eeeebbb2 commited on
Commit
06e9641
1 Parent(s): 2458c3b

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:c3eb2ed91b0373817fde5fcfa2076eb4a3d94fea0d49aac042fe5bcc55d4f7be
3
  size 156926880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2da984e0d5eb8b75c69588783b787576367fce9639778e0d2e364ac7e05126d0
3
  size 156926880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79a406a2af918ae33ef5c04eef31c029e03966a0735141aca7ec0f68bbc98e8a
3
  size 313998650
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d24e2c3b61d2076c78c4e8ff727bd1b64b9e94e8ef70444cc7745a457ad0d659
3
  size 313998650
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91d22b688cf66283ee087d9f1e8f64f84fca6694cbe460a2583a0af6942fdb67
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee4d92c96f053939859e1de9b125afd2001c96b616097b758f007963c9b97d2
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:cebd162aba18f860f51e2cc1ee5936648cae7b887a6a1f05cf77f1291d5c859b
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e6ca730b683b5b228be5c4e973697d55f1249d83ba96868efc19ba82ad088c
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:aadddfe7c61a55a44e273bbb3a7a37cae1e95a431be61cbeeb3000151f9499b2
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4960f1e1dd22d2b4fe1c3e43db66eaac5e947eb69645665c06cba704231b2594
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 sha256:295014528a02b2db72edd87d2b4deaec8abb404c50d476b52f4741079de8eca6
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4392c9d2176dde701259aa7803af164f1fab53fb034001e9577ccf3bcaa286f
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": 1.7811026573181152,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.3421727972626176,
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": 34.21,
199
  "eval_steps_per_second": 8.895,
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": 7.94731890081792e+16,
230
  "train_batch_size": 1,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7397328615188599,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.6843455945252352,
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": 34.21,
199
  "eval_steps_per_second": 8.895,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.3558597091531223,
204
+ "grad_norm": 0.7591701149940491,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 2.0127,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.369546621043627,
211
+ "grad_norm": 0.9103983044624329,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 1.9637,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.38323353293413176,
218
+ "grad_norm": 0.8943213820457458,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 1.9139,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.39692044482463645,
225
+ "grad_norm": 0.8365579843521118,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 1.9006,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.41060735671514115,
232
+ "grad_norm": 0.8076335787773132,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 1.9083,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.42429426860564584,
239
+ "grad_norm": 0.7735624313354492,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 1.8956,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.43798118049615054,
246
+ "grad_norm": 0.7214319705963135,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 1.8705,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.4516680923866553,
253
+ "grad_norm": 0.7641725540161133,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 1.8121,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.46535500427716,
260
+ "grad_norm": 0.7683237195014954,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 1.7478,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.47904191616766467,
267
+ "grad_norm": 0.8942069411277771,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 1.7379,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.49272882805816937,
274
+ "grad_norm": 1.1086134910583496,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 1.6556,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.5064157399486741,
281
+ "grad_norm": 1.8508061170578003,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 1.7596,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.5201026518391788,
288
+ "grad_norm": 0.5953439474105835,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 1.9416,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.5337895637296834,
295
+ "grad_norm": 0.5514473915100098,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 1.9681,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.5474764756201882,
302
+ "grad_norm": 0.5643142461776733,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 1.9015,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.561163387510693,
309
+ "grad_norm": 0.6523820161819458,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 1.9157,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.5748502994011976,
316
+ "grad_norm": 0.6224381923675537,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 1.8996,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.5885372112917023,
323
+ "grad_norm": 0.6665676236152649,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 1.831,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.602224123182207,
330
+ "grad_norm": 0.7095207571983337,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 1.8424,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.6159110350727117,
337
+ "grad_norm": 0.6559857726097107,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 1.7975,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.6295979469632165,
344
+ "grad_norm": 0.7268767952919006,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 1.8395,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.6432848588537211,
351
+ "grad_norm": 0.7550267577171326,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 1.7475,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.6569717707442259,
358
+ "grad_norm": 0.9330142140388489,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 1.7608,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.6706586826347305,
365
+ "grad_norm": 1.2081230878829956,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 1.7007,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.6843455945252352,
372
+ "grad_norm": 2.4048612117767334,
373
+ "learning_rate": 1e-05,
374
+ "loss": 1.7784,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.6843455945252352,
379
+ "eval_loss": 1.7397328615188599,
380
+ "eval_runtime": 1.4629,
381
+ "eval_samples_per_second": 34.18,
382
+ "eval_steps_per_second": 8.887,
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": 1.589463780163584e+17,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null