38a717dad53ea2862f4011f9bf786397

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

• Loss: 0.8009
• Data Size: 1.0
• Epoch Runtime: 15.3516
• Accuracy: 0.7295
• F1 Macro: 0.6407
• Rouge1: 0.7305
• Rouge2: 0.0
• Rougel: 0.7305
• Rougelsum: 0.7295

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	0.6782	0	1.0457	0.6719	0.5021	0.6738	0.0	0.6729	0.6738
No log	1	267	0.6424	0.0078	1.9689	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	2	534	0.6506	0.0156	1.5159	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	3	801	0.6309	0.0312	1.9951	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	4	1068	0.6116	0.0625	2.6780	0.6895	0.4199	0.6904	0.0	0.6895	0.6895
0.0361	5	1335	0.7127	0.125	3.6369	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.5855	6	1602	0.6014	0.25	5.5148	0.7051	0.5061	0.7061	0.0	0.7051	0.7041
0.5549	7	1869	0.6122	0.5	9.0247	0.7012	0.4604	0.7012	0.0	0.7012	0.7012
0.5043	8.0	2136	0.5482	1.0	15.8392	0.7344	0.6210	0.7344	0.0	0.7344	0.7344
0.3707	9.0	2403	0.7130	1.0	16.6460	0.7383	0.6208	0.7393	0.0	0.7383	0.7383
0.3149	10.0	2670	0.7481	1.0	15.1435	0.7324	0.6442	0.7319	0.0	0.7324	0.7324
0.1996	11.0	2937	0.8402	1.0	14.9485	0.7227	0.6446	0.7227	0.0	0.7227	0.7236
0.2451	12.0	3204	0.8009	1.0	15.3516	0.7295	0.6407	0.7305	0.0	0.7305	0.7295

Framework versions

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