Hugging Face's logo

MinderaLabs
/
idefics-9b-dresses-gpt4

Generated from Trainer
Model card Files Community
idefics-9b-dresses-gpt4 / README.md
diogovelho's picture
diogovelho
Model save
d7d4755
preview code
|
raw
history blame contribute delete
3.92 kB
metadata
license: other
base_model: HuggingFaceM4/idefics-9b
tags:
  - generated_from_trainer
model-index:
  - name: idefics-9b-dresses-gpt4
    results: []

idefics-9b-dresses-gpt4

This model is a fine-tuned version of HuggingFaceM4/idefics-9b on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1806

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: 1
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.0769 0.03 20 0.4830
0.4488 0.06 40 0.3397
0.3575 0.09 60 0.3021
0.3208 0.12 80 0.2790
0.2909 0.14 100 0.2703
0.2829 0.17 120 0.2560
0.2949 0.2 140 0.2529
0.2667 0.23 160 0.2489
0.2647 0.26 180 0.2379
0.2678 0.29 200 0.2353
0.2624 0.32 220 0.2261
0.2446 0.35 240 0.2194
0.2557 0.38 260 0.2203
0.2497 0.41 280 0.2160
0.2454 0.43 300 0.2115
0.2397 0.46 320 0.2077
0.2507 0.49 340 0.2099
0.2379 0.52 360 0.2046
0.239 0.55 380 0.2112
0.2354 0.58 400 0.2060
0.2391 0.61 420 0.2047
0.2293 0.64 440 0.2060
0.2271 0.67 460 0.2034
0.2319 0.7 480 0.1990
0.2188 0.72 500 0.2021
0.2241 0.75 520 0.1987
0.2232 0.78 540 0.1966
0.2264 0.81 560 0.1948
0.2237 0.84 580 0.1944
0.2226 0.87 600 0.1936
0.219 0.9 620 0.1927
0.2314 0.93 640 0.1903
0.2173 0.96 660 0.1924
0.2126 0.99 680 0.1917
0.2032 1.01 700 0.1932
0.2012 1.04 720 0.1883
0.2058 1.07 740 0.1910
0.1918 1.1 760 0.1866
0.1948 1.13 780 0.1859
0.195 1.16 800 0.1847
0.1957 1.19 820 0.1861
0.2009 1.22 840 0.1856
0.1908 1.25 860 0.1838
0.2069 1.28 880 0.1827
0.1985 1.3 900 0.1817
0.1888 1.33 920 0.1821
0.189 1.36 940 0.1813
0.1951 1.39 960 0.1808
0.1889 1.42 980 0.1804
0.1853 1.45 1000 0.1806

Framework versions

  • Transformers 4.35.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.4
  • Tokenizers 0.14.1