metadata
license: apache-2.0
base_model: Dhahlan2000/Chitti-Base-model-for-GPT-v8
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: Chitti-Base-model-for-GPT-v9
results: []
Chitti-Base-model-for-GPT-v9
This model is a fine-tuned version of Dhahlan2000/Chitti-Base-model-for-GPT-v8 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8886
- Bleu: 4.3804
- Gen Len: 12.624
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 3.1399 | 1.0 | 9282 | 2.9151 | 3.8681 | 12.7067 |
| 3.1171 | 2.0 | 18564 | 2.9030 | 4.1487 | 12.6253 |
| 3.0915 | 3.0 | 27846 | 2.8906 | 4.1716 | 12.722 |
| 3.0923 | 4.0 | 37128 | 2.8886 | 4.3804 | 12.624 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1