Mistral-7B_task-2_120-samples_config-2_full_auto

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the GaetanMichelet/chat-60_ft_task-2_auto and the GaetanMichelet/chat-120_ft_task-2_auto datasets. It achieves the following results on the evaluation set:

Loss: 0.7681

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
1.1522	0.9091	5	1.0969
1.0455	2.0	11	0.9818
0.9291	2.9091	16	0.9178
0.8133	4.0	22	0.8174
0.754	4.9091	27	0.7907
0.7232	6.0	33	0.7768
0.7137	6.9091	38	0.7700
0.6783	8.0	44	0.7681
0.6309	8.9091	49	0.7697
0.6237	10.0	55	0.7780
0.5633	10.9091	60	0.7931
0.4943	12.0	66	0.8165
0.4499	12.9091	71	0.8476
0.4037	14.0	77	0.9135
0.3067	14.9091	82	0.9351