ab88a56d01e25a30371bbae610076191

This model is a fine-tuned version of facebook/opt-1.3b on the contemmcm/amazon_reviews_2013 [cell-phone] dataset. It achieves the following results on the evaluation set:

• Loss: 1.2050
• Data Size: 1.0
• Epoch Runtime: 467.0297
• Accuracy: 0.6403
• F1 Macro: 0.5462

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
No log	0	0	1.9030	0	30.4792	0.1424	0.1183
No log	1	1973	0.9557	0.0078	34.3567	0.5853	0.4735
0.0267	2	3946	0.9672	0.0156	38.5151	0.5858	0.5128
0.9283	3	5919	0.8788	0.0312	48.2061	0.6373	0.5041
0.9368	4	7892	0.8649	0.0625	62.0139	0.6254	0.5408
0.8809	5	9865	0.8732	0.125	90.2946	0.6516	0.5374
0.8975	6	11838	0.8588	0.25	143.7256	0.6514	0.4860
0.8613	7	13811	0.8105	0.5	252.8646	0.6609	0.5637
0.8036	8.0	15784	0.8030	1.0	469.3832	0.6616	0.5865
0.729	9.0	17757	0.8161	1.0	465.8273	0.6653	0.5572
0.6443	10.0	19730	0.8481	1.0	467.2068	0.6441	0.5840
0.559	11.0	21703	0.9513	1.0	467.6481	0.6458	0.5660
0.4836	12.0	23676	1.2050	1.0	467.0297	0.6403	0.5462

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.1