You can deploy this model and start earning money today!

contemmcm/
3c1b83a8df1d68db074f66a97730cac9

Name: 3c1b83a8df1d68db074f66a97730cac9
Rating: 2.5 (7 reviews)

generated_from_trainer

meta-llama/Llama-3.2-1B

finetune

llama3.2

text-embeddings-inference

endpoints_compatible

Views

No views yet

3c1b83a8df1d68db074f66a97730cac9

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the contemmcm/hate-speech-and-offensive-language dataset. It achieves the following results on the evaluation set:

Loss: 3.0342
Data Size: 1.0
Epoch Runtime: 86.8158
Accuracy: 0.8900
F1 Macro: 0.7141

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	13.4832	0	7.1079	0.1041	0.1329
No log	1	619	6.2383	0.0078	7.2295	0.6425	0.2847
No log	2	1238	1.9929	0.0156	9.1788	0.8600	0.5560
0.1056	3	1857	1.6679	0.0312	11.5805	0.9008	0.6004
0.1056	4	2476	1.3335	0.0625	15.6161	0.8929	0.6535
1.4166	5	3095	1.3284	0.125	20.7363	0.8910	0.7311
0.1425	6	3714	1.4032	0.25	31.1695	0.9024	0.6019
1.2235	7	4333	1.1632	0.5	51.2381	0.9048	0.7159
1.1456	8.0	4952	1.1510	1.0	93.2187	0.9000	0.6028
0.9023	9.0	5571	1.4357	1.0	87.2206	0.8819	0.7140
0.7132	10.0	6190	1.3980	1.0	88.6522	0.9050	0.7224
0.4737	11.0	6809	1.9670	1.0	87.7096	0.8939	0.7206
0.3483	12.0	7428	3.0342	1.0	86.8158	0.8900	0.7141

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

contemmcm/3c1b83a8df1d68db074f66a97730cac9

3c1b83a8df1d68db074f66a97730cac9

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
3c1b83a8df1d68db074f66a97730cac9