Upload folder using huggingface_hub

checkpoint-225/config.json

@@ -0,0 +1,42 @@
+{
+  "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",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "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": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-225/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd6edfa748c5f311b5e762419fbc3af83038b064a887f6dd73e8c2fda0030eb
+size 437970952

checkpoint-225/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdc8b5b23967853a6efb08dcc7640130f6d7ff3b7308dc83f41f053dc0262b10
+size 876057338

checkpoint-225/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:678ed43f94bb3055af3f7f0b39d18212e3a23712cca8f6b19320a07e10b1f3bf
+size 13990

checkpoint-225/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561579a758914099de6890063b91f3bc3ed70df66b85256165893eb0797ebbb7
+size 1064

checkpoint-225/special_tokens_map.json

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

checkpoint-225/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-225/trainer_state.json

@@ -0,0 +1,188 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.2240008115768433,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6325,
+      "step": 10
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.7366985082626343,
+      "learning_rate": 4.577777777777778e-05,
+      "loss": 0.4912,
+      "step": 20
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.0045955181121826,
+      "learning_rate": 4.355555555555556e-05,
+      "loss": 0.494,
+      "step": 30
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.483319640159607,
+      "learning_rate": 4.133333333333333e-05,
+      "loss": 0.4667,
+      "step": 40
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.3654990196228027,
+      "learning_rate": 3.9111111111111115e-05,
+      "loss": 0.484,
+      "step": 50
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.0798791646957397,
+      "learning_rate": 3.688888888888889e-05,
+      "loss": 0.4405,
+      "step": 60
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 1.4874286651611328,
+      "learning_rate": 3.466666666666667e-05,
+      "loss": 0.4123,
+      "step": 70
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 1.2456817626953125,
+      "learning_rate": 3.2444444444444446e-05,
+      "loss": 0.4057,
+      "step": 80
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.2316265106201172,
+      "learning_rate": 3.0222222222222225e-05,
+      "loss": 0.3726,
+      "step": 90
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.5920876264572144,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.3628,
+      "step": 100
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 1.321195363998413,
+      "learning_rate": 2.5777777777777778e-05,
+      "loss": 0.3365,
+      "step": 110
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.2365787029266357,
+      "learning_rate": 2.3555555555555556e-05,
+      "loss": 0.3477,
+      "step": 120
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 1.9119094610214233,
+      "learning_rate": 2.1333333333333335e-05,
+      "loss": 0.3182,
+      "step": 130
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 1.694663643836975,
+      "learning_rate": 1.9111111111111113e-05,
+      "loss": 0.3231,
+      "step": 140
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.333991527557373,
+      "learning_rate": 1.688888888888889e-05,
+      "loss": 0.3511,
+      "step": 150
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 1.0778796672821045,
+      "learning_rate": 1.4666666666666668e-05,
+      "loss": 0.3234,
+      "step": 160
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 1.3821531534194946,
+      "learning_rate": 1.2444444444444445e-05,
+      "loss": 0.3092,
+      "step": 170
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.8260213732719421,
+      "learning_rate": 1.0222222222222223e-05,
+      "loss": 0.2779,
+      "step": 180
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 1.574690341949463,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.2933,
+      "step": 190
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.8064292073249817,
+      "learning_rate": 5.777777777777778e-06,
+      "loss": 0.2705,
+      "step": 200
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.8645901083946228,
+      "learning_rate": 3.555555555555556e-06,
+      "loss": 0.2681,
+      "step": 210
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 1.3874491453170776,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.3004,
+      "step": 220
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 225,
+  "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": 236808454348800.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-225/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc16a4b2f057b0178cc421e6125bd01e0edc89748b2a74407c84d6f0b920e8e
+size 5240

config.json

@@ -0,0 +1,42 @@
+{
+  "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": "has_phonetic_spelling",
+    "1": "has_letter_reversal",
+    "2": "has_omission",
+    "3": "has_addition",
+    "4": "has_word_boundary",
+    "5": "has_transposition"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "has_phonetic_spelling": 0,
+    "has_letter_reversal": 1,
+    "has_omission": 2,
+    "has_addition": 3,
+    "has_word_boundary": 4,
+    "has_transposition": 5
+  },
+  "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": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd6edfa748c5f311b5e762419fbc3af83038b064a887f6dd73e8c2fda0030eb
+size 437970952

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}