vdos commited on
Commit
add3ed1
·
verified ·
1 Parent(s): 5217166

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 sha256:3ad4f5664d663372a2e89c31957f7e0ad85c1369042727c1afdad679fefa2faa
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:569a5bafff3b87b32cd0bd5b9a6392d1b0939e421b156b257b2b6623ff347057
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23ff778ee95f39b046babda857d331190fdd3294fdabc0f1f57b099dd372dc50
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73033e70034a02b578030a00c7fbb33a78b06f3382d01670cffad8b34a23e557
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 sha256:501db7efe3bba3951c1b8ca1a6bf4a0ac69f9b456a64851df200bb8fdce86995
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56394fd85659b94c3b9cc1869486c17ce86d632d904dcf91dbd1286ffe6415a
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 sha256:678ef81f58242bba72300afb23992bb3993089927e31bf7ef12d307b017e88d1
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f95a1fbd283ff1c89506e2ae64172c6d7204bde531195c82fe7fa4ff48f7ab4
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:f1365095aec21a37df54a5d748b80d8fb283baea1bb0aa230de13c691d82067a
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08b9c675725fd9fdd8f29c4d396288cb96d7751582ab07408b42e41856ca4881
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 sha256:62c0fce48c894e9f8297b8918550c3f32913489b449c6172c118964dd728f561
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83d2294d00e6fce89b284b033052f3ccd76cca7d8864d16099059125214c6b30
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": 1.6387038230895996,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.030632562413845918,
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": 34.431,
199
  "eval_steps_per_second": 4.309,
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": 2.6344827956232192e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.599951148033142,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.061265124827691836,
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": 34.431,
199
  "eval_steps_per_second": 4.309,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.031857864910399755,
204
+ "grad_norm": 0.10918952524662018,
205
+ "learning_rate": 5e-05,
206
+ "loss": 1.0948,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.03308316740695359,
211
+ "grad_norm": 0.1791597455739975,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 1.2498,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.03430846990350743,
218
+ "grad_norm": 0.2935185134410858,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 1.3262,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.03553377240006127,
225
+ "grad_norm": 0.37032783031463623,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 1.3698,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.036759074896615104,
232
+ "grad_norm": 0.2906474769115448,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 1.2198,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.03798437739316894,
239
+ "grad_norm": 0.2047668993473053,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 1.2105,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.03920967988972277,
246
+ "grad_norm": 0.1876075118780136,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 1.197,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.04043498238627661,
253
+ "grad_norm": 0.22366094589233398,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 1.3892,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.041660284882830446,
260
+ "grad_norm": 0.2662312090396881,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 1.612,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.042885587379384284,
267
+ "grad_norm": 0.32836422324180603,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 1.6611,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.04411088987593812,
274
+ "grad_norm": 0.4305000603199005,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 1.9214,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.04533619237249196,
281
+ "grad_norm": 0.5970643758773804,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 1.9747,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.046561494869045796,
288
+ "grad_norm": 0.10557608306407928,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 0.901,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.04778679736559963,
295
+ "grad_norm": 0.14012107253074646,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 1.38,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.04901209986215347,
302
+ "grad_norm": 0.1754305362701416,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 1.1382,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.05023740235870731,
309
+ "grad_norm": 0.24448178708553314,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 1.4041,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.051462704855261145,
316
+ "grad_norm": 0.2805235981941223,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 1.351,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.05268800735181498,
323
+ "grad_norm": 0.1339372992515564,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 1.3022,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.05391330984836882,
330
+ "grad_norm": 0.12944447994232178,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 1.2448,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.05513861234492265,
337
+ "grad_norm": 0.1557026505470276,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 1.4178,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.05636391484147649,
344
+ "grad_norm": 0.20143267512321472,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 1.5663,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.057589217338030324,
351
+ "grad_norm": 0.25110936164855957,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 1.6935,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.05881451983458416,
358
+ "grad_norm": 0.35833045840263367,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 1.7919,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.060039822331138,
365
+ "grad_norm": 0.5051993727684021,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 1.9054,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.061265124827691836,
372
+ "grad_norm": 1.0000535249710083,
373
+ "learning_rate": 0.0,
374
+ "loss": 2.3356,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.061265124827691836,
379
+ "eval_loss": 1.599951148033142,
380
+ "eval_runtime": 159.6819,
381
+ "eval_samples_per_second": 34.431,
382
+ "eval_steps_per_second": 4.309,
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": 5.270609060482253e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null