mt0-base_fine_lr5e-05_bs4_epoch20_wd0.01

This model is a fine-tuned version of bigscience/mt0-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
0.3613	1.0	157	0.0044
0.0162	2.0	314	0.0006
0.0114	3.0	471	0.0003
0.0108	4.0	628	0.0001
0.0092	5.0	785	0.0001
0.0091	6.0	942	0.0001
0.0031	7.0	1099	0.0001
0.001	8.0	1256	0.0000
0.0112	9.0	1413	0.0007
0.0049	10.0	1570	0.0000
0.0008	11.0	1727	0.0000
0.005	12.0	1884	0.0000
0.0043	13.0	2041	0.0000
0.0005	14.0	2198	0.0000
0.0007	15.0	2355	0.0000
0.0059	16.0	2512	0.0000
0.0003	17.0	2669	0.0000
0.0005	18.0	2826	0.0000
0.0004	19.0	2983	0.0000
0.0028	20.0	3140	0.0000

Framework versions

• Transformers 4.36.2
• Pytorch 2.0.1
• Datasets 2.16.1
• Tokenizers 0.15.0