lesso11 commited on
Commit
2f946aa
·
verified ·
1 Parent(s): c308c9c

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:dcf84abecff6952bf331153b2e6415de9e33e594cfe8b290fb04ff197ef59e73
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b3031ff882756e719cde82cdf765f8178edc04fcd4d1a16ab609c47b0d43d1d
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2288f0b7ba9a29b1097e0ac5ac96f41b084ae236e0e100e007152622c19b023
3
  size 501168482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad604ec4db76e468c56eb83095d30c33f856f4aa17c5d4ad429bb7a507138764
3
  size 501168482
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c334162029911df951f21e152e5ddf37f5d979575a6d060ad1d369247ccd5d4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c08c9f2db3519491f65c896dc5570f0688363fea4110372251c117212111fc45
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.09107468123861566,
5
  "eval_steps": 9,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -206,6 +206,205 @@
206
  "learning_rate": 9.330127018922194e-05,
207
  "loss": 2.5564,
208
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
209
  }
210
  ],
211
  "logging_steps": 1,
@@ -225,7 +424,7 @@
225
  "attributes": {}
226
  }
227
  },
228
- "total_flos": 3.1739149811712e+16,
229
  "train_batch_size": 8,
230
  "trial_name": null,
231
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.18214936247723132,
5
  "eval_steps": 9,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
206
  "learning_rate": 9.330127018922194e-05,
207
  "loss": 2.5564,
208
  "step": 25
209
+ },
210
+ {
211
+ "epoch": 0.0947176684881603,
212
+ "grad_norm": 0.5033605098724365,
213
+ "learning_rate": 9.24024048078213e-05,
214
+ "loss": 2.5636,
215
+ "step": 26
216
+ },
217
+ {
218
+ "epoch": 0.09836065573770492,
219
+ "grad_norm": 0.3843136429786682,
220
+ "learning_rate": 9.145187862775209e-05,
221
+ "loss": 2.7431,
222
+ "step": 27
223
+ },
224
+ {
225
+ "epoch": 0.09836065573770492,
226
+ "eval_loss": 1.2466179132461548,
227
+ "eval_runtime": 36.1779,
228
+ "eval_samples_per_second": 6.385,
229
+ "eval_steps_per_second": 0.802,
230
+ "step": 27
231
+ },
232
+ {
233
+ "epoch": 0.10200364298724955,
234
+ "grad_norm": 0.4826091229915619,
235
+ "learning_rate": 9.045084971874738e-05,
236
+ "loss": 2.3946,
237
+ "step": 28
238
+ },
239
+ {
240
+ "epoch": 0.10564663023679417,
241
+ "grad_norm": 0.48955684900283813,
242
+ "learning_rate": 8.940053768033609e-05,
243
+ "loss": 2.5544,
244
+ "step": 29
245
+ },
246
+ {
247
+ "epoch": 0.1092896174863388,
248
+ "grad_norm": 0.5087964534759521,
249
+ "learning_rate": 8.83022221559489e-05,
250
+ "loss": 2.7766,
251
+ "step": 30
252
+ },
253
+ {
254
+ "epoch": 0.11293260473588343,
255
+ "grad_norm": 0.463750422000885,
256
+ "learning_rate": 8.715724127386972e-05,
257
+ "loss": 2.5906,
258
+ "step": 31
259
+ },
260
+ {
261
+ "epoch": 0.11657559198542805,
262
+ "grad_norm": 0.3833313286304474,
263
+ "learning_rate": 8.596699001693255e-05,
264
+ "loss": 2.4696,
265
+ "step": 32
266
+ },
267
+ {
268
+ "epoch": 0.12021857923497267,
269
+ "grad_norm": 0.4325249493122101,
270
+ "learning_rate": 8.473291852294987e-05,
271
+ "loss": 2.4887,
272
+ "step": 33
273
+ },
274
+ {
275
+ "epoch": 0.12386156648451731,
276
+ "grad_norm": 1.51544988155365,
277
+ "learning_rate": 8.345653031794292e-05,
278
+ "loss": 2.427,
279
+ "step": 34
280
+ },
281
+ {
282
+ "epoch": 0.12750455373406194,
283
