Mistral-7B_task-1_180-samples_config-2_full

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the GaetanMichelet/chat-60_ft_task-1, the GaetanMichelet/chat-120_ft_task-1 and the GaetanMichelet/chat-180_ft_task-1 datasets. It achieves the following results on the evaluation set:

• Loss: 0.9159

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: 16
• 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: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
1.9695	0.9412	8	1.8462
1.4658	2.0	17	1.3229
1.0873	2.9412	25	1.0281
0.8963	4.0	34	0.9578
0.8173	4.9412	42	0.9242
0.7207	6.0	51	0.9159
0.5468	6.9412	59	0.9483
0.4071	8.0	68	1.0524
0.2885	8.9412	76	1.2125
0.2064	10.0	85	1.2909
0.1585	10.9412	93	1.3461
0.125	12.0	102	1.3770
0.1121	12.9412	110	1.4892

Framework versions

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