Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
climategpt-climate-finetune – AI Model by fayetitchenal | AlphaNeural AI
You can deploy this model and start earning money today!
fayetitchenal
/
climategpt-climate-finetune
like
0
peft
safetensors
generated_from_trainer
eci-io/climategpt-7b
adapter
other
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Visualize in Weights & Biases
climategpt-climate-finetune
This model is a fine-tuned version of
eci-io/climategpt-7b
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.6497
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
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
1.6928
0.4444
50
1.6347
1.439
0.8889
100
1.3206
1.0466
1.3333
150
1.0716
0.9062
1.7778
200
0.8967
0.5053
2.2222
250
0.7718
0.4923
2.6667
300
0.6497
Framework versions
PEFT 0.11.1
Transformers 4.42.4
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1
