recipe-dialogpt-medium-500k – AI Model by samyh | AlphaNeural AI

You can deploy this model and start earning money today!

samyh/
recipe-dialogpt-medium-500k

like

0

generated_from_trainer

microsoft/DialoGPT-medium

Views

No views yet

recipe-dialogpt-medium-500k

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

Loss: 1.2151

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
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.6271	0.03	1000	1.5619
1.512	0.07	2000	1.4689
1.463	0.1	3000	1.4210
1.4411	0.13	4000	1.3873
1.4148	0.17	5000	1.3626
1.3873	0.2	6000	1.3434
1.3548	0.24	7000	1.3309
1.3486	0.27	8000	1.3153
1.3452	0.3	9000	1.3047
1.328	0.34	10000	1.2952
1.3209	0.37	11000	1.2865
1.2906	0.4	12000	1.2776
1.3143	0.44	13000	1.2710
1.3003	0.47	14000	1.2640
1.275	0.51	15000	1.2591
1.2892	0.54	16000	1.2535
1.2883	0.57	17000	1.2479
1.274	0.61	18000	1.2440
1.2658	0.64	19000	1.2395
1.2667	0.67	20000	1.2356
1.2602	0.71	21000	1.2324
1.2633	0.74	22000	1.2298
1.2544	0.77	23000	1.2262
1.265	0.81	24000	1.2235
1.26	0.84	25000	1.2210
1.2501	0.88	26000	1.2192
1.2552	0.91	27000	1.2172
1.2638	0.94	28000	1.2159
1.2551	0.98	29000	1.2151

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.14.0
Tokenizers 0.15.2