Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:904fdbaae30c130b440bd0202b33546417b7ecd72fd7f4e5a5545a7ffe8811a7
+oid sha256:bab364cbac0a1539fe33803469d620a932c42a7d2c2975c32cc5a98832170a08
 size 437958648

run-4/checkpoint-1263/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-1263/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca5bf6d05c67c92d078cea46c1fc2ac40673315153d53c325c0dece20d4a951
+size 437958648

run-4/checkpoint-1263/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2407fd2d78f3ee00fc29247421e4dd062319bd9bdd5eb1af70503af1c279c958
+size 876038394

run-4/checkpoint-1263/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae456fe0d9968a5f662bec0ac8d34635027fcfb4552becc0dd1b442fa0bf71f3
+size 14244

run-4/checkpoint-1263/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08780a3c1cdc95e9ae27b487d0d73e527da6822450de85a1d7374facf7d457a
+size 1064

run-4/checkpoint-1263/special_tokens_map.json

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

run-4/checkpoint-1263/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-1263/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.911697247706422,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-4/checkpoint-421",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1263,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.911697247706422,
+      "eval_loss": 0.22564278542995453,
+      "eval_runtime": 2.3507,
+      "eval_samples_per_second": 370.952,
+      "eval_steps_per_second": 23.397,
+      "step": 421
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 22.03980827331543,
+      "learning_rate": 1.3592312257395198e-05,
+      "loss": 0.3224,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.908256880733945,
+      "eval_loss": 0.28558045625686646,
+      "eval_runtime": 2.3703,
+      "eval_samples_per_second": 367.886,
+      "eval_steps_per_second": 23.204,
+      "step": 842
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 6.299999713897705,
+      "learning_rate": 7.85231552707628e-06,
+      "loss": 0.1554,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9071100917431193,
+      "eval_loss": 0.4138067066669464,
+      "eval_runtime": 2.3765,
+      "eval_samples_per_second": 366.925,
+      "eval_steps_per_second": 23.143,
+      "step": 1263
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1684,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 290833299485880.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9332308987714115e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 7
+  }
+}

run-4/checkpoint-1263/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ddfa9214cc4a8744b1acb7c736584356b64328d1bba7daa8c13355771e08a2
+size 4920

run-4/checkpoint-1684/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-1684/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f10c17dc5490af1664967c90cb1a898d66a933416d302fd14134871fb0459a
+size 437958648

run-4/checkpoint-1684/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2065ab8edfc9ea4cc6b009ce49dbfd1f759265ef14462bc84d0b28e72f2772b
+size 876038394

run-4/checkpoint-1684/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c9e729eb66348c2f068ec40fa879102e2d7e630532918da21836a0b85233978
+size 14244

run-4/checkpoint-1684/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8abd0bceacecd05ed24ef71c0457e0e19e7a020890b3d566246b707cf4373ca
+size 1064

run-4/checkpoint-1684/special_tokens_map.json

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

run-4/checkpoint-1684/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-1684/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": 0.9128440366972477,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-4/checkpoint-1684",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1684,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.911697247706422,
+      "eval_loss": 0.22564278542995453,
+      "eval_runtime": 2.3507,
+      "eval_samples_per_second": 370.952,
+      "eval_steps_per_second": 23.397,
+      "step": 421
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 22.03980827331543,
+      "learning_rate": 1.3592312257395198e-05,
+      "loss": 0.3224,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.908256880733945,
+      "eval_loss": 0.28558045625686646,
+      "eval_runtime": 2.3703,
+      "eval_samples_per_second": 367.886,
+      "eval_steps_per_second": 23.204,
+      "step": 842
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 6.299999713897705,
+      "learning_rate": 7.85231552707628e-06,
+      "loss": 0.1554,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9071100917431193,
+      "eval_loss": 0.4138067066669464,
+      "eval_runtime": 2.3765,
+      "eval_samples_per_second": 366.925,
+      "eval_steps_per_second": 23.143,
+      "step": 1263
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 0.3025916516780853,
+      "learning_rate": 2.112318796757362e-06,
+      "loss": 0.0672,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9128440366972477,
+      "eval_loss": 0.4202166199684143,
+      "eval_runtime": 2.4066,
+      "eval_samples_per_second": 362.344,
+      "eval_steps_per_second": 22.854,
+      "step": 1684
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1684,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 436318296436560.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9332308987714115e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 7
+  }
+}

