
Sanity Checking DataLoader 0:   0%|          | 0/2 [00:00<?, ?it/s]
Sanity Checking DataLoader 0: 100%|██████████| 2/2 [00:00<00:00,  3.57it/s]
                                                                           

Training: |          | 0/? [00:00<?, ?it/s]
Training:   0%|          | 0/192 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/192 [00:00<?, ?it/s] 
Epoch 0:   3%|▎         | 5/192 [00:01<01:12,  2.58it/s]
Epoch 0:   3%|▎         | 5/192 [00:01<01:12,  2.58it/s, v_num=ym_1, train_loss_step=10.50, train_rouge1_fmeasure_step=0.00277, train_rouge1_precision_step=0.0014, train_rouge1_recall_step=0.167, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.00277, train_rougeL_precision_step=0.0014, train_rougeL_recall_step=0.167, train_rougeLsum_fmeasure_step=0.00277, train_rougeLsum_precision_step=0.0014, train_rougeLsum_recall_step=0.167]
Epoch 0:   5%|▌         | 10/192 [00:03<01:05,  2.77it/s, v_num=ym_1, train_loss_step=10.50, train_rouge1_fmeasure_step=0.00277, train_rouge1_precision_step=0.0014, train_rouge1_recall_step=0.167, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.00277, train_rougeL_precision_step=0.0014, train_rougeL_recall_step=0.167, train_rougeLsum_fmeasure_step=0.00277, train_rougeLsum_precision_step=0.0014, train_rougeLsum_recall_step=0.167]
Epoch 0:   5%|▌         | 10/192 [00:03<01:05,  2.77it/s, v_num=ym_1, train_loss_step=8.880, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]         
Epoch 0:   8%|▊         | 15/192 [00:05<01:01,  2.87it/s, v_num=ym_1, train_loss_step=8.880, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:   8%|▊         | 15/192 [00:05<01:01,  2.87it/s, v_num=ym_1, train_loss_step=3.280, train_rouge1_fmeasure_step=0.00959, train_rouge1_precision_step=0.00506, train_rouge1_recall_step=0.0909, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.00959, train_rougeL_precision_step=0.00506, train_rougeL_recall_step=0.0909, train_rougeLsum_fmeasure_step=0.00959, train_rougeLsum_precision_step=0.00506, train_rougeLsum_recall_step=0.0909]
Epoch 0:  10%|█         | 20/192 [00:06<00:59,  2.91it/s, v_num=ym_1, train_loss_step=3.280, train_rouge1_fmeasure_step=0.00959, train_rouge1_precision_step=0.00506, train_rouge1_recall_step=0.0909, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.00959, train_rougeL_precision_step=0.00506, train_rougeL_recall_step=0.0909, train_rougeLsum_fmeasure_step=0.00959, train_rougeLsum_precision_step=0.00506, train_rougeLsum_recall_step=0.0909]
Epoch 0:  10%|█         | 20/192 [00:06<00:59,  2.91it/s, v_num=ym_1, train_loss_step=2.130, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]               
Epoch 0:  13%|█▎        | 25/192 [00:08<00:56,  2.95it/s, v_num=ym_1, train_loss_step=2.130, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  13%|█▎        | 25/192 [00:08<00:56,  2.95it/s, v_num=ym_1, train_loss_step=0.495, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  16%|█▌        | 30/192 [00:10<00:54,  2.97it/s, v_num=ym_1, train_loss_step=0.495, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  16%|█▌        | 30/192 [00:10<00:54,  2.97it/s, v_num=ym_1, train_loss_step=0.216, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  18%|█▊        | 35/192 [00:11<00:52,  2.99it/s, v_num=ym_1, train_loss_step=0.216, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  18%|█▊        | 35/192 [00:11<00:52,  2.99it/s, v_num=ym_1, train_loss_step=1.370, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  21%|██        | 40/192 [00:13<00:50,  3.01it/s, v_num=ym_1, train_loss_step=1.370, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  21%|██        | 40/192 [00:13<00:50,  3.01it/s, v_num=ym_1, train_loss_step=0.390, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  23%|██▎       | 45/192 [00:14<00:48,  3.02it/s, v_num=ym_1, train_loss_step=0.390, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  23%|██▎       | 45/192 [00:14<00:48,  3.02it/s, v_num=ym_1, train_loss_step=0.245, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  26%|██▌       | 50/192 [00:16<00:46,  3.03it/s, v_num=ym_1, train_loss_step=0.245, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  26%|██▌       | 50/192 [00:16<00:46,  3.03it/s, v_num=ym_1, train_loss_step=0.512, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  29%|██▊       | 55/192 [00:18<00:45,  3.04it/s, v_num=ym_1, train_loss_step=0.512, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  29%|██▊       | 55/192 [00:18<00:45,  3.04it/s, v_num=ym_1, train_loss_step=0.258, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  31%|███▏      | 60/192 [00:19<00:43,  3.04it/s, v_num=ym_1, train_loss_step=0.258, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  31%|███▏      | 60/192 [00:19<00:43,  3.04it/s, v_num=ym_1, train_loss_step=0.144, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  34%|███▍      | 65/192 [00:21<00:41,  3.05it/s, v_num=ym_1, train_loss_step=0.144, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  34%|███▍      | 65/192 [00:21<00:41,  3.05it/s, v_num=ym_1, train_loss_step=0.231, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  36%|███▋      | 70/192 [00:22<00:39,  3.05it/s, v_num=ym_1, train_loss_step=0.231, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  36%|███▋      | 70/192 [00:22<00:39,  3.05it/s, v_num=ym_1, train_loss_step=0.0623, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  39%|███▉      | 75/192 [00:24<00:38,  3.06it/s, v_num=ym_1, train_loss_step=0.0623, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  39%|███▉      | 75/192 [00:24<00:38,  3.06it/s, v_num=ym_1, train_loss_step=1.880, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000] 
Epoch 0:  42%|████▏     | 80/192 [00:26<00:36,  3.06it/s, v_num=ym_1, train_loss_step=1.880, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  42%|████▏     | 80/192 [00:26<00:36,  3.06it/s, v_num=ym_1, train_loss_step=0.791, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  44%|████▍     | 85/192 [00:27<00:34,  3.06it/s, v_num=ym_1, train_loss_step=0.791, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  44%|████▍     | 85/192 [00:27<00:34,  3.06it/s, v_num=ym_1, train_loss_step=0.548, train_rouge1_fmeasure_step=0.0351, train_rouge1_precision_step=0.040, train_rouge1_recall_step=0.0312, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0351, train_rougeL_precision_step=0.040, train_rougeL_recall_step=0.0312, train_rougeLsum_fmeasure_step=0.0351, train_rougeLsum_precision_step=0.040, train_rougeLsum_recall_step=0.0312]
Epoch 0:  47%|████▋     | 90/192 [00:29<00:33,  3.07it/s, v_num=ym_1, train_loss_step=0.548, train_rouge1_fmeasure_step=0.0351, train_rouge1_precision_step=0.040, train_rouge1_recall_step=0.0312, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0351, train_rougeL_precision_step=0.040, train_rougeL_recall_step=0.0312, train_rougeLsum_fmeasure_step=0.0351, train_rougeLsum_precision_step=0.040, train_rougeLsum_recall_step=0.0312]
Epoch 0:  47%|████▋     | 90/192 [00:29<00:33,  3.07it/s, v_num=ym_1, train_loss_step=1.660, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]      
Epoch 0:  49%|████▉     | 95/192 [00:30<00:31,  3.07it/s, v_num=ym_1, train_loss_step=1.660, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  49%|████▉     | 95/192 [00:30<00:31,  3.07it/s, v_num=ym_1, train_loss_step=0.176, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  52%|█████▏    | 100/192 [00:32<00:29,  3.07it/s, v_num=ym_1, train_loss_step=0.176, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  52%|█████▏    | 100/192 [00:32<00:29,  3.07it/s, v_num=ym_1, train_loss_step=0.229, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  55%|█████▍    | 105/192 [00:34<00:28,  3.07it/s, v_num=ym_1, train_loss_step=0.229, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  55%|█████▍    | 105/192 [00:34<00:28,  3.07it/s, v_num=ym_1, train_loss_step=0.0995, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  57%|█████▋    | 110/192 [00:35<00:26,  3.07it/s, v_num=ym_1, train_loss_step=0.0995, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  57%|█████▋    | 110/192 [00:35<00:26,  3.07it/s, v_num=ym_1, train_loss_step=0.092, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000] 
Epoch 0:  60%|█████▉    | 115/192 [00:37<00:25,  3.08it/s, v_num=ym_1, train_loss_step=0.092, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  60%|█████▉    | 115/192 [00:37<00:25,  3.08it/s, v_num=ym_1, train_loss_step=1.250, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  62%|██████▎   | 120/192 [00:38<00:23,  3.08it/s, v_num=ym_1, train_loss_step=1.250, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  62%|██████▎   | 120/192 [00:38<00:23,  3.08it/s, v_num=ym_1, train_loss_step=0.134, train_rouge1_fmeasure_step=0.100, train_rouge1_precision_step=0.200, train_rouge1_recall_step=0.0667, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.100, train_rougeL_precision_step=0.200, train_rougeL_recall_step=0.0667, train_rougeLsum_fmeasure_step=0.100, train_rougeLsum_precision_step=0.200, train_rougeLsum_recall_step=0.0667]
Epoch 0:  65%|██████▌   | 125/192 [00:40<00:21,  3.08it/s, v_num=ym_1, train_loss_step=0.134, train_rouge1_fmeasure_step=0.100, train_rouge1_precision_step=0.200, train_rouge1_recall_step=0.0667, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.100, train_rougeL_precision_step=0.200, train_rougeL_recall_step=0.0667, train_rougeLsum_fmeasure_step=0.100, train_rougeLsum_precision_step=0.200, train_rougeLsum_recall_step=0.0667]
Epoch 0:  65%|██████▌   | 125/192 [00:40<00:21,  3.08it/s, v_num=ym_1, train_loss_step=0.103, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]   
Epoch 0:  68%|██████▊   | 130/192 [00:42<00:20,  3.08it/s, v_num=ym_1, train_loss_step=0.103, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  68%|██████▊   | 130/192 [00:42<00:20,  3.08it/s, v_num=ym_1, train_loss_step=1.170, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  70%|███████   | 135/192 [00:43<00:18,  3.08it/s, v_num=ym_1, train_loss_step=1.170, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  70%|███████   | 135/192 [00:43<00:18,  3.08it/s, v_num=ym_1, train_loss_step=0.502, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  73%|███████▎  | 140/192 [00:45<00:16,  3.08it/s, v_num=ym_1, train_loss_step=0.502, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  73%|███████▎  | 140/192 [00:45<00:16,  3.08it/s, v_num=ym_1, train_loss_step=1.120, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  76%|███████▌  | 145/192 [00:47<00:15,  3.08it/s, v_num=ym_1, train_loss_step=1.120, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  76%|███████▌  | 145/192 [00:47<00:15,  3.08it/s, v_num=ym_1, train_loss_step=0.0634, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  78%|███████▊  | 150/192 [00:48<00:13,  3.09it/s, v_num=ym_1, train_loss_step=0.0634, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  78%|███████▊  | 150/192 [00:48<00:13,  3.09it/s, v_num=ym_1, train_loss_step=0.492, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000] 
Epoch 0:  81%|████████  | 155/192 [00:50<00:11,  3.09it/s, v_num=ym_1, train_loss_step=0.492, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  81%|████████  | 155/192 [00:50<00:11,  3.09it/s, v_num=ym_1, train_loss_step=0.550, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  83%|████████▎ | 160/192 [00:51<00:10,  3.09it/s, v_num=ym_1, train_loss_step=0.550, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  83%|████████▎ | 160/192 [00:51<00:10,  3.09it/s, v_num=ym_1, train_loss_step=0.173, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  86%|████████▌ | 165/192 [00:53<00:08,  3.09it/s, v_num=ym_1, train_loss_step=0.173, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  86%|████████▌ | 165/192 [00:53<00:08,  3.09it/s, v_num=ym_1, train_loss_step=0.591, train_rouge1_fmeasure_step=0.400, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.500, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.400, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.500, train_rougeLsum_fmeasure_step=0.400, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.500]
Epoch 0:  89%|████████▊ | 170/192 [00:55<00:07,  3.09it/s, v_num=ym_1, train_loss_step=0.591, train_rouge1_fmeasure_step=0.400, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.500, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.400, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.500, train_rougeLsum_fmeasure_step=0.400, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.500]
Epoch 0:  89%|████████▊ | 170/192 [00:55<00:07,  3.09it/s, v_num=ym_1, train_loss_step=0.140, train_rouge1_fmeasure_step=0.286, train_rouge1_precision_step=0.167, train_rouge1_recall_step=1.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.286, train_rougeL_precision_step=0.167, train_rougeL_recall_step=1.000, train_rougeLsum_fmeasure_step=0.286, train_rougeLsum_precision_step=0.167, train_rougeLsum_recall_step=1.000]
Epoch 0:  91%|█████████ | 175/192 [00:56<00:05,  3.09it/s, v_num=ym_1, train_loss_step=0.140, train_rouge1_fmeasure_step=0.286, train_rouge1_precision_step=0.167, train_rouge1_recall_step=1.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.286, train_rougeL_precision_step=0.167, train_rougeL_recall_step=1.000, train_rougeLsum_fmeasure_step=0.286, train_rougeLsum_precision_step=0.167, train_rougeLsum_recall_step=1.000]
Epoch 0:  91%|█████████ | 175/192 [00:56<00:05,  3.09it/s, v_num=ym_1, train_loss_step=0.157, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  94%|█████████▍| 180/192 [00:58<00:03,  3.09it/s, v_num=ym_1, train_loss_step=0.157, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  94%|█████████▍| 180/192 [00:58<00:03,  3.09it/s, v_num=ym_1, train_loss_step=0.141, train_rouge1_fmeasure_step=0.500, train_rouge1_precision_step=0.333, train_rouge1_recall_step=1.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.500, train_rougeL_precision_step=0.333, train_rougeL_recall_step=1.000, train_rougeLsum_fmeasure_step=0.500, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=1.000]
Epoch 0:  96%|█████████▋| 185/192 [00:59<00:02,  3.09it/s, v_num=ym_1, train_loss_step=0.141, train_rouge1_fmeasure_step=0.500, train_rouge1_precision_step=0.333, train_rouge1_recall_step=1.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.500, train_rougeL_precision_step=0.333, train_rougeL_recall_step=1.000, train_rougeLsum_fmeasure_step=0.500, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=1.000]
Epoch 0:  96%|█████████▋| 185/192 [00:59<00:02,  3.09it/s, v_num=ym_1, train_loss_step=2.820, train_rouge1_fmeasure_step=0.286, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.250, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.286, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.250, train_rougeLsum_fmeasure_step=0.286, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.250]
Epoch 0:  99%|█████████▉| 190/192 [01:01<00:00,  3.09it/s, v_num=ym_1, train_loss_step=2.820, train_rouge1_fmeasure_step=0.286, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.250, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.286, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.250, train_rougeLsum_fmeasure_step=0.286, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.250]
Epoch 0:  99%|█████████▉| 190/192 [01:01<00:00,  3.09it/s, v_num=ym_1, train_loss_step=0.229, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0: 100%|██████████| 192/192 [01:02<00:00,  3.09it/s, v_num=ym_1, train_loss_step=0.229, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0: 100%|██████████| 192/192 [01:02<00:00,  3.09it/s, v_num=ym_1, train_loss_step=0.185, train_rouge1_fmeasure_step=0.500, train_rouge1_precision_step=0.333, train_rouge1_recall_step=1.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.500, train_rougeL_precision_step=0.333, train_rougeL_recall_step=1.000, train_rougeLsum_fmeasure_step=0.500, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=1.000]

Validation: |          | 0/? [00:00<?, ?it/s]

Validation:   0%|          | 0/12 [00:00<?, ?it/s]

Validation DataLoader 0:   0%|          | 0/12 [00:00<?, ?it/s]

Validation DataLoader 0:  42%|████▏     | 5/12 [00:00<00:01,  5.30it/s]

Validation DataLoader 0:  83%|████████▎ | 10/12 [00:01<00:00,  5.26it/s]

Validation DataLoader 0: 100%|██████████| 12/12 [00:02<00:00,  5.26it/s]

