Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:118b9e30d6ba753e129f144784e81c66c9f54dfe0e443e050a97f3aee09e6a89
+oid sha256:74155891d985b0d42ab73fff22f25b8d3ec62478beed1d5b251aca605465c701
 size 267832560

run-0/checkpoint-108/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc23ec6c9b99f7db9871e18c0c6c6b5a7f76de0099a138273dde8a71f02c418
+size 267832560

run-0/checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2813b65a0911926f37d8128a020a6d3edd9bf71c2e3e2664a98ca4d2271e0f5a
+size 535727290

run-0/checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d344819f2e055d3295c3153ae912bf7e7a3a1b7486fccd5b5f6d042316f900
+size 14244

run-0/checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67956c369d07429b010040d83c80330b5c70f2c6ea13f345939bbacb8a220880
+size 1064

run-0/checkpoint-108/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-108/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-108/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.3508011277661142,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-81",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5963238477706909,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4957,
+      "eval_samples_per_second": 2103.954,
+      "eval_steps_per_second": 133.136,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5681455731391907,
+      "eval_matthews_correlation": 0.2145337380780115,
+      "eval_runtime": 0.5534,
+      "eval_samples_per_second": 1884.845,
+      "eval_steps_per_second": 119.271,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5657972693443298,
+      "eval_matthews_correlation": 0.3508011277661142,
+      "eval_runtime": 0.5816,
+      "eval_samples_per_second": 1793.217,
+      "eval_steps_per_second": 113.473,
+      "step": 81
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5970165133476257,
+      "eval_matthews_correlation": 0.3395845015956295,
+      "eval_runtime": 0.7089,
+      "eval_samples_per_second": 1471.251,
+      "eval_steps_per_second": 93.099,
+      "step": 108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.092084833236513e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 5
+  }
+}

run-0/checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0528b625bd56c5f820c6a81109a84f0cb3b06c0ef021c43787878a2c5d2ba02
+size 4984

run-0/checkpoint-27/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7da22ad4eab57d7f75f227a7e86180d679df13dd0f44ce401b24a90efb8d2b
+size 267832560

run-0/checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d289e6ab0d6a4cfb2126a250cb48079727e361c488c719ebbdfe227c47bdc1f
+size 535727290

run-0/checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cc9229173c7c9478c79be5e4d3be5b496d0478c042c4a00eef5442cda10e039
+size 14244

run-0/checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faed53a12ca49031f285ccdbb56fa11610bb4e971c2b33e5ef9375c9a2a7d448
+size 1064

run-0/checkpoint-27/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-27/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-27/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-27",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5963238477706909,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4957,
+      "eval_samples_per_second": 2103.954,
+      "eval_steps_per_second": 133.136,
+      "step": 27
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.092084833236513e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 5
+  }
+}

run-0/checkpoint-27/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0528b625bd56c5f820c6a81109a84f0cb3b06c0ef021c43787878a2c5d2ba02
+size 4984

run-0/checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb29a274a9f4796cfc327e736fcf38327227a01cb03b7189ba50dbb219592b9
+oid sha256:b4b6a63ce9d46e1ae3cde219ca81b1533b07205e9af068914457b198860a26d5
 size 267832560

run-0/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8e09f1a6c11df4f5e819d4994208eaea6a30d494e70cd0d49380f5f1a4c7f31
+oid sha256:f0f74901e395bdea4b91798c80ae61a3c84da4be2eeebab193e6995ae7a567ba
 size 535727290

run-0/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44da968c6952a4010dfe7ab99b3b2a5e8ed126ffb3289a260aed361d65a6001c
+oid sha256:6ac6a3f739be45632e4af9f35c1d9c117846755b0a505b5a570d07cb5b90b58f
 size 14244

run-0/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebfa140991c390428dd17747db69853d779663c4aca0a3c1e089933ba28ed9eb
+oid sha256:bcc93b69403b1613e45b57f6a0bcd68f331b2f63242419eb3b3da8f1b645a82c
 size 1064

