diogopaes10's picture
update model card README.md
3d398e2
|
raw
history blame
6.52 kB
metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
  - precision
  - recall
model-index:
  - name: 008-microsoft-deberta-v3-base-finetuned-yahoo-800_200
    results: []

008-microsoft-deberta-v3-base-finetuned-yahoo-800_200

This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1139
  • F1: 0.6463
  • Accuracy: 0.65
  • Precision: 0.6514
  • Recall: 0.65
  • System Ram Used: 4.2190
  • System Ram Total: 83.4807
  • Gpu Ram Allocated: 2.0914
  • Gpu Ram Cached: 24.6602
  • Gpu Ram Total: 39.5640
  • Gpu Utilization: 33
  • Disk Space Used: 31.6928
  • Disk Space Total: 78.1898

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: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss F1 Accuracy Precision Recall System Ram Used System Ram Total Gpu Ram Allocated Gpu Ram Cached Gpu Ram Total Gpu Utilization Disk Space Used Disk Space Total
2.2992 0.52 13 2.3031 0.0182 0.1 0.01 0.1 3.9340 83.4807 2.0915 24.6484 39.5640 50 24.7853 78.1898
2.3096 1.04 26 2.2984 0.0182 0.1 0.01 0.1 4.1195 83.4807 2.0915 24.6602 39.5640 43 29.6206 78.1898
2.2906 1.56 39 2.2852 0.0648 0.145 0.0525 0.145 4.2050 83.4807 2.0915 24.6602 39.5640 51 29.6206 78.1898
2.2723 2.08 52 2.2198 0.1283 0.225 0.1625 0.225 4.2165 83.4807 2.0915 24.6602 39.5640 43 31.6924 78.1898
2.1387 2.6 65 2.0293 0.2580 0.335 0.2655 0.335 4.2218 83.4807 2.0916 24.6602 39.5640 56 31.6925 78.1898
1.9534 3.12 78 1.8757 0.3730 0.4 0.4419 0.4 4.2092 83.4807 2.0915 24.6602 39.5640 41 31.6925 78.1898
1.7689 3.64 91 1.7209 0.4443 0.48 0.5198 0.48 4.2303 83.4807 2.0915 24.6602 39.5640 46 31.6925 78.1898
1.6052 4.16 104 1.6318 0.5044 0.525 0.5139 0.525 4.2297 83.4807 2.0915 24.6602 39.5640 45 31.6926 78.1898
1.4606 4.68 117 1.4969 0.5539 0.575 0.5788 0.575 4.2315 83.4807 2.0915 24.6602 39.5640 47 31.6926 78.1898
1.2963 5.2 130 1.3920 0.6037 0.61 0.6063 0.61 4.2420 83.4807 2.0916 24.6602 39.5640 43 31.6926 78.1898
1.1948 5.72 143 1.3030 0.6251 0.63 0.6292 0.63 4.2687 83.4807 2.0915 24.6602 39.5640 48 31.6926 78.1898
1.0248 6.24 156 1.2568 0.6184 0.625 0.6354 0.625 4.2596 83.4807 2.0915 24.6602 39.5640 50 31.6927 78.1898
0.9509 6.76 169 1.1911 0.6448 0.65 0.6552 0.65 4.2625 83.4807 2.0915 24.6602 39.5640 44 31.6927 78.1898
0.9081 7.28 182 1.1784 0.6441 0.655 0.6450 0.655 4.1955 83.4807 2.0915 24.6602 39.5640 50 31.6927 78.1898
0.7629 7.8 195 1.1354 0.6598 0.655 0.6737 0.655 4.1868 83.4807 2.0915 24.6602 39.5640 44 31.6927 78.1898
0.7348 8.32 208 1.1369 0.6430 0.65 0.6483 0.65 4.2168 83.4807 2.0915 24.6602 39.5640 43 31.6927 78.1898
0.7443 8.84 221 1.1274 0.6531 0.66 0.6576 0.66 4.2273 83.4807 2.0915 24.6602 39.5640 51 31.6927 78.1898
0.5945 9.36 234 1.1228 0.6640 0.67 0.6694 0.67 4.1791 83.4807 2.0915 24.6602 39.5640 44 31.6928 78.1898
0.6885 9.88 247 1.1145 0.6463 0.65 0.6514 0.65 4.1849 83.4807 2.0915 24.6602 39.5640 48 31.6928 78.1898

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3