vdos commited on
Commit
e084760
·
verified ·
1 Parent(s): 44354c2

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 sha256:927d60d734180a5382193bb6f208488d1daa72fec25592e4e21eea3f343cffc2
3
  size 239536272
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65db0c61f6bc751ec3c71180f933e89ee030416f07f81df2ee0d61cd69706a0a
3
  size 239536272
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f218f9b6e22482b76f07166b0ed7a53b26feb46b4f50574451199d9479fe3061
3
  size 479362682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de2785090f83dc159c050cdf1c62f4f4e299aa76a3b7bcbe17c3e160915f29da
3
  size 479362682
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b556539d1d4705b7f0142c8cd9eed3c992ece026d253fc19151efc6408c2e70
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13a1e2a8f2d209c7c9662529a5423f857e3c01bfabd1198964c5e65eea0d0b2e
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 sha256:0c4b8b1d3d79e7cbe607f49b2a8cf26bdfd1064723f7b701b01fc8ec55b61130
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bae5474f75c61c9a0d413df8aab34ab8256bdb971d495e89be4af58b9a649eaa
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 sha256:42441f16c0c0be7218ad2a557ddd15fcaf33566c1d0e679c7e6978bcfa5de3ed
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e7c294700ed36f2650cddab58c02f47a9f0848cf5f2dd7cf7c554e3ed585cb4
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 sha256:189439e2ef482762e8f54b288f44a7758bec61626a9110512620bc89c832919e
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f75fb65da0bcb2461add98b4fba0e9c423c51132a687f95b29d21631f37a4a
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": 1.6248844861984253,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.0069270066672439175,
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": 55.112,
199
  "eval_steps_per_second": 6.891,
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": 1.114626154561536e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.574446678161621,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.013854013334487835,
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": 55.112,
199
  "eval_steps_per_second": 6.891,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.007204086933933674,
204
+ "grad_norm": 0.569159209728241,
205
+ "learning_rate": 5e-05,
206
+ "loss": 1.6105,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.007481167200623431,
211
+ "grad_norm": 0.6634584069252014,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 1.5842,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.0077582474673131875,
218
+ "grad_norm": 0.6659657955169678,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 1.614,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.008035327734002944,
225
+ "grad_norm": 0.7010889053344727,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 1.6537,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.008312408000692701,
232
+ "grad_norm": 0.6605480313301086,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 1.6621,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.008589488267382457,
239
+ "grad_norm": 0.698592483997345,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 1.7071,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.008866568534072214,
246
+ "grad_norm": 0.7084943056106567,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 1.5723,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.009143648800761971,
253
+ "grad_norm": 0.6080454587936401,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 1.5525,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.009420729067451727,
260
+ "grad_norm": 0.7002612352371216,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 1.6181,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.009697809334141484,
267
+ "grad_norm": 0.6785765886306763,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 1.5518,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.009974889600831241,
274
+ "grad_norm": 0.7487239241600037,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 1.5369,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.010251969867520997,
281
+ "grad_norm": 0.8074867129325867,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 1.6678,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.010529050134210753,
288
+ "grad_norm": 0.6005417704582214,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 1.6568,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.010806130400900511,
295
+ "grad_norm": 0.596122145652771,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 1.5572,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.011083210667590267,
302
+ "grad_norm": 0.5598776936531067,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 1.5768,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.011360290934280023,
309
+ "grad_norm": 0.56935054063797,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 1.4968,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.011637371200969781,
316
+ "grad_norm": 0.5927587151527405,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 1.5508,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.011914451467659537,
323
+ "grad_norm": 0.8119907975196838,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 1.663,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.012191531734349295,
330
+ "grad_norm": 0.6603608727455139,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 1.5939,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.012468612001039051,
337
+ "grad_norm": 0.6734949350357056,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 1.6528,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.012745692267728807,
344
+ "grad_norm": 0.6059690117835999,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 1.5085,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.013022772534418565,
351
+ "grad_norm": 0.6954624056816101,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 1.501,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.013299852801108321,
358
+ "grad_norm": 0.7555593252182007,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 1.5964,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.013576933067798077,
365
+ "grad_norm": 0.7384346723556519,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 1.5567,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.013854013334487835,
372
+ "grad_norm": 1.1048245429992676,
373
+ "learning_rate": 0.0,
374
+ "loss": 1.7697,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.013854013334487835,
379
+ "eval_loss": 1.574446678161621,
380
+ "eval_runtime": 440.9601,
381
+ "eval_samples_per_second": 55.139,
382
+ "eval_steps_per_second": 6.894,
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": 2.229252309123072e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null