56919bdbdfdd954d770d12196a0d3799

This model is a fine-tuned version of facebook/opt-1.3b on the nyu-mll/glue [qnli] dataset. It achieves the following results on the evaluation set:

• Loss: 0.6662
• Data Size: 0.25
• Epoch Runtime: 129.5714
• Accuracy: 0.5871
• F1 Macro: 0.5775
• Rouge1: 0.5869
• Rouge2: 0.0
• Rougel: 0.5873
• Rougelsum: 0.5868

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	1.1223	0	8.3389	0.4838	0.3479	0.4840	0.0	0.4840	0.4840
No log	1	3273	0.4985	0.0078	12.3384	0.7612	0.7604	0.7612	0.0	0.7616	0.7612
0.0125	2	6546	0.4545	0.0156	17.5379	0.7943	0.7933	0.7945	0.0	0.7943	0.7939
0.5897	3	9819	0.7189	0.0312	26.9412	0.5107	0.4329	0.5103	0.0	0.5103	0.5099
0.7105	4	13092	0.7228	0.0625	42.4374	0.5086	0.3434	0.5085	0.0	0.5085	0.5085
0.6823	5	16365	0.6711	0.125	71.1761	0.5969	0.5965	0.5971	0.0	0.5966	0.5967
0.6927	6	19638	0.6662	0.25	129.5714	0.5871	0.5775	0.5869	0.0	0.5873	0.5868

Framework versions

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