learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Chrf++	Gen Len
26.7580	1.0	2	2.8588	10.7471	188.9375
26.7580	2.0	4	2.8554	10.8352	189.0
26.7580	3.0	6	2.8549	10.834	188.9375
26.7580	4.0	8	2.8544	10.8194	188.8125
26.7580	5.0	10	2.8541	10.8249	189.0
26.7580	6.0	12	2.8535	10.8352	189.0
26.7580	7.0	14	2.8528	10.7611	189.125
26.7580	8.0	16	2.8517	12.1789	189.125
26.7580	9.0	18	2.8518	10.7643	189.1875
26.7580	10.0	20	2.8501	12.3543	189.25
26.7580	11.0	22	2.8494	12.2123	189.125
26.7580	12.0	24	2.8484	12.2218	188.75
26.7580	13.0	26	2.8455	12.3371	188.9375
26.7580	14.0	28	2.8433	12.8507	189.0
26.7580	15.0	30	2.8411	13.3142	188.75
26.7580	16.0	32	2.8361	14.7363	188.8125
26.7580	17.0	34	2.8361	15.7393	188.5625
26.7580	18.0	36	2.8324	15.7478	188.5625
26.7580	19.0	38	2.8260	14.5721	188.4375
26.7580	20.0	40	2.8230	15.2666	188.6875
26.7580	21.0	42	2.8144	15.2691	188.6875
26.7580	22.0	44	2.8042	14.6407	188.9375
26.7580	23.0	46	2.7935	14.57	188.625
26.7580	24.0	48	2.7789	13.4664	188.375
26.7580	25.0	50	2.7626	14.6085	188.4375
26.7580	26.0	52	2.7465	14.5546	188.3125
26.7580	27.0	54	2.7307	14.6896	188.375
26.7580	28.0	56	2.7161	14.5769	188.375
26.7580	29.0	58	2.6964	15.3374	188.25
26.7580	30.0	60	2.6715	16.1603	188.3125
26.7580	31.0	62	2.6445	15.6414	188.25
26.7580	32.0	64	2.6131	17.2029	188.3125
26.7580	33.0	66	2.5833	16.5351	188.1875
26.7580	34.0	68	2.5486	17.3096	187.9375
26.7580	35.0	70	2.5185	17.2417	187.8125
26.7580	36.0	72	2.4843	16.9894	187.8125
26.7580	37.0	74	2.4500	17.0052	188.125
26.7580	38.0	76	2.4204	16.9242	187.9375
26.7580	39.0	78	2.3796	16.3571	188.125
26.7580	40.0	80	2.3434	16.2646	188.0
26.7580	41.0	82	2.3120	16.8646	187.875
26.7580	42.0	84	2.2731	16.358	187.75
26.7580	43.0	86	2.2336	17.5372	187.625
26.7580	44.0	88	2.1956	17.2877	187.75
26.7580	45.0	90	2.1650	16.7112	187.8125
26.7580	46.0	92	2.1262	16.9389	187.75
26.7580	47.0	94	2.1038	16.1182	187.8125
26.7580	48.0	96	2.0664	17.0087	187.625
26.7580	49.0	98	2.0345	15.4397	187.8125
22.0101	50.0	100	2.0098	15.5398	187.9375
22.0101	51.0	102	1.9735	15.2735	188.0625
22.0101	52.0	104	1.9476	15.7513	187.75
22.0101	53.0	106	1.9131	15.5153	187.75
22.0101	54.0	108	1.8834	15.3355	187.6875
22.0101	55.0	110	1.8590	15.4841	188.0
22.0101	56.0	112	1.8313	15.7017	187.8125
22.0101	57.0	114	1.7989	15.6474	187.6875
22.0101	58.0	116	1.7650	15.8156	187.875

Framework versions

Transformers 5.12.1
Pytorch 2.6.0+cu124
Datasets 5.0.0
Tokenizers 0.22.2

Tsedeniya/finetuned_byT5base_pan_joint

finetuned_byT5base_pan_joint

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Tsedeniya/
finetuned_byT5base_pan_joint