Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:787954613f44e4663c42543d9fe668f4e267480a972d0f0b3e45c093793760ce
+oid sha256:01fc96d144ec639072ef6fb21284cff73f4bacbdae788fe3849cd8f6473e6ad5
 size 267832560

run-2/checkpoint-28/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-28/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d5475134b0d8d15645f58b1aaa8c8daa220af7406d8fe49662ad1a311361ddc
+size 267832560

run-2/checkpoint-28/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aed56f35bb59dfbd38c38a21e712ef794d6e6fdf5bd1cfa33eea5f42f702536
+size 535727290

run-2/checkpoint-28/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa60102c035cbba7028976710753ada479d38c34d83eeb4af0457a69a243d5bd
+size 14308

run-2/checkpoint-28/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abb70fec8961811bbf70b0f94cdafec3c8c95d40f26a346548fc09ef0d49206
+size 1064

run-2/checkpoint-28/special_tokens_map.json

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

run-2/checkpoint-28/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-2/checkpoint-28/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.32301000206570946,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-28",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 28,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5672691464424133,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4893,
+      "eval_samples_per_second": 2131.421,
+      "eval_steps_per_second": 134.874,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6490755677223206,
+      "eval_matthews_correlation": 0.32301000206570946,
+      "eval_runtime": 0.4762,
+      "eval_samples_per_second": 2190.233,
+      "eval_steps_per_second": 138.596,
+      "step": 28
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 70,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.881638457643646e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 17
+  }
+}

run-2/checkpoint-28/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8a2f53a405f321cf90788b9039982bb31601b72430591127a453fbb500d00a
+size 4984

run-2/checkpoint-42/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-42/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f317f00ceaab169e3b4049dc4bd80cd81c4ca3fe157906612cd935bcd670ed3
+size 267832560

run-2/checkpoint-42/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f29fdab247d13baeb4322c57c55178ec22e55b4f4f2770ba6c9dbdbe18a8c7d
+size 535727290

run-2/checkpoint-42/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d566e55f63c120a87424d9197348969714c658b1ea03a005e91d60234016fe33
+size 14308

run-2/checkpoint-42/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b18d3a2602b65c5dc1fb610798f1b8009f1ef67d8d8635e764b3838f201c92
+size 1064

run-2/checkpoint-42/special_tokens_map.json

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

run-2/checkpoint-42/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-2/checkpoint-42/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.3666014217930852,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-42",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 42,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5672691464424133,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4893,
+      "eval_samples_per_second": 2131.421,
+      "eval_steps_per_second": 134.874,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6490755677223206,
+      "eval_matthews_correlation": 0.32301000206570946,
+      "eval_runtime": 0.4762,
+      "eval_samples_per_second": 2190.233,
+      "eval_steps_per_second": 138.596,
+      "step": 28
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7178954482078552,
+      "eval_matthews_correlation": 0.3666014217930852,
+      "eval_runtime": 0.5039,
+      "eval_samples_per_second": 2069.918,
+      "eval_steps_per_second": 130.982,
+      "step": 42
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 70,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.881638457643646e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 17
+  }
+}

run-2/checkpoint-42/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8a2f53a405f321cf90788b9039982bb31601b72430591127a453fbb500d00a
+size 4984

run-2/checkpoint-56/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-56/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a51a98da0a2acb16c4a7d7630f15ccbf943610ae6197b52a8ad888c4815c671
+size 267832560

run-2/checkpoint-56/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab205ea60cfab7e42d3bbd5f8781c9a79b4b509417137d2c5d1e4b2819f5053
+size 535727290

run-2/checkpoint-56/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef39d81c42a9c79c6cc646812ca39e1b95a3d343fab288cc4b7cf06f390f2790
+size 14308

run-2/checkpoint-56/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c4d1514cdc16dc6fe38175fa6b1648adfbc44b1cd16781f9279c727d4898cd
+size 1064

