Mistral-7B_task-1_60-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 dataset. It achieves the following results on the evaluation set:

Loss: 0.9316

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
2.1677	0.6957	2	1.9772
2.0588	1.7391	5	1.7098
1.6144	2.7826	8	1.4226
1.3861	3.8261	11	1.1334
1.0181	4.8696	14	0.9961
0.9301	5.9130	17	0.9633
0.8066	6.9565	20	0.9348
0.7473	8.0	23	0.9316
0.6909	8.6957	25	0.9585
0.5525	9.7391	28	0.9743
0.49	10.7826	31	1.0671
0.3604	11.8261	34	1.1000
0.3096	12.8696	37	1.2756
0.2231	13.9130	40	1.3029
0.1846	14.9565	43	1.4381