dixedus commited on
Commit
991384a
·
verified ·
1 Parent(s): 7672b74

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 sha256:90db6f7523257cea8034b331d2e099960a6ae4b7c656d63dba11bcd490841f89
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50deb99a0b7a438467da0c716b3d345f8abb26fd8eff569ceff46d7f1733710f
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea0b2a565948281537a525addfa5a45bdfce4f07d92bf0efe30dffd3c187c5d3
3
  size 111142
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc13504cb3f8dbad87758f0631389015a1e09fe768ac646a3565eefac80318f
3
  size 111142
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b6aa6d92613d8ec55613881281a6c881897813d14e7c601a64ba4f3be3d2a35
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3d7638315e3e0a14cff55b75bcf9d18fa85d487a83a898f3906ffbf5885ed30
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
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": 0.3525954946131244,
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": 570.3,
306
  "eval_steps_per_second": 71.619,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 9414440386560.0,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3878550440744368,
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": 570.3,
306
  "eval_steps_per_second": 71.619,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.3643486777668952,
311
+ "grad_norm": 0.05382026731967926,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 10.366,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.376101860920666,
318
+ "grad_norm": 0.05993453785777092,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 10.3649,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.3878550440744368,
325
+ "grad_norm": 0.05342447757720947,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 10.3646,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.3878550440744368,
332
+ "eval_loss": 10.365524291992188,
333
+ "eval_runtime": 0.7745,
334
+ "eval_samples_per_second": 555.185,
335
+ "eval_steps_per_second": 69.721,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 10355884425216.0,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null