biogpt-mlma

README.md

@@ -0,0 +1,64 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/biogpt
+tags:
+- generated_from_trainer
+datasets:
+- ncbi_disease
+model-index:
+- name: model_folder
+  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. -->
+
+# model_folder
+
+This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on the ncbi_disease dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 1.6682
+- eval_model_preparation_time: 0.0035
+- eval_precision: 0.0217
+- eval_recall: 0.3078
+- eval_f1: 0.0405
+- eval_accuracy: 0.0532
+- eval_runtime: 40.9733
+- eval_samples_per_second: 22.966
+- eval_steps_per_second: 2.88
+- 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Framework versions
+
+- Transformers 4.51.0
+- Pytorch 2.1.0+cu121
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,50 @@
+{
+  "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": "4.51.0",
+  "use_cache": true,
+  "vocab_size": 42384
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:704a5cdf192e599380eac17c418bbd5df8c2d635a94114eecd43c4ccdf981a36
+size 1387087524

runs/Apr11_10-07-41_gpuz01/events.out.tfevents.1744380477.gpuz01.2453034.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:325e85518930d5388f39aed744aaa20798e1bc9a254635052404f57823531705
+size 7587

runs/Apr11_10-07-41_gpuz01/events.out.tfevents.1744382413.gpuz01.2453034.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9df25b2f4c990f610ca5567eb2f669163bef2ef850378ade84e144b048f9ac9
+size 984

runs/Apr11_18-45-18_gpuz03/events.out.tfevents.1744411780.gpuz03.23710.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b08b39ec570cfe220c69aa029aa3590a379825d9984327561b130856c75ba68
+size 501

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 +1,45 @@
+{
+  "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": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "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:c49b040f4d742232f5955d7a2f322cbbae3de7b96279f328cbc6e0a0ef2d8fce
+size 5368