ttlanhhh/mlma-biogpt

README.md

@@ -0,0 +1,65 @@
+---
+license: mit
+base_model: microsoft/biogpt
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1870
+- Overall Precision: 0.4821
+- Overall Recall: 0.5760
+- Overall F1: 0.5249
+- Overall Accuracy: 0.9506
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 0.2295        | 1.0   | 1358 | 0.1735          | 0.3341            | 0.3926         | 0.3610     | 0.9483           |
+| 0.1401        | 2.0   | 2716 | 0.1512          | 0.3905            | 0.5413         | 0.4537     | 0.9509           |
+| 0.0948        | 3.0   | 4074 | 0.1627          | 0.4667            | 0.5070         | 0.4860     | 0.9578           |
+| 0.0778        | 4.0   | 5432 | 0.1672          | 0.4831            | 0.5642         | 0.5205     | 0.9587           |
+| 0.0614        | 5.0   | 6790 | 0.1755          | 0.4967            | 0.5781         | 0.5344     | 0.9594           |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 1.12.1+cu113
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "microsoft/biogpt",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_norm_epsilon": 1e-05,
+  "layerdrop": 0.0,
+  "model_type": "gpt2",
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "pad_token_id": 1,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "scale_embedding": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 42384
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af87b39077fcb050ec6cb9c1d4269bbac2dc3b897b5bd37b16ce392200e6675
+size 1387087524

runs/Apr11_21-45-29_bunbo/events.out.tfevents.1712886331.bunbo.3542636.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad8e4b94170da720d2c3eb53f642c83c97c11ebd2de5da53f735d6b6ddaea84
+size 10692

runs/Apr11_21-45-29_bunbo/events.out.tfevents.1712887689.bunbo.3542636.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b3a9dc1b3d0f624129fa8e501c510b7d123edc0d5f07405d1f1c2df91cdd63
+size 1096

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BioGptTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a84b3b03989c5240752411afa66863e6afa0fa79439ae31c6524f3f71cb553c
+size 4463