Rodo-Sami commited on
Commit
ffd28b6
1 Parent(s): 5a2665b

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:f1454917ea86cfdc7ac7a54a73c878f30d8e3041b174db0c4a87041b7504c622
3
  size 100690288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:462b316da5fd48b60cdae78474c88d76b1d6346616e3cd979267420cd4eda148
3
  size 100690288
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:507e6984d9911ee783bf669ef75a81fde9b0f048bd3c8b9b308b7fe06f8f2f34
3
  size 201488570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c03db1b49565e8cff8d9627f4c07cce8812dc6e06cb9328039457d4c0366951d
3
  size 201488570
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1eef7f329b77da595f4e65adf4f1fd3e13161f5754a7159c5a732250b485cac
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9c59a9739f0166580d71d83759a5082fcb2c662b9ea5409c8bdd8459e017625
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 sha256:5ae861b2023fa6e1b3157baa72fd49c7f8422c45c558ba4d9e24ddc830bcbfe3
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:084fe7b5c8bbbc6b63122dcdaa493c7aa79d18bece4bdbfcd0b32ae30153eab2
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 sha256:549e1db6be807091d15c55dad401b5bffef0367648168dc90af145729530db2d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15d3f3e8899e8b0621e4f237ca02195c9796e76b28074aec90fa100a6c3c0bbe
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 sha256:2e4c7610ff9395f8f34cddd6a1e3f1b360f2cca11fd9341da1ec8a459a434c41
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de6a687bd2ea42e6c8bc336be824793fb265fb9597eeeef8ae344fa1ee795214
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": 0.9295913577079773,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 1.221884498480243,
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": 37.837,
199
  "eval_steps_per_second": 4.9,
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": 4.85137494048768e+16,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.738952100276947,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 2.443768996960486,
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": 37.837,
199
  "eval_steps_per_second": 4.9,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 1.2705167173252279,
204
+ "grad_norm": 57.16689682006836,
205
+ "learning_rate": 5e-05,
206
+ "loss": 0.8051,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 1.3191489361702127,
211
+ "grad_norm": 32.02121353149414,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 0.4653,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 1.3677811550151975,
218
+ "grad_norm": 48.5133056640625,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 0.825,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 1.4164133738601823,
225
+ "grad_norm": 66.22747039794922,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 0.856,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 1.465045592705167,
232
+ "grad_norm": 65.52440643310547,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 0.9969,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 1.513677811550152,
239
+ "grad_norm": 52.595699310302734,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 0.7564,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 1.5623100303951367,
246
+ "grad_norm": 56.82194519042969,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 0.5235,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 1.6109422492401215,
253
+ "grad_norm": 49.04568862915039,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 0.7778,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 1.6595744680851063,
260
+ "grad_norm": 61.08024978637695,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 0.8873,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 1.7082066869300911,
267
+ "grad_norm": 59.74906921386719,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 0.772,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 1.756838905775076,
274
+ "grad_norm": 39.438392639160156,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 0.8044,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 1.8054711246200608,
281
+ "grad_norm": 44.79551696777344,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 0.5302,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 1.8541033434650456,
288
+ "grad_norm": 41.50120162963867,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 0.6659,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 1.9027355623100304,
295
+ "grad_norm": 92.41071319580078,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 0.8416,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 1.9513677811550152,
302
+ "grad_norm": 57.740657806396484,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 0.7625,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 2.0060790273556233,
309
+ "grad_norm": 37.433349609375,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 0.7985,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 2.054711246200608,
316
+ "grad_norm": 32.22288513183594,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 0.5062,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 2.103343465045593,
323
+ "grad_norm": 32.619056701660156,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 0.558,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 2.1519756838905777,
330
+ "grad_norm": 35.74100112915039,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 0.7794,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 2.2006079027355625,
337
+ "grad_norm": 38.613834381103516,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 0.7587,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 2.2492401215805473,
344
+ "grad_norm": 43.844451904296875,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 0.8223,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 2.297872340425532,
351
+ "grad_norm": 27.004453659057617,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 0.4098,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 2.3465045592705165,
358
+ "grad_norm": 28.623008728027344,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 0.5683,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 2.3951367781155017,
365
+ "grad_norm": 36.22129821777344,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 0.8083,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 2.443768996960486,
372
+ "grad_norm": 42.232688903808594,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.9155,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 2.443768996960486,
379
+ "eval_loss": 0.738952100276947,
380
+ "eval_runtime": 3.6618,
381
+ "eval_samples_per_second": 37.96,
382
+ "eval_steps_per_second": 4.916,
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": 9.70274988097536e+16,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null