Regression_albert_9_with_translation

This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3629
• Mse: 0.3629
• Mae: 0.4551
• R2: 0.1650
• Accuracy: 0.6333

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Mae	R2	Accuracy
No log	1.0	53	0.3421	0.3421	0.4573	0.2292	0.6167
No log	2.0	106	0.2617	0.2617	0.3888	0.4104	0.6667
No log	3.0	159	0.2117	0.2117	0.3422	0.5230	0.7667
No log	4.0	212	0.3250	0.3250	0.4990	0.2677	0.55
No log	5.0	265	0.2494	0.2494	0.3321	0.4380	0.7167
No log	6.0	318	0.2477	0.2477	0.3488	0.4419	0.75
No log	7.0	371	0.3209	0.3209	0.3599	0.2770	0.7833
No log	8.0	424	0.2704	0.2704	0.3715	0.3909	0.7
No log	9.0	477	0.2886	0.2886	0.3185	0.3498	0.7833
0.1507	10.0	530	0.2477	0.2477	0.3071	0.4418	0.7667
0.1507	11.0	583	0.2670	0.2670	0.3232	0.3984	0.7833
0.1507	12.0	636	0.2285	0.2285	0.2926	0.4851	0.75
0.1507	13.0	689	0.2378	0.2378	0.2980	0.4643	0.7833
0.1507	14.0	742	0.2544	0.2544	0.3194	0.4269	0.7667
0.1507	15.0	795	0.2571	0.2571	0.2904	0.4208	0.8
0.1507	16.0	848	0.2505	0.2505	0.2884	0.4357	0.8
0.1507	17.0	901	0.2654	0.2654	0.2846	0.4022	0.8
0.1507	18.0	954	0.2606	0.2606	0.2785	0.4128	0.8
0.0203	19.0	1007	0.2519	0.2519	0.2816	0.4324	0.8
0.0203	20.0	1060	0.2634	0.2634	0.2826	0.4065	0.8

Framework versions

• Transformers 4.27.4
• Pytorch 1.13.1+cu116
• Datasets 2.11.0
• Tokenizers 0.13.2