Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+base_model: dmis-lab/biobert-v1.1
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: ddi_42
+  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. -->
+
+# ddi_42
+
+This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2816
+- Accuracy: 0.9535
+
+## 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: 32
+- eval_batch_size: 256
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 791  | 0.1755          | 0.9411   |
+| 0.2029        | 2.0   | 1582 | 0.1931          | 0.9495   |
+| 0.0749        | 3.0   | 2373 | 0.2716          | 0.9475   |
+| 0.0442        | 4.0   | 3164 | 0.2566          | 0.9515   |
+| 0.0442        | 5.0   | 3955 | 0.2816          | 0.9535   |
+| 0.0249        | 6.0   | 4746 | 0.3136          | 0.9471   |
+| 0.0135        | 7.0   | 5537 | 0.3219          | 0.9475   |
+| 0.0102        | 8.0   | 6328 | 0.3054          | 0.9503   |
+| 0.006         | 9.0   | 7119 | 0.3304          | 0.9515   |
+| 0.006         | 10.0  | 7910 | 0.3346          | 0.9507   |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9535256410256411,
+    "eval_loss": 0.2816075086593628,
+    "eval_runtime": 4.6959,
+    "eval_samples": 25296,
+    "eval_samples_per_second": 531.522,
+    "eval_steps_per_second": 2.129,
+    "test_accuracy": 0.943666899930021,
+    "test_loss": 0.35502904653549194,
+    "test_runtime": 9.8103,
+    "test_samples_per_second": 582.65,
+    "test_steps_per_second": 2.344,
+    "train_accuracy": 0.9965211891208097,
+    "train_loss": 0.013760130852460861,
+    "train_runtime": 40.2929,
+    "train_samples": 25296,
+    "train_samples_per_second": 627.803,
+    "train_steps_per_second": 2.457
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "dmis-lab/biobert-v1.1",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "text-classification",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 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": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9535256410256411,
+    "eval_loss": 0.2816075086593628,
+    "eval_runtime": 4.6959,
+    "eval_samples": 2496,
+    "eval_samples_per_second": 531.522,
+    "eval_steps_per_second": 2.129
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e487188e605f5d213dc922ba1bdf83cdd516b55c0b7189ab96b3430d54598d6e
+size 433279996

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39cb07f90a94fc2b6cc2f465326f83ed17694307bfbb993eb932eee13185c789
+size 50048

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:086e42a2df6d0b7314e0c766fba270fa874c2243734beeee0ddbdaa41b19a0c5
+size 114448

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dde01ff2306049ff3ed33984dc32aad221b2c9c4c1fb7804fed782cc2a35aae
+size 506048

runs/Apr26_22-36-10_clu/events.out.tfevents.1714170981.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec979c24bfb20e6569fe7df9168e131c8c0042a606683dc8cde0a24bcded2e7d
+size 9971

runs/Apr26_22-36-10_clu/events.out.tfevents.1714172415.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3854026147c9c7b0804b89834ae538a1a55fdec5a22c6fca84159078125842df
+size 1044

runs/Apr27_01-37-49_clu/events.out.tfevents.1714181882.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c18072ca67067719b3f6e06df704f7534a64f7efadae8fcf96c117ddba2ad98
+size 9971

runs/Apr27_01-37-49_clu/events.out.tfevents.1714183314.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed0820e738ae92eeec36c448124b27fc99ad2c6b6e237d4adb8de1d966ed429
+size 1044

special_tokens_map.json

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

test_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_samples": 5716,
+    "test_accuracy": 0.943666899930021,
+    "test_loss": 0.35502904653549194,
+    "test_runtime": 9.8103,
+    "test_samples_per_second": 582.65,
+    "test_steps_per_second": 2.344
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_samples": 25296,
+    "train_accuracy": 0.9965211891208097,
+    "train_loss": 0.013760130852460861,
+    "train_runtime": 40.2929,
+    "train_samples_per_second": 627.803,
+    "train_steps_per_second": 2.457
+}

