train_3

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

• Loss: 0.1641

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
0.2789	1.0	6351	0.1682
0.2849	2.0	12702	0.1695
0.2948	3.0	19053	0.1728
0.2806	4.0	25404	0.1641
0.2941	5.0	31755	0.1645
0.2926	6.0	38106	0.1533
0.2997	7.0	44457	0.1724
0.2867	8.0	50808	0.1663
0.2739	9.0	57159	0.1562
0.2884	10.0	63510	0.1708
0.306	11.0	69861	0.1569
0.2888	12.0	76212	0.1854
0.2933	13.0	82563	0.1756
0.2953	14.0	88914	0.1599
0.2987	15.0	95265	0.1701
0.3047	16.0	101616	0.2214
0.3126	17.0	107967	0.1564
0.3066	18.0	114318	0.2439
0.2861	19.0	120669	0.1590
0.3045	20.0	127020	0.3101
0.3045	21.0	133371	0.1641

Framework versions

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