eeeebbb2 commited on
Commit
81cb66c
1 Parent(s): 41ff664

Training in progress, step 43, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:742d7d6b09eceb8a893ef3294602a4da77806a229682af265a781d9889815994
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7d5ff2a0d108e41ae85e53bbf492ec1fae97e2b7e8e4ead0320e0d738b36e65
3
  size 671466706
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87f490d9b058452de6083933609031da97b25e8e1cdc93810a66cee409bc28d1
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9d691571bd89d18e6b4b42a66c68be3ffe2ca8a8d5439985b59322304de5aba
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 sha256:10e24003942246a09c0a69fa8eaaf3bcd568ef637269087c244f7c448f5da6ed
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fee0ac0c86b2d59028e0f36191745084fe97d08f197f12d214d956586dfa17a
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:b8dc3237e263eaee1953872b5ad5a2c51be988ac2b027bdd863cf4c7b6180cd4
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c813d5de458dcb1d7994b2f7e8380036fd8607256752118412cb24172050092
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 sha256:424ee3a629fc9373914465bc1852754a127d7bf9f43491d8ce9f1f4a94971500
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:121cdd9f8267544c4a2a2b19947b5a84a8887c53209ba520ebbe39b62a519ed9
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f73e6deadf3f08547d8bef9e9b3d87995c0c2ef87d51b8801270b8b2d32ac55
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9ca16dc5125aa616f8880e7477dabd4029e096d950b1e4b31474d314c00eace
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 1.7665198237885462,
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 +198,132 @@
198
  "eval_samples_per_second": 13.815,
199
  "eval_steps_per_second": 3.592,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -221,12 +347,12 @@
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": 3.0677119162279526e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
+ "epoch": 3.0440528634361232,
5
  "eval_steps": 25,
6
+ "global_step": 43,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
198
  "eval_samples_per_second": 13.815,
199
  "eval_steps_per_second": 3.592,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 1.8370044052863435,
204
+ "grad_norm": NaN,
205
+ "learning_rate": 4.307583240115024e-05,
206
+ "loss": 0.0,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 1.907488986784141,
211
+ "grad_norm": NaN,
212
+ "learning_rate": 3.9789240471617385e-05,
213
+ "loss": 0.0,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 1.9779735682819384,
218
+ "grad_norm": NaN,
219
+ "learning_rate": 3.659191132728971e-05,
220
+ "loss": 0.0,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 2.052863436123348,
225
+ "grad_norm": NaN,
226
+ "learning_rate": 3.350260816694816e-05,
227
+ "loss": 0.0,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 2.1233480176211454,
232
+ "grad_norm": NaN,
233
+ "learning_rate": 3.0539460249945056e-05,
234
+ "loss": 0.0,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 2.193832599118943,
239
+ "grad_norm": NaN,
240
+ "learning_rate": 2.7719856506501306e-05,
241
+ "loss": 0.0,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 2.26431718061674,
246
+ "grad_norm": NaN,
247
+ "learning_rate": 2.5060343492549566e-05,
248
+ "loss": 0.0,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 2.3348017621145374,
253
+ "grad_norm": NaN,
254
+ "learning_rate": 2.257652828796459e-05,
255
+ "loss": 0.0,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 2.405286343612335,
260
+ "grad_norm": NaN,
261
+ "learning_rate": 2.0282986908012567e-05,
262
+ "loss": 0.0,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 2.4757709251101323,
267
+ "grad_norm": NaN,
268
+ "learning_rate": 1.819317876549771e-05,
269
+ "loss": 0.0,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 2.5462555066079293,
274
+ "grad_norm": NaN,
275
+ "learning_rate": 1.631936768557596e-05,
276
+ "loss": 0.0,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 2.616740088105727,
281
+ "grad_norm": NaN,
282
+ "learning_rate": 1.4672549936752506e-05,
283
+ "loss": 0.0,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 2.6872246696035242,
288
+ "grad_norm": NaN,
289
+ "learning_rate": 1.3262389700405744e-05,
290
+ "loss": 0.0,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 2.7577092511013217,
295
+ "grad_norm": NaN,
296
+ "learning_rate": 1.2097162357528127e-05,
297
+ "loss": 0.0,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 2.828193832599119,
302
+ "grad_norm": NaN,
303
+ "learning_rate": 1.1183705925499948e-05,
304
+ "loss": 0.0,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 2.898678414096916,
309
+ "grad_norm": NaN,
310
+ "learning_rate": 1.0527380929884324e-05,
311
+ "loss": 0.0,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 2.9691629955947136,
316
+ "grad_norm": NaN,
317
+ "learning_rate": 1.013203894673168e-05,
318
+ "loss": 0.0,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 3.0440528634361232,
323
+ "grad_norm": NaN,
324
+ "learning_rate": 1e-05,
325
+ "loss": 0.0,
326
+ "step": 43
327
  }
328
  ],
329
  "logging_steps": 1,
 
347
  "should_evaluate": false,
348
  "should_log": false,
349
  "should_save": true,
350
+ "should_training_stop": true
351
  },
352
  "attributes": {}
353
  }
354
  },
355
+ "total_flos": 5.251356976952115e+17,
356
  "train_batch_size": 2,
357
  "trial_name": null,
358
  "trial_params": null