20250513_010808.log

[2025-05-13 01:08:08] Created output directory: train_results/google_t5-v1_1-large_ds100_upsample1000
[2025-05-13 01:08:08] Chat mode disabled
[2025-05-13 01:08:08] Model size is 3B or smaller (0 B). Using full fine-tuning.
[2025-05-13 01:08:08] Adjusted parameters for t5 model:
[2025-05-13 01:08:08]   - LEARNING_RATE: 1e-4
[2025-05-13 01:08:08]   - BATCH_SIZE: 64
[2025-05-13 01:08:08]   - GRADIENT_ACCUMULATION_STEPS: 1
[2025-05-13 01:08:08] No QA format data will be used
[2025-05-13 01:08:08] Limiting dataset size to: 100 samples
[2025-05-13 01:08:08] =======================================
[2025-05-13 01:08:08] Starting training for model: google/t5-v1_1-large
[2025-05-13 01:08:08] =======================================
[2025-05-13 01:08:08] CUDA_VISIBLE_DEVICES: 2,3
[2025-05-13 01:08:08] WANDB_PROJECT: wikidyk-ar
[2025-05-13 01:08:08] DATA_PATH: data/wikidyk2022-2025_01082025_gpt-4o_evalv2_pages_formatted_combined_v2.json
[2025-05-13 01:08:08] Global Batch Size: 128
[2025-05-13 01:08:08] Data Size: 100
[2025-05-13 01:08:08] Executing command: torchrun --nproc_per_node "2" --master-port 29501 src/train.py       --model_name_or_path "google/t5-v1_1-large"       --data_path "data/wikidyk2022-2025_01082025_gpt-4o_evalv2_pages_formatted_combined_v2.json"       --output_dir "train_results/google_t5-v1_1-large_ds100_upsample1000"       --num_upsample "1000"       --per_device_train_batch_size "64"       --gradient_accumulation_steps "1"       --learning_rate "1e-4"       --num_train_epochs "1"       --model_max_length "32768"       --report_to wandb --logging_steps 50 --save_strategy no       --bf16 True --use_flash_attention_2 True       --qa_data_ratio "-1"       --predict_mask "false"                            --ds_size 100
[2025-05-13 01:08:08] Training started at Tue May 13 01:08:08 UTC 2025
W0513 01:08:10.171000 443637 site-packages/torch/distributed/run.py:792] 
W0513 01:08:10.171000 443637 site-packages/torch/distributed/run.py:792] *****************************************
W0513 01:08:10.171000 443637 site-packages/torch/distributed/run.py:792] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
W0513 01:08:10.171000 443637 site-packages/torch/distributed/run.py:792] *****************************************
WARNING:root:Output directory: train_results/google_t5-v1_1-large_ds100_upsample1000
WARNING:root:Output directory: train_results/google_t5-v1_1-large_ds100_upsample1000
You are using the default legacy behaviour of the <class 'transformers.models.t5.tokenization_t5.T5Tokenizer'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565
You are using the default legacy behaviour of the <class 'transformers.models.t5.tokenization_t5.T5Tokenizer'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565
WARNING:root:Loading data...
WARNING:root:Loading data...
WARNING:root:Dataset initialized with all QA data:
WARNING:root:  - 0 QA examples
WARNING:root:  - 100 fact examples with upsampling factor 1000
WARNING:root:  - Total examples: 100000
WARNING:root:Dataset initialized with all QA data:
WARNING:root:  - 0 QA examples
WARNING:root:  - 100 fact examples with upsampling factor 1000
WARNING:root:  - Total examples: 100000
/root/yuwei/WikiDYKEvalV2/src/train.py:119: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
  trainer = Trainer(model=model, tokenizer=tokenizer, args=training_args, **data_module)
/root/yuwei/WikiDYKEvalV2/src/train.py:119: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
  trainer = Trainer(model=model, tokenizer=tokenizer, args=training_args, **data_module)
wandb: WARNING The `run_name` is currently set to the same value as `TrainingArguments.output_dir`. If this was not intended, please specify a different run name by setting the `TrainingArguments.run_name` parameter.
/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/transformers/tokenization_utils_base.py:3980: UserWarning: `as_target_tokenizer` is deprecated and will be removed in v5 of Transformers. You can tokenize your labels by using the argument `text_target` of the regular `__call__` method (either in the same call as your input texts if you use the same keyword arguments, or in a separate call.
  warnings.warn(
wandb: Currently logged in as: yuweiz to https://api.wandb.ai. Use `wandb login --relogin` to force relogin
Passing a tuple of `past_key_values` is deprecated and will be removed in Transformers v4.48.0. You should pass an instance of `EncoderDecoderCache` instead, e.g. `past_key_values=EncoderDecoderCache.from_legacy_cache(past_key_values)`.
[rank1]:[W513 01:08:40.694530638 reducer.cpp:1400] Warning: find_unused_parameters=True was specified in DDP constructor, but did not find any unused parameters in the forward pass. This flag results in an extra traversal of the autograd graph every iteration,  which can adversely affect performance. If your model indeed never has any unused parameters in the forward pass, consider turning this flag off. Note that this warning may be a false positive if your model has flow control causing later iterations to have unused parameters. (function operator())
wandb: Tracking run with wandb version 0.19.11
wandb: Run data is saved locally in /root/yuwei/WikiDYKEvalV2/wandb/run-20250513_010840-ovxz0tx6
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run train_results/google_t5-v1_1-large_ds100_upsample1000
wandb: ⭐️ View project at https://wandb.ai/yuweiz/wikidyk-ar
wandb: 🚀 View run at https://wandb.ai/yuweiz/wikidyk-ar/runs/ovxz0tx6

  0%|          | 0/782 [00:00<?, ?it/s]/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/transformers/tokenization_utils_base.py:3980: UserWarning: `as_target_tokenizer` is deprecated and will be removed in v5 of Transformers. You can tokenize your labels by using the argument `text_target` of the regular `__call__` method (either in the same call as your input texts if you use the same keyword arguments, or in a separate call.
  warnings.warn(
Passing a tuple of `past_key_values` is deprecated and will be removed in Transformers v4.48.0. You should pass an instance of `EncoderDecoderCache` instead, e.g. `past_key_values=EncoderDecoderCache.from_legacy_cache(past_key_values)`.
[rank0]:[W513 01:08:40.426723468 reducer.cpp:1400] Warning: find_unused_parameters=True was specified in DDP constructor, but did not find any unused parameters in the forward pass. This flag results in an extra traversal of the autograd graph every iteration,  which can adversely affect performance. If your model indeed never has any unused parameters in the forward pass, consider turning this flag off. Note that this warning may be a false positive if your model has flow control causing later iterations to have unused parameters. (function operator())

  0%|          | 1/782 [00:00<11:29,  1.13it/s]
  0%|          | 2/782 [00:02<15:37,  1.20s/it]
  0%|          | 3/782 [00:02<11:24,  1.14it/s]
  1%|          | 4/782 [00:03<09:45,  1.33it/s]
  1%|          | 5/782 [00:03<08:53,  1.46it/s]
  1%|          | 6/782 [00:04<07:57,  1.62it/s]
  1%|          | 7/782 [00:05<10:15,  1.26it/s]
  1%|          | 8/782 [00:06<09:03,  1.42it/s]
  1%|          | 9/782 [00:06<08:31,  1.51it/s]
  1%|▏         | 10/782 [00:07<08:10,  1.57it/s]
  1%|▏         | 11/782 [00:07<07:35,  1.69it/s]
  2%|▏         | 12/782 [00:08<07:17,  1.76it/s]
  2%|▏         | 13/782 [00:08<07:22,  1.74it/s]
  2%|▏         | 14/782 [00:09<07:07,  1.80it/s]
  2%|▏         | 15/782 [00:09<06:59,  1.83it/s]
  2%|▏         | 16/782 [00:10<06:50,  1.87it/s]
  2%|▏         | 17/782 [00:10<06:54,  1.85it/s]
  2%|▏         | 18/782 [00:11<06:49,  1.87it/s]
  2%|▏         | 19/782 [00:11<06:42,  1.90it/s]
  3%|▎         | 20/782 [00:12<06:51,  1.85it/s]
  3%|▎         | 21/782 [00:13<06:52,  1.85it/s]
  3%|▎         | 22/782 [00:13<06:37,  1.91it/s]
  3%|▎         | 23/782 [00:14<06:56,  1.82it/s]
  3%|▎         | 24/782 [00:14<06:59,  1.81it/s]
  3%|▎         | 25/782 [00:15<06:37,  1.90it/s]
  3%|▎         | 26/782 [00:15<06:40,  1.89it/s]
  3%|▎         | 27/782 [00:16<06:50,  1.84it/s]
  4%|▎         | 28/782 [00:16<06:48,  1.85it/s]
  4%|▎         | 29/782 [00:17<06:40,  1.88it/s]
  4%|▍         | 30/782 [00:17<06:41,  1.87it/s]
  4%|▍         | 31/782 [00:18<06:38,  1.89it/s]
  4%|▍         | 32/782 [00:18<06:35,  1.89it/s]
  4%|▍         | 33/782 [00:19<06:40,  1.87it/s]
  4%|▍         | 34/782 [00:19<06:34,  1.89it/s]
  4%|▍         | 35/782 [00:20<06:34,  1.90it/s]
  5%|▍         | 36/782 [00:21<06:40,  1.86it/s]
  5%|▍         | 37/782 [00:21<06:29,  1.91it/s]
  5%|▍         | 38/782 [00:22<08:52,  1.40it/s]
  5%|▍         | 39/782 [00:23<08:07,  1.52it/s]
  5%|▌         | 40/782 [00:23<07:41,  1.61it/s]
  5%|▌         | 41/782 [00:24<07:14,  1.71it/s]
  5%|▌         | 42/782 [00:24<06:50,  1.80it/s]
  5%|▌         | 43/782 [00:25<06:53,  1.79it/s]
  6%|▌         | 44/782 [00:25<07:05,  1.74it/s]
  6%|▌         | 45/782 [00:26<06:50,  1.80it/s]
  6%|▌         | 46/782 [00:27<06:47,  1.81it/s]
  6%|▌         | 47/782 [00:27<06:47,  1.80it/s]
  6%|▌         | 48/782 [00:28<06:53,  1.78it/s]
  6%|▋         | 49/782 [00:28<06:33,  1.86it/s]
  6%|▋         | 50/782 [00:29<06:33,  1.86it/s]
                                                
{'loss': 28.359, 'grad_norm': 74.1916732788086, 'learning_rate': 9.373401534526855e-05, 'epoch': 0.06}

