fedovtt commited on
Commit
2016342
·
verified ·
1 Parent(s): 4893e7a

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 sha256:6df402f8e63dba5cf11164bec7ccd2a6028e5a61f3523329ea94fbcd5baf31aa
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ac530c3cdf7ab57f4e6cbdcb7fb96a697f9507336bf714d16a16e1a456b739c
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a43219ff1ba7866551ac0bba45d93e5a319a36aa019f8d0fca4f7318dd98a79f
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4c72aaa6aa6f639e9bc932786d1c3f03f8b50a7b08c1c3b4cf264020b22d85
3
  size 640009682
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5234a81032eee510b6f5ae1f5ad56198035478ffefc47d26d26d050d76b33bcb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0cfc3dbc1f81baef1c47f01d24590b864393562186da63f4fdab5ee803cb939
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
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": 0.06487187804086929,
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": 4.15,
199
  "eval_steps_per_second": 2.082,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -217,7 +400,7 @@
217
  "attributes": {}
218
  }
219
  },
220
- "total_flos": 3.28697269714944e+16,
221
  "train_batch_size": 2,
222
  "trial_name": null,
223
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.12974375608173858,
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": 4.15,
199
  "eval_steps_per_second": 2.082,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.06746675316250406,
204
+ "grad_norm": 15.00766658782959,
205
+ "learning_rate": 7.68649804173412e-05,
206
+ "loss": 0.4404,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.07006162828413882,
211
+ "grad_norm": 13.661465644836426,
212
+ "learning_rate": 7.500000000000001e-05,
213
+ "loss": 0.4163,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.07265650340577359,
218
+ "grad_norm": 19.321388244628906,
219
+ "learning_rate": 7.308743066175172e-05,
220
+ "loss": 0.6755,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.07525137852740837,
225
+ "grad_norm": 22.267826080322266,
226
+ "learning_rate": 7.113091308703498e-05,
227
+ "loss": 0.9669,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.07784625364904314,
232
+ "grad_norm": 7.646611213684082,
233
+ "learning_rate": 6.91341716182545e-05,
234
+ "loss": 0.3168,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.08044112877067791,
239
+ "grad_norm": 36.85639190673828,
240
+ "learning_rate": 6.710100716628344e-05,
241
+ "loss": 1.2373,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.08303600389231268,
246
+ "grad_norm": 10.440677642822266,
247
+ "learning_rate": 6.503528997521366e-05,
248
+ "loss": 1.3768,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.08563087901394745,
253
+ "grad_norm": 38.025997161865234,
254
+ "learning_rate": 6.294095225512603e-05,
255
+ "loss": 0.7102,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.08822575413558223,
260
+ "grad_norm": 10.360336303710938,
261
+ "learning_rate": 6.0821980696905146e-05,
262
+ "loss": 1.5797,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.090820629257217,
267
+ "grad_norm": 19.017549514770508,
268
+ "learning_rate": 5.868240888334653e-05,
269
+ "loss": 1.0114,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.09341550437885177,
274
+ "grad_norm": 44.58971405029297,
275
+ "learning_rate": 5.6526309611002594e-05,
276
+ "loss": 4.6878,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.09601037950048653,
281
+ "grad_norm": 30.749067306518555,
282
+ "learning_rate": 5.435778713738292e-05,
283
+ "loss": 1.1462,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.09860525462212132,
288
+ "grad_norm": 14.544421195983887,
289
+ "learning_rate": 5.218096936826681e-05,
290
+ "loss": 0.3816,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.10120012974375608,
295
+ "grad_norm": 20.164777755737305,
296
+ "learning_rate": 5e-05,
297
+ "loss": 1.1987,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.10379500486539085,
302
+ "grad_norm": 9.724178314208984,
303
+ "learning_rate": 4.781903063173321e-05,
304
+ "loss": 0.3555,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.10638987998702562,
309
+ "grad_norm": 24.466894149780273,
310
+ "learning_rate": 4.564221286261709e-05,
311
+ "loss": 0.6404,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.10898475510866039,
316
+ "grad_norm": 7.151639938354492,
317
+ "learning_rate": 4.347369038899744e-05,
318
+ "loss": 0.3062,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.11157963023029517,
323
+ "grad_norm": 3.3515334129333496,
324
+ "learning_rate": 4.131759111665349e-05,
325
+ "loss": 0.0569,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.11417450535192994,
330
+ "grad_norm": 24.75587272644043,
331
+ "learning_rate": 3.917801930309486e-05,
332
+ "loss": 0.9388,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.11676938047356471,
337
+ "grad_norm": 7.871204376220703,
338
+ "learning_rate": 3.705904774487396e-05,
339
+ "loss": 0.1559,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.11936425559519948,
344
+ "grad_norm": 24.41685676574707,
345
+ "learning_rate": 3.4964710024786354e-05,
346
+ "loss": 0.894,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.12195913071683426,
351
+ "grad_norm": 28.60738182067871,
352
+ "learning_rate": 3.289899283371657e-05,
353
+ "loss": 1.8821,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.12455400583846903,
358
+ "grad_norm": 29.086261749267578,
359
+ "learning_rate": 3.086582838174551e-05,
360
+ "loss": 1.6304,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.1271488809601038,
365
+ "grad_norm": 23.895931243896484,
366
+ "learning_rate": 2.886908691296504e-05,
367
+ "loss": 0.7597,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.12974375608173858,
372
+ "grad_norm": 53.810604095458984,
373
+ "learning_rate": 2.6912569338248315e-05,
374
+ "loss": 2.9703,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.12974375608173858,
379
+ "eval_loss": 0.1682109385728836,
380
+ "eval_runtime": 78.312,
381
+ "eval_samples_per_second": 4.15,
382
+ "eval_steps_per_second": 2.081,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
400
  "attributes": {}
401
  }
402
  },
403
+ "total_flos": 6.57394539429888e+16,
404
  "train_batch_size": 2,
405
  "trial_name": null,
406
  "trial_params": null