dsakerkwq commited on
Commit
e003062
1 Parent(s): b0a6bb8

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:b603b2ae456db6f899005a714748168a0cbed2708faa43b2a70e5b5d2da13f13
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fa4c7ff4d8e4168e3d79e4fec7bcff4b5919d0bb57fc787febecb005b5107b6
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65c1ff41fc660fdec4b5bb50472664ed93ad0f26a83f57d278b231ae59a18b66
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e30e3062bff1b36b6eebf7a8441924f9ea64a325862dda5dc353c27a0d54d772
3
  size 640009682
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd46732ea485a8c6d4076bcb2969fd03c7f8db3074ad048ed1dc69441e817149
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef658ddb0029cb254e393761787b71e6accc3be330001e6ed073cc2fc293dbef
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:f50f069b647594212794bb73b151ac9bcf9c62cac99bcae8561b681f41a5674f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30ed8e4a89ffdbeb53b8cf8c81ff8d6f3535bdec41ad30d9d01d00c9c089a2ca
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 sha256:8137d5dd5332cf90e24a223ec76efe8ad77dd5918605ed9ea781120e3030282c
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fee7afbde275e53b70160fc284c0a4ff30d879fb0f426acd7fe144bf3c906df
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 sha256:7c2e2f7af63318c8ed77ae9f1567da8f9cbf09ab18f5bdea364d626296a93e6e
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebbfc374e3b39a496828d0d262a34379f096fc2620909130b5d8eb8b6dbdbf51
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1061513423919678,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.012519953676171399,
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": 21.391,
199
  "eval_steps_per_second": 5.562,
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": 2.9582754301188506e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0602198839187622,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.025039907352342797,
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": 21.391,
199
  "eval_steps_per_second": 5.562,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.013020751823218255,
204
+ "grad_norm": 6.150357246398926,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 20.203,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.01352154997026511,
211
+ "grad_norm": 7.324110984802246,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 20.2245,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.014022348117311966,
218
+ "grad_norm": 4.4846391677856445,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 17.0902,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.014523146264358822,
225
+ "grad_norm": 4.2537126541137695,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 17.783,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.015023944411405678,
232
+ "grad_norm": 3.3687477111816406,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 19.8318,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.015524742558452534,
239
+ "grad_norm": 3.4171719551086426,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 17.4442,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.01602554070549939,
246
+ "grad_norm": 4.006035327911377,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 17.9844,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.016526338852546247,
253
+ "grad_norm": 4.396282196044922,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 18.255,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.0170271369995931,
260
+ "grad_norm": 4.883106231689453,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 18.8518,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.01752793514663996,
267
+ "grad_norm": 5.509437561035156,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 17.9827,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.018028733293686813,
274
+ "grad_norm": 4.919665813446045,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 15.706,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.01852953144073367,
281
+ "grad_norm": 6.44651460647583,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 16.1781,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.019030329587780524,
288
+ "grad_norm": 5.128076553344727,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 21.4918,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.019531127734827382,
295
+ "grad_norm": 9.525840759277344,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 21.2966,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.020031925881874236,
302
+ "grad_norm": 3.75991153717041,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 17.6723,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.020532724028921093,
309
+ "grad_norm": 3.4625003337860107,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 15.4358,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.021033522175967947,
316
+ "grad_norm": 4.435390472412109,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 17.5912,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.021534320323014805,
323
+ "grad_norm": 4.710116386413574,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 16.8838,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.02203511847006166,
330
+ "grad_norm": 4.531633377075195,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 17.465,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.022535916617108517,
337
+ "grad_norm": 3.9686601161956787,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 17.882,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.023036714764155374,
344
+ "grad_norm": 3.2548906803131104,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 17.3054,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.02353751291120223,
351
+ "grad_norm": 3.3293542861938477,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 16.5476,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.024038311058249086,
358
+ "grad_norm": 3.773627996444702,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 16.9503,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.02453910920529594,
365
+ "grad_norm": 3.537731647491455,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 14.9813,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.025039907352342797,
372
+ "grad_norm": 6.06915283203125,
373
+ "learning_rate": 1e-05,
374
+ "loss": 17.1321,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.025039907352342797,
379
+ "eval_loss": 1.0602198839187622,
380
+ "eval_runtime": 2.2315,
381
+ "eval_samples_per_second": 22.407,
382
+ "eval_steps_per_second": 5.826,
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": 5.9050464574754e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null