393175e67c42b8331fdcab39742da6de

This model is a fine-tuned version of facebook/opt-1.3b on the nyu-mll/glue [sst2] dataset. It achieves the following results on the evaluation set:

• Loss: 0.4612
• Data Size: 1.0
• Epoch Runtime: 315.3915
• Accuracy: 0.8252
• F1 Macro: 0.8239
• Rouge1: 0.8252
• Rouge2: 0.0
• Rougel: 0.8241
• Rougelsum: 0.8241

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	0.7922	0	2.3565	0.4699	0.4697	0.4699	0.0	0.4711	0.4699
No log	1	2104	0.4579	0.0078	5.5325	0.7743	0.7670	0.7731	0.0	0.7743	0.7743
No log	2	4208	0.3654	0.0156	9.2153	0.8507	0.8503	0.8507	0.0	0.8507	0.8495
0.0119	3	6312	0.4426	0.0312	15.9827	0.8137	0.8130	0.8125	0.0	0.8148	0.8137
0.382	4	8416	0.3450	0.0625	27.2920	0.8449	0.8444	0.8461	0.0	0.8449	0.8449
0.3683	5	10520	0.4838	0.125	48.2522	0.7801	0.7731	0.7801	0.0	0.7795	0.7801
0.3238	6	12624	0.3981	0.25	84.9059	0.8356	0.8354	0.8345	0.0	0.8356	0.8356
0.3099	7	14728	0.4545	0.5	165.1068	0.8252	0.8247	0.8252	0.0	0.8252	0.8252
0.22	8.0	16832	0.4612	1.0	315.3915	0.8252	0.8239	0.8252	0.0	0.8241	0.8241

Framework versions

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