t5-base-finetuned-resumes_t2json_large

This model is a fine-tuned version of t5-base on the resumes_t2json_large dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Rouge1: 4.3177
• Rouge2: 1.1704
• Rougel: 3.5786
• Rougelsum: 3.7496
• Gen Len: 18.4438

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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.0	1.0	10280	nan	4.3177	1.1704	3.5786	3.7496	18.4438
0.0	2.0	20560	nan	4.3177	1.1704	3.5786	3.7496	18.4438
0.0	3.0	30840	nan	4.3177	1.1704	3.5786	3.7496	18.4438
0.0	4.0	41120	nan	4.3177	1.1704	3.5786	3.7496	18.4438
0.0	5.0	51400	nan	4.3177	1.1704	3.5786	3.7496	18.4438
0.0	6.0	61680	nan	4.3177	1.1704	3.5786	3.7496	18.4438
0.0	7.0	71960	nan	4.3177	1.1704	3.5786	3.7496	18.4438
0.0	8.0	82240	nan	4.3177	1.1704	3.5786	3.7496	18.4438
0.0	9.0	92520	nan	4.3177	1.1704	3.5786	3.7496	18.4438
0.0	10.0	102800	nan	4.3177	1.1704	3.5786	3.7496	18.4438

Framework versions

• Transformers 4.20.1
• Pytorch 2.0.0+cu117
• Datasets 2.9.0
• Tokenizers 0.12.1