version_1305

This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:

• Bp: 0.0692
• Counts: [1132, 692, 368, 143]
• Loss: 0.1515
• Precisions: [70.35425730267247, 57.85953177257525, 46.93877551020408, 37.53280839895013]
• Ref Len: 5907
• Score: 3.5793
• Sys Len: 1609
• Totals: [1609, 1196, 784, 381]

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: 2e-05
• train_batch_size: 12
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Bp	Counts	Validation Loss	Precisions	Ref Len	Score	Sys Len	Totals
0.1836	1.0	464	0.0693	[1132, 692, 368, 143]	0.1625	[70.31055900621118, 57.811194653299914, 46.87898089171974, 37.43455497382199]	5907	3.5827	1610	[1610, 1197, 785, 382]
0.1712	2.0	928	0.0693	[1136, 696, 371, 145]	0.1545	[70.55900621118012, 58.145363408521305, 47.261146496815286, 37.95811518324607]	5907	3.6109	1610	[1610, 1197, 785, 382]
0.1626	3.0	1392	0.0692	[1132, 692, 368, 143]	0.1515	[70.35425730267247, 57.85953177257525, 46.93877551020408, 37.53280839895013]	5907	3.5793	1609	[1609, 1196, 784, 381]

Framework versions

• Transformers 4.44.1
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.19.1