                                                                        
Epoch 0: 100%|██████████| 192/192 [01:04<00:00,  2.98it/s, v_num=ym_1, train_loss_step=0.185, train_rouge1_fmeasure_step=0.500, train_rouge1_precision_step=0.333, train_rouge1_recall_step=1.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.500, train_rougeL_precision_step=0.333, train_rougeL_recall_step=1.000, train_rougeLsum_fmeasure_step=0.500, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=1.000, val_loss_step=2.200, val_rouge1_fmeasure_step=0.321, val_rouge1_precision_step=0.300, val_rouge1_recall_step=0.389, val_rouge2_fmeasure_step=0.000, val_rouge2_precision_step=0.000, val_rouge2_recall_step=0.000, val_rougeL_fmeasure_step=0.321, val_rougeL_precision_step=0.300, val_rougeL_recall_step=0.389, val_rougeLsum_fmeasure_step=0.321, val_rougeLsum_precision_step=0.300, val_rougeLsum_recall_step=0.389, val_loss_epoch=0.531, val_rouge1_fmeasure_epoch=0.200, val_rouge1_precision_epoch=0.232, val_rouge1_recall_epoch=0.359, val_rouge2_fmeasure_epoch=0.000, val_rouge2_precision_epoch=0.000, val_rouge2_recall_epoch=0.000, val_rougeL_fmeasure_epoch=0.200, val_rougeL_precision_epoch=0.232, val_rougeL_recall_epoch=0.359, val_rougeLsum_fmeasure_epoch=0.200, val_rougeLsum_precision_epoch=0.232, val_rougeLsum_recall_epoch=0.359]
Epoch 0: 100%|██████████| 192/192 [01:04<00:00,  2.98it/s, v_num=ym_1, train_loss_step=0.185, train_rouge1_fmeasure_step=0.500, train_rouge1_precision_step=0.333, train_rouge1_recall_step=1.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.500, train_rougeL_precision_step=0.333, train_rougeL_recall_step=1.000, train_rougeLsum_fmeasure_step=0.500, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=1.000, val_loss_step=2.200, val_rouge1_fmeasure_step=0.321, val_rouge1_precision_step=0.300, val_rouge1_recall_step=0.389, val_rouge2_fmeasure_step=0.000, val_rouge2_precision_step=0.000, val_rouge2_recall_step=0.000, val_rougeL_fmeasure_step=0.321, val_rougeL_precision_step=0.300, val_rougeL_recall_step=0.389, val_rougeLsum_fmeasure_step=0.321, val_rougeLsum_precision_step=0.300, val_rougeLsum_recall_step=0.389, val_loss_epoch=0.531, val_rouge1_fmeasure_epoch=0.200, val_rouge1_precision_epoch=0.232, val_rouge1_recall_epoch=0.359, val_rouge2_fmeasure_epoch=0.000, val_rouge2_precision_epoch=0.000, val_rouge2_recall_epoch=0.000, val_rougeL_fmeasure_epoch=0.200, val_rougeL_precision_epoch=0.232, val_rougeL_recall_epoch=0.359, val_rougeLsum_fmeasure_epoch=0.200, val_rougeLsum_precision_epoch=0.232, val_rougeLsum_recall_epoch=0.359, train_loss_epoch=1.190, train_rouge1_fmeasure_epoch=0.0338, train_rouge1_precision_epoch=0.037, train_rouge1_recall_epoch=0.0593, train_rouge2_fmeasure_epoch=2.76e-5, train_rouge2_precision_epoch=1.47e-5, train_rouge2_recall_epoch=0.000223, train_rougeL_fmeasure_epoch=0.0337, train_rougeL_precision_epoch=0.0369, train_rougeL_recall_epoch=0.0589, train_rougeLsum_fmeasure_epoch=0.0338, train_rougeLsum_precision_epoch=0.037, train_rougeLsum_recall_epoch=0.0593]`Trainer.fit` stopped: `max_epochs=1` reached.

Epoch 0: 100%|██████████| 192/192 [01:29<00:00,  2.15it/s, v_num=ym_1, train_loss_step=0.185, train_rouge1_fmeasure_step=0.500, train_rouge1_precision_step=0.333, train_rouge1_recall_step=1.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.500, train_rougeL_precision_step=0.333, train_rougeL_recall_step=1.000, train_rougeLsum_fmeasure_step=0.500, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=1.000, val_loss_step=2.200, val_rouge1_fmeasure_step=0.321, val_rouge1_precision_step=0.300, val_rouge1_recall_step=0.389, val_rouge2_fmeasure_step=0.000, val_rouge2_precision_step=0.000, val_rouge2_recall_step=0.000, val_rougeL_fmeasure_step=0.321, val_rougeL_precision_step=0.300, val_rougeL_recall_step=0.389, val_rougeLsum_fmeasure_step=0.321, val_rougeLsum_precision_step=0.300, val_rougeLsum_recall_step=0.389, val_loss_epoch=0.531, val_rouge1_fmeasure_epoch=0.200, val_rouge1_precision_epoch=0.232, val_rouge1_recall_epoch=0.359, val_rouge2_fmeasure_epoch=0.000, val_rouge2_precision_epoch=0.000, val_rouge2_recall_epoch=0.000, val_rougeL_fmeasure_epoch=0.200, val_rougeL_precision_epoch=0.232, val_rougeL_recall_epoch=0.359, val_rougeLsum_fmeasure_epoch=0.200, val_rougeLsum_precision_epoch=0.232, val_rougeLsum_recall_epoch=0.359, train_loss_epoch=1.190, train_rouge1_fmeasure_epoch=0.0338, train_rouge1_precision_epoch=0.037, train_rouge1_recall_epoch=0.0593, train_rouge2_fmeasure_epoch=2.76e-5, train_rouge2_precision_epoch=1.47e-5, train_rouge2_recall_epoch=0.000223, train_rougeL_fmeasure_epoch=0.0337, train_rougeL_precision_epoch=0.0369, train_rougeL_recall_epoch=0.0589, train_rougeLsum_fmeasure_epoch=0.0338, train_rougeLsum_precision_epoch=0.037, train_rougeLsum_recall_epoch=0.0593]wandb: - 0.014 MB of 0.014 MB uploaded
wandb: \ 0.014 MB of 0.024 MB uploaded
wandb: | 0.014 MB of 0.025 MB uploaded
wandb: / 0.025 MB of 0.025 MB uploaded
wandb: - 0.025 MB of 0.025 MB uploaded
wandb: \ 0.025 MB of 0.025 MB uploaded
wandb: | 0.025 MB of 0.025 MB uploaded
wandb:                                                                                
wandb: 
wandb: Run history:
wandb:                           epoch ▁▁▁▁▁
wandb:                    lr-PagedLion ▆█▁
wandb:                train_loss_epoch ▁
wandb:                 train_loss_step █▁█
wandb:     train_rouge1_fmeasure_epoch ▁
wandb:      train_rouge1_fmeasure_step ▁▁▁
wandb:    train_rouge1_precision_epoch ▁
wandb:     train_rouge1_precision_step ▁▁▁
wandb:       train_rouge1_recall_epoch ▁
wandb:        train_rouge1_recall_step ▁▁▁
wandb:     train_rouge2_fmeasure_epoch ▁
wandb:      train_rouge2_fmeasure_step ▁▁▁
wandb:    train_rouge2_precision_epoch ▁
wandb:     train_rouge2_precision_step ▁▁▁
wandb:       train_rouge2_recall_epoch ▁
wandb:        train_rouge2_recall_step ▁▁▁
wandb:     train_rougeL_fmeasure_epoch ▁
wandb:      train_rougeL_fmeasure_step ▁▁▁
wandb:    train_rougeL_precision_epoch ▁
wandb:     train_rougeL_precision_step ▁▁▁
wandb:       train_rougeL_recall_epoch ▁
wandb:        train_rougeL_recall_step ▁▁▁
wandb:  train_rougeLsum_fmeasure_epoch ▁
wandb:   train_rougeLsum_fmeasure_step ▁▁▁
wandb: train_rougeLsum_precision_epoch ▁
wandb:  train_rougeLsum_precision_step ▁▁▁
wandb:    train_rougeLsum_recall_epoch ▁
wandb:     train_rougeLsum_recall_step ▁▁▁
wandb:             trainer/global_step ▃▃▅▅▆▆▁▁▁▁▁▁▁▁▁▁▁▁██
wandb:                  val_loss_epoch ▁
wandb:                   val_loss_step ▂▁▁▁▁▅▃▁▂▁▂█
wandb:       val_rouge1_fmeasure_epoch ▁
wandb:        val_rouge1_fmeasure_step ▄▆▃▃▃▁▆█▆▇▇█
wandb:      val_rouge1_precision_epoch ▁
wandb:       val_rouge1_precision_step ▅▅▅▅▅▅▂▂▁▂▂█
wandb:         val_rouge1_recall_epoch ▁
wandb:          val_rouge1_recall_step ▂▃▁▁▁▁▅█▄▆▆▄
wandb:       val_rouge2_fmeasure_epoch ▁
wandb:        val_rouge2_fmeasure_step ▁▁▁▁▁▁▁▁▁▁▁▁
wandb:      val_rouge2_precision_epoch ▁
wandb:       val_rouge2_precision_step ▁▁▁▁▁▁▁▁▁▁▁▁
wandb:         val_rouge2_recall_epoch ▁
wandb:          val_rouge2_recall_step ▁▁▁▁▁▁▁▁▁▁▁▁
wandb:       val_rougeL_fmeasure_epoch ▁
wandb:        val_rougeL_fmeasure_step ▄▆▃▃▃▁▆█▆▇▇█
wandb:      val_rougeL_precision_epoch ▁
wandb:       val_rougeL_precision_step ▅▅▅▅▅▅▂▂▁▂▂█
wandb:         val_rougeL_recall_epoch ▁
wandb:          val_rougeL_recall_step ▂▃▁▁▁▁▅█▄▆▆▄
wandb:    val_rougeLsum_fmeasure_epoch ▁
wandb:     val_rougeLsum_fmeasure_step ▄▆▃▃▃▁▆█▆▇▇█
wandb:   val_rougeLsum_precision_epoch ▁
wandb:    val_rougeLsum_precision_step ▅▅▅▅▅▅▂▂▁▂▂█
wandb:      val_rougeLsum_recall_epoch ▁
wandb:       val_rougeLsum_recall_step ▂▃▁▁▁▁▅█▄▆▆▄
wandb: 
wandb: Run summary:
wandb:                           epoch 0
wandb:                    lr-PagedLion 1e-05
wandb:                train_loss_epoch 1.19016
wandb:                 train_loss_step 0.49164
wandb:     train_rouge1_fmeasure_epoch 0.03375
wandb:      train_rouge1_fmeasure_step 0.0
wandb:    train_rouge1_precision_epoch 0.03697
wandb:     train_rouge1_precision_step 0.0
wandb:       train_rouge1_recall_epoch 0.05931
wandb:        train_rouge1_recall_step 0.0
wandb:     train_rouge2_fmeasure_epoch 3e-05
wandb:      train_rouge2_fmeasure_step 0.0
wandb:    train_rouge2_precision_epoch 1e-05
wandb:     train_rouge2_precision_step 0.0
wandb:       train_rouge2_recall_epoch 0.00022
wandb:        train_rouge2_recall_step 0.0
wandb:     train_rougeL_fmeasure_epoch 0.03368
wandb:      train_rougeL_fmeasure_step 0.0
wandb:    train_rougeL_precision_epoch 0.03693
wandb:     train_rougeL_precision_step 0.0
wandb:       train_rougeL_recall_epoch 0.05894
wandb:        train_rougeL_recall_step 0.0
wandb:  train_rougeLsum_fmeasure_epoch 0.03375
wandb:   train_rougeLsum_fmeasure_step 0.0
wandb: train_rougeLsum_precision_epoch 0.03697
wandb:  train_rougeLsum_precision_step 0.0
wandb:    train_rougeLsum_recall_epoch 0.05931
wandb:     train_rougeLsum_recall_step 0.0
wandb:             trainer/global_step 191
wandb:                  val_loss_epoch 0.5311
wandb:                   val_loss_step 2.19732
wandb:       val_rouge1_fmeasure_epoch 0.20039
wandb:        val_rouge1_fmeasure_step 0.32143
wandb:      val_rouge1_precision_epoch 0.23194
wandb:       val_rouge1_precision_step 0.3
wandb:         val_rouge1_recall_epoch 0.35879
wandb:          val_rouge1_recall_step 0.38889
wandb:       val_rouge2_fmeasure_epoch 0.0
wandb:        val_rouge2_fmeasure_step 0.0
wandb:      val_rouge2_precision_epoch 0.0
wandb:       val_rouge2_precision_step 0.0
wandb:         val_rouge2_recall_epoch 0.0
wandb:          val_rouge2_recall_step 0.0
wandb:       val_rougeL_fmeasure_epoch 0.20039
wandb:        val_rougeL_fmeasure_step 0.32143
wandb:      val_rougeL_precision_epoch 0.23194
wandb:       val_rougeL_precision_step 0.3
wandb:         val_rougeL_recall_epoch 0.35879
wandb:          val_rougeL_recall_step 0.38889
wandb:    val_rougeLsum_fmeasure_epoch 0.20039
wandb:     val_rougeLsum_fmeasure_step 0.32143
wandb:   val_rougeLsum_precision_epoch 0.23194
wandb:    val_rougeLsum_precision_step 0.3
wandb:      val_rougeLsum_recall_epoch 0.35879
wandb:       val_rougeLsum_recall_step 0.38889
wandb: 
wandb: 🚀 View run peach-sweep-2 at: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/rwwzlqym
wandb: ⭐️ View project at: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)
wandb: Find logs at: ./wandb/run-20240806_135122-rwwzlqym/logs
wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information.
wandb: Agent Starting Run: jpmw6qcg with config:
wandb: 	accumulate_grad_batches: 3
wandb: 	epochs: 1
wandb: 	gradient_clip_val: 0.9721876127240872
wandb: 	init_lora_weights: loftq
wandb: 	lora_alpha: 32
wandb: 	lora_dropout: 0.07538488186871073
wandb: 	lora_rank: 16
wandb: 	lr: 0.00017737658879369092
wandb: 	model_name: mistralai/Mistral-Nemo-Instruct-2407
wandb: WARNING Ignored wandb.init() arg project when running a sweep.
wandb: Tracking run with wandb version 0.17.5
wandb: Run data is saved locally in /user/jonathan/wandb/run-20240806_135615-jpmw6qcg
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run dutiful-sweep-3
wandb: ⭐️ View project at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: 🧹 View sweep at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/sweeps/4ik6ex9z
wandb: 🚀 View run at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/jpmw6qcg
Unused kwargs: ['bnb_8bit_quant_type', 'bnb_8bit_compute_dtype']. These kwargs are not used in <class 'transformers.utils.quantization_config.BitsAndBytesConfig'>.
Repo card metadata block was not found. Setting CardData to empty.
WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty.


