180715c48bee8667d4ed3428d0c1732e

This model is a fine-tuned version of albert/albert-xxlarge-v2 on the contemmcm/amazon_reviews_2013 [cell-phone] dataset. It achieves the following results on the evaluation set:

• Loss: 1.4820
• Data Size: 0.125
• Epoch Runtime: 142.3290
• Accuracy: 0.3853
• F1 Macro: 0.1112

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	2.0084	0	56.0280	0.2252	0.1225
No log	1	1973	1.4765	0.0078	61.8715	0.3847	0.1262
0.0345	2	3946	1.4872	0.0156	66.9257	0.3923	0.1311
1.4446	3	5919	1.4843	0.0312	77.8494	0.3853	0.1112
1.5734	4	7892	1.4921	0.0625	99.0788	0.3853	0.1112
1.4989	5	9865	1.4820	0.125	142.3290	0.3853	0.1112

Framework versions

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