eeeebbb2 commited on
Commit
ea0e21f
1 Parent(s): de8b641

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:ad45b18318708d1dd5dfe343f043f51b2f6279ca7016e219deaa02ba446ecf0e
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:516a7e4298841753ade3d517262d2658797f5d9a52798381a382f47c3b5bfff1
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c9e3e4e10f19119fb8507d6be2f904d17a206fcce7ab5f43ce68168eb628065
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9977a8183ca9cf83da41cd96ea03a72cc6379d0b0c452252b0d21b2393d5cba0
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:f490ce0e05cb1ce4d372f0f73d384cb3c5e161d4cf27dfcb68db46977a7c7444
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba40e84e991758419f82ccf5f7a8e9bbb6a30417ff7897a5638663d5a7264007
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:cf520a628e41e61266bf94e40b1e2d6b014291f6ee1392360bc12ca17689783f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa365110780f12edfe54751fa123785ae60819def704e87e3c35ec31663f554
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 sha256:57adae6defcd61ecf6e7ccc8b83ab430f9f27dcca4e6d866af8c17ecbd77812d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f23a7eb8010a262826dd3f54f5e41025aae2374c9a7273de5fb4db8b8948d20
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:ab32244f72d2e219a79d8144a921a4f9e4f9d7acdd093d06091f58961b985b16
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75bec37b27a29ce04cc68bbfd89a8339927f93b8cf9c91c52bcd30fb9e9e5fe0
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": 1.8228825330734253,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.3109211037699184,
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": 11.449,
199
  "eval_steps_per_second": 2.977,
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": 2.984041808658432e+17,
230
  "train_batch_size": 1,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5995488166809082,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.6218422075398368,
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": 11.449,
199
  "eval_steps_per_second": 2.977,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.3233579479207151,
204
+ "grad_norm": 3.0982296466827393,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 2.3577,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.33579479207151186,
211
+ "grad_norm": 2.92927885055542,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 2.2911,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.34823163622230857,
218
+ "grad_norm": 2.458441972732544,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 2.0293,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.36066848037310534,
225
+ "grad_norm": 2.1433932781219482,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 2.0705,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.37310532452390205,
232
+ "grad_norm": 1.8144245147705078,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 1.8359,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.3855421686746988,
239
+ "grad_norm": 1.615573525428772,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 1.8279,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.3979790128254955,
246
+ "grad_norm": 1.7636524438858032,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 1.9141,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.4104158569762923,
253
+ "grad_norm": 1.6936835050582886,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 1.9035,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.422852701127089,
260
+ "grad_norm": 1.7628343105316162,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 1.5598,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.4352895452778857,
267
+ "grad_norm": 2.0483028888702393,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 1.6121,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.4477263894286825,
274
+ "grad_norm": 2.3952748775482178,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 1.2943,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.4601632335794792,
281
+ "grad_norm": 2.835444211959839,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 0.9927,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.47260007773027596,
288
+ "grad_norm": 1.7717387676239014,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 1.8088,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.48503692188107267,
295
+ "grad_norm": 1.5801821947097778,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 2.074,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.49747376603186944,
302
+ "grad_norm": 1.5096017122268677,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 1.9525,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.5099106101826661,
309
+ "grad_norm": 1.5900380611419678,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 1.7708,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.5223474543334629,
316
+ "grad_norm": 1.4869619607925415,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 1.9034,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.5347842984842596,
323
+ "grad_norm": 1.295594573020935,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 1.8161,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.5472211426350564,
330
+ "grad_norm": 1.4549026489257812,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 1.7517,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.5596579867858531,
337
+ "grad_norm": 1.751529335975647,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 1.7905,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.5720948309366498,
344
+ "grad_norm": 1.6213444471359253,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 1.5946,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.5845316750874465,
351
+ "grad_norm": 1.8312252759933472,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 1.5736,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.5969685192382433,
358
+ "grad_norm": 1.7476670742034912,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 1.4217,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.6094053633890401,
365
+ "grad_norm": 1.5351223945617676,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 0.9661,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.6218422075398368,
372
+ "grad_norm": 1.8565118312835693,
373
+ "learning_rate": 1e-05,
374
+ "loss": 0.4582,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.6218422075398368,
379
+ "eval_loss": 1.5995488166809082,
380
+ "eval_runtime": 4.3433,
381
+ "eval_samples_per_second": 11.512,
382
+ "eval_steps_per_second": 2.993,
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": 5.968083617316864e+17,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null