sm commited on
Commit
1c3d951
·
verified ·
1 Parent(s): 060f336

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 sha256:27d2ffeaff17fa220273c3d441af252a8687e8b1c6b9fc05b1453bd54abc4e11
3
  size 147770496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef6f5479a7140700df3d8df2cd3d647b4b06949e0aab9e79c71359c0bae52ca
3
  size 147770496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8959c2699f789991803def38c9e8314f1ae030601d2b151a7dd80196324d1f0d
3
  size 295765866
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91241bab8251b5f521434049995a8d7d63d824b2d80567cd6115748c97836264
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 sha256:12f0ad0b06082cca3193f6f5f2df64db4f13ac17feb42a1819888373af9a1dee
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2281d341c790676f03f48f0d785ae5b26eff9d73c2c3bc49b2ecb4722f2cd5f
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:abaad29d63df3a15839bd804dac167d05be1ebadd12aac47a8ded08db454c144
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ccd3c572ef20998bcb1ae4071c2dfc825c4f5f667751835ca783692a0d80f46
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 sha256:599ee2150c4bd2049788b1de6a5bb2ca3a9feec5e3cee4a7e3168f0a2fb93f78
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8725a629b9d3eefe8bc61bdc10a316f84881107e88a23956d3beafe37fa0af36
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:b1fb8fe897ad25264cf48849ab1ebe8f1fd54c07f6a1fcbb230064a70d1b6aa4
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292df9665dd4fb4ff0491075aacd126bdb68cffa8fec38f10aa671c64088de16
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": 0.49585384130477905,
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": 66.923,
199
  "eval_steps_per_second": 17.4,
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": 0.14452199637889862,
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": 66.923,
199
  "eval_steps_per_second": 17.4,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.685337726523888,
204
+ "grad_norm": 2.4734058380126953,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 0.598,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.7116968698517299,
211
+ "grad_norm": 3.428785562515259,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 0.672,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.7380560131795717,
218
+ "grad_norm": 2.8462884426116943,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 0.6942,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.7644151565074135,
225
+ "grad_norm": 2.8353283405303955,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 0.534,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.7907742998352554,
232
+ "grad_norm": 1.8473469018936157,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 0.1867,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.8171334431630972,
239
+ "grad_norm": 1.3983721733093262,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 0.1956,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.8434925864909391,
246
+ "grad_norm": 1.2318115234375,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 0.2022,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.8698517298187809,
253
+ "grad_norm": 0.9489920735359192,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 0.1785,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.8962108731466227,
260
+ "grad_norm": 1.4298465251922607,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 0.2614,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.9225700164744646,
267
+ "grad_norm": 1.7149752378463745,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 0.3176,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.9489291598023064,
274
+ "grad_norm": 2.3903605937957764,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 0.389,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.9752883031301482,
281
+ "grad_norm": 3.662409543991089,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 0.4364,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 1.0247116968698518,
288
+ "grad_norm": 4.705199718475342,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 0.6616,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 1.0510708401976936,
295
+ "grad_norm": 0.9721773266792297,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 0.1232,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 1.0774299835255354,
302
+ "grad_norm": 0.9221625924110413,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 0.1,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 1.1037891268533773,
309
+ "grad_norm": 1.6013553142547607,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 0.1023,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 1.130148270181219,
316
+ "grad_norm": 1.0896989107131958,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 0.093,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 1.156507413509061,
323
+ "grad_norm": 1.2368277311325073,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 0.1512,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 1.1828665568369028,
330
+ "grad_norm": 1.908003807067871,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 0.2024,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 1.2092257001647446,
337
+ "grad_norm": 2.1720011234283447,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 0.2848,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 1.2355848434925865,
344
+ "grad_norm": 3.783008575439453,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 0.3299,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 1.2619439868204283,
351
+ "grad_norm": 2.4560554027557373,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 0.2846,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 1.2883031301482701,
358
+ "grad_norm": 1.1371558904647827,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 0.0989,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 1.314662273476112,
365
+ "grad_norm": 0.7374827861785889,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 0.0588,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 1.3410214168039538,
372
+ "grad_norm": 0.9319198727607727,
373
+ "learning_rate": 1e-05,
374
+ "loss": 0.0628,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 1.3410214168039538,
379
+ "eval_loss": 0.14452199637889862,
380
+ "eval_runtime": 0.747,
381
+ "eval_samples_per_second": 66.931,
382
+ "eval_steps_per_second": 17.402,
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