Upload 5 files

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2-medium",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.26.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d130260118893300dedaaad6a9e4fb238d261f45fa067d1debb018c69e86d2
+size 1444569373

training-log.txt

@@ -0,0 +1,270 @@
+Downloading (…)lve/main/config.json: 100%|██████████| 718/718 [00:00<00:00, 180kB/s]
+Downloading (…)olve/main/vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 1.34MB/s]
+Downloading (…)olve/main/merges.txt: 100%|██████████| 456k/456k [00:01<00:00, 283kB/s]
+Downloading (…)/main/tokenizer.json: 100%|██████████| 1.36M/1.36M [00:03<00:00, 386kB/s]
+Downloading (…)"pytorch_model.bin";: 100%|██████████| 1.52G/1.52G [06:17<00:00, 4.03MB/s]
+Downloading (…)neration_config.json: 100%|██████████| 124/124 [00:00<00:00, 24.8kB/s]
+Found cached dataset common_gen (C:/Users/Jingqian/.cache/huggingface/datasets/common_gen/default/2020.5.30/1a9e8bdc026c41ce7a9e96260debf7d2809cb7fd63fa02b017e4fac1b00c6b23)
+100%|██████████| 3/3 [00:00<00:00, 749.61it/s]
+100%|██████████| 68/68 [00:01<00:00, 65.32ba/s]
+100%|██████████| 5/5 [00:00<00:00, 84.73ba/s]
+100%|██████████| 2/2 [00:00<00:00, 133.33ba/s]
+100%|██████████| 68/68 [00:03<00:00, 22.30ba/s]
+100%|██████████| 5/5 [00:00<00:00, 25.37ba/s]
+100%|██████████| 2/2 [00:00<00:00, 76.81ba/s]
+C:\Users\Jingqian\anaconda3\lib\site-packages\transformers\optimization.py:306: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
+  warnings.warn(
+***** Running training *****
+  Num examples = 4592
+  Num Epochs = 5
+  Instantaneous batch size per device = 8
+  Total train batch size (w. parallel, distributed & accumulation) = 8
+  Gradient Accumulation steps = 1
+  Total optimization steps = 2870
+  Number of trainable parameters = 354823168
+ 17%|█▋        | 500/2870 [03:25<16:23,  2.41it/s]{'loss': 2.4535, 'learning_rate': 4.128919860627178e-05, 'epoch': 0.87}
+ 20%|██        | 574/2870 [03:55<15:39,  2.44it/s]***** Running Evaluation *****
+  Num examples = 297
+  Batch size = 8
+
+  0%|          | 0/38 [00:00<?, ?it/s]
+  5%|▌         | 2/38 [00:00<00:02, 17.24it/s]
+ 11%|█         | 4/38 [00:00<00:03, 10.30it/s]
+ 16%|█▌        | 6/38 [00:00<00:03,  9.32it/s]
+ 21%|██        | 8/38 [00:00<00:03,  8.95it/s]
+ 24%|██▎       | 9/38 [00:00<00:03,  8.82it/s]
+ 26%|██▋       | 10/38 [00:01<00:03,  8.74it/s]
+ 29%|██▉       | 11/38 [00:01<00:03,  8.61it/s]
+ 32%|███▏      | 12/38 [00:01<00:03,  8.52it/s]
+ 34%|███▍      | 13/38 [00:01<00:02,  8.41it/s]
+ 37%|███▋      | 14/38 [00:01<00:02,  8.45it/s]
+ 39%|███▉      | 15/38 [00:01<00:02,  8.33it/s]
+ 42%|████▏     | 16/38 [00:01<00:02,  8.27it/s]
+ 45%|████▍     | 17/38 [00:01<00:02,  8.31it/s]
+ 47%|████▋     | 18/38 [00:02<00:02,  8.32it/s]
+ 50%|█████     | 19/38 [00:02<00:02,  8.28it/s]
+ 53%|█████▎    | 20/38 [00:02<00:02,  8.26it/s]
+ 55%|█████▌    | 21/38 [00:02<00:02,  8.24it/s]
+ 58%|█████▊    | 22/38 [00:02<00:01,  8.17it/s]
+ 61%|██████    | 23/38 [00:02<00:01,  8.24it/s]
