TracyTank commited on
Commit
374a2a7
1 Parent(s): f27683f

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:ed196c4e6795eff0e5d52e934ac3c00ddc2fa9d5af31426449c922d387bb91b4
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff339ad4e2ae779b6c5acbdeba118e87fe5d7e0855331c21c71418f6386eafc
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2307534116ae009b334e2ba53486509b2e224a0e484024906c72d0e835cbbdfe
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5601b0702bf2c4c3e7d1db8941752ae6d2706ac9faa42e8d13240a9aa51da9a6
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 sha256:532f0f245cca9ec64ae51526cc5e1612882bc1d5d62df4bc336310e00b71c6a3
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab19e9d57d2343f999cbd33c0c95240336185c029fcaaee8821e713ddf94f72
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:af5b571293032fc6da1affbc9f86eac11bab9aa84d43a6e4ee938a4a856aff94
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bce6514a724205802240199e4f1acc3f89b6aacfab809ec7d397cdee0f5ca82
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:f67fca3186bfa47c726ee11f030f9bd768d6cdb83a85850fccbbe8950f8efcc7
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:805b654ea4fb21ab2718981d433b2925268cb941f6625b6641ce62451c16344c
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:eacf6e2d644fa60f7cfbe42e73a0f19c50e470291fd3274abe34b1b70274767d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c67547f53a8529213ab65f1d4d284f9c9dc2d9fd6c4b65dee9816858b820c7f
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4368922710418701,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.0332944897619444,
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": 32.514,
199
  "eval_steps_per_second": 4.068,
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": 2.984041808658432e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3975412845611572,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.0665889795238888,
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": 32.514,
199
  "eval_steps_per_second": 4.068,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.034626269352422176,
204
+ "grad_norm": 0.7546113729476929,
205
+ "learning_rate": 5e-05,
206
+ "loss": 1.6641,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.03595804894289995,
211
+ "grad_norm": 0.7036129832267761,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 1.5849,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.03728982853337773,
218
+ "grad_norm": 0.7657355666160583,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 1.4307,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.038621608123855504,
225
+ "grad_norm": 0.7765692472457886,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 1.4377,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.03995338771433328,
232
+ "grad_norm": 0.8169478178024292,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 1.3892,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.041285167304811056,
239
+ "grad_norm": 0.8468606472015381,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 1.2886,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.04261694689528883,
246
+ "grad_norm": 0.842719554901123,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 1.1519,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.04394872648576661,
253
+ "grad_norm": 0.8773880004882812,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 1.4317,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.045280506076244384,
260
+ "grad_norm": 1.0714538097381592,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 1.4496,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.04661228566672216,
267
+ "grad_norm": 1.0184491872787476,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 1.4086,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.047944065257199936,
274
+ "grad_norm": 1.0979220867156982,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 1.2355,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.04927584484767771,
281
+ "grad_norm": 1.6338611841201782,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 1.4841,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.05060762443815549,
288
+ "grad_norm": 0.7203386425971985,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 1.7433,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.051939404028633264,
295
+ "grad_norm": 0.6181879043579102,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 1.5915,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.05327118361911104,
302
+ "grad_norm": 0.6601304411888123,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 1.5255,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.054602963209588816,
309
+ "grad_norm": 0.7737628817558289,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 1.4904,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.05593474280006659,
316
+ "grad_norm": 0.6829192638397217,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 1.3329,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.05726652239054437,
323
+ "grad_norm": 0.7644971609115601,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 1.3325,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.058598301981022144,
330
+ "grad_norm": 0.7881768941879272,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 1.2382,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.05993008157149992,
337
+ "grad_norm": 0.9224614500999451,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 1.3537,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.061261861161977696,
344
+ "grad_norm": 0.8903812170028687,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 1.2534,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.06259364075245546,
351
+ "grad_norm": 0.9834040403366089,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 1.3721,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.06392542034293325,
358
+ "grad_norm": 1.1316769123077393,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 1.1691,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.06525719993341102,
365
+ "grad_norm": 1.144602656364441,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 1.2945,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.0665889795238888,
372
+ "grad_norm": 1.6286240816116333,
373
+ "learning_rate": 0.0,
374
+ "loss": 1.5057,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0665889795238888,
379
+ "eval_loss": 1.3975412845611572,
380
+ "eval_runtime": 132.4989,
381
+ "eval_samples_per_second": 38.181,
382
+ "eval_steps_per_second": 4.777,
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": 5.968083617316864e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null