Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
msb-roshan_-_molgpt-4bits – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
msb-roshan_-_molgpt-4bits
like
0
safetensors
gpt2
4-bit
bitsandbytes
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Quantization made by Richard Erkhov.
Github
Discord
Request more models
molgpt - bnb 4bits
Model creator:
https://huggingface.co/msb-roshan/
Original model:
https://huggingface.co/msb-roshan/molgpt/
Original model description:
license: mit tags:
generated_from_trainer model-index:
name: molgpt results: []
molgpt
This model is a fine-tuned version of
gpt2
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 3.2035
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: 0.0005
train_batch_size: 128
eval_batch_size: 128
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 1024
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10000
num_epochs: 1
Training results
Training Loss
Epoch
Step
Validation Loss
3.3029
1.0
100906
3.2035
Framework versions
Transformers 4.30.2
Pytorch 2.0.0+cu117
Datasets 2.14.4
Tokenizers 0.13.3
