MIDICausalFinetuning2

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

• Loss: 0.6756

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	9	7.7655
No log	2.0	18	6.4257
No log	3.0	27	5.4697
No log	4.0	36	4.9705
No log	5.0	45	4.7258
No log	6.0	54	4.5740
No log	7.0	63	4.4554
No log	8.0	72	4.3483
No log	9.0	81	4.2406
No log	10.0	90	4.1217
No log	11.0	99	3.9690
No log	12.0	108	3.7765
No log	13.0	117	3.6364
No log	14.0	126	3.5090
No log	15.0	135	3.4009
No log	16.0	144	3.2948
No log	17.0	153	3.1934
No log	18.0	162	3.1031
No log	19.0	171	3.0232
No log	20.0	180	2.9464
No log	21.0	189	2.8734
No log	22.0	198	2.8016
No log	23.0	207	2.7296
No log	24.0	216	2.6571
No log	25.0	225	2.5846
No log	26.0	234	2.5193
No log	27.0	243	2.4498
No log	28.0	252	2.3844
No log	29.0	261	2.3150
No log	30.0	270	2.2558
No log	31.0	279	2.1873
No log	32.0	288	2.1213
No log	33.0	297	2.0649
No log	34.0	306	1.9997
No log	35.0	315	1.9421
No log	36.0	324	1.8803
No log	37.0	333	1.8131
No log	38.0	342	1.7380
No log	39.0	351	1.6847
No log	40.0	360	1.5993
No log	41.0	369	1.5855
No log	42.0	378	1.5034
No log	43.0	387	1.4867
No log	44.0	396	1.4380
No log	45.0	405	1.4309
No log	46.0	414	1.3585
No log	47.0	423	1.3231
No log	48.0	432	1.3071
No log	49.0	441	1.2690
No log	50.0	450	1.2417
No log	51.0	459	1.2078
No log	52.0	468	1.1709
No log	53.0	477	1.1457
No log	54.0	486	1.1317
No log	55.0	495	1.1155
2.8999	56.0	504	1.0914
2.8999	57.0	513	1.0625
2.8999	58.0	522	1.0380
2.8999	59.0	531	1.0190
2.8999	60.0	540	0.9976
2.8999	61.0	549	0.9716
2.8999	62.0	558	0.9544
2.8999	63.0	567	0.9289
2.8999	64.0	576	0.9157
2.8999	65.0	585	0.8983
2.8999	66.0	594	0.8923
2.8999	67.0	603	0.8751
2.8999	68.0	612	0.8684
2.8999	69.0	621	0.8485
2.8999	70.0	630	0.8349
2.8999	71.0	639	0.8261
2.8999	72.0	648	0.8072
2.8999	73.0	657	0.8034
2.8999	74.0	666	0.7947
2.8999	75.0	675	0.7787
2.8999	76.0	684	0.7700
2.8999	77.0	693	0.7581
2.8999	78.0	702	0.7577
2.8999	79.0	711	0.7472
2.8999	80.0	720	0.7514
2.8999	81.0	729	0.7317
2.8999	82.0	738	0.7334
2.8999	83.0	747	0.7233
2.8999	84.0	756	0.7148
2.8999	85.0	765	0.7139
2.8999	86.0	774	0.7048
2.8999	87.0	783	0.7033
2.8999	88.0	792	0.6972
2.8999	89.0	801	0.6946
2.8999	90.0	810	0.6899
2.8999	91.0	819	0.6867
2.8999	92.0	828	0.6852
2.8999	93.0	837	0.6855
2.8999	94.0	846	0.6815
2.8999	95.0	855	0.6793
2.8999	96.0	864	0.6782
2.8999	97.0	873	0.6754
2.8999	98.0	882	0.6763
2.8999	99.0	891	0.6758
2.8999	100.0	900	0.6756

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1