mamung commited on
Commit
2ec7a5a
·
verified ·
1 Parent(s): f497389

Training in progress, step 90, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:160429ba22b04fdbad7986d3afa68476d7c662fd7a918ab53b902b2e11e43a96
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:088f8bae62a5af3f96c18c4ee43c521c1fb8248a9ead1c47807a1f581aba283c
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55fae3faf0e97152f1535d44bb7cd537b1b90ea36c196f3303a58e63422b4a5d
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2d2e4348163db8a6005a35bbf36d286235f03b5b6a202278adbad74e100c0dc
3
  size 671466706
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9db0a36de4bb96902a948897c32d08fcc8f52ec7148136028a54d1ab041188bd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8584d63d2faee24e8a54114c8749ed64521b513195990dab72712f855912e2d1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4967fab956f007beafd6b8bc5c5dee4d86950ea055e4ab46c9a7cdc66a69112d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6b7babead6c4be4368caff2650e543461856d401ff242b042a60fc57cd3bcca
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": 0.011352786075317325,
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,
@@ -276,6 +276,35 @@
276
  "eval_samples_per_second": 8.988,
277
  "eval_steps_per_second": 4.494,
278
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  }
280
  ],
281
  "logging_steps": 3,
@@ -295,7 +324,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 4.83414773002666e+17,
299
  "train_batch_size": 2,
300
  "trial_name": null,
301
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.012614206750352585,
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,
 
276
  "eval_samples_per_second": 8.988,
277
  "eval_steps_per_second": 4.494,
278
  "step": 81
279
+ },
280
+ {
281
+ "epoch": 0.011773259633662412,
282
+ "grad_norm": 0.9498192667961121,
283
+ "learning_rate": 1.9098300562505266e-05,
284
+ "loss": 1.331,
285
+ "step": 84
286
+ },
287
+ {
288
+ "epoch": 0.012193733192007498,
289
+ "grad_norm": 0.8051778078079224,
290
+ "learning_rate": 1.2750399292720283e-05,
291
+ "loss": 1.2632,
292
+ "step": 87
293
+ },
294
+ {
295
+ "epoch": 0.012614206750352585,
296
+ "grad_norm": 0.9142070412635803,
297
+ "learning_rate": 7.612046748871327e-06,
298
+ "loss": 1.3475,
299
+ "step": 90
300
+ },
301
+ {
302
+ "epoch": 0.012614206750352585,
303
+ "eval_loss": 1.3223891258239746,
304
+ "eval_runtime": 2674.1901,
305
+ "eval_samples_per_second": 8.987,
306
+ "eval_steps_per_second": 4.494,
307
+ "step": 90
308
  }
309
  ],
310
  "logging_steps": 3,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 5.3712752555851776e+17,
328
  "train_batch_size": 2,
329
  "trial_name": null,
330
  "trial_params": null