+ 63%|██████▎   | 24/38 [00:02<00:01,  8.18it/s]
+ 66%|██████▌   | 25/38 [00:02<00:01,  8.19it/s]
+ 68%|██████▊   | 26/38 [00:03<00:01,  8.17it/s]
+ 71%|███████   | 27/38 [00:03<00:01,  8.24it/s]
+ 74%|███████▎  | 28/38 [00:03<00:01,  8.25it/s]
+ 76%|███████▋  | 29/38 [00:03<00:01,  8.29it/s]
+ 79%|███████▉  | 30/38 [00:03<00:00,  8.24it/s]
+ 82%|████████▏ | 31/38 [00:03<00:00,  8.31it/s]
+ 84%|████████▍ | 32/38 [00:03<00:00,  8.38it/s]
+ 87%|████████▋ | 33/38 [00:03<00:00,  8.28it/s]
+ 89%|████████▉ | 34/38 [00:03<00:00,  8.24it/s]
+ 92%|█████████▏| 35/38 [00:04<00:00,  8.29it/s]
+ 95%|█████████▍| 36/38 [00:04<00:00,  8.34it/s]
+
+ 20%|██        | 574/2870 [04:00<15:39,  2.44it/s]
+100%|██████████| 38/38 [00:04<00:00,  8.26it/s]
+                                               Saving model checkpoint to gpt2-medium-finetuned-commongen\checkpoint-574
+Configuration saved in gpt2-medium-finetuned-commongen\checkpoint-574\config.json
+Configuration saved in gpt2-medium-finetuned-commongen\checkpoint-574\generation_config.json
+{'eval_loss': 2.1204423904418945, 'eval_runtime': 4.495, 'eval_samples_per_second': 66.073, 'eval_steps_per_second': 8.454, 'epoch': 1.0}
+Model weights saved in gpt2-medium-finetuned-commongen\checkpoint-574\pytorch_model.bin
+ 35%|███▍      | 1000/2870 [06:59<12:28,  2.50it/s]{'loss': 2.1332, 'learning_rate': 3.2578397212543556e-05, 'epoch': 1.74}
+ 40%|████      | 1148/2870 [07:58<11:29,  2.50it/s]***** Running Evaluation *****
+  Num examples = 297
+  Batch size = 8
+
+  0%|          | 0/38 [00:00<?, ?it/s]
+  5%|▌         | 2/38 [00:00<00:02, 15.27it/s]
+ 11%|█         | 4/38 [00:00<00:03,  9.98it/s]
+ 16%|█▌        | 6/38 [00:00<00:03,  9.21it/s]
+ 18%|█▊        | 7/38 [00:00<00:03,  9.04it/s]
+ 21%|██        | 8/38 [00:00<00:03,  8.76it/s]
+ 24%|██▎       | 9/38 [00:00<00:03,  8.64it/s]
+ 26%|██▋       | 10/38 [00:01<00:03,  8.37it/s]
+ 29%|██▉       | 11/38 [00:01<00:03,  8.44it/s]
+ 32%|███▏      | 12/38 [00:01<00:03,  8.21it/s]
+ 34%|███▍      | 13/38 [00:01<00:03,  8.33it/s]
+ 37%|███▋      | 14/38 [00:01<00:02,  8.15it/s]
+ 39%|███▉      | 15/38 [00:01<00:02,  8.28it/s]
+ 42%|████▏     | 16/38 [00:01<00:02,  8.06it/s]
+ 45%|████▍     | 17/38 [00:01<00:02,  8.22it/s]
+ 47%|████▋     | 18/38 [00:02<00:02,  8.11it/s]
+ 50%|█████     | 19/38 [00:02<00:02,  8.20it/s]
+ 53%|█████▎    | 20/38 [00:02<00:02,  8.08it/s]
+ 55%|█████▌    | 21/38 [00:02<00:02,  8.25it/s]
+ 58%|█████▊    | 22/38 [00:02<00:01,  8.02it/s]
+ 61%|██████    | 23/38 [00:02<00:01,  8.19it/s]
+ 63%|██████▎   | 24/38 [00:02<00:01,  8.16it/s]
+ 66%|██████▌   | 25/38 [00:02<00:01,  8.17it/s]
+ 68%|██████▊   | 26/38 [00:03<00:01,  8.00it/s]
+ 71%|███████   | 27/38 [00:03<00:01,  8.16it/s]
+ 74%|███████▎  | 28/38 [00:03<00:01,  8.13it/s]
+ 76%|███████▋  | 29/38 [00:03<00:01,  8.17it/s]
+ 79%|███████▉  | 30/38 [00:03<00:00,  8.00it/s]
+ 82%|████████▏ | 31/38 [00:03<00:00,  8.16it/s]
+ 84%|████████▍ | 32/38 [00:03<00:00,  8.01it/s]
+ 87%|████████▋ | 33/38 [00:03<00:00,  8.21it/s]
+ 89%|████████▉ | 34/38 [00:04<00:00,  8.14it/s]
