Training in progress, epoch 2

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1432
-- Precision: 0.8526
+- Loss: 0.0913
+- Precision: 0.8712
 - Recall: 0.8979
-- F1: 0.8746
-- Accuracy: 0.9691
+- F1: 0.8844
+- Accuracy: 0.9850
 
 ## Model description
 
@@ -55,11 +55,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.1596        | 1.0   | 2489  | 0.1205          | 0.7993    | 0.8141 | 0.8066 | 0.9577   |
-| 0.0944        | 2.0   | 4978  | 0.1156          | 0.8250    | 0.8503 | 0.8375 | 0.9646   |
-| 0.0579        | 3.0   | 7467  | 0.1109          | 0.8231    | 0.8986 | 0.8592 | 0.9669   |
-| 0.0357        | 4.0   | 9956  | 0.1246          | 0.8471    | 0.8943 | 0.8701 | 0.9686   |
-| 0.0177        | 5.0   | 12445 | 0.1432          | 0.8526    | 0.8979 | 0.8746 | 0.9691   |
+| 0.0612        | 1.0   | 2489  | 0.0625          | 0.8264    | 0.8552 | 0.8405 | 0.9816   |
+| 0.0351        | 2.0   | 4978  | 0.0643          | 0.8474    | 0.8716 | 0.8594 | 0.9831   |
+| 0.0189        | 3.0   | 7467  | 0.0651          | 0.8585    | 0.8995 | 0.8785 | 0.9843   |
+| 0.0105        | 4.0   | 9956  | 0.0811          | 0.8690    | 0.8943 | 0.8815 | 0.9847   |
+| 0.0047        | 5.0   | 12445 | 0.0913          | 0.8712    | 0.8979 | 0.8844 | 0.9850   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f9925edb862824f722705b77fa6d25d3567800e19aec4845f3fc6e53be59ee
+oid sha256:faabf245ccab7a385ae458fecf61bb615a5a8f7ee0384d02a7d08ac8d63e6cfa
 size 430923588

run-0/checkpoint-12445/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "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": "O",
+    "1": "B-Disease",
+    "2": "I-Disease",
+    "3": "B-Chemical",
+    "4": "I-Chemical",
+    "5": "B-Gene",
+    "6": "I-Gene"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Chemical": 3,
+    "B-Disease": 1,
+    "B-Gene": 5,
+    "I-Chemical": 4,
+    "I-Disease": 2,
+    "I-Gene": 6,
+    "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

run-0/checkpoint-12445/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:274bc7c738ad86b1a7e48210f2603b8100879e1eae209acb392a86012cc88698
+size 121874640

run-0/checkpoint-12445/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994e6fbc76aea7272a09804c4856c40666e48ebab71a37b832609b9c68b0955e
+size 14308

run-0/checkpoint-12445/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d180bb96258e20ad72d1898bf883191432f703339712eaf41d37423345e690b
+size 1064

run-0/checkpoint-12445/special_tokens_map.json

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

run-0/checkpoint-12445/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": true,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-12445/trainer_state.json

