Hugging Face's logo

circlemachinelearning
/
bart-email-multitask

Transformers
Safetensors
bart
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
rosypossyyyy commited on
Commit
5403ed2
·
verified ·
1 Parent(s): b86fa7c

Training in progress, step 1500, checkpoint

Browse files
Files changed (6) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +89 -6
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8643f86078135c17503f042064a248fd2dfd23291d808f114b85a9adcf72b194
3
  size 1625422896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2d009fa9acb2b78f813d89270550f919a3f4b577a7460370dfe12fa03ff7af2
3
  size 1625422896
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:898d52a1935671e63dc5f4c9454b31e201c1cde7bfeebd8fe1e249bc27887e03
3
  size 3250759392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2947112888e0b0a163210d845429170c50382af84dbf994949e4e6f9ab23162a
3
  size 3250759392
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a25f0989e8e91af9e8637f85210bc8171a9ace36462fb90ce2e6d3e8f7ae2fa2
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4799eb2d919a7e0ac96b4d1b7ad46d7dd1d0d16fcd886aff21cf516bc01cd21
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59e669c259ab78606714a8e6e7364a6b5f41fb1fdae56b4e6aa576ada4060cbf
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456186d80ba1cb08cf09751e950cd6ffaa49f7521ab8872f1128630a6572e66b
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c5955ff7ae3c292679cb2d15dfab21a83841dbd226cd7e259de6ef2a4c905fc
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b44fb2a9542e90532b93ebac4a5e8666f98d6d7698a2bf80999186ee0ee3983
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 1000,
3
- "best_metric": 49.95,
4
- "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-1000",
5
- "epoch": 0.34521446448606197,
6
  "eval_steps": 500,
7
- "global_step": 1000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -174,6 +174,89 @@
174
  "eval_samples_per_second": 1.702,
175
  "eval_steps_per_second": 0.426,
176
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
177
  }
178
  ],
179
  "logging_steps": 50,
@@ -202,7 +285,7 @@
202
  "attributes": {}
203
  }
204
  },
205
- "total_flos": 3.4335063539712e+16,
206
  "train_batch_size": 4,
207
  "trial_name": null,
208
  "trial_params": null
 
1
  {
2
+ "best_global_step": 1500,
3
+ "best_metric": 50.35,
4
+ "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-1500",
5
+ "epoch": 0.517821696729093,
6
  "eval_steps": 500,
7
+ "global_step": 1500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
174
  "eval_samples_per_second": 1.702,
175
  "eval_steps_per_second": 0.426,
176
  "step": 1000
177
+ },
178
+ {
179
+ "epoch": 0.3624751877103651,
180
+ "grad_norm": 4.618715286254883,
181
+ "learning_rate": 4.241151233464427e-06,
182
+ "loss": 0.4252,
183
+ "step": 1050
184
+ },
185
+ {
186
+ "epoch": 0.3797359109346682,
187
+ "grad_norm": 3.20849871635437,
188
+ "learning_rate": 4.19646049338577e-06,
189
+ "loss": 0.4157,
190
+ "step": 1100
191
+ },
192
+ {
193
+ "epoch": 0.39699663415897124,
194
+ "grad_norm": 2.707479238510132,
195
+ "learning_rate": 4.151769753307115e-06,
196
+ "loss": 0.4099,
197
+ "step": 1150
198
+ },
199
+ {
200
+ "epoch": 0.41425735738327435,
201
+ "grad_norm": 3.7561733722686768,
202
+ "learning_rate": 4.107079013228459e-06,
203
+ "loss": 0.3867,
204
+ "step": 1200
205
+ },
206
+ {
207
+ "epoch": 0.43151808060757746,
208
+ "grad_norm": 3.146683692932129,
209
+ "learning_rate": 4.062388273149804e-06,
210
+ "loss": 0.3949,
211
+ "step": 1250
212
+ },
213
+ {
214
+ "epoch": 0.44877880383188057,
215
+ "grad_norm": 2.949275255203247,
216
+ "learning_rate": 4.017697533071148e-06,
217
+ "loss": 0.4018,
218
+ "step": 1300
219
+ },
220
+ {
221
+ "epoch": 0.4660395270561837,
222
+ "grad_norm": 3.40734601020813,
223
+ "learning_rate": 3.973006792992492e-06,
224
+ "loss": 0.4169,
225
+ "step": 1350
226
+ },
227
+ {
228
+ "epoch": 0.48330025028048673,
229
+ "grad_norm": 3.736387014389038,
230
+ "learning_rate": 3.928316052913836e-06,
231
+ "loss": 0.3897,
232
+ "step": 1400
233
+ },
234
+ {
235
+ "epoch": 0.5005609735047899,
236
+ "grad_norm": 3.2508416175842285,
237
+ "learning_rate": 3.883625312835181e-06,
238
+ "loss": 0.4062,
239
+ "step": 1450
240
+ },
241
+ {
242
+ "epoch": 0.517821696729093,
243
+ "grad_norm": 2.803189754486084,
244
+ "learning_rate": 3.838934572756525e-06,
245
+ "loss": 0.4158,
246
+ "step": 1500
247
+ },
248
+ {
249
+ "epoch": 0.517821696729093,
250
+ "eval_gen_len": 54.936474694589876,
251
+ "eval_loss": 0.5606315732002258,
252
+ "eval_rouge1": 50.35,
253
+ "eval_rouge2": 36.21,
254
+ "eval_rougeL": 43.87,
255
+ "eval_rougeLsum": 44.34,
256
+ "eval_runtime": 3383.5495,
257
+ "eval_samples_per_second": 1.693,
258
+ "eval_steps_per_second": 0.424,
259
+ "step": 1500
260
  }
261
  ],
262
  "logging_steps": 50,
 
285
  "attributes": {}
286
  }
287
  },
288
+ "total_flos": 5.1502595309568e+16,
289
  "train_batch_size": 4,
290
  "trial_name": null,
291
  "trial_params": null