metadata

license: mit
base_model: microsoft/deberta-v3-large
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: checkpoints_29_9_microsoft_deberta_V1
    results: []

checkpoints_29_9_microsoft_deberta_V1

This model is a fine-tuned version of microsoft/deberta-v3-large on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.6667
Map@3: 0.8692
Accuracy: 0.8

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
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Map@3	Accuracy
1.6098	0.05	100	1.6090	0.5250	0.38
1.6092	0.11	200	1.6040	0.7408	0.63
1.1308	0.16	300	1.1807	0.7475	0.63
1.0343	0.21	400	0.9997	0.8108	0.705
0.9673	0.27	500	0.9104	0.8042	0.69
0.9579	0.32	600	0.8178	0.8542	0.775
0.8286	0.37	700	0.7612	0.8592	0.785
0.8198	0.43	800	0.7236	0.8600	0.795
0.8379	0.48	900	0.7237	0.8583	0.79
0.8646	0.53	1000	0.7052	0.8583	0.785
0.8876	0.59	1100	0.6899	0.8692	0.8
0.8598	0.64	1200	0.6897	0.8683	0.8
0.8218	0.69	1300	0.6655	0.8725	0.805
0.8695	0.75	1400	0.6742	0.8692	0.8
0.8136	0.8	1500	0.6739	0.8692	0.8
0.7843	0.85	1600	0.6644	0.8725	0.81
0.8477	0.91	1700	0.6655	0.8717	0.805
0.7881	0.96	1800	0.6667	0.8692	0.8

Framework versions

Transformers 4.32.1
Pytorch 2.0.0
Datasets 2.9.0
Tokenizers 0.13.3