Built with Axolotl

e400ee91-2a2f-4954-903b-c904b0871bb6

This model is a fine-tuned version of bigscience/bloomz-560m on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.7393

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: 0.000201
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • 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 0.0008 1 4.9157
7.3965 0.0408 50 3.8861
6.8288 0.0816 100 3.4400
6.3435 0.1224 150 3.2122
5.9867 0.1632 200 3.0657
6.0373 0.2040 250 2.9484
5.6437 0.2448 300 2.8734
5.6993 0.2856 350 2.8080
5.3656 0.3264 400 2.7667
5.6639 0.3672 450 2.7451
5.5662 0.4080 500 2.7393

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
17
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 lesso01/e400ee91-2a2f-4954-903b-c904b0871bb6

Adapter
(373)
this model