Hugging Face's logo

nbtpj
/
bart-base-mqa-fine-tune

Text2Text Generation
Transformers
PyTorch
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
nbtpj commited on
Commit
5c6665a
·
1 Parent(s): e1c32fa

Training in progress, step 5000

Browse files
Files changed (7) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +2 -2
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +153 -3
  6. pytorch_model.bin +1 -1
  7. runs/Jan01_04-28-26_6ea5fb75c867/events.out.tfevents.1672547319.6ea5fb75c867.24.0 +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ec2c97bb156c6d257f8577705f2d4445aee082bdebd9da6f08cb492c9671da6
3
  size 1115513717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26877d744980b431b76d3e2c4397501813f741bfd4d56d3d01913dd7a72edf84
3
  size 1115513717
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:693dfa4e4e56bac990dac21b8fe757510daaf51de65de333584544574c1bdc24
3
  size 557969145
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3788c718c873a5a631cbd6930b47d0c500358621cac639d4e9bc55c21520493c
3
  size 557969145
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdb0fe4905a7633b14383ef952b93a78452b17a47d82a1f59d15c9573967fd13
3
- size 15459
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e580d1df17d3fc5663dd4d2a79e58e94c4e8b7aa63ccfd53d9b69366e2d1f1a
3
+ size 15523
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9d0af232cb02e9821619a36e3205ece6ae1dbe2e922db09496bf05b6937c641
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c57b88e1b4f27dad7565a46df4569bd671ad83f261df06872ce384b18b5f02c6
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.2872572676088705,
5
- "global_step": 2500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -156,11 +156,161 @@
156
  "learning_rate": 4.202093706115154e-05,
157
  "loss": 2.5994,
158
  "step": 2500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
159
  }
160
  ],
161
  "max_steps": 15666,
162
  "num_train_epochs": 2,
163
- "total_flos": 9894917569904640.0,
164
  "trial_name": null,
165
  "trial_params": null
166
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.574514535217741,
5
+ "global_step": 5000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
156
  "learning_rate": 4.202093706115154e-05,
157
  "loss": 2.5994,
158
  "step": 2500
159
+ },
160
+ {
161
+ "epoch": 0.3,
162
+ "learning_rate": 4.17017745435976e-05,
163
+ "loss": 2.6479,
164
+ "step": 2600
165
+ },
166
+ {
167
+ "epoch": 0.31,
168
+ "learning_rate": 4.1382612026043666e-05,
169
+ "loss": 2.7357,
170
+ "step": 2700
171
+ },
172
+ {
173
+ "epoch": 0.32,
174
+ "learning_rate": 4.1063449508489726e-05,
175
+ "loss": 2.6819,
176
+ "step": 2800
177
+ },
178
+ {
179
+ "epoch": 0.33,
180
+ "learning_rate": 4.0744286990935785e-05,
181
+ "loss": 2.5451,
182
+ "step": 2900
183
+ },
184
+ {
185
+ "epoch": 0.34,
186
+ "learning_rate": 4.0425124473381845e-05,
187
+ "loss": 2.6343,
188
+ "step": 3000
189
+ },
190
+ {
191
+ "epoch": 0.36,
192
+ "learning_rate": 4.010596195582791e-05,
193
+ "loss": 2.5168,
194
+ "step": 3100
195
+ },
196
+ {
197
+ "epoch": 0.37,
198
+ "learning_rate": 3.978679943827397e-05,
