RoyJoy commited on
Commit
a390bac
1 Parent(s): 6621630

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 sha256:0e20d855196b0a5a431111879825930a8e746bb641dd1b50692b4f968a5832b9
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1917a5f8509c6216baa4a40f973c6f6a86736ec9be48b45620bd082c3d6b658
3
  size 640009682
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0dd1ee46340ee5bc365cdd8e8716bcbcdecd536cc8b44c082bb140f5159df1c2
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ade0b1544b5432c02c629d743fcfdb104c6c039b58276ba96722337f91758e18
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 sha256:79ec02fc020a8dc3173476948a5972558632fd7f8145991e11796687a635438c
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe3e63930b8f3bbcbc65ef05cd960fbe9a6793804ab1f6b32e249c22b8bdec5
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 sha256:9e3ffc4751ccee63eb5814ee9fc5d0c62c3843530dd693aa726d5333388ec100
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:361a04de78da44c0421afe441cfa1c0736559d80fa2b0f44201a7fa64e44d7dd
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 sha256:49333ad16370f882a50e13520d9f84cb79df30a9373911b25f37f0dbf61822c0
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dedc7be3b013ddf4e3c45e5cbd97fd6a196faa7ced4f5291a3ee7d202310a2b
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:107607e336ff02e6e3fc135f6b55fc089901c7172808564e7046a8e836a537c9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
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": 0.026308000920780034,
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": 33.371,
199
  "eval_steps_per_second": 8.676,
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": 2.652642132099072e+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": 0.05261600184156007,
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": 33.371,
199
  "eval_steps_per_second": 8.676,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.027360320957611234,
204
+ "grad_norm": NaN,
205
+ "learning_rate": 8.957804998855866e-05,
206
+ "loss": 0.0,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.028412640994442434,
211
+ "grad_norm": NaN,
212
+ "learning_rate": 8.860696646428693e-05,
213
+ "loss": 0.0,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.029464961031273638,
218
+ "grad_norm": NaN,
219
+ "learning_rate": 8.759913421559902e-05,
220
+ "loss": 0.0,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.030517281068104838,
225
+ "grad_norm": NaN,
226
+ "learning_rate": 8.655565529226198e-05,
227
+ "loss": 0.0,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.03156960110493604,
232
+ "grad_norm": NaN,
233
+ "learning_rate": 8.547767072315835e-05,
234
+ "loss": 0.0,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.03262192114176724,
239
+ "grad_norm": NaN,
240
+ "learning_rate": 8.436635926858759e-05,
241
+ "loss": 0.0,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.03367424117859844,
246
+ "grad_norm": NaN,
247
+ "learning_rate": 8.322293613130917e-05,
248
+ "loss": 0.0,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.03472656121542964,
253
+ "grad_norm": NaN,
254
+ "learning_rate": 8.204865162773613e-05,
255
+ "loss": 0.0,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.03577888125226084,
260
+ "grad_norm": NaN,
261
+ "learning_rate": 8.084478982073247e-05,
262
+ "loss": 0.0,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.03683120128909204,
267
+ "grad_norm": NaN,
268
+ "learning_rate": 7.961266711550922e-05,
269
+ "loss": 0.0,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.03788352132592324,
274
+ "grad_norm": NaN,
275
+ "learning_rate": 7.835363082015468e-05,
276
+ "loss": 0.0,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.03893584136275445,
281
+ "grad_norm": NaN,
282
+ "learning_rate": 7.706905767237288e-05,
283
+ "loss": 0.0,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.03998816139958565,
288
+ "grad_norm": NaN,
289
+ "learning_rate": 7.576035233404096e-05,
290
+ "loss": 0.0,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.04104048143641685,
295
+ "grad_norm": NaN,
296
+ "learning_rate": 7.442894585523218e-05,
297
+ "loss": 0.0,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.04209280147324805,
302
+ "grad_norm": NaN,
303
+ "learning_rate": 7.307629410938363e-05,
304
+ "loss": 0.0,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.04314512151007925,
309
+ "grad_norm": NaN,
310
+ "learning_rate": 7.170387620131993e-05,
311
+ "loss": 0.0,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.04419744154691045,
316
+ "grad_norm": NaN,
317
+ "learning_rate": 7.031319284987394e-05,
318
+ "loss": 0.0,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.04524976158374166,
323
+ "grad_norm": NaN,
324
+ "learning_rate": 6.890576474687263e-05,
325
+ "loss": 0.0,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.04630208162057286,
330
+ "grad_norm": NaN,
331
+ "learning_rate": 6.7483130894283e-05,
332
+ "loss": 0.0,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.04735440165740406,
337
+ "grad_norm": NaN,
338
+ "learning_rate": 6.604684692133597e-05,
339
+ "loss": 0.0,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.04840672169423526,
344
+ "grad_norm": NaN,
345
+ "learning_rate": 6.459848338346861e-05,
346
+ "loss": 0.0,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.04945904173106646,
351
+ "grad_norm": NaN,
352
+ "learning_rate": 6.313962404494496e-05,
353
+ "loss": 0.0,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.05051136176789766,
358
+ "grad_norm": NaN,
359
+ "learning_rate": 6.167186414703289e-05,
360
+ "loss": 0.0,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.05156368180472886,
365
+ "grad_norm": NaN,
366
+ "learning_rate": 6.019680866363139e-05,
367
+ "loss": 0.0,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.05261600184156007,
372
+ "grad_norm": NaN,
373
+ "learning_rate": 5.8716070546254966e-05,
374
+ "loss": 0.0,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.05261600184156007,
379
+ "eval_loss": NaN,
380
+ "eval_runtime": 3.304,
381
+ "eval_samples_per_second": 15.133,
382
+ "eval_steps_per_second": 3.935,
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": 5.305284264198144e+17,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null