mt0-base_IA3_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: 0.0587

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
0.5794	1.0	157	0.3078
0.5388	2.0	314	0.2805
0.5028	3.0	471	0.2418
0.4281	4.0	628	0.2026
0.3694	5.0	785	0.1730
0.3233	6.0	942	0.1490
0.295	7.0	1099	0.1303
0.2743	8.0	1256	0.1150
0.2312	9.0	1413	0.1027
0.2173	10.0	1570	0.0931
0.1977	11.0	1727	0.0853
0.189	12.0	1884	0.0790
0.1668	13.0	2041	0.0738
0.1703	14.0	2198	0.0695
0.1624	15.0	2355	0.0660
0.1532	16.0	2512	0.0632
0.1448	17.0	2669	0.0612
0.1487	18.0	2826	0.0598
0.1517	19.0	2983	0.0590
0.1418	20.0	3140	0.0587

Framework versions

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.0.1
• Datasets 2.16.1
• Tokenizers 0.15.0