  6%|▋         | 50/782 [00:29<06:33,  1.86it/s]
  7%|▋         | 51/782 [00:29<06:53,  1.77it/s]
  7%|▋         | 52/782 [00:30<06:49,  1.78it/s]
  7%|▋         | 53/782 [00:30<06:34,  1.85it/s]
  7%|▋         | 54/782 [00:31<06:31,  1.86it/s]
  7%|▋         | 55/782 [00:32<06:50,  1.77it/s]
  7%|▋         | 56/782 [00:32<06:42,  1.80it/s]
  7%|▋         | 57/782 [00:33<06:32,  1.85it/s]
  7%|▋         | 58/782 [00:33<06:25,  1.88it/s]
  8%|▊         | 59/782 [00:34<06:32,  1.84it/s]
  8%|▊         | 60/782 [00:34<06:28,  1.86it/s]
  8%|▊         | 61/782 [00:35<06:18,  1.90it/s]
  8%|▊         | 62/782 [00:36<08:41,  1.38it/s]
  8%|▊         | 63/782 [00:36<08:00,  1.50it/s]
  8%|▊         | 64/782 [00:37<07:31,  1.59it/s]
  8%|▊         | 65/782 [00:37<06:59,  1.71it/s]
  8%|▊         | 66/782 [00:38<06:56,  1.72it/s]
  9%|▊         | 67/782 [00:39<06:52,  1.73it/s]
  9%|▊         | 68/782 [00:39<06:35,  1.81it/s]
  9%|▉         | 69/782 [00:40<06:38,  1.79it/s]
  9%|▉         | 70/782 [00:40<06:58,  1.70it/s]
  9%|▉         | 71/782 [00:41<06:36,  1.79it/s]
  9%|▉         | 72/782 [00:41<06:26,  1.84it/s]
  9%|▉         | 73/782 [00:42<06:22,  1.85it/s]
  9%|▉         | 74/782 [00:42<06:24,  1.84it/s]
 10%|▉         | 75/782 [00:43<06:24,  1.84it/s]
 10%|▉         | 76/782 [00:43<06:30,  1.81it/s]
 10%|▉         | 77/782 [00:44<06:43,  1.75it/s]
 10%|▉         | 78/782 [00:45<06:40,  1.76it/s]
 10%|█         | 79/782 [00:45<06:28,  1.81it/s]
 10%|█         | 80/782 [00:46<06:27,  1.81it/s]
 10%|█         | 81/782 [00:46<06:33,  1.78it/s]
 10%|█         | 82/782 [00:47<06:17,  1.85it/s]
 11%|█         | 83/782 [00:47<06:09,  1.89it/s]
 11%|█         | 84/782 [00:48<06:09,  1.89it/s]
 11%|█         | 85/782 [00:48<06:16,  1.85it/s]
 11%|█         | 86/782 [00:49<06:16,  1.85it/s]
 11%|█         | 87/782 [00:49<06:07,  1.89it/s]
 11%|█▏        | 88/782 [00:50<06:10,  1.87it/s]
 11%|█▏        | 89/782 [00:50<06:07,  1.89it/s]
 12%|█▏        | 90/782 [00:51<06:02,  1.91it/s]
 12%|█▏        | 91/782 [00:52<06:33,  1.76it/s]
 12%|█▏        | 92/782 [00:53<09:21,  1.23it/s]
 12%|█▏        | 93/782 [00:54<08:28,  1.35it/s]
 12%|█▏        | 94/782 [00:54<07:33,  1.52it/s]
 12%|█▏        | 95/782 [00:55<07:15,  1.58it/s]
 12%|█▏        | 96/782 [00:55<07:19,  1.56it/s]
 12%|█▏        | 97/782 [00:56<06:48,  1.68it/s]
 13%|█▎        | 98/782 [00:56<06:40,  1.71it/s]
 13%|█▎        | 99/782 [00:57<06:28,  1.76it/s]
 13%|█▎        | 100/782 [00:57<06:23,  1.78it/s]
                                                 
{'loss': 19.0603, 'grad_norm': 20.285858154296875, 'learning_rate': 8.734015345268543e-05, 'epoch': 0.13}

 13%|█▎        | 100/782 [00:58<06:23,  1.78it/s]
 13%|█▎        | 101/782 [00:58<06:15,  1.81it/s]
 13%|█▎        | 102/782 [00:59<06:08,  1.84it/s]
 13%|█▎        | 103/782 [00:59<06:12,  1.82it/s]
 13%|█▎        | 104/782 [01:00<06:14,  1.81it/s]
 13%|█▎        | 105/782 [01:00<06:01,  1.87it/s]
 14%|█▎        | 106/782 [01:01<05:58,  1.88it/s]
 14%|█▎        | 107/782 [01:01<06:06,  1.84it/s]
 14%|█▍        | 108/782 [01:02<05:53,  1.91it/s]
 14%|█▍        | 109/782 [01:02<05:59,  1.87it/s]
 14%|█▍        | 110/782 [01:03<06:05,  1.84it/s]
 14%|█▍        | 111/782 [01:03<05:54,  1.89it/s]
 14%|█▍        | 112/782 [01:04<05:57,  1.87it/s]
 14%|█▍        | 113/782 [01:04<06:02,  1.85it/s]
 15%|█▍        | 114/782 [01:05<05:52,  1.89it/s]
 15%|█▍        | 115/782 [01:05<05:59,  1.85it/s]
 15%|█▍        | 116/782 [01:06<06:02,  1.84it/s]
 15%|█▍        | 117/782 [01:07<05:49,  1.90it/s]
 15%|█▌        | 118/782 [01:07<05:57,  1.86it/s]
 15%|█▌        | 119/782 [01:08<06:02,  1.83it/s]
 15%|█▌        | 120/782 [01:08<05:54,  1.87it/s]
 15%|█▌        | 121/782 [01:09<05:52,  1.88it/s]
 16%|█▌        | 122/782 [01:09<06:00,  1.83it/s]
 16%|█▌        | 123/782 [01:10<05:54,  1.86it/s]
 16%|█▌        | 124/782 [01:10<05:49,  1.89it/s]
 16%|█▌        | 125/782 [01:11<05:45,  1.90it/s]
 16%|█▌        | 126/782 [01:11<05:49,  1.88it/s]
 16%|█▌        | 127/782 [01:12<05:41,  1.92it/s]
 16%|█▋        | 128/782 [01:12<05:33,  1.96it/s]
 16%|█▋        | 129/782 [01:13<05:43,  1.90it/s]
 17%|█▋        | 130/782 [01:13<05:48,  1.87it/s]
 17%|█▋        | 131/782 [01:14<05:36,  1.94it/s]
 17%|█▋        | 132/782 [01:14<05:44,  1.89it/s]
 17%|█▋        | 133/782 [01:15<05:58,  1.81it/s]
 17%|█▋        | 134/782 [01:16<05:47,  1.87it/s]
 17%|█▋        | 135/782 [01:16<05:53,  1.83it/s]
 17%|█▋        | 136/782 [01:17<06:16,  1.72it/s]
 18%|█▊        | 137/782 [01:17<05:56,  1.81it/s]
 18%|█▊        | 138/782 [01:18<05:55,  1.81it/s]
 18%|█▊        | 139/782 [01:18<06:02,  1.77it/s]
 18%|█▊        | 140/782 [01:19<05:45,  1.86it/s]
 18%|█▊        | 141/782 [01:19<05:41,  1.88it/s]
 18%|█▊        | 142/782 [01:20<05:41,  1.88it/s]
 18%|█▊        | 143/782 [01:20<05:35,  1.91it/s]
 18%|█▊        | 144/782 [01:21<05:34,  1.91it/s]
 19%|█▊        | 145/782 [01:22<05:32,  1.92it/s]
 19%|█▊        | 146/782 [01:22<05:53,  1.80it/s]
 19%|█▉        | 147/782 [01:23<05:42,  1.86it/s]
 19%|█▉        | 148/782 [01:23<05:40,  1.86it/s]
 19%|█▉        | 149/782 [01:24<05:44,  1.84it/s]
 19%|█▉        | 150/782 [01:24<05:44,  1.84it/s]
                                                 
{'loss': 15.0203, 'grad_norm': 185.91448974609375, 'learning_rate': 8.094629156010231e-05, 'epoch': 0.19}

 19%|█▉        | 150/782 [01:24<05:44,  1.84it/s]
 19%|█▉        | 151/782 [01:25<05:36,  1.87it/s]
 19%|█▉        | 152/782 [01:25<05:39,  1.86it/s]
 20%|█▉        | 153/782 [01:26<05:49,  1.80it/s]
 20%|█▉        | 154/782 [01:26<05:34,  1.88it/s]
 20%|█▉        | 155/782 [01:27<05:42,  1.83it/s]
 20%|█▉        | 156/782 [01:28<05:57,  1.75it/s]
 20%|██        | 157/782 [01:28<05:43,  1.82it/s]
 20%|██        | 158/782 [01:29<05:38,  1.85it/s]
 20%|██        | 159/782 [01:29<05:47,  1.79it/s]
 20%|██        | 160/782 [01:30<05:37,  1.84it/s]
 21%|██        | 161/782 [01:30<05:37,  1.84it/s]
 21%|██        | 162/782 [01:31<05:53,  1.75it/s]
 21%|██        | 163/782 [01:31<05:43,  1.80it/s]
 21%|██        | 164/782 [01:32<05:34,  1.85it/s]
 21%|██        | 165/782 [01:32<05:27,  1.88it/s]
 21%|██        | 166/782 [01:33<05:31,  1.86it/s]
 21%|██▏       | 167/782 [01:34<05:51,  1.75it/s]
 21%|██▏       | 168/782 [01:34<05:29,  1.86it/s]
 22%|██▏       | 169/782 [01:35<05:31,  1.85it/s]
 22%|██▏       | 170/782 [01:35<05:39,  1.80it/s]
 22%|██▏       | 171/782 [01:36<05:23,  1.89it/s]
 22%|██▏       | 172/782 [01:36<05:27,  1.86it/s]
 22%|██▏       | 173/782 [01:37<05:29,  1.85it/s]
 22%|██▏       | 174/782 [01:37<05:31,  1.84it/s]
 22%|██▏       | 175/782 [01:38<05:23,  1.88it/s]
 23%|██▎       | 176/782 [01:38<05:26,  1.86it/s]
 23%|██▎       | 177/782 [01:39<05:23,  1.87it/s]
 23%|██▎       | 178/782 [01:40<05:23,  1.86it/s]
 23%|██▎       | 179/782 [01:40<05:17,  1.90it/s]
 23%|██▎       | 180/782 [01:41<05:24,  1.86it/s]
 23%|██▎       | 181/782 [01:41<05:21,  1.87it/s]
 23%|██▎       | 182/782 [01:42<05:21,  1.87it/s]
 23%|██▎       | 183/782 [01:42<05:22,  1.86it/s]
 24%|██▎       | 184/782 [01:43<05:19,  1.87it/s]
 24%|██▎       | 185/782 [01:43<05:20,  1.86it/s]
 24%|██▍       | 186/782 [01:44<05:28,  1.82it/s]
 24%|██▍       | 187/782 [01:44<05:18,  1.87it/s]
 24%|██▍       | 188/782 [01:45<05:15,  1.89it/s]
 24%|██▍       | 189/782 [01:45<05:16,  1.87it/s]
 24%|██▍       | 190/782 [01:46<05:16,  1.87it/s]
 24%|██▍       | 191/782 [01:46<05:12,  1.89it/s]
 25%|██▍       | 192/782 [01:47<05:29,  1.79it/s]
 25%|██▍       | 193/782 [01:48<05:26,  1.81it/s]
 25%|██▍       | 194/782 [01:48<05:18,  1.84it/s]
 25%|██▍       | 195/782 [01:49<05:22,  1.82it/s]
 25%|██▌       | 196/782 [01:49<05:20,  1.83it/s]
 25%|██▌       | 197/782 [01:50<05:10,  1.88it/s]
 25%|██▌       | 198/782 [01:50<05:15,  1.85it/s]
 25%|██▌       | 199/782 [01:51<05:31,  1.76it/s]
 26%|██▌       | 200/782 [01:51<05:20,  1.81it/s]
                                                 
{'loss': 13.3998, 'grad_norm': 26.281652450561523, 'learning_rate': 7.455242966751919e-05, 'epoch': 0.26}

