You can deploy this model and start earning money today!

contemmcm/
d33e63cac256a292bae04b5990110475

Name: d33e63cac256a292bae04b5990110475
Rating: 2.5 (6 reviews)

generated_from_trainer

Qwen/Qwen2.5-3B

finetune

other

text-embeddings-inference

endpoints_compatible

Views

No views yet

d33e63cac256a292bae04b5990110475

This model is a fine-tuned version of Qwen/Qwen2.5-3B on the contemmcm/hate-speech-and-offensive-language dataset. It achieves the following results on the evaluation set:

Loss: 1.4536
Data Size: 1.0
Epoch Runtime: 199.2717
Accuracy: 0.8732
F1 Macro: 0.6988

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
No log	0	0	4.8095	0	13.4534	0.4982	0.2854
No log	1	619	3.4914	0.0078	14.6423	0.6922	0.4359
No log	2	1238	1.7902	0.0156	19.7770	0.8634	0.6235
0.0759	3	1857	1.5353	0.0312	28.9125	0.9044	0.6059
0.0759	4	2476	1.2173	0.0625	38.8073	0.9008	0.6030
1.6793	5	3095	1.1467	0.125	46.8236	0.9006	0.6810
0.1916	6	3714	2.4368	0.25	67.8458	0.7593	0.4779
1.6194	7	4333	1.4040	0.5	111.4199	0.8947	0.6047
1.2728	8.0	4952	1.2265	1.0	204.2218	0.9056	0.6097
0.8778	9.0	5571	1.4536	1.0	199.2717	0.8732	0.6988

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

contemmcm/d33e63cac256a292bae04b5990110475

d33e63cac256a292bae04b5990110475

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
d33e63cac256a292bae04b5990110475