bert-large-uncased-sst-2-16-13-30

This model is a fine-tuned version of bert-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6328
• Accuracy: 0.625

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: 1.5e-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
• lr_scheduler_warmup_steps: 5
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	0.7326	0.5
No log	2.0	2	0.7299	0.5
No log	3.0	3	0.7258	0.5
No log	4.0	4	0.7173	0.5
No log	5.0	5	0.7098	0.5
No log	6.0	6	0.7019	0.4688
No log	7.0	7	0.6969	0.5
No log	8.0	8	0.6889	0.5312
No log	9.0	9	0.6846	0.5625
0.6763	10.0	10	0.6781	0.5625
0.6763	11.0	11	0.6697	0.5938
0.6763	12.0	12	0.6681	0.625
0.6763	13.0	13	0.6675	0.625
0.6763	14.0	14	0.6668	0.625
0.6763	15.0	15	0.6666	0.625
0.6763	16.0	16	0.6648	0.5938
0.6763	17.0	17	0.6607	0.625
0.6763	18.0	18	0.6589	0.6562
0.6763	19.0	19	0.6564	0.6562
0.4935	20.0	20	0.6533	0.6562
0.4935	21.0	21	0.6502	0.6562
0.4935	22.0	22	0.6472	0.5938
0.4935	23.0	23	0.6445	0.5938
0.4935	24.0	24	0.6418	0.5938
0.4935	25.0	25	0.6391	0.5938
0.4935	26.0	26	0.6370	0.5938
0.4935	27.0	27	0.6353	0.5938
0.4935	28.0	28	0.6341	0.625
0.4935	29.0	29	0.6333	0.625
0.3659	30.0	30	0.6328	0.625

Framework versions

• Transformers 4.32.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.4.0
• Tokenizers 0.13.3