Built with Axolotl

b9a30e92-29d7-4af0-bde5-747f1757200f

This model is a fine-tuned version of EleutherAI/pythia-70m-deduped on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 7.7040

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: 0.000207
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 70
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 50
  • training_steps: 500

Training results

Training Loss Epoch Step Validation Loss
No log 0.0004 1 7.3686
25.3868 0.0213 50 7.4258
13.8099 0.0425 100 7.3802
23.4798 0.0638 150 33.8753
21.1787 0.0851 200 8.7964
16.7208 0.1063 250 7.7040

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1
Downloads last month
7
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Model tree for lesso07/b9a30e92-29d7-4af0-bde5-747f1757200f

Adapter
(301)
this model