Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mistral7b_instruct_generation – AI Model by vpkrishna | AlphaNeural AI
You can deploy this model and start earning money today!
vpkrishna
/
mistral7b_instruct_generation
like
0
peft
tensorboard
safetensors
trl
sft
generated_from_trainer
generator
mistralai/Mistral-7B-v0.1
adapter
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
mistral7b_instruct_generation
This model is a fine-tuned version of
mistralai/Mistral-7B-v0.1
on the generator dataset. It achieves the following results on the evaluation set:
Loss: 1.9267
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
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
lr_scheduler_warmup_steps: 0.03
training_steps: 150
Training results
Training Loss
Epoch
Step
Validation Loss
1.9861
0.01
40
1.9412
2.0157
0.02
80
1.9411
2.0032
0.03
120
1.9267
Framework versions
PEFT 0.8.1
Transformers 4.37.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.1
