saiga_double_lora200

This model is a fine-tuned version of TheBloke/Llama-2-7B-fp16 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.4338

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: 0.0003
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 10
• total_train_batch_size: 20
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
1.5965	2.86	20	1.6827
1.4291	5.71	40	1.7434
1.2662	8.57	60	1.8297
1.1034	11.43	80	1.9381
0.9573	14.29	100	2.0414
0.8209	17.14	120	2.1761
0.71	20.0	140	2.2933
0.6181	22.86	160	2.3642
0.572	25.71	180	2.4225
0.544	28.57	200	2.4338

Framework versions

• PEFT 0.10.0
• Transformers 4.36.2
• Pytorch 2.2.2+cu121
• Datasets 2.19.0
• Tokenizers 0.15.2