+ 92%|█████████▏| 35/38 [00:04<00:00,  8.14it/s]
+ 95%|█████████▍| 36/38 [00:04<00:00,  8.00it/s]
+
+ 40%|████      | 1148/2870 [08:03<11:29,  2.50it/s]
+100%|██████████| 38/38 [00:04<00:00,  8.18it/s]
+                                               Saving model checkpoint to gpt2-medium-finetuned-commongen\checkpoint-1148
+Configuration saved in gpt2-medium-finetuned-commongen\checkpoint-1148\config.json
+Configuration saved in gpt2-medium-finetuned-commongen\checkpoint-1148\generation_config.json
+{'eval_loss': 2.131284475326538, 'eval_runtime': 4.5627, 'eval_samples_per_second': 65.093, 'eval_steps_per_second': 8.328, 'epoch': 2.0}
+Model weights saved in gpt2-medium-finetuned-commongen\checkpoint-1148\pytorch_model.bin
+ 52%|█████▏    | 1500/2870 [10:29<09:09,  2.49it/s]{'loss': 1.9859, 'learning_rate': 2.3867595818815333e-05, 'epoch': 2.61}
+ 60%|██████    | 1722/2870 [11:58<07:39,  2.50it/s]***** Running Evaluation *****
+  Num examples = 297
+  Batch size = 8
+
+  0%|          | 0/38 [00:00<?, ?it/s]
+  5%|▌         | 2/38 [00:00<00:02, 15.26it/s]
+ 11%|█         | 4/38 [00:00<00:03, 10.01it/s]
+ 16%|█▌        | 6/38 [00:00<00:03,  9.30it/s]
+ 18%|█▊        | 7/38 [00:00<00:03,  9.04it/s]
+ 21%|██        | 8/38 [00:00<00:03,  8.65it/s]
+ 24%|██▎       | 9/38 [00:00<00:03,  8.64it/s]
+ 26%|██▋       | 10/38 [00:01<00:03,  8.33it/s]
+ 29%|██▉       | 11/38 [00:01<00:03,  8.39it/s]
+ 32%|███▏      | 12/38 [00:01<00:03,  8.18it/s]
+ 34%|███▍      | 13/38 [00:01<00:03,  8.30it/s]
+ 37%|███▋      | 14/38 [00:01<00:02,  8.19it/s]
+ 39%|███▉      | 15/38 [00:01<00:02,  8.31it/s]
+ 42%|████▏     | 16/38 [00:01<00:02,  8.20it/s]
+ 45%|████▍     | 17/38 [00:01<00:02,  8.26it/s]
+ 47%|████▋     | 18/38 [00:02<00:02,  8.14it/s]
+ 50%|█████     | 19/38 [00:02<00:02,  8.27it/s]
+ 53%|█████▎    | 20/38 [00:02<00:02,  8.09it/s]
+ 55%|█████▌    | 21/38 [00:02<00:02,  8.22it/s]
+ 58%|█████▊    | 22/38 [00:02<00:01,  8.05it/s]
+ 61%|██████    | 23/38 [00:02<00:01,  8.19it/s]
+ 63%|██████▎   | 24/38 [00:02<00:01,  8.06it/s]
+ 66%|██████▌   | 25/38 [00:02<00:01,  8.20it/s]
+ 68%|██████▊   | 26/38 [00:03<00:01,  8.04it/s]
+ 71%|███████   | 27/38 [00:03<00:01,  8.20it/s]
+ 74%|███████▎  | 28/38 [00:03<00:01,  8.16it/s]
+ 76%|███████▋  | 29/38 [00:03<00:01,  8.15it/s]
+ 79%|███████▉  | 30/38 [00:03<00:00,  8.01it/s]
+ 82%|████████▏ | 31/38 [00:03<00:00,  8.19it/s]
+ 84%|████████▍ | 32/38 [00:03<00:00,  8.03it/s]
+ 87%|████████▋ | 33/38 [00:03<00:00,  8.18it/s]
+ 89%|████████▉ | 34/38 [00:04<00:00,  8.01it/s]
+ 92%|█████████▏| 35/38 [00:04<00:00,  8.18it/s]
+ 95%|█████████▍| 36/38 [00:04<00:00,  8.03it/s]
+
+{'eval_loss': 2.1727805137634277, 'eval_runtime': 4.5585, 'eval_samples_per_second': 65.152, 'eval_steps_per_second': 8.336, 'epoch': 3.0}
+ 60%|█████��    | 1722/2870 [12:03<07:39,  2.50it/s]
+100%|██████████| 38/38 [00:04<00:00,  8.18it/s]
+                                               Saving model checkpoint to gpt2-medium-finetuned-commongen\checkpoint-1722
