tanshi-models-224-ep10

This model is a fine-tuned version of YxBxRyXJx/tanshi-models-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8686

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.1351	20	1.0816
No log	0.2703	40	1.1103
1.2252	0.4054	60	1.0766
1.2252	0.5405	80	1.1650
1.2016	0.6757	100	1.0430
1.2016	0.8108	120	1.0198
1.2016	0.9459	140	1.0058
1.1913	1.0811	160	1.0173
1.1913	1.2162	180	1.0246
1.1996	1.3514	200	1.0407
1.1996	1.4865	220	1.0185
1.1996	1.6216	240	0.9941
1.1931	1.7568	260	0.9983
1.1931	1.8919	280	1.0098
1.1227	2.0270	300	1.0127
1.1227	2.1622	320	0.9726
1.1227	2.2973	340	0.9944
1.1479	2.4324	360	1.0146
1.1479	2.5676	380	0.9614
1.0578	2.7027	400	0.9794
1.0578	2.8378	420	0.9699
1.0578	2.9730	440	0.9782
1.1325	3.1081	460	0.9551
1.1325	3.2432	480	0.9714
1.0768	3.3784	500	0.9524
1.0768	3.5135	520	0.9540
1.0768	3.6486	540	0.9115
1.067	3.7838	560	0.8934
1.067	3.9189	580	0.9231
1.0786	4.0541	600	0.9242
1.0786	4.1892	620	0.8910
1.0786	4.3243	640	0.8810
1.0959	4.4595	660	0.8875
1.0959	4.5946	680	0.8753
1.0206	4.7297	700	0.8724
1.0206	4.8649	720	0.8699
1.0206	5.0	740	0.8686

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1+cu124
• Datasets 3.0.2
• Tokenizers 0.20.1