+ "grad_norm": 0.47455018758773804,
284
+ "learning_rate": 8.213938048432697e-05,
285
+ "loss": 2.3536,
286
+ "step": 35
287
+ },
288
+ {
289
+ "epoch": 0.13114754098360656,
290
+ "grad_norm": 0.45129895210266113,
291
+ "learning_rate": 8.07830737662829e-05,
292
+ "loss": 2.3617,
293
+ "step": 36
294
+ },
295
+ {
296
+ "epoch": 0.13114754098360656,
297
+ "eval_loss": 1.231567144393921,
298
+ "eval_runtime": 36.1382,
299
+ "eval_samples_per_second": 6.392,
300
+ "eval_steps_per_second": 0.802,
301
+ "step": 36
302
+ },
303
+ {
304
+ "epoch": 0.13479052823315119,
305
+ "grad_norm": 0.47395437955856323,
306
+ "learning_rate": 7.938926261462366e-05,
307
+ "loss": 2.424,
308
+ "step": 37
309
+ },
310
+ {
311
+ "epoch": 0.1384335154826958,
312
+ "grad_norm": 0.4069020748138428,
313
+ "learning_rate": 7.795964517353735e-05,
314
+ "loss": 2.3032,
315
+ "step": 38
316
+ },
317
+ {
318
+ "epoch": 0.14207650273224043,
319
+ "grad_norm": 0.47907042503356934,
320
+ "learning_rate": 7.649596321166024e-05,
321
+ "loss": 2.6569,
322
+ "step": 39
323
+ },
324
+ {
325
+ "epoch": 0.14571948998178508,
326
+ "grad_norm": 0.5535211563110352,
327
+ "learning_rate": 7.500000000000001e-05,
328
+ "loss": 2.442,
329
+ "step": 40
330
+ },
331
+ {
332
+ "epoch": 0.1493624772313297,
333
+ "grad_norm": 0.4240165650844574,
334
+ "learning_rate": 7.347357813929454e-05,
335
+ "loss": 2.474,
336
+ "step": 41
337
+ },
338
+ {
339
+ "epoch": 0.15300546448087432,
340
+ "grad_norm": 0.48536279797554016,
341
+ "learning_rate": 7.191855733945387e-05,
342
+ "loss": 2.7711,
343
+ "step": 42
344
+ },
345
+ {
346
+ "epoch": 0.15664845173041894,
347
+ "grad_norm": 0.44794994592666626,
348
+ "learning_rate": 7.033683215379002e-05,
349
+ "loss": 2.4307,
350
+ "step": 43
351
+ },
352
+ {
353
+ "epoch": 0.16029143897996356,
354
+ "grad_norm": 0.38578876852989197,
355
+ "learning_rate": 6.873032967079561e-05,
356
+ "loss": 2.5097,
357
+ "step": 44
358
+ },
359
+ {
360
+ "epoch": 0.16393442622950818,
361
+ "grad_norm": 0.4519205093383789,
362
+ "learning_rate": 6.710100716628344e-05,
363
+ "loss": 2.4849,
364
+ "step": 45
365
+ },
366
+ {
367
+ "epoch": 0.16393442622950818,
368
+ "eval_loss": 1.223783016204834,
369
+ "eval_runtime": 36.2336,
370
+ "eval_samples_per_second": 6.375,
371
+ "eval_steps_per_second": 0.8,
372
+ "step": 45
373
+ },
374
+ {
375
+ "epoch": 0.16757741347905283,
376
+ "grad_norm": 0.5709835290908813,
377
+ "learning_rate": 6.545084971874738e-05,
378
+ "loss": 2.6203,
379
+ "step": 46
380
+ },
381
+ {
382
+ "epoch": 0.17122040072859745,
383
+ "grad_norm": 0.5105118155479431,
384
+ "learning_rate": 6.378186779084995e-05,
385
+ "loss": 2.4076,
386
+ "step": 47
387
+ },
388
+ {
389
+ "epoch": 0.17486338797814208,
390
+ "grad_norm": 0.4190482199192047,
391
+ "learning_rate": 6.209609477998338e-05,
392
+ "loss": 2.6536,
393
+ "step": 48
394
+ },
395
+ {
396
+ "epoch": 0.1785063752276867,
397
+ "grad_norm": 0.5616876482963562,
398
+ "learning_rate": 6.0395584540887963e-05,
399
+ "loss": 2.171,
400
+ "step": 49
401
+ },
402
+ {
403
+ "epoch": 0.18214936247723132,
404
+ "grad_norm": 0.47931408882141113,
405
+ "learning_rate": 5.868240888334653e-05,
406
+ "loss": 2.3936,
407
+ "step": 50
408
  }
409
  ],
410
  "logging_steps": 1,
 
424
  "attributes": {}
425
  }
426
  },
427
+ "total_flos": 6.3478299623424e+16,
428
  "train_batch_size": 8,
429
  "trial_name": null,
430
  "trial_params": null