Map:   0%|          | 0/960 [00:00<?, ? examples/s]
Map:   0%|          | 0/960 [00:00<?, ? examples/s]
wandb: - 0.014 MB of 0.014 MB uploaded
wandb: \ 0.014 MB of 0.014 MB uploaded
wandb: | 0.014 MB of 0.014 MB uploaded
wandb: / 0.015 MB of 0.019 MB uploaded
wandb: - 0.019 MB of 0.019 MB uploaded
wandb: \ 0.019 MB of 0.019 MB uploaded
wandb: | 0.019 MB of 0.019 MB uploaded
wandb:                                                                                
wandb: 🚀 View run dutiful-sweep-3 at: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/jpmw6qcg
wandb: ⭐️ View project at: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)
wandb: Find logs at: ./wandb/run-20240806_135615-jpmw6qcg/logs
wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information.
Run jpmw6qcg errored:
Traceback (most recent call last):
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/wandb/agents/pyagent.py", line 307, in _run_job
    self._function()
  File "/user/jonathan/l_sweep.py", line 50, in l2ray_trainer
    dataset = get_dataset(dataset_name=dataset_path, tokenizer=tokenizer)
  File "/user/jonathan/finetuning_datasets.py", line 40, in get_dataset
    en_dataset = raw_dataset.map(
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/dataset_dict.py", line 869, in map
    {
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/dataset_dict.py", line 870, in <dictcomp>
    k: dataset.map(
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 602, in wrapper
    out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 567, in wrapper
    out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3161, in map
    for rank, done, content in Dataset._map_single(**dataset_kwargs):
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3552, in _map_single
    batch = apply_function_on_filtered_inputs(
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3421, in apply_function_on_filtered_inputs
    processed_inputs = function(*fn_args, *additional_args, **fn_kwargs)
  File "/user/jonathan/finetuning_datafunctions.py", line 65, in preprocess_function
    templated_text, labels = formatting(sample=sample,
  File "/user/jonathan/finetuning_datafunctions.py", line 38, in formatting
    bot_message = tokenizer.apply_chat_template(conversation=label_template,
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1855, in apply_chat_template
    rendered_chat = compiled_template.render(
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/environment.py", line 1304, in render
    self.environment.handle_exception()
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/environment.py", line 939, in handle_exception
    raise rewrite_traceback_stack(source=source)
  File "<template>", line 14, in top-level template code
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/sandbox.py", line 394, in call
    return __context.call(__obj, *args, **kwargs)
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1899, in raise_exception
    raise TemplateError(message)
jinja2.exceptions.TemplateError: After the optional system message, conversation roles must alternate user/assistant/user/assistant/...

wandb: ERROR Run jpmw6qcg errored:
wandb: ERROR Traceback (most recent call last):
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/wandb/agents/pyagent.py", line 307, in _run_job
wandb: ERROR     self._function()
wandb: ERROR   File "/user/jonathan/l_sweep.py", line 50, in l2ray_trainer
wandb: ERROR     dataset = get_dataset(dataset_name=dataset_path, tokenizer=tokenizer)
wandb: ERROR   File "/user/jonathan/finetuning_datasets.py", line 40, in get_dataset
wandb: ERROR     en_dataset = raw_dataset.map(
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/dataset_dict.py", line 869, in map
wandb: ERROR     {
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/dataset_dict.py", line 870, in <dictcomp>
wandb: ERROR     k: dataset.map(
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 602, in wrapper
wandb: ERROR     out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 567, in wrapper
wandb: ERROR     out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3161, in map
wandb: ERROR     for rank, done, content in Dataset._map_single(**dataset_kwargs):
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3552, in _map_single
wandb: ERROR     batch = apply_function_on_filtered_inputs(
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3421, in apply_function_on_filtered_inputs
wandb: ERROR     processed_inputs = function(*fn_args, *additional_args, **fn_kwargs)
wandb: ERROR   File "/user/jonathan/finetuning_datafunctions.py", line 65, in preprocess_function
wandb: ERROR     templated_text, labels = formatting(sample=sample,
wandb: ERROR   File "/user/jonathan/finetuning_datafunctions.py", line 38, in formatting
wandb: ERROR     bot_message = tokenizer.apply_chat_template(conversation=label_template,
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1855, in apply_chat_template
wandb: ERROR     rendered_chat = compiled_template.render(
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/environment.py", line 1304, in render
wandb: ERROR     self.environment.handle_exception()
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/environment.py", line 939, in handle_exception
wandb: ERROR     raise rewrite_traceback_stack(source=source)
wandb: ERROR   File "<template>", line 14, in top-level template code
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/sandbox.py", line 394, in call
wandb: ERROR     return __context.call(__obj, *args, **kwargs)
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1899, in raise_exception
wandb: ERROR     raise TemplateError(message)
wandb: ERROR jinja2.exceptions.TemplateError: After the optional system message, conversation roles must alternate user/assistant/user/assistant/...
wandb: ERROR 
wandb: Agent Starting Run: dky0jtjo with config:
wandb: 	accumulate_grad_batches: 2
wandb: 	epochs: 1
wandb: 	gradient_clip_val: 0.3061416587717848
wandb: 	init_lora_weights: pissa_niter_16
wandb: 	lora_alpha: 64
wandb: 	lora_dropout: 0.06667523190780655
wandb: 	lora_rank: 4
wandb: 	lr: 0.00043427990527397366
wandb: 	model_name: vilm/vulture-40b
wandb: WARNING Ignored wandb.init() arg project when running a sweep.
wandb: - Waiting for wandb.init()...
wandb: \ Waiting for wandb.init()...
wandb: Tracking run with wandb version 0.17.5
wandb: Run data is saved locally in /user/jonathan/wandb/run-20240806_135652-dky0jtjo
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run divine-sweep-4
wandb: ⭐️ View project at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: 🧹 View sweep at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/sweeps/4ik6ex9z
wandb: 🚀 View run at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/dky0jtjo
Unused kwargs: ['bnb_8bit_quant_type', 'bnb_8bit_compute_dtype']. These kwargs are not used in <class 'transformers.utils.quantization_config.BitsAndBytesConfig'>.
Repo card metadata block was not found. Setting CardData to empty.
WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty.

Map:   0%|          | 0/960 [00:00<?, ? examples/s]No chat template is set for this tokenizer, falling back to a default class-level template. This is very error-prone, because models are often trained with templates different from the class default! Default chat templates are a legacy feature and will be removed in Transformers v4.43, at which point any code depending on them will stop working. We recommend setting a valid chat template before then to ensure that this model continues working without issues.

Map: 100%|██████████| 960/960 [00:00<00:00, 17278.95 examples/s]

Map:   0%|          | 0/120 [00:00<?, ? examples/s]
Map: 100%|██████████| 120/120 [00:00<00:00, 5231.00 examples/s]

Map:   0%|          | 0/121 [00:00<?, ? examples/s]
Map: 100%|██████████| 121/121 [00:00<00:00, 5878.32 examples/s]

Map:   0%|          | 0/960 [00:00<?, ? examples/s]
Map: 100%|██████████| 960/960 [00:00<00:00, 16413.59 examples/s]

Map:   0%|          | 0/120 [00:00<?, ? examples/s]
Map: 100%|██████████| 120/120 [00:00<00:00, 5707.83 examples/s]

Map:   0%|          | 0/121 [00:00<?, ? examples/s]
Map: 100%|██████████| 121/121 [00:00<00:00, 6219.88 examples/s]
GPU available: True (cuda), used: True
TPU available: False, using: 0 TPU cores
HPU available: False, using: 0 HPUs
initializing deepspeed distributed: GLOBAL_RANK: 0, MEMBER: 1/1
Enabling DeepSpeed BF16. Model parameters and inputs will be cast to `bfloat16`.
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]
[2024-08-06 13:59:56,471] [WARNING] [engine.py:1179:_do_optimizer_sanity_check] **** You are using ZeRO with an untested optimizer, proceed with caution *****

  | Name  | Type                 | Params | Mode 
-------------------------------------------------------
0 | model | PeftModelForCausalLM | 1.5 B  | train
-------------------------------------------------------
544 K     Trainable params
1.5 B     Non-trainable params
1.5 B     Total params
6,179.215 Total estimated model params size (MB)

Sanity Checking: |          | 0/? [00:00<?, ?it/s]
Sanity Checking:   0%|          | 0/2 [00:00<?, ?it/s]
Sanity Checking DataLoader 0:   0%|          | 0/2 [00:00<?, ?it/s]
Sanity Checking DataLoader 0: 100%|██████████| 2/2 [00:00<00:00,  3.62it/s]
                                                                           

