Upload folder using huggingface_hub

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
+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-fulltext](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3300
+- Accuracy: 0.9547
+
+## 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  | 0.1947          | 0.9471   |
+| 0.1709        | 2.0   | 1582 | 0.2474          | 0.9527   |
+| 0.0734        | 3.0   | 2373 | 0.2485          | 0.9475   |
+| 0.0475        | 4.0   | 3164 | 0.2686          | 0.9499   |
+| 0.0475        | 5.0   | 3955 | 0.3196          | 0.9475   |
+| 0.0284        | 6.0   | 4746 | 0.3014          | 0.9527   |
+| 0.0194        | 7.0   | 5537 | 0.3125          | 0.9523   |
+| 0.0133        | 8.0   | 6328 | 0.3641          | 0.9491   |
+| 0.0065        | 9.0   | 7119 | 0.3300          | 0.9547   |
+| 0.0065        | 10.0  | 7910 | 0.3502          | 0.9543   |
+
+
+### 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": 0.9547275641025641,
+    "eval_loss": 0.3299635350704193,
+    "eval_runtime": 4.9525,
+    "eval_samples": 25296,
+    "eval_samples_per_second": 503.99,
+    "eval_steps_per_second": 2.019,
+    "test_accuracy": 0.947515745276417,
+    "test_loss": 0.40029823780059814,
+    "test_runtime": 10.3731,
+    "test_samples_per_second": 551.038,
+    "test_steps_per_second": 2.217,
+    "train_accuracy": 0.9991698292220114,
+    "train_loss": 0.002276296028867364,
+    "train_runtime": 40.6031,
+    "train_samples": 25296,
+    "train_samples_per_second": 623.007,
+    "train_steps_per_second": 2.438
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext",
+  "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": 0.9547275641025641,
+    "eval_loss": 0.3299635350704193,
+    "eval_runtime": 4.9525,
+    "eval_samples": 2496,
+    "eval_samples_per_second": 503.99,
+    "eval_steps_per_second": 2.019
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e1d878bba795edd7a5272e3ee922827866a61d9e41243233be61ab9f756f42d
+size 437967876

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d1d717d0deeedc20d8c035b7c48de5b4c25f7e75fdcf077e3bc16038eb4268
+size 50048

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b64ab8c89f2134f96b6c121aa574cb8b09b81bf61ffce47e8208d6f490330f
+size 114448

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6319821e0cdf80d556c13b128714327cce202217065ee9eb94d88b89d5e5c097
+size 506048

runs/Apr27_05-49-22_clu/events.out.tfevents.1714196981.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de062eb1830c0fa104368adbe3afd101e2ca69e1f6aa866efb5fd5181eda2ee0
+size 10030

runs/Apr27_05-49-22_clu/events.out.tfevents.1714198415.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8606758a7cd90f4665e25585c1fd0235b22a4fd867093b0dece4fe59f7b2cf27
+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": 0.947515745276417,
+    "test_loss": 0.40029823780059814,
+    "test_runtime": 10.3731,
+    "test_samples_per_second": 551.038,
+    "test_steps_per_second": 2.217
+}

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": 0.9991698292220114,
+    "train_loss": 0.002276296028867364,
+    "train_runtime": 40.6031,
+    "train_samples_per_second": 623.007,
+    "train_steps_per_second": 2.438
+}

trainer_state.json

@@ -0,0 +1,169 @@
+{
+  "best_metric": 0.9547275641025641,
+  "best_model_checkpoint": "text/train/checkpoint/pubmedbert-fulltext/ddi_42/checkpoint-7119",
+  "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": 0.9471153846153846,
+      "eval_loss": 0.19469894468784332,
+      "eval_runtime": 5.2082,
+      "eval_samples_per_second": 479.246,
+      "eval_steps_per_second": 1.92,
+      "step": 791
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 8.167149543762207,
+      "learning_rate": 4.367888748419722e-05,
+      "loss": 0.1709,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9527243589743589,
+      "eval_loss": 0.2473936378955841,
+      "eval_runtime": 4.9302,
+      "eval_samples_per_second": 506.267,
+      "eval_steps_per_second": 2.028,
+      "step": 1582
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 0.3635082244873047,
+      "learning_rate": 3.735777496839444e-05,
+      "loss": 0.0734,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9475160256410257,
+      "eval_loss": 0.24853640794754028,
+      "eval_runtime": 4.9236,
+      "eval_samples_per_second": 506.945,
+      "eval_steps_per_second": 2.031,
+      "step": 2373
+    },
+    {
+      "epoch": 3.79,
+      "grad_norm": 7.960566520690918,
+      "learning_rate": 3.1036662452591655e-05,
+      "loss": 0.0475,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9499198717948718,
+      "eval_loss": 0.26862233877182007,
+      "eval_runtime": 4.8986,
+      "eval_samples_per_second": 509.536,
+      "eval_steps_per_second": 2.041,
+      "step": 3164
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9475160256410257,
+      "eval_loss": 0.3195907175540924,
+      "eval_runtime": 4.8903,
+      "eval_samples_per_second": 510.395,
+      "eval_steps_per_second": 2.045,
+      "step": 3955
+    },
+    {
+      "epoch": 5.06,
+      "grad_norm": 0.0017318876925855875,
+      "learning_rate": 2.4715549936788876e-05,
+      "loss": 0.0284,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9527243589743589,
+      "eval_loss": 0.3014063239097595,
+      "eval_runtime": 4.8924,
+      "eval_samples_per_second": 510.174,
+      "eval_steps_per_second": 2.044,
+      "step": 4746
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.025161907076835632,
+      "learning_rate": 1.8394437420986094e-05,
+      "loss": 0.0194,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.952323717948718,
+      "eval_loss": 0.3125186860561371,
+      "eval_runtime": 4.9579,
+      "eval_samples_per_second": 503.443,
+      "eval_steps_per_second": 2.017,
+      "step": 5537
+    },
+    {
+      "epoch": 7.59,
+      "grad_norm": 0.21671424806118011,
+      "learning_rate": 1.2073324905183313e-05,
+      "loss": 0.0133,
+      "step": 6000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9491185897435898,
+      "eval_loss": 0.3640977442264557,
+      "eval_runtime": 4.9394,
+      "eval_samples_per_second": 505.32,
+      "eval_steps_per_second": 2.025,
+      "step": 6328
+    },
+    {
+      "epoch": 8.85,
+      "grad_norm": 0.002933135023340583,
+      "learning_rate": 5.752212389380531e-06,
+      "loss": 0.0065,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9547275641025641,
+      "eval_loss": 0.3299635350704193,
+      "eval_runtime": 4.8971,
+      "eval_samples_per_second": 509.686,
+      "eval_steps_per_second": 2.042,
+      "step": 7119
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9543269230769231,
+      "eval_loss": 0.3501527011394501,
+      "eval_runtime": 4.9496,
+      "eval_samples_per_second": 504.282,
+      "eval_steps_per_second": 2.02,
+      "step": 7910
+    },
+    {
+      "epoch": 10.0,
+      "step": 7910,
+      "total_flos": 1.663959132942336e+16,
+      "train_loss": 0.04588771306458677,
+      "train_runtime": 1428.2798,
+      "train_samples_per_second": 177.108,
+      "train_steps_per_second": 5.538
+    }
+  ],
+  "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:b604336e5303a5987dd2272e4fa97c85c421f495d21a3ecb2720fd7a2daf98d3
+size 5048