baseline_seed-42_1e-3

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.0426
• Accuracy: 0.4215

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: 0.001
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 32000
• num_epochs: 20.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
6.4165	0.9996	1977	4.6002	0.2628
4.4252	1.9996	3955	3.9054	0.3265
3.8303	2.9997	5933	3.5867	0.3593
3.552	3.9997	7911	3.4361	0.3746
3.4003	4.9998	9889	3.3533	0.3826
3.3048	5.9999	11867	3.2995	0.3884
3.2405	6.9999	13845	3.2618	0.3921
3.1938	8.0	15823	3.2395	0.3949
3.1584	8.9996	17800	3.2179	0.3974
3.1331	9.9996	19778	3.1996	0.3994
3.1128	10.9997	21756	3.1903	0.4005
3.0941	11.9997	23734	3.1839	0.4014
3.0833	12.9998	25712	3.1728	0.4024
3.0736	13.9999	27690	3.1701	0.4029
3.0665	14.9999	29668	3.1649	0.4034
3.0616	16.0	31646	3.1627	0.4037
3.0446	16.9996	33623	3.1264	0.4081
2.9699	17.9996	35601	3.0900	0.4133
2.8822	18.9997	37579	3.0569	0.4182
2.7774	19.9912	39540	3.0426	0.4215

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.1+cu121
• Datasets 2.19.1
• Tokenizers 0.20.0