You can deploy this model and start earning money today!

contemmcm/
b50f9cf6b7a8ee8aa912970e684a8d27

Name: b50f9cf6b7a8ee8aa912970e684a8d27
Rating: 2.5 (7 reviews)

generated_from_trainer

studio-ousia/luke-japanese-base-lite

finetune

apache-2.0

endpoints_compatible

Views

No views yet

b50f9cf6b7a8ee8aa912970e684a8d27

This model is a fine-tuned version of studio-ousia/luke-japanese-base-lite on the nyu-mll/glue [qqp] dataset. It achieves the following results on the evaluation set:

Loss: 0.6583
Data Size: 1.0
Epoch Runtime: 985.0528
Accuracy: 0.6320
F1 Macro: 0.3872
Rouge1: 0.6318
Rouge2: 0.0
Rougel: 0.6319
Rougelsum: 0.6317

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: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro	Rouge1	Rougel	Rougelsum
No log	0	0	0.6585	0	33.6943	0.6320	0.3872	0.6318	0.6319	0.6317
0.6518	1	11370	0.5219	0.0078	40.8873	0.7225	0.6904	0.7226	0.7225	0.7224
0.5324	2	22740	0.5142	0.0156	48.4858	0.7410	0.7083	0.7412	0.7411	0.7409
0.496	3	34110	0.4727	0.0312	64.3654	0.7564	0.7510	0.7566	0.7564	0.7563
0.4957	4	45480	0.4385	0.0625	96.5501	0.7846	0.7741	0.7846	0.7845	0.7846
0.5043	5	56850	0.6300	0.125	157.1827	0.7117	0.7116	0.7117	0.7116	0.7116
0.452	6	68220	0.4376	0.25	278.5063	0.7921	0.7842	0.7922	0.7921	0.7921
0.6572	7	79590	0.6581	0.5	514.1366	0.6320	0.3872	0.6318	0.6319	0.6317
0.6544	8.0	90960	0.6581	1.0	980.6688	0.6320	0.3872	0.6318	0.6319	0.6317
0.6529	9.0	102330	0.6614	1.0	972.9140	0.6320	0.3872	0.6318	0.6319	0.6317
0.6631	10.0	113700	0.6583	1.0	985.0528	0.6320	0.3872	0.6318	0.6319	0.6317

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

contemmcm/b50f9cf6b7a8ee8aa912970e684a8d27

b50f9cf6b7a8ee8aa912970e684a8d27

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
b50f9cf6b7a8ee8aa912970e684a8d27