Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
step_val_10_gemma-2-2b_hs2_iter1_sftsd2 – AI Model by jkazdan | AlphaNeural AI
You can deploy this model and start earning money today!
jkazdan
/
step_val_10_gemma-2-2b_hs2_iter1_sftsd2
like
0
safetensors
gemma2
trl
sft
generated_from_trainer
google/gemma-2-2b
finetune
gemma
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
step_val_10_gemma-2-2b_hs2_iter1_sftsd2
This model is a fine-tuned version of
google/gemma-2-2b
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 1.1458
Num Input Tokens Seen: 591104
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: 8e-06
train_batch_size: 8
eval_batch_size: 16
seed: 2
gradient_accumulation_steps: 16
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_ratio: 0.05
training_steps: 10
Training results
Training Loss
Epoch
Step
Validation Loss
Input Tokens Seen
No log
0
0
1.3956
0
1.1688
0.0511
5
1.1953
295904
1.1574
0.1021
10
1.1458
591104
Framework versions
Transformers 4.44.0
Pytorch 2.4.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1
