Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1aa681463369c5518af56b6b969918f9115a02c874dab9ad06dd502b977872d
+oid sha256:c33de66df47b89a59c9acc83dac020e6af8316fa90e5e9b533ae16b375f62ad0
 size 437958648

run-5/checkpoint-312/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-5/checkpoint-312/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b669882049e7ee1f00d416f7eb06507280540943d71adf9393d9aa62ccfb305d
+size 437958648

run-5/checkpoint-312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5ffca2844143e3b30785de48443ea220edc0e929a47fe2ddc0dcb9fe6cdd569
+size 876038394

run-5/checkpoint-312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a69fbc11d3f7bdd194c4f6febc68ff9beadd46e45ba247e1b80b7871f6f7be0
+size 14244

run-5/checkpoint-312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63dc01c9fab8a643873c04eea9cd44dad052eef3a2f0038e9708fa0393a2b3a0
+size 1064

run-5/checkpoint-312/special_tokens_map.json

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

run-5/checkpoint-312/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-5/checkpoint-312/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_global_step": 156,
+  "best_metric": 0.4729241877256318,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-5/checkpoint-156",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7094579935073853,
+      "eval_runtime": 0.6559,
+      "eval_samples_per_second": 422.293,
+      "eval_steps_per_second": 7.623,
+      "step": 156
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4693140794223827,
+      "eval_loss": 0.7010825276374817,
+      "eval_runtime": 0.6542,
+      "eval_samples_per_second": 423.45,
+      "eval_steps_per_second": 7.643,
+      "step": 312
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 624,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "classifier_dropout": 0.12660170710684812,
+    "learning_rate": 1.3468686238004616e-06,
+    "max_length": 256,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16
+  }
+}

run-5/checkpoint-312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5866170a9798aba340b04ec2b4f352653fde1fe7c667f932ce5aae5c1a0bec82
+size 5432

run-6/checkpoint-156/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-6/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a00b703c5fe8f8675f74c8bd879c71556f18734cd21dff75554ea64304a3d06e
+size 437958648

run-6/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9519f7d9853ab94257de40b6f10ac1c49dde8b7e5a39eb5478ad462e6e6f5c5f
+size 876038394

run-6/checkpoint-156/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0bd0ecbea6accdf7a51551feef7c19310fde6287eee32a3f2a6d63776d2405c
+size 14244

run-6/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ef4df71059f87ec39968af768242f4ea7dd354df76176a8f05ae0126c24df7
+size 1064

run-6/checkpoint-156/special_tokens_map.json

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

run-6/checkpoint-156/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-6/checkpoint-156/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_global_step": 156,
+  "best_metric": 0.4729241877256318,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-6/checkpoint-156",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7125602960586548,
+      "eval_runtime": 0.6582,
+      "eval_samples_per_second": 420.874,
+      "eval_steps_per_second": 7.597,
+      "step": 156
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 624,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "classifier_dropout": 0.1089452955136888,
+    "learning_rate": 1.0795727692518032e-06,
+    "max_length": 128,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16
+  }
+}

run-6/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c4c40de6da2713a66290bee006324690cb84c9d1fcf729c16fd8f7f74e7681
+size 5432

run-6/checkpoint-312/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-6/checkpoint-312/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3efd109e4df2f57eed80fdc4c75e8a4648c470507bb6977272387db9b1699889
+size 437958648

run-6/checkpoint-312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e90037dee78db02073b248d1234a9617cb483aaf495a1a36b39d34728ddd905
+size 876038394

run-6/checkpoint-312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a69fbc11d3f7bdd194c4f6febc68ff9beadd46e45ba247e1b80b7871f6f7be0
+size 14244

run-6/checkpoint-312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c5d00f788971702c0e1ff753b457837badb4eee4ab0c15c35f36560c1f8549
+size 1064

run-6/checkpoint-312/special_tokens_map.json

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

run-6/checkpoint-312/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-6/checkpoint-312/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_global_step": 156,
+  "best_metric": 0.4729241877256318,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-6/checkpoint-156",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7125602960586548,
+      "eval_runtime": 0.6582,
+      "eval_samples_per_second": 420.874,
+      "eval_steps_per_second": 7.597,
+      "step": 156
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4693140794223827,
+      "eval_loss": 0.7045787572860718,
+      "eval_runtime": 0.6572,
+      "eval_samples_per_second": 421.495,
+      "eval_steps_per_second": 7.608,
+      "step": 312
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 624,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "classifier_dropout": 0.1089452955136888,
+    "learning_rate": 1.0795727692518032e-06,
+    "max_length": 128,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16
+  }
+}

run-6/checkpoint-312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c4c40de6da2713a66290bee006324690cb84c9d1fcf729c16fd8f7f74e7681
+size 5432

run-8/checkpoint-156/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-8/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33de66df47b89a59c9acc83dac020e6af8316fa90e5e9b533ae16b375f62ad0
+size 437958648

run-8/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bbf87cdc0f8880b85ec8fd6b03b6aedb526811823f1443b31531098089a9dbe
+size 876038394

run-8/checkpoint-156/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a64755083f7633da1abd1de577e641d7084f1c57535fb19884090b3171beb5
+size 14244

run-8/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a961adbc85fe90567fd1ae99ff28472a204d25e5c5db032c900a1d6a42c9ea4
+size 1064

run-8/checkpoint-156/special_tokens_map.json

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

run-8/checkpoint-156/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-156/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_global_step": 156,
+  "best_metric": 0.6173285198555957,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-8/checkpoint-156",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6028880866425993,
+      "eval_loss": 0.6886783242225647,
+      "eval_runtime": 0.6558,
+      "eval_samples_per_second": 422.378,
+      "eval_steps_per_second": 7.624,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6173285198555957,
+      "eval_loss": 0.6687993407249451,
+      "eval_runtime": 0.6547,
+      "eval_samples_per_second": 423.094,
+      "eval_steps_per_second": 7.637,
+      "step": 156
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "classifier_dropout": 0.3144563028637545,
+    "learning_rate": 8.273485183328586e-06,
+    "max_length": 512,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32
+  }
+}

run-8/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:531460a5e6a46a6be5016d26066192a4d9b5aec325fca2f3ead68fd2e84685b3
+size 5432

run-8/checkpoint-78/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-8/checkpoint-78/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:933b368f56f92df0f2264f8d7c68ae23bde9309f813a00d7ec4da3d24e451a47
+size 437958648

run-8/checkpoint-78/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e8dac67296ecf0eba1384654d15f90ac4e7d10740137ebec3f0175be9822b02
+size 876038394

run-8/checkpoint-78/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ab796df965c74c106f46f16854d55804fecfe14c1d69ae73ebe7269fc9ed28
+size 14244

run-8/checkpoint-78/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3737711308bb8b6f842a0a089be2a5047ccbc681b591aa88db6a736ffe9b0a29
+size 1064