Initial Commit

README.md

@@ -0,0 +1,71 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: best_model
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# best_model
+
+This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.1](https://huggingface.co/dmis-lab/biobert-base-cased-v1.1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2832
+- Accuracy: 0.8934
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.3587        | 0.14  | 5000  | 0.3137          | 0.8834   |
+| 0.3318        | 0.29  | 10000 | 0.3100          | 0.8831   |
+| 0.3286        | 0.43  | 15000 | 0.3033          | 0.8864   |
+| 0.3236        | 0.58  | 20000 | 0.3037          | 0.8862   |
+| 0.3182        | 0.72  | 25000 | 0.2939          | 0.8876   |
+| 0.3129        | 0.87  | 30000 | 0.2910          | 0.8885   |
+| 0.3078        | 1.01  | 35000 | 0.2914          | 0.8887   |
+| 0.2791        | 1.16  | 40000 | 0.2975          | 0.8874   |
+| 0.2723        | 1.3   | 45000 | 0.2913          | 0.8906   |
+| 0.2724        | 1.45  | 50000 | 0.2879          | 0.8904   |
+| 0.27          | 1.59  | 55000 | 0.2874          | 0.8911   |
+| 0.2681        | 1.74  | 60000 | 0.2848          | 0.8928   |
+| 0.2672        | 1.88  | 65000 | 0.2832          | 0.8934   |
+
+
+### Framework versions
+
+- Transformers 4.18.0.dev0
+- Pytorch 1.10.0+cu111
+- Datasets 1.18.4
+- Tokenizers 0.11.6

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.893439769744873,
+    "eval_loss": 0.2832432985305786,
+    "eval_runtime": 132.9041,
+    "eval_samples": 28932,
+    "eval_samples_per_second": 217.691,
+    "eval_steps_per_second": 3.408,
+    "train_loss": 0.29886255871073064,
+    "train_runtime": 56655.4623,
+    "train_samples": 2211861,
+    "train_samples_per_second": 78.081,
+    "train_steps_per_second": 1.22
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "dmis-lab/biobert-base-cased-v1.1",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "BACKGROUND",
+    "1": "CONCLUSIONS",
+    "2": "METHODS",
+    "3": "OBJECTIVE",
+    "4": "RESULTS"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "BACKGROUND": 0,
+    "CONCLUSIONS": 1,
+    "METHODS": 2,
+    "OBJECTIVE": 3,
+    "RESULTS": 4
+  },
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.893439769744873,
+    "eval_loss": 0.2832432985305786,
+    "eval_runtime": 132.9041,
+    "eval_samples": 28932,
+    "eval_samples_per_second": 217.691,
+    "eval_steps_per_second": 3.408
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eefad34e64af048ea4b9de235c39a8cb8fcbf0352f8d75a6807261335706ff9
+size 433341485

runs/Mar14_20-34-02_ef586ffcf6f8/1647290356.345718/events.out.tfevents.1647290356.ef586ffcf6f8.959.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2adae1cdd324c1df34b0a4457598483e9ff1870dbb3d4692bdbd0d2ce97ace0
+size 4807

runs/Mar14_20-34-02_ef586ffcf6f8/events.out.tfevents.1647290356.ef586ffcf6f8.959.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cbef9103cf47b5c85025cce5b52e07efc3ae8e3fa5c9c88470cf3b1d39b9498
+size 10198

runs/Mar14_20-34-02_ef586ffcf6f8/events.out.tfevents.1647347145.ef586ffcf6f8.959.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89d16f1cf9f17853ba5c51110791f1f3ee36cb900226fc80bb632fc81d7e68f0
+size 369

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "dmis-lab/biobert-base-cased-v1.1", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.29886255871073064,
+    "train_runtime": 56655.4623,
+    "train_samples": 2211861,
+    "train_samples_per_second": 78.081,
+    "train_steps_per_second": 1.22
+}

