Hugging Face's logo

JiAYu1997
/
HRJD_FinetuneV3_2

trl
sft
Generated from Trainer
Model card Files Community
HRJD_FinetuneV3_2 / README.md
JiAYu1997's picture
JiAYu1997
Training in progress, step 100
7fd6b00 verified
preview code
|
raw
history blame
1.2 kB
metadata
license: llama2
base_model: INX-TEXT/Bailong-instruct-7B
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: HRJD_FinetuneV3_2
    results: []

HRJD_FinetuneV3_2

This model is a fine-tuned version of INX-TEXT/Bailong-instruct-7B on the None dataset.

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: 0.0002
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_ratio: 0.03
  • training_steps: 3000

Training results

Framework versions

  • Transformers 4.33.0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.13.3