Training: |          | 0/? [00:00<?, ?it/s]
Training:   0%|          | 0/192 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/192 [00:00<?, ?it/s] 
Epoch 0:   3%|▎         | 5/192 [00:01<01:02,  3.01it/s]
Epoch 0:   3%|▎         | 5/192 [00:01<01:02,  3.01it/s, v_num=jo_1, train_loss_step=4.400, train_rouge1_fmeasure_step=0.00624, train_rouge1_precision_step=0.00314, train_rouge1_recall_step=0.400, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.00468, train_rougeL_precision_step=0.00236, train_rougeL_recall_step=0.300, train_rougeLsum_fmeasure_step=0.00468, train_rougeLsum_precision_step=0.00236, train_rougeLsum_recall_step=0.300]
Epoch 0:   5%|▌         | 10/192 [00:03<01:00,  3.01it/s, v_num=jo_1, train_loss_step=4.400, train_rouge1_fmeasure_step=0.00624, train_rouge1_precision_step=0.00314, train_rouge1_recall_step=0.400, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.00468, train_rougeL_precision_step=0.00236, train_rougeL_recall_step=0.300, train_rougeLsum_fmeasure_step=0.00468, train_rougeLsum_precision_step=0.00236, train_rougeLsum_recall_step=0.300]
Epoch 0:   5%|▌         | 10/192 [00:03<01:00,  3.01it/s, v_num=jo_1, train_loss_step=3.670, train_rouge1_fmeasure_step=0.00506, train_rouge1_precision_step=0.00255, train_rouge1_recall_step=0.333, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.00506, train_rougeL_precision_step=0.00255, train_rougeL_recall_step=0.333, train_rougeLsum_fmeasure_step=0.00253, train_rougeLsum_precision_step=0.00127, train_rougeLsum_recall_step=0.167]
Epoch 0:   8%|▊         | 15/192 [00:04<00:58,  3.04it/s, v_num=jo_1, train_loss_step=3.670, train_rouge1_fmeasure_step=0.00506, train_rouge1_precision_step=0.00255, train_rouge1_recall_step=0.333, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.00506, train_rougeL_precision_step=0.00255, train_rougeL_recall_step=0.333, train_rougeLsum_fmeasure_step=0.00253, train_rougeLsum_precision_step=0.00127, train_rougeLsum_recall_step=0.167]
Epoch 0:   8%|▊         | 15/192 [00:04<00:58,  3.04it/s, v_num=jo_1, train_loss_step=2.200, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]            
Epoch 0:  10%|█         | 20/192 [00:06<00:56,  3.06it/s, v_num=jo_1, train_loss_step=2.200, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  10%|█         | 20/192 [00:06<00:56,  3.06it/s, v_num=jo_1, train_loss_step=1.880, train_rouge1_fmeasure_step=0.0131, train_rouge1_precision_step=0.00719, train_rouge1_recall_step=0.0714, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0131, train_rougeL_precision_step=0.00719, train_rougeL_recall_step=0.0714, train_rougeLsum_fmeasure_step=0.0131, train_rougeLsum_precision_step=0.00719, train_rougeLsum_recall_step=0.0714]
Epoch 0:  13%|█▎        | 25/192 [00:08<00:54,  3.07it/s, v_num=jo_1, train_loss_step=1.880, train_rouge1_fmeasure_step=0.0131, train_rouge1_precision_step=0.00719, train_rouge1_recall_step=0.0714, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0131, train_rougeL_precision_step=0.00719, train_rougeL_recall_step=0.0714, train_rougeLsum_fmeasure_step=0.0131, train_rougeLsum_precision_step=0.00719, train_rougeLsum_recall_step=0.0714]
Epoch 0:  13%|█▎        | 25/192 [00:08<00:54,  3.07it/s, v_num=jo_1, train_loss_step=0.432, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]            
Epoch 0:  16%|█▌        | 30/192 [00:09<00:52,  3.08it/s, v_num=jo_1, train_loss_step=0.432, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  16%|█▌        | 30/192 [00:09<00:52,  3.08it/s, v_num=jo_1, train_loss_step=0.274, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  18%|█▊        | 35/192 [00:11<00:50,  3.09it/s, v_num=jo_1, train_loss_step=0.274, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  18%|█▊        | 35/192 [00:11<00:50,  3.09it/s, v_num=jo_1, train_loss_step=1.270, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  21%|██        | 40/192 [00:12<00:49,  3.09it/s, v_num=jo_1, train_loss_step=1.270, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  21%|██        | 40/192 [00:12<00:49,  3.09it/s, v_num=jo_1, train_loss_step=0.435, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  23%|██▎       | 45/192 [00:14<00:47,  3.10it/s, v_num=jo_1, train_loss_step=0.435, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  23%|██▎       | 45/192 [00:14<00:47,  3.10it/s, v_num=jo_1, train_loss_step=0.691, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  26%|██▌       | 50/192 [00:16<00:45,  3.10it/s, v_num=jo_1, train_loss_step=0.691, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  26%|██▌       | 50/192 [00:16<00:45,  3.10it/s, v_num=jo_1, train_loss_step=1.530, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  29%|██▊       | 55/192 [00:17<00:44,  3.11it/s, v_num=jo_1, train_loss_step=1.530, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  29%|██▊       | 55/192 [00:17<00:44,  3.11it/s, v_num=jo_1, train_loss_step=0.322, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  31%|███▏      | 60/192 [00:19<00:42,  3.11it/s, v_num=jo_1, train_loss_step=0.322, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  31%|███▏      | 60/192 [00:19<00:42,  3.11it/s, v_num=jo_1, train_loss_step=0.193, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  34%|███▍      | 65/192 [00:20<00:40,  3.11it/s, v_num=jo_1, train_loss_step=0.193, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  34%|███▍      | 65/192 [00:20<00:40,  3.11it/s, v_num=jo_1, train_loss_step=0.262, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  36%|███▋      | 70/192 [00:22<00:39,  3.11it/s, v_num=jo_1, train_loss_step=0.262, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  36%|███▋      | 70/192 [00:22<00:39,  3.11it/s, v_num=jo_1, train_loss_step=0.0885, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  39%|███▉      | 75/192 [00:24<00:37,  3.12it/s, v_num=jo_1, train_loss_step=0.0885, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  39%|███▉      | 75/192 [00:24<00:37,  3.12it/s, v_num=jo_1, train_loss_step=4.540, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000] 
Epoch 0:  42%|████▏     | 80/192 [00:25<00:35,  3.12it/s, v_num=jo_1, train_loss_step=4.540, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  42%|████▏     | 80/192 [00:25<00:35,  3.12it/s, v_num=jo_1, train_loss_step=0.826, train_rouge1_fmeasure_step=0.0168, train_rouge1_precision_step=0.200, train_rouge1_recall_step=0.00877, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0168, train_rougeL_precision_step=0.200, train_rougeL_recall_step=0.00877, train_rougeLsum_fmeasure_step=0.0168, train_rougeLsum_precision_step=0.200, train_rougeLsum_recall_step=0.00877]
Epoch 0:  44%|████▍     | 85/192 [00:27<00:34,  3.12it/s, v_num=jo_1, train_loss_step=0.826, train_rouge1_fmeasure_step=0.0168, train_rouge1_precision_step=0.200, train_rouge1_recall_step=0.00877, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0168, train_rougeL_precision_step=0.200, train_rougeL_recall_step=0.00877, train_rougeLsum_fmeasure_step=0.0168, train_rougeLsum_precision_step=0.200, train_rougeLsum_recall_step=0.00877]
Epoch 0:  44%|████▍     | 85/192 [00:27<00:34,  3.12it/s, v_num=jo_1, train_loss_step=0.316, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]         
Epoch 0:  47%|████▋     | 90/192 [00:28<00:32,  3.12it/s, v_num=jo_1, train_loss_step=0.316, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  47%|████▋     | 90/192 [00:28<00:32,  3.12it/s, v_num=jo_1, train_loss_step=3.980, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  49%|████▉     | 95/192 [00:30<00:31,  3.12it/s, v_num=jo_1, train_loss_step=3.980, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  49%|████▉     | 95/192 [00:30<00:31,  3.12it/s, v_num=jo_1, train_loss_step=0.119, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  52%|█████▏    | 100/192 [00:32<00:29,  3.12it/s, v_num=jo_1, train_loss_step=0.119, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  52%|█████▏    | 100/192 [00:32<00:29,  3.12it/s, v_num=jo_1, train_loss_step=0.684, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  55%|█████▍    | 105/192 [00:33<00:27,  3.12it/s, v_num=jo_1, train_loss_step=0.684, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  55%|█████▍    | 105/192 [00:33<00:27,  3.12it/s, v_num=jo_1, train_loss_step=0.134, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  57%|█████▋    | 110/192 [00:35<00:26,  3.12it/s, v_num=jo_1, train_loss_step=0.134, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  57%|█████▋    | 110/192 [00:35<00:26,  3.12it/s, v_num=jo_1, train_loss_step=0.123, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  60%|█████▉    | 115/192 [00:36<00:24,  3.12it/s, v_num=jo_1, train_loss_step=0.123, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  60%|█████▉    | 115/192 [00:36<00:24,  3.12it/s, v_num=jo_1, train_loss_step=3.160, train_rouge1_fmeasure_step=0.111, train_rouge1_precision_step=0.167, train_rouge1_recall_step=0.0833, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.111, train_rougeL_precision_step=0.167, train_rougeL_recall_step=0.0833, train_rougeLsum_fmeasure_step=0.111, train_rougeLsum_precision_step=0.167, train_rougeLsum_recall_step=0.0833]
Epoch 0:  62%|██████▎   | 120/192 [00:38<00:23,  3.12it/s, v_num=jo_1, train_loss_step=3.160, train_rouge1_fmeasure_step=0.111, train_rouge1_precision_step=0.167, train_rouge1_recall_step=0.0833, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.111, train_rougeL_precision_step=0.167, train_rougeL_recall_step=0.0833, train_rougeLsum_fmeasure_step=0.111, train_rougeLsum_precision_step=0.167, train_rougeLsum_recall_step=0.0833]
Epoch 0:  62%|██████▎   | 120/192 [00:38<00:23,  3.12it/s, v_num=jo_1, train_loss_step=0.132, train_rouge1_fmeasure_step=0.087, train_rouge1_precision_step=0.250, train_rouge1_recall_step=0.0526, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.087, train_rougeL_precision_step=0.250, train_rougeL_recall_step=0.0526, train_rougeLsum_fmeasure_step=0.087, train_rougeLsum_precision_step=0.250, train_rougeLsum_recall_step=0.0526]
Epoch 0:  65%|██████▌   | 125/192 [00:40<00:21,  3.12it/s, v_num=jo_1, train_loss_step=0.132, train_rouge1_fmeasure_step=0.087, train_rouge1_precision_step=0.250, train_rouge1_recall_step=0.0526, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.087, train_rougeL_precision_step=0.250, train_rougeL_recall_step=0.0526, train_rougeLsum_fmeasure_step=0.087, train_rougeLsum_precision_step=0.250, train_rougeLsum_recall_step=0.0526]
Epoch 0:  65%|██████▌   | 125/192 [00:40<00:21,  3.12it/s, v_num=jo_1, train_loss_step=0.105, train_rouge1_fmeasure_step=0.125, train_rouge1_precision_step=0.167, train_rouge1_recall_step=0.100, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.125, train_rougeL_precision_step=0.167, train_rougeL_recall_step=0.100, train_rougeLsum_fmeasure_step=0.125, train_rougeLsum_precision_step=0.167, train_rougeLsum_recall_step=0.100]   
Epoch 0:  68%|██████▊   | 130/192 [00:41<00:19,  3.12it/s, v_num=jo_1, train_loss_step=0.105, train_rouge1_fmeasure_step=0.125, train_rouge1_precision_step=0.167, train_rouge1_recall_step=0.100, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.125, train_rougeL_precision_step=0.167, train_rougeL_recall_step=0.100, train_rougeLsum_fmeasure_step=0.125, train_rougeLsum_precision_step=0.167, train_rougeLsum_recall_step=0.100]
Epoch 0:  68%|██████▊   | 130/192 [00:41<00:19,  3.12it/s, v_num=jo_1, train_loss_step=1.050, train_rouge1_fmeasure_step=0.0253, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.0132, train_rouge2_fmeasure_step=0.0128, train_rouge2_precision_step=0.200, train_rouge2_recall_step=0.00662, train_rougeL_fmeasure_step=0.0253, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.0132, train_rougeLsum_fmeasure_step=0.0253, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.0132]
Epoch 0:  70%|███████   | 135/192 [00:43<00:18,  3.13it/s, v_num=jo_1, train_loss_step=1.050, train_rouge1_fmeasure_step=0.0253, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.0132, train_rouge2_fmeasure_step=0.0128, train_rouge2_precision_step=0.200, train_rouge2_recall_step=0.00662, train_rougeL_fmeasure_step=0.0253, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.0132, train_rougeLsum_fmeasure_step=0.0253, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.0132]
Epoch 0:  70%|███████   | 135/192 [00:43<00:18,  3.13it/s, v_num=jo_1, train_loss_step=1.100, train_rouge1_fmeasure_step=0.400, train_rouge1_precision_step=0.600, train_rouge1_recall_step=0.300, train_rouge2_fmeasure_step=0.308, train_rouge2_precision_step=0.500, train_rouge2_recall_step=0.222, train_rougeL_fmeasure_step=0.400, train_rougeL_precision_step=0.600, train_rougeL_recall_step=0.300, train_rougeLsum_fmeasure_step=0.400, train_rougeLsum_precision_step=0.600, train_rougeLsum_recall_step=0.300]         
Epoch 0:  73%|███████▎  | 140/192 [00:44<00:16,  3.13it/s, v_num=jo_1, train_loss_step=1.100, train_rouge1_fmeasure_step=0.400, train_rouge1_precision_step=0.600, train_rouge1_recall_step=0.300, train_rouge2_fmeasure_step=0.308, train_rouge2_precision_step=0.500, train_rouge2_recall_step=0.222, train_rougeL_fmeasure_step=0.400, train_rougeL_precision_step=0.600, train_rougeL_recall_step=0.300, train_rougeLsum_fmeasure_step=0.400, train_rougeLsum_precision_step=0.600, train_rougeLsum_recall_step=0.300]
Epoch 0:  73%|███████▎  | 140/192 [00:44<00:16,  3.13it/s, v_num=jo_1, train_loss_step=2.410, train_rouge1_fmeasure_step=0.333, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.333, train_rouge2_fmeasure_step=0.200, train_rouge2_precision_step=0.200, train_rouge2_recall_step=0.200, train_rougeL_fmeasure_step=0.333, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.333, train_rougeLsum_fmeasure_step=0.333, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.333]
Epoch 0:  76%|███████▌  | 145/192 [00:46<00:15,  3.13it/s, v_num=jo_1, train_loss_step=2.410, train_rouge1_fmeasure_step=0.333, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.333, train_rouge2_fmeasure_step=0.200, train_rouge2_precision_step=0.200, train_rouge2_recall_step=0.200, train_rougeL_fmeasure_step=0.333, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.333, train_rougeLsum_fmeasure_step=0.333, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.333]
Epoch 0:  76%|███████▌  | 145/192 [00:46<00:15,  3.13it/s, v_num=jo_1, train_loss_step=0.0764, train_rouge1_fmeasure_step=0.286, train_rouge1_precision_step=0.400, train_rouge1_recall_step=0.222, train_rouge2_fmeasure_step=0.167, train_rouge2_precision_step=0.250, train_rouge2_recall_step=0.125, train_rougeL_fmeasure_step=0.286, train_rougeL_precision_step=0.400, train_rougeL_recall_step=0.222, train_rougeLsum_fmeasure_step=0.286, train_rougeLsum_precision_step=0.400, train_rougeLsum_recall_step=0.222]
Epoch 0:  78%|███████▊  | 150/192 [00:47<00:13,  3.13it/s, v_num=jo_1, train_loss_step=0.0764, train_rouge1_fmeasure_step=0.286, train_rouge1_precision_step=0.400, train_rouge1_recall_step=0.222, train_rouge2_fmeasure_step=0.167, train_rouge2_precision_step=0.250, train_rouge2_recall_step=0.125, train_rougeL_fmeasure_step=0.286, train_rougeL_precision_step=0.400, train_rougeL_recall_step=0.222, train_rougeLsum_fmeasure_step=0.286, train_rougeLsum_precision_step=0.400, train_rougeLsum_recall_step=0.222]
Epoch 0:  78%|███████▊  | 150/192 [00:47<00:13,  3.13it/s, v_num=jo_1, train_loss_step=1.410, train_rouge1_fmeasure_step=0.111, train_rouge1_precision_step=0.111, train_rouge1_recall_step=0.111, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.111, train_rougeL_precision_step=0.111, train_rougeL_recall_step=0.111, train_rougeLsum_fmeasure_step=0.111, train_rougeLsum_precision_step=0.111, train_rougeLsum_recall_step=0.111] 
Epoch 0:  81%|████████  | 155/192 [00:49<00:11,  3.13it/s, v_num=jo_1, train_loss_step=1.410, train_rouge1_fmeasure_step=0.111, train_rouge1_precision_step=0.111, train_rouge1_recall_step=0.111, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.111, train_rougeL_precision_step=0.111, train_rougeL_recall_step=0.111, train_rougeLsum_fmeasure_step=0.111, train_rougeLsum_precision_step=0.111, train_rougeLsum_recall_step=0.111]
Epoch 0:  81%|████████  | 155/192 [00:49<00:11,  3.13it/s, v_num=jo_1, train_loss_step=0.629, train_rouge1_fmeasure_step=0.667, train_rouge1_precision_step=0.750, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.571, train_rouge2_precision_step=0.667, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.667, train_rougeL_precision_step=0.750, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.667, train_rougeLsum_precision_step=0.750, train_rougeLsum_recall_step=0.600]
Epoch 0:  83%|████████▎ | 160/192 [00:51<00:10,  3.13it/s, v_num=jo_1, train_loss_step=0.629, train_rouge1_fmeasure_step=0.667, train_rouge1_precision_step=0.750, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.571, train_rouge2_precision_step=0.667, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.667, train_rougeL_precision_step=0.750, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.667, train_rougeLsum_precision_step=0.750, train_rougeLsum_recall_step=0.600]
Epoch 0:  83%|████████▎ | 160/192 [00:51<00:10,  3.13it/s, v_num=jo_1, train_loss_step=0.340, train_rouge1_fmeasure_step=0.750, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.667, train_rouge2_precision_step=1.000, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.750, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.750, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.600]
Epoch 0:  86%|████████▌ | 165/192 [00:52<00:08,  3.13it/s, v_num=jo_1, train_loss_step=0.340, train_rouge1_fmeasure_step=0.750, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.667, train_rouge2_precision_step=1.000, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.750, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.750, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.600]
Epoch 0:  86%|████████▌ | 165/192 [00:52<00:08,  3.13it/s, v_num=jo_1, train_loss_step=1.780, train_rouge1_fmeasure_step=0.182, train_rouge1_precision_step=0.200, train_rouge1_recall_step=0.167, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.182, train_rougeL_precision_step=0.200, train_rougeL_recall_step=0.167, train_rougeLsum_fmeasure_step=0.182, train_rougeLsum_precision_step=0.200, train_rougeLsum_recall_step=0.167]
Epoch 0:  89%|████████▊ | 170/192 [00:54<00:07,  3.13it/s, v_num=jo_1, train_loss_step=1.780, train_rouge1_fmeasure_step=0.182, train_rouge1_precision_step=0.200, train_rouge1_recall_step=0.167, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.182, train_rougeL_precision_step=0.200, train_rougeL_recall_step=0.167, train_rougeLsum_fmeasure_step=0.182, train_rougeLsum_precision_step=0.200, train_rougeLsum_recall_step=0.167]
Epoch 0:  89%|████████▊ | 170/192 [00:54<00:07,  3.13it/s, v_num=jo_1, train_loss_step=0.167, train_rouge1_fmeasure_step=0.667, train_rouge1_precision_step=0.750, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.571, train_rouge2_precision_step=0.667, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.667, train_rougeL_precision_step=0.750, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.667, train_rougeLsum_precision_step=0.750, train_rougeLsum_recall_step=0.600]
Epoch 0:  91%|█████████ | 175/192 [00:55<00:05,  3.13it/s, v_num=jo_1, train_loss_step=0.167, train_rouge1_fmeasure_step=0.667, train_rouge1_precision_step=0.750, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.571, train_rouge2_precision_step=0.667, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.667, train_rougeL_precision_step=0.750, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.667, train_rougeLsum_precision_step=0.750, train_rougeLsum_recall_step=0.600]
Epoch 0:  91%|█████████ | 175/192 [00:55<00:05,  3.13it/s, v_num=jo_1, train_loss_step=0.162, train_rouge1_fmeasure_step=0.333, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.200, train_rouge2_fmeasure_step=0.250, train_rouge2_precision_step=1.000, train_rouge2_recall_step=0.143, train_rougeL_fmeasure_step=0.333, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.200, train_rougeLsum_fmeasure_step=0.333, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.200]
Epoch 0:  94%|█████████▍| 180/192 [00:57<00:03,  3.13it/s, v_num=jo_1, train_loss_step=0.162, train_rouge1_fmeasure_step=0.333, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.200, train_rouge2_fmeasure_step=0.250, train_rouge2_precision_step=1.000, train_rouge2_recall_step=0.143, train_rougeL_fmeasure_step=0.333, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.200, train_rougeLsum_fmeasure_step=0.333, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.200]
Epoch 0:  94%|█████████▍| 180/192 [00:57<00:03,  3.13it/s, v_num=jo_1, train_loss_step=0.352, train_rouge1_fmeasure_step=0.500, train_rouge1_precision_step=0.667, train_rouge1_recall_step=0.400, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.500, train_rougeL_precision_step=0.667, train_rougeL_recall_step=0.400, train_rougeLsum_fmeasure_step=0.500, train_rougeLsum_precision_step=0.667, train_rougeLsum_recall_step=0.400]
Epoch 0:  96%|█████████▋| 185/192 [00:59<00:02,  3.13it/s, v_num=jo_1, train_loss_step=0.352, train_rouge1_fmeasure_step=0.500, train_rouge1_precision_step=0.667, train_rouge1_recall_step=0.400, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.500, train_rougeL_precision_step=0.667, train_rougeL_recall_step=0.400, train_rougeLsum_fmeasure_step=0.500, train_rougeLsum_precision_step=0.667, train_rougeLsum_recall_step=0.400]
Epoch 0:  96%|█████████▋| 185/192 [00:59<00:02,  3.13it/s, v_num=jo_1, train_loss_step=6.670, train_rouge1_fmeasure_step=0.545, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.375, train_rouge2_fmeasure_step=0.444, train_rouge2_precision_step=1.000, train_rouge2_recall_step=0.286, train_rougeL_fmeasure_step=0.545, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.375, train_rougeLsum_fmeasure_step=0.545, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.375]
Epoch 0:  99%|█████████▉| 190/192 [01:00<00:00,  3.13it/s, v_num=jo_1, train_loss_step=6.670, train_rouge1_fmeasure_step=0.545, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.375, train_rouge2_fmeasure_step=0.444, train_rouge2_precision_step=1.000, train_rouge2_recall_step=0.286, train_rougeL_fmeasure_step=0.545, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.375, train_rougeLsum_fmeasure_step=0.545, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.375]
Epoch 0:  99%|█████████▉| 190/192 [01:00<00:00,  3.13it/s, v_num=jo_1, train_loss_step=0.370, train_rouge1_fmeasure_step=0.667, train_rouge1_precision_step=0.750, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.571, train_rouge2_precision_step=0.667, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.667, train_rougeL_precision_step=0.750, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.667, train_rougeLsum_precision_step=0.750, train_rougeLsum_recall_step=0.600]
Epoch 0: 100%|██████████| 192/192 [01:01<00:00,  3.13it/s, v_num=jo_1, train_loss_step=0.370, train_rouge1_fmeasure_step=0.667, train_rouge1_precision_step=0.750, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.571, train_rouge2_precision_step=0.667, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.667, train_rougeL_precision_step=0.750, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.667, train_rougeLsum_precision_step=0.750, train_rougeLsum_recall_step=0.600]
Epoch 0: 100%|██████████| 192/192 [01:01<00:00,  3.13it/s, v_num=jo_1, train_loss_step=0.454, train_rouge1_fmeasure_step=0.750, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.667, train_rouge2_precision_step=1.000, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.750, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.750, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.600]

Validation: |          | 0/? [00:00<?, ?it/s]

Validation:   0%|          | 0/12 [00:00<?, ?it/s]

Validation DataLoader 0:   0%|          | 0/12 [00:00<?, ?it/s]

Validation DataLoader 0:  42%|████▏     | 5/12 [00:00<00:01,  5.42it/s]

Validation DataLoader 0:  83%|████████▎ | 10/12 [00:01<00:00,  5.38it/s]

Validation DataLoader 0: 100%|██████████| 12/12 [00:02<00:00,  5.36it/s]

                                                                        
Epoch 0: 100%|██████████| 192/192 [01:03<00:00,  3.02it/s, v_num=jo_1, train_loss_step=0.454, train_rouge1_fmeasure_step=0.750, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.667, train_rouge2_precision_step=1.000, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.750, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.750, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.600, val_loss_step=5.190, val_rouge1_fmeasure_step=0.488, val_rouge1_precision_step=1.000, val_rouge1_recall_step=0.330, val_rouge2_fmeasure_step=0.393, val_rouge2_precision_step=1.000, val_rouge2_recall_step=0.250, val_rougeL_fmeasure_step=0.488, val_rougeL_precision_step=1.000, val_rougeL_recall_step=0.330, val_rougeLsum_fmeasure_step=0.488, val_rougeLsum_precision_step=1.000, val_rougeLsum_recall_step=0.330, val_loss_epoch=0.967, val_rouge1_fmeasure_epoch=0.440, val_rouge1_precision_epoch=0.929, val_rouge1_recall_epoch=0.322, val_rouge2_fmeasure_epoch=0.363, val_rouge2_precision_epoch=0.882, val_rouge2_recall_epoch=0.253, val_rougeL_fmeasure_epoch=0.440, val_rougeL_precision_epoch=0.929, val_rougeL_recall_epoch=0.322, val_rougeLsum_fmeasure_epoch=0.440, val_rougeLsum_precision_epoch=0.929, val_rougeLsum_recall_epoch=0.322]
Epoch 0: 100%|██████████| 192/192 [01:03<00:00,  3.02it/s, v_num=jo_1, train_loss_step=0.454, train_rouge1_fmeasure_step=0.750, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.667, train_rouge2_precision_step=1.000, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.750, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.750, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.600, val_loss_step=5.190, val_rouge1_fmeasure_step=0.488, val_rouge1_precision_step=1.000, val_rouge1_recall_step=0.330, val_rouge2_fmeasure_step=0.393, val_rouge2_precision_step=1.000, val_rouge2_recall_step=0.250, val_rougeL_fmeasure_step=0.488, val_rougeL_precision_step=1.000, val_rougeL_recall_step=0.330, val_rougeLsum_fmeasure_step=0.488, val_rougeLsum_precision_step=1.000, val_rougeLsum_recall_step=0.330, val_loss_epoch=0.967, val_rouge1_fmeasure_epoch=0.440, val_rouge1_precision_epoch=0.929, val_rouge1_recall_epoch=0.322, val_rouge2_fmeasure_epoch=0.363, val_rouge2_precision_epoch=0.882, val_rouge2_recall_epoch=0.253, val_rougeL_fmeasure_epoch=0.440, val_rougeL_precision_epoch=0.929, val_rougeL_recall_epoch=0.322, val_rougeLsum_fmeasure_epoch=0.440, val_rougeLsum_precision_epoch=0.929, val_rougeLsum_recall_epoch=0.322, train_loss_epoch=1.170, train_rouge1_fmeasure_epoch=0.132, train_rouge1_precision_epoch=0.219, train_rouge1_recall_epoch=0.124, train_rouge2_fmeasure_epoch=0.0815, train_rouge2_precision_epoch=0.142, train_rouge2_recall_epoch=0.064, train_rougeL_fmeasure_epoch=0.131, train_rougeL_precision_epoch=0.218, train_rougeL_recall_epoch=0.122, train_rougeLsum_fmeasure_epoch=0.131, train_rougeLsum_precision_epoch=0.219, train_rougeLsum_recall_epoch=0.122]`Trainer.fit` stopped: `max_epochs=1` reached.