 26%|██▌       | 200/782 [01:52<05:20,  1.81it/s]
 26%|██▌       | 201/782 [01:52<05:17,  1.83it/s]
 26%|██▌       | 202/782 [01:53<05:25,  1.78it/s]
 26%|██▌       | 203/782 [01:53<05:12,  1.85it/s]
 26%|██▌       | 204/782 [01:54<05:13,  1.84it/s]
 26%|██▌       | 205/782 [01:54<05:23,  1.79it/s]
 26%|██▋       | 206/782 [01:55<05:07,  1.87it/s]
 26%|██▋       | 207/782 [01:55<05:09,  1.86it/s]
 27%|██▋       | 208/782 [01:56<05:20,  1.79it/s]
 27%|██▋       | 209/782 [01:56<05:12,  1.83it/s]
 27%|██▋       | 210/782 [01:57<05:05,  1.87it/s]
 27%|██▋       | 211/782 [01:57<05:03,  1.88it/s]
 27%|██▋       | 212/782 [01:58<05:05,  1.86it/s]
 27%|██▋       | 213/782 [01:59<05:15,  1.80it/s]
 27%|██▋       | 214/782 [01:59<05:02,  1.88it/s]
 27%|██▋       | 215/782 [02:00<05:07,  1.85it/s]
 28%|██▊       | 216/782 [02:00<05:14,  1.80it/s]
 28%|██▊       | 217/782 [02:01<05:02,  1.87it/s]
 28%|██▊       | 218/782 [02:01<05:03,  1.86it/s]
 28%|██▊       | 219/782 [02:02<05:09,  1.82it/s]
 28%|██▊       | 220/782 [02:02<04:59,  1.88it/s]
 28%|██▊       | 221/782 [02:03<04:57,  1.89it/s]
 28%|██▊       | 222/782 [02:03<04:51,  1.92it/s]
 29%|██▊       | 223/782 [02:04<04:56,  1.89it/s]
 29%|██▊       | 224/782 [02:04<04:56,  1.88it/s]
 29%|██▉       | 225/782 [02:05<04:48,  1.93it/s]
 29%|██▉       | 226/782 [02:05<04:55,  1.88it/s]
 29%|██▉       | 227/782 [02:06<05:02,  1.83it/s]
 29%|██▉       | 228/782 [02:07<04:53,  1.89it/s]
 29%|██▉       | 229/782 [02:07<04:54,  1.87it/s]
 29%|██▉       | 230/782 [02:08<05:09,  1.78it/s]
 30%|██▉       | 231/782 [02:08<04:57,  1.85it/s]
 30%|██▉       | 232/782 [02:09<04:58,  1.84it/s]
 30%|██▉       | 233/782 [02:09<05:01,  1.82it/s]
 30%|██▉       | 234/782 [02:10<04:59,  1.83it/s]
 30%|███       | 235/782 [02:10<04:55,  1.85it/s]
 30%|███       | 236/782 [02:11<04:54,  1.85it/s]
 30%|███       | 237/782 [02:11<04:55,  1.84it/s]
 30%|███       | 238/782 [02:12<04:45,  1.90it/s]
 31%|███       | 239/782 [02:12<04:47,  1.89it/s]
 31%|███       | 240/782 [02:13<04:52,  1.86it/s]
 31%|███       | 241/782 [02:14<04:54,  1.84it/s]
 31%|███       | 242/782 [02:14<04:39,  1.93it/s]
 31%|███       | 243/782 [02:15<04:43,  1.90it/s]
 31%|███       | 244/782 [02:15<05:08,  1.74it/s]
 31%|███▏      | 245/782 [02:16<04:53,  1.83it/s]
 31%|███▏      | 246/782 [02:16<04:51,  1.84it/s]
 32%|███▏      | 247/782 [02:17<04:48,  1.86it/s]
 32%|███▏      | 248/782 [02:17<04:54,  1.81it/s]
 32%|███▏      | 249/782 [02:18<04:53,  1.82it/s]
 32%|███▏      | 250/782 [02:18<04:40,  1.90it/s]
                                                 
{'loss': 12.2939, 'grad_norm': 15.767915725708008, 'learning_rate': 6.815856777493607e-05, 'epoch': 0.32}

 32%|███▏      | 250/782 [02:19<04:40,  1.90it/s]
 32%|███▏      | 251/782 [02:19<04:45,  1.86it/s]
 32%|███▏      | 252/782 [02:20<04:51,  1.82it/s]
 32%|███▏      | 253/782 [02:20<04:42,  1.87it/s]
 32%|███▏      | 254/782 [02:21<04:40,  1.88it/s]
 33%|███▎      | 255/782 [02:21<04:39,  1.89it/s]
 33%|███▎      | 256/782 [02:22<04:37,  1.90it/s]
 33%|███▎      | 257/782 [02:22<04:34,  1.91it/s]
 33%|███▎      | 258/782 [02:23<04:36,  1.89it/s]
 33%|███▎      | 259/782 [02:23<04:45,  1.83it/s]
 33%|███▎      | 260/782 [02:24<04:37,  1.88it/s]
 33%|███▎      | 261/782 [02:24<04:31,  1.92it/s]
 34%|███▎      | 262/782 [02:25<04:36,  1.88it/s]
 34%|███▎      | 263/782 [02:25<04:38,  1.86it/s]
 34%|███▍      | 264/782 [02:26<04:37,  1.87it/s]
 34%|███▍      | 265/782 [02:26<04:40,  1.84it/s]
 34%|███▍      | 266/782 [02:27<04:33,  1.89it/s]
 34%|███▍      | 267/782 [02:28<04:37,  1.86it/s]
 34%|███▍      | 268/782 [02:28<04:43,  1.81it/s]
 34%|███▍      | 269/782 [02:29<04:47,  1.78it/s]
 35%|███▍      | 270/782 [02:29<04:36,  1.85it/s]
 35%|███▍      | 271/782 [02:30<04:40,  1.82it/s]
 35%|███▍      | 272/782 [02:30<04:49,  1.76it/s]
 35%|███▍      | 273/782 [02:31<04:37,  1.84it/s]
 35%|███▌      | 274/782 [02:31<04:35,  1.84it/s]
 35%|███▌      | 275/782 [02:32<04:41,  1.80it/s]
 35%|███▌      | 276/782 [02:32<04:30,  1.87it/s]
 35%|███▌      | 277/782 [02:33<04:35,  1.83it/s]
 36%|███▌      | 278/782 [02:34<04:34,  1.84it/s]
 36%|███▌      | 279/782 [02:34<04:33,  1.84it/s]
 36%|███▌      | 280/782 [02:35<04:33,  1.84it/s]
 36%|███▌      | 281/782 [02:35<04:36,  1.81it/s]
 36%|███▌      | 282/782 [02:36<04:26,  1.88it/s]
 36%|███▌      | 283/782 [02:36<04:29,  1.85it/s]
 36%|███▋      | 284/782 [02:37<04:38,  1.79it/s]
 36%|███▋      | 285/782 [02:37<04:29,  1.85it/s]
 37%|███▋      | 286/782 [02:38<04:30,  1.83it/s]
 37%|███▋      | 287/782 [02:38<04:28,  1.85it/s]
 37%|███▋      | 288/782 [02:39<04:22,  1.88it/s]
 37%|███▋      | 289/782 [02:40<04:24,  1.87it/s]
 37%|███▋      | 290/782 [02:40<04:41,  1.75it/s]
 37%|███▋      | 291/782 [02:41<04:33,  1.80it/s]
 37%|███▋      | 292/782 [02:41<04:29,  1.82it/s]
 37%|███▋      | 293/782 [02:42<04:37,  1.76it/s]
 38%|███▊      | 294/782 [02:42<04:24,  1.85it/s]
 38%|███▊      | 295/782 [02:43<04:26,  1.83it/s]
 38%|███▊      | 296/782 [02:43<04:32,  1.78it/s]
 38%|███▊      | 297/782 [02:44<04:26,  1.82it/s]
 38%|███▊      | 298/782 [02:44<04:17,  1.88it/s]
 38%|███▊      | 299/782 [02:45<04:18,  1.87it/s]
 38%|███▊      | 300/782 [02:46<04:16,  1.88it/s]
                                                 
{'loss': 5.9866, 'grad_norm': 6.948846817016602, 'learning_rate': 6.176470588235295e-05, 'epoch': 0.38}

 38%|███▊      | 300/782 [02:46<04:16,  1.88it/s]
 38%|███▊      | 301/782 [02:46<04:18,  1.86it/s]
 39%|███▊      | 302/782 [02:47<04:18,  1.86it/s]
 39%|███▊      | 303/782 [02:47<04:20,  1.84it/s]
 39%|███▉      | 304/782 [02:48<04:19,  1.84it/s]
 39%|███▉      | 305/782 [02:48<04:13,  1.88it/s]
 39%|███▉      | 306/782 [02:49<04:16,  1.86it/s]
 39%|███▉      | 307/782 [02:49<04:10,  1.89it/s]
 39%|███▉      | 308/782 [02:50<04:10,  1.89it/s]
 40%|███▉      | 309/782 [02:50<04:11,  1.88it/s]
 40%|███▉      | 310/782 [02:51<04:09,  1.89it/s]
 40%|███▉      | 311/782 [02:51<04:07,  1.90it/s]
 40%|███▉      | 312/782 [02:52<04:08,  1.89it/s]
 40%|████      | 313/782 [02:52<04:09,  1.88it/s]
 40%|████      | 314/782 [02:53<04:08,  1.88it/s]
 40%|████      | 315/782 [02:54<04:15,  1.83it/s]
 40%|████      | 316/782 [02:54<04:13,  1.84it/s]
 41%|████      | 317/782 [02:55<04:07,  1.88it/s]
 41%|████      | 318/782 [02:55<04:06,  1.88it/s]
 41%|████      | 319/782 [02:56<04:03,  1.90it/s]
 41%|████      | 320/782 [02:56<04:00,  1.92it/s]
 41%|████      | 321/782 [02:57<04:05,  1.87it/s]
 41%|████      | 322/782 [02:57<04:09,  1.84it/s]
 41%|████▏     | 323/782 [02:58<04:05,  1.87it/s]
 41%|████▏     | 324/782 [02:58<04:04,  1.88it/s]
 42%|████▏     | 325/782 [02:59<04:05,  1.86it/s]
 42%|████▏     | 326/782 [02:59<04:01,  1.89it/s]
 42%|████▏     | 327/782 [03:00<03:59,  1.90it/s]
 42%|████▏     | 328/782 [03:01<04:06,  1.84it/s]
 42%|████▏     | 329/782 [03:01<04:02,  1.86it/s]
 42%|████▏     | 330/782 [03:02<04:00,  1.88it/s]
 42%|████▏     | 331/782 [03:02<03:59,  1.88it/s]
 42%|████▏     | 332/782 [03:03<04:12,  1.78it/s]
 43%|████▎     | 333/782 [03:03<04:09,  1.80it/s]
 43%|████▎     | 334/782 [03:04<04:01,  1.86it/s]
 43%|████▎     | 335/782 [03:04<04:05,  1.82it/s]
 43%|████▎     | 336/782 [03:05<04:19,  1.72it/s]
 43%|████▎     | 337/782 [03:05<04:03,  1.83it/s]
 43%|████▎     | 338/782 [03:06<04:02,  1.83it/s]
 43%|████▎     | 339/782 [03:07<03:59,  1.85it/s]
 43%|████▎     | 340/782 [03:07<03:50,  1.91it/s]
 44%|████▎     | 341/782 [03:08<03:51,  1.90it/s]
 44%|████▎     | 342/782 [03:08<03:55,  1.87it/s]
 44%|████▍     | 343/782 [03:09<03:53,  1.88it/s]
 44%|████▍     | 344/782 [03:09<03:48,  1.91it/s]
 44%|████▍     | 345/782 [03:10<03:48,  1.92it/s]
 44%|████▍     | 346/782 [03:10<03:54,  1.86it/s]
 44%|████▍     | 347/782 [03:11<03:55,  1.85it/s]
 45%|████▍     | 348/782 [03:11<03:51,  1.88it/s]
 45%|████▍     | 349/782 [03:12<04:01,  1.79it/s]
 45%|████▍     | 350/782 [03:12<04:02,  1.78it/s]
                                                 
{'loss': 0.1617, 'grad_norm': 0.6942098140716553, 'learning_rate': 5.537084398976983e-05, 'epoch': 0.45}