trainer_state.json

@@ -0,0 +1,169 @@
+{
+  "best_metric": 0.9535256410256411,
+  "best_model_checkpoint": "text/train/checkpoint/biobert/ddi_42/checkpoint-3955",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 7910,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9411057692307693,
+      "eval_loss": 0.1755092442035675,
+      "eval_runtime": 4.5748,
+      "eval_samples_per_second": 545.6,
+      "eval_steps_per_second": 2.186,
+      "step": 791
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 5.126912593841553,
+      "learning_rate": 4.367888748419722e-05,
+      "loss": 0.2029,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9495192307692307,
+      "eval_loss": 0.19307143986225128,
+      "eval_runtime": 4.5897,
+      "eval_samples_per_second": 543.827,
+      "eval_steps_per_second": 2.179,
+      "step": 1582
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 4.425409317016602,
+      "learning_rate": 3.735777496839444e-05,
+      "loss": 0.0749,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9475160256410257,
+      "eval_loss": 0.27157464623451233,
+      "eval_runtime": 4.611,
+      "eval_samples_per_second": 541.313,
+      "eval_steps_per_second": 2.169,
+      "step": 2373
+    },
+    {
+      "epoch": 3.79,
+      "grad_norm": 0.21999871730804443,
+      "learning_rate": 3.1036662452591655e-05,
+      "loss": 0.0442,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9515224358974359,
+      "eval_loss": 0.25661203265190125,
+      "eval_runtime": 4.5979,
+      "eval_samples_per_second": 542.858,
+      "eval_steps_per_second": 2.175,
+      "step": 3164
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9535256410256411,
+      "eval_loss": 0.2816075086593628,
+      "eval_runtime": 4.559,
+      "eval_samples_per_second": 547.487,
+      "eval_steps_per_second": 2.193,
+      "step": 3955
+    },
+    {
+      "epoch": 5.06,
+      "grad_norm": 0.018685705959796906,
+      "learning_rate": 2.4715549936788876e-05,
+      "loss": 0.0249,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9471153846153846,
+      "eval_loss": 0.31359541416168213,
+      "eval_runtime": 4.623,
+      "eval_samples_per_second": 539.91,
+      "eval_steps_per_second": 2.163,
+      "step": 4746
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.039792679250240326,
+      "learning_rate": 1.8394437420986094e-05,
+      "loss": 0.0135,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9475160256410257,
+      "eval_loss": 0.3218846023082733,
+      "eval_runtime": 4.5644,
+      "eval_samples_per_second": 546.846,
+      "eval_steps_per_second": 2.191,
+      "step": 5537
+    },
+    {
+      "epoch": 7.59,
+      "grad_norm": 0.004741465672850609,
+      "learning_rate": 1.2073324905183313e-05,
+      "loss": 0.0102,
+      "step": 6000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9503205128205128,
+      "eval_loss": 0.30540913343429565,
+      "eval_runtime": 4.5686,
+      "eval_samples_per_second": 546.34,
+      "eval_steps_per_second": 2.189,
+      "step": 6328
+    },
+    {
+      "epoch": 8.85,
+      "grad_norm": 0.0014904498821124434,
+      "learning_rate": 5.752212389380531e-06,
+      "loss": 0.006,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9515224358974359,
+      "eval_loss": 0.3304109275341034,
+      "eval_runtime": 4.5703,
+      "eval_samples_per_second": 546.14,
+      "eval_steps_per_second": 2.188,
+      "step": 7119
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9507211538461539,
+      "eval_loss": 0.334633469581604,
+      "eval_runtime": 4.6402,
+      "eval_samples_per_second": 537.905,
+      "eval_steps_per_second": 2.155,
+      "step": 7910
+    },
+    {
+      "epoch": 10.0,
+      "step": 7910,
+      "total_flos": 1.663959132942336e+16,
+      "train_loss": 0.04803710016981238,
+      "train_runtime": 1426.0933,
+      "train_samples_per_second": 177.38,
+      "train_steps_per_second": 5.547
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 7910,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.663959132942336e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3089a448d56a582bb33bdcdb527373e91b01b8ff86f4c336970dcf8405218e
+size 4984