Epoch 0: 100%|██████████| 192/192 [01:27<00:00,  2.19it/s, v_num=jo_1, train_loss_step=0.454, train_rouge1_fmeasure_step=0.750, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.667, train_rouge2_precision_step=1.000, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.750, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.750, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.600, val_loss_step=5.190, val_rouge1_fmeasure_step=0.488, val_rouge1_precision_step=1.000, val_rouge1_recall_step=0.330, val_rouge2_fmeasure_step=0.393, val_rouge2_precision_step=1.000, val_rouge2_recall_step=0.250, val_rougeL_fmeasure_step=0.488, val_rougeL_precision_step=1.000, val_rougeL_recall_step=0.330, val_rougeLsum_fmeasure_step=0.488, val_rougeLsum_precision_step=1.000, val_rougeLsum_recall_step=0.330, val_loss_epoch=0.967, val_rouge1_fmeasure_epoch=0.440, val_rouge1_precision_epoch=0.929, val_rouge1_recall_epoch=0.322, val_rouge2_fmeasure_epoch=0.363, val_rouge2_precision_epoch=0.882, val_rouge2_recall_epoch=0.253, val_rougeL_fmeasure_epoch=0.440, val_rougeL_precision_epoch=0.929, val_rougeL_recall_epoch=0.322, val_rougeLsum_fmeasure_epoch=0.440, val_rougeLsum_precision_epoch=0.929, val_rougeLsum_recall_epoch=0.322, train_loss_epoch=1.170, train_rouge1_fmeasure_epoch=0.132, train_rouge1_precision_epoch=0.219, train_rouge1_recall_epoch=0.124, train_rouge2_fmeasure_epoch=0.0815, train_rouge2_precision_epoch=0.142, train_rouge2_recall_epoch=0.064, train_rougeL_fmeasure_epoch=0.131, train_rougeL_precision_epoch=0.218, train_rougeL_recall_epoch=0.122, train_rougeLsum_fmeasure_epoch=0.131, train_rougeLsum_precision_epoch=0.219, train_rougeLsum_recall_epoch=0.122]wandb: - 0.014 MB of 0.014 MB uploaded
wandb: \ 0.014 MB of 0.014 MB uploaded
wandb: | 0.014 MB of 0.014 MB uploaded
wandb: / 0.014 MB of 0.026 MB uploaded
wandb: - 0.014 MB of 0.026 MB uploaded
wandb: \ 0.026 MB of 0.026 MB uploaded
wandb:                                                                                
wandb: 
wandb: Run history:
wandb:                           epoch ▁▁▁
wandb:                    lr-PagedLion ▁▁
wandb:                train_loss_epoch ▁
wandb:                 train_loss_step ▁
wandb:     train_rouge1_fmeasure_epoch ▁
wandb:      train_rouge1_fmeasure_step ▁
wandb:    train_rouge1_precision_epoch ▁
wandb:     train_rouge1_precision_step ▁
wandb:       train_rouge1_recall_epoch ▁
wandb:        train_rouge1_recall_step ▁
wandb:     train_rouge2_fmeasure_epoch ▁
wandb:      train_rouge2_fmeasure_step ▁
wandb:    train_rouge2_precision_epoch ▁
wandb:     train_rouge2_precision_step ▁
wandb:       train_rouge2_recall_epoch ▁
wandb:        train_rouge2_recall_step ▁
wandb:     train_rougeL_fmeasure_epoch ▁
wandb:      train_rougeL_fmeasure_step ▁
wandb:    train_rougeL_precision_epoch ▁
wandb:     train_rougeL_precision_step ▁
wandb:       train_rougeL_recall_epoch ▁
wandb:        train_rougeL_recall_step ▁
wandb:  train_rougeLsum_fmeasure_epoch ▁
wandb:   train_rougeLsum_fmeasure_step ▁
wandb: train_rougeLsum_precision_epoch ▁
wandb:  train_rougeLsum_precision_step ▁
wandb:    train_rougeLsum_recall_epoch ▁
wandb:     train_rougeLsum_recall_step ▁
wandb:             trainer/global_step ▅▅▅▁▁▁▁▁▁▁▂▂▂▂▂██
wandb:                  val_loss_epoch ▁
wandb:                   val_loss_step ▂▁▁▁▁▃▃▁▂▂▂█
wandb:       val_rouge1_fmeasure_epoch ▁
wandb:        val_rouge1_fmeasure_step ▄▆▃▃▃▁▆█▆▇▇▅
wandb:      val_rouge1_precision_epoch ▁
wandb:       val_rouge1_precision_step ██▄▄█▁▄█▄▄██
wandb:         val_rouge1_recall_epoch ▁
wandb:          val_rouge1_recall_step ▃▅▂▃▃▁▆█▆▇▇▅
wandb:       val_rouge2_fmeasure_epoch ▁
wandb:        val_rouge2_fmeasure_step ▃▅▃▃▃▁▆█▆▇▇▅
wandb:      val_rouge2_precision_epoch ▁
wandb:       val_rouge2_precision_step ▅█▅▅█▁▅█▅▅██
wandb:         val_rouge2_recall_epoch ▁
wandb:          val_rouge2_recall_step ▃▅▂▂▂▁▆█▆▇▇▄
wandb:       val_rougeL_fmeasure_epoch ▁
wandb:        val_rougeL_fmeasure_step ▄▆▃▃▃▁▆█▆▇▇▅
wandb:      val_rougeL_precision_epoch ▁
wandb:       val_rougeL_precision_step ██▄▄█▁▄█▄▄██
wandb:         val_rougeL_recall_epoch ▁
wandb:          val_rougeL_recall_step ▃▅▂▃▃▁▆█▆▇▇▅
wandb:    val_rougeLsum_fmeasure_epoch ▁
wandb:     val_rougeLsum_fmeasure_step ▄▆▃▃▃▁▆█▆▇▇▅
wandb:   val_rougeLsum_precision_epoch ▁
wandb:    val_rougeLsum_precision_step ██▄▄█▁▄█▄▄██
wandb:      val_rougeLsum_recall_epoch ▁
wandb:       val_rougeLsum_recall_step ▃▅▂▃▃▁▆█▆▇▇▅
wandb: 
wandb: Run summary:
wandb:                           epoch 0
wandb:                    lr-PagedLion 0.00024
wandb:                train_loss_epoch 1.17233
wandb:                 train_loss_step 0.68395
wandb:     train_rouge1_fmeasure_epoch 0.13158
wandb:      train_rouge1_fmeasure_step 0.0
wandb:    train_rouge1_precision_epoch 0.21929
wandb:     train_rouge1_precision_step 0.0
wandb:       train_rouge1_recall_epoch 0.12398
wandb:        train_rouge1_recall_step 0.0
wandb:     train_rouge2_fmeasure_epoch 0.0815
wandb:      train_rouge2_fmeasure_step 0.0
wandb:    train_rouge2_precision_epoch 0.1422
wandb:     train_rouge2_precision_step 0.0
wandb:       train_rouge2_recall_epoch 0.06396
wandb:        train_rouge2_recall_step 0.0
wandb:     train_rougeL_fmeasure_epoch 0.13104
wandb:      train_rougeL_fmeasure_step 0.0
wandb:    train_rougeL_precision_epoch 0.21798
wandb:     train_rougeL_precision_step 0.0
wandb:       train_rougeL_recall_epoch 0.12244
wandb:        train_rougeL_recall_step 0.0
wandb:  train_rougeLsum_fmeasure_epoch 0.13147
wandb:   train_rougeLsum_fmeasure_step 0.0
wandb: train_rougeLsum_precision_epoch 0.21922
wandb:  train_rougeLsum_precision_step 0.0
wandb:    train_rougeLsum_recall_epoch 0.12245
wandb:     train_rougeLsum_recall_step 0.0
wandb:             trainer/global_step 95
wandb:                  val_loss_epoch 0.9669
wandb:                   val_loss_step 5.18546
wandb:       val_rouge1_fmeasure_epoch 0.44038
wandb:        val_rouge1_fmeasure_step 0.4875
wandb:      val_rouge1_precision_epoch 0.92917
wandb:       val_rouge1_precision_step 1.0
wandb:         val_rouge1_recall_epoch 0.3218
wandb:          val_rouge1_recall_step 0.32967
wandb:       val_rouge2_fmeasure_epoch 0.36287
wandb:        val_rouge2_fmeasure_step 0.39286
wandb:      val_rouge2_precision_epoch 0.88194
wandb:       val_rouge2_precision_step 1.0
wandb:         val_rouge2_recall_epoch 0.2528
wandb:          val_rouge2_recall_step 0.25
wandb:       val_rougeL_fmeasure_epoch 0.44038
wandb:        val_rougeL_fmeasure_step 0.4875
wandb:      val_rougeL_precision_epoch 0.92917
wandb:       val_rougeL_precision_step 1.0
wandb:         val_rougeL_recall_epoch 0.3218
wandb:          val_rougeL_recall_step 0.32967
wandb:    val_rougeLsum_fmeasure_epoch 0.44038
wandb:     val_rougeLsum_fmeasure_step 0.4875
wandb:   val_rougeLsum_precision_epoch 0.92917
wandb:    val_rougeLsum_precision_step 1.0
wandb:      val_rougeLsum_recall_epoch 0.3218
wandb:       val_rougeLsum_recall_step 0.32967
wandb: 
wandb: 🚀 View run divine-sweep-4 at: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/dky0jtjo
wandb: ⭐️ View project at: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)
wandb: Find logs at: ./wandb/run-20240806_135652-dky0jtjo/logs
wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information.
wandb: Agent Starting Run: gc9hmicj with config:
wandb: 	accumulate_grad_batches: 6
wandb: 	epochs: 1
wandb: 	gradient_clip_val: 0.5238534567989753
wandb: 	init_lora_weights: False
wandb: 	lora_alpha: 16
wandb: 	lora_dropout: 0.07289582504867571
wandb: 	lora_rank: 8
wandb: 	lr: 0.00021450017137806743
wandb: 	model_name: jjhsnail0822/danube-ko-1.8b-base
wandb: WARNING Ignored wandb.init() arg project when running a sweep.
wandb: Tracking run with wandb version 0.17.5
wandb: Run data is saved locally in /user/jonathan/wandb/run-20240806_140140-gc9hmicj
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run absurd-sweep-5
wandb: ⭐️ View project at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: 🧹 View sweep at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/sweeps/4ik6ex9z
wandb: 🚀 View run at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/gc9hmicj
Unused kwargs: ['bnb_8bit_quant_type', 'bnb_8bit_compute_dtype']. These kwargs are not used in <class 'transformers.utils.quantization_config.BitsAndBytesConfig'>.
Repo card metadata block was not found. Setting CardData to empty.
WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty.


Map:   0%|          | 0/960 [00:00<?, ? examples/s]Asking to truncate to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no truncation.

Map: 100%|██████████| 960/960 [00:00<00:00, 7789.59 examples/s]
Map: 100%|██████████| 960/960 [00:00<00:00, 6555.33 examples/s]

Map:   0%|          | 0/960 [00:00<?, ? examples/s]
Map:   0%|          | 0/960 [00:00<?, ? examples/s]
wandb: - 0.014 MB of 0.014 MB uploaded
wandb: \ 0.014 MB of 0.014 MB uploaded
wandb: | 0.014 MB of 0.020 MB uploaded
wandb: / 0.014 MB of 0.020 MB uploaded
wandb: - 0.020 MB of 0.020 MB uploaded
wandb:                                                                                
wandb: 🚀 View run absurd-sweep-5 at: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/gc9hmicj
wandb: ⭐️ View project at: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)
wandb: Find logs at: ./wandb/run-20240806_140140-gc9hmicj/logs
wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information.
Run gc9hmicj errored:
Traceback (most recent call last):
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/wandb/agents/pyagent.py", line 307, in _run_job
    self._function()
  File "/user/jonathan/l_sweep.py", line 50, in l2ray_trainer
    dataset = get_dataset(dataset_name=dataset_path, tokenizer=tokenizer)
  File "/user/jonathan/finetuning_datasets.py", line 40, in get_dataset
    en_dataset = raw_dataset.map(
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/dataset_dict.py", line 869, in map
    {
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/dataset_dict.py", line 870, in <dictcomp>
    k: dataset.map(
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 602, in wrapper
    out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 567, in wrapper
    out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3161, in map
    for rank, done, content in Dataset._map_single(**dataset_kwargs):
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3552, in _map_single
    batch = apply_function_on_filtered_inputs(
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3421, in apply_function_on_filtered_inputs
    processed_inputs = function(*fn_args, *additional_args, **fn_kwargs)
  File "/user/jonathan/finetuning_datafunctions.py", line 65, in preprocess_function
    templated_text, labels = formatting(sample=sample,
  File "/user/jonathan/finetuning_datafunctions.py", line 38, in formatting
    bot_message = tokenizer.apply_chat_template(conversation=label_template,
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1855, in apply_chat_template
    rendered_chat = compiled_template.render(
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/environment.py", line 1304, in render
    self.environment.handle_exception()
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/environment.py", line 939, in handle_exception
    raise rewrite_traceback_stack(source=source)
  File "<template>", line 1, in top-level template code
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/sandbox.py", line 394, in call
    return __context.call(__obj, *args, **kwargs)
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1899, in raise_exception
    raise TemplateError(message)
jinja2.exceptions.TemplateError: Conversation roles must alternate user/assistant/user/assistant/...

wandb: ERROR Run gc9hmicj errored:
wandb: ERROR Traceback (most recent call last):
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/wandb/agents/pyagent.py", line 307, in _run_job
wandb: ERROR     self._function()
wandb: ERROR   File "/user/jonathan/l_sweep.py", line 50, in l2ray_trainer
wandb: ERROR     dataset = get_dataset(dataset_name=dataset_path, tokenizer=tokenizer)
wandb: ERROR   File "/user/jonathan/finetuning_datasets.py", line 40, in get_dataset
wandb: ERROR     en_dataset = raw_dataset.map(
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/dataset_dict.py", line 869, in map
wandb: ERROR     {
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/dataset_dict.py", line 870, in <dictcomp>
wandb: ERROR     k: dataset.map(
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 602, in wrapper
wandb: ERROR     out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 567, in wrapper
wandb: ERROR     out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3161, in map
wandb: ERROR     for rank, done, content in Dataset._map_single(**dataset_kwargs):
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3552, in _map_single
wandb: ERROR     batch = apply_function_on_filtered_inputs(
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3421, in apply_function_on_filtered_inputs
wandb: ERROR     processed_inputs = function(*fn_args, *additional_args, **fn_kwargs)
wandb: ERROR   File "/user/jonathan/finetuning_datafunctions.py", line 65, in preprocess_function
wandb: ERROR     templated_text, labels = formatting(sample=sample,
wandb: ERROR   File "/user/jonathan/finetuning_datafunctions.py", line 38, in formatting
wandb: ERROR     bot_message = tokenizer.apply_chat_template(conversation=label_template,
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1855, in apply_chat_template
wandb: ERROR     rendered_chat = compiled_template.render(
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/environment.py", line 1304, in render
wandb: ERROR     self.environment.handle_exception()
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/environment.py", line 939, in handle_exception
wandb: ERROR     raise rewrite_traceback_stack(source=source)
wandb: ERROR   File "<template>", line 1, in top-level template code
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/sandbox.py", line 394, in call
wandb: ERROR     return __context.call(__obj, *args, **kwargs)
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1899, in raise_exception
wandb: ERROR     raise TemplateError(message)
wandb: ERROR jinja2.exceptions.TemplateError: Conversation roles must alternate user/assistant/user/assistant/...
wandb: ERROR 
wandb: Agent Starting Run: iz24uc9a with config:
wandb: 	accumulate_grad_batches: 1
wandb: 	epochs: 1
wandb: 	gradient_clip_val: 0.4449990271546663
wandb: 	init_lora_weights: pissa_niter_16
wandb: 	lora_alpha: 128
wandb: 	lora_dropout: 0.06251410191599312
wandb: 	lora_rank: 8
wandb: 	lr: 0.00022508829909255213
wandb: 	model_name: EleutherAI/polyglot-ko-12.8b
wandb: WARNING Ignored wandb.init() arg project when running a sweep.
wandb: - Waiting for wandb.init()...
wandb: \ Waiting for wandb.init()...
wandb: Tracking run with wandb version 0.17.5
wandb: Run data is saved locally in /user/jonathan/wandb/run-20240806_140206-iz24uc9a
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run chocolate-sweep-6
wandb: ⭐️ View project at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: 🧹 View sweep at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/sweeps/4ik6ex9z
wandb: 🚀 View run at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/iz24uc9a
Unused kwargs: ['bnb_8bit_quant_type', 'bnb_8bit_compute_dtype']. These kwargs are not used in <class 'transformers.utils.quantization_config.BitsAndBytesConfig'>.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Repo card metadata block was not found. Setting CardData to empty.
WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty.