 45%|████▍     | 350/782 [03:13<04:02,  1.78it/s]
 45%|████▍     | 351/782 [03:13<03:53,  1.84it/s]
 45%|████▌     | 352/782 [03:14<03:51,  1.86it/s]
 45%|████▌     | 353/782 [03:14<03:58,  1.80it/s]
 45%|████▌     | 354/782 [03:15<03:48,  1.88it/s]
 45%|████▌     | 355/782 [03:15<03:50,  1.86it/s]
 46%|████▌     | 356/782 [03:16<03:48,  1.86it/s]
 46%|████▌     | 357/782 [03:16<03:38,  1.95it/s]
 46%|████▌     | 358/782 [03:17<03:45,  1.88it/s]
 46%|████▌     | 359/782 [03:17<03:51,  1.83it/s]
 46%|████▌     | 360/782 [03:18<03:46,  1.86it/s]
 46%|████▌     | 361/782 [03:18<03:53,  1.81it/s]
 46%|████▋     | 362/782 [03:19<03:55,  1.78it/s]
 46%|████▋     | 363/782 [03:19<03:48,  1.84it/s]
 47%|████▋     | 364/782 [03:20<03:48,  1.83it/s]
 47%|████▋     | 365/782 [03:21<03:49,  1.82it/s]
 47%|████▋     | 366/782 [03:21<03:40,  1.89it/s]
 47%|████▋     | 367/782 [03:22<03:36,  1.92it/s]
 47%|████▋     | 368/782 [03:22<03:40,  1.88it/s]
 47%|████▋     | 369/782 [03:23<03:34,  1.92it/s]
 47%|████▋     | 370/782 [03:23<03:33,  1.93it/s]
 47%|████▋     | 371/782 [03:24<03:34,  1.92it/s]
 48%|████▊     | 372/782 [03:24<03:40,  1.86it/s]
 48%|████▊     | 373/782 [03:25<03:38,  1.87it/s]
 48%|████▊     | 374/782 [03:25<03:35,  1.89it/s]
 48%|████▊     | 375/782 [03:26<03:37,  1.87it/s]
 48%|████▊     | 376/782 [03:26<03:35,  1.88it/s]
 48%|████▊     | 377/782 [03:27<03:34,  1.89it/s]
 48%|████▊     | 378/782 [03:27<03:35,  1.88it/s]
 48%|████▊     | 379/782 [03:28<03:31,  1.91it/s]
 49%|████▊     | 380/782 [03:28<03:29,  1.91it/s]
 49%|████▊     | 381/782 [03:29<03:36,  1.85it/s]
 49%|████▉     | 382/782 [03:30<03:49,  1.74it/s]
 49%|████▉     | 383/782 [03:30<03:38,  1.83it/s]
 49%|████▉     | 384/782 [03:31<03:41,  1.79it/s]
 49%|████▉     | 385/782 [03:31<03:44,  1.77it/s]
 49%|████▉     | 386/782 [03:32<03:45,  1.76it/s]
 49%|████▉     | 387/782 [03:32<03:39,  1.80it/s]
 50%|████▉     | 388/782 [03:33<03:33,  1.84it/s]
 50%|████▉     | 389/782 [03:33<03:33,  1.84it/s]
 50%|████▉     | 390/782 [03:34<03:38,  1.79it/s]
 50%|█████     | 391/782 [03:35<03:28,  1.87it/s]
 50%|█████     | 392/782 [03:35<03:35,  1.81it/s]
 50%|█████     | 393/782 [03:36<03:48,  1.70it/s]
 50%|█████     | 394/782 [03:36<03:35,  1.80it/s]
 51%|█████     | 395/782 [03:37<03:34,  1.81it/s]
 51%|█████     | 396/782 [03:37<03:34,  1.80it/s]
 51%|█████     | 397/782 [03:38<03:31,  1.82it/s]
 51%|█████     | 398/782 [03:38<03:28,  1.84it/s]
 51%|█████     | 399/782 [03:39<03:31,  1.81it/s]
 51%|█████     | 400/782 [03:40<03:24,  1.87it/s]
                                                 
{'loss': 0.0779, 'grad_norm': 0.5859019756317139, 'learning_rate': 4.89769820971867e-05, 'epoch': 0.51}

 51%|█████     | 400/782 [03:40<03:24,  1.87it/s]
 51%|█████▏    | 401/782 [03:40<03:27,  1.84it/s]
 51%|█████▏    | 402/782 [03:41<03:33,  1.78it/s]
 52%|█████▏    | 403/782 [03:41<03:23,  1.86it/s]
 52%|█████▏    | 404/782 [03:42<03:23,  1.86it/s]
 52%|█████▏    | 405/782 [03:42<03:30,  1.79it/s]
 52%|█████▏    | 406/782 [03:43<03:20,  1.87it/s]
 52%|█████▏    | 407/782 [03:43<03:19,  1.88it/s]
 52%|█████▏    | 408/782 [03:44<03:23,  1.83it/s]
 52%|█████▏    | 409/782 [03:44<03:17,  1.89it/s]
 52%|█████▏    | 410/782 [03:45<03:16,  1.89it/s]
 53%|█████▎    | 411/782 [03:46<03:20,  1.85it/s]
 53%|█████▎    | 412/782 [03:46<03:22,  1.83it/s]
 53%|█████▎    | 413/782 [03:47<03:17,  1.87it/s]
 53%|█████▎    | 414/782 [03:47<03:14,  1.89it/s]
 53%|█████▎    | 415/782 [03:48<03:17,  1.86it/s]
 53%|█████▎    | 416/782 [03:48<03:18,  1.84it/s]
 53%|█████▎    | 417/782 [03:49<03:14,  1.88it/s]
 53%|█████▎    | 418/782 [03:49<03:21,  1.80it/s]
 54%|█████▎    | 419/782 [03:50<03:26,  1.76it/s]
 54%|█████▎    | 420/782 [03:50<03:18,  1.82it/s]
 54%|█████▍    | 421/782 [03:51<03:16,  1.84it/s]
 54%|█████▍    | 422/782 [03:51<03:13,  1.86it/s]
 54%|█████▍    | 423/782 [03:52<03:20,  1.79it/s]
 54%|█████▍    | 424/782 [03:53<03:14,  1.84it/s]
 54%|█████▍    | 425/782 [03:53<03:10,  1.88it/s]
 54%|█████▍    | 426/782 [03:54<03:13,  1.84it/s]
 55%|█████▍    | 427/782 [03:54<03:08,  1.88it/s]
 55%|█████▍    | 428/782 [03:55<03:08,  1.88it/s]
 55%|█████▍    | 429/782 [03:55<03:06,  1.89it/s]
 55%|█████▍    | 430/782 [03:56<03:08,  1.87it/s]
 55%|█████▌    | 431/782 [03:56<03:03,  1.91it/s]
 55%|█████▌    | 432/782 [03:57<03:07,  1.87it/s]
 55%|█████▌    | 433/782 [03:57<03:11,  1.82it/s]
 55%|█████▌    | 434/782 [03:58<03:05,  1.88it/s]
 56%|█████▌    | 435/782 [03:58<03:06,  1.86it/s]
 56%|█████▌    | 436/782 [03:59<03:14,  1.78it/s]
 56%|█████▌    | 437/782 [04:00<03:06,  1.85it/s]
 56%|█████▌    | 438/782 [04:00<03:04,  1.86it/s]
 56%|█████▌    | 439/782 [04:01<03:04,  1.86it/s]
 56%|█████▋    | 440/782 [04:01<03:00,  1.90it/s]
 56%|█████▋    | 441/782 [04:02<02:59,  1.90it/s]
 57%|█████▋    | 442/782 [04:02<03:02,  1.86it/s]
 57%|█████▋    | 443/782 [04:03<02:58,  1.90it/s]
 57%|█████▋    | 444/782 [04:03<02:59,  1.89it/s]
 57%|█████▋    | 445/782 [04:04<03:03,  1.83it/s]
 57%|█████▋    | 446/782 [04:04<02:53,  1.94it/s]
 57%|█████▋    | 447/782 [04:05<02:56,  1.90it/s]
 57%|█████▋    | 448/782 [04:05<03:00,  1.85it/s]
 57%|█████▋    | 449/782 [04:06<03:00,  1.85it/s]
 58%|█████▊    | 450/782 [04:06<02:56,  1.88it/s]
                                                 
{'loss': 0.0536, 'grad_norm': 0.3546956777572632, 'learning_rate': 4.2583120204603584e-05, 'epoch': 0.58}

 58%|█████▊    | 450/782 [04:07<02:56,  1.88it/s]
 58%|█████▊    | 451/782 [04:07<02:53,  1.90it/s]
 58%|█████▊    | 452/782 [04:08<02:55,  1.88it/s]
 58%|█████▊    | 453/782 [04:08<02:49,  1.94it/s]
 58%|█████▊    | 454/782 [04:09<02:47,  1.96it/s]
 58%|█████▊    | 455/782 [04:09<02:48,  1.94it/s]
 58%|█████▊    | 456/782 [04:10<02:47,  1.95it/s]
 58%|█████▊    | 457/782 [04:10<02:46,  1.95it/s]
 59%|█████▊    | 458/782 [04:11<02:52,  1.88it/s]
 59%|█████▊    | 459/782 [04:11<02:56,  1.83it/s]
 59%|█████▉    | 460/782 [04:12<02:51,  1.88it/s]
 59%|█████▉    | 461/782 [04:12<02:52,  1.86it/s]
 59%|█████▉    | 462/782 [04:13<02:53,  1.85it/s]
 59%|█████▉    | 463/782 [04:13<02:51,  1.86it/s]
 59%|█████▉    | 464/782 [04:14<02:51,  1.85it/s]
 59%|█████▉    | 465/782 [04:14<02:47,  1.90it/s]
 60%|█████▉    | 466/782 [04:15<02:43,  1.94it/s]
 60%|█████▉    | 467/782 [04:15<02:43,  1.93it/s]
 60%|█████▉    | 468/782 [04:16<02:49,  1.85it/s]
 60%|█████▉    | 469/782 [04:16<02:40,  1.95it/s]
 60%|██████    | 470/782 [04:17<02:43,  1.91it/s]
 60%|██████    | 471/782 [04:18<02:45,  1.88it/s]
 60%|██████    | 472/782 [04:18<02:41,  1.92it/s]
 60%|██████    | 473/782 [04:19<02:42,  1.90it/s]
 61%|██████    | 474/782 [04:19<02:45,  1.86it/s]
 61%|██████    | 475/782 [04:20<02:39,  1.92it/s]
 61%|██████    | 476/782 [04:20<02:40,  1.91it/s]
 61%|██████    | 477/782 [04:21<02:40,  1.90it/s]
 61%|██████    | 478/782 [04:21<02:44,  1.85it/s]
 61%|██████▏   | 479/782 [04:22<02:41,  1.87it/s]
 61%|██████▏   | 480/782 [04:22<02:37,  1.91it/s]
 62%|██████▏   | 481/782 [04:23<02:41,  1.86it/s]
 62%|██████▏   | 482/782 [04:23<02:40,  1.87it/s]
 62%|██████▏   | 483/782 [04:24<02:37,  1.90it/s]
 62%|██████▏   | 484/782 [04:24<02:39,  1.87it/s]
 62%|██████▏   | 485/782 [04:25<02:42,  1.83it/s]
 62%|██████▏   | 486/782 [04:25<02:34,  1.92it/s]
 62%|██████▏   | 487/782 [04:26<02:35,  1.90it/s]
 62%|██████▏   | 488/782 [04:27<02:47,  1.76it/s]
 63%|██████▎   | 489/782 [04:27<02:38,  1.85it/s]
 63%|██████▎   | 490/782 [04:28<02:34,  1.89it/s]
 63%|██████▎   | 491/782 [04:28<02:33,  1.90it/s]
 63%|██████▎   | 492/782 [04:29<02:34,  1.88it/s]
 63%|██████▎   | 493/782 [04:29<02:30,  1.91it/s]
 63%|██████▎   | 494/782 [04:30<02:30,  1.91it/s]
 63%|██████▎   | 495/782 [04:30<02:30,  1.90it/s]
 63%|██████▎   | 496/782 [04:31<02:30,  1.90it/s]
 64%|██████▎   | 497/782 [04:31<02:28,  1.93it/s]
 64%|██████▎   | 498/782 [04:32<02:33,  1.85it/s]
 64%|██████▍   | 499/782 [04:32<02:33,  1.84it/s]
 64%|██████▍   | 500/782 [04:33<02:27,  1.91it/s]
                                                 
