dialogpt-medium-ear_1-hs_cn_decay

Bainbridge/dialogpt-medium-ear_1-hs_cn_decay

dialogpt-medium-ear_1-hs_cn_decay is a text generation model from Bainbridge. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

4% of all-time downloads

All-time downloads

252

Public

Repo size

13 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.4 GB · 100%

At a glance

Task: Text Generation
Library: transformers
License: mit
Model type: gpt2
Access: Public
Created: Apr 6, 2023
Updated: Apr 6, 2023
SHA: 75d44848

Try a prompt

Model card

From the Hugging Face model README

dialogpt-medium-ear_1-hs_cn_decay

This model is a fine-tuned version of microsoft/DialoGPT-medium on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5666

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: 21
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
6.3092	0.01	10	9.8250
5.7405	0.02	20	8.9631
2.3101	0.03	30	4.2371
-1.1908	0.04	40	1.2645
-1.8271	0.05	50	1.0242
-1.6416	0.06	60	0.9279
-1.8192	0.07	70	0.8478
-1.8256	0.08	80	0.7994
-1.9314	0.09	90	0.7673
-1.8831	0.1	100	0.7432
-1.7094	0.11	110	0.7269
-1.8073	0.12	120	0.7155
-1.8911	0.13	130	0.7037
-1.786	0.14	140	0.6932
-2.0278	0.15	150	0.6846
-1.7418	0.16	160	0.6769
-2.0351	0.17	170	0.6691
-1.8694	0.18	180	0.6612
-1.7626	0.19	190	0.6551
-1.7849	0.2	200	0.6492
-2.0599	0.21	210	0.6446
-1.9591	0.22	220	0.6401
-1.9246	0.23	230	0.6359
-1.8881	0.24	240	0.6334
-1.9835	0.25	250	0.6306
-1.8657	0.26	260	0.6264
-1.9111	0.27	270	0.6225
-1.9939	0.28	280	0.6198
-2.0166	0.29	290	0.6170
-1.755	0.3	300	0.6144
-1.8769	0.31	310	0.6118
-1.9875	0.32	320	0.6107
-1.8674	0.33	330	0.6091
-1.8181	0.34	340	0.6079
-1.8287	0.35	350	0.6071
-1.8231	0.36	360	0.6043
-1.745	0.37	370	0.6030
-1.7558	0.38	380	0.6011
-1.9552	0.39	390	0.6009
-1.7529	0.4	400	0.5994
-1.8206	0.41	410	0.5984
-1.7374	0.42	420	0.5972
-1.6562	0.43	430	0.5952
-1.6346	0.44	440	0.5932
-1.7629	0.45	450	0.5933
-1.8789	0.46	460	0.5939
-1.7258	0.47	470	0.5912
-1.8586	0.48	480	0.5896
-1.8896	0.49	490	0.5890
-1.7129	0.5	500	0.5876
-1.7824	0.51	510	0.5860
-1.725	0.52	520	0.5855
-1.7602	0.53	530	0.5849
-1.6211	0.54	540	0.5848
-1.8583	0.55	550	0.5842
-1.5637	0.56	560	0.5832
-1.5247	0.57	570	0.5830
-1.7575	0.58	580	0.5818
-1.6036	0.59	590	0.5809
-1.7476	0.6	600	0.5802
-1.5963	0.61	610	0.5784
-1.6185	0.62	620	0.5778
-1.543	0.63	630	0.5770
-1.4096	0.64	640	0.5765
-1.6566	0.65	650	0.5771
-1.6998	0.66	660	0.5765
-1.5556	0.67	670	0.5762
-1.5735	0.68	680	0.5756
-1.4755	0.69	690	0.5750
-1.631	0.7	700	0.5756
-1.4281	0.71	710	0.5751
-1.5514	0.72	720	0.5739
-1.4284	0.73	730	0.5736
-1.5609	0.74	740	0.5729
-1.5762	0.75	750	0.5727
-1.5067	0.76	760	0.5719
-1.4276	0.77	770	0.5710
-1.4509	0.78	780	0.5707
-1.5881	0.79	790	0.5699
-1.5085	0.8	800	0.5696
-1.5048	0.81	810	0.5694
-1.4063	0.82	820	0.5694
-1.6457	0.83	830	0.5689
-1.357	0.84	840	0.5683
-1.5625	0.85	850	0.5684
-1.3136	0.86	860	0.5680
-1.3961	0.87	870	0.5669
-1.322	0.88	880	0.5664
-1.3932	0.89	890	0.5662
-1.3923	0.9	900	0.5665
-1.4139	0.91	910	0.5675
-1.4337	0.92	920	0.5666

Framework versions

Transformers 4.27.4
Pytorch 1.11.0+cu113
Datasets 2.11.0
Tokenizers 0.12.1

Task: Text Generation
Library: transformers
Type: gpt2
License: mit
Created: Apr 6, 2023
Updated: Apr 6, 2023