SweetZiyi/MLMA_Lab8_Task2

README.md

@@ -0,0 +1,58 @@
+---
+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:
+- eval_precision: 0.4837
+- eval_recall: 0.5349
+- eval_f1: 0.5080
+- eval_accuracy: 0.9438
+- eval_loss: 0.1802
+- eval_runtime: 14.3435
+- eval_samples_per_second: 65.605
+- eval_steps_per_second: 1.046
+- step: 0
+
+## 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: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### 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": "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": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 42384
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:632e01819e52a66ad78e2418c25cf5001bea76b3278f0f101fdb16c409f35ed3
+size 1387087524

runs/Apr12_18-31-11_5dc5875bbc28/events.out.tfevents.1712946685.5dc5875bbc28.709.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efdd03ca5163c58860bb654f988050ec829e4050cce189ef21dde0cd98402e12
+size 518

runs/Apr12_18-32-03_5dc5875bbc28/events.out.tfevents.1712946737.5dc5875bbc28.709.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1101e615204ee2b5b9c07e13d8e4733d949d3dd4aa0c793675e0dbb7a07eb1
+size 518

runs/Apr12_18-35-56_5dc5875bbc28/events.out.tfevents.1712946970.5dc5875bbc28.709.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c8818cfe08b2e6029aef04bf55dd967e7f75f344da0d9200fc172f82d6cec3
+size 486

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d3cf6aafbb5035dc6e46cfbd0f139aa877de7626e9a801b27431cab28f59920
+size 4856