CollectedDataModel

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4365

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4302	0.9913	100	0.4359
0.4275	1.9827	200	0.4396
0.4208	2.9740	300	0.4366
0.4217	3.9653	400	0.4389
0.4154	4.9566	500	0.4282
0.4173	5.9480	600	0.4362
0.4127	6.9393	700	0.4378
0.4104	7.9306	800	0.4340
0.4076	8.9219	900	0.4347
0.4065	9.9133	1000	0.4365

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1