eo_train1-10_eval1-10_lr1e-5

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

• Loss: 0.4512
• Accuracy: 0.75

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: 128
• eval_batch_size: 128
• seed: 7658372
• 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: cosine
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 3000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0	0	3.0162	0.0
1.4977	100.0	100	1.4741	0.5
0.7396	200.0	200	0.7389	0.5
0.6815	300.0	300	0.6810	0.6
0.6378	400.0	400	0.6373	0.55
0.5971	500.0	500	0.5969	0.6
0.5768	600.0	600	0.5763	0.6
0.555	700.0	700	0.5545	0.65
0.5395	800.0	800	0.5393	0.7
0.5279	900.0	900	0.5281	0.65
0.5228	1000.0	1000	0.5224	0.7
0.5161	1100.0	1100	0.5167	0.8
0.5104	1200.0	1200	0.5106	0.8
0.5049	1300.0	1300	0.5047	0.8
0.4987	1400.0	1400	0.4991	0.75
0.493	1500.0	1500	0.4933	0.7
0.4877	1600.0	1600	0.4884	0.75
0.4826	1700.0	1700	0.4824	0.7
0.4766	1800.0	1800	0.4763	0.7
0.4714	1900.0	1900	0.4713	0.7
0.4673	2000.0	2000	0.4674	0.7
0.4635	2100.0	2100	0.4633	0.7
0.4602	2200.0	2200	0.4601	0.7
0.4577	2300.0	2300	0.4577	0.75
0.4556	2400.0	2400	0.4555	0.75
0.4538	2500.0	2500	0.4538	0.75
0.4525	2600.0	2600	0.4525	0.75
0.4518	2700.0	2700	0.4518	0.75
0.4514	2800.0	2800	0.4514	0.75
0.4512	2900.0	2900	0.4512	0.75
0.4512	3000.0	3000	0.4512	0.75

Framework versions

• Transformers 4.46.0
• Pytorch 2.5.1
• Datasets 3.1.0
• Tokenizers 0.20.1