Llama-31-8B_task-1_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-1_auto, the GaetanMichelet/chat-120_ft_task-1_auto and the GaetanMichelet/chat-180_ft_task-1_auto datasets. It achieves the following results on the evaluation set:

• Loss: 0.7769

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
1.9328	1.0	17	1.8837
1.3207	2.0	34	1.2487
0.8894	3.0	51	0.9027
0.8023	4.0	68	0.8472
0.7382	5.0	85	0.8033
0.6937	6.0	102	0.7769
0.6042	7.0	119	0.7946
0.4994	8.0	136	0.8584
0.3568	9.0	153	0.9741
0.2463	10.0	170	1.0730
0.1823	11.0	187	1.1565
0.1229	12.0	204	1.2557
0.1015	13.0	221	1.3300

Framework versions

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