Hugging Face's logo

Gunslinger3D
/
fine-tuning-Phi2-with-webglm-qa-with-lora

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
fine-tuning-Phi2-with-webglm-qa-with-lora / README.md
Gunslinger3D's picture
Gunslinger3D
fine-tuning-Phi2-with-webglm-qa-with-lora
c8c85cb verified
preview code
|
raw
history blame
2.96 kB
metadata
license: mit
library_name: peft
tags:
  - generated_from_trainer
base_model: microsoft/phi-2
model-index:
  - name: fine-tuning-Phi2-with-webglm-qa-with-lora
    results: []

fine-tuning-Phi2-with-webglm-qa-with-lora

This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1475

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: 5e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 5
  • total_train_batch_size: 10
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 30
  • training_steps: 300
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
No log 0.2 10 7.7121
7.4808 0.4 20 4.3398
7.4808 0.6 30 0.6362
1.5296 0.8 40 0.5285
1.5296 1.0 50 0.4668
0.3883 1.2 60 0.4194
0.3883 1.39 70 0.3737
0.3482 1.59 80 0.3338
0.3482 1.79 90 0.3036
0.2296 1.99 100 0.2802
0.2296 2.19 110 0.2595
0.212 2.39 120 0.2452
0.212 2.59 130 0.2307
0.1943 2.79 140 0.2145
0.1943 2.99 150 0.2031
0.1635 3.19 160 0.1957
0.1635 3.39 170 0.1857
0.1543 3.59 180 0.1788
0.1543 3.78 190 0.1732
0.1492 3.98 200 0.1687
0.1492 4.18 210 0.1650
0.1327 4.38 220 0.1632
0.1327 4.58 230 0.1597
0.1359 4.78 240 0.1552
0.1359 4.98 250 0.1522
0.1367 5.18 260 0.1506
0.1367 5.38 270 0.1495
0.1204 5.58 280 0.1484
0.1204 5.78 290 0.1477
0.125 5.98 300 0.1475

Framework versions

  • PEFT 0.7.1
  • Transformers 4.36.2
  • Pytorch 2.0.0
  • Datasets 2.15.0
  • Tokenizers 0.15.0