grammer_correction

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

• Loss: 0.5597
• Rouge1: 72.0915
• Rouge2: 62.3018
• Rougel: 71.394
• Rougelsum: 71.4259
• Gen Len: 17.2788

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: 64
• seed: 42
• gradient_accumulation_steps: 6
• total_train_batch_size: 96
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.7668	0.1	500	0.6242	71.3363	60.9781	70.5891	70.6201	17.3304
0.6709	0.19	1000	0.5964	71.6241	61.4598	70.8874	70.9203	17.3076
0.6519	0.29	1500	0.5821	71.7998	61.7754	71.0777	71.1094	17.2958
0.6391	0.39	2000	0.5748	71.9032	61.9596	71.1882	71.2215	17.2895
0.6311	0.48	2500	0.5684	71.9839	62.09	71.2714	71.3041	17.2805
0.6233	0.58	3000	0.5667	72.0308	62.1784	71.3246	71.3588	17.2816
0.6236	0.68	3500	0.5626	72.0792	62.2549	71.3753	71.4061	17.2703
0.6223	0.78	4000	0.5607	72.0838	62.2734	71.38	71.4126	17.2766
0.6157	0.87	4500	0.5603	72.0975	62.2993	71.3977	71.4284	17.2772
0.6167	0.97	5000	0.5597	72.0915	62.3018	71.394	71.4259	17.2788

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.0
• Tokenizers 0.13.3