+Configuration saved in gpt2-medium-finetuned-commongen\checkpoint-1722\config.json
+Configuration saved in gpt2-medium-finetuned-commongen\checkpoint-1722\generation_config.json
+Model weights saved in gpt2-medium-finetuned-commongen\checkpoint-1722\pytorch_model.bin
+ 70%|██████▉   | 2000/2870 [13:59<05:47,  2.51it/s]{'loss': 1.885, 'learning_rate': 1.5156794425087109e-05, 'epoch': 3.48}
+ 80%|████████  | 2296/2870 [15:57<03:48,  2.51it/s]***** Running Evaluation *****
+  Num examples = 297
+  Batch size = 8
+
+  0%|          | 0/38 [00:00<?, ?it/s]
+  5%|▌         | 2/38 [00:00<00:02, 14.39it/s]
+ 11%|█         | 4/38 [00:00<00:03, 10.02it/s]
+ 16%|█▌        | 6/38 [00:00<00:03,  9.21it/s]
+ 18%|█▊        | 7/38 [00:00<00:03,  9.04it/s]
+ 21%|██        | 8/38 [00:00<00:03,  8.78it/s]
+ 24%|██▎       | 9/38 [00:00<00:03,  8.62it/s]
+ 26%|██▋       | 10/38 [00:01<00:03,  8.37it/s]
+ 29%|██▉       | 11/38 [00:01<00:03,  8.42it/s]
+ 32%|███▏      | 12/38 [00:01<00:03,  8.20it/s]
+ 34%|███▍      | 13/38 [00:01<00:02,  8.34it/s]
+ 37%|███▋      | 14/38 [00:01<00:02,  8.20it/s]
+ 39%|███▉      | 15/38 [00:01<00:02,  8.26it/s]
+ 42%|████▏     | 16/38 [00:01<00:02,  8.06it/s]
+ 45%|████▍     | 17/38 [00:01<00:02,  8.22it/s]
+ 47%|████▋     | 18/38 [00:02<00:02,  8.11it/s]
+ 50%|█████     | 19/38 [00:02<00:02,  8.26it/s]
+ 53%|█████▎    | 20/38 [00:02<00:02,  8.14it/s]
+ 55%|█████▌    | 21/38 [00:02<00:02,  8.28it/s]
+ 58%|█████▊    | 22/38 [00:02<00:01,  8.15it/s]
+ 61%|██████    | 23/38 [00:02<00:01,  8.29it/s]
+ 63%|██████▎   | 24/38 [00:02<00:01,  8.16it/s]
+ 66%|██████▌   | 25/38 [00:02<00:01,  8.31it/s]
+ 68%|██████▊   | 26/38 [00:03<00:01,  8.10it/s]
+ 71%|███████   | 27/38 [00:03<00:01,  8.27it/s]
+ 74%|███████▎  | 28/38 [00:03<00:01,  8.07it/s]
+ 76%|███████▋  | 29/38 [00:03<00:01,  8.22it/s]
+ 79%|███████▉  | 30/38 [00:03<00:00,  8.04it/s]
+ 82%|████████▏ | 31/38 [00:03<00:00,  8.20it/s]
+ 84%|████████▍ | 32/38 [00:03<00:00,  8.04it/s]
+ 87%|████████▋ | 33/38 [00:03<00:00,  8.21it/s]
+ 89%|████████▉ | 34/38 [00:04<00:00,  8.03it/s]
+ 92%|█████████▏| 35/38 [00:04<00:00,  8.20it/s]
+ 95%|█████████▍| 36/38 [00:04<00:00,  8.04it/s]
+
+{'eval_loss': 2.2184627056121826, 'eval_runtime': 4.5511, 'eval_samples_per_second': 65.259, 'eval_steps_per_second': 8.35, 'epoch': 4.0}
+ 80%|████████  | 2296/2870 [16:01<03:48,  2.51it/s]
+100%|██████████| 38/38 [00:04<00:00,  8.20it/s]
+                                               Saving model checkpoint to gpt2-medium-finetuned-commongen\checkpoint-2296
+Configuration saved in gpt2-medium-finetuned-commongen\checkpoint-2296\config.json
+Configuration saved in gpt2-medium-finetuned-commongen\checkpoint-2296\generation_config.json
+Model weights saved in gpt2-medium-finetuned-commongen\checkpoint-2296\pytorch_model.bin
+ 87%|████████▋ | 2500/2870 [17:28<02:28,  2.50it/s]{'loss': 1.8157, 'learning_rate': 6.445993031358885e-06, 'epoch': 4.36}
+100%|██████████| 2870/2870 [19:56<00:00,  2.49it/s]***** Running Evaluation *****
+  Num examples = 297
+  Batch size = 8
+
