rubert_tiny2_ner_finetuned_with_mlm

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2349
• Precision: 0.8405
• Recall: 0.8890
• F1: 0.8641
• Accuracy: 0.9338

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 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	Precision	Recall	F1	Accuracy
No log	1.0	50	1.3648	0.2726	0.2392	0.2548	0.5990
No log	2.0	100	0.8073	0.6141	0.6759	0.6435	0.7939
No log	3.0	150	0.5637	0.7251	0.7957	0.7587	0.8755
No log	4.0	200	0.4456	0.7815	0.8381	0.8088	0.9057
No log	5.0	250	0.3809	0.8021	0.8574	0.8288	0.9128
No log	6.0	300	0.3357	0.8191	0.8726	0.8450	0.9214
No log	7.0	350	0.3094	0.8211	0.8770	0.8481	0.9235
No log	8.0	400	0.2894	0.8207	0.8802	0.8494	0.9263
No log	9.0	450	0.2758	0.8361	0.8870	0.8608	0.9313
0.6048	10.0	500	0.2645	0.8322	0.8862	0.8584	0.9302
0.6048	11.0	550	0.2546	0.8339	0.8870	0.8596	0.9316
0.6048	12.0	600	0.2509	0.8322	0.8862	0.8584	0.9304
0.6048	13.0	650	0.2467	0.8347	0.8842	0.8588	0.9316
0.6048	14.0	700	0.2433	0.8387	0.8874	0.8624	0.9328
0.6048	15.0	750	0.2410	0.8348	0.8870	0.8601	0.9335
0.6048	16.0	800	0.2390	0.8358	0.8874	0.8609	0.9332
0.6048	17.0	850	0.2377	0.8368	0.8874	0.8614	0.9335
0.6048	18.0	900	0.2361	0.8393	0.8874	0.8627	0.9335
0.6048	19.0	950	0.2353	0.8398	0.8882	0.8633	0.9334
0.1597	20.0	1000	0.2349	0.8405	0.8890	0.8641	0.9338

Framework versions

• Transformers 4.50.0
• Pytorch 2.6.0
• Datasets 3.5.0
• Tokenizers 0.21.1