adyogigpt-ft

This model is a fine-tuned version of TheBloke/Llama-2-13B-chat-GPTQ on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.6650

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.2052	0.8	2	3.3403
2.7583	2.0	5	3.2177
3.988	2.8	7	3.1077
2.548	4.0	10	2.9435
3.6494	4.8	12	2.8515
2.3538	6.0	15	2.7460
3.4301	6.8	17	2.6985
2.251	8.0	20	2.6650

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1