Upload fine-tuned model checkpoints

results/checkpoint-1036/config.json

@@ -0,0 +1,36 @@
+{
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

results/checkpoint-1036/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:304d8bebc9d40f660512dacd5d5aaf89b011e7f10d64f23eb6ade644b09ee2ab
+size 437961724

results/checkpoint-1036/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f8d2a1911ff0cac9c5e77a3f43f35c84c03b9a8ba353cb0ff0349d6eee8416
+size 876044538

results/checkpoint-1036/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0629cb201d6cce55fae01158323ad0516f839e51d2619895706900248cbf7482
+size 14244

results/checkpoint-1036/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb7e297daec985eb7e99899959fd2694bf17404b54a6bb42e96fffed5862754e
+size 988

results/checkpoint-1036/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2a9be62f30a3b1b49236be95738d002f2b118bb769c8414e0fe4137c849db6c
+size 1064

results/checkpoint-1036/special_tokens_map.json

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

results/checkpoint-1036/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]"
+}

results/checkpoint-1036/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_global_step": 1036,
+  "best_metric": 0.3279893696308136,
+  "best_model_checkpoint": "./results/checkpoint-1036",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1036,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4826254826254826,
+      "grad_norm": 14.053184509277344,
+      "learning_rate": 1.680823680823681e-05,
+      "loss": 0.5034,
+      "step": 500
+    },
+    {
+      "epoch": 0.9652509652509652,
+      "grad_norm": 6.887276649475098,
+      "learning_rate": 1.3590733590733592e-05,
+      "loss": 0.3842,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8750678978815861,
+      "eval_loss": 0.3279893696308136,
+      "eval_runtime": 14.343,
+      "eval_samples_per_second": 128.355,
+      "eval_steps_per_second": 4.044,
+      "step": 1036
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 4358999991499776.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

results/checkpoint-1036/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de091362311e93a221844d4823e672138d7ebf5733d80c9b5892fee2d61670c
+size 5304

results/checkpoint-1551/config.json

@@ -0,0 +1,36 @@
+{
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

results/checkpoint-1551/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4073b2e81f8f8647444da00fbc1d26ce3172e527456d1de6c688fb83f7529e02
+size 437961724

results/checkpoint-1551/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a9ce7118c29c0ee451a36785a7174fac1195d897b12741400ac8cc9d60dcf29
+size 876044538

results/checkpoint-1551/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df7766fff8012fece33853aa61e44d27616387ca52c1e889219531835a54d9b1
+size 14244

results/checkpoint-1551/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd4074f750df5ac2f7e47d1229e819273e01094a91dfab76dc17e459cc338919
+size 988

results/checkpoint-1551/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e30ebf3dd1984c606aef006051ab279358c7a99291741fdf6705ec21d28313fa
+size 1064

results/checkpoint-1551/special_tokens_map.json

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

results/checkpoint-1551/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]"
+}

results/checkpoint-1551/trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_global_step": 1034,
+  "best_metric": 0.33625534176826477,
+  "best_model_checkpoint": "./results/checkpoint-1034",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1551,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9671179883945842,
+      "grad_norm": 4.731949329376221,
+      "learning_rate": 1.3578336557059963e-05,
+      "loss": 0.4624,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8535655960805661,
+      "eval_loss": 0.36626842617988586,
+      "eval_runtime": 12.9343,
+      "eval_samples_per_second": 142.025,
+      "eval_steps_per_second": 2.242,
+      "step": 517
+    },
+    {
+      "epoch": 1.9342359767891684,
+      "grad_norm": 6.004007816314697,
+      "learning_rate": 7.1437782076079955e-06,
+      "loss": 0.2511,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8677191072400653,
+      "eval_loss": 0.33625534176826477,
+      "eval_runtime": 12.8805,
+      "eval_samples_per_second": 142.619,
+      "eval_steps_per_second": 2.251,
+      "step": 1034
+    },
+    {
+      "epoch": 2.9013539651837523,
+      "grad_norm": 8.314071655273438,
+      "learning_rate": 7.092198581560285e-07,
+      "loss": 0.1552,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8720740337506805,
+      "eval_loss": 0.3812296390533447,
+      "eval_runtime": 12.8743,
+      "eval_samples_per_second": 142.687,
+      "eval_steps_per_second": 2.253,
+      "step": 1551
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1551,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3045426364371968e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

results/checkpoint-1551/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfe12af29f7e720c2ae21286ce810666d033081b14cba2d61e95517c40bdccbc
+size 5304

results/checkpoint-3108/config.json

@@ -0,0 +1,36 @@
+{
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

results/checkpoint-3108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8720ae69ad8a22ba0dd71584ead2776498a8842b7c4bdc2b5c79fc42caffda6
+size 437961724

results/checkpoint-3108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55dd7cb68ef49dc05ee5b79a06e188ea2fdbcdda15a34f12dccf845eb2887056
+size 876044538

results/checkpoint-3108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d6b50ae4e13693031045bbf878094d509455c7420ae0665f0eddf8c7448058b
+size 14244

results/checkpoint-3108/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95eae2156f99f50b8dc0b0f561c513731d026409dcb7ef3f71a5ba36ecca69bf
+size 988

results/checkpoint-3108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3be100ced370b55c37f4b72599fd06a2dd51966d1d498e02be2ca92c51508c79
+size 1064

results/checkpoint-3108/special_tokens_map.json

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

results/checkpoint-3108/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]"
+}

results/checkpoint-3108/trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_global_step": 1036,
+  "best_metric": 0.3279893696308136,
+  "best_model_checkpoint": "./results/checkpoint-1036",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3108,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4826254826254826,
+      "grad_norm": 14.053184509277344,
+      "learning_rate": 1.680823680823681e-05,
+      "loss": 0.5034,
+      "step": 500
+    },
+    {
+      "epoch": 0.9652509652509652,
+      "grad_norm": 6.887276649475098,
+      "learning_rate": 1.3590733590733592e-05,
+      "loss": 0.3842,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8750678978815861,
+      "eval_loss": 0.3279893696308136,
+      "eval_runtime": 14.343,
+      "eval_samples_per_second": 128.355,
+      "eval_steps_per_second": 4.044,
+      "step": 1036
+    },
+    {
+      "epoch": 1.4478764478764479,
+      "grad_norm": 6.9067792892456055,
+      "learning_rate": 1.0373230373230373e-05,
+      "loss": 0.2572,
+      "step": 1500
+    },
+    {
+      "epoch": 1.9305019305019306,
+      "grad_norm": 13.993288040161133,
+      "learning_rate": 7.155727155727157e-06,
+      "loss": 0.2339,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8750678978815861,
+      "eval_loss": 0.3709438443183899,
+      "eval_runtime": 14.2627,
+      "eval_samples_per_second": 129.078,
+      "eval_steps_per_second": 4.067,
+      "step": 2072
+    },
+    {
+      "epoch": 2.413127413127413,
+      "grad_norm": 0.07056383788585663,
+      "learning_rate": 3.938223938223939e-06,
+      "loss": 0.1442,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8957528957528957,
+      "grad_norm": 22.20907211303711,
+      "learning_rate": 7.335907335907337e-07,
+      "loss": 0.1488,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8804997284084737,
+      "eval_loss": 0.46850883960723877,
+      "eval_runtime": 14.2613,
+      "eval_samples_per_second": 129.09,
+      "eval_steps_per_second": 4.067,
+      "step": 3108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3076999974499328e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

results/checkpoint-3108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de091362311e93a221844d4823e672138d7ebf5733d80c9b5892fee2d61670c
+size 5304