damage_trigger_effect_2024-11-06_13_00

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

• Loss: 0.5939

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use 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: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	34	0.6901
No log	2.0	68	0.5241
No log	3.0	102	0.4540
No log	4.0	136	0.4661
No log	5.0	170	0.4877
No log	6.0	204	0.4716
No log	7.0	238	0.4778
No log	8.0	272	0.5008
No log	9.0	306	0.5195
No log	10.0	340	0.5669
No log	11.0	374	0.5807
No log	12.0	408	0.5776
No log	13.0	442	0.5938
No log	14.0	476	0.5854
0.2729	15.0	510	0.5939

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3