chayankb_model_checkpoints

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

• Loss: 0.6451
• Rouge1: 42.0175
• Rouge2: 22.1212
• Rougel: 42.0175
• Rougelsum: 42.0175
• Gen Len: 19.0

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
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	1	0.6473	42.0175	22.1212	42.0175	42.0175	19.0
No log	2.0	2	0.6451	42.0175	22.1212	42.0175	42.0175	19.0
No log	3.0	3	0.6460	42.0175	22.1212	42.0175	42.0175	19.0
No log	4.0	4	0.6457	42.0175	22.1212	42.0175	42.0175	19.0
No log	5.0	5	0.6458	42.0175	22.1212	42.0175	42.0175	19.0

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0