17925b280e9c6be8f5fa7204cfa528bf

This model is a fine-tuned version of facebook/opt-350m on the nyu-mll/glue [qqp] dataset. It achieves the following results on the evaluation set:

• Loss: 0.6869
• Data Size: 1.0
• Epoch Runtime: 1519.2449
• Accuracy: 0.6320
• F1 Macro: 0.3872
• Rouge1: 0.6318
• Rouge2: 0.0
• Rougel: 0.6319
• Rougelsum: 0.6317

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	1.6351	0	53.7531	0.3857	0.3709	0.3858	0.0	0.3856	0.3858
0.8635	1	11370	0.5858	0.0078	65.0684	0.7281	0.6865	0.7281	0.0	0.7281	0.7280
0.502	2	22740	0.4709	0.0156	76.5208	0.7719	0.7412	0.7718	0.0	0.7718	0.7719
0.4518	3	34110	0.4244	0.0312	100.5861	0.8012	0.7826	0.8010	0.0	0.8011	0.8011
0.4052	4	45480	0.4419	0.0625	146.9538	0.8081	0.8018	0.8081	0.0	0.8079	0.8082
0.3992	5	56850	0.3631	0.125	245.7876	0.8356	0.8250	0.8355	0.0	0.8355	0.8355
0.3628	6	68220	0.3802	0.25	422.2440	0.8230	0.8178	0.8231	0.0	0.8230	0.8231
0.3407	7	79590	0.3642	0.5	795.6486	0.8409	0.8279	0.8409	0.0	0.8409	0.8409
0.6551	8.0	90960	0.6581	1.0	1529.3243	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6557	9.0	102330	0.6869	1.0	1519.2449	0.6320	0.3872	0.6318	0.0	0.6319	0.6317

Framework versions

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