{'loss': 0.0399, 'grad_norm': 0.542077362537384, 'learning_rate': 3.6189258312020464e-05, 'epoch': 0.64}

 64%|██████▍   | 500/782 [04:33<02:27,  1.91it/s]
 64%|██████▍   | 501/782 [04:33<02:29,  1.88it/s]
 64%|██████▍   | 502/782 [04:34<02:29,  1.88it/s]
 64%|██████▍   | 503/782 [04:34<02:24,  1.93it/s]
 64%|██████▍   | 504/782 [04:35<02:27,  1.88it/s]
 65%|██████▍   | 505/782 [04:36<02:26,  1.89it/s]
 65%|██████▍   | 506/782 [04:36<02:23,  1.92it/s]
 65%|██████▍   | 507/782 [04:37<02:25,  1.88it/s]
 65%|██████▍   | 508/782 [04:37<02:26,  1.87it/s]
 65%|██████▌   | 509/782 [04:38<02:21,  1.93it/s]
 65%|██████▌   | 510/782 [04:38<02:22,  1.91it/s]
 65%|██████▌   | 511/782 [04:39<02:23,  1.89it/s]
 65%|██████▌   | 512/782 [04:39<02:27,  1.83it/s]
 66%|██████▌   | 513/782 [04:40<02:25,  1.85it/s]
 66%|██████▌   | 514/782 [04:40<02:21,  1.90it/s]
 66%|██████▌   | 515/782 [04:41<02:23,  1.86it/s]
 66%|██████▌   | 516/782 [04:41<02:27,  1.80it/s]
 66%|██████▌   | 517/782 [04:42<02:20,  1.88it/s]
 66%|██████▌   | 518/782 [04:43<02:21,  1.86it/s]
 66%|██████▋   | 519/782 [04:43<02:27,  1.78it/s]
 66%|██████▋   | 520/782 [04:44<02:20,  1.87it/s]
 67%|██████▋   | 521/782 [04:44<02:20,  1.86it/s]
 67%|██████▋   | 522/782 [04:45<02:21,  1.84it/s]
 67%|██████▋   | 523/782 [04:45<02:15,  1.91it/s]
 67%|██████▋   | 524/782 [04:46<02:15,  1.90it/s]
 67%|██████▋   | 525/782 [04:46<02:17,  1.86it/s]
 67%|██████▋   | 526/782 [04:47<02:11,  1.94it/s]
 67%|██████▋   | 527/782 [04:47<02:12,  1.92it/s]
 68%|██████▊   | 528/782 [04:48<02:16,  1.86it/s]
 68%|██████▊   | 529/782 [04:48<02:10,  1.94it/s]
 68%|██████▊   | 530/782 [04:49<02:09,  1.95it/s]
 68%|██████▊   | 531/782 [04:49<02:18,  1.81it/s]
 68%|██████▊   | 532/782 [04:50<02:18,  1.80it/s]
 68%|██████▊   | 533/782 [04:51<02:13,  1.86it/s]
 68%|██████▊   | 534/782 [04:51<02:11,  1.89it/s]
 68%|██████▊   | 535/782 [04:52<02:12,  1.87it/s]
 69%|██████▊   | 536/782 [04:52<02:15,  1.81it/s]
 69%|██████▊   | 537/782 [04:53<02:09,  1.89it/s]
 69%|██████▉   | 538/782 [04:53<02:08,  1.89it/s]
 69%|██████▉   | 539/782 [04:54<02:12,  1.84it/s]
 69%|██████▉   | 540/782 [04:54<02:08,  1.88it/s]
 69%|██████▉   | 541/782 [04:55<02:06,  1.91it/s]
 69%|██████▉   | 542/782 [04:55<02:07,  1.89it/s]
 69%|██████▉   | 543/782 [04:56<02:04,  1.92it/s]
 70%|██████▉   | 544/782 [04:56<02:02,  1.94it/s]
 70%|██████▉   | 545/782 [04:57<02:03,  1.92it/s]
 70%|██████▉   | 546/782 [04:57<02:05,  1.89it/s]
 70%|██████▉   | 547/782 [04:58<02:04,  1.88it/s]
 70%|███████   | 548/782 [04:58<02:04,  1.89it/s]
 70%|███████   | 549/782 [04:59<02:03,  1.88it/s]
 70%|███████   | 550/782 [05:00<02:02,  1.89it/s]
                                                 
{'loss': 0.0336, 'grad_norm': 0.38286203145980835, 'learning_rate': 2.9795396419437344e-05, 'epoch': 0.7}

 70%|███████   | 550/782 [05:00<02:02,  1.89it/s]
 70%|███████   | 551/782 [05:00<02:03,  1.87it/s]
 71%|███████   | 552/782 [05:01<02:03,  1.86it/s]
 71%|███████   | 553/782 [05:01<02:03,  1.85it/s]
 71%|███████   | 554/782 [05:02<02:02,  1.86it/s]
 71%|███████   | 555/782 [05:02<02:01,  1.87it/s]
 71%|███████   | 556/782 [05:03<02:02,  1.85it/s]
 71%|███████   | 557/782 [05:03<02:08,  1.75it/s]
 71%|███████▏  | 558/782 [05:04<02:09,  1.73it/s]
 71%|███████▏  | 559/782 [05:05<02:08,  1.74it/s]
 72%|███████▏  | 560/782 [05:05<02:04,  1.79it/s]
 72%|███████▏  | 561/782 [05:06<02:09,  1.71it/s]
 72%|███████▏  | 562/782 [05:06<02:13,  1.65it/s]
 72%|███████▏  | 563/782 [05:07<02:19,  1.57it/s]
 72%|███████▏  | 564/782 [05:08<02:16,  1.59it/s]
 72%|███████▏  | 565/782 [05:08<02:17,  1.58it/s]
 72%|███████▏  | 566/782 [05:09<02:19,  1.55it/s]
 73%|███████▎  | 567/782 [05:10<02:18,  1.55it/s]
 73%|███████▎  | 568/782 [05:10<02:15,  1.58it/s]
 73%|███████▎  | 569/782 [05:11<02:20,  1.51it/s]
 73%|███████▎  | 570/782 [05:12<02:16,  1.55it/s]
 73%|███████▎  | 571/782 [05:12<02:16,  1.54it/s]
 73%|███████▎  | 572/782 [05:13<02:16,  1.54it/s]
 73%|███████▎  | 573/782 [05:14<02:19,  1.50it/s]
 73%|███████▎  | 574/782 [05:14<02:16,  1.53it/s]
 74%|███████▎  | 575/782 [05:15<02:15,  1.52it/s]
 74%|███████▎  | 576/782 [05:16<02:16,  1.50it/s]
 74%|███████▍  | 577/782 [05:16<02:15,  1.52it/s]
 74%|███████▍  | 578/782 [05:17<02:18,  1.47it/s]
 74%|███████▍  | 579/782 [05:18<02:12,  1.53it/s]
 74%|███████▍  | 580/782 [05:18<02:12,  1.53it/s]
 74%|███████▍  | 581/782 [05:19<02:15,  1.48it/s]
 74%|███████▍  | 582/782 [05:20<02:10,  1.53it/s]
 75%|███████▍  | 583/782 [05:20<02:11,  1.51it/s]
 75%|███████▍  | 584/782 [05:21<02:10,  1.51it/s]
 75%|███████▍  | 585/782 [05:22<02:07,  1.55it/s]
 75%|███████▍  | 586/782 [05:22<02:08,  1.53it/s]
 75%|███████▌  | 587/782 [05:23<02:11,  1.49it/s]
 75%|███████▌  | 588/782 [05:24<02:07,  1.52it/s]
 75%|███████▌  | 589/782 [05:24<02:09,  1.49it/s]
 75%|███████▌  | 590/782 [05:25<02:09,  1.49it/s]
 76%|███████▌  | 591/782 [05:26<02:05,  1.52it/s]
 76%|███████▌  | 592/782 [05:26<02:03,  1.54it/s]
 76%|███████▌  | 593/782 [05:27<02:01,  1.55it/s]
 76%|███████▌  | 594/782 [05:27<02:02,  1.53it/s]
 76%|███████▌  | 595/782 [05:28<02:01,  1.54it/s]
 76%|███████▌  | 596/782 [05:29<02:00,  1.54it/s]
 76%|███████▋  | 597/782 [05:29<02:01,  1.52it/s]
 76%|███████▋  | 598/782 [05:30<02:00,  1.53it/s]
 77%|███████▋  | 599/782 [05:31<01:56,  1.57it/s]
 77%|███████▋  | 600/782 [05:31<01:57,  1.54it/s]
                                                 
{'loss': 0.0286, 'grad_norm': 0.4268437325954437, 'learning_rate': 2.340153452685422e-05, 'epoch': 0.77}

 77%|███████▋  | 600/782 [05:31<01:57,  1.54it/s]
 77%|███████▋  | 601/782 [05:32<01:59,  1.52it/s]
 77%|███████▋  | 602/782 [05:33<01:56,  1.55it/s]
 77%|███████▋  | 603/782 [05:33<01:58,  1.51it/s]
 77%|███████▋  | 604/782 [05:34<02:01,  1.47it/s]
 77%|███████▋  | 605/782 [05:35<01:58,  1.49it/s]
 77%|███████▋  | 606/782 [05:35<01:55,  1.52it/s]
 78%|███████▊  | 607/782 [05:36<01:55,  1.51it/s]
 78%|███████▊  | 608/782 [05:37<01:50,  1.57it/s]
 78%|███████▊  | 609/782 [05:37<01:52,  1.54it/s]
 78%|███████▊  | 610/782 [05:38<01:57,  1.46it/s]
 78%|███████▊  | 611/782 [05:39<01:53,  1.51it/s]
 78%|███████▊  | 612/782 [05:39<01:55,  1.48it/s]
 78%|███████▊  | 613/782 [05:40<01:51,  1.52it/s]
 79%|███████▊  | 614/782 [05:41<01:48,  1.54it/s]
 79%|███████▊  | 615/782 [05:41<01:48,  1.54it/s]
 79%|███████▉  | 616/782 [05:42<01:51,  1.49it/s]
 79%|███████▉  | 617/782 [05:43<01:48,  1.53it/s]
 79%|███████▉  | 618/782 [05:43<01:50,  1.48it/s]
 79%|███████▉  | 619/782 [05:44<01:50,  1.48it/s]
 79%|███████▉  | 620/782 [05:45<01:48,  1.49it/s]
 79%|███████▉  | 621/782 [05:45<01:48,  1.48it/s]
 80%|███████▉  | 622/782 [05:46<01:47,  1.49it/s]
 80%|███████▉  | 623/782 [05:47<01:43,  1.54it/s]
 80%|███████▉  | 624/782 [05:47<01:42,  1.53it/s]
 80%|███████▉  | 625/782 [05:48<01:42,  1.53it/s]
 80%|████████  | 626/782 [05:49<01:42,  1.52it/s]
 80%|████████  | 627/782 [05:49<01:43,  1.50it/s]
 80%|████████  | 628/782 [05:50<01:42,  1.51it/s]
 80%|████████  | 629/782 [05:51<01:38,  1.56it/s]
 81%|████████  | 630/782 [05:51<01:43,  1.46it/s]
 81%|████████  | 631/782 [05:52<01:41,  1.48it/s]
 81%|████████  | 632/782 [05:52<01:33,  1.61it/s]
 81%|████████  | 633/782 [05:53<01:28,  1.69it/s]
 81%|████████  | 634/782 [05:54<01:27,  1.69it/s]
 81%|████████  | 635/782 [05:54<01:22,  1.78it/s]
 81%|████████▏ | 636/782 [05:55<01:22,  1.77it/s]
 81%|████████▏ | 637/782 [05:55<01:23,  1.73it/s]
 82%|████████▏ | 638/782 [05:56<01:21,  1.77it/s]
 82%|████████▏ | 639/782 [05:56<01:18,  1.82it/s]
 82%|████████▏ | 640/782 [05:57<01:18,  1.81it/s]
 82%|████████▏ | 641/782 [05:57<01:17,  1.83it/s]
 82%|████████▏ | 642/782 [05:58<01:14,  1.87it/s]
 82%|████████▏ | 643/782 [05:58<01:15,  1.85it/s]
 82%|████████▏ | 644/782 [05:59<01:14,  1.86it/s]
 82%|████████▏ | 645/782 [06:00<01:13,  1.85it/s]
 83%|████████▎ | 646/782 [06:00<01:13,  1.85it/s]
 83%|████████▎ | 647/782 [06:01<01:14,  1.82it/s]
 83%|████████▎ | 648/782 [06:01<01:11,  1.86it/s]
 83%|████████▎ | 649/782 [06:02<01:10,  1.88it/s]
 83%|████████▎ | 650/782 [06:02<01:11,  1.85it/s]
                                                 
