You can deploy this model and start earning money today!

yspkm/
Mistral-7B-Instruct-v0.3-lora-math

Name: Mistral-7B-Instruct-v0.3-lora-math
Availability: InStock

safetensors

generated_from_trainer

mistralai/Mistral-7B-Instruct-v0.3

finetune

apache-2.0

Views

No views yet

Visualize in Weights & Biases

Mistral-7B-Instruct-v0.3-lora-math

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3461

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: 0.0001
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.3882	0.5133	200	0.3837
0.3388	1.0266	400	0.3599
0.3189	1.5399	600	0.3498
0.2659	2.0533	800	0.3459
0.269	2.5666	1000	0.3461

Framework versions

Transformers 4.42.3
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1

yspkm/Mistral-7B-Instruct-v0.3-lora-math

Mistral-7B-Instruct-v0.3-lora-math

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

yspkm/
Mistral-7B-Instruct-v0.3-lora-math