trainer6

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: 2.1849
• Precision: 0.7169
• Recall: 0.6966
• F1: 0.7001
• Accuracy: 0.6966

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: 5e-05
• train_batch_size: 100
• eval_batch_size: 100
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 60

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.3484	3.4483	100	1.5305	0.6491	0.5838	0.5902	0.5838
0.0689	6.8966	200	1.6797	0.6814	0.6543	0.6555	0.6543
0.0422	10.3448	300	1.9755	0.7036	0.6332	0.6426	0.6332
0.0253	13.7931	400	2.0218	0.6909	0.6455	0.6497	0.6455
0.0204	17.2414	500	2.1947	0.6785	0.6437	0.6498	0.6437
0.0113	20.6897	600	2.1949	0.6635	0.6367	0.6378	0.6367
0.0074	24.1379	700	2.3199	0.7000	0.6561	0.6535	0.6561
0.0055	27.5862	800	2.2287	0.7061	0.6737	0.6794	0.6737
0.0038	31.0345	900	2.0396	0.7120	0.7055	0.7048	0.7055
0.0033	34.4828	1000	2.2570	0.6870	0.6720	0.6743	0.6720
0.0052	37.9310	1100	2.1839	0.6979	0.6808	0.6819	0.6808
0.0024	41.3793	1200	2.1763	0.7029	0.6878	0.6906	0.6878
0.0024	44.8276	1300	2.2240	0.7111	0.6931	0.6945	0.6931
0.0032	48.2759	1400	2.3088	0.7134	0.6843	0.6868	0.6843
0.0021	51.7241	1500	2.3203	0.6999	0.6737	0.6763	0.6737
0.0022	55.1724	1600	2.1679	0.7217	0.7002	0.7039	0.7002
0.0017	58.6207	1700	2.1849	0.7169	0.6966	0.7001	0.6966

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1