mamung commited on
Commit
40e644e
·
verified ·
1 Parent(s): 43664b6

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 sha256:55a16deace7db4dca26ff393678ecf892d9bd8adf30160a6e4f9c90ae7cfd755
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1666456c3161e9f5a1d2d5f477be162b3d1154447465cb1222c372489093edd6
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94afdcfe23d4f1bd836f0532add3aa0577052ce7e3ae56b24537e63dd3a3653f
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7a46c3bb12d80f412e89aa6bb907e4782c7d0445d5437d015e3c0c4b01afb76
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:d42e8c1df81a33b793c5a211458c107027d88dcb82feca62f3fac4579f6bd01f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e18e668860aa083adef211013189cd3d58c25adbb67cd9b0e99f8ed5231c4495
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": 1.3615907901622188,
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": 2.758,
277
  "eval_steps_per_second": 1.379,
278
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  }
280
  ],
281
  "logging_steps": 3,
@@ -295,7 +324,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 4.259874868423557e+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": 1.5122972265829409,
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": 2.758,
277
  "eval_steps_per_second": 1.379,
278
  "step": 81
279
+ },
280
+ {
281
+ "epoch": 1.411826268969126,
282
+ "grad_norm": 5.425446033477783,
283
+ "learning_rate": 1.9098300562505266e-05,
284
+ "loss": 1.4703,
285
+ "step": 84
286
+ },
287
+ {
288
+ "epoch": 1.4620617477760334,
289
+ "grad_norm": 5.082719802856445,
290
+ "learning_rate": 1.2750399292720283e-05,
291
+ "loss": 1.6151,
292
+ "step": 87
293
+ },
294
+ {
295
+ "epoch": 1.5122972265829409,
296
+ "grad_norm": 5.419787406921387,
297
+ "learning_rate": 7.612046748871327e-06,
298
+ "loss": 1.6353,
299
+ "step": 90
300
+ },
301
+ {
302
+ "epoch": 1.5122972265829409,
303
+ "eval_loss": 0.0507192499935627,
304
+ "eval_runtime": 73.2046,
305
+ "eval_samples_per_second": 2.759,
306
+ "eval_steps_per_second": 1.38,
307
+ "step": 90
308
  }
309
  ],
310
  "logging_steps": 3,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 4.733194298248397e+17,
328
  "train_batch_size": 2,
329
  "trial_name": null,
330
  "trial_params": null