199
+ "loss": 2.5881,
200
+ "step": 3200
201
+ },
202
+ {
203
+ "epoch": 0.38,
204
+ "learning_rate": 3.946763692072003e-05,
205
+ "loss": 2.6411,
206
+ "step": 3300
207
+ },
208
+ {
209
+ "epoch": 0.39,
210
+ "learning_rate": 3.9148474403166096e-05,
211
+ "loss": 2.5901,
212
+ "step": 3400
213
+ },
214
+ {
215
+ "epoch": 0.4,
216
+ "learning_rate": 3.8829311885612155e-05,
217
+ "loss": 2.5842,
218
+ "step": 3500
219
+ },
220
+ {
221
+ "epoch": 0.41,
222
+ "learning_rate": 3.851014936805822e-05,
223
+ "loss": 2.5436,
224
+ "step": 3600
225
+ },
226
+ {
227
+ "epoch": 0.43,
228
+ "learning_rate": 3.819098685050428e-05,
229
+ "loss": 2.6021,
230
+ "step": 3700
231
+ },
232
+ {
233
+ "epoch": 0.44,
234
+ "learning_rate": 3.787182433295034e-05,
235
+ "loss": 2.6307,
236
+ "step": 3800
237
+ },
238
+ {
239
+ "epoch": 0.45,
240
+ "learning_rate": 3.75526618153964e-05,
241
+ "loss": 2.5632,
242
+ "step": 3900
243
+ },
244
+ {
245
+ "epoch": 0.46,
246
+ "learning_rate": 3.723349929784246e-05,
247
+ "loss": 2.5933,
248
+ "step": 4000
249
+ },
250
+ {
251
+ "epoch": 0.47,
252
+ "learning_rate": 3.6914336780288525e-05,
253
+ "loss": 2.5458,
254
+ "step": 4100
255
+ },
256
+ {
257
+ "epoch": 0.48,
258
+ "learning_rate": 3.659517426273459e-05,
259
+ "loss": 2.5212,
260
+ "step": 4200
261
+ },
262
+ {
263
+ "epoch": 0.49,
264
+ "learning_rate": 3.627601174518065e-05,
265
+ "loss": 2.4532,
266
+ "step": 4300
267
+ },
268
+ {
269
+ "epoch": 0.51,
270
+ "learning_rate": 3.595684922762671e-05,
271
+ "loss": 2.5134,
272
+ "step": 4400
273
+ },
274
+ {
275
+ "epoch": 0.52,
276
+ "learning_rate": 3.563768671007277e-05,
277
+ "loss": 2.5368,
278
+ "step": 4500
279
+ },
280
+ {
281
+ "epoch": 0.53,
282
+ "learning_rate": 3.531852419251883e-05,
283
+ "loss": 2.5547,
284
+ "step": 4600
285
+ },
286
+ {
287
+ "epoch": 0.54,
288
+ "learning_rate": 3.4999361674964895e-05,
289
+ "loss": 2.4786,
290
+ "step": 4700
291
+ },
292
+ {
293
+ "epoch": 0.55,
294
+ "learning_rate": 3.4680199157410954e-05,
295
+ "loss": 2.5377,
296
+ "step": 4800
297
+ },
298
+ {
299
+ "epoch": 0.56,
300
+ "learning_rate": 3.436103663985702e-05,
301
+ "loss": 2.5462,
302
+ "step": 4900
303
+ },
304
+ {
305
+ "epoch": 0.57,
306
+ "learning_rate": 3.404187412230308e-05,
307
+ "loss": 2.5644,
308
+ "step": 5000
309
  }
310
  ],
311
  "max_steps": 15666,
312
  "num_train_epochs": 2,
313
+ "total_flos": 1.976059637121024e+16,
314
  "trial_name": null,
315
  "trial_params": null
316
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:693dfa4e4e56bac990dac21b8fe757510daaf51de65de333584544574c1bdc24
3
  size 557969145
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3788c718c873a5a631cbd6930b47d0c500358621cac639d4e9bc55c21520493c
3
  size 557969145
runs/Jan01_04-28-26_6ea5fb75c867/events.out.tfevents.1672547319.6ea5fb75c867.24.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6d1cd4831e53469a937a15316e8a11e633699d723260e7dab9000b8504aee42
3
- size 8760
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1294decc8c9ef75cd30d8852ab459f4a1f68f6df2d4da45e86410f825db4f1d7
3
+ size 12685