Dnsx077 commited on
Commit
4b5211c
1 Parent(s): 63ae921

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 sha256:5a362847fc20448e2cc80a172c755f4ee86475d1e3ad31d7612919f49e42704e
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635948db3d7dc287407379f1fe8732c927b5ec71fcf302c871277686c5359742
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1794d350b0949c928c1a45630ec4095336955cc3be61a9b6cd9549e45aa580af
3
  size 90365754
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488c48e0adeed68c1c3937719ccd4c371e0fe8d922b66d9178467f10b07bae33
3
  size 90365754
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df9a9ed87ecb21bcc3fcb66206aa46e76dca7b93705e3880a71c079b0d25aaa5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5291c661a5b9c3b19b574f0b903cd648890a2f4a8731fbbc827629f02a244b
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": 2.5090396404266357,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.006094959468519534,
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": 10.046,
199
  "eval_steps_per_second": 5.026,
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": 4838612847820800.0,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.4238104820251465,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.012189918937039069,
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": 10.046,
199
  "eval_steps_per_second": 5.026,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.006338757847260316,
204
+ "grad_norm": 1.9765174388885498,
205
+ "learning_rate": 0.0001,
206
+ "loss": 2.5108,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.006582556226001097,
211
+ "grad_norm": 2.027369737625122,
212
+ "learning_rate": 9.345968707698569e-05,
213
+ "loss": 2.5258,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.006826354604741879,
218
+ "grad_norm": 2.7139859199523926,
219
+ "learning_rate": 8.694738077799488e-05,
220
+ "loss": 2.4354,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.00707015298348266,
225
+ "grad_norm": 2.5592691898345947,
226
+ "learning_rate": 8.049096779838719e-05,
227
+ "loss": 2.3317,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.007313951362223441,
232
+ "grad_norm": 3.9472053050994873,
233
+ "learning_rate": 7.411809548974792e-05,
234
+ "loss": 2.2022,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.007557749740964222,
239
+ "grad_norm": 2.6229476928710938,
240
+ "learning_rate": 6.785605346968386e-05,
241
+ "loss": 2.5237,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.007801548119705004,
246
+ "grad_norm": 2.831041097640991,
247
+ "learning_rate": 6.173165676349103e-05,
248
+ "loss": 2.228,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.008045346498445785,
253
+ "grad_norm": 2.713304042816162,
254
+ "learning_rate": 5.577113097809989e-05,
255
+ "loss": 2.0782,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.008289144877186566,
260
+ "grad_norm": 3.9535391330718994,
261
+ "learning_rate": 5.000000000000002e-05,
262
+ "loss": 2.0093,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.008532943255927348,
267
+ "grad_norm": 4.031512260437012,
268
+ "learning_rate": 4.444297669803981e-05,
269
+ "loss": 2.1973,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.00877674163466813,
274
+ "grad_norm": 3.933284282684326,
275
+ "learning_rate": 3.9123857099127936e-05,
276
+ "loss": 2.6964,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.009020540013408912,
281
+ "grad_norm": 3.9383676052093506,
282
+ "learning_rate": 3.406541848999312e-05,
283
+ "loss": 2.0572,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.009264338392149692,
288
+ "grad_norm": 3.3363380432128906,
289
+ "learning_rate": 2.9289321881345254e-05,
290
+ "loss": 1.7806,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.009508136770890473,
295
+ "grad_norm": 5.100573539733887,
296
+ "learning_rate": 2.4816019252102273e-05,
297
+ "loss": 1.9677,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.009751935149631255,
302
+ "grad_norm": 3.5059847831726074,
303
+ "learning_rate": 2.0664665970876496e-05,
304
+ "loss": 2.2317,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.009995733528372037,
309
+ "grad_norm": 5.321730613708496,
310
+ "learning_rate": 1.6853038769745467e-05,
311
+ "loss": 2.1228,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.010239531907112819,
316
+ "grad_norm": 4.9000630378723145,
317
+ "learning_rate": 1.339745962155613e-05,
318
+ "loss": 2.4057,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.010483330285853599,
323
+ "grad_norm": 5.210293769836426,
324
+ "learning_rate": 1.0312725846731175e-05,
325
+ "loss": 2.1145,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.01072712866459438,
330
+ "grad_norm": 4.690629959106445,
331
+ "learning_rate": 7.612046748871327e-06,
332
+ "loss": 2.3281,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.010970927043335162,
337
+ "grad_norm": 6.070462226867676,
338
+ "learning_rate": 5.306987050489442e-06,
339
+ "loss": 2.1419,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.011214725422075944,
344
+ "grad_norm": 7.646251201629639,
345
+ "learning_rate": 3.40741737109318e-06,
346
+ "loss": 3.2018,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.011458523800816725,
351
+ "grad_norm": 7.303621768951416,
352
+ "learning_rate": 1.921471959676957e-06,
353
+ "loss": 2.7462,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.011702322179557505,
358
+ "grad_norm": 5.764501571655273,
359
+ "learning_rate": 8.555138626189618e-07,
360
+ "loss": 2.3094,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.011946120558298287,
365
+ "grad_norm": 7.291966438293457,
366
+ "learning_rate": 2.141076761396521e-07,
367
+ "loss": 2.6926,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.012189918937039069,
372
+ "grad_norm": 13.362791061401367,
373
+ "learning_rate": 0.0,
374
+ "loss": 2.6087,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.012189918937039069,
379
+ "eval_loss": 2.4238104820251465,
380
+ "eval_runtime": 172.7252,
381
+ "eval_samples_per_second": 9.999,
382
+ "eval_steps_per_second": 5.002,
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": 9677225695641600.0,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null