jssky commited on
Commit
357466e
1 Parent(s): cf067bd

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 sha256:9ebdf1b48c51b87ba61738c2daa0f686e666adc4da2b111b770ec3d39dc85d2b
3
  size 97728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ac19f51c2148eeac5bdbfc2d3e82433e828c73e5aa7270e9ea0ba51328edd73
3
  size 97728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51f44ddd221a3830cf2c975cc4f09a78b270ec0f1c3b6cec555929131eb4d0cb
3
  size 212298
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62eb26226a94c8d76df5618aef4d341d16283e48b8ecd422c001178a33d2856a
3
  size 212298
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e1d2be50a0535244244d5b8ab5eb6262c3e06caca3b5b7b1ff406ed8f2aeeab
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ebe8dd4f8a10c734446f2a1158dedaefc538ae2d043d16b0568f8cd88c1ab0f
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 sha256:123d716bc5ebb29ccb7a4f36f26016e0d513c39664c9f76b6f9982e61e2fa033
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f136b7028e9a93341b429d91e1dde762ba3a33f684eb6c78c5432f1c952680
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 sha256:5ddf05dc3c78e063f7988074e041fce8ac18ca47da15097c65b542d41faa7784
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0461307e9338b6aa0e0568d7301d203c18e4a75bcf196f1201f361ae620ea073
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:c34732c7dcf3b1569e6b698feaff197d48a676aedbba3d1d41c76e9e1f9079bb
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4469e3945fed34bb2b6bc1e64bcee57965a510691908b65159e88c9185b6d5db
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": 10.368462562561035,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.14684287812041116,
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": 315.488,
199
  "eval_steps_per_second": 39.608,
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": 21557775040512.0,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.363272666931152,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.2936857562408223,
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": 315.488,
199
  "eval_steps_per_second": 39.608,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.1527165932452276,
204
+ "grad_norm": 0.21917545795440674,
205
+ "learning_rate": 5e-05,
206
+ "loss": 10.3686,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.15859030837004406,
211
+ "grad_norm": 0.20469699800014496,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 10.3687,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.1644640234948605,
218
+ "grad_norm": 0.20218636095523834,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 10.3679,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.17033773861967694,
225
+ "grad_norm": 0.19212639331817627,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 10.3662,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.1762114537444934,
232
+ "grad_norm": 0.18560166656970978,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 10.3675,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.18208516886930984,
239
+ "grad_norm": 0.18543921411037445,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 10.368,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.18795888399412627,
246
+ "grad_norm": 0.18739567697048187,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 10.3678,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.19383259911894274,
253
+ "grad_norm": 0.1920151710510254,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 10.3679,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.19970631424375918,
260
+ "grad_norm": 0.18959976732730865,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 10.3669,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.2055800293685756,
267
+ "grad_norm": 0.1854933500289917,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 10.3668,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.21145374449339208,
274
+ "grad_norm": 0.18347898125648499,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 10.3623,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.2173274596182085,
281
+ "grad_norm": 0.1941113919019699,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 10.3596,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.22320117474302498,
288
+ "grad_norm": 0.24184665083885193,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 10.3645,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.2290748898678414,
295
+ "grad_norm": 0.24406494200229645,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 10.3634,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.23494860499265785,
302
+ "grad_norm": 0.23579344153404236,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 10.3638,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.24082232011747431,
309
+ "grad_norm": 0.2283434420824051,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 10.3634,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.24669603524229075,
316
+ "grad_norm": 0.21662116050720215,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 10.3624,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.2525697503671072,
323
+ "grad_norm": 0.21385407447814941,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 10.3656,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.25844346549192365,
330
+ "grad_norm": 0.20657625794410706,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 10.3659,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.2643171806167401,
337
+ "grad_norm": 0.20029610395431519,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 10.3655,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.2701908957415565,
344
+ "grad_norm": 0.2030303031206131,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 10.365,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.27606461086637296,
351
+ "grad_norm": 0.20757298171520233,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 10.3641,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.28193832599118945,
358
+ "grad_norm": 0.20119069516658783,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 10.3643,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.2878120411160059,
365
+ "grad_norm": 0.1982789784669876,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 10.3607,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.2936857562408223,
372
+ "grad_norm": 0.20990411937236786,
373
+ "learning_rate": 0.0,
374
+ "loss": 10.3577,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.2936857562408223,
379
+ "eval_loss": 10.363272666931152,
380
+ "eval_runtime": 3.6828,
381
+ "eval_samples_per_second": 311.451,
382
+ "eval_steps_per_second": 39.101,
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": 43062090006528.0,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null