kooff11 commited on
Commit
dd2d27f
·
verified ·
1 Parent(s): 1589ac6

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1e26bf3a339e3a31a9b595cef472952414206620319d72fb49f8f7b4bed1b61
3
  size 124606
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbadaf223260ebfb0f7d07045def973582b038a1553f67df32fa6c53a4f8e809
3
  size 124606
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04732c8c2e16f0dfe69365b1325d4a79b777de313cb9ad5a334db046def79d61
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3848ab9088068892741d484f87da8e9c68e36d2fe8e75c5c8aeecb12bb09263
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8a51a76ac2870b6151b18050fb3209a9f46d244ed22a262eea2fe28a9b1969e
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b61e915a5fdf8265019395627befc85bd0007e20095542800ed00d06133e222
3
  size 14512
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.029161263187410184,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -213,6 +213,105 @@
213
  "eval_samples_per_second": 375.464,
214
  "eval_steps_per_second": 93.882,
215
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
216
  }
217
  ],
218
  "logging_steps": 1,
@@ -232,7 +331,7 @@
232
  "attributes": {}
233
  }
234
  },
235
- "total_flos": 86780015542272.0,
236
  "train_batch_size": 2,
237
  "trial_name": null,
238
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.04374189478111528,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
213
  "eval_samples_per_second": 375.464,
214
  "eval_steps_per_second": 93.882,
215
  "step": 26
216
+ },
217
+ {
218
+ "epoch": 0.03028285023307981,
219
+ "grad_norm": NaN,
220
+ "learning_rate": 4.6729843538492847e-05,
221
+ "loss": 0.0,
222
+ "step": 27
223
+ },
224
+ {
225
+ "epoch": 0.031404437278749434,
226
+ "grad_norm": NaN,
227
+ "learning_rate": 4.347369038899744e-05,
228
+ "loss": 0.0,
229
+ "step": 28
230
+ },
231
+ {
232
+ "epoch": 0.032526024324419055,
233
+ "grad_norm": NaN,
234
+ "learning_rate": 4.0245483899193595e-05,
235
+ "loss": 0.0,
236
+ "step": 29
237
+ },
238
+ {
239
+ "epoch": 0.033647611370088676,
240
+ "grad_norm": NaN,
241
+ "learning_rate": 3.705904774487396e-05,
242
+ "loss": 0.0,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 0.0347691984157583,
247
+ "grad_norm": NaN,
248
+ "learning_rate": 3.392802673484193e-05,
249
+ "loss": 0.0,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 0.03589078546142792,
254
+ "grad_norm": NaN,
255
+ "learning_rate": 3.086582838174551e-05,
256
+ "loss": 0.0,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 0.037012372507097546,
261
+ "grad_norm": NaN,
262
+ "learning_rate": 2.7885565489049946e-05,
263
+ "loss": 0.0,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 0.03813395955276717,
268
+ "grad_norm": NaN,
269
+ "learning_rate": 2.500000000000001e-05,
270
+ "loss": 0.0,
271
+ "step": 34
272
+ },
273
+ {
274
+ "epoch": 0.03925554659843679,
275
+ "grad_norm": NaN,
276
+ "learning_rate": 2.2221488349019903e-05,
277
+ "loss": 0.0,
278
+ "step": 35
279
+ },
280
+ {
281
+ "epoch": 0.04037713364410641,
282
+ "grad_norm": NaN,
283
+ "learning_rate": 1.9561928549563968e-05,
284
+ "loss": 0.0,
285
+ "step": 36
286
+ },
287
+ {
288
+ "epoch": 0.04149872068977603,
289
+ "grad_norm": NaN,
290
+ "learning_rate": 1.703270924499656e-05,
291
+ "loss": 0.0,
292
+ "step": 37
293
+ },
294
+ {
295
+ "epoch": 0.04262030773544566,
296
+ "grad_norm": NaN,
297
+ "learning_rate": 1.4644660940672627e-05,
298
+ "loss": 0.0,
299
+ "step": 38
300
+ },
301
+ {
302
+ "epoch": 0.04374189478111528,
303
+ "grad_norm": NaN,
304
+ "learning_rate": 1.2408009626051137e-05,
305
+ "loss": 0.0,
306
+ "step": 39
307
+ },
308
+ {
309
+ "epoch": 0.04374189478111528,
310
+ "eval_loss": NaN,
311
+ "eval_runtime": 16.0055,
312
+ "eval_samples_per_second": 375.309,
313
+ "eval_steps_per_second": 93.843,
314
+ "step": 39
315
  }
316
  ],
317
  "logging_steps": 1,
 
331
  "attributes": {}
332
  }
333
  },
334
+ "total_flos": 130170023313408.0,
335
  "train_batch_size": 2,
336
  "trial_name": null,
337
  "trial_params": null