Team Ai
Modelpublic

zfir/typescriptmate-500000

sourceHugging Facemitupdated 1y agoView on Hugging Face
0likes12downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

typescriptmate-500000

This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.1136

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
  • —trainbatchsize: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 8
  • —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —num_epochs: 5

Training results

Training LossEpochStepValidation Loss
1.80110.05185001.6532
1.6780.103610001.5555
1.59420.155515001.5039
1.55680.207320001.4671
1.55950.259125001.4372
1.51260.310930001.4117
1.48060.362835001.3926
1.44510.414640001.3764
1.42740.466445001.3599
1.4330.518250001.3466
1.41150.570155001.3372
1.43280.621960001.3246
1.38040.673765001.3123
1.35960.725570001.3050
1.3930.777475001.2951
1.31760.829280001.2860
1.3530.881085001.2762
1.36950.932890001.2723
1.34060.984795001.2651
1.34881.0365100001.2578
1.31481.0883105001.2539
1.31041.1401110001.2470
1.28221.1920115001.2443
1.29541.2438120001.2400
1.25891.2956125001.2317
1.27421.3474130001.2277
1.26251.3993135001.2251
1.22971.4511140001.2192
1.24581.5029145001.2148
1.24291.5547150001.2118
1.26631.6066155001.2079
1.24591.6584160001.2036
1.281.7102165001.2020
1.25991.7620170001.1995
1.21021.8138175001.1938
1.23851.8657180001.1904
1.22581.9175185001.1882
1.23031.9693190001.1858
1.21192.0211195001.1837
1.23052.0730200001.1791
1.20132.1248205001.1779
1.19692.1766210001.1743
1.20092.2284215001.1737
1.20052.2803220001.1710
1.18022.3321225001.1694
1.22282.3839230001.1672
1.2012.4357235001.1637
1.18362.4876240001.1611
1.19182.5394245001.1594
1.19312.5912250001.1581
1.19892.6430255001.1550
1.18292.6949260001.1533
1.17032.7467265001.1531
1.18342.7985270001.1501
1.14862.8503275001.1483
1.14812.9022280001.1457
1.17112.9540285001.1457
1.14663.0058290001.1430
1.14093.0576295001.1413
1.15353.1095300001.1407
1.13093.1613305001.1397
1.15523.2131310001.1392
1.13163.2649315001.1364
1.16553.3167320001.1353
1.14633.3686325001.1358
1.14753.4204330001.1331
1.1553.4722335001.1319
1.14373.5240340001.1307
1.11523.5759345001.1310
1.12373.6277350001.1298
1.16173.6795355001.1276
1.12023.7313360001.1266
1.14043.7832365001.1262
1.13313.8350370001.1244
1.13663.8868375001.1238
1.11543.9386380001.1235
1.14353.9905385001.1224
1.10844.0423390001.1209
1.1154.0941395001.1223
1.10774.1459400001.1209
1.08674.1978405001.1197
1.10494.2496410001.1191
1.09764.3014415001.1199
1.11994.3532420001.1183
1.1094.4051425001.1172
1.11194.4569430001.1168
1.10064.5087435001.1165
1.12614.5605440001.1168
1.06764.6124445001.1165
1.13584.6642450001.1160
1.13844.7160455001.1151
1.09744.7678460001.1152
1.13574.8197465001.1143
1.11864.8715470001.1142
1.11564.9233475001.1140
1.11554.9751480001.1136

Framework versions

  • —Transformers 4.52.4
  • —Pytorch 2.6.0+cu124
  • —Datasets 3.6.0
  • —Tokenizers 0.21.1