CLMBR/full-transformer-2

full2-transformer-2

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.8584

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: 32
• eval_batch_size: 32
• seed: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 3052726

Training results

Training Loss	Epoch	Step	Validation Loss
4.22	0.03	76320	4.1907
4.0167	1.03	152640	4.0230
3.9066	0.03	228960	3.9490
3.8414	1.03	305280	3.9087
3.7903	0.03	381600	3.8839
3.7508	1.03	457920	3.8681
3.7209	0.03	534240	3.8568
3.6915	1.03	610560	3.8505
3.6633	0.03	686880	3.8461
3.637	1.03	763200	3.8436
3.6162	0.03	839520	3.8419
3.5939	1.03	915840	3.8410
3.5798	0.03	992160	3.8408
3.5601	1.03	1068480	3.8400
3.5423	0.03	1144800	3.8404
3.5269	1.03	1221120	3.8419
3.5095	0.03	1297440	3.8427
3.4963	0.03	1373760	3.8442
3.4819	1.03	1450080	3.8454
3.4756	0.03	1526400	3.8473
3.464	1.03	1602720	3.8481
3.4565	0.03	1679040	3.8492
3.4517	1.03	1755360	3.8505
3.442	0.03	1831680	3.8521
3.4276	1.03	1908000	3.8537
3.4171	0.03	1984320	3.8547
3.405	1.03	2060640	3.8551
3.3944	0.03	2136960	3.8572
3.3867	1.03	2213280	3.8572
3.3758	0.03	2289600	3.8585
3.3616	1.03	2365920	3.8600
3.3521	0.03	2442240	3.8597
3.3394	0.03	2518560	3.8603
3.331	1.03	2594880	3.8607
3.3193	0.03	2671200	3.8603
3.316	0.03	2747520	3.8615
3.308	1.03	2823840	3.8602
3.3024	0.03	2900160	3.8606
3.3017	0.03	2976480	3.8594
3.296	1.02	3052726	3.8584

Framework versions

• Transformers 4.33.3
• Pytorch 2.0.1
• Datasets 2.12.0
• Tokenizers 0.13.3