Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
wholism – AI Model by awilliamson | AlphaNeural AI
You can deploy this model and start earning money today!
awilliamson
/
wholism
like
0
transformers
pytorch
safetensors
gguf
llama
text-generation
generated_from_trainer
TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T
quantized
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Built with Axolotl
out_fft
This model is a fine-tuned version of
TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.8797
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: 1
eval_batch_size: 1
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 1000
num_epochs: 1
Training results
Training Loss
Epoch
Step
Validation Loss
2.0547
0.0
1
2.0329
1.9388
0.25
3087
1.0713
1.4746
0.5
6174
0.9426
1.1822
0.75
9261
0.8797
Framework versions
Transformers 4.37.0.dev0
Pytorch 2.0.1
Datasets 2.15.0
Tokenizers 0.15.0
