flan-t5-base-ARv1-ARv2

This model is a fine-tuned version of G-R-A-V-I-T-Y/flan-t5-base-ARv1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7981
• Exact Match: 10.0
• Gen Len: 4.0

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Exact Match	Gen Len
No log	1.0	7	0.7981	10.0	4.0
No log	2.0	14	0.7982	10.0	4.0
No log	3.0	21	0.7982	10.0	4.0
No log	4.0	28	0.7982	10.0	4.0
No log	5.0	35	0.7982	10.0	4.0
No log	6.0	42	0.7982	10.0	4.0
No log	7.0	49	0.7982	10.0	4.0
No log	8.0	56	0.7982	10.0	4.0
No log	9.0	63	0.7982	10.0	4.0
No log	10.0	70	0.7982	10.0	4.0
No log	11.0	77	0.7983	10.0	4.0
No log	12.0	84	0.7983	10.0	4.0
No log	13.0	91	0.7983	10.0	4.0
No log	14.0	98	0.7983	10.0	4.0
No log	15.0	105	0.7984	10.0	4.0
No log	16.0	112	0.7984	10.0	4.0
No log	17.0	119	0.7984	10.0	4.0
No log	18.0	126	0.7984	10.0	4.0
No log	19.0	133	0.7984	10.0	4.0
No log	20.0	140	0.7984	10.0	4.0

Framework versions

• Transformers 4.41.0
• Pytorch 2.2.1
• Datasets 2.19.1
• Tokenizers 0.19.1