DeepDream2045 commited on
Commit
5afe5fd
1 Parent(s): ccc0772

Training in progress, step 25, checkpoint

Browse files
last-checkpoint/adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "q_proj",
24
  "k_proj",
25
- "down_proj",
26
  "up_proj",
27
  "v_proj",
28
- "o_proj",
 
29
  "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "k_proj",
24
+ "o_proj",
25
  "up_proj",
26
  "v_proj",
27
+ "down_proj",
28
+ "q_proj",
29
  "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c6c3b49517918f71b5a8df86ce64802524c101812f6310fcee02fef5d317af6
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecacf0120c3313aa6d110d54cdb0747ee47b71b2cd60beeadeed0c4feac79962
3
  size 671466706
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4096bbde6d582953ae6d3e0451be1d831604d98af6d8a1de69bbcb44ff1e950
3
- size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d1f61bfc6ffc8d8e1c8ff53a0044cf9902a1ddf2c637f9612610bf4762747d
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 sha256:1cdc5d4fb006b4b93de906620f37a527e4627449685bf46a5ac4411228b2cb2f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f616f705ba7cb291af7d9f513f11d6e0e42ec727e886627085ef561e88f6bad
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:cbe389e1cf00ae954d39bffec47561432676c1e4ab5f84230142dbc16ac036f4
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d30fd2f50252b0b0137d88cde7a2c3bc7bdfb6dc03455e0923b6a91b2be12da1
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:aa6ef691995f1233121abf8096e6f45d06d1dd2fab2496a7e8a454c331df8991
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd2dda9948c4cbe11886349ce34a931605871e324bf11c12c42b99ab05f62fb
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.029967036260113874,
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,
@@ -18,9 +18,9 @@
18
  {
19
  "epoch": 0.0005993407252022775,
20
  "eval_loss": NaN,
21
- "eval_runtime": 302.1838,
22
- "eval_samples_per_second": 37.199,
23
- "eval_steps_per_second": 4.653,
24
  "step": 1
25
  },
26
  {
@@ -194,193 +194,10 @@
194
  {
195
  "epoch": 0.014983518130056937,
196
  "eval_loss": NaN,
197
- "eval_runtime": 302.4917,
198
- "eval_samples_per_second": 37.161,
199
- "eval_steps_per_second": 4.648,
200
  "step": 25
201
- },
202
- {
203
- "epoch": 0.015582858855259216,
204
- "grad_norm": NaN,
205
- "learning_rate": 5e-05,
206
- "loss": 0.0,
207
- "step": 26
208
- },
209
- {
210
- "epoch": 0.016182199580461493,
211
- "grad_norm": NaN,
212
- "learning_rate": 4.6729843538492847e-05,
213
- "loss": 0.0,
214
- "step": 27
215
- },
216
- {
217
- "epoch": 0.01678154030566377,
218
- "grad_norm": NaN,
219
- "learning_rate": 4.347369038899744e-05,
220
- "loss": 0.0,
221
- "step": 28
222
- },
223
- {
224
- "epoch": 0.017380881030866047,
225
- "grad_norm": NaN,
226
- "learning_rate": 4.0245483899193595e-05,
227
- "loss": 0.0,
228
- "step": 29
229
- },
230
- {
231
- "epoch": 0.017980221756068324,
232
- "grad_norm": NaN,
233
- "learning_rate": 3.705904774487396e-05,
234
- "loss": 0.0,
235
- "step": 30
236
- },
237
- {
238
- "epoch": 0.0185795624812706,
239
- "grad_norm": NaN,
240
- "learning_rate": 3.392802673484193e-05,
241
- "loss": 0.0,
242
- "step": 31
243
- },
244
- {
245
- "epoch": 0.01917890320647288,
246
- "grad_norm": NaN,
247
- "learning_rate": 3.086582838174551e-05,
248
- "loss": 0.0,
249
- "step": 32
250
- },
251
- {
252
- "epoch": 0.019778243931675158,
253
- "grad_norm": NaN,
254
- "learning_rate": 2.7885565489049946e-05,
255
- "loss": 0.0,
256
- "step": 33
257
- },
258
- {
259
- "epoch": 0.020377584656877435,
260
- "grad_norm": NaN,
261
- "learning_rate": 2.500000000000001e-05,
262
- "loss": 0.0,
263
- "step": 34
264
- },
265
- {
266
- "epoch": 0.020976925382079712,
267
- "grad_norm": NaN,
268
- "learning_rate": 2.2221488349019903e-05,
269
- "loss": 0.0,
270
- "step": 35
271
- },
272
- {
273
- "epoch": 0.02157626610728199,
274
- "grad_norm": NaN,
275
- "learning_rate": 1.9561928549563968e-05,
