Upload 11 files

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51328e494916fee221fd02bc98e25cabdd998921b843034706648674a13a3b9b
+size 260803668

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c97166a89baddc253ae9d1b5a3443117f2168400f9b2b37de0d8f15d09f2752
+size 521668154

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8d2fcd16bbaf227a4ae4dbdfc68aff27fe79a29171974feecb6651a80e97d0
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978877cae901ec2c46d434efe80b38f1ca497bc6de28bf3a2c1989cef39a6762
+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 +1,55 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 5268,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2847380410022779,
+      "grad_norm": 7.928560256958008,
+      "learning_rate": 1.810174639331815e-05,
+      "loss": 0.2906,
+      "step": 500
+    },
+    {
+      "epoch": 0.5694760820045558,
+      "grad_norm": 0.12530961632728577,
+      "learning_rate": 1.6203492786636296e-05,
+      "loss": 0.1285,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8542141230068337,
+      "grad_norm": 2.731761932373047,
+      "learning_rate": 1.4305239179954442e-05,
+      "loss": 0.0912,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9761288043798199,
+      "eval_f1": 0.8952098276857119,
+      "eval_loss": 0.08535858988761902,
+      "eval_precision": 0.8774850492969128,
+      "eval_recall": 0.913665432514305,
+      "eval_runtime": 6.7803,
+      "eval_samples_per_second": 479.332,
+      "eval_steps_per_second": 60.027,
+      "step": 1756
+    },
+    {
+      "epoch": 1.1389521640091116,
+      "grad_norm": 0.34379810094833374,
+      "learning_rate": 1.240698557327259e-05,
+      "loss": 0.0756,
+      "step": 2000
+    },
+    {
+      "epoch": 1.4236902050113895,
+      "grad_norm": 0.34557342529296875,
+      "learning_rate": 1.0508731966590738e-05,
+      "loss": 0.055,
+      "step": 2500
+    },
+    {
+      "epoch": 1.7084282460136673,
+      "grad_norm": 0.9085732102394104,
+      "learning_rate": 8.610478359908885e-06,
+      "loss": 0.0546,
+      "step": 3000
+    },
+    {
+      "epoch": 1.9931662870159452,
+      "grad_norm": 2.8519742488861084,
+      "learning_rate": 6.712224753227031e-06,
+      "loss": 0.0464,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9827367987284394,
+      "eval_f1": 0.9272848565710473,
+      "eval_loss": 0.06802816689014435,
+      "eval_precision": 0.9190082644628099,
+      "eval_recall": 0.9357118815213733,
+      "eval_runtime": 6.6043,
+      "eval_samples_per_second": 492.101,
+      "eval_steps_per_second": 61.626,
+      "step": 3512
+    },
+    {
+      "epoch": 2.277904328018223,
+      "grad_norm": 2.584799289703369,
+      "learning_rate": 4.8139711465451785e-06,
+      "loss": 0.0312,
+      "step": 4000
+    },
+    {
+      "epoch": 2.562642369020501,
+      "grad_norm": 0.4364319145679474,
+      "learning_rate": 2.9157175398633257e-06,
+      "loss": 0.0278,
+      "step": 4500
+    },
+    {
+      "epoch": 2.847380410022779,
+      "grad_norm": 0.10701252520084381,
+      "learning_rate": 1.0174639331814731e-06,
+      "loss": 0.0292,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.983354918467063,
+      "eval_f1": 0.9289044289044289,
+      "eval_loss": 0.07014655321836472,
+      "eval_precision": 0.9191103789126853,
+      "eval_recall": 0.9389094580949175,
+      "eval_runtime": 6.9523,
+      "eval_samples_per_second": 467.471,
+      "eval_steps_per_second": 58.542,
+      "step": 5268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5268,
+  "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": 460431563935266.0,
+  "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:d9606cd16377eb86788c1f296de2538082ff67bd7e82666b94d59cb97cb395db
+size 5240