Map:   0%|          | 0/960 [00:00<?, ? examples/s]Asking to truncate to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no truncation.

Map: 100%|██████████| 960/960 [00:00<00:00, 6642.05 examples/s]
Map: 100%|██████████| 960/960 [00:00<00:00, 5915.19 examples/s]
GPU available: True (cuda), used: True
TPU available: False, using: 0 TPU cores
HPU available: False, using: 0 HPUs
initializing deepspeed distributed: GLOBAL_RANK: 0, MEMBER: 1/1
Enabling DeepSpeed BF16. Model parameters and inputs will be cast to `bfloat16`.
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]
[2024-08-06 14:05:09,952] [WARNING] [engine.py:1179:_do_optimizer_sanity_check] **** You are using ZeRO with an untested optimizer, proceed with caution *****

  | Name  | Type                 | Params | Mode 
-------------------------------------------------------
0 | model | PeftModelForCausalLM | 1.5 B  | train
-------------------------------------------------------
1.1 M     Trainable params
1.5 B     Non-trainable params
1.5 B     Total params
6,183.574 Total estimated model params size (MB)

Sanity Checking: |          | 0/? [00:00<?, ?it/s]
Sanity Checking:   0%|          | 0/2 [00:00<?, ?it/s]
Sanity Checking DataLoader 0:   0%|          | 0/2 [00:00<?, ?it/s]
Sanity Checking DataLoader 0: 100%|██████████| 2/2 [00:00<00:00,  2.10it/s]
                                                                           

Training: |          | 0/? [00:00<?, ?it/s]
Training:   0%|          | 0/192 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/192 [00:00<?, ?it/s] 
Epoch 0:   3%|▎         | 5/192 [00:02<01:42,  1.82it/s]
Epoch 0:   3%|▎         | 5/192 [00:02<01:42,  1.82it/s, v_num=9a_1, train_loss_step=3.600, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:   5%|▌         | 10/192 [00:05<01:39,  1.83it/s, v_num=9a_1, train_loss_step=3.600, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:   5%|▌         | 10/192 [00:05<01:39,  1.82it/s, v_num=9a_1, train_loss_step=1.520, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:   8%|▊         | 15/192 [00:08<01:36,  1.83it/s, v_num=9a_1, train_loss_step=1.520, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:   8%|▊         | 15/192 [00:08<01:36,  1.83it/s, v_num=9a_1, train_loss_step=0.391, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  10%|█         | 20/192 [00:10<01:33,  1.84it/s, v_num=9a_1, train_loss_step=0.391, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  10%|█         | 20/192 [00:10<01:33,  1.84it/s, v_num=9a_1, train_loss_step=0.172, train_rouge1_fmeasure_step=0.118, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.0714, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.118, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.0714, train_rougeLsum_fmeasure_step=0.118, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.0714]
Epoch 0:  13%|█▎        | 25/192 [00:13<01:30,  1.84it/s, v_num=9a_1, train_loss_step=0.172, train_rouge1_fmeasure_step=0.118, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.0714, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.118, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.0714, train_rougeLsum_fmeasure_step=0.118, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.0714]
Epoch 0:  13%|█▎        | 25/192 [00:13<01:30,  1.84it/s, v_num=9a_1, train_loss_step=0.135, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]   
Epoch 0:  16%|█▌        | 30/192 [00:16<01:27,  1.84it/s, v_num=9a_1, train_loss_step=0.135, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  16%|█▌        | 30/192 [00:16<01:27,  1.84it/s, v_num=9a_1, train_loss_step=0.0721, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  18%|█▊        | 35/192 [00:19<01:26,  1.81it/s, v_num=9a_1, train_loss_step=0.0721, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  18%|█▊        | 35/192 [00:19<01:26,  1.81it/s, v_num=9a_1, train_loss_step=1.960, train_rouge1_fmeasure_step=0.0132, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.00662, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0132, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.00662, train_rougeLsum_fmeasure_step=0.0132, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.00662]
Epoch 0:  21%|██        | 40/192 [00:22<01:23,  1.81it/s, v_num=9a_1, train_loss_step=1.960, train_rouge1_fmeasure_step=0.0132, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.00662, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0132, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.00662, train_rougeLsum_fmeasure_step=0.0132, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.00662]
Epoch 0:  21%|██        | 40/192 [00:22<01:23,  1.81it/s, v_num=9a_1, train_loss_step=0.382, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]         
Epoch 0:  23%|██▎       | 45/192 [00:24<01:20,  1.82it/s, v_num=9a_1, train_loss_step=0.382, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  23%|██▎       | 45/192 [00:24<01:20,  1.82it/s, v_num=9a_1, train_loss_step=0.120, train_rouge1_fmeasure_step=0.250, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.200, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.250, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.200, train_rougeLsum_fmeasure_step=0.250, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.200]
Epoch 0:  26%|██▌       | 50/192 [00:27<01:17,  1.82it/s, v_num=9a_1, train_loss_step=0.120, train_rouge1_fmeasure_step=0.250, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.200, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.250, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.200, train_rougeLsum_fmeasure_step=0.250, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.200]
Epoch 0:  26%|██▌       | 50/192 [00:27<01:17,  1.82it/s, v_num=9a_1, train_loss_step=0.198, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  29%|██▊       | 55/192 [00:30<01:15,  1.83it/s, v_num=9a_1, train_loss_step=0.198, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  29%|██▊       | 55/192 [00:30<01:15,  1.83it/s, v_num=9a_1, train_loss_step=0.305, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  31%|███▏      | 60/192 [00:32<01:12,  1.83it/s, v_num=9a_1, train_loss_step=0.305, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  31%|███▏      | 60/192 [00:32<01:12,  1.83it/s, v_num=9a_1, train_loss_step=0.190, train_rouge1_fmeasure_step=0.0769, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.0435, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0769, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.0435, train_rougeLsum_fmeasure_step=0.0769, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.0435]
Epoch 0:  34%|███▍      | 65/192 [00:35<01:09,  1.83it/s, v_num=9a_1, train_loss_step=0.190, train_rouge1_fmeasure_step=0.0769, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.0435, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0769, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.0435, train_rougeLsum_fmeasure_step=0.0769, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.0435]
Epoch 0:  34%|███▍      | 65/192 [00:35<01:09,  1.83it/s, v_num=9a_1, train_loss_step=0.252, train_rouge1_fmeasure_step=0.0667, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.0345, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0667, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.0345, train_rougeLsum_fmeasure_step=0.0667, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.0345]
Epoch 0:  36%|███▋      | 70/192 [00:38<01:06,  1.83it/s, v_num=9a_1, train_loss_step=0.252, train_rouge1_fmeasure_step=0.0667, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.0345, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0667, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.0345, train_rougeLsum_fmeasure_step=0.0667, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.0345]
Epoch 0:  36%|███▋      | 70/192 [00:38<01:06,  1.83it/s, v_num=9a_1, train_loss_step=0.0595, train_rouge1_fmeasure_step=0.286, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.167, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.286, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.167, train_rougeLsum_fmeasure_step=0.286, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.167]     
Epoch 0:  39%|███▉      | 75/192 [00:40<01:03,  1.84it/s, v_num=9a_1, train_loss_step=0.0595, train_rouge1_fmeasure_step=0.286, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.167, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.286, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.167, train_rougeLsum_fmeasure_step=0.286, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.167]
Epoch 0:  39%|███▉      | 75/192 [00:40<01:03,  1.84it/s, v_num=9a_1, train_loss_step=0.660, train_rouge1_fmeasure_step=0.250, train_rouge1_precision_step=0.500, train_rouge1_recall_step=0.167, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.250, train_rougeL_precision_step=0.500, train_rougeL_recall_step=0.167, train_rougeLsum_fmeasure_step=0.250, train_rougeLsum_precision_step=0.500, train_rougeLsum_recall_step=0.167] 
Epoch 0:  42%|████▏     | 80/192 [00:43<01:00,  1.84it/s, v_num=9a_1, train_loss_step=0.660, train_rouge1_fmeasure_step=0.250, train_rouge1_precision_step=0.500, train_rouge1_recall_step=0.167, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.250, train_rougeL_precision_step=0.500, train_rougeL_recall_step=0.167, train_rougeLsum_fmeasure_step=0.250, train_rougeLsum_precision_step=0.500, train_rougeLsum_recall_step=0.167]
Epoch 0:  42%|████▏     | 80/192 [00:43<01:00,  1.84it/s, v_num=9a_1, train_loss_step=1.130, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  44%|████▍     | 85/192 [00:46<00:58,  1.84it/s, v_num=9a_1, train_loss_step=1.130, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  44%|████▍     | 85/192 [00:46<00:58,  1.84it/s, v_num=9a_1, train_loss_step=0.373, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  47%|████▋     | 90/192 [00:48<00:55,  1.84it/s, v_num=9a_1, train_loss_step=0.373, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  47%|████▋     | 90/192 [00:48<00:55,  1.84it/s, v_num=9a_1, train_loss_step=0.493, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  49%|████▉     | 95/192 [00:51<00:52,  1.84it/s, v_num=9a_1, train_loss_step=0.493, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  49%|████▉     | 95/192 [00:51<00:52,  1.84it/s, v_num=9a_1, train_loss_step=0.0936, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  52%|█████▏    | 100/192 [00:54<00:49,  1.84it/s, v_num=9a_1, train_loss_step=0.0936, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  52%|█████▏    | 100/192 [00:54<00:49,  1.84it/s, v_num=9a_1, train_loss_step=0.0976, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  55%|█████▍    | 105/192 [00:57<00:47,  1.84it/s, v_num=9a_1, train_loss_step=0.0976, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  55%|█████▍    | 105/192 [00:57<00:47,  1.84it/s, v_num=9a_1, train_loss_step=0.0899, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  57%|█████▋    | 110/192 [00:59<00:44,  1.84it/s, v_num=9a_1, train_loss_step=0.0899, train_rouge1_fmeasure_step=0.000, train_rouge1_precision_step=0.000, train_rouge1_recall_step=0.000, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.000, train_rougeL_precision_step=0.000, train_rougeL_recall_step=0.000, train_rougeLsum_fmeasure_step=0.000, train_rougeLsum_precision_step=0.000, train_rougeLsum_recall_step=0.000]
Epoch 0:  57%|█████▋    | 110/192 [00:59<00:44,  1.84it/s, v_num=9a_1, train_loss_step=0.110, train_rouge1_fmeasure_step=0.235, train_rouge1_precision_step=0.400, train_rouge1_recall_step=0.167, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.235, train_rougeL_precision_step=0.400, train_rougeL_recall_step=0.167, train_rougeLsum_fmeasure_step=0.235, train_rougeLsum_precision_step=0.400, train_rougeLsum_recall_step=0.167] 
Epoch 0:  60%|█████▉    | 115/192 [01:02<00:41,  1.84it/s, v_num=9a_1, train_loss_step=0.110, train_rouge1_fmeasure_step=0.235, train_rouge1_precision_step=0.400, train_rouge1_recall_step=0.167, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.235, train_rougeL_precision_step=0.400, train_rougeL_recall_step=0.167, train_rougeLsum_fmeasure_step=0.235, train_rougeLsum_precision_step=0.400, train_rougeLsum_recall_step=0.167]
Epoch 0:  60%|█████▉    | 115/192 [01:02<00:41,  1.84it/s, v_num=9a_1, train_loss_step=0.433, train_rouge1_fmeasure_step=0.100, train_rouge1_precision_step=0.125, train_rouge1_recall_step=0.0833, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.100, train_rougeL_precision_step=0.125, train_rougeL_recall_step=0.0833, train_rougeLsum_fmeasure_step=0.100, train_rougeLsum_precision_step=0.125, train_rougeLsum_recall_step=0.0833]
Epoch 0:  62%|██████▎   | 120/192 [01:05<00:39,  1.84it/s, v_num=9a_1, train_loss_step=0.433, train_rouge1_fmeasure_step=0.100, train_rouge1_precision_step=0.125, train_rouge1_recall_step=0.0833, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.100, train_rougeL_precision_step=0.125, train_rougeL_recall_step=0.0833, train_rougeLsum_fmeasure_step=0.100, train_rougeLsum_precision_step=0.125, train_rougeLsum_recall_step=0.0833]
Epoch 0:  62%|██████▎   | 120/192 [01:05<00:39,  1.84it/s, v_num=9a_1, train_loss_step=0.141, train_rouge1_fmeasure_step=0.087, train_rouge1_precision_step=0.250, train_rouge1_recall_step=0.0526, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.087, train_rougeL_precision_step=0.250, train_rougeL_recall_step=0.0526, train_rougeLsum_fmeasure_step=0.087, train_rougeLsum_precision_step=0.250, train_rougeLsum_recall_step=0.0526]
Epoch 0:  65%|██████▌   | 125/192 [01:07<00:36,  1.84it/s, v_num=9a_1, train_loss_step=0.141, train_rouge1_fmeasure_step=0.087, train_rouge1_precision_step=0.250, train_rouge1_recall_step=0.0526, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.087, train_rougeL_precision_step=0.250, train_rougeL_recall_step=0.0526, train_rougeLsum_fmeasure_step=0.087, train_rougeLsum_precision_step=0.250, train_rougeLsum_recall_step=0.0526]
Epoch 0:  65%|██████▌   | 125/192 [01:07<00:36,  1.84it/s, v_num=9a_1, train_loss_step=0.0931, train_rouge1_fmeasure_step=0.111, train_rouge1_precision_step=0.125, train_rouge1_recall_step=0.100, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.111, train_rougeL_precision_step=0.125, train_rougeL_recall_step=0.100, train_rougeLsum_fmeasure_step=0.111, train_rougeLsum_precision_step=0.125, train_rougeLsum_recall_step=0.100]  
Epoch 0:  68%|██████▊   | 130/192 [01:10<00:33,  1.84it/s, v_num=9a_1, train_loss_step=0.0931, train_rouge1_fmeasure_step=0.111, train_rouge1_precision_step=0.125, train_rouge1_recall_step=0.100, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.111, train_rougeL_precision_step=0.125, train_rougeL_recall_step=0.100, train_rougeLsum_fmeasure_step=0.111, train_rougeLsum_precision_step=0.125, train_rougeLsum_recall_step=0.100]
Epoch 0:  68%|██████▊   | 130/192 [01:10<00:33,  1.84it/s, v_num=9a_1, train_loss_step=1.360, train_rouge1_fmeasure_step=0.0129, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.00658, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0129, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.00658, train_rougeLsum_fmeasure_step=0.0129, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.00658]
Epoch 0:  70%|███████   | 135/192 [01:13<00:30,  1.85it/s, v_num=9a_1, train_loss_step=1.360, train_rouge1_fmeasure_step=0.0129, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.00658, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.0129, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.00658, train_rougeLsum_fmeasure_step=0.0129, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.00658]
Epoch 0:  70%|███████   | 135/192 [01:13<00:30,  1.85it/s, v_num=9a_1, train_loss_step=0.183, train_rouge1_fmeasure_step=0.143, train_rouge1_precision_step=0.250, train_rouge1_recall_step=0.100, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.143, train_rougeL_precision_step=0.250, train_rougeL_recall_step=0.100, train_rougeLsum_fmeasure_step=0.143, train_rougeLsum_precision_step=0.250, train_rougeLsum_recall_step=0.100]         
Epoch 0:  73%|███████▎  | 140/192 [01:15<00:28,  1.85it/s, v_num=9a_1, train_loss_step=0.183, train_rouge1_fmeasure_step=0.143, train_rouge1_precision_step=0.250, train_rouge1_recall_step=0.100, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.143, train_rougeL_precision_step=0.250, train_rougeL_recall_step=0.100, train_rougeLsum_fmeasure_step=0.143, train_rougeLsum_precision_step=0.250, train_rougeLsum_recall_step=0.100]
Epoch 0:  73%|███████▎  | 140/192 [01:15<00:28,  1.85it/s, v_num=9a_1, train_loss_step=0.347, train_rouge1_fmeasure_step=0.400, train_rouge1_precision_step=0.500, train_rouge1_recall_step=0.333, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.400, train_rougeL_precision_step=0.500, train_rougeL_recall_step=0.333, train_rougeLsum_fmeasure_step=0.200, train_rougeLsum_precision_step=0.250, train_rougeLsum_recall_step=0.167]
Epoch 0:  76%|███████▌  | 145/192 [01:18<00:25,  1.85it/s, v_num=9a_1, train_loss_step=0.347, train_rouge1_fmeasure_step=0.400, train_rouge1_precision_step=0.500, train_rouge1_recall_step=0.333, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.400, train_rougeL_precision_step=0.500, train_rougeL_recall_step=0.333, train_rougeLsum_fmeasure_step=0.200, train_rougeLsum_precision_step=0.250, train_rougeLsum_recall_step=0.167]
Epoch 0:  76%|███████▌  | 145/192 [01:18<00:25,  1.85it/s, v_num=9a_1, train_loss_step=0.0571, train_rouge1_fmeasure_step=0.308, train_rouge1_precision_step=0.500, train_rouge1_recall_step=0.222, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.308, train_rougeL_precision_step=0.500, train_rougeL_recall_step=0.222, train_rougeLsum_fmeasure_step=0.308, train_rougeLsum_precision_step=0.500, train_rougeLsum_recall_step=0.222]
Epoch 0:  78%|███████▊  | 150/192 [01:21<00:22,  1.85it/s, v_num=9a_1, train_loss_step=0.0571, train_rouge1_fmeasure_step=0.308, train_rouge1_precision_step=0.500, train_rouge1_recall_step=0.222, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.308, train_rougeL_precision_step=0.500, train_rougeL_recall_step=0.222, train_rougeLsum_fmeasure_step=0.308, train_rougeLsum_precision_step=0.500, train_rougeLsum_recall_step=0.222]
Epoch 0:  78%|███████▊  | 150/192 [01:21<00:22,  1.85it/s, v_num=9a_1, train_loss_step=0.200, train_rouge1_fmeasure_step=0.167, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.111, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.167, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.111, train_rougeLsum_fmeasure_step=0.167, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.111] 
Epoch 0:  81%|████████  | 155/192 [01:23<00:20,  1.85it/s, v_num=9a_1, train_loss_step=0.200, train_rouge1_fmeasure_step=0.167, train_rouge1_precision_step=0.333, train_rouge1_recall_step=0.111, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.167, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.111, train_rougeLsum_fmeasure_step=0.167, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.111]
Epoch 0:  81%|████████  | 155/192 [01:23<00:20,  1.85it/s, v_num=9a_1, train_loss_step=0.117, train_rouge1_fmeasure_step=0.545, train_rouge1_precision_step=0.500, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.364, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.400, train_rougeLsum_fmeasure_step=0.364, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.400]
Epoch 0:  83%|████████▎ | 160/192 [01:26<00:17,  1.85it/s, v_num=9a_1, train_loss_step=0.117, train_rouge1_fmeasure_step=0.545, train_rouge1_precision_step=0.500, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.364, train_rougeL_precision_step=0.333, train_rougeL_recall_step=0.400, train_rougeLsum_fmeasure_step=0.364, train_rougeLsum_precision_step=0.333, train_rougeLsum_recall_step=0.400]
Epoch 0:  83%|████████▎ | 160/192 [01:26<00:17,  1.85it/s, v_num=9a_1, train_loss_step=0.0689, train_rouge1_fmeasure_step=0.444, train_rouge1_precision_step=0.500, train_rouge1_recall_step=0.400, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.444, train_rougeL_precision_step=0.500, train_rougeL_recall_step=0.400, train_rougeLsum_fmeasure_step=0.444, train_rougeLsum_precision_step=0.500, train_rougeLsum_recall_step=0.400]
Epoch 0:  86%|████████▌ | 165/192 [01:29<00:14,  1.85it/s, v_num=9a_1, train_loss_step=0.0689, train_rouge1_fmeasure_step=0.444, train_rouge1_precision_step=0.500, train_rouge1_recall_step=0.400, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.444, train_rougeL_precision_step=0.500, train_rougeL_recall_step=0.400, train_rougeLsum_fmeasure_step=0.444, train_rougeLsum_precision_step=0.500, train_rougeLsum_recall_step=0.400]
Epoch 0:  86%|████████▌ | 165/192 [01:29<00:14,  1.85it/s, v_num=9a_1, train_loss_step=0.222, train_rouge1_fmeasure_step=0.200, train_rouge1_precision_step=0.250, train_rouge1_recall_step=0.167, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.200, train_rougeL_precision_step=0.250, train_rougeL_recall_step=0.167, train_rougeLsum_fmeasure_step=0.200, train_rougeLsum_precision_step=0.250, train_rougeLsum_recall_step=0.167] 
Epoch 0:  89%|████████▊ | 170/192 [01:32<00:11,  1.85it/s, v_num=9a_1, train_loss_step=0.222, train_rouge1_fmeasure_step=0.200, train_rouge1_precision_step=0.250, train_rouge1_recall_step=0.167, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.200, train_rougeL_precision_step=0.250, train_rougeL_recall_step=0.167, train_rougeLsum_fmeasure_step=0.200, train_rougeLsum_precision_step=0.250, train_rougeLsum_recall_step=0.167]
Epoch 0:  89%|████████▊ | 170/192 [01:32<00:11,  1.85it/s, v_num=9a_1, train_loss_step=0.079, train_rouge1_fmeasure_step=0.182, train_rouge1_precision_step=0.167, train_rouge1_recall_step=0.200, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.182, train_rougeL_precision_step=0.167, train_rougeL_recall_step=0.200, train_rougeLsum_fmeasure_step=0.182, train_rougeLsum_precision_step=0.167, train_rougeLsum_recall_step=0.200]
Epoch 0:  91%|█████████ | 175/192 [01:34<00:09,  1.85it/s, v_num=9a_1, train_loss_step=0.079, train_rouge1_fmeasure_step=0.182, train_rouge1_precision_step=0.167, train_rouge1_recall_step=0.200, train_rouge2_fmeasure_step=0.000, train_rouge2_precision_step=0.000, train_rouge2_recall_step=0.000, train_rougeL_fmeasure_step=0.182, train_rougeL_precision_step=0.167, train_rougeL_recall_step=0.200, train_rougeLsum_fmeasure_step=0.182, train_rougeLsum_precision_step=0.167, train_rougeLsum_recall_step=0.200]
Epoch 0:  91%|█████████ | 175/192 [01:34<00:09,  1.85it/s, v_num=9a_1, train_loss_step=0.147, train_rouge1_fmeasure_step=0.211, train_rouge1_precision_step=0.500, train_rouge1_recall_step=0.133, train_rouge2_fmeasure_step=0.118, train_rouge2_precision_step=0.333, train_rouge2_recall_step=0.0714, train_rougeL_fmeasure_step=0.211, train_rougeL_precision_step=0.500, train_rougeL_recall_step=0.133, train_rougeLsum_fmeasure_step=0.211, train_rougeLsum_precision_step=0.500, train_rougeLsum_recall_step=0.133]
Epoch 0:  94%|█████████▍| 180/192 [01:37<00:06,  1.85it/s, v_num=9a_1, train_loss_step=0.147, train_rouge1_fmeasure_step=0.211, train_rouge1_precision_step=0.500, train_rouge1_recall_step=0.133, train_rouge2_fmeasure_step=0.118, train_rouge2_precision_step=0.333, train_rouge2_recall_step=0.0714, train_rougeL_fmeasure_step=0.211, train_rougeL_precision_step=0.500, train_rougeL_recall_step=0.133, train_rougeLsum_fmeasure_step=0.211, train_rougeLsum_precision_step=0.500, train_rougeLsum_recall_step=0.133]
Epoch 0:  94%|█████████▍| 180/192 [01:37<00:06,  1.85it/s, v_num=9a_1, train_loss_step=0.0519, train_rouge1_fmeasure_step=0.800, train_rouge1_precision_step=0.800, train_rouge1_recall_step=0.800, train_rouge2_fmeasure_step=0.750, train_rouge2_precision_step=0.750, train_rouge2_recall_step=0.750, train_rougeL_fmeasure_step=0.800, train_rougeL_precision_step=0.800, train_rougeL_recall_step=0.800, train_rougeLsum_fmeasure_step=0.800, train_rougeLsum_precision_step=0.800, train_rougeLsum_recall_step=0.800]
Epoch 0:  96%|█████████▋| 185/192 [01:40<00:03,  1.85it/s, v_num=9a_1, train_loss_step=0.0519, train_rouge1_fmeasure_step=0.800, train_rouge1_precision_step=0.800, train_rouge1_recall_step=0.800, train_rouge2_fmeasure_step=0.750, train_rouge2_precision_step=0.750, train_rouge2_recall_step=0.750, train_rougeL_fmeasure_step=0.800, train_rougeL_precision_step=0.800, train_rougeL_recall_step=0.800, train_rougeLsum_fmeasure_step=0.800, train_rougeLsum_precision_step=0.800, train_rougeLsum_recall_step=0.800]
Epoch 0:  96%|█████████▋| 185/192 [01:40<00:03,  1.85it/s, v_num=9a_1, train_loss_step=1.010, train_rouge1_fmeasure_step=0.615, train_rouge1_precision_step=0.800, train_rouge1_recall_step=0.500, train_rouge2_fmeasure_step=0.364, train_rouge2_precision_step=0.500, train_rouge2_recall_step=0.286, train_rougeL_fmeasure_step=0.615, train_rougeL_precision_step=0.800, train_rougeL_recall_step=0.500, train_rougeLsum_fmeasure_step=0.615, train_rougeLsum_precision_step=0.800, train_rougeLsum_recall_step=0.500] 
Epoch 0:  99%|█████████▉| 190/192 [01:42<00:01,  1.85it/s, v_num=9a_1, train_loss_step=1.010, train_rouge1_fmeasure_step=0.615, train_rouge1_precision_step=0.800, train_rouge1_recall_step=0.500, train_rouge2_fmeasure_step=0.364, train_rouge2_precision_step=0.500, train_rouge2_recall_step=0.286, train_rougeL_fmeasure_step=0.615, train_rougeL_precision_step=0.800, train_rougeL_recall_step=0.500, train_rougeLsum_fmeasure_step=0.615, train_rougeLsum_precision_step=0.800, train_rougeLsum_recall_step=0.500]
Epoch 0:  99%|█████████▉| 190/192 [01:42<00:01,  1.85it/s, v_num=9a_1, train_loss_step=0.0602, train_rouge1_fmeasure_step=0.667, train_rouge1_precision_step=0.750, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.571, train_rouge2_precision_step=0.667, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.667, train_rougeL_precision_step=0.750, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.667, train_rougeLsum_precision_step=0.750, train_rougeLsum_recall_step=0.600]
Epoch 0: 100%|██████████| 192/192 [01:43<00:00,  1.85it/s, v_num=9a_1, train_loss_step=0.0602, train_rouge1_fmeasure_step=0.667, train_rouge1_precision_step=0.750, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.571, train_rouge2_precision_step=0.667, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.667, train_rougeL_precision_step=0.750, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.667, train_rougeLsum_precision_step=0.750, train_rougeLsum_recall_step=0.600]
Epoch 0: 100%|██████████| 192/192 [01:43<00:00,  1.85it/s, v_num=9a_1, train_loss_step=0.0711, train_rouge1_fmeasure_step=0.750, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.667, train_rouge2_precision_step=1.000, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.750, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.750, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.600]

