SweetZiyi/MLMA_Lab8_Task2

README.md

@@ -0,0 +1,68 @@
+---
+license: mit
+base_model: microsoft/biogpt
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: test-trainer
+  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. -->
+
+# test-trainer
+
+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: 0.2658
+- Precision: 0.0656
+- Recall: 0.0323
+- F1: 0.0433
+- Accuracy: 0.9309
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.3448        | 1.0   | 679  | 0.2682          | 0.0046    | 0.0013 | 0.0020 | 0.9289   |
+| 0.267         | 2.0   | 1358 | 0.2548          | 0.0347    | 0.0142 | 0.0201 | 0.9309   |
+| 0.2122        | 3.0   | 2037 | 0.2658          | 0.0656    | 0.0323 | 0.0433 | 0.9309   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- 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": "O",
+    "1": "B-Disease",
+    "2": "I-Disease"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-Disease": 1,
+    "I-Disease": 2,
+    "O": 0
+  },
+  "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": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 42384
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e1a11cc368ab17a00ee170e14c8ca913c53ac625ec1d2e36193f31b3e0290a4
+size 1387087524

runs/Apr12_04-19-53_df600707e3d1/events.out.tfevents.1712895594.df600707e3d1.2367.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1686bbd3a6612c63e68f4bb8c9ba98829c3e3cf6289c63a920d0edf2fba5c7b
+size 4684

runs/Apr12_04-32-39_df600707e3d1/events.out.tfevents.1712896359.df600707e3d1.30806.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:814f74869a65e598ee02dee1b53d1307d79f9ad5da188035cb410f733a02d26e
+size 4686

runs/Apr12_04-34-18_df600707e3d1/events.out.tfevents.1712896458.df600707e3d1.30806.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77502e91540a2d21401c00a5aea849acaac33616541e0268ed0e1dbd93484b01
+size 4688

runs/Apr12_04-35-10_df600707e3d1/events.out.tfevents.1712896511.df600707e3d1.30806.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b48edb906f5123a38a1b8c55648f9a7726fa7bb8e3d57a7361d5d5e4d44446
+size 5271

runs/Apr12_05-08-55_df600707e3d1/events.out.tfevents.1712898535.df600707e3d1.30806.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d6d95c232dc51b966a82d89d12eceed0a315bde2186d57ae3440e417f3a86a6
+size 5060

runs/Apr12_05-09-25_df600707e3d1/events.out.tfevents.1712898566.df600707e3d1.30806.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac722a4f1aea0143eacf3b57716bf5b1b50e912ec7a948e676158930b40686f
+size 5542

runs/Apr12_05-41-07_df600707e3d1/events.out.tfevents.1712900468.df600707e3d1.30806.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291762e18d512fde911f79459698417e7c5247d8388172e247e5466df7f17481
+size 7674

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 sha256:10b5be5cd882f897814d72eeaa1fad273bedd0e6efbe898835772e8009f183a8
+size 4856