trainer_state.json

@@ -0,0 +1,220 @@
+{
+  "best_metric": 0.2832432985305786,
+  "best_model_checkpoint": "/content/best_model/checkpoint-65000",
+  "epoch": 2.0,
+  "global_step": 69122,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.6385376580538756e-05,
+      "loss": 0.3587,
+      "step": 5000
+    },
+    {
+      "epoch": 0.14,
+      "eval_accuracy": 0.883381724357605,
+      "eval_loss": 0.313699334859848,
+      "eval_runtime": 130.2101,
+      "eval_samples_per_second": 222.195,
+      "eval_steps_per_second": 3.479,
+      "step": 5000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.2770029802378405e-05,
+      "loss": 0.3318,
+      "step": 10000
+    },
+    {
+      "epoch": 0.29,
+      "eval_accuracy": 0.8830706477165222,
+      "eval_loss": 0.31002119183540344,
+      "eval_runtime": 130.4095,
+      "eval_samples_per_second": 221.855,
+      "eval_steps_per_second": 3.474,
+      "step": 10000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.915395966551894e-05,
+      "loss": 0.3286,
+      "step": 15000
+    },
+    {
+      "epoch": 0.43,
+      "eval_accuracy": 0.8863887786865234,
+      "eval_loss": 0.303303599357605,
+      "eval_runtime": 130.6696,
+      "eval_samples_per_second": 221.413,
+      "eval_steps_per_second": 3.467,
+      "step": 15000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 3.5537889528659474e-05,
+      "loss": 0.3236,
+      "step": 20000
+    },
+    {
+      "epoch": 0.58,
+      "eval_accuracy": 0.8862159252166748,
+      "eval_loss": 0.3037019670009613,
+      "eval_runtime": 130.8546,
+      "eval_samples_per_second": 221.1,
+      "eval_steps_per_second": 3.462,
+      "step": 20000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.1922542750499116e-05,
+      "loss": 0.3182,
+      "step": 25000
+    },
+    {
+      "epoch": 0.72,
+      "eval_accuracy": 0.8876330852508545,
+      "eval_loss": 0.2938973009586334,
+      "eval_runtime": 130.8776,
+      "eval_samples_per_second": 221.061,
+      "eval_steps_per_second": 3.461,
+      "step": 25000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.830647261363965e-05,
+      "loss": 0.3129,
+      "step": 30000
+    },
+    {
+      "epoch": 0.87,
+      "eval_accuracy": 0.8885317444801331,
+      "eval_loss": 0.2910305857658386,
+      "eval_runtime": 131.4925,
+      "eval_samples_per_second": 220.028,
+      "eval_steps_per_second": 3.445,
+      "step": 30000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.469184919417841e-05,
+      "loss": 0.3078,
+      "step": 35000
+    },
+    {
+      "epoch": 1.01,
+      "eval_accuracy": 0.8887391090393066,
+      "eval_loss": 0.29142218828201294,
+      "eval_runtime": 131.659,
+      "eval_samples_per_second": 219.75,
+      "eval_steps_per_second": 3.441,
+      "step": 35000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2.107794913341628e-05,
+      "loss": 0.2791,
+      "step": 40000
+    },
+    {
+      "epoch": 1.16,
+      "eval_accuracy": 0.8873911499977112,
+      "eval_loss": 0.2975434362888336,
+      "eval_runtime": 132.2605,
+      "eval_samples_per_second": 218.75,
+      "eval_steps_per_second": 3.425,
+      "step": 40000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.7462602355255925e-05,
+      "loss": 0.2723,
+      "step": 45000
+    },
+    {
+      "epoch": 1.3,
+      "eval_accuracy": 0.8906055688858032,
+      "eval_loss": 0.29133233428001404,
+      "eval_runtime": 132.58,
+      "eval_samples_per_second": 218.223,
+      "eval_steps_per_second": 3.417,
+      "step": 45000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.384580885969735e-05,
+      "loss": 0.2724,
+      "step": 50000
+    },
+    {
+      "epoch": 1.45,
+      "eval_accuracy": 0.8903636336326599,
+      "eval_loss": 0.2879472076892853,
+      "eval_runtime": 132.7015,
+      "eval_samples_per_second": 218.023,
+      "eval_steps_per_second": 3.414,
+      "step": 50000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.0229738722837882e-05,
+      "loss": 0.27,
+      "step": 55000
+    },
+    {
+      "epoch": 1.59,
+      "eval_accuracy": 0.8910548686981201,
+      "eval_loss": 0.28737255930900574,
+      "eval_runtime": 132.683,
+      "eval_samples_per_second": 218.054,
+      "eval_steps_per_second": 3.414,
+      "step": 55000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 6.615115303376639e-06,
+      "loss": 0.2681,
+      "step": 60000
+    },
+    {
+      "epoch": 1.74,
+      "eval_accuracy": 0.8927831053733826,
+      "eval_loss": 0.28480109572410583,
+      "eval_runtime": 132.2639,
+      "eval_samples_per_second": 218.744,
+      "eval_steps_per_second": 3.425,
+      "step": 60000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 2.9997685252162845e-06,
+      "loss": 0.2672,
+      "step": 65000
+    },
+    {
+      "epoch": 1.88,
+      "eval_accuracy": 0.893439769744873,
+      "eval_loss": 0.2832432985305786,
+      "eval_runtime": 132.917,
+      "eval_samples_per_second": 217.67,
+      "eval_steps_per_second": 3.408,
+      "step": 65000
+    },
+    {
+      "epoch": 2.0,
+      "step": 69122,
+      "total_flos": 2.955371035238809e+17,
+      "train_loss": 0.29886255871073064,
+      "train_runtime": 56655.4623,
+      "train_samples_per_second": 78.081,
+      "train_steps_per_second": 1.22
+    }
+  ],
+  "max_steps": 69122,
+  "num_train_epochs": 2,
+  "total_flos": 2.955371035238809e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1802f27481ade8a7a37fb3236357b1d39966895d0506e183ec8691bec204c914
+size 3055