dsakerkwq commited on
Commit
b9f922f
·
verified ·
1 Parent(s): b4a2e11

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 sha256:54bd3784b798ab03a7cf3a95bcfd221548a11c6798b0a98cdec71e726dd3ffb5
3
  size 1204200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00074ad93855df381e9af9f8e2f4c7f763efca08ef932aa6460a943ca2a92edf
3
  size 1204200
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bcc43ad0308758e324c94e1b1931c4bc11413f89eee14798a30a365cbb737e6
3
  size 2558458
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7d3da7623044bb719d6569aafded54861916631647b905ef5f04b05dbfc4889
3
  size 2558458
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73df0a75848952494933968d449f6ef3e504c3fef4b7abe11d58c48b66e58da0
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335c91802479357ec15a5a85ee8eb4706d70c6a573982bbd2d474b8473b1e9ef
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:da810dd6590df27183d499b9efad33fceb89310583cb0efe4c87e645a0dd028d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6de731093ddd54a76777d2dae84ec785035da78d109745b26d693bab92f35eea
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:c9cced44e88ca40cc37c8e917c06505caec9eed908a71d167105ea50f6cc2f0d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb95aabd0473604f6c1c4559030200af1529faf4e032104bf5ad68216e7733ff
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 sha256:8a63a23fcfac5e38933bafeb58dd8a47f4918e74d96ba8fbff4bfb8f234b9c38
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c018caa96fb39dea74642ee9aea782ed9a6e6f139dc5c5b4eb5ac43e38433af3
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": 11.894679069519043,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.6042296072507553,
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": 118.789,
199
  "eval_steps_per_second": 30.885,
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": 208998073630720.0,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.88502311706543,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 1.2084592145015105,
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": 118.789,
199
  "eval_steps_per_second": 30.885,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.6283987915407855,
204
+ "grad_norm": 0.3264436721801758,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 11.8956,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.6525679758308157,
211
+ "grad_norm": 0.3049549460411072,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 11.8927,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.676737160120846,
218
+ "grad_norm": 0.2916337549686432,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 11.8941,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.7009063444108762,
225
+ "grad_norm": 0.3138973116874695,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 11.89,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.7250755287009063,
232
+ "grad_norm": 0.3552839756011963,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 11.8897,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.7492447129909365,
239
+ "grad_norm": 0.32448610663414,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 11.8933,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.7734138972809668,
246
+ "grad_norm": 0.2939136028289795,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 11.895,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.797583081570997,
253
+ "grad_norm": 0.2980336844921112,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 11.8914,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.8217522658610272,
260
+ "grad_norm": 0.28817757964134216,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 11.8898,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.8459214501510574,
267
+ "grad_norm": 0.2792845070362091,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 11.8892,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.8700906344410876,
274
+ "grad_norm": 0.27374735474586487,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 11.8883,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.8942598187311178,
281
+ "grad_norm": 0.26833635568618774,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 11.8914,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.918429003021148,
288
+ "grad_norm": 0.25294485688209534,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 11.8892,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.9425981873111783,
295
+ "grad_norm": 0.2815414071083069,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 11.8866,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.9667673716012085,
302
+ "grad_norm": 0.2786562740802765,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 11.8819,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.9909365558912386,
309
+ "grad_norm": 0.4206508696079254,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 11.8803,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 1.0151057401812689,
316
+ "grad_norm": 0.523430585861206,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 20.7278,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 1.039274924471299,
323
+ "grad_norm": 0.24907422065734863,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 11.0273,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 1.0634441087613293,
330
+ "grad_norm": 0.24350455403327942,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 11.7038,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 1.0876132930513596,
337
+ "grad_norm": 0.2529279887676239,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 11.9333,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 1.1117824773413898,
344
+ "grad_norm": 0.24483628571033478,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 11.8469,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 1.13595166163142,
351
+ "grad_norm": 0.246808722615242,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 11.8908,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 1.1601208459214503,
358
+ "grad_norm": 0.2349546253681183,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 11.8041,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 1.1842900302114803,
365
+ "grad_norm": 0.2555924355983734,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 11.8472,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 1.2084592145015105,
372
+ "grad_norm": 0.2848963737487793,
373
+ "learning_rate": 1e-05,
374
+ "loss": 12.1816,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 1.2084592145015105,
379
+ "eval_loss": 11.88502311706543,
380
+ "eval_runtime": 0.391,
381
+ "eval_samples_per_second": 127.875,
382
+ "eval_steps_per_second": 33.247,
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": 418126689206272.0,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null