Hugging Face's logo

c10
/
eeve-2.8B_B

trl
sft
Generated from Trainer
Model card Files Community
eeve-2.8B_B / README.md
c10's picture
c10
Model save
1a8a9b9 verified
preview code
|
raw
history blame contribute delete
1.48 kB
metadata
license: apache-2.0
base_model: yanolja/EEVE-Korean-Instruct-2.8B-v1.0
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: eeve-2.8B_B
    results: []

eeve-2.8B_B

This model is a fine-tuned version of yanolja/EEVE-Korean-Instruct-2.8B-v1.0 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3918

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-05
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 3
  • total_train_batch_size: 48
  • total_eval_batch_size: 24
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.2894 1.0 291 0.3918

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1