julioman122

This model is a fine-tuned version of openai-community/gpt2-medium on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0712

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: 0.001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
4.7058	0.0109	11	4.6079
3.9486	0.0219	22	3.7382
3.5783	0.0328	33	3.0404
2.6835	0.0438	44	2.6246
2.4222	0.0547	55	2.4352
2.4473	0.0657	66	2.2854
2.2547	0.0766	77	2.2369
2.3009	0.0876	88	2.1463
2.0201	0.0985	99	2.0739
1.9644	0.1095	110	1.9892
1.8807	0.1204	121	1.8742
1.8819	0.1313	132	1.8135
1.8239	0.1423	143	1.7054
1.6466	0.1532	154	1.6327
1.7081	0.1642	165	1.7165
1.6211	0.1751	176	1.5426
1.5935	0.1861	187	1.5338
1.4733	0.1970	198	1.5042
1.3999	0.2080	209	1.4885
1.4967	0.2189	220	1.4794
1.4968	0.2299	231	1.4542
1.4162	0.2408	242	1.4161
1.5097	0.2517	253	1.4026
1.4211	0.2627	264	1.3943
1.4140	0.2736	275	1.3709
1.2964	0.2846	286	1.3717
1.3270	0.2955	297	1.3514
1.3149	0.3065	308	1.3302
1.3435	0.3174	319	1.3173
1.4001	0.3284	330	1.3217
1.3066	0.3393	341	1.3019
1.3499	0.3502	352	1.2936
1.3636	0.3612	363	1.2877
1.2976	0.3721	374	1.2810
1.2853	0.3831	385	1.2709
1.3444	0.3940	396	1.2513
1.1589	0.4050	407	1.2455
1.1139	0.4159	418	1.2340
1.3532	0.4269	429	1.2226
1.2268	0.4378	440	1.2209
1.3001	0.4488	451	1.2192
1.3120	0.4597	462	1.2180
1.3207	0.4706	473	1.2122
1.3011	0.4816	484	1.2044
1.2147	0.4925	495	1.1963
1.2448	0.5035	506	1.1894
1.2330	0.5144	517	1.1839
1.2105	0.5254	528	1.1751
1.2583	0.5363	539	1.1746
1.3129	0.5473	550	1.1656
1.1487	0.5582	561	1.1599
1.1758	0.5692	572	1.1601
1.2356	0.5801	583	1.1588
1.2493	0.5910	594	1.1498
1.2088	0.6020	605	1.1418
1.1203	0.6129	616	1.1405
1.2530	0.6239	627	1.1362
1.2425	0.6348	638	1.1288
1.2036	0.6458	649	1.1281
1.1254	0.6567	660	1.1261
1.0665	0.6677	671	1.1204
1.1175	0.6786	682	1.1188
1.2206	0.6896	693	1.1148
1.2102	0.7005	704	1.1067
1.1407	0.7114	715	1.1113
1.1669	0.7224	726	1.1037
1.1661	0.7333	737	1.1037
1.0426	0.7443	748	1.1007
1.1524	0.7552	759	1.0980
1.0919	0.7662	770	1.0920
1.1114	0.7771	781	1.0906
1.0876	0.7881	792	1.0907
1.1860	0.7990	803	1.0883
1.1940	0.8100	814	1.0865
1.0855	0.8209	825	1.0839
1.0433	0.8318	836	1.0814
1.1601	0.8428	847	1.0795
1.1156	0.8537	858	1.0774
1.1035	0.8647	869	1.0767
1.0335	0.8756	880	1.0763
1.1359	0.8866	891	1.0754
1.1049	0.8975	902	1.0734
1.0392	0.9085	913	1.0731
1.0587	0.9194	924	1.0740
1.0991	0.9303	935	1.0736
1.1115	0.9413	946	1.0725
1.1474	0.9522	957	1.0718
1.1920	0.9632	968	1.0715
1.0279	0.9741	979	1.0713
1.0404	0.9851	990	1.0712
1.0508	0.9960	1001	1.0712
1.1812	1.0	1005	1.0712

Framework versions

• Transformers 5.15.0
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2