+  0%|          | 0/38 [00:00<?, ?it/s]
+  5%|▌         | 2/38 [00:00<00:02, 14.49it/s]
+ 11%|█         | 4/38 [00:00<00:03, 10.04it/s]
+ 16%|█▌        | 6/38 [00:00<00:03,  9.32it/s]
+ 18%|█▊        | 7/38 [00:00<00:03,  9.08it/s]
+ 21%|██        | 8/38 [00:00<00:03,  8.63it/s]
+ 24%|██▎       | 9/38 [00:00<00:03,  8.63it/s]
+ 26%|██▋       | 10/38 [00:01<00:03,  8.33it/s]
+ 29%|██▉       | 11/38 [00:01<00:03,  8.41it/s]
+ 32%|███▏      | 12/38 [00:01<00:03,  8.19it/s]
+ 34%|███▍      | 13/38 [00:01<00:03,  8.31it/s]
+ 37%|███▋      | 14/38 [00:01<00:02,  8.12it/s]
+ 39%|███▉      | 15/38 [00:01<00:02,  8.26it/s]
+ 42%|████▏     | 16/38 [00:01<00:02,  8.08it/s]
+ 45%|████▍     | 17/38 [00:01<00:02,  8.24it/s]
+ 47%|████▋     | 18/38 [00:02<00:02,  8.07it/s]
+ 50%|█████     | 19/38 [00:02<00:02,  8.22it/s]
+ 53%|█████▎    | 20/38 [00:02<00:02,  8.04it/s]
+ 55%|█████▌    | 21/38 [00:02<00:02,  8.20it/s]
+ 58%|█████▊    | 22/38 [00:02<00:01,  8.02it/s]
+ 61%|██████    | 23/38 [00:02<00:01,  8.19it/s]
+ 63%|██████▎   | 24/38 [00:02<00:01,  8.17it/s]
+ 66%|██████▌   | 25/38 [00:02<00:01,  8.18it/s]
+ 68%|██████▊   | 26/38 [00:03<00:01,  8.03it/s]
+ 71%|███████   | 27/38 [00:03<00:01,  8.18it/s]
+ 74%|███████▎  | 28/38 [00:03<00:01,  8.03it/s]
+ 76%|███████▋  | 29/38 [00:03<00:01,  8.20it/s]
+ 79%|███████▉  | 30/38 [00:03<00:00,  8.18it/s]
+ 82%|████████▏ | 31/38 [00:03<00:00,  8.18it/s]
+ 84%|████████▍ | 32/38 [00:03<00:00,  8.01it/s]
+ 87%|████████▋ | 33/38 [00:03<00:00,  8.16it/s]
+ 89%|████████▉ | 34/38 [00:04<00:00,  8.02it/s]
+ 92%|█████████▏| 35/38 [00:04<00:00,  8.19it/s]
+ 95%|█████████▍| 36/38 [00:04<00:00,  8.03it/s]
+
+{'eval_loss': 2.2336463928222656, 'eval_runtime': 4.5651, 'eval_samples_per_second': 65.059, 'eval_steps_per_second': 8.324, 'epoch': 5.0}
+100%|██████████| 2870/2870 [20:01<00:00,  2.49it/s]
+100%|██████████| 38/38 [00:04<00:00,  8.20it/s]
+                                               Saving model checkpoint to gpt2-medium-finetuned-commongen\checkpoint-2870
+Configuration saved in gpt2-medium-finetuned-commongen\checkpoint-2870\config.json
+Configuration saved in gpt2-medium-finetuned-commongen\checkpoint-2870\generation_config.json
+Model weights saved in gpt2-medium-finetuned-commongen\checkpoint-2870\pytorch_model.bin
+
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+Loading best model from gpt2-medium-finetuned-commongen\checkpoint-574 (score: 2.1204423904418945).
+{'train_runtime': 1208.3557, 'train_samples_per_second': 19.001, 'train_steps_per_second': 2.375, 'train_loss': 2.0178993145347888, 'epoch': 5.0}
+100%|██████████| 2870/2870 [20:08<00:00,  2.38it/s]
+Saving model checkpoint to gpt2-medium-finetuned-commongen
+Configuration saved in gpt2-medium-finetuned-commongen\config.json
+Configuration saved in gpt2-medium-finetuned-commongen\generation_config.json
+Model weights saved in gpt2-medium-finetuned-commongen\pytorch_model.bin

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b137bf1edc916528945b557b930e16ce5b38fdb15382f6071cfe065758708add
+size 3579