You can deploy this model and start earning money today!

ThuyenTruongHau/
ytb-comment-mistral

Name: ytb-comment-mistral
Availability: InStock

mistralai/Mistral-7B-Instruct-v0.2

apache-2.0

Views

No views yet

ytb-comment-mistral

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.3621

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: 0.0002
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.8147	1.0	4	3.1189
2.9524	2.0	8	2.5634
2.3554	3.0	12	2.0824
1.8249	4.0	16	1.6727
1.5778	5.0	20	1.4669
1.2514	6.0	24	1.3929
1.1782	7.0	28	1.3754
1.2409	8.0	32	1.3665
1.2177	9.0	36	1.3631
1.151	10.0	40	1.3621

Framework versions

PEFT 0.17.1
Transformers 4.57.1
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

ThuyenTruongHau/ytb-comment-mistral

ytb-comment-mistral

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

ThuyenTruongHau/
ytb-comment-mistral