run-0/checkpoint-54/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.0463559874942472,
+  "best_metric": 0.2145337380780115,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-54",
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 54,
   "is_hyper_param_search": true,
@@ -10,26 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5884751677513123,
-      "eval_matthews_correlation": 0.0463559874942472,
-      "eval_runtime": 0.4958,
-      "eval_samples_per_second": 2103.484,
-      "eval_steps_per_second": 133.106,
+      "eval_loss": 0.5963238477706909,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4957,
+      "eval_samples_per_second": 2103.954,
+      "eval_steps_per_second": 133.136,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5681455731391907,
+      "eval_matthews_correlation": 0.2145337380780115,
+      "eval_runtime": 0.5534,
+      "eval_samples_per_second": 1884.845,
+      "eval_steps_per_second": 119.271,
       "step": 54
     }
   ],
   "logging_steps": 500,
-  "max_steps": 54,
+  "max_steps": 108,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 16,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 6.512461119853454e-05,
-    "num_train_epochs": 1,
-    "per_device_train_batch_size": 16,
-    "seed": 3
+    "learning_rate": 3.092084833236513e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 5
   }
 }

run-0/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cfb5803ec23c1c2dd9c46be94ed5fddaf79512fab886cf00c69777f781c10dd
+oid sha256:b0528b625bd56c5f820c6a81109a84f0cb3b06c0ef021c43787878a2c5d2ba02
 size 4984

run-0/checkpoint-81/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-81/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa281389f8903747b388fa28b77c7ab78085becf5516402c2cf418720384c017
+size 267832560

run-0/checkpoint-81/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798daf08ae165353999bf64897f5602447c4a3bc1339ad7deef64facf65e5dfc
+size 535727290

run-0/checkpoint-81/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ea43076e2a6a6f6fccc5e1bba1409298cbb028a45bcde1e1db4c9d96576bc5
+size 14244

run-0/checkpoint-81/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d846dcb394c6918f7be65f8e45ab030343a71ddbde11836828150e64a603805a
+size 1064

run-0/checkpoint-81/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-81/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-81/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.3508011277661142,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-81",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 81,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5963238477706909,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4957,
+      "eval_samples_per_second": 2103.954,
+      "eval_steps_per_second": 133.136,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5681455731391907,
+      "eval_matthews_correlation": 0.2145337380780115,
+      "eval_runtime": 0.5534,
+      "eval_samples_per_second": 1884.845,
+      "eval_steps_per_second": 119.271,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5657972693443298,
+      "eval_matthews_correlation": 0.3508011277661142,
+      "eval_runtime": 0.5816,
+      "eval_samples_per_second": 1793.217,
+      "eval_steps_per_second": 113.473,
+      "step": 81
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.092084833236513e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 5
+  }
+}

run-0/checkpoint-81/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0528b625bd56c5f820c6a81109a84f0cb3b06c0ef021c43787878a2c5d2ba02
+size 4984

run-1/checkpoint-14/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-14/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74155891d985b0d42ab73fff22f25b8d3ec62478beed1d5b251aca605465c701
+size 267832560

run-1/checkpoint-14/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86309ebdef9cc2efb3682147508f45e81a889cc00200e9c99edf3cf8cc624a4
+size 535727290

run-1/checkpoint-14/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389cabed0d047b1be35be02b5952ab8e1860c987423c5e5cff25a6eb6f41b94c
+size 14244

run-1/checkpoint-14/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f07ea2836ff7c1f70c312e54c4927fac05939742a8500a18c3733797c5a086c
+size 1064

run-1/checkpoint-14/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-14/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-14/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": -0.004094348593533731,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-14",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 14,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6712570190429688,
+      "eval_matthews_correlation": -0.004094348593533731,
+      "eval_runtime": 0.4692,
+      "eval_samples_per_second": 2222.921,
+      "eval_steps_per_second": 140.664,
+      "step": 14
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 28,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.482861293435522e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64,
+    "seed": 22
+  }
+}

run-1/checkpoint-14/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df0f639343d75cb266d6d449e470a6f2e2f119cf3158ecf6b8d9125888beaf82
+size 4984