flanT5_Task2

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

• Loss: 2.1812
• Accuracy: 0.7706
• Precision: 0.7861
• Recall: 0.7435
• F1 score: 0.7642

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: 1
• eval_batch_size: 1
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1 score
1.1443	0.4205	2500	1.6635	0.6718	0.7829	0.4753	0.5915
1.0447	0.8410	5000	0.5585	0.7282	0.8149	0.5906	0.6849
0.9057	1.2616	7500	0.9051	0.7318	0.7275	0.7412	0.7343
0.8348	1.6821	10000	0.6307	0.7659	0.8742	0.6212	0.7263
0.7331	2.1026	12500	0.9500	0.7612	0.7489	0.7859	0.7669
0.6167	2.5231	15000	1.1524	0.7788	0.7970	0.7482	0.7718
0.6209	2.9437	17500	1.1690	0.7635	0.7872	0.7224	0.7534
0.4411	3.3642	20000	1.7563	0.7847	0.8438	0.6988	0.7645
0.4196	3.7847	22500	1.7767	0.7412	0.7204	0.7882	0.7528
0.292	4.2052	25000	2.0410	0.7624	0.7648	0.7576	0.7612
0.1791	4.6257	27500	2.1812	0.7706	0.7861	0.7435	0.7642

Framework versions

• Transformers 4.48.3
• Pytorch 2.3.0+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0