eeeebbb2 commited on
Commit
26f92ee
1 Parent(s): 21872cd

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:a10e55fb010949a309cde1b830fb5166b20dbbc523032b81726202586d6a9047
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c7ffc64ef0eb9224371e27c740f2cdc1786b6d74393e8d6dcda9abf75c72463
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fe657cac8d2f7c8183ebb9f6e312186ac79dbedf944659c571c25b77c80e526
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dc402880ea9959eaf8c8550a4fee637a32748e5889fcb219fbb0568a2737b2d
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:df89a07ed649280abebe1e15a498df1df5a2ff6ce374a8b6a2c40c17aebd242a
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae782fb4b2360c5c661fa50cc71c3cdfb2bfe458084a568b320bd3133732c7cf
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 sha256:57750b1be31d4e2e38a8f16c44a2955f0d1a5eaad364edc9d8ea8479b365eada
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d48b1c2e48c2dc0b17fe1bbf0481b44f0e1a775b8466a06131bea6834a2fe94
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:f4117060884d40ebb3b1a5b7391fcd8a95547d92876754223b8ea617f3b46757
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d235996992a22436d64cd8f5c6c8bb46fe20d47a1dd8801fd38c11e0fb3afba6
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:b213cabd98584acd9a35a0c6ea8920fb2615a090817bbcdbec451c5d78b4822e
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6da86df9e521f6bf0bd4ce9dffd828cc9d2ef8be93207bc7992cc2397361ef3
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": 2.2737886905670166,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.00835578951766205,
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": 10.539,
199
  "eval_steps_per_second": 2.74,
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": 2.829010669142016e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.2648308277130127,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.0167115790353241,
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": 10.539,
199
  "eval_steps_per_second": 2.74,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.008690021098368531,
204
+ "grad_norm": 4.368255615234375,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 32.8048,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.009024252679075015,
211
+ "grad_norm": 5.049758434295654,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 33.632,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.009358484259781497,
218
+ "grad_norm": 5.552004337310791,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 33.4633,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.009692715840487979,
225
+ "grad_norm": 6.246798038482666,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 31.611,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.01002694742119446,
232
+ "grad_norm": 5.866751670837402,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 32.8603,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.010361179001900943,
239
+ "grad_norm": 7.1694865226745605,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 33.6185,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.010695410582607425,
246
+ "grad_norm": 7.402153491973877,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 33.4369,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.011029642163313907,
253
+ "grad_norm": 7.939614772796631,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 34.4956,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.011363873744020389,
260
+ "grad_norm": 9.427316665649414,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 35.5888,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.01169810532472687,
267
+ "grad_norm": 11.526426315307617,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 34.8295,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.012032336905433353,
274
+ "grad_norm": 15.830511093139648,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 38.0113,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.012366568486139835,
281
+ "grad_norm": 16.048410415649414,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 41.1285,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.012700800066846317,
288
+ "grad_norm": 17.221982955932617,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 40.34,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.013035031647552799,
295
+ "grad_norm": 3.4482598304748535,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 32.6562,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.01336926322825928,
302
+ "grad_norm": 4.213986873626709,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 33.9774,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.013703494808965763,
309
+ "grad_norm": 4.579893589019775,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 32.5801,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.014037726389672244,
316
+ "grad_norm": 5.420438289642334,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 31.9658,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.014371957970378726,
323
+ "grad_norm": 6.065475940704346,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 34.2332,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.014706189551085208,
330
+ "grad_norm": 6.8349080085754395,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 32.6066,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.01504042113179169,
337
+ "grad_norm": 7.83049201965332,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 33.1971,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.015374652712498172,
344
+ "grad_norm": 9.868491172790527,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 33.5423,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.015708884293204654,
351
+ "grad_norm": 10.248172760009766,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 35.64,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.016043115873911135,
358
+ "grad_norm": 12.959470748901367,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 36.4588,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.01637734745461762,
365
+ "grad_norm": 14.926746368408203,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 38.2075,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.0167115790353241,
372
+ "grad_norm": 21.086666107177734,
373
+ "learning_rate": 1e-05,
374
+ "loss": 45.6951,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0167115790353241,
379
+ "eval_loss": 2.2648308277130127,
380
+ "eval_runtime": 4.7822,
381
+ "eval_samples_per_second": 10.455,
382
+ "eval_steps_per_second": 2.718,
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": 5.658021338284032e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null