{'loss': 0.0237, 'grad_norm': 0.49761509895324707, 'learning_rate': 1.70076726342711e-05, 'epoch': 0.83}

 83%|████████▎ | 650/782 [06:02<01:11,  1.85it/s]
 83%|████████▎ | 651/782 [06:03<01:10,  1.87it/s]
 83%|████████▎ | 652/782 [06:03<01:08,  1.89it/s]
 84%|████████▎ | 653/782 [06:04<01:11,  1.81it/s]
 84%|████████▎ | 654/782 [06:04<01:10,  1.83it/s]
 84%|████████▍ | 655/782 [06:05<01:07,  1.88it/s]
 84%|████████▍ | 656/782 [06:05<01:09,  1.83it/s]
 84%|████████▍ | 657/782 [06:06<01:08,  1.81it/s]
 84%|████████▍ | 658/782 [06:07<01:06,  1.88it/s]
 84%|████████▍ | 659/782 [06:07<01:06,  1.85it/s]
 84%|████████▍ | 660/782 [06:08<01:08,  1.79it/s]
 85%|████████▍ | 661/782 [06:08<01:04,  1.87it/s]
 85%|████████▍ | 662/782 [06:09<01:04,  1.86it/s]
 85%|████████▍ | 663/782 [06:09<01:05,  1.81it/s]
 85%|████████▍ | 664/782 [06:10<01:03,  1.86it/s]
 85%|████████▌ | 665/782 [06:10<01:03,  1.86it/s]
 85%|████████▌ | 666/782 [06:11<01:05,  1.78it/s]
 85%|████████▌ | 667/782 [06:11<01:01,  1.88it/s]
 85%|████████▌ | 668/782 [06:12<01:00,  1.88it/s]
 86%|████████▌ | 669/782 [06:12<01:00,  1.87it/s]
 86%|████████▌ | 670/782 [06:13<00:59,  1.88it/s]
 86%|████████▌ | 671/782 [06:14<00:58,  1.90it/s]
 86%|████████▌ | 672/782 [06:14<00:57,  1.92it/s]
 86%|████████▌ | 673/782 [06:15<00:58,  1.88it/s]
 86%|████████▌ | 674/782 [06:15<00:56,  1.90it/s]
 86%|████████▋ | 675/782 [06:16<00:55,  1.92it/s]
 86%|████████▋ | 676/782 [06:16<00:58,  1.82it/s]
 87%|████████▋ | 677/782 [06:17<00:58,  1.79it/s]
 87%|████████▋ | 678/782 [06:17<00:55,  1.88it/s]
 87%|████████▋ | 679/782 [06:18<00:55,  1.86it/s]
 87%|████████▋ | 680/782 [06:18<00:57,  1.77it/s]
 87%|████████▋ | 681/782 [06:19<00:53,  1.88it/s]
 87%|████████▋ | 682/782 [06:19<00:54,  1.84it/s]
 87%|████████▋ | 683/782 [06:20<00:54,  1.81it/s]
 87%|████████▋ | 684/782 [06:21<00:51,  1.90it/s]
 88%|████████▊ | 685/782 [06:21<00:52,  1.85it/s]
 88%|████████▊ | 686/782 [06:22<00:52,  1.83it/s]
 88%|████████▊ | 687/782 [06:22<00:50,  1.89it/s]
 88%|████████▊ | 688/782 [06:23<00:49,  1.88it/s]
 88%|████████▊ | 689/782 [06:23<00:49,  1.89it/s]
 88%|████████▊ | 690/782 [06:24<00:49,  1.87it/s]
 88%|████████▊ | 691/782 [06:24<00:48,  1.89it/s]
 88%|████████▊ | 692/782 [06:25<00:47,  1.90it/s]
 89%|████████▊ | 693/782 [06:25<00:46,  1.90it/s]
 89%|████████▊ | 694/782 [06:26<00:46,  1.90it/s]
 89%|████████▉ | 695/782 [06:26<00:47,  1.84it/s]
 89%|████████▉ | 696/782 [06:27<00:45,  1.89it/s]
 89%|████████▉ | 697/782 [06:27<00:45,  1.87it/s]
 89%|████████▉ | 698/782 [06:28<00:44,  1.88it/s]
 89%|████████▉ | 699/782 [06:29<00:44,  1.85it/s]
 90%|████████▉ | 700/782 [06:29<00:43,  1.88it/s]
                                                 
{'loss': 0.0215, 'grad_norm': 0.2186804562807083, 'learning_rate': 1.061381074168798e-05, 'epoch': 0.9}

 90%|████████▉ | 700/782 [06:29<00:43,  1.88it/s]
 90%|████████▉ | 701/782 [06:30<00:43,  1.87it/s]
 90%|████████▉ | 702/782 [06:30<00:44,  1.80it/s]
 90%|████████▉ | 703/782 [06:31<00:44,  1.79it/s]
 90%|█████████ | 704/782 [06:31<00:41,  1.86it/s]
 90%|█████████ | 705/782 [06:32<00:41,  1.84it/s]
 90%|█████████ | 706/782 [06:32<00:40,  1.87it/s]
 90%|█████████ | 707/782 [06:33<00:39,  1.89it/s]
 91%|█████████ | 708/782 [06:33<00:39,  1.89it/s]
 91%|█████████ | 709/782 [06:34<00:38,  1.89it/s]
 91%|█████████ | 710/782 [06:34<00:39,  1.83it/s]
 91%|█████████ | 711/782 [06:35<00:38,  1.86it/s]
 91%|█████████ | 712/782 [06:36<00:37,  1.88it/s]
 91%|█████████ | 713/782 [06:36<00:37,  1.84it/s]
 91%|█████████▏| 714/782 [06:37<00:37,  1.82it/s]
 91%|█████████▏| 715/782 [06:37<00:35,  1.87it/s]
 92%|█████████▏| 716/782 [06:38<00:35,  1.86it/s]
 92%|█████████▏| 717/782 [06:38<00:35,  1.84it/s]
 92%|█████████▏| 718/782 [06:39<00:34,  1.87it/s]
 92%|█████████▏| 719/782 [06:39<00:33,  1.86it/s]
 92%|█████████▏| 720/782 [06:40<00:33,  1.87it/s]
 92%|█████████▏| 721/782 [06:40<00:32,  1.87it/s]
 92%|█████████▏| 722/782 [06:41<00:31,  1.91it/s]
 92%|█████████▏| 723/782 [06:41<00:30,  1.91it/s]
 93%|█████████▎| 724/782 [06:42<00:31,  1.84it/s]
 93%|█████████▎| 725/782 [06:43<00:31,  1.82it/s]
 93%|█████████▎| 726/782 [06:43<00:31,  1.77it/s]
 93%|█████████▎| 727/782 [06:44<00:30,  1.80it/s]
 93%|█████████▎| 728/782 [06:44<00:29,  1.81it/s]
 93%|█████████▎| 729/782 [06:45<00:29,  1.82it/s]
 93%|█████████▎| 730/782 [06:45<00:28,  1.85it/s]
 93%|█████████▎| 731/782 [06:46<00:27,  1.86it/s]
 94%|█████████▎| 732/782 [06:46<00:27,  1.85it/s]
 94%|█████████▎| 733/782 [06:47<00:26,  1.88it/s]
 94%|█████████▍| 734/782 [06:47<00:25,  1.86it/s]
 94%|█████████▍| 735/782 [06:48<00:25,  1.85it/s]
 94%|█████████▍| 736/782 [06:49<00:24,  1.88it/s]
 94%|█████████▍| 737/782 [06:49<00:23,  1.89it/s]
 94%|█████████▍| 738/782 [06:50<00:23,  1.88it/s]
 95%|█████████▍| 739/782 [06:50<00:22,  1.90it/s]
 95%|█████████▍| 740/782 [06:51<00:22,  1.90it/s]
 95%|█████████▍| 741/782 [06:51<00:22,  1.85it/s]
 95%|█████████▍| 742/782 [06:52<00:21,  1.89it/s]
 95%|█████████▌| 743/782 [06:52<00:20,  1.91it/s]
 95%|█████████▌| 744/782 [06:53<00:20,  1.84it/s]
 95%|█████████▌| 745/782 [06:53<00:19,  1.88it/s]
 95%|█████████▌| 746/782 [06:54<00:19,  1.88it/s]
 96%|█████████▌| 747/782 [06:54<00:19,  1.83it/s]
 96%|█████████▌| 748/782 [06:55<00:18,  1.82it/s]
 96%|█████████▌| 749/782 [06:55<00:17,  1.86it/s]
 96%|█████████▌| 750/782 [06:56<00:17,  1.81it/s]
                                                 
{'loss': 0.0212, 'grad_norm': 0.354276180267334, 'learning_rate': 4.219948849104859e-06, 'epoch': 0.96}

 96%|█████████▌| 750/782 [06:56<00:17,  1.81it/s]
 96%|█████████▌| 751/782 [06:57<00:17,  1.73it/s]
 96%|█████████▌| 752/782 [06:57<00:16,  1.82it/s]
 96%|█████████▋| 753/782 [06:58<00:15,  1.83it/s]
 96%|█████████▋| 754/782 [06:58<00:15,  1.80it/s]
 97%|█████████▋| 755/782 [06:59<00:14,  1.82it/s]
 97%|█████████▋| 756/782 [06:59<00:14,  1.83it/s]
 97%|█████████▋| 757/782 [07:00<00:13,  1.82it/s]
 97%|█████████▋| 758/782 [07:00<00:13,  1.80it/s]
 97%|█████████▋| 759/782 [07:01<00:12,  1.83it/s]
 97%|█████████▋| 760/782 [07:02<00:11,  1.89it/s]
 97%|█████████▋| 761/782 [07:02<00:11,  1.90it/s]
 97%|█████████▋| 762/782 [07:03<00:10,  1.90it/s]
 98%|█████████▊| 763/782 [07:03<00:09,  1.91it/s]
 98%|█████████▊| 764/782 [07:04<00:09,  1.89it/s]
 98%|█████████▊| 765/782 [07:04<00:09,  1.88it/s]
 98%|█████████▊| 766/782 [07:05<00:08,  1.86it/s]
 98%|█████████▊| 767/782 [07:05<00:08,  1.85it/s]
 98%|█████████▊| 768/782 [07:06<00:07,  1.87it/s]
 98%|█████████▊| 769/782 [07:06<00:06,  1.87it/s]
 98%|█████████▊| 770/782 [07:07<00:06,  1.86it/s]
 99%|█████████▊| 771/782 [07:07<00:05,  1.90it/s]
 99%|█████████▊| 772/782 [07:08<00:05,  1.92it/s]
 99%|█████████▉| 773/782 [07:08<00:04,  1.85it/s]
 99%|█████████▉| 774/782 [07:09<00:04,  1.85it/s]
 99%|█████████▉| 775/782 [07:09<00:03,  1.91it/s]
 99%|█████████▉| 776/782 [07:10<00:03,  1.90it/s]
 99%|█████████▉| 777/782 [07:11<00:02,  1.90it/s]
 99%|█████████▉| 778/782 [07:11<00:02,  1.92it/s]
100%|█████████▉| 779/782 [07:12<00:01,  1.89it/s]
100%|█████████▉| 780/782 [07:12<00:01,  1.90it/s]
100%|█████████▉| 781/782 [07:13<00:00,  1.94it/s]
100%|██████████| 782/782 [07:13<00:00,  1.92it/s]
                                                 
