diaenra commited on
Commit
a0cde66
1 Parent(s): 98534e6

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 sha256:3612226dc1e5994c776b8f5aba9ff0b99caa90934a619d1cabd2fa985768eb68
3
  size 216151256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f10112e9cef44a1783ae83183ec226e77e0aa765076b98d4bafab696cb30cd
3
  size 216151256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39b860c69612f4a705533c516097591693fb882c0d7b24ace8dca434ebd3225d
3
  size 432640054
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139b94d97f57bc43c1f37d3f05ef905c461dfd01b640bd9e5603913a53d72f7f
3
  size 432640054
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3233b2c1d81f526ea891c28e383ed026dc217699cb47deb84cf150984410f49a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:444a1343202e84b85beae9482da900be504c62c1030c70496984ce2847da3967
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": 3.883234739303589,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.1443001443001443,
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": 2.442,
199
  "eval_steps_per_second": 1.238,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -221,12 +404,12 @@
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": 4.11806271012864e+16,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.52176570892334,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.2886002886002886,
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": 2.442,
199
  "eval_steps_per_second": 1.238,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.15007215007215008,
204
+ "grad_norm": 5.483874320983887,
205
+ "learning_rate": 0.0001,
206
+ "loss": 2.8525,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.15584415584415584,
211
+ "grad_norm": 4.851412296295166,
212
+ "learning_rate": 9.345968707698569e-05,
213
+ "loss": 3.1477,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.16161616161616163,
218
+ "grad_norm": 5.818398952484131,
219
+ "learning_rate": 8.694738077799488e-05,
220
+ "loss": 3.1177,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.1673881673881674,
225
+ "grad_norm": 6.832301139831543,
226
+ "learning_rate": 8.049096779838719e-05,
227
+ "loss": 3.5393,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.17316017316017315,
232
+ "grad_norm": 5.470390319824219,
233
+ "learning_rate": 7.411809548974792e-05,
234
+ "loss": 3.6273,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.17893217893217894,
239
+ "grad_norm": 7.099745750427246,
240
+ "learning_rate": 6.785605346968386e-05,
241
+ "loss": 2.8683,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.1847041847041847,
246
+ "grad_norm": 6.852536678314209,
247
+ "learning_rate": 6.173165676349103e-05,
248
+ "loss": 4.697,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.19047619047619047,
253
+ "grad_norm": 7.737475395202637,
254
+ "learning_rate": 5.577113097809989e-05,
255
+ "loss": 5.2704,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.19624819624819625,
260
+ "grad_norm": 8.485671997070312,
261
+ "learning_rate": 5.000000000000002e-05,
262
+ "loss": 4.3796,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.20202020202020202,
267
+ "grad_norm": 5.709878444671631,
268
+ "learning_rate": 4.444297669803981e-05,
269
+ "loss": 3.9743,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.2077922077922078,
274
+ "grad_norm": 5.483663082122803,
275
+ "learning_rate": 3.9123857099127936e-05,
276
+ "loss": 3.9421,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.21356421356421357,
281
+ "grad_norm": 4.827873706817627,
282
+ "learning_rate": 3.406541848999312e-05,
283
+ "loss": 4.0746,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.21933621933621933,
288
+ "grad_norm": 15.908256530761719,
289
+ "learning_rate": 2.9289321881345254e-05,
290
+ "loss": 7.8459,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.22510822510822512,
295
+ "grad_norm": 17.669963836669922,
296
+ "learning_rate": 2.4816019252102273e-05,
297
+ "loss": 7.6677,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.23088023088023088,
302
+ "grad_norm": 15.907238006591797,
303
+ "learning_rate": 2.0664665970876496e-05,
304
+ "loss": 6.4001,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.23665223665223664,
309
+ "grad_norm": 11.9762601852417,
310
+ "learning_rate": 1.6853038769745467e-05,
311
+ "loss": 7.4365,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.24242424242424243,
316
+ "grad_norm": 8.19090461730957,
317
+ "learning_rate": 1.339745962155613e-05,
318
+ "loss": 6.703,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.2481962481962482,
323
+ "grad_norm": 8.14680290222168,
324
+ "learning_rate": 1.0312725846731175e-05,
325
+ "loss": 7.3564,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.25396825396825395,
330
+ "grad_norm": 7.9732561111450195,
331
+ "learning_rate": 7.612046748871327e-06,
332
+ "loss": 2.4814,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.2597402597402597,
337
+ "grad_norm": 8.285723686218262,
338
+ "learning_rate": 5.306987050489442e-06,
339
+ "loss": 3.1881,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.26551226551226553,
344
+ "grad_norm": 10.690110206604004,
345
+ "learning_rate": 3.40741737109318e-06,
346
+ "loss": 3.5401,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.2712842712842713,
351
+ "grad_norm": 9.28165340423584,
352
+ "learning_rate": 1.921471959676957e-06,
353
+ "loss": 3.6229,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.27705627705627706,
358
+ "grad_norm": 12.119881629943848,
359
+ "learning_rate": 8.555138626189618e-07,
360
+ "loss": 3.1769,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.2828282828282828,
365
+ "grad_norm": 8.861678123474121,
366
+ "learning_rate": 2.141076761396521e-07,
367
+ "loss": 3.5118,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.2886002886002886,
372
+ "grad_norm": 9.257101058959961,
373
+ "learning_rate": 0.0,
374
+ "loss": 3.6435,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.2886002886002886,
379
+ "eval_loss": 3.52176570892334,
380
+ "eval_runtime": 29.8722,
381
+ "eval_samples_per_second": 2.444,
382
+ "eval_steps_per_second": 1.239,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
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": 8.23612542025728e+16,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null