Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be4d7435872c2d1b12199f3cf150185fa3c9e6ef3b0f9097141f6d5c40405ac
+oid sha256:489e1a0abcb037eb7dc061054b1f47203e044d66938c47ac0d0cfc81e5533ad6
 size 267832560

run-0/checkpoint-27/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91af475fd2b2d56257e2e3a818c4da6e7d9b8274095e7806b65a5addff899a67
+oid sha256:781270389c8e467dbd57f8e0e8cb42fc60e1973a73ceb479703b33f718ba60c4
 size 267832560

run-0/checkpoint-27/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ad58ab5a532f25eb40ce1755ac7571be3d33f0784d05ed83e56e802bc27ce88
+oid sha256:dfca6e35b448ba025afaed0df1cce257c6d1d924d32a73d3c25673d2665872bc
 size 535727290

run-0/checkpoint-27/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ead47b2f2567648ce574bbf6c0a46d8ef7b32e7fa89ee7b50934a8b9edfd7c75
+oid sha256:6ed8a6a7cc9ad4d74bd0b8d8702a11fc742a13b46a022e73d93059df839e309c
 size 14308

run-0/checkpoint-27/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db2d6b3f215836cbd143b40035ff957d8166197f84598875db8b97f665054611
+oid sha256:1a15680c56ccb334d92958b387ced800a0376f792cc26882cdb7ce83c7a13a96
 size 1064

run-0/checkpoint-27/trainer_state.json

@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6102426052093506,
+      "eval_loss": 0.6574864983558655,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.9488,
-      "eval_samples_per_second": 1099.274,
-      "eval_steps_per_second": 69.561,
+      "eval_runtime": 1.9642,
+      "eval_samples_per_second": 531.017,
+      "eval_steps_per_second": 66.695,
       "step": 27
     }
   ],
   "logging_steps": 500,
-  "max_steps": 108,
+  "max_steps": 54,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 32,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.559780212217026e-05,
-    "num_train_epochs": 4,
-    "per_device_train_batch_size": 32,
-    "seed": 32
+    "learning_rate": 5.3265813071360445e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 13
   }
 }

run-0/checkpoint-27/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d2f9695e673b526ea3b986464bec921862363aca43669741ff3d3f92a54834e
+oid sha256:f70adfe015fecd9960d47db1a6db0b2fcb189135dac63884bd43ef51a4d93bd7
 size 4984

run-0/checkpoint-54/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": "4.38.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-54/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:196f3218ba1222be1a340f6322c644b711d0e75cadabce3c76e202be760cf799
+size 267832560

run-0/checkpoint-54/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f602613131cd52df0ff8a113bbad897337a6eb05ef327bec8da3ac7bb8575d7
+size 535727290

run-0/checkpoint-54/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77913aae7e298c2cba21379b940dc1d2776712c26786cfff65112dc563603ed4
+size 14308

run-0/checkpoint-54/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c19b2ce51a171519d7012b0faf139bef36a3fb0461aa0b09bffe9d16a1edcc52
+size 1064

run-0/checkpoint-54/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-54/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-54/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-27",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 54,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6574864983558655,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9642,
+      "eval_samples_per_second": 531.017,
+      "eval_steps_per_second": 66.695,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.639704167842865,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 3.0976,
+      "eval_samples_per_second": 336.715,
+      "eval_steps_per_second": 42.291,
+      "step": 54
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 54,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.3265813071360445e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 13
+  }
+}

run-0/checkpoint-54/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70adfe015fecd9960d47db1a6db0b2fcb189135dac63884bd43ef51a4d93bd7
+size 4984

run-1/checkpoint-107/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": "4.38.1",
+  "vocab_size": 30522
+}

run-1/checkpoint-107/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b828a4daa2b8031a9a3681255c0aabbc5f768abdff88bfb6f6fa6c41b7efcbd7
+size 267832560

run-1/checkpoint-107/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b2a50d83bc576bfccb57053ceb245062fc59452ab4fd4ef10c517770b0c5ab
+size 535727290

run-1/checkpoint-107/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aeded5f395e9f5a2c1bef6bb1bad380e929c54cfbc8cdc92eff01e1acefe73c
+size 14244

run-1/checkpoint-107/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b908ec7b37a2a9c729a1c8e02dadf0c0e005f404c0c7442b295cc3ef71da124
+size 1064

run-1/checkpoint-107/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-107/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-107/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-107",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 107,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6146374940872192,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.9611,
+      "eval_samples_per_second": 1085.271,
+      "eval_steps_per_second": 136.309,
+      "step": 107
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.953884936724958e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 3
+  }
+}

run-1/checkpoint-107/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee984d70f75a2468c22cfd998312bd4d58e9705e58ec6c050f6541fd5b4a56c
+size 4984

