mistral-7B-v0.1-adaptor-qlora-prompt_prediction-stf-packing – AI Model by t0r0id | AlphaNeural AI

You can deploy this model and start earning money today!

t0r0id/
mistral-7B-v0.1-adaptor-qlora-prompt_prediction-stf-packing

like

0

generated_from_trainer

mistralai/Mistral-7B-v0.1

Views

No views yet

mistral-7B-v0.1-adaptor-qlora-prompt_prediction-stf-packing

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: 1.2910

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: 2.5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 3
total_train_batch_size: 24
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.05
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.4894	0.1	28	1.4172
1.3072	0.2	56	1.3256
1.3538	0.3	84	1.3117
1.3487	0.41	112	1.3040
1.3897	0.51	140	1.3000
1.3847	0.61	168	1.2960
1.3974	0.71	196	1.2935
1.2481	0.81	224	1.2918
1.3313	0.91	252	1.2910

Framework versions

PEFT 0.7.1
Transformers 4.37.1
Pytorch 2.0.1+cu117
Datasets 2.16.1
Tokenizers 0.15.1