Hugging Face's logo

binh230
/
seallm-v3-4bit-qlora

PEFT
Safetensors
Generated from Trainer
Model card Files Community
seallm-v3-4bit-qlora / README.md
binh230's picture
binh230
End of training
cb78ebe verified
preview code
|
raw
history blame contribute delete
1.63 kB
metadata
base_model: SeaLLMs/SeaLLMs-v3-7B-Chat
library_name: peft
license: other
tags:
  - generated_from_trainer
model-index:
  - name: seallm-v3-4bit-qlora
    results: []

seallm-v3-4bit-qlora

This model is a fine-tuned version of SeaLLMs/SeaLLMs-v3-7B-Chat on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3075

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: 0.0003
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.4404 0.2036 50 1.4168
1.3317 0.4072 100 1.3570
1.3188 0.6108 150 1.3248
1.3048 0.8144 200 1.3075

Framework versions

  • PEFT 0.13.0
  • Transformers 4.45.1
  • Pytorch 2.4.1
  • Datasets 2.19.1
  • Tokenizers 0.20.0