slack-emoji-generator

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3188

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: 4
• seed: 42
• optimizer: Use adamw_torch 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: 50
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
18.1521	2.5	10	17.1681
15.4149	5.0	20	11.3836
10.3577	7.5	30	6.3989
4.866	10.0	40	1.3543
2.276	12.5	50	0.6950
1.4199	15.0	60	0.6021
1.0376	17.5	70	0.5347
0.7419	20.0	80	0.5178
0.7222	22.5	90	0.4806
0.6657	25.0	100	0.4621
0.6824	27.5	110	0.4357
0.6017	30.0	120	0.4310
0.5891	32.5	130	0.4146
0.5646	35.0	140	0.3816
0.5527	37.5	150	0.3708
0.5031	40.0	160	0.3625
0.4712	42.5	170	0.3439
0.4247	45.0	180	0.3290
0.4768	47.5	190	0.3219
0.4949	50.0	200	0.3188

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.0+cu121
• Tokenizers 0.20.3