stage2_v5

This model is a fine-tuned version of linker_v5/stage1 on the jarod0411/linker_v3 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2448
• Accuracy: 0.9165

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: 24
• eval_batch_size: 24
• seed: 1
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 192
• total_eval_batch_size: 192
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3173	1.0	11304	0.2837	0.9060
0.284	2.0	22608	0.2613	0.9124
0.2719	3.0	33912	0.2546	0.9140
0.2654	4.0	45216	0.2511	0.9148
0.2613	5.0	56520	0.2489	0.9154
0.2586	6.0	67824	0.2474	0.9158
0.2569	7.0	79128	0.2463	0.9161
0.2553	8.0	90432	0.2455	0.9163
0.2545	9.0	101736	0.2450	0.9164
0.2539	10.0	113040	0.2448	0.9165

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.2.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2