Training in progress, epoch 1

README.md

@@ -0,0 +1,92 @@
+---
+base_model: arnabdhar/tinybert-ner
+tags:
+- generated_from_trainer
+datasets:
+- ncbi_disease
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: checkpoint-1000
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: ncbi_disease
+      type: ncbi_disease
+      config: ncbi_disease
+      split: test
+      args: ncbi_disease
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.4722222222222222
+    - name: Recall
+      type: recall
+      value: 0.40729166666666666
+    - name: F1
+      type: f1
+      value: 0.43736017897091717
+    - name: Accuracy
+      type: accuracy
+      value: 0.9466873494713638
+---
+
+<!-- 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. -->
+
+# checkpoint-1000
+
+This model is a fine-tuned version of [arnabdhar/tinybert-ner](https://huggingface.co/arnabdhar/tinybert-ner) on the ncbi_disease dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1611
+- Precision: 0.4722
+- Recall: 0.4073
+- F1: 0.4374
+- Accuracy: 0.9467
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 340  | 0.2055          | 0.2744    | 0.1521 | 0.1957 | 0.9318   |
+| 0.2656        | 2.0   | 680  | 0.1761          | 0.4051    | 0.3    | 0.3447 | 0.9417   |
+| 0.1738        | 3.0   | 1020 | 0.1638          | 0.4582    | 0.4    | 0.4271 | 0.9455   |
+| 0.1738        | 4.0   | 1360 | 0.1611          | 0.4722    | 0.4073 | 0.4374 | 0.9467   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-Disease",
+    "2": "I-Disease"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Disease": 1,
+    "I-Disease": 2,
+    "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": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f34b2e185653aa2f1e3ec3eeda8458f0a1271a561148e2b60a9e40de1e3f14
+size 435599164

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5981d85e93edd4f4c002d716f412c863acbe96eebe06b95193b5a3d9f11abc6
+size 34991162

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ffd64f9c59f4cc6191772b63cbbf114d3a28b67901f6e4da062e33b80e64799
+size 14244

runs/Nov27_16-49-42_0289733fd6c3/events.out.tfevents.1701103794.0289733fd6c3.579.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f608d4ce7f77121fe7fc1a2689ce7a95afb73adadede076d70fababc8dd828f
+size 6980

runs/Nov27_17-15-13_0289733fd6c3/events.out.tfevents.1701105421.0289733fd6c3.579.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e03a50b9a6d5f87bfb39753d39c57852817b97ecad3dc01f24c34e659a5246
+size 4899

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e408cd00542e53b37c9d20a61603e57ee2b15e617c35a98de110fa7b5570e590
+size 1064

special_tokens_map.json

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

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]"
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4705882352941178,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.774509803921569e-05,
+      "loss": 0.2314,
+      "step": 500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.5490196078431373e-05,
+      "loss": 0.1472,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2040,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1149951689880.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea94b55f433bbe2f8ea757c1ea53f6910e6153d92f90350b3fe20600a342e2bb
+size 4600