kooff11 commited on
Commit
3df8967
·
verified ·
1 Parent(s): d4bb0bf

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c1f6fdb340a7842c3b9d36197925fb5bf38a2e7f9b94b787db9723351428b75
3
  size 61392180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf58058fb76a002bc6efae5178f7a20c69d69a804fafc9fe9c7cd72a855a66db
3
  size 61392180
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1267e27514ca082f15efcd9adc6d0200682d3f44164420487cb0111523d9e10d
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c01dc6b6b79bb1a145c9d5bca87caf8173c23bcb65b2b0baa3ce464f2a62ef30
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c647c105ea30c8bac469833b3ddfe277a90f35d8ed9ca5a5875bd90949ac4ce9
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da99bab535c7b2762cd9da2c665522b87dc475a603b4ea3c8b905af8261224b
3
  size 14512
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.3652326602282704,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -213,6 +213,105 @@
213
  "eval_samples_per_second": 15.548,
214
  "eval_steps_per_second": 3.887,
215
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
216
  }
217
  ],
218
  "logging_steps": 1,
@@ -232,7 +331,7 @@
232
  "attributes": {}
233
  }
234
  },
235
- "total_flos": 2.293940057108644e+17,
236
  "train_batch_size": 2,
237
  "trial_name": null,
238
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.5478489903424056,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
213
  "eval_samples_per_second": 15.548,
214
  "eval_steps_per_second": 3.887,
215
  "step": 26
216
+ },
217
+ {
218
+ "epoch": 0.37928007023705007,
219
+ "grad_norm": NaN,
220
+ "learning_rate": 4.6729843538492847e-05,
221
+ "loss": 0.0,
222
+ "step": 27
223
+ },
224
+ {
225
+ "epoch": 0.3933274802458297,
226
+ "grad_norm": NaN,
227
+ "learning_rate": 4.347369038899744e-05,
228
+ "loss": 0.0,
229
+ "step": 28
230
+ },
231
+ {
232
+ "epoch": 0.4073748902546093,
233
+ "grad_norm": NaN,
234
+ "learning_rate": 4.0245483899193595e-05,
235
+ "loss": 0.0,
236
+ "step": 29
237
+ },
238
+ {
239
+ "epoch": 0.42142230026338895,
240
+ "grad_norm": NaN,
241
+ "learning_rate": 3.705904774487396e-05,
242
+ "loss": 0.0,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 0.4354697102721686,
247
+ "grad_norm": NaN,
248
+ "learning_rate": 3.392802673484193e-05,
249
+ "loss": 0.0,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 0.4495171202809482,
254
+ "grad_norm": NaN,
255
+ "learning_rate": 3.086582838174551e-05,
256
+ "loss": 0.0,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 0.4635645302897278,
261
+ "grad_norm": NaN,
262
+ "learning_rate": 2.7885565489049946e-05,
263
+ "loss": 0.0,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 0.47761194029850745,
268
+ "grad_norm": NaN,
269
+ "learning_rate": 2.500000000000001e-05,
270
+ "loss": 0.0,
271
+ "step": 34
272
+ },
273
+ {
274
+ "epoch": 0.4916593503072871,
275
+ "grad_norm": NaN,
276
+ "learning_rate": 2.2221488349019903e-05,
277
+ "loss": 0.0,
278
+ "step": 35
279
+ },
280
+ {
281
+ "epoch": 0.5057067603160668,
282
+ "grad_norm": NaN,
283
+ "learning_rate": 1.9561928549563968e-05,
284
+ "loss": 0.0,
285
+ "step": 36
286
+ },
287
+ {
288
+ "epoch": 0.5197541703248464,
289
+ "grad_norm": NaN,
290
+ "learning_rate": 1.703270924499656e-05,
291
+ "loss": 0.0,
292
+ "step": 37
293
+ },
294
+ {
295
+ "epoch": 0.533801580333626,
296
+ "grad_norm": NaN,
297
+ "learning_rate": 1.4644660940672627e-05,
298
+ "loss": 0.0,
299
+ "step": 38
300
+ },
301
+ {
302
+ "epoch": 0.5478489903424056,
303
+ "grad_norm": NaN,
304
+ "learning_rate": 1.2408009626051137e-05,
305
+ "loss": 0.0,
306
+ "step": 39
307
+ },
308
+ {
309
+ "epoch": 0.5478489903424056,
310
+ "eval_loss": NaN,
311
+ "eval_runtime": 30.9187,
312
+ "eval_samples_per_second": 15.525,
313
+ "eval_steps_per_second": 3.881,
314
+ "step": 39
315
  }
316
  ],
317
  "logging_steps": 1,
 
331
  "attributes": {}
332
  }
333
  },
334
+ "total_flos": 3.440910085662966e+17,
335
  "train_batch_size": 2,
336
  "trial_name": null,
337
  "trial_params": null