You can deploy this model and start earning money today!

Jonasbukhave/
shawgpt-ft-lr0.0002-wd0.05

Name: shawgpt-ft-lr0.0002-wd0.05
Availability: InStock

peft

tensorboard

safetensors

generated_from_trainer

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

adapter

apache-2.0

Views

No views yet

shawgpt-ft-lr0.0002-wd0.05

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: 3.2789

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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
25.5434	0.5714	1	4.2401
25.7032	1.5714	2	4.1611
24.6801	2.5714	3	3.9766
23.5885	3.5714	4	3.8072
22.457	4.5714	5	3.6633
21.6522	5.5714	6	3.5395
20.926	6.5714	7	3.4376
20.4754	7.5714	8	3.3595
20.0631	8.5714	9	3.3062
12.9153	9.5714	10	3.2789

Framework versions

PEFT 0.14.0
Transformers 4.47.1
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

Jonasbukhave/shawgpt-ft-lr0.0002-wd0.05

shawgpt-ft-lr0.0002-wd0.05

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Jonasbukhave/
shawgpt-ft-lr0.0002-wd0.05