README.md

metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: gokulsrinivasagan/bert_base_train_book_ent_15p_s_init
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model-index:
  - name: bert_base_train_book_ent_15p_s_init_mrpc
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MRPC
          type: glue
          args: mrpc
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6838235294117647
          - name: F1
            type: f1
            value: 0.8122270742358079

bert_base_train_book_ent_15p_s_init_mrpc

This model is a fine-tuned version of gokulsrinivasagan/bert_base_train_book_ent_15p_s_init on the GLUE MRPC dataset. It achieves the following results on the evaluation set:

• Loss: 0.6236
• Accuracy: 0.6838
• F1: 0.8122
• Combined Score: 0.7480

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: 256
• eval_batch_size: 256
• seed: 10
• 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Combined Score
0.6428	1.0	15	0.6255	0.6838	0.8122	0.7480
0.6363	2.0	30	0.6297	0.6838	0.8122	0.7480
0.6317	3.0	45	0.6301	0.6838	0.8122	0.7480
0.6411	4.0	60	0.6255	0.6838	0.8122	0.7480
0.6336	5.0	75	0.6254	0.6838	0.8122	0.7480
0.6348	6.0	90	0.6239	0.6838	0.8122	0.7480
0.6346	7.0	105	0.6236	0.6838	0.8122	0.7480
0.6364	8.0	120	0.6242	0.6838	0.8122	0.7480
0.6309	9.0	135	0.6321	0.6838	0.8122	0.7480
0.6392	10.0	150	0.6242	0.6838	0.8122	0.7480
0.6353	11.0	165	0.6271	0.6838	0.8122	0.7480
0.6339	12.0	180	0.6260	0.6838	0.8122	0.7480

Framework versions

• Transformers 4.51.2
• Pytorch 2.6.0+cu126
• Datasets 3.5.0
• Tokenizers 0.21.1