HachiML's picture
End of training
b888f8e verified
metadata
tags:
  - generated_from_trainer
model-index:
  - name: myBit-Llama2-jp-127M-test-16
    results: []

myBit-Llama2-jp-127M-test-16

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 4.5029

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: 0.00024
  • train_batch_size: 96
  • eval_batch_size: 96
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: polynomial
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
9.0668 0.07 200 7.8313
6.9502 0.15 400 6.3292
5.8696 0.22 600 5.4250
5.285 0.3 800 5.1157
5.0167 0.37 1000 4.9604
4.9441 0.45 1200 4.9913
4.8204 0.52 1400 4.7712
4.7314 0.6 1600 4.7058
4.6562 0.67 1800 4.6503
4.5941 0.74 2000 4.5901
4.5479 0.82 2200 4.5508
4.5155 0.89 2400 4.5194
4.4939 0.97 2600 4.5029

Framework versions

  • Transformers 4.39.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2