@@ -0,0 +1,254 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 12445,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2008838891120932,
+      "grad_norm": 2.296739339828491,
+      "learning_rate": 1.0356804114498648e-06,
+      "loss": 0.5028,
+      "step": 500
+    },
+    {
+      "epoch": 0.4017677782241864,
+      "grad_norm": 2.885403871536255,
+      "learning_rate": 9.9232836408905e-07,
+      "loss": 0.1797,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6026516673362796,
+      "grad_norm": 4.714044570922852,
+      "learning_rate": 9.489763167282352e-07,
+      "loss": 0.1448,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8035355564483728,
+      "grad_norm": 3.8532094955444336,
+      "learning_rate": 9.056242693674206e-07,
+      "loss": 0.1199,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9636836795859589,
+      "eval_f1": 0.6468026587210636,
+      "eval_loss": 0.10681386291980743,
+      "eval_precision": 0.5823359471729261,
+      "eval_recall": 0.727319587628866,
+      "eval_runtime": 20.4746,
+      "eval_samples_per_second": 208.356,
+      "eval_steps_per_second": 26.081,
+      "step": 2489
+    },
+    {
+      "epoch": 1.004419445560466,
+      "grad_norm": 1.4627267122268677,
+      "learning_rate": 8.622722220066057e-07,
+      "loss": 0.1126,
+      "step": 2500
+    },
+    {
+      "epoch": 1.2053033346725592,
+      "grad_norm": 2.071267604827881,
+      "learning_rate": 8.189201746457909e-07,
+      "loss": 0.1053,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4061872237846524,
+      "grad_norm": 6.656711101531982,
+      "learning_rate": 7.755681272849762e-07,
+      "loss": 0.0984,
+      "step": 3500
+    },
+    {
+      "epoch": 1.6070711128967456,
+      "grad_norm": 1.1916735172271729,
+      "learning_rate": 7.322160799241614e-07,
+      "loss": 0.0966,
+      "step": 4000
+    },
+    {
+      "epoch": 1.8079550020088389,
+      "grad_norm": 2.3483071327209473,
+      "learning_rate": 6.888640325633467e-07,
+      "loss": 0.0914,
+      "step": 4500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9708767672041989,
+      "eval_f1": 0.7143198661247907,
+      "eval_loss": 0.0914178416132927,
+      "eval_precision": 0.6660722246990638,
+      "eval_recall": 0.7701030927835052,
+      "eval_runtime": 19.9542,
+      "eval_samples_per_second": 213.79,
+      "eval_steps_per_second": 26.761,
+      "step": 4978
+    },
+    {
+      "epoch": 2.008838891120932,
+      "grad_norm": 4.1778669357299805,
+      "learning_rate": 6.455119852025319e-07,
+      "loss": 0.0846,
+      "step": 5000
+    },
+    {
+      "epoch": 2.2097227802330255,
+      "grad_norm": 2.798360586166382,
+      "learning_rate": 6.02159937841717e-07,
+      "loss": 0.0857,
+      "step": 5500
+    },
+    {
+      "epoch": 2.4106066693451185,
+      "grad_norm": 1.7000788450241089,
+      "learning_rate": 5.588078904809024e-07,
+      "loss": 0.0809,
+      "step": 6000
+    },
+    {
+      "epoch": 2.611490558457212,
+      "grad_norm": 2.7977373600006104,
+      "learning_rate": 5.154558431200876e-07,
+      "loss": 0.083,
+      "step": 6500
+    },
+    {
+      "epoch": 2.812374447569305,
+      "grad_norm": 2.01316499710083,
+      "learning_rate": 4.721037957592728e-07,
+      "loss": 0.0776,
+      "step": 7000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9727700697378616,
+      "eval_f1": 0.7365162519347542,
+      "eval_loss": 0.08494957536458969,
+      "eval_precision": 0.6844434609426865,
+      "eval_recall": 0.7971649484536083,
+      "eval_runtime": 19.9143,
+      "eval_samples_per_second": 214.218,
+      "eval_steps_per_second": 26.815,
+      "step": 7467
+    },
+    {
+      "epoch": 3.0132583366813983,
+      "grad_norm": 0.729656457901001,
+      "learning_rate": 4.287517483984581e-07,
+      "loss": 0.0834,
+      "step": 7500
+    },
+    {
+      "epoch": 3.2141422257934913,
+      "grad_norm": 4.330155849456787,
+      "learning_rate": 3.853997010376433e-07,
+      "loss": 0.0772,
+      "step": 8000
+    },
+    {
+      "epoch": 3.4150261149055847,
+      "grad_norm": 2.2002146244049072,
+      "learning_rate": 3.420476536768285e-07,
+      "loss": 0.075,
+      "step": 8500
+    },
+    {
+      "epoch": 3.6159100040176777,
+      "grad_norm": 2.16339111328125,
+      "learning_rate": 2.9869560631601374e-07,
+      "loss": 0.0753,
+      "step": 9000
+    },
+    {
+      "epoch": 3.816793893129771,
+      "grad_norm": 1.6610848903656006,
+      "learning_rate": 2.55343558955199e-07,
+      "loss": 0.0696,
+      "step": 9500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9732963932221231,
+      "eval_f1": 0.7483106105512746,
+      "eval_loss": 0.0842830166220665,
+      "eval_precision": 0.6928649835345774,
+      "eval_recall": 0.8134020618556701,
+      "eval_runtime": 21.3601,
+      "eval_samples_per_second": 199.718,
+      "eval_steps_per_second": 25.0,
+      "step": 9956
+    },
+    {
+      "epoch": 4.017677782241864,
+      "grad_norm": 2.6126861572265625,
+      "learning_rate": 2.119915115943842e-07,
+      "loss": 0.0718,
+      "step": 10000
+    },
+    {
+      "epoch": 4.2185616713539575,
+      "grad_norm": 1.186840295791626,
+      "learning_rate": 1.6863946423356944e-07,
+      "loss": 0.0731,
+      "step": 10500
+    },
+    {
+      "epoch": 4.419445560466051,
+      "grad_norm": 1.0546451807022095,
+      "learning_rate": 1.2528741687275467e-07,
+      "loss": 0.0698,
+      "step": 11000
+    },
+    {
+      "epoch": 4.6203294495781435,
+      "grad_norm": 4.4253950119018555,
+      "learning_rate": 8.193536951193991e-08,
+      "loss": 0.0712,
+      "step": 11500
+    },
+    {
+      "epoch": 4.821213338690237,
+      "grad_norm": 2.7206404209136963,
+      "learning_rate": 3.858332215112514e-08,
+      "loss": 0.0678,
+      "step": 12000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 12445,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 3124720717875636.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0790324588106795e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 32
+  }
+}

