asdfgh

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

• Loss: 1.2150
• Bleu: 5.1668
• Gen Len: 15.0

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	1	1.4290	4.4635	15.0
No log	2.0	2	1.3866	4.5654	15.0
No log	3.0	3	1.3549	4.784	15.0
No log	4.0	4	1.3278	4.784	15.0
No log	5.0	5	1.3044	4.784	15.0
No log	6.0	6	1.2858	4.6714	15.0
No log	7.0	7	1.2698	4.6714	15.0
No log	8.0	8	1.2562	4.6714	15.0
No log	9.0	9	1.2458	4.6714	15.0
No log	10.0	10	1.2380	4.9065	15.0
No log	11.0	11	1.2319	5.1668	15.0
No log	12.0	12	1.2266	5.1668	15.0
No log	13.0	13	1.2219	5.1668	15.0
No log	14.0	14	1.2184	5.1668	15.0
No log	15.0	15	1.2161	5.1668	15.0
No log	16.0	16	1.2150	5.1668	15.0

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0