Nexspear commited on
Commit
0c7c417
·
verified ·
1 Parent(s): a0231ce

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 sha256:9e5ae1455f13db9b27f32134b02d3129ddfcdb195bfc53900c81c044adf49de0
3
  size 34793120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4003efb915e5573c7bab56b16ceed2622bbc92a50e703fd011d3df1496bd74f7
3
  size 34793120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec6b41927c2d77c84a8e452939b93ffd1455afdf3b305d77c6bfb8886fb69c36
3
  size 18132116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a547a4bfb6e979055ba3b234ae13f752b69af4b853afc07995e1fa8569ed2f0
3
  size 18132116
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49efe4d02f8ecea18dd22b5963355d96fe082e5f38212558a53764a758a95dd5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23e36f109a61d2914b7aeefe6196b94a1d2bbdc07258ecfe18666fedd59e55b5
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": 0.029261155815654718,
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": 68.489,
306
  "eval_steps_per_second": 8.568,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 5721034221158400.0,
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": 0.03218727139722019,
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": 68.489,
306
  "eval_steps_per_second": 8.568,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.03023652767617654,
311
+ "grad_norm": 0.07801888138055801,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 0.4643,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.031211899536698368,
318
+ "grad_norm": 0.09624099731445312,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 0.4155,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.03218727139722019,
325
+ "grad_norm": 0.09031011909246445,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 0.4894,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.03218727139722019,
332
+ "eval_loss": 0.4705558717250824,
333
+ "eval_runtime": 75.4568,
334
+ "eval_samples_per_second": 68.649,
335
+ "eval_steps_per_second": 8.588,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 6293137643274240.0,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null