Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
BaoLocTown_-_sft-metamath-mistral-7b-vi-v1-4bits – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
BaoLocTown_-_sft-metamath-mistral-7b-vi-v1-4bits
like
0
safetensors
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Quantization made by Richard Erkhov.
Github
Discord
Request more models
sft-metamath-mistral-7b-vi-v1 - bnb 4bits
Model creator:
https://huggingface.co/BaoLocTown/
Original model:
https://huggingface.co/BaoLocTown/sft-metamath-mistral-7b-vi-v1/
Original model description:
base_model: hllj/meta-math-mistral-vi-math tags:
generated_from_trainer model-index:
name: sft-metamath-mistral-7b-vi-v1 results: []
sft-metamath-mistral-7b-vi-v1
This model is a fine-tuned version of
hllj/meta-math-mistral-vi-math
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.4947
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: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 2
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
0.3128
0.26
500
0.5093
0.2751
1.07
1000
0.4884
0.2585
1.33
1500
0.4943
Framework versions
Transformers 4.35.2
Pytorch 2.1.0
Datasets 2.15.0
Tokenizers 0.15.0
