eeeebbb2 commited on
Commit
d60296c
1 Parent(s): 069a1cc

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 sha256:75eb7d235f8c903fc1f86af69a6bf67a7ac06a837112318eb74722543e5c41ac
3
  size 147770496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21e2a1a5e9260e85d9aa5e75cacef9c6cc7f47de2985a7c3c7db782d8c2eb66e
3
  size 147770496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b0ae3bed6bf8e6bf965a5a027dc1462c611af41cf1c308c7904314b2ed41ca5
3
  size 295765866
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a7c5feedee78035a8663082e234da384cf856aa8ae54fc77f8696f048c7448b
3
  size 295765866
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12f46f549e08e4de9b13dfd15943f207873cefae03ba86dd844c013c78c19d4e
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0967168fdc397d539c736eab97c8c31717d9795c6c6962f3bda6c36eb65cf23
3
  size 14960
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f93031ee92693951f7562964ce0be13246486809776db9a6a80c3650bbacf2b3
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1356bfcc59da4f00dd18593893d4cbb0ff70ddc212c9ad462e4e728d43cfa7b
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:e8cc2b70f581f63a0afc6a33ed22b923602cb936a6a87f4acd2611a2fd882f80
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02d8700df175605714b8637cebcf2ebccdfb3b8f3a32c3ff4877ed71c7ca0465
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:a957aa4a2a763bbe311e785c1e2994b18689037f06db53306ce99c4d783656db
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7ab071d9c76c98b4b92e6b8b5c1778fc500a77ed244fb8d485009350009d12c
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": 0.5001410841941833,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.6589785831960461,
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": 43.628,
199
  "eval_steps_per_second": 11.343,
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": 5.29768176943104e+16,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.1482105553150177,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 1.3410214168039538,
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": 43.628,
199
  "eval_steps_per_second": 11.343,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.685337726523888,
204
+ "grad_norm": 2.631470203399658,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 0.6052,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.7116968698517299,
211
+ "grad_norm": 3.366347551345825,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 0.6785,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.7380560131795717,
218
+ "grad_norm": 2.787581443786621,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 0.6834,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.7644151565074135,
225
+ "grad_norm": 2.7616989612579346,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 0.521,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.7907742998352554,
232
+ "grad_norm": 1.800349473953247,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 0.1854,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.8171334431630972,
239
+ "grad_norm": 1.3683643341064453,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 0.1933,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.8434925864909391,
246
+ "grad_norm": 1.2189134359359741,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 0.1998,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.8698517298187809,
253
+ "grad_norm": 0.9834485054016113,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 0.1772,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.8962108731466227,
260
+ "grad_norm": 1.4624574184417725,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 0.2667,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.9225700164744646,
267
+ "grad_norm": 2.1892504692077637,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 0.3295,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.9489291598023064,
274
+ "grad_norm": 2.554065704345703,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 0.3938,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.9752883031301482,
281
+ "grad_norm": 4.097619533538818,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 0.4655,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 1.0247116968698518,
288
+ "grad_norm": 4.688210964202881,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 0.6527,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 1.0510708401976936,
295
+ "grad_norm": 1.0379397869110107,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 0.1263,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 1.0774299835255354,
302
+ "grad_norm": 1.0427350997924805,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 0.1028,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 1.1037891268533773,
309
+ "grad_norm": 1.8991127014160156,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 0.1048,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 1.130148270181219,
316
+ "grad_norm": 1.0854698419570923,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 0.0931,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 1.156507413509061,
323
+ "grad_norm": 1.1111361980438232,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 0.1551,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 1.1828665568369028,
330
+ "grad_norm": 1.4815325736999512,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 0.1946,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 1.2092257001647446,
337
+ "grad_norm": 1.8528581857681274,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 0.2864,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 1.2355848434925865,
344
+ "grad_norm": 3.5704665184020996,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 0.3412,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 1.2619439868204283,
351
+ "grad_norm": 2.261692762374878,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 0.2793,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 1.2883031301482701,
358
+ "grad_norm": 1.0988763570785522,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 0.0969,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 1.314662273476112,
365
+ "grad_norm": 0.856013298034668,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 0.0607,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 1.3410214168039538,
372
+ "grad_norm": 0.9837825894355774,
373
+ "learning_rate": 1e-05,
374
+ "loss": 0.0639,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 1.3410214168039538,
379
+ "eval_loss": 0.1482105553150177,
380
+ "eval_runtime": 1.1545,
381
+ "eval_samples_per_second": 43.307,
382
+ "eval_steps_per_second": 11.26,
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": 1.059536353886208e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null