ania3000/ossbert-morph

trainer_output

This model is a fine-tuned version of AlexeySorokin/ossbert-onc-unlab-from_multilingual-bs64-5epochs on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2180
• Accuracy: 95.3662
• Sentence accuracy: 61.1009

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Sentence accuracy
No log	0.3663	200	0.7365	85.6227	26.4220
No log	0.7326	400	0.4917	89.7247	35.4128
1.0818	1.0989	600	0.3859	91.3683	42.0183
1.0818	1.4652	800	0.3291	92.7312	48.0734
0.3537	1.8315	1000	0.3010	93.3191	50.4587
0.3537	2.1978	1200	0.2756	93.9738	52.6606
0.3537	2.5641	1400	0.2665	94.2678	54.6789
0.2244	2.9304	1600	0.2540	94.4949	56.5138
0.2244	3.2967	1800	0.2494	94.6686	55.0459
0.1549	3.6630	2000	0.2410	95.0695	60.1835
0.1549	4.0293	2200	0.2380	95.0027	59.6330
0.1549	4.3956	2400	0.2393	94.9759	58.3486
0.1165	4.7619	2600	0.2350	95.1897	59.8165

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2