run-1/checkpoint-214/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": "4.38.1",
+  "vocab_size": 30522
+}

run-1/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f096769a07348351c66424a96eae861b86cf5cf737bcb2f362fc890c5f507669
+size 267832560

run-1/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36d655f7c68dc7c479ac783c986d41bf89ae7bacaccaec7fa2e24b1989c9dcc
+size 535727290

run-1/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7289d6b29aa9ab85a7afa321503098b917e1616d0eebe7c14318e153361c88f
+size 14244

run-1/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4285d38d8f4e0e6bb0170539e0c23d3c7dc320358fe790ade66671b8168b5a7f
+size 1064

run-1/checkpoint-214/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-214/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-214/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-107",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 214,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6146374940872192,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.9611,
+      "eval_samples_per_second": 1085.271,
+      "eval_steps_per_second": 136.309,
+      "step": 107
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6122422218322754,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 3.3931,
+      "eval_samples_per_second": 307.393,
+      "eval_steps_per_second": 38.608,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.953884936724958e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 3
+  }
+}

run-1/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee984d70f75a2468c22cfd998312bd4d58e9705e58ec6c050f6541fd5b4a56c
+size 4984

run-2/checkpoint-108/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94b6f1e3c1a543d3f1944a51003949b115ae8684a480dbb510f856e0cc2aa8fa
+oid sha256:ceb10accb7d81d35bbe681a361518215f1c20603c73d5f80952c90c7f2ae0e0e
 size 267832560

run-2/checkpoint-108/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf9d74ca447919cb00c2eb2466bdbfc459d010f4ef881dabb2b5815b29de6ead
+oid sha256:dc7fac18aac4649a912f79250471ba9db02c39006c1847ddebf752fff8ca813e
 size 535727290

run-2/checkpoint-108/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455d3c21c1a460a690a7144ff5008874689ceac0c59ef21436ace505b2ab9be9
+oid sha256:652f44369c98326325ee34bc25593c43c4fd2b79776ee36a5b95ff0814413f2f
 size 14244

run-2/checkpoint-108/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2a64c6dc2736b6f206a7df5acdc80d91a138f9fc193e0cf29be85a539520c91
+oid sha256:c86af6e14fb62c9b95af8323f459c530a752a2b1249666161ba3ff55f8ef2ef4
 size 1064

run-2/checkpoint-108/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.170590548044492,
+  "best_metric": 0.06558874629318973,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-108",
-  "epoch": 2.0,
+  "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 108,
   "is_hyper_param_search": true,
@@ -10,35 +10,53 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5949434041976929,
+      "eval_loss": 0.6096456050872803,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6642,
-      "eval_samples_per_second": 1570.266,
-      "eval_steps_per_second": 99.365,
-      "step": 54
+      "eval_runtime": 1.4581,
+      "eval_samples_per_second": 715.302,
+      "eval_steps_per_second": 89.841,
+      "step": 27
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.5589540004730225,
-      "eval_matthews_correlation": 0.170590548044492,
-      "eval_runtime": 1.2474,
-      "eval_samples_per_second": 836.172,
-      "eval_steps_per_second": 52.912,
+      "eval_loss": 0.597160816192627,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.2595,
+      "eval_samples_per_second": 828.082,
+      "eval_steps_per_second": 104.006,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5858974456787109,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.2399,
+      "eval_samples_per_second": 841.219,
+      "eval_steps_per_second": 105.656,
+      "step": 81
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5826720595359802,
+      "eval_matthews_correlation": 0.06558874629318973,
+      "eval_runtime": 1.4527,
+      "eval_samples_per_second": 717.949,
+      "eval_steps_per_second": 90.174,
       "step": 108
     }
   ],
   "logging_steps": 500,
-  "max_steps": 162,
+  "max_steps": 108,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.8548433860537384e-05,
-    "num_train_epochs": 3,
+    "learning_rate": 1.5597728261866613e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 16,
-    "seed": 19
+    "seed": 23
   }
 }

run-2/checkpoint-108/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f43db310149dc85ff8b52f32f702ad0e0fc7c0abc14ab704372d592275b95932
+oid sha256:19211b12813edf1c7b40cfe693e9822ce2b40a82fd578e9939d526af991d8e58
 size 4984

run-2/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": "4.38.1",
+  "vocab_size": 30522
+}

run-2/checkpoint-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:489e1a0abcb037eb7dc061054b1f47203e044d66938c47ac0d0cfc81e5533ad6
+size 267832560

run-2/checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f3991edcc498a3667fd025d53dbc2cd1742c5fa5ab78a84b8537de640d6d66a
+size 535727290

run-2/checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f71081fa25de27f6b6bcba854528dd775e89167c3ada2997c3434ae8b86f8c
+size 14244