eddysang commited on
Commit
8354a1b
·
verified ·
1 Parent(s): 47d1414

Training in progress, step 99, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:815d6bb5bf102182e22a1174867f1fb39e240d76c6eb3906632181e6235e80eb
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33cf26ff62e214ee6fc2d05a911e5eb05dd51fcdb3e46f75bd1bf5c8f3121809
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25995127a8eff83576b0aa8269e0157f0685925857b5fdd51022cb4dda263146
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ed53735ad8f68e592453a181a595592f1f6ec1b749802e0e890afc92238ce9a
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:a12a89be9332cd67b8b31b4c46ef54558059ca89ed9c61c00ead2e0293a8fd09
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5598b7987a0e047c8edfb1d3e18c76537a517df0b8e8a5f7629abec91df7c92c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6b7babead6c4be4368caff2650e543461856d401ff242b042a60fc57cd3bcca
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7041fa0be7432c15ac468c1425bc3b5d595e4b5b769cfa7728743ab80ef12291
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": 0.008659388370561688,
5
  "eval_steps": 9,
6
- "global_step": 90,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -305,6 +305,35 @@
305
  "eval_samples_per_second": 2.847,
306
  "eval_steps_per_second": 1.424,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 4.7332406838951936e+17,
328
  "train_batch_size": 2,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.009525327207617857,
5
  "eval_steps": 9,
6
+ "global_step": 99,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
305
  "eval_samples_per_second": 2.847,
306
  "eval_steps_per_second": 1.424,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.00894803464958041,
311
+ "grad_norm": 14.83832836151123,
312
+ "learning_rate": 3.7544763546352834e-06,
313
+ "loss": 4.7525,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.009236680928599134,
318
+ "grad_norm": 12.520251274108887,
319
+ "learning_rate": 1.231165940486234e-06,
320
+ "loss": 4.5588,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.009525327207617857,
325
+ "grad_norm": 17.722375869750977,
326
+ "learning_rate": 7.709637592770991e-08,
327
+ "loss": 4.3476,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.009525327207617857,
332
+ "eval_loss": 0.14178016781806946,
333
+ "eval_runtime": 9365.6187,
334
+ "eval_samples_per_second": 3.738,
335
+ "eval_steps_per_second": 1.869,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 5.206564752284713e+17,
357
  "train_batch_size": 2,
358
  "trial_name": null,
359
  "trial_params": null