run-0/checkpoint-12445/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d43e989f6f8e3748c1514af63a5b86043726cda1141564108d087f161829651
+size 5112

run-0/checkpoint-2489/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "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": "O",
+    "1": "B-Disease",
+    "2": "I-Disease",
+    "3": "B-Chemical",
+    "4": "I-Chemical",
+    "5": "B-Gene",
+    "6": "I-Gene"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Chemical": 3,
+    "B-Disease": 1,
+    "B-Gene": 5,
+    "I-Chemical": 4,
+    "I-Disease": 2,
+    "I-Gene": 6,
+    "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

run-0/checkpoint-2489/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a50eff5e9d5ec2b14941cbe845656eb59328c048f816637c5af6b9ee9ef890a9
+size 430923588

run-0/checkpoint-2489/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcddb991367c7bb50242465159bef7aacb85122659cb90083297e0f8426bee00
+size 861966906

run-0/checkpoint-2489/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97046cfcc3d27e0d332c57cdddbf742a73f17d2e67c4991ec1b66afac2823621
+size 14308

run-0/checkpoint-2489/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeafa3f69ca80f10c966f7ff86089991aa6b84e3018450c5db58cc1b58173e5d
+size 1064

run-0/checkpoint-2489/special_tokens_map.json

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

run-0/checkpoint-2489/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": true,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-2489/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2489,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2008838891120932,
+      "grad_norm": 2.296739339828491,
+      "learning_rate": 1.0356804114498648e-06,
+      "loss": 0.5028,
+      "step": 500
+    },
+    {
+      "epoch": 0.4017677782241864,
+      "grad_norm": 2.885403871536255,
+      "learning_rate": 9.9232836408905e-07,
+      "loss": 0.1797,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6026516673362796,
+      "grad_norm": 4.714044570922852,
+      "learning_rate": 9.489763167282352e-07,
+      "loss": 0.1448,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8035355564483728,
+      "grad_norm": 3.8532094955444336,
+      "learning_rate": 9.056242693674206e-07,
+      "loss": 0.1199,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9636836795859589,
+      "eval_f1": 0.6468026587210636,
+      "eval_loss": 0.10681386291980743,
+      "eval_precision": 0.5823359471729261,
+      "eval_recall": 0.727319587628866,
+      "eval_runtime": 20.4746,
+      "eval_samples_per_second": 208.356,
+      "eval_steps_per_second": 26.081,
+      "step": 2489
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 12445,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 520518502710624.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0790324588106795e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 32
+  }
+}

run-0/checkpoint-2489/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d43e989f6f8e3748c1514af63a5b86043726cda1141564108d087f161829651
+size 5112

run-0/checkpoint-312/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "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": "O",
+    "1": "B-Disease",
+    "2": "I-Disease",
+    "3": "B-Chemical",
+    "4": "I-Chemical",
+    "5": "B-Gene",
+    "6": "I-Gene"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Chemical": 3,
+    "B-Disease": 1,
+    "B-Gene": 5,
+    "I-Chemical": 4,
+    "I-Disease": 2,
+    "I-Gene": 6,
+    "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

run-0/checkpoint-312/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:129857f166d4b5001f3e2ec5dd35d30db1064c21419cc2092b9be823455bb955
+size 430923588

run-0/checkpoint-312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c220f45254df3b52959699235c388ca531d71f7f7a0b9b01448ca67494d2360
+size 861966906

run-0/checkpoint-312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a480f66bf8e92e5a89b4d0dfc1d56756ad3330ae4a7816acacecc128a03519a
+size 14244

run-0/checkpoint-312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991c9db4c08fc910c0d6856ad3f591a25cdd00bd448c4be69d17e5480ec7e882
+size 1064

run-0/checkpoint-312/special_tokens_map.json

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

run-0/checkpoint-312/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": true,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-312/trainer_state.json

