mt5-base-finetuned-novel-chinese-to-spanish

This model is a fine-tuned version of quickman/mt5-base-finetuned-chinese-to-spanish-finetuned-chinese-to-spanish on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3193
• Score: 0.0000
• Counts: [545, 246, 135, 80]
• Totals: [777, 713, 649, 585]
• Precisions: [70.14157014157014, 34.50210378681627, 20.801232665639446, 13.675213675213675]
• Bp: 0.0000
• Sys Len: 777
• Ref Len: 17012
• Bleu: 0.0000
• Gen Len: 19.0

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 40
• training_steps: 10000

Training results

Training Loss	Epoch	Step	Validation Loss	Score	Counts	Totals	Precisions	Bp	Sys Len	Ref Len	Bleu	Gen Len
2.7861	0.6	500	1.9548	0.0000	[465, 147, 51, 23]	[754, 690, 626, 562]	[61.6710875331565, 21.304347826086957, 8.146964856230031, 4.092526690391459]	0.0000	754	17012	0.0000	19.0
2.5103	1.19	1000	1.7626	0.0000	[491, 174, 62, 24]	[770, 706, 642, 578]	[63.76623376623377, 24.64589235127479, 9.657320872274143, 4.1522491349480966]	0.0000	770	17012	0.0000	19.0
2.3148	1.79	1500	1.6428	0.0000	[499, 181, 73, 35]	[781, 717, 653, 589]	[63.892445582586426, 25.24407252440725, 11.179173047473201, 5.942275042444821]	0.0000	781	17012	0.0000	19.0
2.17	2.39	2000	1.5580	0.0000	[524, 201, 90, 44]	[784, 720, 656, 592]	[66.83673469387755, 27.916666666666668, 13.71951219512195, 7.4324324324324325]	0.0000	784	17012	0.0000	19.0
2.0889	2.99	2500	1.5197	0.0000	[529, 214, 102, 55]	[781, 717, 653, 589]	[67.73367477592829, 29.846582984658298, 15.620214395099541, 9.33786078098472]	0.0000	781	17012	0.0000	19.0
2.009	3.58	3000	1.4945	0.0000	[527, 217, 103, 59]	[789, 725, 661, 597]	[66.7934093789607, 29.93103448275862, 15.582450832072617, 9.882747068676716]	0.0000	789	17012	0.0000	19.0
1.9494	4.18	3500	1.4647	0.0000	[518, 214, 105, 60]	[774, 710, 646, 582]	[66.9250645994832, 30.140845070422536, 16.25386996904025, 10.309278350515465]	0.0000	774	17012	0.0000	19.0
1.9289	4.78	4000	1.4282	0.0000	[539, 234, 116, 66]	[781, 717, 653, 589]	[69.01408450704226, 32.63598326359833, 17.76416539050536, 11.205432937181664]	0.0000	781	17012	0.0000	19.0
1.8661	5.38	4500	1.4049	0.0000	[520, 217, 117, 74]	[763, 699, 635, 571]	[68.15203145478375, 31.044349070100143, 18.4251968503937, 12.959719789842381]	0.0000	763	17012	0.0000	19.0
1.8417	5.97	5000	1.3815	0.0000	[536, 235, 119, 71]	[774, 710, 646, 582]	[69.25064599483204, 33.098591549295776, 18.42105263157895, 12.199312714776632]	0.0000	774	17012	0.0000	19.0
1.8094	6.57	5500	1.3651	0.0000	[528, 226, 117, 68]	[765, 701, 637, 573]	[69.01960784313725, 32.23965763195435, 18.367346938775512, 11.8673647469459]	0.0000	765	17012	0.0000	19.0
1.811	7.17	6000	1.3629	0.0000	[526, 225, 119, 69]	[768, 704, 640, 576]	[68.48958333333333, 31.960227272727273, 18.59375, 11.979166666666666]	0.0000	768	17012	0.0000	19.0
1.7635	7.77	6500	1.3451	0.0000	[529, 230, 124, 72]	[765, 701, 637, 573]	[69.15032679738562, 32.810271041369475, 19.46624803767661, 12.565445026178011]	0.0000	765	17012	0.0000	19.0
1.7782	8.36	7000	1.3376	0.0000	[530, 240, 132, 79]	[771, 707, 643, 579]	[68.74189364461738, 33.946251768033946, 20.52877138413686, 13.644214162348877]	0.0000	771	17012	0.0000	19.0
1.7528	8.96	7500	1.3305	0.0000	[543, 242, 129, 78]	[779, 715, 651, 587]	[69.70474967907573, 33.84615384615385, 19.81566820276498, 13.287904599659285]	0.0000	779	17012	0.0000	19.0
1.7365	9.56	8000	1.3273	0.0000	[532, 232, 123, 73]	[770, 706, 642, 578]	[69.0909090909091, 32.861189801699716, 19.1588785046729, 12.629757785467127]	0.0000	770	17012	0.0000	19.0
1.7212	10.16	8500	1.3247	0.0000	[544, 245, 136, 80]	[777, 713, 649, 585]	[70.01287001287001, 34.36185133239832, 20.955315870570107, 13.675213675213675]	0.0000	777	17012	0.0000	19.0
1.7027	10.75	9000	1.3229	0.0000	[548, 244, 131, 77]	[776, 712, 648, 584]	[70.61855670103093, 34.26966292134831, 20.21604938271605, 13.184931506849315]	0.0000	776	17012	0.0000	19.0
1.702	11.35	9500	1.3198	0.0000	[544, 247, 137, 82]	[774, 710, 646, 582]	[70.2842377260982, 34.7887323943662, 21.207430340557277, 14.0893470790378]	0.0000	774	17012	0.0000	19.0
1.7258	11.95	10000	1.3193	0.0000	[545, 246, 135, 80]	[777, 713, 649, 585]	[70.14157014157014, 34.50210378681627, 20.801232665639446, 13.675213675213675]	0.0000	777	17012	0.0000	19.0

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3