Saiga_timelist_task10steps

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: 2.1174

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: 5
• total_train_batch_size: 10
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 10

Training results

Training Loss	Epoch	Step	Validation Loss
2.2271	0.19	2	2.2100
2.1157	0.37	4	2.1626
2.0908	0.56	6	2.1361
2.0042	0.74	8	2.1218
1.9971	0.93	10	2.1174

Framework versions

• PEFT 0.10.0
• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2