Chitti-Large-model-for-GPT-v11

This model is a fine-tuned version of Dhahlan2000/Chitti-Base-model-for-GPT-v10 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.8143
• Bleu: 5.3746
• Gen Len: 12.2533

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: 6
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
3.0362	1.0	9282	2.8427	4.9768	12.194
3.0372	2.0	18564	2.8305	5.2045	12.3033
3.0038	3.0	27846	2.8253	5.2307	12.268
2.9933	4.0	37128	2.8188	5.4433	12.3027
2.9947	5.0	46410	2.8139	5.3825	12.2993
2.9752	6.0	55692	2.8143	5.3746	12.2533

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1