diaenra commited on
Commit
0c259d1
·
verified ·
1 Parent(s): e0bb5ab

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:b336c7028dc9c76a65e3d4107812721e5abd6fea0ab548ad65111d27e8d3c752
3
  size 83115256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95054becb4d4b8cf655cd8e6bf230ea6b6fe8bb51a29bbbf1eaab7871504a164
3
  size 83115256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c0df0ecca2e8ec04d4ff2380a9179174806545d5ce4b773be58e6b047973935
3
  size 166439638
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:489ecea0daa164762eae7608fcf56a5580523c9e54ea4d91c2775bd44ad7ae4a
3
  size 166439638
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e3d41de716736e12dafbd11be068ea31ebe2d631b929e5d1da2c9c1c8750fc7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dda35150537efcaa35f5dc9a353ae196533e259e9b0a38fc01ee055b5232095
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.7356017231941223,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.00839278220730172,
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": 5.934,
199
  "eval_steps_per_second": 2.969,
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": 1.00529829052416e+16,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7258085012435913,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.01678556441460344,
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": 5.934,
199
  "eval_steps_per_second": 2.969,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.008728493495593789,
204
+ "grad_norm": 0.47435083985328674,
205
+ "learning_rate": 0.0001,
206
+ "loss": 0.829,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.009064204783885858,
211
+ "grad_norm": 0.4807548224925995,
212
+ "learning_rate": 9.345968707698569e-05,
213
+ "loss": 0.7353,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.009399916072177926,
218
+ "grad_norm": 0.43215635418891907,
219
+ "learning_rate": 8.694738077799488e-05,
220
+ "loss": 0.776,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.009735627360469996,
225
+ "grad_norm": 0.398535817861557,
226
+ "learning_rate": 8.049096779838719e-05,
227
+ "loss": 0.778,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.010071338648762064,
232
+ "grad_norm": 0.4872318208217621,
233
+ "learning_rate": 7.411809548974792e-05,
234
+ "loss": 0.8021,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.010407049937054134,
239
+ "grad_norm": 0.4282318651676178,
240
+ "learning_rate": 6.785605346968386e-05,
241
+ "loss": 0.8409,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.010742761225346202,
246
+ "grad_norm": 0.412360280752182,
247
+ "learning_rate": 6.173165676349103e-05,
248
+ "loss": 0.641,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.011078472513638271,
253
+ "grad_norm": 0.44958484172821045,
254
+ "learning_rate": 5.577113097809989e-05,
255
+ "loss": 0.7708,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.01141418380193034,
260
+ "grad_norm": 0.5542835593223572,
261
+ "learning_rate": 5.000000000000002e-05,
262
+ "loss": 0.8557,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.01174989509022241,
267
+ "grad_norm": 0.506291925907135,
268
+ "learning_rate": 4.444297669803981e-05,
269
+ "loss": 0.703,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.012085606378514477,
274
+ "grad_norm": 0.5930730700492859,
275
+ "learning_rate": 3.9123857099127936e-05,
276
+ "loss": 0.907,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.012421317666806547,
281
+ "grad_norm": 0.44674548506736755,
282
+ "learning_rate": 3.406541848999312e-05,
283
+ "loss": 0.6435,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.012757028955098615,
288
+ "grad_norm": 0.5273513793945312,
289
+ "learning_rate": 2.9289321881345254e-05,
290
+ "loss": 0.9527,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.013092740243390685,
295
+ "grad_norm": 0.48624753952026367,
296
+ "learning_rate": 2.4816019252102273e-05,
297
+ "loss": 0.8207,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.013428451531682753,
302
+ "grad_norm": 0.5799288153648376,
303
+ "learning_rate": 2.0664665970876496e-05,
304
+ "loss": 0.7522,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.013764162819974822,
309
+ "grad_norm": 0.4889924228191376,
310
+ "learning_rate": 1.6853038769745467e-05,
311
+ "loss": 0.7454,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.01409987410826689,
316
+ "grad_norm": 0.5171151161193848,
317
+ "learning_rate": 1.339745962155613e-05,
318
+ "loss": 0.7182,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.01443558539655896,
323
+ "grad_norm": 0.5659388899803162,
324
+ "learning_rate": 1.0312725846731175e-05,
325
+ "loss": 0.7468,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.014771296684851028,
330
+ "grad_norm": 0.5659289360046387,
331
+ "learning_rate": 7.612046748871327e-06,
332
+ "loss": 0.7714,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.015107007973143098,
337
+ "grad_norm": 0.60720294713974,
338
+ "learning_rate": 5.306987050489442e-06,
339
+ "loss": 0.7841,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.015442719261435166,
344
+ "grad_norm": 0.6002097129821777,
345
+ "learning_rate": 3.40741737109318e-06,
346
+ "loss": 0.8471,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.015778430549727235,
351
+ "grad_norm": 0.653490424156189,
352
+ "learning_rate": 1.921471959676957e-06,
353
+ "loss": 0.6657,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.016114141838019302,
358
+ "grad_norm": 0.6233632564544678,
359
+ "learning_rate": 8.555138626189618e-07,
360
+ "loss": 0.7918,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.01644985312631137,
365
+ "grad_norm": 0.7531246542930603,
366
+ "learning_rate": 2.141076761396521e-07,
367
+ "loss": 0.7391,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.01678556441460344,
372
+ "grad_norm": 0.7968045473098755,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.636,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.01678556441460344,
379
+ "eval_loss": 0.7258085012435913,
380
+ "eval_runtime": 211.581,
381
+ "eval_samples_per_second": 5.932,
382
+ "eval_steps_per_second": 2.968,
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": 2.01059658104832e+16,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null