metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: office-character
    results: []

office-character

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.3380
Accuracy: 0.3293

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: 3.3e-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.2896	0.09	200	2.3458	0.328
2.3881	0.18	400	2.3456	0.3207
2.3149	0.27	600	2.3552	0.3283
2.2579	0.36	800	2.3468	0.327
2.3016	0.45	1000	2.3512	0.327
2.3923	0.54	1200	2.3410	0.3313
2.3458	0.63	1400	2.3416	0.328
2.3522	0.72	1600	2.3303	0.3287
2.2485	0.81	1800	2.3291	0.3343
2.3083	0.9	2000	2.3289	0.3327
2.2594	0.99	2200	2.3336	0.3387
2.229	1.08	2400	2.3446	0.3213
2.3017	1.17	2600	2.3362	0.3327
2.2405	1.26	2800	2.3299	0.335
2.3291	1.35	3000	2.3291	0.33
2.2518	1.43	3200	2.3363	0.3297
2.268	1.52	3400	2.3623	0.3187
2.3198	1.61	3600	2.3480	0.3277
2.1873	1.7	3800	2.3355	0.3293
2.2634	1.79	4000	2.3291	0.326
2.1011	1.88	4200	2.3345	0.333
2.1965	1.97	4400	2.3383	0.3293
2.2368	2.06	4600	2.3320	0.329
2.2226	2.15	4800	2.3453	0.3263
2.2354	2.24	5000	2.3372	0.33
2.2829	2.33	5200	2.3547	0.3223
2.1544	2.42	5400	2.3336	0.3287
2.2777	2.51	5600	2.3425	0.3283
2.0763	2.6	5800	2.3339	0.3307
2.2738	2.69	6000	2.3389	0.3293
2.1013	2.78	6200	2.3411	0.327
2.1058	2.87	6400	2.3357	0.332
2.1621	2.96	6600	2.3380	0.3293

Framework versions

Transformers 4.32.1
Pytorch 2.0.1
Datasets 2.14.4
Tokenizers 0.13.3