mamung commited on
Commit
c6c85f6
·
verified ·
1 Parent(s): 9ef6034

Training in progress, step 81, 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:cfd8957fc076960c30b730496f2c8be0968e87df245ba83540c8fe45c8ce1b5c
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55a16deace7db4dca26ff393678ecf892d9bd8adf30160a6e4f9c90ae7cfd755
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23991589a9558d35301f754221fb75eb5d034a6e6a21b3ffbef0e6f1636637df
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94afdcfe23d4f1bd836f0532add3aa0577052ce7e3ae56b24537e63dd3a3653f
3
  size 640009682
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54695bae591aceb2574c0570650d7a15033601e879a5235bc5ef9cc452369efd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d42e8c1df81a33b793c5a211458c107027d88dcb82feca62f3fac4579f6bd01f
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": 1.2108843537414966,
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": 2.76,
248
  "eval_steps_per_second": 1.38,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 3.7865554385987174e+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": 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,
 
247
  "eval_samples_per_second": 2.76,
248
  "eval_steps_per_second": 1.38,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 1.2611198325484039,
253
+ "grad_norm": 8.14849853515625,
254
+ "learning_rate": 4.444297669803981e-05,
255
+ "loss": 1.6062,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 1.3113553113553114,
260
+ "grad_norm": 6.613561153411865,
261
+ "learning_rate": 3.5055195166981645e-05,
262
+ "loss": 1.7725,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 1.3615907901622188,
267
+ "grad_norm": 6.738033771514893,
268
+ "learning_rate": 2.6567749056431467e-05,
269
+ "loss": 1.4988,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 1.3615907901622188,
274
+ "eval_loss": 0.052346888929605484,
275
+ "eval_runtime": 73.2318,
276
+ "eval_samples_per_second": 2.758,
277
+ "eval_steps_per_second": 1.379,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 4.259874868423557e+17,
299
  "train_batch_size": 2,
300
  "trial_name": null,
301
  "trial_params": null