dsakerkwq commited on
Commit
f0e394d
1 Parent(s): cd52b9a

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 sha256:1099dc82dbb3ebbe9911478b3468591f718b37c7547970948e1d23c1d8d244ce
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d4bdaf38d516bfb25e1c94a09135ed7012570b91266244d6461fe354b3af29
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90bd9ae4545500229a718a1819ca2e24e941f59d624d9ef1a733cbdbcb9514de
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b96f1680a4903c82ecb6049a2a3b05ce8ef7573fe1273e81dd8b847d4eabd6
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 sha256:48b73d85b5d11812d53b2f56adb534519d10e877c96d5da23c98726134d6e63c
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a346fc91c0e450dac17c1c77cfeed2f9a6accf0a239967a00102891876ab05d
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 sha256:7bc7eed2e4201c2206188a5d33ae2049cbde04c17e40ee426684a0aa529e924e
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:163d9b7bf2410627c1fa1f5f1c197202b3e9cee74e525404c7f5c97b6e97836f
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 sha256:5bd1bb873a39567c690744ec17d002143b09095ab9ccdae25cdfc0cc568d70d2
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:851ea0747f29183ac5351c9da7fe604dbc7f49700311a5d4ea3354b0e4f4b958
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 sha256:29e77c847da734a9b50c99436bdc5cbe4883c2889bc1e6b5e96bce1246fc65e7
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:520aad99c25b64197809e3c734f7d9a0379e7e8d47f4ebefa0e7f4cff756a469
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": 0.30715107917785645,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.055282979752608666,
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": 16.312,
199
  "eval_steps_per_second": 4.241,
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": 2.829013890367488e+17,
230
  "train_batch_size": 1,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.2368658483028412,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.11056595950521733,
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": 16.312,
199
  "eval_steps_per_second": 4.241,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.05749429894271301,
204
+ "grad_norm": 112.55488586425781,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 9.1382,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.059705618132817356,
211
+ "grad_norm": 166.33534240722656,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 9.9689,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.06191693732292171,
218
+ "grad_norm": 146.36526489257812,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 10.5303,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.06412825651302605,
225
+ "grad_norm": 121.34736633300781,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 9.7238,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.0663395757031304,
232
+ "grad_norm": 87.24940490722656,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 6.6125,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.06855089489323475,
239
+ "grad_norm": 96.96258544921875,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 8.0596,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.07076221408333909,
246
+ "grad_norm": 122.00680541992188,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 8.7681,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.07297353327344344,
253
+ "grad_norm": 114.9303207397461,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 10.3328,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.07518485246354778,
260
+ "grad_norm": 112.72858428955078,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 8.9349,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.07739617165365213,
267
+ "grad_norm": 100.95106506347656,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 8.6053,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.07960749084375648,
274
+ "grad_norm": 95.06898498535156,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 7.9513,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.08181881003386082,
281
+ "grad_norm": 101.6524658203125,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 8.3089,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.08403012922396517,
288
+ "grad_norm": 89.02762603759766,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 6.7646,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.08624144841406951,
295
+ "grad_norm": 184.59141540527344,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 12.0435,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.08845276760417387,
302
+ "grad_norm": 123.04720306396484,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 8.9847,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.09066408679427822,
309
+ "grad_norm": 127.1465072631836,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 9.742,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.09287540598438256,
316
+ "grad_norm": 91.50184631347656,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 8.8613,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.09508672517448691,
323
+ "grad_norm": 121.56517791748047,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 11.1114,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.09729804436459125,
330
+ "grad_norm": 167.5218048095703,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 8.5462,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.0995093635546956,
337
+ "grad_norm": 109.18016815185547,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 6.4312,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.10172068274479995,
344
+ "grad_norm": 119.26715087890625,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 6.6959,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.10393200193490429,
351
+ "grad_norm": 88.47723388671875,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 7.4441,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.10614332112500864,
358
+ "grad_norm": 90.03621673583984,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 6.4245,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.10835464031511298,
365
+ "grad_norm": 180.63720703125,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 9.3648,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.11056595950521733,
372
+ "grad_norm": 119.29557800292969,
373
+ "learning_rate": 1e-05,
374
+ "loss": 9.1602,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.11056595950521733,
379
+ "eval_loss": 0.2368658483028412,
380
+ "eval_runtime": 3.0471,
381
+ "eval_samples_per_second": 16.409,
382
+ "eval_steps_per_second": 4.266,
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": 5.658027780734976e+17,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null