eddysang commited on
Commit
34f24c8
·
verified ·
1 Parent(s): 0b8ea35

Training in progress, step 81, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7fc409f0cd4922b48234cc46633800eb915f58fb50d607b96a99d2abf746ba4f
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d45f5c174872a9615990632d8308157dffeffe982d8809a1ddd7f0c3fd8d282a
3
  size 640009682
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:963103910acf3003b8f4035e02dee57e8e13bbe04dcb03283c8c89f04827e98f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76176b194774cb7a663950593f31d2e41cbb03e09a4aaaaf2425c3c4a43bad6c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f9245597e5014ecf432f2646dbac4f88c26cbc6ab1676ee7be71281b45d826d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4967fab956f007beafd6b8bc5c5dee4d86950ea055e4ab46c9a7cdc66a69112d
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": 0.025996885789723107,
5
  "eval_steps": 9,
6
- "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -247,6 +247,35 @@
247
  "eval_samples_per_second": 4.352,
248
  "eval_steps_per_second": 2.176,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 3.819804670222664e+17,
270
  "train_batch_size": 2,
271
  "trial_name": null,
272
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.029246496513438493,
5
  "eval_steps": 9,
6
+ "global_step": 81,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
247
  "eval_samples_per_second": 4.352,
248
  "eval_steps_per_second": 2.176,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.0270800893642949,
253
+ "grad_norm": NaN,
254
+ "learning_rate": 4.444297669803981e-05,
255
+ "loss": 0.0,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.0281632929388667,
260
+ "grad_norm": NaN,
261
+ "learning_rate": 3.5055195166981645e-05,
262
+ "loss": 0.0,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.029246496513438493,
267
+ "grad_norm": NaN,
268
+ "learning_rate": 2.6567749056431467e-05,
269
+ "loss": 0.0,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.029246496513438493,
274
+ "eval_loss": NaN,
275
+ "eval_runtime": 2143.4135,
276
+ "eval_samples_per_second": 4.352,
277
+ "eval_steps_per_second": 2.176,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 4.2972802540004966e+17,
299
  "train_batch_size": 2,
300
  "trial_name": null,
301
  "trial_params": null