mix_ensemble_v1

iTroned/mix_ensemble_v1

mix_ensemble_v1 is a machine learning model from iTroned. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

Access

Public

Updated Apr 3, 2025

Parameters

383K

30.7 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.5 MB · 99%

At a glance

Library: transformers
Access: Public
Created: Apr 3, 2025
Updated: Apr 3, 2025
SHA: 9fea158a

Model card

From the Hugging Face model README

mix_ensemble_v1

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4263
Accuracy Offensive: 0.8097
F1 Offensive: 0.7871
Accuracy Targeted: 0.8788
F1 Targeted: 0.8574
Accuracy Stance: 0.8263
F1 Stance: 0.7841

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: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Offensive	F1 Offensive	Accuracy Targeted	F1 Targeted	Accuracy Stance	F1 Stance
0.7638	1.0	1324	0.7520	0.6545	0.5178	0.6545	0.5178	0.7009	0.5777
0.7218	2.0	2648	0.7018	0.6643	0.5449	0.6616	0.5360	0.7009	0.5777
0.6952	3.0	3972	0.6439	0.7035	0.6312	0.7311	0.6883	0.7009	0.5779
0.6489	4.0	5296	0.6076	0.7073	0.6355	0.7560	0.7174	0.7349	0.6592
0.6195	5.0	6620	0.5649	0.7557	0.7159	0.7919	0.7696	0.7685	0.7236
0.6161	6.0	7944	0.5540	0.7224	0.6572	0.7946	0.7637	0.7715	0.7168
0.5808	7.0	9268	0.5206	0.7602	0.7198	0.8248	0.8013	0.7847	0.7393
0.5684	8.0	10592	0.5034	0.7591	0.7176	0.8353	0.8124	0.7912	0.7477
0.5512	9.0	11916	0.4976	0.7519	0.7044	0.8346	0.8102	0.7987	0.7523
0.5487	10.0	13240	0.4687	0.7851	0.7549	0.8618	0.8407	0.8131	0.7719
0.5367	11.0	14564	0.4690	0.7704	0.7325	0.8512	0.8282	0.8063	0.7610
0.5446	12.0	15888	0.4558	0.7893	0.7588	0.8652	0.8433	0.8119	0.7689
0.5243	13.0	17212	0.4497	0.8032	0.7789	0.8705	0.8493	0.8138	0.7720
0.5283	14.0	18536	0.4415	0.7866	0.7561	0.8731	0.8511	0.8191	0.7758
0.5333	15.0	19860	0.4354	0.7934	0.7649	0.8776	0.8561	0.8285	0.7854
0.5228	16.0	21184	0.4395	0.7863	0.7552	0.8712	0.8488	0.8206	0.7760
0.5323	17.0	22508	0.4262	0.8199	0.8005	0.8829	0.8617	0.8278	0.7866
0.5186	18.0	23832	0.4304	0.8108	0.7889	0.8765	0.8551	0.8252	0.7832
0.5198	19.0	25156	0.4262	0.8104	0.7881	0.8833	0.8618	0.8319	0.7896
0.5076	20.0	26480	0.4255	0.8104	0.7885	0.8803	0.8588	0.8233	0.7823

Framework versions

Transformers 4.50.2
Pytorch 2.6.0+cu124
Datasets 3.0.1
Tokenizers 0.21.1

Library: transformers
Created: Apr 3, 2025
Updated: Apr 3, 2025