OpenDispatcher_v2_gpt35turbo_and_gpt4

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

• Loss: 0.5490

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: 16
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 3000

Training results

Training Loss	Epoch	Step	Validation Loss
0.6348	0.07	100	0.5852
0.5826	0.14	200	0.5731
0.5683	0.21	300	0.5681
0.5606	0.28	400	0.5640
0.5557	0.35	500	0.5705
0.5637	0.41	600	0.5647
0.5655	0.48	700	0.5569
0.5565	0.55	800	0.5747
0.5656	0.62	900	0.5570
0.5545	0.69	1000	0.5573
0.5474	0.76	1100	0.5595
0.5566	0.83	1200	0.5539
0.5738	0.9	1300	0.5499
0.5727	0.97	1400	0.5499
0.5463	1.04	1500	0.5683
0.5396	1.1	1600	0.5529
0.5529	1.17	1700	0.5603
0.5444	1.24	1800	0.5540
0.5388	1.31	1900	0.5652
0.5347	1.38	2000	0.5563
0.5303	1.45	2100	0.5542
0.5419	1.52	2200	0.5480
0.5344	1.59	2300	0.5512
0.5316	1.66	2400	0.5548
0.5487	1.73	2500	0.5500
0.5388	1.8	2600	0.5472
0.5423	1.86	2700	0.5469
0.5067	1.93	2800	0.5521
0.5236	2.0	2900	0.5482
0.5126	2.07	3000	0.5490

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Tokenizers 0.15.2