72b16c3cf27be60b655b9f1adc4579cc

This model is a fine-tuned version of albert/albert-xlarge-v1 on the dair-ai/emotion [split] dataset. It achieves the following results on the evaluation set:

• Loss: 1.6010
• Data Size: 0.125
• Epoch Runtime: 5.5153
• Accuracy: 0.2908
• F1 Macro: 0.0751

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	1.9393	0	1.6661	0.1043	0.0551
No log	1	500	1.5869	0.0078	2.1589	0.3644	0.1258
No log	2	1000	1.6447	0.0156	2.1748	0.3296	0.1260
No log	3	1500	1.6596	0.0312	2.6962	0.3488	0.0862
No log	4	2000	1.7912	0.0625	3.7576	0.2908	0.0751
0.0888	5	2500	1.6010	0.125	5.5153	0.2908	0.0751

Framework versions

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