0ff1b5cb3f896d7541d86af17aab3c0a

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

• Loss: 0.6918
• Data Size: 1.0
• Epoch Runtime: 13.4754
• Accuracy: 0.8242
• F1 Macro: 0.7798
• Rouge1: 0.8242
• Rouge2: 0.0
• Rougel: 0.8242
• Rougelsum: 0.8242

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	0.6761	0	1.0298	0.6621	0.5333	0.6621	0.0	0.6621	0.6621
No log	1	267	0.6199	0.0078	1.9645	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	2	534	0.6707	0.0156	1.3830	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	3	801	0.6193	0.0312	1.7838	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	4	1068	0.6004	0.0625	2.2040	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.0345	5	1335	0.6490	0.125	3.0421	0.7285	0.5472	0.7285	0.0	0.7285	0.7285
0.4819	6	1602	0.4736	0.25	4.6587	0.7900	0.7247	0.7910	0.0	0.7900	0.7900
0.4008	7	1869	0.4962	0.5	7.6662	0.7910	0.7045	0.7910	0.0	0.7920	0.7920
0.333	8.0	2136	0.4247	1.0	13.8941	0.8135	0.7578	0.8135	0.0	0.8135	0.8145
0.1829	9.0	2403	0.7283	1.0	14.4975	0.8047	0.7325	0.8047	0.0	0.8047	0.8047
0.1825	10.0	2670	0.6732	1.0	13.2736	0.8154	0.7685	0.8154	0.0	0.8154	0.8164
0.1045	11.0	2937	0.7550	1.0	13.1812	0.8027	0.7472	0.8027	0.0	0.8027	0.8027
0.1343	12.0	3204	0.6918	1.0	13.4754	0.8242	0.7798	0.8242	0.0	0.8242	0.8242

Framework versions

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