mistral7b_instruct_generation – AI Model by 4ndr3w | AlphaNeural AI

You can deploy this model and start earning money today!

4ndr3w/
mistral7b_instruct_generation

like

0

generated_from_trainer

mistralai/Mistral-7B-v0.1

Views

No views yet

mistral7b_instruct_generation

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

Loss: 1.8017

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: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
lr_scheduler_warmup_steps: 0.03
training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
1.8552	0.0	20	1.8246
1.9103	0.01	40	1.7950
1.8802	0.01	60	1.7918
1.7641	0.01	80	1.7952
1.8434	0.01	100	1.7969
1.8108	0.02	120	1.7955
1.8556	0.02	140	1.7928
1.8986	0.02	160	1.7948
1.8581	0.03	180	1.8270
1.7897	0.03	200	1.7943
1.7806	0.03	220	1.7922
1.8261	0.03	240	1.7956
1.8138	0.04	260	1.7988
1.8244	0.04	280	1.7902
1.8769	0.04	300	1.7977
1.896	0.04	320	1.7932
1.9111	0.05	340	1.7987
1.8624	0.05	360	1.7998
1.9663	0.05	380	1.7964
1.9383	0.06	400	1.7989
1.8478	0.06	420	1.7924
1.9117	0.06	440	1.7899
1.8742	0.06	460	1.7920
1.7778	0.07	480	1.8015
1.9523	0.07	500	1.8017

Framework versions

PEFT 0.8.2
Transformers 4.37.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.1