You can deploy this model and start earning money today!

contemmcm/
e63ba28d0387320a07b48b0f89176fcb

Name: e63ba28d0387320a07b48b0f89176fcb
Rating: 2.5 (7 reviews)

generated_from_trainer

studio-ousia/luke-japanese-large-lite

finetune

apache-2.0

endpoints_compatible

Views

No views yet

e63ba28d0387320a07b48b0f89176fcb

This model is a fine-tuned version of studio-ousia/luke-japanese-large-lite on the nyu-mll/glue [sst2] dataset. It achieves the following results on the evaluation set:

Loss: 0.7577
Data Size: 0.125
Epoch Runtime: 49.0760
Accuracy: 0.5093
F1 Macro: 0.3374
Rouge1: 0.5093
Rouge2: 0.0
Rougel: 0.5093
Rougelsum: 0.5081

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	0.6901	0	1.9697	0.5185	0.4611	0.5174	0.5185	0.5185
No log	1	2104	0.6950	0.0078	5.3077	0.4907	0.3292	0.4907	0.4907	0.4919
No log	2	4208	0.7614	0.0156	8.2411	0.5093	0.3374	0.5093	0.5093	0.5081
0.0155	3	6312	0.6988	0.0312	14.7471	0.5093	0.3374	0.5093	0.5093	0.5081
0.6974	4	8416	0.7006	0.0625	25.8885	0.5093	0.3374	0.5093	0.5093	0.5081
0.6999	5	10520	0.7577	0.125	49.0760	0.5093	0.3374	0.5093	0.5093	0.5081

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

contemmcm/e63ba28d0387320a07b48b0f89176fcb

e63ba28d0387320a07b48b0f89176fcb

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
e63ba28d0387320a07b48b0f89176fcb