Built with Axolotl

9acc971e-661b-4ca5-9cf6-e34f7feb5f4a

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

  • Loss: 1.9610

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: 0.000214
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 140
  • 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 0.0001 1 4.1637
5.6835 0.0042 50 2.3631
5.3968 0.0084 100 2.2632
5.2146 0.0127 150 2.1901
5.2724 0.0169 200 2.1400
4.9923 0.0211 250 2.1044
4.4694 0.0253 300 2.0497
4.92 0.0295 350 2.0047
4.7397 0.0338 400 1.9765
4.8422 0.0380 450 1.9575
4.5776 0.0422 500 1.9610

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
1
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 lesso14/9acc971e-661b-4ca5-9cf6-e34f7feb5f4a

Adapter
(206)
this model