Llama-31-8B_task-3_180-samples_config-1_full_auto

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the GaetanMichelet/chat-60_ft_task-3_auto, the GaetanMichelet/chat-120_ft_task-3_auto and the GaetanMichelet/chat-180_ft_task-3_auto datasets. It achieves the following results on the evaluation set:

• Loss: 1.1245

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
1.6152	1.0	17	1.6114
1.4448	2.0	34	1.4188
1.1866	3.0	51	1.2109
1.071	4.0	68	1.1619
1.0559	5.0	85	1.1390
0.9877	6.0	102	1.1245
0.9672	7.0	119	1.1272
0.8614	8.0	136	1.1425
0.7722	9.0	153	1.1850
0.7255	10.0	170	1.2317
0.6638	11.0	187	1.2752
0.4688	12.0	204	1.3816
0.5007	13.0	221	1.3800

Framework versions

• PEFT 0.12.0
• Transformers 4.44.0
• Pytorch 2.1.2+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1