Hugging Face's logo

salbatarni
/
bert_baseline_prompt_adherence_task4_fold1

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
bert_baseline_prompt_adherence_task4_fold1 / README.md
salbatarni's picture
salbatarni
Training in progress, step 67
74ed991 verified
preview code
|
raw
history blame
3.68 kB
metadata
license: apache-2.0
base_model: google-bert/bert-base-cased
tags:
  - generated_from_trainer
model-index:
  - name: bert_baseline_prompt_adherence_task4_fold0
    results: []

bert_baseline_prompt_adherence_task4_fold0

This model is a fine-tuned version of google-bert/bert-base-cased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4271
  • Qwk: 0.6387
  • Mse: 0.4239

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Qwk Mse
No log 0.0299 2 1.2960 0.0 1.2930
No log 0.0597 4 0.9177 0.0 0.9154
No log 0.0896 6 0.8271 0.3838 0.8254
No log 0.1194 8 0.7326 0.3465 0.7313
No log 0.1493 10 0.6599 0.3581 0.6586
No log 0.1791 12 0.6243 0.3717 0.6227
No log 0.2090 14 0.6024 0.3919 0.6005
No log 0.2388 16 0.5293 0.3990 0.5275
No log 0.2687 18 0.5958 0.6599 0.5946
No log 0.2985 20 0.5865 0.6470 0.5851
No log 0.3284 22 0.4997 0.6200 0.4975
No log 0.3582 24 0.4852 0.4550 0.4825
No log 0.3881 26 0.5626 0.3360 0.5596
No log 0.4179 28 0.6943 0.2663 0.6911
No log 0.4478 30 0.6648 0.2753 0.6616
No log 0.4776 32 0.5340 0.3669 0.5308
No log 0.5075 34 0.4475 0.5778 0.4444
No log 0.5373 36 0.4749 0.6546 0.4720
No log 0.5672 38 0.5331 0.6635 0.5306
No log 0.5970 40 0.5591 0.6712 0.5569
No log 0.6269 42 0.5329 0.6517 0.5307
No log 0.6567 44 0.4773 0.6521 0.4749
No log 0.6866 46 0.4526 0.5105 0.4499
No log 0.7164 48 0.4667 0.4248 0.4638
No log 0.7463 50 0.4597 0.4232 0.4567
No log 0.7761 52 0.4413 0.4921 0.4382
No log 0.8060 54 0.4265 0.5327 0.4234
No log 0.8358 56 0.4218 0.5857 0.4188
No log 0.8657 58 0.4221 0.6155 0.4191
No log 0.8955 60 0.4244 0.6239 0.4213
No log 0.9254 62 0.4273 0.6354 0.4242
No log 0.9552 64 0.4272 0.6387 0.4241
No log 0.9851 66 0.4271 0.6387 0.4239

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1