Hugging Face's logo

affecto
/
Vigogne70b-ass-fan

Safetensors
Generated from Trainer
Model card Files Community
Vigogne70b-ass-fan / README.md
affecto's picture
affecto
End of training
f97a336
preview code
|
raw
history blame contribute delete
1.97 kB
metadata
license: llama2
base_model: TheBloke/vigogne-2-70B-chat-GPTQ
tags:
  - generated_from_trainer
model-index:
  - name: Vigogne70b-ass-fan
    results: []

Vigogne70b-ass-fan

This model is a fine-tuned version of TheBloke/vigogne-2-70B-chat-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8725

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: 0.0004
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
No log 0.09 40 1.0751
No log 0.17 80 0.9983
No log 0.26 120 0.9894
No log 0.35 160 0.9468
No log 0.44 200 0.9348
No log 0.52 240 0.9185
No log 0.61 280 0.9027
No log 0.7 320 0.8952
No log 0.78 360 0.8924
No log 0.87 400 0.8806
No log 0.96 440 0.8769
No log 1.05 480 0.8725

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0