RichardErkhov's picture
uploaded readme
137e743 verified

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mpt_150_STEPS_1e6_SFT_SFT - bnb 8bits

Original model description:

license: apache-2.0 base_model: mosaicml/mpt-7b-instruct tags: - trl - sft - generated_from_trainer model-index: - name: mpt_150_STEPS_1e6_SFT_SFT results: []

mpt_150_STEPS_1e6_SFT_SFT

This model is a fine-tuned version of mosaicml/mpt-7b-instruct on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4549

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: 1e-06
  • train_batch_size: 2
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • training_steps: 150

Training results

Training Loss Epoch Step Validation Loss
1.568 0.05 50 1.4778
0.4601 0.1 100 0.4773
0.4772 0.15 150 0.4549

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.0.0+cu117
  • Datasets 2.18.0
  • Tokenizers 0.15.2