CoolFace
Modelpublic

gjonesQ02/StatementOfWork_Generator_Omega_BS_512

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes17downloads
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. -->

StatementOfWorkGeneratorOmegaBS512

This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.7165

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: 2e-05
  • —trainbatchsize: 50
  • —evalbatchsize: 50
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 150

Training results

Training LossEpochStepValidation Loss
No log1.040.8137
No log2.080.7930
No log3.0120.7915
No log4.0160.7846
No log5.0200.7785
No log6.0240.7751
No log7.0280.7724
No log8.0320.7687
No log9.0360.7654
No log10.0400.7630
No log11.0440.7615
No log12.0480.7604
No log13.0520.7595
No log14.0560.7572
No log15.0600.7559
No log16.0640.7549
No log17.0680.7541
No log18.0720.7541
No log19.0760.7522
No log20.0800.7496
No log21.0840.7485
No log22.0880.7492
No log23.0920.7481
No log24.0960.7469
No log25.01000.7447
No log26.01040.7436
No log27.01080.7435
No log28.01120.7431
No log29.01160.7426
No log30.01200.7418
No log31.01240.7414
No log32.01280.7409
No log33.01320.7393
No log34.01360.7393
No log35.01400.7392
No log36.01440.7368
No log37.01480.7361
No log38.01520.7366
No log39.01560.7367
No log40.01600.7349
No log41.01640.7344
No log42.01680.7341
No log43.01720.7328
No log44.01760.7317
No log45.01800.7314
No log46.01840.7325
No log47.01880.7325
No log48.01920.7311
No log49.01960.7301
No log50.02000.7306
No log51.02040.7305
No log52.02080.7301
No log53.02120.7286
No log54.02160.7266
No log55.02200.7275
No log56.02240.7292
No log57.02280.7288
No log58.02320.7275
No log59.02360.7263
No log60.02400.7265
No log61.02440.7269
No log62.02480.7271
No log63.02520.7262
No log64.02560.7252
No log65.02600.7262
No log66.02640.7251
No log67.02680.7243
No log68.02720.7241
No log69.02760.7248
No log70.02800.7238
No log71.02840.7227
No log72.02880.7234
No log73.02920.7233
No log74.02960.7222
No log75.03000.7213
No log76.03040.7223
No log77.03080.7230
No log78.03120.7226
No log79.03160.7222
No log80.03200.7220
No log81.03240.7222
No log82.03280.7220
No log83.03320.7209
No log84.03360.7202
No log85.03400.7208
No log86.03440.7218
No log87.03480.7214
No log88.03520.7195
No log89.03560.7190
No log90.03600.7199
No log91.03640.7213
No log92.03680.7207
No log93.03720.7198
No log94.03760.7198
No log95.03800.7200
No log96.03840.7199
No log97.03880.7198
No log98.03920.7198
No log99.03960.7194
No log100.04000.7192
No log101.04040.7187
No log102.04080.7181
No log103.04120.7186
No log104.04160.7192
No log105.04200.7184
No log106.04240.7178
No log107.04280.7181
No log108.04320.7188
No log109.04360.7192
No log110.04400.7189
No log111.04440.7186
No log112.04480.7183
No log113.04520.7181
No log114.04560.7184
No log115.04600.7187
No log116.04640.7186
No log117.04680.7180
No log118.04720.7178
No log119.04760.7176
No log120.04800.7175
No log121.04840.7171
No log122.04880.7170
No log123.04920.7172
No log124.04960.7173
0.2218125.05000.7174
0.2218126.05040.7173
0.2218127.05080.7174
0.2218128.05120.7174
0.2218129.05160.7174
0.2218130.05200.7171
0.2218131.05240.7167
0.2218132.05280.7166
0.2218133.05320.7169
0.2218134.05360.7171
0.2218135.05400.7172
0.2218136.05440.7171
0.2218137.05480.7168
0.2218138.05520.7166
0.2218139.05560.7165
0.2218140.05600.7165
0.2218141.05640.7165
0.2218142.05680.7165
0.2218143.05720.7166
0.2218144.05760.7166
0.2218145.05800.7166
0.2218146.05840.7166
0.2218147.05880.7166
0.2218148.05920.7166
0.2218149.05960.7165
0.2218150.06000.7165

Framework versions

  • —Transformers 4.38.2
  • —Pytorch 2.2.1+cu121
  • —Datasets 2.18.0
  • —Tokenizers 0.15.2