leixa commited on
Commit
2301a14
·
verified ·
1 Parent(s): 55ff9c3

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 sha256:2bc46fc2e367ca35bce5646a527a94ecf20ba7fe26937c34d90b79e7f566b2c4
3
  size 458278
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb2de700abee18cc74db321ece69444250660040db4c9d2d79dba989035f4c8d
3
  size 458278
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4e5ddb47409a725b0ce35a57468a5a86b6d3ba77f237c7b0a5f2c7aae804145
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd0aaedb551c4ed6d1a681a74f25d0e7f09df1298892466b2d9d6f1f8889fb30
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
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": 0.036753445635528334,
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": 426.439,
248
  "eval_steps_per_second": 53.37,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 20460574605312.0,
270
  "train_batch_size": 8,
271
  "trial_name": null,
272
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.04134762633996937,
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": 426.439,
248
  "eval_steps_per_second": 53.37,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.03828483920367534,
253
+ "grad_norm": NaN,
254
+ "learning_rate": 1.7860619515673033e-05,
255
+ "loss": 0.0,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.039816232771822356,
260
+ "grad_norm": NaN,
261
+ "learning_rate": 1.4033009983067452e-05,
262
+ "loss": 0.0,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.04134762633996937,
267
+ "grad_norm": NaN,
268
+ "learning_rate": 1.0599462319663905e-05,
269
+ "loss": 0.0,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.04134762633996937,
274
+ "eval_loss": NaN,
275
+ "eval_runtime": 7.6954,
276
+ "eval_samples_per_second": 428.825,
277
+ "eval_steps_per_second": 53.668,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 23038284791808.0,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null