Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c375946bea59b8e753f0ebc1e9914a2da39e1aa6d22f171b0f856a44092946f
+oid sha256:5f9341337fe75b4774a0ec41f29c999e21bf5b10b633c07b804a59a9b3102a1f
 size 267832560

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

run-1/checkpoint-108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea05c446d657e32c5e55fbc4d18b773ea7b9aa315c589f668c31a9ab5803d2b
+size 267832560

run-1/checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ba465dd1c41addfeed61a1225959939e586888b520699bb929f14b6d3bae0d7
+size 535727290

run-1/checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd538b40b5e376328ac0270ddd397017a003ad0a9a2a76406475d6253e3ccebb
+size 14308

run-1/checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:879e8bf86c00303878d56d3e0aa14f0e62be835aa75005a8dca119d91f15a207
+size 1064

run-1/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-1/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-1/checkpoint-108/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.28705233720123585,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-108",
+  "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": 0.6071667075157166,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7427,
+      "eval_samples_per_second": 1404.262,
+      "eval_steps_per_second": 88.86,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5741562247276306,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7709,
+      "eval_samples_per_second": 1353.039,
+      "eval_steps_per_second": 85.619,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5594291687011719,
+      "eval_matthews_correlation": 0.22891469610262768,
+      "eval_runtime": 1.3341,
+      "eval_samples_per_second": 781.793,
+      "eval_steps_per_second": 49.471,
+      "step": 81
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5665815472602844,
+      "eval_matthews_correlation": 0.28705233720123585,
+      "eval_runtime": 1.1697,
+      "eval_samples_per_second": 891.671,
+      "eval_steps_per_second": 56.424,
+      "step": 108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6729437236425433e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 29
+  }
+}

run-1/checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e40ddc88d1c649395128f3a5c9afae8b6e9d0ff360ce6e6c1ebf6c4c2a28434
+size 4984

run-1/checkpoint-135/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-135/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75e9e3c94a295590244b7a0a8483cb0a6e0a91a6eab4a256f0598923198133b
+size 267832560

run-1/checkpoint-135/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f24ea4daa7ffa4ab51fc1392a0f383ce82fe3c3fd250915bfff14d525c640d
+size 535727290

run-1/checkpoint-135/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498ed256df9a7e8cbaa8109e99b00f876288489cc2c6e90af78f1b2a903f8fef
+size 14308

run-1/checkpoint-135/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aede505fa55d5975b81bd7abf0f74c96b962906c5961871671e558f5cacbb825
+size 1064

run-1/checkpoint-135/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-135/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-135/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": 0.3026133754974134,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-135",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 135,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6071667075157166,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7427,
+      "eval_samples_per_second": 1404.262,
+      "eval_steps_per_second": 88.86,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5741562247276306,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7709,
+      "eval_samples_per_second": 1353.039,
+      "eval_steps_per_second": 85.619,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5594291687011719,
+      "eval_matthews_correlation": 0.22891469610262768,
+      "eval_runtime": 1.3341,
+      "eval_samples_per_second": 781.793,
+      "eval_steps_per_second": 49.471,
+      "step": 81
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5665815472602844,
+      "eval_matthews_correlation": 0.28705233720123585,
+      "eval_runtime": 1.1697,
+      "eval_samples_per_second": 891.671,
+      "eval_steps_per_second": 56.424,
+      "step": 108
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5657250881195068,
+      "eval_matthews_correlation": 0.3026133754974134,
+      "eval_runtime": 1.2172,
+      "eval_samples_per_second": 856.881,
+      "eval_steps_per_second": 54.223,
+      "step": 135
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6729437236425433e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 29
+  }
+}

run-1/checkpoint-135/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e40ddc88d1c649395128f3a5c9afae8b6e9d0ff360ce6e6c1ebf6c4c2a28434
+size 4984

run-1/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-1/checkpoint-54/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed490708a8dc9005a984df34b90e717a2356cd84d8792e6e449e3d781ff6e2c
+size 267832560

run-1/checkpoint-54/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aeb5a87759c5d750c9503803dc4902ec7d73e53dffdc9fb6cc6220f38a98bf4
+size 535727290

run-1/checkpoint-54/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66a2fa1cff907046cb769c2c23d55bfab9701864d47b50571e12b3b51b706c6
+size 14308

run-1/checkpoint-54/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d969a02d4f06e2d6f4ebdd2bcc849155494fad7d6e34998d8b33b9e024ae4b7
+size 1064

run-1/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-1/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-1/checkpoint-54/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 0.6071667075157166,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7427,
+      "eval_samples_per_second": 1404.262,
+      "eval_steps_per_second": 88.86,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5741562247276306,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7709,
+      "eval_samples_per_second": 1353.039,
+      "eval_steps_per_second": 85.619,
+      "step": 54
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6729437236425433e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 29
+  }
+}

run-1/checkpoint-54/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e40ddc88d1c649395128f3a5c9afae8b6e9d0ff360ce6e6c1ebf6c4c2a28434
+size 4984

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

run-1/checkpoint-81/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d82d650f7194fb62269ea557559948558f64c04090d4132d3757d7cf5346c3df
+size 267832560

run-1/checkpoint-81/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb38fa42842c9c6ee470ead777fb880b3c2ee4c0ec3831a5cc27bfb1ebffe3f
+size 535727290

run-1/checkpoint-81/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90ba11e095f2bce4cc3e84a1d73066fa99734a63bf6e277e2f29599058cf2c56
+size 14308

run-1/checkpoint-81/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ae7750bee7bfe6ac678ffe35f0527a405e5b7e209dd8a5cc8ca3081418e852
+size 1064

run-1/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-1/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-1/checkpoint-81/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.22891469610262768,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 0.6071667075157166,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7427,
+      "eval_samples_per_second": 1404.262,
+      "eval_steps_per_second": 88.86,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5741562247276306,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7709,
+      "eval_samples_per_second": 1353.039,
+      "eval_steps_per_second": 85.619,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5594291687011719,
+      "eval_matthews_correlation": 0.22891469610262768,
+      "eval_runtime": 1.3341,
+      "eval_samples_per_second": 781.793,
+      "eval_steps_per_second": 49.471,
+      "step": 81
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6729437236425433e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 29
+  }
+}

run-1/checkpoint-81/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e40ddc88d1c649395128f3a5c9afae8b6e9d0ff360ce6e6c1ebf6c4c2a28434
+size 4984

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

run-2/checkpoint-14/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9341337fe75b4774a0ec41f29c999e21bf5b10b633c07b804a59a9b3102a1f
+size 267832560

run-2/checkpoint-14/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92a72035f6142b5de8d9ce90f5defbb885e212730082e135f60255a2c98a5ed
+size 535727290

run-2/checkpoint-14/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ed288cd1d7f33983e156ebb2b0d229399c8436f09fc8fec974bc8a222d9801
+size 14308

run-2/checkpoint-14/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e24026de726dd437485f8eb30cc7b147fa06b78a17944b07d10a7664657189
+size 1064