You can deploy this model and start earning money today!

wenxinkoh06/
mt5-base-zh-tailo_ver3.1b

generated_from_trainer

wenxinkoh06/mt5-base-zh-tailo_ver3.1

finetune

apache-2.0

endpoints_compatible

Views

No views yet

mt5-base-zh-tailo_ver3.1b

This model is a fine-tuned version of wenxinkoh06/mt5-base-zh-tailo_ver3.1 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.0342
Chrf: 73.7005

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: 6e-05
train_batch_size: 8
eval_batch_size: 16
seed: 1
gradient_accumulation_steps: 2
total_train_batch_size: 16
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
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Chrf
6.2546	2.0914	3250	2.2683	24.3654
3.2352	4.1828	6500	1.3091	52.2864
2.2857	6.2742	9750	1.0311	61.7503
1.7482	8.3656	13000	0.9281	67.5931
1.4606	10.4570	16250	0.8842	69.5538
1.2158	12.5484	19500	0.8796	71.2859
1.0204	14.6398	22750	0.8815	71.9894
0.8941	16.7313	26000	0.8909	72.7127
0.7953	18.8227	29250	0.9096	73.3105
0.6804	20.9141	32500	0.9516	73.4062
0.6100	23.0051	35750	0.9604	73.3586
0.5676	25.0966	39000	0.9930	73.8119
0.4894	27.1880	42250	1.0248	73.9041
0.4729	29.2794	45500	1.0342	73.7005

Framework versions

Transformers 5.0.0
Pytorch 2.11.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

wenxinkoh06/mt5-base-zh-tailo_ver3.1b

mt5-base-zh-tailo_ver3.1b

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

wenxinkoh06/
mt5-base-zh-tailo_ver3.1b