results – AI Model by kta-dev | AlphaNeural AI

You can deploy this model and start earning money today!

kta-dev/
results

like

0

generated_from_trainer

mistralai/Mistral-7B-v0.1

Views

No views yet

results

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.3856

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: 2e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.4616	0.0	1	1.4223
1.4337	0.0	2	1.4204
1.6083	0.0	3	1.4186
1.0152	0.0	4	1.4168
1.5549	0.0	5	1.4150
1.4039	0.0	6	1.4132
1.0972	0.01	7	1.4115
1.4686	0.01	8	1.4098
1.3683	0.01	9	1.4081
1.2799	0.01	10	1.4065
1.2553	0.01	11	1.4048
1.3466	0.01	12	1.4032
1.1299	0.01	13	1.4016
1.8492	0.01	14	1.4000
1.3812	0.01	15	1.3985
1.1716	0.01	16	1.3970
1.1015	0.01	17	1.3955
1.5655	0.01	18	1.3942
1.4379	0.02	19	1.3930
1.2552	0.02	20	1.3918
1.1698	0.02	21	1.3907
1.3563	0.02	22	1.3897
1.6058	0.02	23	1.3889
1.4902	0.02	24	1.3881
1.6846	0.02	25	1.3874
1.2315	0.02	26	1.3868
1.0901	0.02	27	1.3863
1.2795	0.02	28	1.3860
1.1802	0.02	29	1.3857
1.2028	0.02	30	1.3856

Framework versions

PEFT 0.10.0
Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2