metadata
library_name: transformers
license: mit
base_model: openai-community/gpt2
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: finetuned_gpt2_model2
results: []
finetuned_gpt2_model2
This model is a fine-tuned version of openai-community/gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1285
- Precision: 0.3701
- Recall: 0.4221
- F1: 0.3944
- Accuracy: 0.9579
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 250 | 0.1313 | 0.3755 | 0.4334 | 0.4024 | 0.9570 |
| 0.1287 | 2.0 | 500 | 0.1298 | 0.3706 | 0.4266 | 0.3967 | 0.9577 |
| 0.1287 | 3.0 | 750 | 0.1298 | 0.3746 | 0.4242 | 0.3979 | 0.9573 |
| 0.1269 | 4.0 | 1000 | 0.1285 | 0.3701 | 0.4221 | 0.3944 | 0.9579 |
| 0.1269 | 5.0 | 1250 | 0.1287 | 0.3771 | 0.4300 | 0.4018 | 0.9576 |
| 0.127 | 6.0 | 1500 | 0.1288 | 0.3774 | 0.4300 | 0.4020 | 0.9575 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1