dada22231 commited on
Commit
592eb73
1 Parent(s): a46d20a

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16a5569594fb4df5bf1c750785f3494d46feefa182cb2b32b73b96c59ce4dfb9
3
  size 295765866
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab3bcbb9ec6038367b1ea709631a09053a575952c1be07e37c59ac223fdb2341
3
  size 295765866
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8551b92053f78ac2ac8a7032556af81f16787fa0b4697468351e63223b3bc75
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae2a4e981faeea31b5bf6f06e3265fc0bcded1b1d2f8ba2304d19bbe366ce6c
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6adbada1dfec67ff24bc8d150c9149447576f265439bddea26f0d36496c890a
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddc2dcac81549ebba6bf8c9460e058b138817639635ae9a3f0ab55d721f7dbca
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3a07c68ec8674bc75dea7e9f1e7536ac159290df01f9893eb5032b2a75acd13
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:983660c27f1afe0074f73e3e9b83b13d9a2473899e1060ca9297e0b5b2497237
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:454fefbe9db97784bb2aac29282c463dd349a0b2a735bafe239c32c4593346ae
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f47c2ae90db38a205a6e05fb5417f02241bdfb165226c8ae3eef91bd8007f329
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
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": 0.06332620913480566,
5
  "eval_steps": 25,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -198,6 +198,189 @@
198
  "eval_samples_per_second": 44.806,
199
  "eval_steps_per_second": 11.649,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -212,12 +395,12 @@
212
  "should_evaluate": false,
213
  "should_log": false,
214
  "should_save": true,
215
- "should_training_stop": false
216
  },
217
  "attributes": {}
218
  }
219
  },
220
- "total_flos": 5.29768176943104e+16,
221
  "train_batch_size": 1,
222
  "trial_name": null,
223
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.12665241826961132,
5
  "eval_steps": 25,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
198
  "eval_samples_per_second": 44.806,
199
  "eval_steps_per_second": 11.649,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.06585925750019789,
204
+ "grad_norm": NaN,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 0.0,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.06839230586559013,
211
+ "grad_norm": NaN,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 0.0,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.07092535423098235,
218
+ "grad_norm": NaN,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 0.0,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.07345840259637458,
225
+ "grad_norm": NaN,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 0.0,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.07599145096176681,
232
+ "grad_norm": NaN,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 0.0,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.07852449932715903,
239
+ "grad_norm": NaN,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 0.0,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.08105754769255126,
246
+ "grad_norm": NaN,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 0.0,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.08359059605794349,
253
+ "grad_norm": NaN,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 0.0,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.08612364442333571,
260
+ "grad_norm": NaN,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 0.0,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.08865669278872794,
267
+ "grad_norm": NaN,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 0.0,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.09118974115412017,
274
+ "grad_norm": NaN,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 0.0,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.09372278951951239,
281
+ "grad_norm": NaN,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 0.0,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.09625583788490462,
288
+ "grad_norm": NaN,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 0.0,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.09878888625029685,
295
+ "grad_norm": NaN,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 0.0,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.10132193461568907,
302
+ "grad_norm": NaN,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 0.0,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.1038549829810813,
309
+ "grad_norm": NaN,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 0.0,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.10638803134647352,
316
+ "grad_norm": NaN,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 0.0,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.10892107971186575,
323
+ "grad_norm": NaN,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 0.0,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.11145412807725798,
330
+ "grad_norm": NaN,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 0.0,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.1139871764426502,
337
+ "grad_norm": NaN,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 0.0,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.11652022480804243,
344
+ "grad_norm": NaN,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 0.0,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.11905327317343466,
351
+ "grad_norm": NaN,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 0.0,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.12158632153882688,
358
+ "grad_norm": NaN,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 0.0,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.12411936990421911,
365
+ "grad_norm": NaN,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 0.0,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.12665241826961132,
372
+ "grad_norm": NaN,
373
+ "learning_rate": 1e-05,
374
+ "loss": 0.0,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.12665241826961132,
379
+ "eval_loss": NaN,
380
+ "eval_runtime": 1.137,
381
+ "eval_samples_per_second": 43.976,
382
+ "eval_steps_per_second": 11.434,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
395
  "should_evaluate": false,
396
  "should_log": false,
397
  "should_save": true,
398
+ "should_training_stop": true
399
  },
400
  "attributes": {}
401
  }
402
  },
403
+ "total_flos": 1.059536353886208e+17,
404
  "train_batch_size": 1,
405
  "trial_name": null,
406
  "trial_params": null