README.md

metadata

base_model: VuongQuoc/checkpoints_30_9_microsoft_deberta_V1.0_384
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: checkpoints_10_1_microsoft_deberta_V1.1_384
    results: []

checkpoints_10_1_microsoft_deberta_V1.1_384

This model is a fine-tuned version of VuongQuoc/checkpoints_30_9_microsoft_deberta_V1.0_384 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7675
• Map@3: 0.8483
• Accuracy: 0.755

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-06
• train_batch_size: 2
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 1200

Training results

Training Loss	Epoch	Step	Validation Loss	Map@3	Accuracy
1.5583	0.05	100	1.4269	0.7675	0.65
1.1541	0.11	200	1.0863	0.765	0.66
1.0126	0.16	300	0.9547	0.8133	0.72
0.9608	0.21	400	0.8926	0.8275	0.74
0.9224	0.27	500	0.8429	0.8400	0.76
0.8834	0.32	600	0.8297	0.8342	0.745
0.8585	0.37	700	0.7904	0.8483	0.76
0.8491	0.43	800	0.7726	0.8542	0.765
0.878	0.48	900	0.7693	0.8517	0.755
0.8529	0.53	1000	0.7703	0.8450	0.75
0.8485	0.59	1100	0.7682	0.8483	0.755
0.8353	0.64	1200	0.7675	0.8483	0.755

Framework versions

• Transformers 4.32.1
• Pytorch 2.0.0
• Datasets 2.9.0
• Tokenizers 0.13.3