Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mistral_instruct_generation_st_geometry – AI Model by vishaljangra29 | AlphaNeural AI
You can deploy this model and start earning money today!
vishaljangra29
/
mistral_instruct_generation_st_geometry
like
0
peft
tensorboard
safetensors
trl
sft
generated_from_trainer
generator
sid321axn/Mistral-7B-text-to-sql-finetuned
adapter
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
mistral_instruct_generation_st_geometry
This model is a fine-tuned version of
sid321axn/Mistral-7B-text-to-sql-finetuned
on the generator dataset. It achieves the following results on the evaluation set:
Loss: 0.2155
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: 4
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
lr_scheduler_warmup_steps: 0.03
training_steps: 100
Training results
Training Loss
Epoch
Step
Validation Loss
0.2741
4.0
20
0.1555
0.0834
8.0
40
0.1331
0.0236
12.0
60
0.1771
0.0098
16.0
80
0.2101
0.0063
20.0
100
0.2155
Framework versions
PEFT 0.11.1
Transformers 4.41.0
Pytorch 2.2.2+cu121
Datasets 2.15.0
Tokenizers 0.19.1