Validation: |          | 0/? [00:00<?, ?it/s]

Validation:   0%|          | 0/12 [00:00<?, ?it/s]

Validation DataLoader 0:   0%|          | 0/12 [00:00<?, ?it/s]

Validation DataLoader 0:  42%|████▏     | 5/12 [00:01<00:02,  2.93it/s]

Validation DataLoader 0:  83%|████████▎ | 10/12 [00:03<00:00,  2.92it/s]

Validation DataLoader 0: 100%|██████████| 12/12 [00:04<00:00,  2.92it/s]

                                                                        
Epoch 0: 100%|██████████| 192/192 [01:48<00:00,  1.78it/s, v_num=9a_1, train_loss_step=0.0711, train_rouge1_fmeasure_step=0.750, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.667, train_rouge2_precision_step=1.000, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.750, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.750, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.600, val_loss_step=0.793, val_rouge1_fmeasure_step=0.599, val_rouge1_precision_step=1.000, val_rouge1_recall_step=0.440, val_rouge2_fmeasure_step=0.356, val_rouge2_precision_step=0.667, val_rouge2_recall_step=0.250, val_rougeL_fmeasure_step=0.599, val_rougeL_precision_step=1.000, val_rougeL_recall_step=0.440, val_rougeLsum_fmeasure_step=0.599, val_rougeLsum_precision_step=1.000, val_rougeLsum_recall_step=0.440, val_loss_epoch=0.386, val_rouge1_fmeasure_epoch=0.545, val_rouge1_precision_epoch=1.000, val_rouge1_recall_epoch=0.428, val_rouge2_fmeasure_epoch=0.391, val_rouge2_precision_epoch=0.736, val_rouge2_recall_epoch=0.305, val_rougeL_fmeasure_epoch=0.545, val_rougeL_precision_epoch=1.000, val_rougeL_recall_epoch=0.428, val_rougeLsum_fmeasure_epoch=0.545, val_rougeLsum_precision_epoch=1.000, val_rougeLsum_recall_epoch=0.428]
Epoch 0: 100%|██████████| 192/192 [01:48<00:00,  1.78it/s, v_num=9a_1, train_loss_step=0.0711, train_rouge1_fmeasure_step=0.750, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.667, train_rouge2_precision_step=1.000, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.750, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.750, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.600, val_loss_step=0.793, val_rouge1_fmeasure_step=0.599, val_rouge1_precision_step=1.000, val_rouge1_recall_step=0.440, val_rouge2_fmeasure_step=0.356, val_rouge2_precision_step=0.667, val_rouge2_recall_step=0.250, val_rougeL_fmeasure_step=0.599, val_rougeL_precision_step=1.000, val_rougeL_recall_step=0.440, val_rougeLsum_fmeasure_step=0.599, val_rougeLsum_precision_step=1.000, val_rougeLsum_recall_step=0.440, val_loss_epoch=0.386, val_rouge1_fmeasure_epoch=0.545, val_rouge1_precision_epoch=1.000, val_rouge1_recall_epoch=0.428, val_rouge2_fmeasure_epoch=0.391, val_rouge2_precision_epoch=0.736, val_rouge2_recall_epoch=0.305, val_rougeL_fmeasure_epoch=0.545, val_rougeL_precision_epoch=1.000, val_rougeL_recall_epoch=0.428, val_rougeLsum_fmeasure_epoch=0.545, val_rougeLsum_precision_epoch=1.000, val_rougeLsum_recall_epoch=0.428, train_loss_epoch=0.510, train_rouge1_fmeasure_epoch=0.150, train_rouge1_precision_epoch=0.293, train_rouge1_recall_epoch=0.118, train_rouge2_fmeasure_epoch=0.0405, train_rouge2_precision_epoch=0.0738, train_rouge2_recall_epoch=0.0313, train_rougeL_fmeasure_epoch=0.147, train_rougeL_precision_epoch=0.290, train_rougeL_recall_epoch=0.115, train_rougeLsum_fmeasure_epoch=0.140, train_rougeLsum_precision_epoch=0.277, train_rougeLsum_recall_epoch=0.110]`Trainer.fit` stopped: `max_epochs=1` reached.

