leixa commited on
Commit
dccfaaf
·
verified ·
1 Parent(s): 5e151ec

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:b88f3c7c77d99c048e6add4680d23bd6bf2387e1016bd93ca52827ba82bfe877
3
  size 402688040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d2ac8ffaae35ebc46c10eb63842612e594db14a9786b774ebe177b66c1ca036
3
  size 402688040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45df09bb7e4a46b62eaa2a3dc0e75a6cc9fa523d37622e62105bc461b76c49b8
3
  size 204773716
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:880ed321941e1257528cdd71143c52d322cc8ca83d2bd070a7cb16de46a471db
3
  size 204773716
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16215388afc6623b7ea6ac94c4730d97bc2f908553fda11448447197c6028958
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53aacfa60b6ea0694f6b68c1cfef1e229e0abd3a022abe1a726e9429d5208a11
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": 0.9183673469387755,
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": 14.768,
306
  "eval_steps_per_second": 1.88,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 6.76512009289728e+16,
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": 1.010204081632653,
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": 14.768,
306
  "eval_steps_per_second": 1.88,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.9489795918367347,
311
+ "grad_norm": 3.8432347774505615,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 6.5667,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.9795918367346939,
318
+ "grad_norm": 3.743124008178711,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 6.4069,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 1.010204081632653,
325
+ "grad_norm": 3.2074642181396484,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 6.4376,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 1.010204081632653,
332
+ "eval_loss": 1.579128384590149,
333
+ "eval_runtime": 11.1546,
334
+ "eval_samples_per_second": 14.792,
335
+ "eval_steps_per_second": 1.883,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 7.43458510209024e+16,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null