mt5v2

This model is a fine-tuned version of thenameisdeba/results_mt5 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.6690
• Score: 0.1
• Counts: [259, 47, 3, 1]
• Totals: [14640, 14057, 13519, 13151]
• Precisions: [1.7691256830601092, 0.33435299139218894, 0.022190990457874104, 0.007603984487871644]
• Bp: 1.0
• Sys Len: 14640
• Ref Len: 1945
• Gen Len: 117.3533

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: 0.0002
• train_batch_size: 8
• 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Score	Counts	Totals	Precisions	Bp	Sys Len	Ref Len	Gen Len
3.6412	0.7622	500	2.8887	0.1453	[209, 42, 3, 1]	[9552, 8969, 8447, 8153]	[2.1880234505862646, 0.4682796298361021, 0.03551556765715639, 0.012265423770391267]	1.0	9552	1945	89.7581
3.109	1.5244	1000	2.7566	0.0687	[258, 47, 2, 0]	[16092, 15509, 14949, 14563]	[1.6032811334824757, 0.30304984202721, 0.013378821325841193, 0.0034333585112957493]	1.0	16092	1945	122.3619
2.764	2.2866	1500	2.6690	0.1	[259, 47, 3, 1]	[14640, 14057, 13519, 13151]	[1.7691256830601092, 0.33435299139218894, 0.022190990457874104, 0.007603984487871644]	1.0	14640	1945	117.3533

Framework versions

• Transformers 4.51.3
• Pytorch 2.7.0+cu126
• Datasets 4.0.0
• Tokenizers 0.21.1