Epoch 0: 100%|██████████| 192/192 [02:17<00:00,  1.40it/s, v_num=9a_1, train_loss_step=0.0711, train_rouge1_fmeasure_step=0.750, train_rouge1_precision_step=1.000, train_rouge1_recall_step=0.600, train_rouge2_fmeasure_step=0.667, train_rouge2_precision_step=1.000, train_rouge2_recall_step=0.500, train_rougeL_fmeasure_step=0.750, train_rougeL_precision_step=1.000, train_rougeL_recall_step=0.600, train_rougeLsum_fmeasure_step=0.750, train_rougeLsum_precision_step=1.000, train_rougeLsum_recall_step=0.600, val_loss_step=0.793, val_rouge1_fmeasure_step=0.599, val_rouge1_precision_step=1.000, val_rouge1_recall_step=0.440, val_rouge2_fmeasure_step=0.356, val_rouge2_precision_step=0.667, val_rouge2_recall_step=0.250, val_rougeL_fmeasure_step=0.599, val_rougeL_precision_step=1.000, val_rougeL_recall_step=0.440, val_rougeLsum_fmeasure_step=0.599, val_rougeLsum_precision_step=1.000, val_rougeLsum_recall_step=0.440, val_loss_epoch=0.386, val_rouge1_fmeasure_epoch=0.545, val_rouge1_precision_epoch=1.000, val_rouge1_recall_epoch=0.428, val_rouge2_fmeasure_epoch=0.391, val_rouge2_precision_epoch=0.736, val_rouge2_recall_epoch=0.305, val_rougeL_fmeasure_epoch=0.545, val_rougeL_precision_epoch=1.000, val_rougeL_recall_epoch=0.428, val_rougeLsum_fmeasure_epoch=0.545, val_rougeLsum_precision_epoch=1.000, val_rougeLsum_recall_epoch=0.428, train_loss_epoch=0.510, train_rouge1_fmeasure_epoch=0.150, train_rouge1_precision_epoch=0.293, train_rouge1_recall_epoch=0.118, train_rouge2_fmeasure_epoch=0.0405, train_rouge2_precision_epoch=0.0738, train_rouge2_recall_epoch=0.0313, train_rougeL_fmeasure_epoch=0.147, train_rougeL_precision_epoch=0.290, train_rougeL_recall_epoch=0.115, train_rougeLsum_fmeasure_epoch=0.140, train_rougeLsum_precision_epoch=0.277, train_rougeLsum_recall_epoch=0.110]wandb: - 0.014 MB of 0.014 MB uploaded
wandb: \ 0.014 MB of 0.014 MB uploaded
wandb: | 0.014 MB of 0.014 MB uploaded
wandb: / 0.014 MB of 0.025 MB uploaded
wandb: - 0.014 MB of 0.025 MB uploaded
wandb: \ 0.025 MB of 0.025 MB uploaded
wandb:                                                                                
wandb: 
wandb: Run history:
wandb:                           epoch ▁▁▁▁▁
wandb:                    lr-PagedLion ▆█▁
wandb:                train_loss_epoch ▁
wandb:                 train_loss_step █▁█
wandb:     train_rouge1_fmeasure_epoch ▁
wandb:      train_rouge1_fmeasure_step ▁▁█
wandb:    train_rouge1_precision_epoch ▁
wandb:     train_rouge1_precision_step ▁▁█
wandb:       train_rouge1_recall_epoch ▁
wandb:        train_rouge1_recall_step ▁▁█
wandb:     train_rouge2_fmeasure_epoch ▁
wandb:      train_rouge2_fmeasure_step ▁▁▁
wandb:    train_rouge2_precision_epoch ▁
wandb:     train_rouge2_precision_step ▁▁▁
wandb:       train_rouge2_recall_epoch ▁
wandb:        train_rouge2_recall_step ▁▁▁
wandb:     train_rougeL_fmeasure_epoch ▁
wandb:      train_rougeL_fmeasure_step ▁▁█
wandb:    train_rougeL_precision_epoch ▁
wandb:     train_rougeL_precision_step ▁▁█
wandb:       train_rougeL_recall_epoch ▁
wandb:        train_rougeL_recall_step ▁▁█
wandb:  train_rougeLsum_fmeasure_epoch ▁
wandb:   train_rougeLsum_fmeasure_step ▁▁█
wandb: train_rougeLsum_precision_epoch ▁
wandb:  train_rougeLsum_precision_step ▁▁█
wandb:    train_rougeLsum_recall_epoch ▁
wandb:     train_rougeLsum_recall_step ▁▁█
wandb:             trainer/global_step ▃▃▅▅▆▆▁▁▁▁▁▁▁▁▁▁▁▁██
wandb:                  val_loss_epoch ▁
wandb:                   val_loss_step ▃▁▂▂▂█▂▁▁▁▁▄
wandb:       val_rouge1_fmeasure_epoch ▁
wandb:        val_rouge1_fmeasure_step ▄▆▃▃▃▁▇█▇▇▇▆
wandb:      val_rouge1_precision_epoch ▁
wandb:       val_rouge1_precision_step ▁▁▁▁▁▁▁▁▁▁▁▁
wandb:         val_rouge1_recall_epoch ▁
wandb:          val_rouge1_recall_step ▃▅▂▃▃▁▆█▆▇▇▅
wandb:       val_rouge2_fmeasure_epoch ▁
wandb:        val_rouge2_fmeasure_step ▃▄▂▂▂▁▆█▅▆▆▄
wandb:      val_rouge2_precision_epoch ▁
wandb:       val_rouge2_precision_step ▁▁▁▁▁▁▅█▁▅▅▁
wandb:         val_rouge2_recall_epoch ▁
wandb:          val_rouge2_recall_step ▂▃▂▂▂▁▅█▄▆▆▃
wandb:       val_rougeL_fmeasure_epoch ▁
wandb:        val_rougeL_fmeasure_step ▄▆▃▃▃▁▇█▇▇▇▆
wandb:      val_rougeL_precision_epoch ▁
wandb:       val_rougeL_precision_step ▁▁▁▁▁▁▁▁▁▁▁▁
wandb:         val_rougeL_recall_epoch ▁
wandb:          val_rougeL_recall_step ▃▅▂▃▃▁▆█▆▇▇▅
wandb:    val_rougeLsum_fmeasure_epoch ▁
wandb:     val_rougeLsum_fmeasure_step ▄▆▃▃▃▁▇█▇▇▇▆
wandb:   val_rougeLsum_precision_epoch ▁
wandb:    val_rougeLsum_precision_step ▁▁▁▁▁▁▁▁▁▁▁▁
wandb:      val_rougeLsum_recall_epoch ▁
wandb:       val_rougeLsum_recall_step ▃▅▂▃▃▁▆█▆▇▇▅
wandb: 
wandb: Run summary:
wandb:                           epoch 0
wandb:                    lr-PagedLion 1e-05
wandb:                train_loss_epoch 0.50961
wandb:                 train_loss_step 0.19961
wandb:     train_rouge1_fmeasure_epoch 0.14963
wandb:      train_rouge1_fmeasure_step 0.16667
wandb:    train_rouge1_precision_epoch 0.29329
wandb:     train_rouge1_precision_step 0.33333
wandb:       train_rouge1_recall_epoch 0.11779
wandb:        train_rouge1_recall_step 0.11111
wandb:     train_rouge2_fmeasure_epoch 0.04048
wandb:      train_rouge2_fmeasure_step 0.0
wandb:    train_rouge2_precision_epoch 0.07378
wandb:     train_rouge2_precision_step 0.0
wandb:       train_rouge2_recall_epoch 0.03132
wandb:        train_rouge2_recall_step 0.0
wandb:     train_rougeL_fmeasure_epoch 0.14714
wandb:      train_rougeL_fmeasure_step 0.16667
wandb:    train_rougeL_precision_epoch 0.28968
wandb:     train_rougeL_precision_step 0.33333
wandb:       train_rougeL_recall_epoch 0.11543
wandb:        train_rougeL_recall_step 0.11111
wandb:  train_rougeLsum_fmeasure_epoch 0.13952
wandb:   train_rougeLsum_fmeasure_step 0.16667
wandb: train_rougeLsum_precision_epoch 0.27658
wandb:  train_rougeLsum_precision_step 0.33333
wandb:    train_rougeLsum_recall_epoch 0.10955
wandb:     train_rougeLsum_recall_step 0.11111
wandb:             trainer/global_step 191
wandb:                  val_loss_epoch 0.3865
wandb:                   val_loss_step 0.79297
wandb:       val_rouge1_fmeasure_epoch 0.54495
wandb:        val_rouge1_fmeasure_step 0.59893
wandb:      val_rouge1_precision_epoch 1.0
wandb:       val_rouge1_precision_step 1.0
wandb:         val_rouge1_recall_epoch 0.4281
wandb:          val_rouge1_recall_step 0.43956
wandb:       val_rouge2_fmeasure_epoch 0.3909
wandb:        val_rouge2_fmeasure_step 0.35556
wandb:      val_rouge2_precision_epoch 0.73611
wandb:       val_rouge2_precision_step 0.66667
wandb:         val_rouge2_recall_epoch 0.30488
wandb:          val_rouge2_recall_step 0.25
wandb:       val_rougeL_fmeasure_epoch 0.54495
wandb:        val_rougeL_fmeasure_step 0.59893
wandb:      val_rougeL_precision_epoch 1.0
wandb:       val_rougeL_precision_step 1.0
wandb:         val_rougeL_recall_epoch 0.4281
wandb:          val_rougeL_recall_step 0.43956
wandb:    val_rougeLsum_fmeasure_epoch 0.54495
wandb:     val_rougeLsum_fmeasure_step 0.59893
wandb:   val_rougeLsum_precision_epoch 1.0
wandb:    val_rougeLsum_precision_step 1.0
wandb:      val_rougeLsum_recall_epoch 0.4281
wandb:       val_rougeLsum_recall_step 0.43956
wandb: 
wandb: 🚀 View run chocolate-sweep-6 at: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/iz24uc9a
wandb: ⭐️ View project at: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)
wandb: Find logs at: ./wandb/run-20240806_140206-iz24uc9a/logs
wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information.
wandb: Agent Starting Run: yal4wup5 with config:
wandb: 	accumulate_grad_batches: 2
wandb: 	epochs: 1
wandb: 	gradient_clip_val: 0.7997351101275753
wandb: 	init_lora_weights: loftq
wandb: 	lora_alpha: 64
wandb: 	lora_dropout: 0.07665943005300253
wandb: 	lora_rank: 8
wandb: 	lr: 6.477116281072834e-05
wandb: 	model_name: mistralai/Mistral-7B-Instruct-v0.3
wandb: WARNING Ignored wandb.init() arg project when running a sweep.
wandb: Tracking run with wandb version 0.17.5
wandb: Run data is saved locally in /user/jonathan/wandb/run-20240806_140745-yal4wup5
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run snowy-sweep-7
wandb: ⭐️ View project at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: 🧹 View sweep at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/sweeps/4ik6ex9z
wandb: 🚀 View run at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/yal4wup5
Unused kwargs: ['bnb_8bit_quant_type', 'bnb_8bit_compute_dtype']. These kwargs are not used in <class 'transformers.utils.quantization_config.BitsAndBytesConfig'>.
Repo card metadata block was not found. Setting CardData to empty.
WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty.


Map:   0%|          | 0/960 [00:00<?, ? examples/s]Asking to truncate to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no truncation.

Map: 100%|██████████| 960/960 [00:00<00:00, 7690.93 examples/s]
Map: 100%|██████████| 960/960 [00:00<00:00, 6509.79 examples/s]

Map:   0%|          | 0/960 [00:00<?, ? examples/s]
Map:   0%|          | 0/960 [00:00<?, ? examples/s]
wandb: - 0.014 MB of 0.014 MB uploaded
wandb: \ 0.014 MB of 0.014 MB uploaded
wandb: | 0.014 MB of 0.014 MB uploaded
wandb: / 0.014 MB of 0.020 MB uploaded
wandb: - 0.014 MB of 0.020 MB uploaded
wandb: \ 0.020 MB of 0.020 MB uploaded
wandb:                                                                                
wandb: 🚀 View run snowy-sweep-7 at: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/yal4wup5
wandb: ⭐️ View project at: https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)
wandb: Find logs at: ./wandb/run-20240806_140745-yal4wup5/logs
wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information.
Run yal4wup5 errored:
Traceback (most recent call last):
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/wandb/agents/pyagent.py", line 307, in _run_job
    self._function()
  File "/user/jonathan/l_sweep.py", line 50, in l2ray_trainer
    dataset = get_dataset(dataset_name=dataset_path, tokenizer=tokenizer)
  File "/user/jonathan/finetuning_datasets.py", line 40, in get_dataset
    en_dataset = raw_dataset.map(
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/dataset_dict.py", line 869, in map
    {
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/dataset_dict.py", line 870, in <dictcomp>
    k: dataset.map(
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 602, in wrapper
    out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 567, in wrapper
    out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3161, in map
    for rank, done, content in Dataset._map_single(**dataset_kwargs):
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3552, in _map_single
    batch = apply_function_on_filtered_inputs(
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3421, in apply_function_on_filtered_inputs
    processed_inputs = function(*fn_args, *additional_args, **fn_kwargs)
  File "/user/jonathan/finetuning_datafunctions.py", line 65, in preprocess_function
    templated_text, labels = formatting(sample=sample,
  File "/user/jonathan/finetuning_datafunctions.py", line 38, in formatting
    bot_message = tokenizer.apply_chat_template(conversation=label_template,
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1855, in apply_chat_template
    rendered_chat = compiled_template.render(
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/environment.py", line 1304, in render
    self.environment.handle_exception()
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/environment.py", line 939, in handle_exception
    raise rewrite_traceback_stack(source=source)
  File "<template>", line 14, in top-level template code
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/sandbox.py", line 394, in call
    return __context.call(__obj, *args, **kwargs)
  File "/user/jonathan/jonathan/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1899, in raise_exception
    raise TemplateError(message)
jinja2.exceptions.TemplateError: After the optional system message, conversation roles must alternate user/assistant/user/assistant/...

wandb: ERROR Run yal4wup5 errored:
wandb: ERROR Traceback (most recent call last):
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/wandb/agents/pyagent.py", line 307, in _run_job
wandb: ERROR     self._function()
wandb: ERROR   File "/user/jonathan/l_sweep.py", line 50, in l2ray_trainer
wandb: ERROR     dataset = get_dataset(dataset_name=dataset_path, tokenizer=tokenizer)
wandb: ERROR   File "/user/jonathan/finetuning_datasets.py", line 40, in get_dataset
wandb: ERROR     en_dataset = raw_dataset.map(
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/dataset_dict.py", line 869, in map
wandb: ERROR     {
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/dataset_dict.py", line 870, in <dictcomp>
wandb: ERROR     k: dataset.map(
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 602, in wrapper
wandb: ERROR     out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 567, in wrapper
wandb: ERROR     out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3161, in map
wandb: ERROR     for rank, done, content in Dataset._map_single(**dataset_kwargs):
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3552, in _map_single
wandb: ERROR     batch = apply_function_on_filtered_inputs(
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3421, in apply_function_on_filtered_inputs
wandb: ERROR     processed_inputs = function(*fn_args, *additional_args, **fn_kwargs)
wandb: ERROR   File "/user/jonathan/finetuning_datafunctions.py", line 65, in preprocess_function
wandb: ERROR     templated_text, labels = formatting(sample=sample,
wandb: ERROR   File "/user/jonathan/finetuning_datafunctions.py", line 38, in formatting
wandb: ERROR     bot_message = tokenizer.apply_chat_template(conversation=label_template,
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1855, in apply_chat_template
wandb: ERROR     rendered_chat = compiled_template.render(
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/environment.py", line 1304, in render
wandb: ERROR     self.environment.handle_exception()
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/environment.py", line 939, in handle_exception
wandb: ERROR     raise rewrite_traceback_stack(source=source)
wandb: ERROR   File "<template>", line 14, in top-level template code
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/jinja2/sandbox.py", line 394, in call
wandb: ERROR     return __context.call(__obj, *args, **kwargs)
wandb: ERROR   File "/user/jonathan/jonathan/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1899, in raise_exception
wandb: ERROR     raise TemplateError(message)
wandb: ERROR jinja2.exceptions.TemplateError: After the optional system message, conversation roles must alternate user/assistant/user/assistant/...
wandb: ERROR 
wandb: Agent Starting Run: sdukfiai with config:
wandb: 	accumulate_grad_batches: 8
wandb: 	epochs: 1
wandb: 	gradient_clip_val: 0.6215211095494333
wandb: 	init_lora_weights: pissa
wandb: 	lora_alpha: 128
wandb: 	lora_dropout: 0.07980021035260737
wandb: 	lora_rank: 16
wandb: 	lr: 0.0004110872288961411
wandb: 	model_name: mistralai/Mistral-7B-Instruct-v0.3
wandb: WARNING Ignored wandb.init() arg project when running a sweep.
wandb: Tracking run with wandb version 0.17.5
wandb: Run data is saved locally in /user/jonathan/wandb/run-20240806_140823-sdukfiai
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run snowy-sweep-8
wandb: ⭐️ View project at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning
wandb: 🧹 View sweep at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/sweeps/4ik6ex9z
wandb: 🚀 View run at https://wandb.ai/j0ntendo-yonsei-university/LLM-Finetuning/runs/sdukfiai
Unused kwargs: ['bnb_8bit_quant_type', 'bnb_8bit_compute_dtype']. These kwargs are not used in <class 'transformers.utils.quantization_config.BitsAndBytesConfig'>.