dixedus commited on
Commit
be42669
·
verified ·
1 Parent(s): ef72d7b

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 sha256:4aa12ba5484f85c91b6a60e663c128eb6be44608ac18b2b925eab289ed7e7ba9
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d077144c5400130fe701b66c9e94ce0dab07892d8a38a29f2f28e4f308f824a4
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdc4e7e3b89124f9aa6911802a31c74e5123002b6aa78bc60ebb71424358ed4c
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc70df486ddd3a33fc454c0cee5bd8d31ef2768d65e0ef1215260d81e733325
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b202cc35d4d82828b46ac25c2aa3b0d5b24c9fdd644bb03957f013b307cbc71d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca5ed7077b7e80b15b5b40bb67c00bb6aeb10626f97d2892620cc3f79d1da45
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": 0.030911901081916538,
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": 14.316,
306
  "eval_steps_per_second": 1.789,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.2656330976264192e+17,
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": 0.03400309119010819,
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": 14.316,
306
  "eval_steps_per_second": 1.789,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.03194229778464709,
311
+ "grad_norm": 4.3883514404296875,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 1.1972,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.03297269448737764,
318
+ "grad_norm": 3.4957001209259033,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 1.2607,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.03400309119010819,
325
+ "grad_norm": 4.808172225952148,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 1.2998,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.03400309119010819,
332
+ "eval_loss": 0.3200424015522003,
333
+ "eval_runtime": 342.4378,
334
+ "eval_samples_per_second": 14.321,
335
+ "eval_steps_per_second": 1.79,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.3921964073890611e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null