lesso05 commited on
Commit
d8cac87
·
verified ·
1 Parent(s): 0615f1b

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:fa73689c5a6974ea93065ed42bc5f2b379044d0a4787d5a351daa4181c8f665e
3
  size 2269195160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b415a21ad762c5e830744ee0c36e01d94d1b4b59c769bac5981ae5a60672a7bc
3
  size 2269195160
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3dd41d7bfc891c5f8700bee952014fd977e1aa64b3c2971a5290f1b58314995d
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b2e074c6d58dccbf42b5483f8523a085996cf33cf4f8961fdfb79e0d5f24be
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7dccf15704fbdf23856e1119baffae48b962f09fb2232cc45a115390986e7d5d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:828a7e6e11ce6fb1a2356180954a5b20df0e28e99bfb6b79a96217eb20a3be28
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": 0.0023720290336353717,
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": 1.5855,
208
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
209
  }
210
  ],
211
  "logging_steps": 1,
@@ -225,7 +424,7 @@
225
  "attributes": {}
226
  }
227
  },
228
- "total_flos": 1.85471921553408e+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": 0.0047440580672707434,
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": 1.5855,
208
  "step": 25
209
+ },
210
+ {
211
+ "epoch": 0.0024669101949807864,
212
+ "grad_norm": 0.8661882877349854,
213
+ "learning_rate": 9.24024048078213e-05,
214
+ "loss": 1.5336,
215
+ "step": 26
216
+ },
217
+ {
218
+ "epoch": 0.0025617913563262015,
219
+ "grad_norm": 0.9252780675888062,
220
+ "learning_rate": 9.145187862775209e-05,
221
+ "loss": 1.6042,
222
+ "step": 27
223
+ },
224
+ {
225
+ "epoch": 0.0025617913563262015,
226
+ "eval_loss": 1.634818196296692,
227
+ "eval_runtime": 1085.0329,
228
+ "eval_samples_per_second": 8.18,
229
+ "eval_steps_per_second": 1.023,
230
+ "step": 27
231
+ },
232
+ {
233
+ "epoch": 0.002656672517671616,
234
+ "grad_norm": 1.040569543838501,
235
+ "learning_rate": 9.045084971874738e-05,
236
+ "loss": 1.6379,
237
+ "step": 28
238
+ },
239
+ {
240
+ "epoch": 0.0027515536790170313,
241
+ "grad_norm": 0.934683084487915,
242
+ "learning_rate": 8.940053768033609e-05,
243
+ "loss": 1.5159,
244
+ "step": 29
245
+ },
246
+ {
247
+ "epoch": 0.002846434840362446,
248
+ "grad_norm": 0.908628523349762,
249
+ "learning_rate": 8.83022221559489e-05,
250
+ "loss": 1.5628,
251
+ "step": 30
252
+ },
253
+ {
254
+ "epoch": 0.002941316001707861,
255
+ "grad_norm": 0.8518630862236023,
256
+ "learning_rate": 8.715724127386972e-05,
257
+ "loss": 1.5605,
258
+ "step": 31
259
+ },
260
+ {
261
+ "epoch": 0.0030361971630532758,
262
+ "grad_norm": 0.9292842149734497,
263
+ "learning_rate": 8.596699001693255e-05,
264
+ "loss": 1.6211,
265
+ "step": 32
266
+ },
267
+ {
268
+ "epoch": 0.0031310783243986904,
269
+ "grad_norm": 0.9021596312522888,
270
+ "learning_rate": 8.473291852294987e-05,
271
+ "loss": 1.6151,
272
+ "step": 33
273
+ },
274
+ {
275
+ "epoch": 0.0032259594857441056,
276
+ "grad_norm": 0.8258885741233826,
277
+ "learning_rate": 8.345653031794292e-05,
278
+ "loss": 1.6105,
279
+ "step": 34
280
+ },
281
+ {
282
+ "epoch": 0.0033208406470895202,
283
+ "grad_norm": 0.8333180546760559,
284
+ "learning_rate": 8.213938048432697e-05,
285
+ "loss": 1.4312,
286
+ "step": 35
