damage_trigger_effect_2023-10-06_11_33

This model is a fine-tuned version of DeepPavlov/rubert-base-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3069
• Precision: 0.0
• Recall: 0.0
• F1: 0.0
• Accuracy: 0.9128

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: 20
• eval_batch_size: 20
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	28	0.3496	0.0	0.0	0.0	0.9016
No log	2.0	56	0.2948	0.0	0.0	0.0	0.9147
No log	3.0	84	0.2590	0.0	0.0	0.0	0.9171
No log	4.0	112	0.2689	0.0	0.0	0.0	0.9078
No log	5.0	140	0.2561	0.0	0.0	0.0	0.9101
No log	6.0	168	0.2447	0.0	0.0	0.0	0.9155
No log	7.0	196	0.2621	0.0	0.0	0.0	0.9085
No log	8.0	224	0.2734	0.0	0.0	0.0	0.9143
No log	9.0	252	0.2806	0.0	0.0	0.0	0.9066
No log	10.0	280	0.2954	0.0	0.0	0.0	0.9105
No log	11.0	308	0.2929	0.0	0.0	0.0	0.9128
No log	12.0	336	0.2936	0.0	0.0	0.0	0.9116
No log	13.0	364	0.2948	0.0	0.0	0.0	0.9132
No log	14.0	392	0.2973	0.0	0.0	0.0	0.9151
No log	15.0	420	0.3069	0.0	0.0	0.0	0.9128

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.0