run-2/checkpoint-56/special_tokens_map.json

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

run-2/checkpoint-56/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-2/checkpoint-56/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.3721270886368035,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-56",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 56,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5672691464424133,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4893,
+      "eval_samples_per_second": 2131.421,
+      "eval_steps_per_second": 134.874,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6490755677223206,
+      "eval_matthews_correlation": 0.32301000206570946,
+      "eval_runtime": 0.4762,
+      "eval_samples_per_second": 2190.233,
+      "eval_steps_per_second": 138.596,
+      "step": 28
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7178954482078552,
+      "eval_matthews_correlation": 0.3666014217930852,
+      "eval_runtime": 0.5039,
+      "eval_samples_per_second": 2069.918,
+      "eval_steps_per_second": 130.982,
+      "step": 42
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8480371832847595,
+      "eval_matthews_correlation": 0.3721270886368035,
+      "eval_runtime": 0.4908,
+      "eval_samples_per_second": 2125.166,
+      "eval_steps_per_second": 134.478,
+      "step": 56
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 70,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.881638457643646e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 17
+  }
+}

run-2/checkpoint-56/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8a2f53a405f321cf90788b9039982bb31601b72430591127a453fbb500d00a
+size 4984

run-2/checkpoint-70/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-70/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a42792e27666366082c2ffd3da3bb10bd64d6b6cce7dd57d36d0177e37eceea8
+size 267832560

run-2/checkpoint-70/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7c2a4e5bcf7f606fb53e4952593fe84fb92ac44842dcd664b08337599214b9
+size 535727290

run-2/checkpoint-70/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463c22dac687af47d21ab331b20eeca568cafeee7fcd7c6f04335610c09d3475
+size 14308

run-2/checkpoint-70/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a8f5bb53fea4846b9e8566ecd1f80c789b61ef5f5ce16749841723b9f1adbd
+size 1064

run-2/checkpoint-70/special_tokens_map.json

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

run-2/checkpoint-70/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-2/checkpoint-70/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": 0.3721270886368035,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-56",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 70,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5672691464424133,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4893,
+      "eval_samples_per_second": 2131.421,
+      "eval_steps_per_second": 134.874,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6490755677223206,
+      "eval_matthews_correlation": 0.32301000206570946,
+      "eval_runtime": 0.4762,
+      "eval_samples_per_second": 2190.233,
+      "eval_steps_per_second": 138.596,
+      "step": 28
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7178954482078552,
+      "eval_matthews_correlation": 0.3666014217930852,
+      "eval_runtime": 0.5039,
+      "eval_samples_per_second": 2069.918,
+      "eval_steps_per_second": 130.982,
+      "step": 42
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8480371832847595,
+      "eval_matthews_correlation": 0.3721270886368035,
+      "eval_runtime": 0.4908,
+      "eval_samples_per_second": 2125.166,
+      "eval_steps_per_second": 134.478,
+      "step": 56
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.928974986076355,
+      "eval_matthews_correlation": 0.3513943614298585,
+      "eval_runtime": 0.4823,
+      "eval_samples_per_second": 2162.407,
+      "eval_steps_per_second": 136.835,
+      "step": 70
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 70,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.881638457643646e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 17
+  }
+}

run-2/checkpoint-70/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8a2f53a405f321cf90788b9039982bb31601b72430591127a453fbb500d00a
+size 4984

run-3/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-3/checkpoint-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01fc96d144ec639072ef6fb21284cff73f4bacbdae788fe3849cd8f6473e6ad5
+size 267832560

run-3/checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d945b0e9f5247b253f39cd70d85b8ae819ef9ec1a115f56178370ee460a45bd
+size 535727290

run-3/checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91fb4d02591f83254765fd7c519e8196113a2bad0a42c89ead729de6baea4828
+size 14308

run-3/checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695b2efe3133e58ffefe1f8c828b87ce3d9ae0e829707be3e4a0978b0bca71a5
+size 1064