eeeebbb2 commited on
Commit
844ea7d
1 Parent(s): ee89733

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 sha256:622023844275649264055a994dc4dd4092f0b37cc9b8e8b6b00ccdbeb2a4a19e
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b9512b753f0ada553d5ff8dc7716ad4299d37aad42a6bf61bdcdc183ac7b8f2
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4301159ead907ee46d369c21cea68077ded0c75cb41b754f1ca8201ecadd1b48
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b943b9de0456c6a5f819b6d3ee09b911eac3e40d61746079e23b9921b89e60
3
  size 640009682
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5ba96b0028687b93de9b6b6026d134b62af60cbc2ce69d7cf4ad4573b66f3f3
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8648271cce672d74467d1667899dc2b2b505b7bd1b603a5c08116bf9cb9fe678
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 sha256:861005bff7ece8ac3e7aca10639fbb14b1920dcebe11e6b0c94ba0bce671de7e
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10dddb0e421ebf852d636528edcdd7203172e8a53296eb0a2f16e387ed3b37b0
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 sha256:91361697b23882b57c1f358ddb58e9ff8eceb3621c3efaac774f5b0f4f5ce6c8
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d2be7de4c48bf05b206132cb1eb3b640297aedbc8feb0abf5481e4b026f44d
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 sha256:0464a3a0d87399133aeb14e1269270cf8aec26f08491b316ee2e8cfc5bb1553d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a19c6de691a3ee76b06645bee0830ccb37c09fc542f7c5a8f9deb7fc5c72841f
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": 2.79341983795166,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 1.1976047904191618,
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": 10.985,
199
  "eval_steps_per_second": 2.856,
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": 3.93611124643201e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.6709249019622803,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 2.3952095808383236,
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": 10.985,
199
  "eval_steps_per_second": 2.856,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 1.2455089820359282,
204
+ "grad_norm": 13.066014289855957,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 43.7104,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 1.2934131736526946,
211
+ "grad_norm": 15.47722053527832,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 42.2966,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 1.341317365269461,
218
+ "grad_norm": 18.106525421142578,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 47.1484,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 1.3892215568862276,
225
+ "grad_norm": 17.03740692138672,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 42.2896,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 1.437125748502994,
232
+ "grad_norm": 15.306708335876465,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 41.9534,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 1.4850299401197604,
239
+ "grad_norm": 14.26751708984375,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 45.2017,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 1.532934131736527,
246
+ "grad_norm": 17.206789016723633,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 43.9349,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 1.5808383233532934,
253
+ "grad_norm": 18.50804901123047,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 45.4069,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 1.6287425149700598,
260
+ "grad_norm": 20.458311080932617,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 44.5455,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 1.6766467065868262,
267
+ "grad_norm": 15.671262741088867,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 42.9807,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 1.7245508982035929,
274
+ "grad_norm": 14.376961708068848,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 45.5037,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 1.7724550898203593,
281
+ "grad_norm": 15.421966552734375,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 42.4266,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 1.8203592814371259,
288
+ "grad_norm": 21.55309295654297,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 48.5389,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 1.8682634730538923,
295
+ "grad_norm": 15.796401977539062,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 41.4078,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 1.9161676646706587,
302
+ "grad_norm": 16.036413192749023,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 42.5856,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 1.964071856287425,
309
+ "grad_norm": 14.152937889099121,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 39.9044,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 2.0119760479041915,
316
+ "grad_norm": 15.67934513092041,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 43.7522,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 2.059880239520958,
323
+ "grad_norm": 15.741512298583984,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 39.6389,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 2.1077844311377247,
330
+ "grad_norm": 17.636999130249023,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 41.9672,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 2.155688622754491,
337
+ "grad_norm": 20.343563079833984,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 43.9301,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 2.2035928143712575,
344
+ "grad_norm": 15.532905578613281,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 41.1395,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 2.251497005988024,
351
+ "grad_norm": 14.655294418334961,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 38.4739,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 2.2994011976047903,
358
+ "grad_norm": 16.103124618530273,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 38.3927,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 2.3473053892215567,
365
+ "grad_norm": 20.670578002929688,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 43.2779,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 2.3952095808383236,
372
+ "grad_norm": 15.122425079345703,
373
+ "learning_rate": 1e-05,
374
+ "loss": 40.8576,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 2.3952095808383236,
379
+ "eval_loss": 2.6709249019622803,
380
+ "eval_runtime": 4.9264,
381
+ "eval_samples_per_second": 10.149,
382
+ "eval_steps_per_second": 2.639,
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": 7.875509431335649e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null