init commit

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fdcd4f0f1209395fde7739420c0a1347a36d5348fdd027a046f7cd93258aea6
+size 709096284

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41fe982724cd3de1137111a0bd53c358162c492f42716dc6f9a17eb91d02159c
+size 1418312250

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf20707cfe44b9a2276c69f13c12e7734e37012f02f270f239bb9bfd5745003
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:977b16ce1d671299321ed5cdc5925bcc339f51b69ce7fef2d33400b154276801
+size 1064

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 +1,56 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "num_labels": 7,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,183 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 6250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9648939348670451,
+      "eval_f1": 0.8973252804141502,
+      "eval_loss": 0.189955934882164,
+      "eval_precision": 0.8587943848059455,
+      "eval_recall": 0.9394760614272809,
+      "eval_runtime": 2.5262,
+      "eval_samples_per_second": 395.851,
+      "eval_steps_per_second": 24.939,
+      "step": 625
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.951064109802246,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.0567,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.97169106662683,
+      "eval_f1": 0.9429726088908846,
+      "eval_loss": 0.1852019727230072,
+      "eval_precision": 0.9375,
+      "eval_recall": 0.948509485094851,
+      "eval_runtime": 2.561,
+      "eval_samples_per_second": 390.465,
+      "eval_steps_per_second": 24.599,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9731102479832686,
+      "eval_f1": 0.9533213644524237,
+      "eval_loss": 0.17272309958934784,
+      "eval_precision": 0.9473684210526315,
+      "eval_recall": 0.959349593495935,
+      "eval_runtime": 3.904,
+      "eval_samples_per_second": 256.151,
+      "eval_steps_per_second": 16.137,
+      "step": 1875
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.4564518630504608,
+      "learning_rate": 1.3600000000000002e-05,
+      "loss": 0.0338,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9777412608305945,
+      "eval_f1": 0.9547288211564321,
+      "eval_loss": 0.15044009685516357,
+      "eval_precision": 0.947508896797153,
+      "eval_recall": 0.962059620596206,
+      "eval_runtime": 2.4284,
+      "eval_samples_per_second": 411.796,
+      "eval_steps_per_second": 25.943,
+      "step": 2500
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.006230680737644434,
+      "learning_rate": 1.04e-05,
+      "loss": 0.0318,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9756498356737376,
+      "eval_f1": 0.9563259792886086,
+      "eval_loss": 0.17377431690692902,
+      "eval_precision": 0.9533213644524237,
+      "eval_recall": 0.959349593495935,
+      "eval_runtime": 2.4667,
+      "eval_samples_per_second": 405.403,
+      "eval_steps_per_second": 25.54,
+      "step": 3125
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9788616671646251,
+      "eval_f1": 0.9630297565374211,
+      "eval_loss": 0.1647682785987854,
+      "eval_precision": 0.9612961296129613,
+      "eval_recall": 0.964769647696477,
+      "eval_runtime": 3.1374,
+      "eval_samples_per_second": 318.737,
+      "eval_steps_per_second": 20.08,
+      "step": 3750
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 0.0044134571217000484,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.02,
+      "step": 4000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9770690170301762,
+      "eval_f1": 0.9643340857787811,
+      "eval_loss": 0.17450480163097382,
+      "eval_precision": 0.9638989169675091,
+      "eval_recall": 0.964769647696477,
+      "eval_runtime": 2.53,
+      "eval_samples_per_second": 395.256,
+      "eval_steps_per_second": 24.901,
+      "step": 4375
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.0022473218850791454,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0063,
+      "step": 5000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9793845234538393,
+      "eval_f1": 0.9652370203160271,
+      "eval_loss": 0.16244609653949738,
+      "eval_precision": 0.9648014440433214,
+      "eval_recall": 0.9656729900632339,
+      "eval_runtime": 2.5135,
+      "eval_samples_per_second": 397.859,
+      "eval_steps_per_second": 25.065,
+      "step": 5000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.98125186734389,
+      "eval_f1": 0.9643340857787811,
+      "eval_loss": 0.16350433230400085,
+      "eval_precision": 0.9638989169675091,
+      "eval_recall": 0.964769647696477,
+      "eval_runtime": 2.4878,
+      "eval_samples_per_second": 401.967,
+      "eval_steps_per_second": 25.324,
+      "step": 5625
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 0.0036331522278487682,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 0.0036,
+      "step": 6000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9799820734986555,
+      "eval_f1": 0.9643662607126748,
+      "eval_loss": 0.16758297383785248,
+      "eval_precision": 0.9630630630630631,
+      "eval_recall": 0.9656729900632339,
+      "eval_runtime": 2.4417,
+      "eval_samples_per_second": 409.55,
+      "eval_steps_per_second": 25.802,
+      "step": 6250
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 6250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1559350717084512.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f1b754cd60aa361668b15b13955195a067f3076165ef6deae96d79c0a157511
+size 4984