Chitti-Large-model-for-GPT-v12

This model is a fine-tuned version of Dhahlan2000/Chitti-Base-model-for-GPT-v11 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.6474
• Bleu: 0.0
• Gen Len: 2.9375

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
No log	1.0	98	2.8825	0.0	2.9375
No log	2.0	196	2.7710	0.0	3.0
No log	3.0	294	2.6990	0.0	2.875
No log	4.0	392	2.6685	0.0	2.9375
No log	5.0	490	2.6490	0.0	2.9375
3.4263	6.0	588	2.6474	0.0	2.9375

Framework versions

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