eeeebbb2 commited on
Commit
0c567dc
·
verified ·
1 Parent(s): cb22cd7

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:fd58cc77e7b8ef6e04dd5355fb67ec66af29df5a28748d53fc6732ddbbfae99e
3
  size 1521616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb4fa247f612a76e15cfc72f6a77e9f5d45e4df9aa63b2e1c66f87df2cfa855e
3
  size 1521616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60b981585bc10d7190ade4c568b81894c2b783fb882728b79d6703c7c508bf21
3
  size 3108666
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e083a7153073f86c25833a87cb059576b783fa355f98f8d2214ce348bace310b
3
  size 3108666
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68051133b224d14b3a05a71fdf735aea34a69ab4dbb15889b8b2a3e7e2765474
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c0b685af4713b728ab0078e5715a41026b78380d2a13b592850d0cb90750bb1
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 sha256:08e7078462b285fe3a7c395fee40a5cfca1374e399178c1e02d06c1f2117c63d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c2de72519579dfbcb1c11cc4240685f7638dc6b686b130a87e89127d89216c5
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 sha256:75c74ac7f9ace065c1b611a206d33b5c8169e48671262216d25d007e2fce6e13
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a32acc284c918884645b6f88831b507926064147740f2a2ea25c6a0bf1b12e9
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 sha256:401958eefff1f69ab390c2e9495e4c1267a3489a25dc6f86819fb797b3889bbd
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0b8730a7a2b117c1714f8a4785fa9557d28e88e10df3edf6a0233baab0b5be8
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": 9.286540985107422,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.08210180623973727,
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": 67.207,
199
  "eval_steps_per_second": 17.474,
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": 116006898892800.0,
230
  "train_batch_size": 1,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 9.034330368041992,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.16420361247947454,
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": 67.207,
199
  "eval_steps_per_second": 17.474,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.08538587848932677,
204
+ "grad_norm": 2.6121907234191895,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 9.0977,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.08866995073891626,
211
+ "grad_norm": 2.2141213417053223,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 9.1782,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.09195402298850575,
218
+ "grad_norm": 2.1672656536102295,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 9.2533,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.09523809523809523,
225
+ "grad_norm": 2.1206374168395996,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 9.4548,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.09852216748768473,
232
+ "grad_norm": 2.081202268600464,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 9.3319,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.10180623973727422,
239
+ "grad_norm": 2.0032904148101807,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 9.1952,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.10509031198686371,
246
+ "grad_norm": 2.0835368633270264,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 9.1689,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.10837438423645321,
253
+ "grad_norm": 2.2021350860595703,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 9.1592,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.1116584564860427,
260
+ "grad_norm": 2.3087997436523438,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 9.127,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.11494252873563218,
267
+ "grad_norm": 2.4689571857452393,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 8.8672,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.11822660098522167,
274
+ "grad_norm": 3.0260496139526367,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 8.9765,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.12151067323481117,
281
+ "grad_norm": 3.4635651111602783,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 8.9259,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.12479474548440066,
288
+ "grad_norm": 2.264085531234741,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 8.8283,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.12807881773399016,
295
+ "grad_norm": 2.1152355670928955,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 9.0926,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.13136288998357964,
302
+ "grad_norm": 1.843088984489441,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 9.0987,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.13464696223316913,
309
+ "grad_norm": 1.9147875308990479,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 9.2151,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.13793103448275862,
316
+ "grad_norm": 1.868973970413208,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 9.1413,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.1412151067323481,
323
+ "grad_norm": 1.8492201566696167,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 9.1159,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.1444991789819376,
330
+ "grad_norm": 1.908602237701416,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 9.0776,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.1477832512315271,
337
+ "grad_norm": 1.9235059022903442,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 9.0402,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.1510673234811166,
344
+ "grad_norm": 2.0559000968933105,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 8.9646,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.15435139573070608,
351
+ "grad_norm": 2.4485461711883545,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 8.8393,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.15763546798029557,
358
+ "grad_norm": 2.6814403533935547,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 8.8943,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.16091954022988506,
365
+ "grad_norm": 3.552027940750122,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 9.0081,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.16420361247947454,
372
+ "grad_norm": 4.193510055541992,
373
+ "learning_rate": 1e-05,
374
+ "loss": 8.7117,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.16420361247947454,
379
+ "eval_loss": 9.034330368041992,
380
+ "eval_runtime": 0.7358,
381
+ "eval_samples_per_second": 67.95,
382
+ "eval_steps_per_second": 17.667,
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": 232013797785600.0,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null