dada22231 commited on
Commit
b40276a
·
verified ·
1 Parent(s): fe087fb

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51a72428a21e639e14b73d11573c000cd723401d25a0d09df721832ee30c7c49
3
  size 203456160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81c6f7962e6f9334458c0c5a8a5e48170051bcc4515075daeda5d48c7dd5a906
3
  size 203456160
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b2b409a51126805498c1f3b03d70f856cf84d47f04408be97ab58cb584b100a
3
  size 407121750
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3cb19928ec806036de9f142b967349fb9994a1d824082512647e8af6f88030
3
  size 407121750
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a71b2bab288ade9cea5f0954fe1635eeb05a5568b3a2e3cdcc811ac492358ff
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:963da77e28a79c49726aaff68d5428bd8972ae48c9e9b190a036a13e6408e499
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 sha256:25ac94a9ba71f91adeff9026b21a1272d8637941dd3a6f211fa7ecf17d6fa60b
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d917e591803fad098e847848af9616da7dcfe38988b6a4b564667ac35a38fba
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 sha256:0d1390965ec64775a90c093062515831e450cd74b28d80e58dc63683688d3107
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbb7e5660c873b6c06ab23c32c8c7e65d19a17154b75fb7e055b9e982a0ab8a4
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 sha256:464e2304b987b2d80793bca767631d87e73c60200d8680ebc470a0de39d23983
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfe109cefa4f44c352b6118a390da6da9ef394c170fbc85ad61ad443b52fb72e
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": 4.630157470703125,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.034381983840467596,
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": 11.173,
199
  "eval_steps_per_second": 2.905,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -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": 1.327074698592256e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 4.59688663482666,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.06876396768093519,
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": 11.173,
199
  "eval_steps_per_second": 2.905,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.0357572631940863,
204
+ "grad_norm": 3.5470054149627686,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 4.4535,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.037132542547705004,
211
+ "grad_norm": 3.0198135375976562,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 4.5103,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.03850782190132371,
218
+ "grad_norm": 1.6239436864852905,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 4.5091,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.03988310125494241,
225
+ "grad_norm": 0.7438290119171143,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 4.5166,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.041258380608561115,
232
+ "grad_norm": 1.5961905717849731,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 4.549,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.04263365996217982,
239
+ "grad_norm": 1.9019944667816162,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 4.6353,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.04400893931579852,
246
+ "grad_norm": 1.608849048614502,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 4.6285,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.04538421866941723,
253
+ "grad_norm": 0.9246691465377808,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 4.7333,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.04675949802303593,
260
+ "grad_norm": 0.5985221862792969,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 4.7893,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.048134777376654635,
267
+ "grad_norm": 1.3541096448898315,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 4.8817,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.04951005673027334,
274
+ "grad_norm": 1.3304661512374878,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 4.8802,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.05088533608389204,
281
+ "grad_norm": 0.7560667395591736,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 5.1148,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.052260615437510746,
288
+ "grad_norm": 0.7408563494682312,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 4.8291,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.05363589479112945,
295
+ "grad_norm": 1.689084529876709,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 4.4322,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.055011174144748154,
302
+ "grad_norm": 1.04849112033844,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 4.4272,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.05638645349836686,
309
+ "grad_norm": 0.40013745427131653,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 4.4528,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.05776173285198556,
316
+ "grad_norm": 0.9821546673774719,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 4.5102,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.059137012205604265,
323
+ "grad_norm": 1.4204320907592773,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 4.6064,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.06051229155922297,
330
+ "grad_norm": 1.5107200145721436,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 4.5763,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.06188757091284167,
337
+ "grad_norm": 1.8442341089248657,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 4.7101,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.06326285026646038,
344
+ "grad_norm": 1.6146044731140137,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 4.6966,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.06463812962007907,
351
+ "grad_norm": 1.5591859817504883,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 4.8572,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.06601340897369778,
358
+ "grad_norm": 1.0972256660461426,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 4.9027,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.06738868832731648,
365
+ "grad_norm": 1.1528632640838623,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 4.9912,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.06876396768093519,
372
+ "grad_norm": 0.9311072826385498,
373
+ "learning_rate": 1e-05,
374
+ "loss": 5.3241,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.06876396768093519,
379
+ "eval_loss": 4.59688663482666,
380
+ "eval_runtime": 4.4655,
381
+ "eval_samples_per_second": 11.197,
382
+ "eval_steps_per_second": 2.911,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
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": 2.654149397184512e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null