dzanbek commited on
Commit
b96a396
1 Parent(s): 32a61c7

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 sha256:315177a280ed98fedbd06d6fb34c0b3028cd61cfaadfc54a0543a0f3be5e9033
3
  size 200068512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37891a14a2d3119c765795bdf86a78c31f6e7848f4ea513b86496f3fc699b280
3
  size 200068512
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91c337a26b4ee68d3244b4bb71462e7b6c343332f716e6c04fc1689fdc2a4b5c
3
  size 400361770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9eb18e96ecfd6cac2134a0ec12639aabc6b79e9871ebd290890eccadb5c3873
3
  size 400361770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7872bf1923164f321afe3cb8b99acb68831b19235f469d62438123cc50586006
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3c6fe1e3951058283a55e7cfcd33b71182bc4fe2888cbb45fcc91b68e90260
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.03240440699935191,
5
  "eval_steps": 500,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -182,6 +182,181 @@
182
  "learning_rate": 0.00010654031292301432,
183
  "loss": 0.016,
184
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
185
  }
186
  ],
187
  "logging_steps": 1,
@@ -196,12 +371,12 @@
196
  "should_evaluate": false,
197
  "should_log": false,
198
  "should_save": true,
199
- "should_training_stop": false
200
  },
201
  "attributes": {}
202
  }
203
  },
204
- "total_flos": 3.83447180771328e+16,
205
  "train_batch_size": 2,
206
  "trial_name": null,
207
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.06480881399870382,
5
  "eval_steps": 500,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
182
  "learning_rate": 0.00010654031292301432,
183
  "loss": 0.016,
184
  "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.033700583279325985,
188
+ "grad_norm": 0.2556341290473938,
189
+ "learning_rate": 0.0001,
190
+ "loss": 0.0023,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.03499675955930007,
195
+ "grad_norm": 0.6813236474990845,
196
+ "learning_rate": 9.345968707698569e-05,
197
+ "loss": 0.0188,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.03629293583927414,
202
+ "grad_norm": 0.08286161720752716,
203
+ "learning_rate": 8.694738077799488e-05,
204
+ "loss": 0.0007,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.037589112119248216,
209
+ "grad_norm": 0.7052176594734192,
210
+ "learning_rate": 8.049096779838719e-05,
211
+ "loss": 0.0111,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.03888528839922229,
216
+ "grad_norm": 0.5274888277053833,
217
+ "learning_rate": 7.411809548974792e-05,
218
+ "loss": 0.0241,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.04018146467919637,
223
+ "grad_norm": 0.08222157508134842,
224
+ "learning_rate": 6.785605346968386e-05,
225
+ "loss": 0.0008,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.04147764095917045,
230
+ "grad_norm": 0.2739109992980957,
231
+ "learning_rate": 6.173165676349103e-05,
232
+ "loss": 0.0114,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.04277381723914452,
237
+ "grad_norm": 0.8266695737838745,
238
+ "learning_rate": 5.577113097809989e-05,
239
+ "loss": 0.0359,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.0440699935191186,
244
+ "grad_norm": 0.05991604924201965,
245
+ "learning_rate": 5.000000000000002e-05,
246
+ "loss": 0.0006,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.04536616979909268,
251
+ "grad_norm": 0.7909983396530151,
252
+ "learning_rate": 4.444297669803981e-05,
253
+ "loss": 0.0127,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.046662346079066754,
258
+ "grad_norm": 0.01229810994118452,
259
+ "learning_rate": 3.9123857099127936e-05,
260
+ "loss": 0.0002,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.04795852235904083,
265
+ "grad_norm": 0.0124417245388031,
266
+ "learning_rate": 3.406541848999312e-05,
267
+ "loss": 0.0002,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.0492546986390149,
272
+ "grad_norm": 0.27802836894989014,
273
+ "learning_rate": 2.9289321881345254e-05,
274
+ "loss": 0.0061,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.050550874918988985,
279
+ "grad_norm": 0.2801899313926697,
280
+ "learning_rate": 2.4816019252102273e-05,
281
+ "loss": 0.0025,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.05184705119896306,
286
+ "grad_norm": 0.4654271602630615,
287
+ "learning_rate": 2.0664665970876496e-05,
288
+ "loss": 0.014,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.053143227478937134,
293
+ "grad_norm": 2.02001690864563,
294
+ "learning_rate": 1.6853038769745467e-05,
295
+ "loss": 0.0504,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.05443940375891121,
300
+ "grad_norm": 0.3809402883052826,
301
+ "learning_rate": 1.339745962155613e-05,
302
+ "loss": 0.024,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.05573558003888529,
307
+ "grad_norm": 0.174382284283638,
308
+ "learning_rate": 1.0312725846731175e-05,
309
+ "loss": 0.0018,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.057031756318859365,
314
+ "grad_norm": 0.7362247705459595,
315
+ "learning_rate": 7.612046748871327e-06,
316
+ "loss": 0.0051,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.05832793259883344,
321
+ "grad_norm": 0.7474696040153503,
322
+ "learning_rate": 5.306987050489442e-06,
323
+ "loss": 0.0234,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.059624108878807515,
328
+ "grad_norm": 0.5843119621276855,
329
+ "learning_rate": 3.40741737109318e-06,
330
+ "loss": 0.01,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.0609202851587816,
335
+ "grad_norm": 0.575708270072937,
336
+ "learning_rate": 1.921471959676957e-06,
337
+ "loss": 0.0195,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.06221646143875567,
342
+ "grad_norm": 0.33101776242256165,
343
+ "learning_rate": 8.555138626189618e-07,
344
+ "loss": 0.0036,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.06351263771872975,
349
+ "grad_norm": 0.9009850025177002,
350
+ "learning_rate": 2.141076761396521e-07,
351
+ "loss": 0.0141,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.06480881399870382,
356
+ "grad_norm": 0.6479219198226929,
357
+ "learning_rate": 0.0,
358
+ "loss": 0.0065,
359
+ "step": 50
360
  }
361
  ],
362
  "logging_steps": 1,
 
371
  "should_evaluate": false,
372
  "should_log": false,
373
  "should_save": true,
374
+ "should_training_stop": true
375
  },
376
  "attributes": {}
377
  }
378
  },
379
+ "total_flos": 7.66894361542656e+16,
380
  "train_batch_size": 2,
381
  "trial_name": null,
382
  "trial_params": null