phobert-human-tl-seed-1337

This model is a fine-tuned version of vinai/phobert-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4534
• Accuracy: 0.8394
• Precision: 0.6550
• Recall: 0.4705
• F1: 0.4951

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: 0.0001
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	346	0.5156	0.8237	0.5296	0.3491	0.3313
0.5885	2.0	692	0.4706	0.8316	0.6120	0.4056	0.4188
0.4669	3.0	1038	0.4642	0.8323	0.6244	0.4044	0.4196
0.4669	4.0	1384	0.4664	0.8365	0.6932	0.4151	0.4351
0.4617	5.0	1730	0.4633	0.8361	0.6690	0.4145	0.4366
0.4579	6.0	2076	0.4603	0.8365	0.6619	0.4273	0.4483
0.4579	7.0	2422	0.4622	0.8365	0.6839	0.4147	0.4373
0.4554	8.0	2768	0.4528	0.8394	0.6474	0.4414	0.4654
0.4544	9.0	3114	0.4597	0.8338	0.6444	0.4071	0.4271
0.4544	10.0	3460	0.4606	0.8338	0.6544	0.4356	0.4510
0.4587	11.0	3806	0.4589	0.8353	0.6548	0.4105	0.4342
0.4488	12.0	4152	0.4534	0.8394	0.6550	0.4705	0.4951
0.4488	13.0	4498	0.4554	0.8361	0.6420	0.4216	0.4483
0.4575	14.0	4844	0.4562	0.8353	0.6472	0.4113	0.4332
0.4491	15.0	5190	0.4593	0.8338	0.6609	0.4020	0.4219
0.4586	16.0	5536	0.4665	0.8327	0.6580	0.3987	0.4161
0.4586	17.0	5882	0.4514	0.8383	0.6232	0.4356	0.4603

Framework versions

• Transformers 4.51.1
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.21.0