README.md

metadata

tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: checkpoints_2_microsoft_deberta_21_9
    results: []

checkpoints_2_microsoft_deberta_21_9

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

• Loss: 0.8635
• Map@3: 0.8558
• Accuracy: 0.76

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: 2
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Map@3	Accuracy
0.6215	0.15	300	0.6511	0.8592	0.76
0.5953	0.3	600	0.6929	0.8533	0.765
0.5332	0.45	900	0.6665	0.8525	0.76
0.587	0.6	1200	0.6638	0.855	0.775
0.5626	0.75	1500	0.6476	0.8692	0.78
0.6712	0.9	1800	0.6499	0.8700	0.785
0.2181	1.05	2100	0.8619	0.8417	0.75
0.2024	1.2	2400	0.8607	0.8467	0.75
0.2571	1.35	2700	0.8282	0.8483	0.75
0.2407	1.5	3000	0.8297	0.8558	0.765
0.2282	1.65	3300	0.8635	0.8558	0.76

Framework versions

• Transformers 4.32.1
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3