train_3

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1924

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: 0.0006047816549758072
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.964129172421366,0.8471340191802936) and epsilon=1.51279024695782e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2593
• num_epochs: 500

Training results

Training Loss	Epoch	Step	Validation Loss
0.3392	1.0	6351	0.1969
0.3365	2.0	12702	0.1806
0.3463	3.0	19053	0.1858
0.3322	4.0	25404	0.1867
0.3532	5.0	31755	0.1803
0.3417	6.0	38106	0.1735
0.3938	7.0	44457	0.2478
0.3552	8.0	50808	0.1916
0.3221	9.0	57159	0.1896
0.3911	10.0	63510	0.2038
0.352	11.0	69861	0.1871
0.3376	12.0	76212	0.1830
0.4283	13.0	82563	3.1414
0.3437	14.0	88914	0.1844
0.3505	15.0	95265	0.1943
0.3591	16.0	101616	0.1819
0.3472	17.0	107967	0.1804
0.3521	18.0	114318	0.1915
0.3428	19.0	120669	0.1933
0.463	20.0	127020	0.6750
0.3515	21.0	133371	0.1924

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0.dev20241217
• Datasets 2.20.0
• Tokenizers 0.21.0