Chitti-Base-model-for-GPT-v13
This model is a fine-tuned version of Dhahlan2000/Chitti-Large-model-for-GPT-v12 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8350
- Bleu: 5.9886
- Gen Len: 12.23
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 3.0613 | 1.0 | 18563 | 2.8614 | 5.7037 | 12.3563 |
| 3.0535 | 2.0 | 37126 | 2.8414 | 5.9119 | 12.292 |
| 3.0117 | 3.0 | 55689 | 2.8350 | 5.9886 | 12.23 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 12
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for Dhahlan2000/Chitti-Base-model-for-GPT-v13
Base model
Dhahlan2000/Chitti-Base-model-for-GPT-v8
Finetuned
Dhahlan2000/Chitti-Base-model-for-GPT-v9