dcdafa507ca8b0d89b0998f5b8aa05e5

This model is a fine-tuned version of google-bert/bert-large-cased on the nyu-mll/glue [cola] dataset. It achieves the following results on the evaluation set:

• Loss: 0.6210
• Data Size: 1.0
• Epoch Runtime: 27.6387
• Accuracy: 0.6885
• F1 Macro: 0.4078
• Rouge1: 0.6895
• Rouge2: 0.0
• Rougel: 0.6885
• Rougelsum: 0.6885

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
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro	Rouge1	Rouge2	Rougel	Rougelsum
No log	0	0	0.7828	0	1.3884	0.3164	0.2513	0.3164	0.0	0.3164	0.3164
No log	1	267	0.6357	0.0078	2.7615	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	2	534	0.6420	0.0156	2.1719	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	3	801	0.6214	0.0312	3.1605	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	4	1068	0.6191	0.0625	4.1402	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.0374	5	1335	0.6476	0.125	6.3594	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.4832	6	1602	0.5722	0.25	10.0093	0.7598	0.6653	0.7588	0.0	0.7598	0.7588
0.4603	7	1869	0.5365	0.5	15.4301	0.7559	0.6256	0.7559	0.0	0.7559	0.7549
0.4258	8.0	2136	0.4723	1.0	27.9522	0.7910	0.7206	0.7910	0.0	0.7910	0.7910
0.3751	9.0	2403	0.5342	1.0	27.1915	0.7773	0.6967	0.7773	0.0	0.7773	0.7773
0.3968	10.0	2670	0.6089	1.0	27.8171	0.7568	0.6627	0.7568	0.0	0.7568	0.7568
0.3763	11.0	2937	0.6224	1.0	26.7262	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.6381	12.0	3204	0.6210	1.0	27.6387	0.6885	0.4078	0.6895	0.0	0.6885	0.6885

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1