584_32_1

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

• Loss: 1.3309
• Accuracy: 0.7104

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	121	1.4221	0.25
No log	2.0	242	1.3270	0.4208
No log	3.0	363	0.9673	0.6125
No log	4.0	484	0.8277	0.6687
1.2322	5.0	605	0.7791	0.6979
1.2322	6.0	726	0.8398	0.6896
1.2322	7.0	847	0.7810	0.7
1.2322	8.0	968	0.8186	0.7125
0.5026	9.0	1089	0.9361	0.7104
0.5026	10.0	1210	0.9895	0.7104
0.5026	11.0	1331	1.0266	0.6958
0.5026	12.0	1452	1.1067	0.7146
0.1724	13.0	1573	1.0984	0.7104
0.1724	14.0	1694	1.1876	0.7063
0.1724	15.0	1815	1.2408	0.7021
0.1724	16.0	1936	1.2624	0.6979
0.074	17.0	2057	1.2954	0.7104
0.074	18.0	2178	1.2911	0.7104
0.074	19.0	2299	1.3218	0.7104
0.074	20.0	2420	1.3309	0.7104

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1