DeepDream2045 commited on
Commit
75545d7
1 Parent(s): 1ae3aec

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 sha256:4e9f304381372deee8b2f469b2299c05fdfc3a77e365acb3154096fda41b1fac
3
  size 147770496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8815c6dd4178f422b2cb05d63f28e0dadf07bca6ae8c2fbb7c73f98efe7d89
3
  size 147770496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3866138c69b8db730ae9aa316bd93f19222053313db1070f90861d866bdb490
3
  size 295765866
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b539947b1aad9d662ec657dfedbb4f99bf65f2df54096e0031828f955ea962d
3
  size 295765866
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56b67862ad0880434da3aa7a3aa87faaa1780ba1c0f8974faa6b3e1071a89150
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bffa06fb708f8e9e82e2e6a2c6e653015f1163b6543323a1379e796b4961be7
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 sha256:647c3de4203978719d289342c64157b535c3de3a7527568807cdb0b980ecb040
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:343250d899eaadabcaad273bddae2d9596cf8e6c900f4c125d1c193e3fe9dba4
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 sha256:9b629af222cca3b95c6d9244d00f4cec7a6707398520443f0d9c57c687b0d3ec
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da575e2ec2c901cb469e378e0ef1ffd42acc7f3807af63daed25a0f98ba5f12a
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 sha256:2b587018478b378ac8a5ac788de9bfd4246c4b614d95e3f00f3e91dae4d6228a
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42e0e80abc9678532ac010afe7c007d8629b40aef3d24dc88e132f0739586376
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": 0.2187383621931076,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.2840909090909091,
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": 87.672,
199
  "eval_steps_per_second": 11.088,
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": 5.29768176943104e+16,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.11914384365081787,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.5681818181818182,
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": 87.672,
199
  "eval_steps_per_second": 11.088,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.29545454545454547,
204
+ "grad_norm": 5.778199672698975,
205
+ "learning_rate": 5e-05,
206
+ "loss": 0.3894,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.3068181818181818,
211
+ "grad_norm": 4.760310173034668,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 0.2936,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.3181818181818182,
218
+ "grad_norm": 2.9043290615081787,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 0.224,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.32954545454545453,
225
+ "grad_norm": 1.8596681356430054,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 0.2239,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.3409090909090909,
232
+ "grad_norm": 2.2370481491088867,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 0.1411,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.3522727272727273,
239
+ "grad_norm": 1.3053345680236816,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 0.1207,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.36363636363636365,
246
+ "grad_norm": 5.874414443969727,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 0.1589,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.375,
253
+ "grad_norm": 3.6689720153808594,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 0.1392,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.38636363636363635,
260
+ "grad_norm": 1.4059278964996338,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 0.0722,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.3977272727272727,
267
+ "grad_norm": 1.3172286748886108,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 0.0914,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.4090909090909091,
274
+ "grad_norm": 4.161808490753174,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 0.133,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.42045454545454547,
281
+ "grad_norm": 7.600207805633545,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 0.1262,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.4318181818181818,
288
+ "grad_norm": 7.597659587860107,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 0.2628,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.4431818181818182,
295
+ "grad_norm": 3.380033016204834,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 0.2251,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.45454545454545453,
302
+ "grad_norm": 2.1588728427886963,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 0.2003,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.4659090909090909,
309
+ "grad_norm": 4.2201032638549805,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 0.2124,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.4772727272727273,
316
+ "grad_norm": 4.442834854125977,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 0.1443,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.48863636363636365,
323
+ "grad_norm": 2.6062257289886475,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 0.1259,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.5,
330
+ "grad_norm": 1.960435390472412,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 0.0906,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.5113636363636364,
337
+ "grad_norm": 1.2171847820281982,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 0.0843,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.5227272727272727,
344
+ "grad_norm": 1.653974175453186,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 0.0865,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.5340909090909091,
351
+ "grad_norm": 2.488990306854248,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 0.0781,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.5454545454545454,
358
+ "grad_norm": 0.5377188324928284,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 0.0432,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.5568181818181818,
365
+ "grad_norm": 1.272202491760254,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 0.0986,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.5681818181818182,
372
+ "grad_norm": 1.9467240571975708,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.1464,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.5681818181818182,
379
+ "eval_loss": 0.11914384365081787,
380
+ "eval_runtime": 6.7655,
381
+ "eval_samples_per_second": 87.65,
382
+ "eval_steps_per_second": 11.086,
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": 1.059536353886208e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null