67aff425315c9876637525fa3daf3485

This model is a fine-tuned version of google-bert/bert-base-chinese 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: 14.1302
• 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	0.6869	0	1.0360	0.5547	0.5141	0.5547	0.0	0.5547	0.5557
No log	1	267	0.6220	0.0078	1.2960	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	2	534	0.6260	0.0156	1.3292	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	3	801	0.6320	0.0312	1.7416	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	4	1068	0.6204	0.0625	2.2011	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.0372	5	1335	0.6594	0.125	3.1531	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.6123	6	1602	0.6225	0.25	4.7343	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.6209	7	1869	0.6300	0.5	7.7867	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.6114	8.0	2136	0.6210	1.0	14.1302	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