Hugging Face's logo

MarkelFe
/
PoliticalSpeech2

Text Generation
Transformers
PyTorch
gpt2
text-generation-inference
Inference Endpoints
Model card Files
MarkelFe commited on
Commit
3ce4480
•
1 Parent(s): 1048045

Training in progress, step 100000

Browse files
Files changed (6) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +131 -3
  6. pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cb35c5ce4af04108203f479dae670d8d2387bc995e569ddd217192af4464df3
3
  size 995605445
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a1421f8e6cb5bb67425311aef9dda9661c917aab4a357a23ec44b2e3daab85
3
  size 995605445
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea5b57c1afcfb613703cab27e0ecdc612f9fb54011d8038bc39bf00d2f9efda7
3
  size 510398013
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f16473c3f1ed9f0581444acbd15664c381713c51843177e152cb72b1bd63766
3
  size 510398013
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c773d9b5ba19d40a8728dbc67546e0b3665d859a9b09fe4a7a38284b71fcc39
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:412df950fe881812d4df452ea4ec2fcd612c8449348c26dda4f3e5ddd7d9a49a
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c47f9fb86395a323bb61e82417c7ea6cc95d7fdffcd278133fc4fb35c1af521
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e61191d318bf68e1245e4fc98bbc55f1b8337c3d4b3f28a8adc2b1ca718b159b
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.1308836064021213,
5
- "global_step": 90000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -1164,11 +1164,139 @@
1164
  "eval_samples_per_second": 166.312,
1165
  "eval_steps_per_second": 20.793,
1166
  "step": 90000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1167
  }
1168
  ],
1169
  "max_steps": 633540,
1170
  "num_train_epochs": 15,
1171
- "total_flos": 1.9109545299072e+16,
1172
  "trial_name": null,
1173
  "trial_params": null
1174
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.367648451557913,
5
+ "global_step": 100000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
1164
  "eval_samples_per_second": 166.312,
1165
  "eval_steps_per_second": 20.793,
1166
  "step": 90000
1167
+ },
1168
+ {
1169
+ "epoch": 2.14,
1170
+ "learning_rate": 2.770628531742274e-05,
1171
+ "loss": 2.8933,
1172
+ "step": 90500
1173
+ },
1174
+ {
1175
+ "epoch": 2.15,
1176
+ "learning_rate": 2.7643148025381194e-05,
1177
+ "loss": 2.8842,
1178
+ "step": 91000
1179
+ },
1180
+ {
1181
+ "epoch": 2.17,
1182
+ "learning_rate": 2.758001073333965e-05,
1183
+ "loss": 2.8859,
1184
+ "step": 91500
1185
+ },
1186
+ {
1187
+ "epoch": 2.18,
1188
+ "learning_rate": 2.7516873441298108e-05,
1189
+ "loss": 2.8765,
1190
+ "step": 92000
1191
+ },
1192
+ {
1193
+ "epoch": 2.19,
1194
+ "learning_rate": 2.7453736149256563e-05,
1195
+ "loss": 2.8814,
1196
+ "step": 92500
1197
+ },
1198
+ {
1199
+ "epoch": 2.2,
1200
+ "learning_rate": 2.7390598857215018e-05,
1201
+ "loss": 2.8964,
1202
+ "step": 93000
1203
+ },
1204
+ {
1205
+ "epoch": 2.21,
1206
+ "learning_rate": 2.732746156517347e-05,
1207
+ "loss": 2.9037,
1208
+ "step": 93500
1209
+ },
1210
+ {
1211
+ "epoch": 2.23,
1212
+ "learning_rate": 2.7264324273131925e-05,
1213
+ "loss": 2.8856,
1214
+ "step": 94000
1215
+ },
1216
+ {
1217
+ "epoch": 2.24,
1218
+ "learning_rate": 2.7201186981090383e-05,
1219
+ "loss": 2.8979,
1220
+ "step": 94500
1221
+ },
1222
+ {
1223
+ "epoch": 2.25,
1224
+ "learning_rate": 2.713804968904884e-05,
1225
+ "loss": 2.8945,
1226
+ "step": 95000
1227
+ },
1228
+ {
1229
+ "epoch": 2.26,
1230
+ "learning_rate": 2.7074912397007294e-05,
1231
+ "loss": 2.9037,
1232
+ "step": 95500
1233
+ },
1234
+ {
1235
+ "epoch": 2.27,
1236
+ "learning_rate": 2.701177510496575e-05,
1237
+ "loss": 2.9087,
1238
+ "step": 96000
1239
+ },
1240
+ {
1241
+ "epoch": 2.28,
1242
+ "learning_rate": 2.6948637812924207e-05,
1243
+ "loss": 2.905,
1244
+ "step": 96500
1245
+ },
1246
+ {
1247
+ "epoch": 2.3,
1248
+ "learning_rate": 2.6885500520882662e-05,
1249
+ "loss": 2.9209,
1250
+ "step": 97000
1251
+ },
1252
+ {
1253
+ "epoch": 2.31,
1254
+ "learning_rate": 2.6822363228841117e-05,
1255
+ "loss": 2.895,
1256
+ "step": 97500
1257
+ },
1258
+ {
1259
+ "epoch": 2.32,
1260
+ "learning_rate": 2.6759225936799572e-05,
1261
+ "loss": 2.8885,
1262
+ "step": 98000
1263
+ },
1264
+ {
1265
+ "epoch": 2.33,
1266
+ "learning_rate": 2.6696088644758028e-05,
1267
+ "loss": 2.9038,
1268
+ "step": 98500
1269
+ },
1270
+ {
1271
+ "epoch": 2.34,
1272
+ "learning_rate": 2.6632951352716486e-05,
1273
+ "loss": 2.9143,
1274
+ "step": 99000
1275
+ },
1276
+ {
1277
+ "epoch": 2.36,
1278
+ "learning_rate": 2.656981406067494e-05,
1279
+ "loss": 2.9099,
1280
+ "step": 99500
1281
+ },
1282
+ {
1283
+ "epoch": 2.37,
1284
+ "learning_rate": 2.6506676768633396e-05,
1285
+ "loss": 2.9092,
1286
+ "step": 100000
1287
+ },
1288
+ {
1289
+ "epoch": 2.37,
1290
+ "eval_loss": 3.122859477996826,
1291
+ "eval_runtime": 113.0124,
1292
+ "eval_samples_per_second": 166.106,
1293
+ "eval_steps_per_second": 20.768,
1294
+ "step": 100000
1295
  }
1296
  ],
1297
  "max_steps": 633540,
1298
  "num_train_epochs": 15,
1299
+ "total_flos": 2.120856134976e+16,
1300
  "trial_name": null,
1301
  "trial_params": null
1302
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea5b57c1afcfb613703cab27e0ecdc612f9fb54011d8038bc39bf00d2f9efda7
3
  size 510398013
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f16473c3f1ed9f0581444acbd15664c381713c51843177e152cb72b1bd63766
3
  size 510398013