Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
gpt2_small_expandedbabyLM_100M_wh_v2_25percent_42 – AI Model by devika-tiwari | AlphaNeural AI
You can deploy this model and start earning money today!
devika-tiwari
/
gpt2_small_expandedbabyLM_100M_wh_v2_25percent_42
like
0
pytorch
gpt2
generated_from_trainer
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
gpt2_small_expandedbabyLM_100M_wh_v2_25percent_42
This model is a fine-tuned version of
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 3.5673
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: 0.0001
train_batch_size: 256
eval_batch_size: 256
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 4000
num_epochs: 20
Training results
Training Loss
Epoch
Step
Validation Loss
3.7628
1.0
4684
4.1673
3.434
2.0
9368
3.7685
3.3003
3.0
14052
3.7431
3.2155
4.0
18736
3.5940
3.1625
5.0
23420
3.5673
3.1196
6.0
28104
3.5921
3.0728
7.0
32788
3.6337
3.0454
8.0
37472
3.6795
Framework versions
Transformers 4.30.2
Pytorch 2.11.0+cu130
Datasets 4.1.1
Tokenizers 0.13.3
