vdos commited on
Commit
4a00a7a
1 Parent(s): c40d11c

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:e4511041da1b406d8925c744eafa1a14218f3a193951bd430f64c067b594f2ed
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:873a8c05298246afce40746c4bc4358c7a22a137a7029372bc0e7649865027f3
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0c193d1e8c797fa61873694ac4afff7d6a5ed7969e210b0970fbb783462911f
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a04b5dd94307e29f7740849ea57f00e841a1d9e3dfc67a0aa90d71424da30e8
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:b0913edda4cb4fa20447473c6eefebab0b961ca10eccaa7b8eb7ac3ea2d02878
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5770d51b1751bcd1d2636745f8d8eb75416a978e15fdd6ae822f37c4e97daee
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:e02ad97dbe9df85197e1669979aea0d763105d8862c41a7aca585996dcfd1b61
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d04181d3c6970f8bc886025373fdbc1431659fe9720fd9f5c574b2be093aea0c
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 sha256:43eda1d014fca2f137d949cbc8261a8c1c4bf318c77d6ee9a33f30f37ba12a45
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13bb6c62199d3fc09401c069bd01c14784ef77a44bbba8b6b1be71c640d5f05a
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:a3c23d40c24babf9ce6408fcc2e1332030d9227b5f9351a25b7f310d7b1519e7
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f31cbbf023a2e70bf30b80b78e6243cb6f759dd6fc42d75f743c4ecb7f4d8a
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": 1.4591978788375854,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.016478536705940513,
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": 35.522,
199
  "eval_steps_per_second": 4.442,
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": 2.629552387915776e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4253883361816406,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.032957073411881026,
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": 35.522,
199
  "eval_steps_per_second": 4.442,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.017137678174178134,
204
+ "grad_norm": 0.19020310044288635,
205
+ "learning_rate": 5e-05,
206
+ "loss": 1.3073,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.017796819642415754,
211
+ "grad_norm": 0.1739782691001892,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 1.2809,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.018455961110653375,
218
+ "grad_norm": 0.1638297438621521,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 1.3014,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.019115102578890996,
225
+ "grad_norm": 0.1574772596359253,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 1.2768,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.019774244047128613,
232
+ "grad_norm": 0.13562825322151184,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 1.3035,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.020433385515366234,
239
+ "grad_norm": 0.13689446449279785,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 1.2952,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.021092526983603855,
246
+ "grad_norm": 0.12440229952335358,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 1.3424,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.021751668451841476,
253
+ "grad_norm": 0.1770576387643814,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 1.4069,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.022410809920079097,
260
+ "grad_norm": 0.2141914814710617,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 1.5183,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.023069951388316717,
267
+ "grad_norm": 0.31634941697120667,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 1.6166,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.023729092856554338,
274
+ "grad_norm": 0.29751285910606384,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 1.6496,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.02438823432479196,
281
+ "grad_norm": 0.28590714931488037,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 1.708,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.02504737579302958,
288
+ "grad_norm": 0.11785943806171417,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 1.3091,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.0257065172612672,
295
+ "grad_norm": 0.10514993965625763,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 1.2735,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.02636565872950482,
302
+ "grad_norm": 0.09633257985115051,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 1.3116,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.027024800197742442,
309
+ "grad_norm": 0.10499632358551025,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 1.2612,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.02768394166598006,
316
+ "grad_norm": 0.09367036074399948,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 1.2759,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.02834308313421768,
323
+ "grad_norm": 0.105850450694561,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 1.2775,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.0290022246024553,
330
+ "grad_norm": 0.11707086116075516,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 1.3,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.029661366070692922,
337
+ "grad_norm": 0.13155709207057953,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 1.3426,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.030320507538930543,
344
+ "grad_norm": 0.17515063285827637,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 1.4371,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.030979649007168163,
351
+ "grad_norm": 0.21689704060554504,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 1.5299,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.031638790475405784,
358
+ "grad_norm": 0.2483842819929123,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 1.6002,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.0322979319436434,
365
+ "grad_norm": 0.2632664442062378,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 1.6981,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.032957073411881026,
372
+ "grad_norm": 0.30653318762779236,
373
+ "learning_rate": 0.0,
374
+ "loss": 1.7189,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.032957073411881026,
379
+ "eval_loss": 1.4253883361816406,
380
+ "eval_runtime": 287.7518,
381
+ "eval_samples_per_second": 35.52,
382
+ "eval_steps_per_second": 4.441,
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": 5.259104775831552e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null