Minbyul's picture
End of training
e2b5caa verified
metadata
license: llama2
base_model: epfl-llm/meditron-7b
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - HuggingFaceH4/deita-10k-v0-sft
model-index:
  - name: meditron-7b-wo-kqa_silver_wogold-sft
    results: []

meditron-7b-wo-kqa_silver_wogold-sft

This model is a fine-tuned version of epfl-llm/meditron-7b on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8975

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: 2e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • total_eval_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
1.1532 0.87 5 1.0827
0.9871 1.91 11 0.9194
0.8631 2.61 15 0.8975

Framework versions

  • Transformers 4.39.0.dev0
  • Pytorch 2.1.2
  • Datasets 2.14.6
  • Tokenizers 0.15.2