Llama-31-8B_task-2_120-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-2 and the GaetanMichelet/chat-120_ft_task-2 datasets. It achieves the following results on the evaluation set:

• Loss: 0.7019

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
1.0038	1.0	11	1.0449
0.7984	2.0	22	0.8689
0.7296	3.0	33	0.7800
0.6657	4.0	44	0.7303
0.6182	5.0	55	0.7019
0.5273	6.0	66	0.7109
0.4129	7.0	77	0.7554
0.3213	8.0	88	0.8617
0.1596	9.0	99	0.9911
0.0669	10.0	110	1.2427
0.0274	11.0	121	1.3832
0.0273	12.0	132	1.3989

Framework versions

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