{'train_runtime': 434.6484, 'train_samples_per_second': 230.071, 'train_steps_per_second': 1.799, 'train_loss': 6.048197149010876, 'epoch': 1.0}

100%|██████████| 782/782 [07:13<00:00,  1.92it/s]
100%|██████████| 782/782 [07:13<00:00,  1.80it/s]

model.safetensors:   0%|          | 0.00/3.13G [00:00<?, ?B/s]

spiece.model:   0%|          | 0.00/792k [00:00<?, ?B/s]


Upload 3 LFS files:   0%|          | 0/3 [00:00<?, ?it/s]



training_args.bin:   0%|          | 0.00/5.37k [00:00<?, ?B/s]
training_args.bin: 100%|██████████| 5.37k/5.37k [00:00<00:00, 59.3kB/s]

model.safetensors:   0%|          | 852k/3.13G [00:00<07:00, 7.45MB/s]
spiece.model: 100%|██████████| 792k/792k [00:00<00:00, 5.49MB/s]

model.safetensors:   1%|          | 16.0M/3.13G [00:00<01:09, 44.7MB/s]
model.safetensors:   1%|          | 32.0M/3.13G [00:00<00:58, 52.7MB/s]
model.safetensors:   2%|▏         | 48.0M/3.13G [00:00<00:56, 54.4MB/s]
model.safetensors:   2%|▏         | 64.0M/3.13G [00:01<00:53, 56.9MB/s]
model.safetensors:   3%|▎         | 80.0M/3.13G [00:01<00:56, 53.8MB/s]
model.safetensors:   3%|▎         | 96.0M/3.13G [00:01<00:56, 54.1MB/s]
model.safetensors:   4%|▎         | 112M/3.13G [00:02<00:53, 56.6MB/s] 
model.safetensors:   4%|▍         | 128M/3.13G [00:02<00:58, 51.2MB/s]
model.safetensors:   5%|▍         | 144M/3.13G [00:02<00:56, 53.1MB/s]
model.safetensors:   5%|▌         | 160M/3.13G [00:02<00:52, 56.1MB/s]
model.safetensors:   6%|▌         | 176M/3.13G [00:03<00:55, 53.0MB/s]
model.safetensors:   6%|▌         | 192M/3.13G [00:03<00:56, 52.3MB/s]
model.safetensors:   7%|▋         | 208M/3.13G [00:03<00:53, 55.0MB/s]
model.safetensors:   7%|▋         | 224M/3.13G [00:04<00:51, 56.2MB/s]
model.safetensors:   8%|▊         | 240M/3.13G [00:04<00:50, 57.4MB/s]
model.safetensors:   8%|▊         | 256M/3.13G [00:04<00:49, 58.6MB/s]
model.safetensors:   9%|▊         | 272M/3.13G [00:04<00:48, 58.7MB/s]
model.safetensors:   9%|▉         | 288M/3.13G [00:05<00:48, 59.0MB/s]
model.safetensors:  10%|▉         | 304M/3.13G [00:05<00:47, 59.2MB/s]
model.safetensors:  10%|█         | 320M/3.13G [00:05<00:47, 59.1MB/s]
model.safetensors:  11%|█         | 336M/3.13G [00:06<00:45, 61.0MB/s]
model.safetensors:  11%|█         | 352M/3.13G [00:06<00:46, 60.3MB/s]
model.safetensors:  12%|█▏        | 368M/3.13G [00:06<00:43, 64.0MB/s]
model.safetensors:  12%|█▏        | 384M/3.13G [00:06<00:44, 62.3MB/s]
model.safetensors:  13%|█▎        | 400M/3.13G [00:07<00:44, 62.1MB/s]
model.safetensors:  13%|█▎        | 416M/3.13G [00:07<00:44, 61.6MB/s]
model.safetensors:  14%|█▍        | 432M/3.13G [00:07<00:47, 56.5MB/s]
model.safetensors:  14%|█▍        | 448M/3.13G [00:07<00:46, 57.7MB/s]
model.safetensors:  15%|█▍        | 464M/3.13G [00:08<00:43, 62.0MB/s]
model.safetensors:  15%|█▌        | 480M/3.13G [00:08<00:43, 60.9MB/s]
model.safetensors:  16%|█▌        | 496M/3.13G [00:08<00:59, 44.5MB/s]
model.safetensors:  16%|█▋        | 512M/3.13G [00:09<00:54, 48.0MB/s]
model.safetensors:  17%|█▋        | 528M/3.13G [00:09<00:49, 53.0MB/s]
model.safetensors:  17%|█▋        | 544M/3.13G [00:09<00:48, 53.8MB/s]
model.safetensors:  18%|█▊        | 560M/3.13G [00:10<01:09, 36.8MB/s]
model.safetensors:  18%|█▊        | 576M/3.13G [00:10<01:02, 40.8MB/s]
model.safetensors:  19%|█▉        | 592M/3.13G [00:11<00:56, 45.1MB/s]
model.safetensors:  19%|█▉        | 608M/3.13G [00:11<00:50, 50.1MB/s]
model.safetensors:  20%|█▉        | 624M/3.13G [00:11<00:51, 49.1MB/s]
model.safetensors:  20%|██        | 640M/3.13G [00:11<00:47, 52.2MB/s]
model.safetensors:  21%|██        | 656M/3.13G [00:12<00:49, 49.7MB/s]
model.safetensors:  21%|██▏       | 672M/3.13G [00:12<00:50, 48.9MB/s]
model.safetensors:  22%|██▏       | 688M/3.13G [00:12<00:46, 52.7MB/s]
model.safetensors:  22%|██▏       | 704M/3.13G [00:13<00:45, 53.8MB/s]
model.safetensors:  23%|██▎       | 720M/3.13G [00:13<00:43, 55.1MB/s]
model.safetensors:  23%|██▎       | 736M/3.13G [00:17<03:41, 10.8MB/s]
model.safetensors:  24%|██▍       | 745M/3.13G [00:17<03:02, 13.1MB/s]
model.safetensors:  24%|██▍       | 752M/3.13G [00:17<02:44, 14.5MB/s]
model.safetensors:  25%|██▍       | 768M/3.13G [00:18<02:04, 19.0MB/s]
model.safetensors:  25%|██▌       | 784M/3.13G [00:18<01:34, 24.8MB/s]
model.safetensors:  26%|██▌       | 800M/3.13G [00:18<01:14, 31.1MB/s]
model.safetensors:  26%|██▌       | 816M/3.13G [00:19<01:02, 37.3MB/s]
model.safetensors:  27%|██▋       | 832M/3.13G [00:19<00:57, 39.9MB/s]
model.safetensors:  27%|██▋       | 848M/3.13G [00:19<00:50, 45.7MB/s]
model.safetensors:  28%|██▊       | 864M/3.13G [00:19<00:43, 52.7MB/s]
model.safetensors:  28%|██▊       | 880M/3.13G [00:20<00:42, 53.0MB/s]
model.safetensors:  29%|██▊       | 896M/3.13G [00:20<00:40, 55.6MB/s]
model.safetensors:  29%|██▉       | 912M/3.13G [00:20<00:38, 57.8MB/s]
model.safetensors:  30%|██▉       | 928M/3.13G [00:20<00:37, 58.2MB/s]
model.safetensors:  30%|███       | 944M/3.13G [00:21<00:35, 62.1MB/s]
model.safetensors:  31%|███       | 960M/3.13G [00:21<00:34, 62.3MB/s]
model.safetensors:  31%|███       | 976M/3.13G [00:21<00:35, 60.3MB/s]
model.safetensors:  32%|███▏      | 992M/3.13G [00:22<00:35, 59.6MB/s]
model.safetensors:  32%|███▏      | 1.01G/3.13G [00:22<00:34, 61.8MB/s]
model.safetensors:  33%|███▎      | 1.02G/3.13G [00:22<00:34, 60.4MB/s]
model.safetensors:  33%|███▎      | 1.04G/3.13G [00:22<00:34, 60.9MB/s]
model.safetensors:  34%|███▎      | 1.06G/3.13G [00:22<00:31, 66.4MB/s]
model.safetensors:  34%|███▍      | 1.07G/3.13G [00:23<00:35, 58.3MB/s]
model.safetensors:  35%|███▍      | 1.09G/3.13G [00:23<00:34, 60.0MB/s]
model.safetensors:  35%|███▌      | 1.10G/3.13G [00:23<00:34, 59.1MB/s]
model.safetensors:  36%|███▌      | 1.12G/3.13G [00:24<00:32, 61.0MB/s]
model.safetensors:  36%|███▋      | 1.14G/3.13G [00:24<00:32, 61.5MB/s]
model.safetensors:  37%|███▋      | 1.15G/3.13G [00:24<00:37, 52.4MB/s]
model.safetensors:  37%|███▋      | 1.17G/3.13G [00:25<00:35, 56.1MB/s]
model.safetensors:  38%|███▊      | 1.18G/3.13G [00:25<00:42, 46.2MB/s]
model.safetensors:  38%|███▊      | 1.20G/3.13G [00:25<00:38, 50.1MB/s]
model.safetensors:  39%|███▉      | 1.22G/3.13G [00:26<00:36, 52.8MB/s]
model.safetensors:  39%|███▉      | 1.23G/3.13G [00:26<00:36, 52.0MB/s]
model.safetensors:  40%|███▉      | 1.25G/3.13G [00:26<00:34, 54.1MB/s]
model.safetensors:  40%|████      | 1.26G/3.13G [00:26<00:32, 56.6MB/s]
model.safetensors:  41%|████      | 1.28G/3.13G [00:27<00:31, 58.0MB/s]
model.safetensors:  41%|████▏     | 1.30G/3.13G [00:27<00:31, 58.3MB/s]
model.safetensors:  42%|████▏     | 1.31G/3.13G [00:27<00:29, 62.2MB/s]
model.safetensors:  42%|████▏     | 1.33G/3.13G [00:27<00:29, 60.6MB/s]
model.safetensors:  43%|████▎     | 1.34G/3.13G [00:28<00:29, 60.2MB/s]
model.safetensors:  43%|████▎     | 1.36G/3.13G [00:28<00:29, 60.4MB/s]
model.safetensors:  44%|████▍     | 1.38G/3.13G [00:29<00:40, 43.0MB/s]
model.safetensors:  44%|████▍     | 1.39G/3.13G [00:29<00:38, 45.5MB/s]
model.safetensors:  45%|████▍     | 1.41G/3.13G [00:29<00:34, 49.6MB/s]
model.safetensors:  45%|████▌     | 1.42G/3.13G [00:29<00:34, 48.9MB/s]
model.safetensors:  46%|████▌     | 1.44G/3.13G [00:30<00:30, 55.2MB/s]
model.safetensors:  46%|████▋     | 1.46G/3.13G [00:30<00:29, 56.8MB/s]
model.safetensors:  47%|████▋     | 1.47G/3.13G [00:30<00:28, 58.1MB/s]
model.safetensors:  47%|████▋     | 1.49G/3.13G [00:30<00:27, 59.7MB/s]
model.safetensors:  48%|████▊     | 1.50G/3.13G [00:31<00:30, 54.2MB/s]
