You can deploy this model and start earning money today!

nour-sam/
shawgpt-ft2

Name: shawgpt-ft2
Availability: InStock

peft

tensorboard

safetensors

generated_from_trainer

TheBloke/Mistral-7B-Instruct-v0.2-GPTQ

adapter

apache-2.0

Views

No views yet

shawgpt-ft2

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

Loss: 4.1637

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: 1e-05
train_batch_size: 42
eval_batch_size: 42
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 168
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2
num_epochs: 15
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.1584	1.0	1	4.2318
2.0801	2.0	2	4.2301
2.1449	3.0	3	4.2222
2.1468	4.0	4	4.2134
2.1144	5.0	5	4.2052
2.1713	6.0	6	4.1977
2.1064	7.0	7	4.1910
2.0914	8.0	8	4.1850
2.0655	9.0	9	4.1798
2.1435	10.0	10	4.1752
2.0765	11.0	11	4.1711
2.136	12.0	12	4.1683
2.0839	13.0	13	4.1657
2.0812	14.0	14	4.1642
2.081	15.0	15	4.1637

Framework versions

PEFT 0.13.2
Transformers 4.44.2
Pytorch 2.5.0+cu124
Datasets 3.0.2
Tokenizers 0.19.1

nour-sam/shawgpt-ft2

shawgpt-ft2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

nour-sam/
shawgpt-ft2