run-4/checkpoint-1684/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ddfa9214cc4a8744b1acb7c736584356b64328d1bba7daa8c13355771e08a2
+size 4920

run-4/checkpoint-842/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-842/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db48d38149dcd09ef50b4792d3354e550988ffb7a40733cf8711446920da591f
+size 437958648

run-4/checkpoint-842/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0546146f912698d86fdb95de4de2edfc82532b8e5a5e5f6f564339302482dd0d
+size 876038394

run-4/checkpoint-842/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b53c59b69bf861c31e06bdd659f8f30785179c11310ebe666f02edc98e27fb
+size 14244

run-4/checkpoint-842/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53acd540e98797c2dc899c7aafb1ad893ee58a07723bf646bbeff386c171ba00
+size 1064

run-4/checkpoint-842/special_tokens_map.json

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

run-4/checkpoint-842/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-842/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_metric": 0.911697247706422,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-4/checkpoint-421",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 842,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.911697247706422,
+      "eval_loss": 0.22564278542995453,
+      "eval_runtime": 2.3507,
+      "eval_samples_per_second": 370.952,
+      "eval_steps_per_second": 23.397,
+      "step": 421
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 22.03980827331543,
+      "learning_rate": 1.3592312257395198e-05,
+      "loss": 0.3224,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.908256880733945,
+      "eval_loss": 0.28558045625686646,
+      "eval_runtime": 2.3703,
+      "eval_samples_per_second": 367.886,
+      "eval_steps_per_second": 23.204,
+      "step": 842
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1684,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 144840580420560.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9332308987714115e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 7
+  }
+}

run-4/checkpoint-842/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ddfa9214cc4a8744b1acb7c736584356b64328d1bba7daa8c13355771e08a2
+size 4920

run-5/checkpoint-211/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-5/checkpoint-211/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43bda8baa353fbc95f0b54e966727687c1ee8db8c980381c5c8c8b06b72be167
+size 437958648

run-5/checkpoint-211/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9638d1ccba78654e36a1d51304662abff70e5b2a025c487e0bced6a2330750a1
+size 876038394

run-5/checkpoint-211/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efab02b5d3da3a4dbb5487f7488f3d786a6461e5283dd06b6cae918f73bf2637
+size 14244

run-5/checkpoint-211/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec5ad38cac26ca3191ab82775462a8626a4d2f4ee42edd9c674f243dad9aa8a
+size 1064

run-5/checkpoint-211/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-211/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-5/checkpoint-211/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.9002293577981652,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-5/checkpoint-211",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 211,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9002293577981652,
+      "eval_loss": 0.24879497289657593,
+      "eval_runtime": 2.3485,
+      "eval_samples_per_second": 371.303,
+      "eval_steps_per_second": 23.419,
+      "step": 211
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 844,
+  "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": 6.50537267718272e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 2
+  }
+}

run-5/checkpoint-211/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ade228fc6bd95046697574a73a36f3413a1273363ebbb392ad60a58f2443b9d
+size 4920

run-5/checkpoint-422/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-5/checkpoint-422/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c9550c41350263e7b24126ab147730e7b461d8a5cd85da832afc8b487caa581
+size 437958648

run-5/checkpoint-422/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b03b91fc69ebfe9c1e06b7f4ce9252dc3f07b773f3f3be0f16846f4386049ff8
+size 876038394

run-5/checkpoint-422/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fcc397c1accf6ac3cd5780d753849a2d25d34651120da70fb88efc8fa19dac6
+size 14244

run-5/checkpoint-422/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4834704ba5086eb8304c4d94a7f1f921a85c582874b9714e24ab46881bf3caec
+size 1064