276
- "loss": 0.0,
277
- "step": 36
278
- },
279
- {
280
- "epoch": 0.022175606832484266,
281
- "grad_norm": NaN,
282
- "learning_rate": 1.703270924499656e-05,
283
- "loss": 0.0,
284
- "step": 37
285
- },
286
- {
287
- "epoch": 0.022774947557686546,
288
- "grad_norm": NaN,
289
- "learning_rate": 1.4644660940672627e-05,
290
- "loss": 0.0,
291
- "step": 38
292
- },
293
- {
294
- "epoch": 0.023374288282888823,
295
- "grad_norm": NaN,
296
- "learning_rate": 1.2408009626051137e-05,
297
- "loss": 0.0,
298
- "step": 39
299
- },
300
- {
301
- "epoch": 0.0239736290080911,
302
- "grad_norm": NaN,
303
- "learning_rate": 1.0332332985438248e-05,
304
- "loss": 0.0,
305
- "step": 40
306
- },
307
- {
308
- "epoch": 0.024572969733293377,
309
- "grad_norm": NaN,
310
- "learning_rate": 8.426519384872733e-06,
311
- "loss": 0.0,
312
- "step": 41
313
- },
314
- {
315
- "epoch": 0.025172310458495654,
316
- "grad_norm": NaN,
317
- "learning_rate": 6.698729810778065e-06,
318
- "loss": 0.0,
319
- "step": 42
320
- },
321
- {
322
- "epoch": 0.02577165118369793,
323
- "grad_norm": NaN,
324
- "learning_rate": 5.156362923365588e-06,
325
- "loss": 0.0,
326
- "step": 43
327
- },
328
- {
329
- "epoch": 0.02637099190890021,
330
- "grad_norm": NaN,
331
- "learning_rate": 3.8060233744356633e-06,
332
- "loss": 0.0,
333
- "step": 44
334
- },
335
- {
336
- "epoch": 0.02697033263410249,
337
- "grad_norm": NaN,
338
- "learning_rate": 2.653493525244721e-06,
339
- "loss": 0.0,
340
- "step": 45
341
- },
342
- {
343
- "epoch": 0.027569673359304766,
344
- "grad_norm": NaN,
345
- "learning_rate": 1.70370868554659e-06,
346
- "loss": 0.0,
347
- "step": 46
348
- },
349
- {
350
- "epoch": 0.028169014084507043,
351
- "grad_norm": NaN,
352
- "learning_rate": 9.607359798384785e-07,
353
- "loss": 0.0,
354
- "step": 47
355
- },
356
- {
357
- "epoch": 0.02876835480970932,
358
- "grad_norm": NaN,
359
- "learning_rate": 4.277569313094809e-07,
360
- "loss": 0.0,
361
- "step": 48
362
- },
363
- {
364
- "epoch": 0.029367695534911597,
365
- "grad_norm": NaN,
366
- "learning_rate": 1.0705383806982606e-07,
367
- "loss": 0.0,
368
- "step": 49
369
- },
370
- {
371
- "epoch": 0.029967036260113874,
372
- "grad_norm": NaN,
373
- "learning_rate": 0.0,
374
- "loss": 0.0,
375
- "step": 50
376
- },
377
- {
378
- "epoch": 0.029967036260113874,
379
- "eval_loss": NaN,
380
- "eval_runtime": 301.9125,
381
- "eval_samples_per_second": 37.233,
382
- "eval_steps_per_second": 4.657,
383
- "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
@@ -395,7 +212,7 @@
395
  "early_stopping_threshold": 0.0
396
  },
397
  "attributes": {
398
- "early_stopping_patience_counter": 1
399
  }
400
  },
401
  "TrainerControl": {
@@ -404,12 +221,12 @@
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": 5.658027780734976e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null
 
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
+ "epoch": 0.014983518130056937,
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,
 
18
  {
19
  "epoch": 0.0005993407252022775,
20
  "eval_loss": NaN,
21
+ "eval_runtime": 619.6678,
22
+ "eval_samples_per_second": 18.14,
23
+ "eval_steps_per_second": 2.269,
24
  "step": 1
25
  },
26
  {
 
194
  {
195
  "epoch": 0.014983518130056937,
196
  "eval_loss": NaN,
197
+ "eval_runtime": 620.162,
198
+ "eval_samples_per_second": 18.126,
199
+ "eval_steps_per_second": 2.267,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
 
212
  "early_stopping_threshold": 0.0
213
  },
214
  "attributes": {
215
+ "early_stopping_patience_counter": 0
216
  }
217
  },
218
  "TrainerControl": {
 
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": 2.829013890367488e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f3518b5c56f452274c8d035d0612a31cf62121706984847bd1089aad20b8410
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0f2acb7d5fd05e7352048c13298f1bc785726fd9d87185bd40cad477c92f76
3
  size 6776