You can deploy this model and start earning money today!

Curiousfox/
mt5_tai-lo_to_chinese_ver7.1.b

Name: mt5_tai-lo_to_chinese_ver7.1.b
Availability: InStock

generated_from_trainer

Curiousfox/mT5_tai-lo_to_chinese_ver6.1

finetune

apache-2.0

endpoints_compatible

Views

No views yet

mt5_tai-lo_to_chinese_ver7.1.b

This model is a fine-tuned version of Curiousfox/mT5_tai-lo_to_chinese_ver6.1 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.2313
Chrf: 51.4668

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: 1e-05
train_batch_size: 8
eval_batch_size: 16
seed: 1
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
lr_scheduler_warmup_steps: 3000
training_steps: 60000

Training results

Training Loss	Epoch	Step	Validation Loss	Chrf
3.0567	0.9461	3000	2.2862	20.3079
2.8265	1.8921	6000	2.0601	25.6548
2.5853	2.8382	9000	1.9024	29.7987
2.4102	3.7843	12000	1.7784	32.9696
2.2495	4.7304	15000	1.6755	36.507
2.1135	5.6764	18000	1.5971	38.8805
2.0277	6.6225	21000	1.5219	41.3789
1.9246	7.5686	24000	1.4638	43.373
1.8610	8.5147	27000	1.4187	45.0972
1.7872	9.4607	30000	1.3898	46.0909
1.7286	10.4068	33000	1.3513	47.7095
1.6866	11.3529	36000	1.3181	48.4392
1.6425	12.2990	39000	1.2974	48.751
1.6157	13.2450	42000	1.2751	49.8305
1.5777	14.1911	45000	1.2667	50.4362
1.5631	15.1372	48000	1.2476	50.7423
1.5445	16.0833	51000	1.2424	51.0013
1.5266	17.0293	54000	1.2392	51.3597
1.5209	17.9754	57000	1.2323	51.3642
1.5143	18.9215	60000	1.2313	51.4668

Framework versions

Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Curiousfox/mt5_tai-lo_to_chinese_ver7.1.b

mt5_tai-lo_to_chinese_ver7.1.b

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Curiousfox/
mt5_tai-lo_to_chinese_ver7.1.b