287
+ },
288
+ {
289
+ "epoch": 0.0034157218084349353,
290
+ "grad_norm": 0.9054083824157715,
291
+ "learning_rate": 8.07830737662829e-05,
292
+ "loss": 1.6345,
293
+ "step": 36
294
+ },
295
+ {
296
+ "epoch": 0.0034157218084349353,
297
+ "eval_loss": 1.6105045080184937,
298
+ "eval_runtime": 1084.7416,
299
+ "eval_samples_per_second": 8.183,
300
+ "eval_steps_per_second": 1.023,
301
+ "step": 36
302
+ },
303
+ {
304
+ "epoch": 0.00351060296978035,
305
+ "grad_norm": 0.9723847508430481,
306
+ "learning_rate": 7.938926261462366e-05,
307
+ "loss": 1.5801,
308
+ "step": 37
309
+ },
310
+ {
311
+ "epoch": 0.003605484131125765,
312
+ "grad_norm": 0.9598375558853149,
313
+ "learning_rate": 7.795964517353735e-05,
314
+ "loss": 1.7289,
315
+ "step": 38
316
+ },
317
+ {
318
+ "epoch": 0.00370036529247118,
319
+ "grad_norm": 0.7757585644721985,
320
+ "learning_rate": 7.649596321166024e-05,
321
+ "loss": 1.3911,
322
+ "step": 39
323
+ },
324
+ {
325
+ "epoch": 0.003795246453816595,
326
+ "grad_norm": 0.9091125726699829,
327
+ "learning_rate": 7.500000000000001e-05,
328
+ "loss": 1.6503,
329
+ "step": 40
330
+ },
331
+ {
332
+ "epoch": 0.0038901276151620096,
333
+ "grad_norm": 0.82570880651474,
334
+ "learning_rate": 7.347357813929454e-05,
335
+ "loss": 1.5909,
336
+ "step": 41
337
+ },
338
+ {
339
+ "epoch": 0.003985008776507424,
340
+ "grad_norm": 0.892005205154419,
341
+ "learning_rate": 7.191855733945387e-05,
342
+ "loss": 1.5125,
343
+ "step": 42
344
+ },
345
+ {
346
+ "epoch": 0.004079889937852839,
347
+ "grad_norm": 0.9276201128959656,
348
+ "learning_rate": 7.033683215379002e-05,
349
+ "loss": 1.554,
350
+ "step": 43
351
+ },
352
+ {
353
+ "epoch": 0.0041747710991982545,
354
+ "grad_norm": 0.9247840642929077,
355
+ "learning_rate": 6.873032967079561e-05,
356
+ "loss": 1.5783,
357
+ "step": 44
358
+ },
359
+ {
360
+ "epoch": 0.004269652260543669,
361
+ "grad_norm": 0.7888846397399902,
362
+ "learning_rate": 6.710100716628344e-05,
363
+ "loss": 1.6686,
364
+ "step": 45
365
+ },
366
+ {
367
+ "epoch": 0.004269652260543669,
368
+ "eval_loss": 1.599737524986267,
369
+ "eval_runtime": 1084.3859,
370
+ "eval_samples_per_second": 8.185,
371
+ "eval_steps_per_second": 1.024,
372
+ "step": 45
373
+ },
374
+ {
375
+ "epoch": 0.004364533421889084,
376
+ "grad_norm": 0.8548523187637329,
377
+ "learning_rate": 6.545084971874738e-05,
378
+ "loss": 1.7366,
379
+ "step": 46
380
+ },
381
+ {
382
+ "epoch": 0.004459414583234499,
383
+ "grad_norm": 0.9126039147377014,
384
+ "learning_rate": 6.378186779084995e-05,
385
+ "loss": 1.7126,
386
+ "step": 47
387
+ },
388
+ {
389
+ "epoch": 0.004554295744579914,
390
+ "grad_norm": 0.8707435727119446,
391
+ "learning_rate": 6.209609477998338e-05,
392
+ "loss": 1.595,
393
+ "step": 48
394
+ },
395
+ {
396
+ "epoch": 0.004649176905925328,
397
+ "grad_norm": 0.9774793386459351,
398
+ "learning_rate": 6.0395584540887963e-05,
399
+ "loss": 1.6117,
400
+ "step": 49
401
+ },
402
+ {
403
+ "epoch": 0.0047440580672707434,
404
+ "grad_norm": 0.96619713306427,
405
+ "learning_rate": 5.868240888334653e-05,
406
+ "loss": 1.7324,
407
+ "step": 50
408
  }
409
  ],
410
  "logging_steps": 1,
 
424
  "attributes": {}
425
  }
426
  },
427
+ "total_flos": 3.70943843106816e+16,
428
  "train_batch_size": 8,
429
  "trial_name": null,
430
  "trial_params": null