model.safetensors:  49%|████▊     | 1.52G/3.13G [00:31<00:35, 46.1MB/s]
model.safetensors:  49%|████▉     | 1.54G/3.13G [00:32<00:32, 49.7MB/s]
model.safetensors:  50%|████▉     | 1.55G/3.13G [00:32<00:30, 51.6MB/s]
model.safetensors:  50%|█████     | 1.57G/3.13G [00:32<00:29, 53.3MB/s]
model.safetensors:  51%|█████     | 1.58G/3.13G [00:32<00:28, 54.2MB/s]
model.safetensors:  51%|█████     | 1.60G/3.13G [00:33<00:27, 56.4MB/s]
model.safetensors:  52%|█████▏    | 1.62G/3.13G [00:33<00:26, 57.2MB/s]
model.safetensors:  52%|█████▏    | 1.63G/3.13G [00:33<00:26, 56.1MB/s]
model.safetensors:  53%|█████▎    | 1.65G/3.13G [00:33<00:25, 58.6MB/s]
model.safetensors:  53%|█████▎    | 1.66G/3.13G [00:34<00:25, 57.5MB/s]
model.safetensors:  54%|█████▎    | 1.68G/3.13G [00:34<00:24, 59.0MB/s]
model.safetensors:  54%|█████▍    | 1.70G/3.13G [00:34<00:23, 60.8MB/s]
model.safetensors:  55%|█████▍    | 1.71G/3.13G [00:35<00:33, 42.0MB/s]
model.safetensors:  55%|█████▌    | 1.73G/3.13G [00:35<00:34, 41.1MB/s]
model.safetensors:  56%|█████▌    | 1.74G/3.13G [00:36<00:29, 46.4MB/s]
model.safetensors:  56%|█████▌    | 1.76G/3.13G [00:36<00:26, 51.5MB/s]
model.safetensors:  57%|█████▋    | 1.78G/3.13G [00:36<00:24, 54.4MB/s]
model.safetensors:  57%|█████▋    | 1.79G/3.13G [00:36<00:23, 56.6MB/s]
model.safetensors:  58%|█████▊    | 1.81G/3.13G [00:37<00:22, 58.5MB/s]
model.safetensors:  58%|█████▊    | 1.82G/3.13G [00:37<00:21, 60.9MB/s]
model.safetensors:  59%|█████▊    | 1.84G/3.13G [00:37<00:19, 65.2MB/s]
model.safetensors:  59%|█████▉    | 1.86G/3.13G [00:38<00:31, 40.5MB/s]
model.safetensors:  60%|█████▉    | 1.87G/3.13G [00:38<00:27, 45.3MB/s]
model.safetensors:  60%|██████    | 1.89G/3.13G [00:38<00:25, 48.9MB/s]
model.safetensors:  61%|██████    | 1.90G/3.13G [00:38<00:23, 51.6MB/s]
model.safetensors:  61%|██████▏   | 1.92G/3.13G [00:39<00:22, 53.8MB/s]
model.safetensors:  62%|██████▏   | 1.94G/3.13G [00:39<00:22, 52.4MB/s]
model.safetensors:  62%|██████▏   | 1.95G/3.13G [00:39<00:21, 55.9MB/s]
model.safetensors:  63%|██████▎   | 1.97G/3.13G [00:40<00:20, 57.0MB/s]
model.safetensors:  63%|██████▎   | 1.98G/3.13G [00:40<00:19, 58.5MB/s]
model.safetensors:  64%|██████▍   | 2.00G/3.13G [00:40<00:19, 58.3MB/s]
model.safetensors:  64%|██████▍   | 2.02G/3.13G [00:40<00:19, 58.2MB/s]
model.safetensors:  65%|██████▍   | 2.03G/3.13G [00:41<00:17, 61.9MB/s]
model.safetensors:  65%|██████▌   | 2.05G/3.13G [00:41<00:19, 54.8MB/s]
model.safetensors:  66%|██████▌   | 2.06G/3.13G [00:41<00:18, 56.9MB/s]
model.safetensors:  66%|██████▋   | 2.08G/3.13G [00:42<00:18, 56.4MB/s]
model.safetensors:  67%|██████▋   | 2.10G/3.13G [00:42<00:19, 52.0MB/s]
model.safetensors:  67%|██████▋   | 2.11G/3.13G [00:42<00:19, 53.1MB/s]
model.safetensors:  68%|██████▊   | 2.13G/3.13G [00:42<00:18, 55.1MB/s]
model.safetensors:  68%|██████▊   | 2.14G/3.13G [00:43<00:17, 57.2MB/s]
model.safetensors:  69%|██████▉   | 2.16G/3.13G [00:43<00:21, 45.4MB/s]
model.safetensors:  69%|██████▉   | 2.18G/3.13G [00:44<00:19, 48.5MB/s]
model.safetensors:  70%|██████▉   | 2.19G/3.13G [00:44<00:18, 51.7MB/s]
model.safetensors:  70%|███████   | 2.21G/3.13G [00:44<00:16, 55.3MB/s]
model.safetensors:  71%|███████   | 2.22G/3.13G [00:44<00:16, 55.1MB/s]
model.safetensors:  72%|███████▏  | 2.24G/3.13G [00:45<00:15, 56.5MB/s]
model.safetensors:  72%|███████▏  | 2.26G/3.13G [00:45<00:15, 57.7MB/s]
model.safetensors:  73%|███████▎  | 2.27G/3.13G [00:45<00:20, 41.8MB/s]
model.safetensors:  73%|███████▎  | 2.29G/3.13G [00:46<00:22, 37.5MB/s]
model.safetensors:  74%|███████▎  | 2.30G/3.13G [00:46<00:19, 41.9MB/s]
model.safetensors:  74%|███████▍  | 2.32G/3.13G [00:47<00:18, 43.9MB/s]
model.safetensors:  75%|███████▍  | 2.34G/3.13G [00:47<00:16, 47.9MB/s]
model.safetensors:  75%|███████▌  | 2.35G/3.13G [00:47<00:15, 51.7MB/s]
model.safetensors:  76%|███████▌  | 2.37G/3.13G [00:48<00:23, 32.6MB/s]
model.safetensors:  76%|███████▌  | 2.38G/3.13G [00:48<00:20, 37.2MB/s]
model.safetensors:  77%|███████▋  | 2.40G/3.13G [00:49<00:18, 40.5MB/s]
model.safetensors:  77%|███████▋  | 2.42G/3.13G [00:49<00:16, 43.5MB/s]
model.safetensors:  78%|███████▊  | 2.43G/3.13G [00:49<00:14, 47.8MB/s]
model.safetensors:  78%|███████▊  | 2.45G/3.13G [00:49<00:13, 50.7MB/s]
model.safetensors:  79%|███████▊  | 2.46G/3.13G [00:50<00:12, 53.2MB/s]
model.safetensors:  79%|███████▉  | 2.48G/3.13G [00:50<00:12, 53.1MB/s]
model.safetensors:  80%|███████▉  | 2.50G/3.13G [00:50<00:12, 53.0MB/s]
model.safetensors:  80%|████████  | 2.51G/3.13G [00:51<00:11, 53.4MB/s]
model.safetensors:  81%|████████  | 2.53G/3.13G [00:51<00:10, 56.8MB/s]
model.safetensors:  81%|████████  | 2.54G/3.13G [00:51<00:10, 58.6MB/s]
model.safetensors:  82%|████████▏ | 2.56G/3.13G [00:51<00:09, 60.3MB/s]
model.safetensors:  82%|████████▏ | 2.58G/3.13G [00:52<00:08, 63.6MB/s]
model.safetensors:  83%|████████▎ | 2.59G/3.13G [00:52<00:08, 63.5MB/s]
model.safetensors:  83%|████████▎ | 2.61G/3.13G [00:52<00:08, 61.8MB/s]
model.safetensors:  84%|████████▍ | 2.62G/3.13G [00:52<00:08, 60.4MB/s]
model.safetensors:  84%|████████▍ | 2.64G/3.13G [00:53<00:08, 61.3MB/s]
model.safetensors:  85%|████████▍ | 2.66G/3.13G [00:53<00:07, 61.7MB/s]
model.safetensors:  85%|████████▌ | 2.67G/3.13G [00:53<00:07, 60.1MB/s]
model.safetensors:  86%|████████▌ | 2.69G/3.13G [00:53<00:07, 57.3MB/s]
model.safetensors:  86%|████████▋ | 2.70G/3.13G [00:54<00:07, 54.9MB/s]
model.safetensors:  87%|████████▋ | 2.72G/3.13G [00:54<00:06, 59.5MB/s]
model.safetensors:  87%|████████▋ | 2.74G/3.13G [00:54<00:06, 60.2MB/s]
model.safetensors:  88%|████████▊ | 2.75G/3.13G [00:55<00:06, 59.9MB/s]
model.safetensors:  88%|████████▊ | 2.77G/3.13G [00:55<00:05, 61.7MB/s]
model.safetensors:  89%|████████▉ | 2.78G/3.13G [00:55<00:05, 60.8MB/s]
model.safetensors:  89%|████████▉ | 2.80G/3.13G [00:55<00:05, 65.7MB/s]
model.safetensors:  90%|████████▉ | 2.82G/3.13G [00:56<00:04, 64.5MB/s]
model.safetensors:  90%|█████████ | 2.83G/3.13G [00:56<00:05, 58.5MB/s]
model.safetensors:  91%|█████████ | 2.85G/3.13G [00:56<00:04, 59.6MB/s]
model.safetensors:  91%|█████████▏| 2.86G/3.13G [00:56<00:04, 58.4MB/s]
model.safetensors:  92%|█████████▏| 2.88G/3.13G [00:57<00:04, 59.9MB/s]
model.safetensors:  92%|█████████▏| 2.90G/3.13G [00:57<00:03, 64.9MB/s]
model.safetensors:  93%|█████████▎| 2.91G/3.13G [00:57<00:04, 44.3MB/s]
model.safetensors:  93%|█████████▎| 2.93G/3.13G [00:58<00:04, 47.8MB/s]
model.safetensors:  94%|█████████▍| 2.94G/3.13G [00:58<00:03, 51.5MB/s]
model.safetensors:  94%|█████████▍| 2.96G/3.13G [00:58<00:03, 56.2MB/s]
model.safetensors:  95%|█████████▍| 2.98G/3.13G [00:59<00:02, 57.0MB/s]
model.safetensors:  96%|█████████▌| 2.99G/3.13G [00:59<00:02, 59.5MB/s]
model.safetensors:  96%|█████████▌| 3.01G/3.13G [00:59<00:02, 59.4MB/s]
model.safetensors:  97%|█████████▋| 3.02G/3.13G [00:59<00:01, 58.0MB/s]
model.safetensors:  97%|█████████▋| 3.04G/3.13G [01:00<00:01, 58.0MB/s]
model.safetensors:  98%|█████████▊| 3.06G/3.13G [01:00<00:01, 60.3MB/s]
model.safetensors:  98%|█████████▊| 3.07G/3.13G [01:00<00:01, 58.3MB/s]
model.safetensors:  99%|█████████▊| 3.09G/3.13G [01:00<00:00, 58.8MB/s]
model.safetensors:  99%|█████████▉| 3.10G/3.13G [01:01<00:00, 61.4MB/s]
model.safetensors: 100%|█████████▉| 3.12G/3.13G [01:01<00:00, 60.7MB/s]
model.safetensors: 100%|██████████| 3.13G/3.13G [01:01<00:00, 50.8MB/s]



Upload 3 LFS files:  33%|███▎      | 1/3 [01:01<02:03, 61.90s/it]
Upload 3 LFS files: 100%|██████████| 3/3 [01:01<00:00, 20.63s/it]