mgh6 commited on
Commit
88261ce
·
verified ·
1 Parent(s): a1a6723

Training in progress, step 3600, 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:b97d4789449a829ba6967c26f88e6fb1d82de78eaecc34cb1d82a6d35e1e894a
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9126986b6437e9424d3d0f5b553512898523903fc8cf9ccdf63aa74be74889c4
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47b1eca478433de5f9c62dea463f61950fd620b0be021230d58e0ae99dadfcca
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5836c907a432621761f7f9927e95937e7c0d2f9d4c25602b26458b989274e68
3
  size 16386426
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d7f6140254e7b0fc70eb6194d0d97925be55a60fce52d6b728d7ec8079bd94d
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1664ff742c3325d24d2f3b861825961c7c40bb94483223e026655af2b4dd0f80
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4aa17ebc8dd2b45de60c809b3e54b378786946552985dbb94de64b75faaaabf3
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36fd92c520dd1b6d66e5d0c226b422ec328d013bd86695dca37c8a578165dcf8
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": 6.998906420871739,
5
  "eval_steps": 500,
6
- "global_step": 3500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -308,6 +308,13 @@
308
  "eval_samples_per_second": 19.9,
309
  "eval_steps_per_second": 2.488,
310
  "step": 3500
 
 
 
 
 
 
 
311
  }
312
  ],
313
  "logging_steps": 100,
@@ -327,7 +334,7 @@
327
  "attributes": {}
328
  }
329
  },
330
- "total_flos": 5.462569050364183e+18,
331
  "train_batch_size": 8,
332
  "trial_name": null,
333
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 7.1988751757537885,
5
  "eval_steps": 500,
6
+ "global_step": 3600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
308
  "eval_samples_per_second": 19.9,
309
  "eval_steps_per_second": 2.488,
310
  "step": 3500
311
+ },
312
+ {
313
+ "epoch": 7.1988751757537885,
314
+ "grad_norm": 0.17379523813724518,
315
+ "learning_rate": 7.6e-05,
316
+ "loss": 1.2688,
317
+ "step": 3600
318
  }
319
  ],
320
  "logging_steps": 100,
 
334
  "attributes": {}
335
  }
336
  },
337
+ "total_flos": 5.618634864682074e+18,
338
  "train_batch_size": 8,
339
  "trial_name": null,
340
  "trial_params": null