experiments

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1042

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 8
• 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: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.9273	0.43	3	1.6630
1.2968	0.86	6	1.3173
0.9918	1.29	9	1.1548
1.1456	1.71	12	1.1042

Framework versions

• Transformers 4.32.1
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3