regressor16

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

• Loss: 0.0575
• Accuracy Agreeableness: 0.0938
• F1 Agreeableness: 0.0161
• Precision Agreeableness: 0.0088
• Recall Agreeableness: 0.0938
• Accuracy Conscientiousness: 0.3125
• F1 Conscientiousness: 0.3036
• Precision Conscientiousness: 0.4091
• Recall Conscientiousness: 0.3125
• Accuracy Extraversion: 0.3125
• F1 Extraversion: 0.2292
• Precision Extraversion: 0.5283
• Recall Extraversion: 0.3125
• Accuracy Openness: 0.2812
• F1 Openness: 0.2943
• Precision Openness: 0.3771
• Recall Openness: 0.2812
• Accuracy Emotional stability: 0.5
• F1 Emotional stability: 0.4255
• Precision Emotional stability: 0.4375
• Recall Emotional stability: 0.5

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Agreeableness	F1 Agreeableness	Precision Agreeableness	Recall Agreeableness	Accuracy Conscientiousness	F1 Conscientiousness	Precision Conscientiousness	Recall Conscientiousness	Accuracy Extraversion	F1 Extraversion	Precision Extraversion	Recall Extraversion	Accuracy Openness	F1 Openness	Precision Openness	Recall Openness	Accuracy Emotional stability	F1 Emotional stability	Precision Emotional stability	Recall Emotional stability
0.1241	1.0	25	0.1025	0.0938	0.0161	0.0088	0.0938	0.625	0.4808	0.3906	0.625	0.4062	0.2347	0.1650	0.4062	0.0938	0.0234	0.0134	0.0938	0.4062	0.2347	0.1650	0.4062
0.077	2.0	50	0.0686	0.0938	0.0161	0.0088	0.0938	0.625	0.4808	0.3906	0.625	0.4062	0.2456	0.1760	0.4062	0.25	0.2619	0.3528	0.25	0.4062	0.3774	0.3589	0.4062
0.0674	3.0	75	0.0571	0.0938	0.0161	0.0088	0.0938	0.5625	0.4688	0.4018	0.5625	0.2188	0.1620	0.1380	0.2188	0.2812	0.2943	0.3771	0.2812	0.4688	0.4031	0.3991	0.4688
0.0549	4.0	100	0.0580	0.0938	0.0161	0.0088	0.0938	0.3438	0.3480	0.4142	0.3438	0.2812	0.2140	0.4870	0.2812	0.2812	0.2943	0.3771	0.2812	0.4062	0.2834	0.2176	0.4062
0.0547	5.0	125	0.0582	0.0938	0.0161	0.0088	0.0938	0.3125	0.3036	0.4091	0.3125	0.3125	0.2292	0.5283	0.3125	0.2812	0.2943	0.3771	0.2812	0.4062	0.2770	0.2101	0.4062
0.0522	6.0	150	0.0575	0.0938	0.0161	0.0088	0.0938	0.3125	0.3036	0.4091	0.3125	0.3125	0.2292	0.5283	0.3125	0.2812	0.2943	0.3771	0.2812	0.5	0.4255	0.4375	0.5

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1