You can deploy this model and start earning money today!

Curiousfox/
mT5_tai-lo_to_chinese_ver7.1.a

Name: mT5_tai-lo_to_chinese_ver7.1.a
Availability: InStock

Views

No views yet

outputs

This model is a fine-tuned version of Curiousfox/mT5_tai-lo_to_chinese_ver7.0.c on an unknown dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

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: constant_with_warmup
lr_scheduler_warmup_steps: 3000
training_steps: 60000

Training Loss	Epoch	Step	Validation Loss	Chrf
7.5572	0.9461	3000	4.5450	1.6933
5.0112	1.8921	6000	4.0485	2.5261
4.4343	2.8382	9000	3.5057	5.0419
3.8788	3.7843	12000	2.9535	11.1145
3.3505	4.7304	15000	2.4957	18.3909
2.9251	5.6764	18000	2.1745	24.9268
2.6285	6.6225	21000	1.9486	30.8335
2.3717	7.5686	24000	1.7753	35.3474
2.1877	8.5147	27000	1.6291	39.4409
2.0095	9.4607	30000	1.5248	43.2546
1.8718	10.4068	33000	1.4351	46.2765
1.7576	11.3529	36000	1.3568	48.976
1.6414	12.2990	39000	1.2831	51.4542
1.5527	13.2450	42000	1.2365	53.5706
1.4577	14.1911	45000	1.1962	55.7439
1.3887	15.1372	48000	1.1310	57.2829
1.3159	16.0833	51000	1.0975	58.754
1.2479	17.0293	54000	1.0717	60.1576
1.1936	17.9754	57000	1.0312	61.6882
1.1394	18.9215	60000	1.0140	62.8549