@@ -0,0 +1,50 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9300062866416176,
+      "eval_f1": 0.4411184592180067,
+      "eval_loss": 0.18884220719337463,
+      "eval_precision": 0.4011394809031441,
+      "eval_recall": 0.4899484536082474,
+      "eval_runtime": 21.9121,
+      "eval_samples_per_second": 194.687,
+      "eval_steps_per_second": 24.37,
+      "step": 312
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1248,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.185628372847623e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 38
+  }
+}

run-0/checkpoint-312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d5fe7f0960a10fd919e8f0857f9df1bbb7be99c920849bf9fba5ecc0df0b0a
+size 5112

run-0/checkpoint-4978/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "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": "O",
+    "1": "B-Disease",
+    "2": "I-Disease",
+    "3": "B-Chemical",
+    "4": "I-Chemical",
+    "5": "B-Gene",
+    "6": "I-Gene"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Chemical": 3,
+    "B-Disease": 1,
+    "B-Gene": 5,
+    "I-Chemical": 4,
+    "I-Disease": 2,
+    "I-Gene": 6,
+    "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

run-0/checkpoint-4978/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4276aa96d801eba65355647f1405c220c4278493baa936e41e41908c3bd603da
+size 430923588

run-0/checkpoint-4978/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce421cebd536d704ab972a4c1278435f9c1c93600259d63782e244bb3f1c2a5
+size 861966906

run-0/checkpoint-4978/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cca452c86ff3b51ff244059362f1bff73fb4bf068abd224b900280f3d26c3ce
+size 14308

run-0/checkpoint-4978/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:debf33005351f49c3caf86a85f7177c209ff6f515dbd5e93a6f3b017ad7c6fb6
+size 1064

run-0/checkpoint-4978/special_tokens_map.json

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

run-0/checkpoint-4978/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": true,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-4978/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4978,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2008838891120932,
+      "grad_norm": 2.296739339828491,
+      "learning_rate": 1.0356804114498648e-06,
+      "loss": 0.5028,
+      "step": 500
+    },
+    {
+      "epoch": 0.4017677782241864,
+      "grad_norm": 2.885403871536255,
+      "learning_rate": 9.9232836408905e-07,
+      "loss": 0.1797,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6026516673362796,
+      "grad_norm": 4.714044570922852,
+      "learning_rate": 9.489763167282352e-07,
+      "loss": 0.1448,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8035355564483728,
+      "grad_norm": 3.8532094955444336,
+      "learning_rate": 9.056242693674206e-07,
+      "loss": 0.1199,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9636836795859589,
+      "eval_f1": 0.6468026587210636,
+      "eval_loss": 0.10681386291980743,
+      "eval_precision": 0.5823359471729261,
+      "eval_recall": 0.727319587628866,
+      "eval_runtime": 20.4746,
+      "eval_samples_per_second": 208.356,
+      "eval_steps_per_second": 26.081,
+      "step": 2489
+    },
+    {
+      "epoch": 1.004419445560466,
+      "grad_norm": 1.4627267122268677,
+      "learning_rate": 8.622722220066057e-07,
+      "loss": 0.1126,
+      "step": 2500
+    },
+    {
+      "epoch": 1.2053033346725592,
+      "grad_norm": 2.071267604827881,
+      "learning_rate": 8.189201746457909e-07,
+      "loss": 0.1053,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4061872237846524,
+      "grad_norm": 6.656711101531982,
+      "learning_rate": 7.755681272849762e-07,
+      "loss": 0.0984,
+      "step": 3500
+    },
+    {
+      "epoch": 1.6070711128967456,
+      "grad_norm": 1.1916735172271729,
+      "learning_rate": 7.322160799241614e-07,
+      "loss": 0.0966,
+      "step": 4000
+    },
+    {
+      "epoch": 1.8079550020088389,
+      "grad_norm": 2.3483071327209473,
+      "learning_rate": 6.888640325633467e-07,
+      "loss": 0.0914,
+      "step": 4500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9708767672041989,
+      "eval_f1": 0.7143198661247907,
+      "eval_loss": 0.0914178416132927,
+      "eval_precision": 0.6660722246990638,
+      "eval_recall": 0.7701030927835052,
+      "eval_runtime": 19.9542,
+      "eval_samples_per_second": 213.79,
+      "eval_steps_per_second": 26.761,
+      "step": 4978
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 12445,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 1174602430481040.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0790324588106795e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 32
+  }
+}

run-0/checkpoint-4978/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d43e989f6f8e3748c1514af63a5b86043726cda1141564108d087f161829651
+size 5112

run-0/checkpoint-7467/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "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": "O",
+    "1": "B-Disease",
+    "2": "I-Disease",
+    "3": "B-Chemical",
+    "4": "I-Chemical",
+    "5": "B-Gene",
+    "6": "I-Gene"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Chemical": 3,
+    "B-Disease": 1,
+    "B-Gene": 5,
+    "I-Chemical": 4,
+    "I-Disease": 2,
+    "I-Gene": 6,
+    "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

run-0/checkpoint-7467/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9dc8531b84f3933726cbbc496e7dc3b71360414f29ceba795eac5c6ce32838
+size 14308

run-0/checkpoint-7467/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161e562e54acdebcebef5c6441dd9d70de9e134ca451e5f38a27022c030230e1
+size 1064

run-0/checkpoint-7467/special_tokens_map.json

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