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

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

• Loss: 0.4377

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
1.9354	1.0	17	1.7708
0.6268	2.0	34	0.6221
0.3923	3.0	51	0.5086
0.2943	4.0	68	0.4581
0.3006	5.0	85	0.4390
0.3831	6.0	102	0.4377
0.2878	7.0	119	0.4980
0.1028	8.0	136	0.6312
0.0608	9.0	153	0.6599
0.0272	10.0	170	0.7522
0.0172	11.0	187	0.8401
0.0086	12.0	204	0.8499
0.0078	13.0	221	0.8358

Framework versions

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