vdos commited on
Commit
6510509
1 Parent(s): ab8e00f

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:c60d44f16dbdc1ce77b7359acc627beb59fcf5353a2141aa677b383519d465be
3
  size 323014168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ad2c600f9f229b39fb67dc6dc9c34d71f1b3ad89544a1ca64061d7e5efcade
3
  size 323014168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2d498c349fcd5821bc4b0c99d7e2b2bcd272864d10a5adb733da55562c147cd
3
  size 646253418
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60562173737c46bf000b691da9d753e6343b9ee6e3f0d00bd56e68a1b2c018a0
3
  size 646253418
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24f89a3282a6b35332ac005f7e29c65dc21c12bfebc2768bbe3d4388000c8944
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7bf981d6d7bb318627a6649dd0308e1ff8c505104a3882742bb7b4de03e1ac6
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:f46ead07a7cc8f24bde67af7158b9ec8794471d2bd8145497c279d6119ccb511
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fe468bf4d05b63325f0c6634d95eaaa0cee7ed864cd67b15b406ddf7ca83784
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 sha256:039bc0be694dccde694f0d5e98a3c5508fbd31ce308f90bf950dd18f51f24afe
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dbdb7aedb0ee90a0bb6efc0f26aba8ea6014a868ab81b2d91a1f30e000e913e
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 sha256:0c9bc607986704587d2f4702db16b9d5eb6787af0f5925675967bb65ce4393ca
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd83d49f6dcfbb9ca838bcd0f0f33dcb9898327deb5174ed93ac8ac7e0a9fb7
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.315967321395874,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.1736111111111111,
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": 32.243,
199
  "eval_steps_per_second": 4.055,
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": 2.89638977248428e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.2535191774368286,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.3472222222222222,
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": 32.243,
199
  "eval_steps_per_second": 4.055,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.18055555555555555,
204
+ "grad_norm": 4.528706073760986,
205
+ "learning_rate": 5e-05,
206
+ "loss": 2.2754,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.1875,
211
+ "grad_norm": 1.2604354619979858,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 1.1671,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.19444444444444445,
218
+ "grad_norm": 1.2874277830123901,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 1.193,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.2013888888888889,
225
+ "grad_norm": 0.8460001349449158,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 1.1593,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.20833333333333334,
232
+ "grad_norm": 0.30335867404937744,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 1.1539,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.2152777777777778,
239
+ "grad_norm": 1.150852084159851,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 1.1991,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.2222222222222222,
246
+ "grad_norm": 1.0014760494232178,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 1.2075,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.22916666666666666,
253
+ "grad_norm": 1.1253355741500854,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 1.2038,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.2361111111111111,
260
+ "grad_norm": 0.4158329665660858,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 1.2013,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.24305555555555555,
267
+ "grad_norm": 0.3990498483181,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 1.179,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.25,
274
+ "grad_norm": 0.34036171436309814,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 1.1811,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.2569444444444444,
281
+ "grad_norm": 0.3939284384250641,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 1.2234,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.2638888888888889,
288
+ "grad_norm": 2.1086604595184326,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 2.2966,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.2708333333333333,
295
+ "grad_norm": 0.648451566696167,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 1.1439,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.2777777777777778,
302
+ "grad_norm": 0.5881859660148621,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 1.1396,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.2847222222222222,
309
+ "grad_norm": 0.5503454208374023,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 1.1291,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.2916666666666667,
316
+ "grad_norm": 0.5237451791763306,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 1.1538,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.2986111111111111,
323
+ "grad_norm": 0.6803749799728394,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 1.176,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.3055555555555556,
330
+ "grad_norm": 0.4073289930820465,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 1.1751,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.3125,
337
+ "grad_norm": 0.397196501493454,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 1.1962,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.3194444444444444,
344
+ "grad_norm": 0.447818398475647,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 1.1877,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.3263888888888889,
351
+ "grad_norm": 0.34394121170043945,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 1.1707,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.3333333333333333,
358
+ "grad_norm": 0.34709423780441284,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 1.1682,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.3402777777777778,
365
+ "grad_norm": 0.2884080410003662,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 1.1722,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.3472222222222222,
372
+ "grad_norm": 0.35996749997138977,
373
+ "learning_rate": 0.0,
374
+ "loss": 1.2179,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.3472222222222222,
379
+ "eval_loss": 1.2535191774368286,
380
+ "eval_runtime": 29.8222,
381
+ "eval_samples_per_second": 32.526,
382
+ "eval_steps_per_second": 4.091,
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": 5.805082167402824e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null