Adding checkpoint-5453 files

config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "I-Definition",
+    "1": "B-Definition",
+    "2": "I-Term",
+    "3": "O",
+    "4": "B-Term"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Definition": 1,
+    "B-Term": 4,
+    "I-Definition": 0,
+    "I-Term": 2,
+    "O": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "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",
+  "transformers_version": "4.56.0",
+  "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:c869b2072e3fa57787e51cb7ec7a9853ba6e8ac5409f9ee293d691cb94cbcd3c
+size 709090132

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8238efd575ff2e920eb29595dab3b8d7a231371a1ae6b09b0fdadacd770e7a8a
+size 1418303243

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3de303ac925d225602f5b7d660ec8751bdb08a88c33ce779e19529fc50f01dd4
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c72df20b8e45da8c93b459bb009040b3463e0c29523733e7855409c846496f
+size 1465

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": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,188 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 5453,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6418485237483954,
+      "grad_norm": 9.85666561126709,
+      "learning_rate": 1.8169814780854577e-05,
+      "loss": 0.5294,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8421842184218422,
+      "eval_f1": 0.7176287051482059,
+      "eval_loss": 0.42669883370399475,
+      "eval_precision": 0.6764705882352942,
+      "eval_recall": 0.7641196013289037,
+      "eval_runtime": 0.5577,
+      "eval_samples_per_second": 421.34,
+      "eval_steps_per_second": 53.788,
+      "step": 779
+    },
+    {
+      "epoch": 1.2836970474967908,
+      "grad_norm": 14.279178619384766,
+      "learning_rate": 1.633596185585916e-05,
+      "loss": 0.3251,
+      "step": 1000
+    },
+    {
+      "epoch": 1.925545571245186,
+      "grad_norm": 3.289396047592163,
+      "learning_rate": 1.4502108930863745e-05,
+      "loss": 0.2522,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.882988298829883,
+      "eval_f1": 0.7681549220010758,
+      "eval_loss": 0.34702780842781067,
+      "eval_precision": 0.7468619246861925,
+      "eval_recall": 0.7906976744186046,
+      "eval_runtime": 0.4659,
+      "eval_samples_per_second": 504.441,
+      "eval_steps_per_second": 64.397,
+      "step": 1558
+    },
+    {
+      "epoch": 2.5673940949935816,
+      "grad_norm": 2.985898733139038,
+      "learning_rate": 1.266825600586833e-05,
+      "loss": 0.1615,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8852385238523852,
+      "eval_f1": 0.7855183763027976,
+      "eval_loss": 0.40044641494750977,
+      "eval_precision": 0.7782608695652173,
+      "eval_recall": 0.7929125138427464,
+      "eval_runtime": 0.5454,
+      "eval_samples_per_second": 430.843,
+      "eval_steps_per_second": 55.001,
+      "step": 2337
+    },
+    {
+      "epoch": 3.209242618741977,
+      "grad_norm": 3.132018804550171,
+      "learning_rate": 1.0834403080872916e-05,
+      "loss": 0.1346,
+      "step": 2500
+    },
+    {
+      "epoch": 3.851091142490372,
+      "grad_norm": 23.86431121826172,
+      "learning_rate": 9.0005501558775e-06,
+      "loss": 0.093,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8876387638763876,
+      "eval_f1": 0.7800875273522976,
+      "eval_loss": 0.4634242355823517,
+      "eval_precision": 0.7708108108108108,
+      "eval_recall": 0.7895902547065338,
+      "eval_runtime": 0.5241,
+      "eval_samples_per_second": 448.366,
+      "eval_steps_per_second": 57.238,
+      "step": 3116
+    },
+    {
+      "epoch": 4.492939666238768,
+      "grad_norm": 10.69092845916748,
+      "learning_rate": 7.166697230882084e-06,
+      "loss": 0.0695,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8912391239123912,
+      "eval_f1": 0.7937024972855592,
+      "eval_loss": 0.512829601764679,
+      "eval_precision": 0.7784877529286475,
+      "eval_recall": 0.8095238095238095,
+      "eval_runtime": 0.5735,
+      "eval_samples_per_second": 409.733,
+      "eval_steps_per_second": 52.306,
+      "step": 3895
+    },
+    {
+      "epoch": 5.134788189987163,
+      "grad_norm": 0.8048956990242004,
+      "learning_rate": 5.332844305886668e-06,
+      "loss": 0.0601,
+      "step": 4000
+    },
+    {
+      "epoch": 5.7766367137355585,
+      "grad_norm": 2.4991579055786133,
+      "learning_rate": 3.498991380891253e-06,
+      "loss": 0.0413,
+      "step": 4500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8915391539153915,
+      "eval_f1": 0.7760702524698133,
+      "eval_loss": 0.5404914021492004,
+      "eval_precision": 0.7693144722524483,
+      "eval_recall": 0.7829457364341085,
+      "eval_runtime": 0.5644,
+      "eval_samples_per_second": 416.369,
+      "eval_steps_per_second": 53.154,
+      "step": 4674
+    },
+    {
+      "epoch": 6.418485237483954,
+      "grad_norm": 18.92781639099121,
+      "learning_rate": 1.6651384558958373e-06,
+      "loss": 0.0341,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8921392139213922,
+      "eval_f1": 0.7840349917987972,
+      "eval_loss": 0.5803054571151733,
+      "eval_precision": 0.7742980561555075,
+      "eval_recall": 0.7940199335548173,
+      "eval_runtime": 0.5542,
+      "eval_samples_per_second": 424.041,
+      "eval_steps_per_second": 54.133,
+      "step": 5453
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5453,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 1159775675802900.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab7313228972ec0283cc87dbb5358157187f385d7cb9628aea0c2a357a0493e6
+size 5713