Upload folder using huggingface_hub

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract
+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 [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2085
+- Accuracy: 0.9551
+
+## 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  | 0.1986          | 0.9383   |
+| 0.1723        | 2.0   | 1582 | 0.2700          | 0.9455   |
+| 0.0772        | 3.0   | 2373 | 0.2085          | 0.9551   |
+| 0.0516        | 4.0   | 3164 | 0.2970          | 0.9427   |
+| 0.0516        | 5.0   | 3955 | 0.2620          | 0.9539   |
+| 0.0341        | 6.0   | 4746 | 0.3973          | 0.9423   |
+| 0.0203        | 7.0   | 5537 | 0.3637          | 0.9423   |
+| 0.0146        | 8.0   | 6328 | 0.4154          | 0.9451   |
+| 0.007         | 9.0   | 7119 | 0.4219          | 0.9463   |
+| 0.007         | 10.0  | 7910 | 0.4098          | 0.9447   |
+
+
+### 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": 0.9551282051282052,
+    "eval_loss": 0.20845328271389008,
+    "eval_runtime": 4.9096,
+    "eval_samples": 25296,
+    "eval_samples_per_second": 508.388,
+    "eval_steps_per_second": 2.037,
+    "test_accuracy": 0.9391182645206438,
+    "test_loss": 0.3346391022205353,
+    "test_runtime": 9.9095,
+    "test_samples_per_second": 576.823,
+    "test_steps_per_second": 2.321,
+    "train_accuracy": 0.9922912713472486,
+    "train_loss": 0.03253408521413803,
+    "train_runtime": 40.6672,
+    "train_samples": 25296,
+    "train_samples_per_second": 622.025,
+    "train_steps_per_second": 2.434
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "text-classification",
+  "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": 30522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9551282051282052,
+    "eval_loss": 0.20845328271389008,
+    "eval_runtime": 4.9096,
+    "eval_samples": 2496,
+    "eval_samples_per_second": 508.388,
+    "eval_steps_per_second": 2.037
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8057e2d26cccbc75703b20f2c650e0332ed275e6f805e991e284c0e4044a8905
+size 437967876

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f136441d59211f3ef7c46ece76cfa43f72aff95f9bf89f08a9e498b737ae4c71
+size 50048

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e9f84d3a6af45c1dfaac187bf20245f80c41373b5675cebf69840e21313f0c
+size 114448

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c30b00c8ac7b65f9f249b5e68a343ea18ecde68212fdc139dd330614ac84a4be
+size 506048

runs/Apr27_03-43-38_clu/events.out.tfevents.1714189438.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33d109447de018595ea36c85d6ab8cdd9dab21ca67f60970ef956be8adb680fd
+size 10021

runs/Apr27_03-43-38_clu/events.out.tfevents.1714190869.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b72bb2cea2e520b69634cc82e12d77526e29bceab32a827e3b09402a5f403e2
+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": 0.9391182645206438,
+    "test_loss": 0.3346391022205353,
+    "test_runtime": 9.9095,
+    "test_samples_per_second": 576.823,
+    "test_steps_per_second": 2.321
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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": true,
+  "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]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_samples": 25296,
+    "train_accuracy": 0.9922912713472486,
+    "train_loss": 0.03253408521413803,
+    "train_runtime": 40.6672,
+    "train_samples_per_second": 622.025,
+    "train_steps_per_second": 2.434
+}

trainer_state.json

@@ -0,0 +1,169 @@
+{
+  "best_metric": 0.9551282051282052,
+  "best_model_checkpoint": "text/train/checkpoint/pubmedbert-abstract/ddi_42/checkpoint-2373",
+  "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": 0.938301282051282,
+      "eval_loss": 0.19862917065620422,
+      "eval_runtime": 5.4522,
+      "eval_samples_per_second": 457.799,
+      "eval_steps_per_second": 1.834,
+      "step": 791
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 1.910953402519226,
+      "learning_rate": 4.367888748419722e-05,
+      "loss": 0.1723,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9455128205128205,
+      "eval_loss": 0.2700441777706146,
+      "eval_runtime": 5.0135,
+      "eval_samples_per_second": 497.859,
+      "eval_steps_per_second": 1.995,
+      "step": 1582
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 19.194658279418945,
+      "learning_rate": 3.735777496839444e-05,
+      "loss": 0.0772,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9551282051282052,
+      "eval_loss": 0.20845328271389008,
+      "eval_runtime": 4.8197,
+      "eval_samples_per_second": 517.874,
+      "eval_steps_per_second": 2.075,
+      "step": 2373
+    },
+    {
+      "epoch": 3.79,
+      "grad_norm": 0.3629066050052643,
+      "learning_rate": 3.1036662452591655e-05,
+      "loss": 0.0516,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9427083333333334,
+      "eval_loss": 0.2969796061515808,
+      "eval_runtime": 4.7872,
+      "eval_samples_per_second": 521.395,
+      "eval_steps_per_second": 2.089,
+      "step": 3164
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.953926282051282,
+      "eval_loss": 0.2620067596435547,
+      "eval_runtime": 4.7806,
+      "eval_samples_per_second": 522.107,
+      "eval_steps_per_second": 2.092,
+      "step": 3955
+    },
+    {
+      "epoch": 5.06,
+      "grad_norm": 0.0031597923953086138,
+      "learning_rate": 2.4715549936788876e-05,
+      "loss": 0.0341,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9423076923076923,
+      "eval_loss": 0.39730244874954224,
+      "eval_runtime": 4.7836,
+      "eval_samples_per_second": 521.783,
+      "eval_steps_per_second": 2.09,
+      "step": 4746
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.006749527528882027,
+      "learning_rate": 1.8394437420986094e-05,
+      "loss": 0.0203,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9423076923076923,
+      "eval_loss": 0.3636617958545685,
+      "eval_runtime": 4.7835,
+      "eval_samples_per_second": 521.797,
+      "eval_steps_per_second": 2.091,
+      "step": 5537
+    },
+    {
+      "epoch": 7.59,
+      "grad_norm": 0.012521493248641491,
+      "learning_rate": 1.2073324905183313e-05,
+      "loss": 0.0146,
+      "step": 6000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9451121794871795,
+      "eval_loss": 0.4154008626937866,
+      "eval_runtime": 4.7634,
+      "eval_samples_per_second": 523.998,
+      "eval_steps_per_second": 2.099,
+      "step": 6328
+    },
+    {
+      "epoch": 8.85,
+      "grad_norm": 0.005341885611414909,
+      "learning_rate": 5.752212389380531e-06,
+      "loss": 0.007,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9463141025641025,
+      "eval_loss": 0.4218637943267822,
+      "eval_runtime": 4.8145,
+      "eval_samples_per_second": 518.431,
+      "eval_steps_per_second": 2.077,
+      "step": 7119
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9447115384615384,
+      "eval_loss": 0.4098478853702545,
+      "eval_runtime": 4.8332,
+      "eval_samples_per_second": 516.428,
+      "eval_steps_per_second": 2.069,
+      "step": 7910
+    },
+    {
+      "epoch": 10.0,
+      "step": 7910,
+      "total_flos": 1.663959132942336e+16,
+      "train_loss": 0.048086456131241864,
+      "train_runtime": 1425.5671,
+      "train_samples_per_second": 177.445,
+      "train_steps_per_second": 5.549
+    }
+  ],
+  "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 sha256:4de6cbc7180e01d7bbaac6d209405970b8c1932b419ce007ab9190aeb3348435
+size 5048