ania3000/ossbert-morph-v2-1

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: 0.2914
• Accuracy: 95.8782
• Sentence accuracy: 60.1835

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: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Sentence accuracy
0.9947	1.0	546	0.3542	91.9569	42.5688
0.3077	2.0	1092	0.2446	94.3247	52.4771
0.1956	3.0	1638	0.2200	94.9637	55.9633
0.1388	4.0	2184	0.2132	95.0388	57.0642
0.1031	5.0	2730	0.2138	95.5525	57.9817
0.0805	6.0	3276	0.2245	95.4397	58.8991
0.0593	7.0	3822	0.2192	95.8031	60.5505
0.0479	8.0	4368	0.2297	95.6527	58.5321
0.0402	9.0	4914	0.2402	95.7028	58.3486
0.0281	10.0	5460	0.2475	95.8782	60.1835
0.0164	11.0	6006	0.2645	95.7529	59.4495
0.0132	12.0	6552	0.2600	95.9910	60.3670
0.0118	13.0	7098	0.2668	95.8532	60.1835
0.0094	14.0	7644	0.2752	95.8908	60.3670
0.0073	15.0	8190	0.2856	95.9409	60.3670
0.0062	16.0	8736	0.2914	95.8782	60.1835

Framework versions

• Transformers 4.57.3
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2