dada22231 commited on
Commit
d1145f8
·
verified ·
1 Parent(s): bd8fff0

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 sha256:8451435c6b33d74771effdd5509d9d9106046b813cb02afe0bcab6eea9eb0167
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:933ecda4bebd0c702b7cd2e8537fcbe734d2163fa993dce8795e1c7ab76444a1
3
  size 671466706
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2cae7929cac16384f02a6cac4375ae39cc1c4c450de8566c5c6679a42773e76
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2cb00c0bf86dc8b9cb53cc924906fa15e9e8ab04db51db088e011b14d6601bb
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:a24e4ff2641111024930a1bbcd63a0e37bcadf0825275605fba694b27d3a1ae0
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb1e8f8b8c0166a125c55ac68e12e85f96a097535ff6d31a940e42190cff6303
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:f143c912e4f6310d3350481514c206eb62f49396aa46e1f85379ecc6d9e807fa
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f26fd9e04dc5f47e9d08cd7d34cf8c50485ee8b0edc5eb41ce72915b38cae21
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:de00895e9264c891de68ee57a88e91889e29f5b807e39dc5fe81664e6b220aaa
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d6431d34abc9567eb56369c3728e1f9d3b740795a71ee622f152edd34284e26
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.0053532115923797035,
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": 11.772,
199
  "eval_steps_per_second": 3.061,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -212,7 +395,7 @@
212
  "early_stopping_threshold": 0.0
213
  },
214
  "attributes": {
215
- "early_stopping_patience_counter": 0
216
  }
217
  },
218
  "TrainerControl": {
@@ -221,12 +404,12 @@
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
- "should_training_stop": false
225
  },
226
  "attributes": {}
227
  }
228
  },
229
- "total_flos": 2.984041808658432e+17,
230
  "train_batch_size": 1,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
+ "epoch": 0.010706423184759407,
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": 11.772,
199
  "eval_steps_per_second": 3.061,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.005567340056074892,
204
+ "grad_norm": NaN,
205
+ "learning_rate": 7.917848237560709e-05,
206
+ "loss": 0.0,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.00578146851977008,
211
+ "grad_norm": NaN,
212
+ "learning_rate": 7.75e-05,
213
+ "loss": 0.0,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.005995596983465267,
218
+ "grad_norm": NaN,
219
+ "learning_rate": 7.577868759557654e-05,
220
+ "loss": 0.0,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.0062097254471604555,
225
+ "grad_norm": NaN,
226
+ "learning_rate": 7.401782177833148e-05,
227
+ "loss": 0.0,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.006423853910855644,
232
+ "grad_norm": NaN,
233
+ "learning_rate": 7.222075445642904e-05,
234
+ "loss": 0.0,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.006637982374550832,
239
+ "grad_norm": NaN,
240
+ "learning_rate": 7.03909064496551e-05,
241
+ "loss": 0.0,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.00685211083824602,
246
+ "grad_norm": NaN,
247
+ "learning_rate": 6.853176097769229e-05,
248
+ "loss": 0.0,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.007066239301941208,
253
+ "grad_norm": NaN,
254
+ "learning_rate": 6.664685702961344e-05,
255
+ "loss": 0.0,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.0072803677656363966,
260
+ "grad_norm": NaN,
261
+ "learning_rate": 6.473978262721463e-05,
262
+ "loss": 0.0,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.007494496229331585,
267
+ "grad_norm": NaN,
268
+ "learning_rate": 6.281416799501188e-05,
269
+ "loss": 0.0,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.007708624693026773,
274
+ "grad_norm": NaN,
275
+ "learning_rate": 6.087367864990233e-05,
276
+ "loss": 0.0,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.007922753156721961,
281
+ "grad_norm": NaN,
282
+ "learning_rate": 5.8922008423644624e-05,
283
+ "loss": 0.0,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.008136881620417149,
288
+ "grad_norm": NaN,
289
+ "learning_rate": 5.696287243144013e-05,
290
+ "loss": 0.0,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.008351010084112338,
295
+ "grad_norm": NaN,
296
+ "learning_rate": 5.500000000000001e-05,
297
+ "loss": 0.0,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.008565138547807525,
302
+ "grad_norm": NaN,
303
+ "learning_rate": 5.303712756855988e-05,
304
+ "loss": 0.0,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.008779267011502714,
309
+ "grad_norm": NaN,
310
+ "learning_rate": 5.107799157635538e-05,
311
+ "loss": 0.0,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.008993395475197901,
316
+ "grad_norm": NaN,
317
+ "learning_rate": 4.912632135009769e-05,
318
+ "loss": 0.0,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.00920752393889309,
323
+ "grad_norm": NaN,
324
+ "learning_rate": 4.718583200498814e-05,
325
+ "loss": 0.0,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.009421652402588278,
330
+ "grad_norm": NaN,
331
+ "learning_rate": 4.526021737278538e-05,
332
+ "loss": 0.0,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.009635780866283465,
337
+ "grad_norm": NaN,
338
+ "learning_rate": 4.3353142970386564e-05,
339
+ "loss": 0.0,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.009849909329978654,
344
+ "grad_norm": NaN,
345
+ "learning_rate": 4.146823902230772e-05,
346
+ "loss": 0.0,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.010064037793673842,
351
+ "grad_norm": NaN,
352
+ "learning_rate": 3.960909355034491e-05,
353
+ "loss": 0.0,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.01027816625736903,
358
+ "grad_norm": NaN,
359
+ "learning_rate": 3.777924554357096e-05,
360
+ "loss": 0.0,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.010492294721064218,
365
+ "grad_norm": NaN,
366
+ "learning_rate": 3.598217822166854e-05,
367
+ "loss": 0.0,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.010706423184759407,
372
+ "grad_norm": NaN,
373
+ "learning_rate": 3.422131240442349e-05,
374
+ "loss": 0.0,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.010706423184759407,
379
+ "eval_loss": NaN,
380
+ "eval_runtime": 4.2631,
381
+ "eval_samples_per_second": 11.728,
382
+ "eval_steps_per_second": 3.049,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
395
  "early_stopping_threshold": 0.0
396
  },
397
  "attributes": {
398
+ "early_stopping_patience_counter": 1
399
  }
400
  },
401
  "TrainerControl": {
 
404
  "should_evaluate": false,
405
  "should_log": false,
406
  "should_save": true,
407
+ "should_training_stop": true
408
  },
409
  "attributes": {}
410
  }
411
  },
412
+ "total_flos": 5.968083617316864e+17,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null