mamung commited on
Commit
41595b1
·
verified ·
1 Parent(s): 6661c51

Training in progress, step 90, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b76fb774cc29aa4a0237aa01ddb7ea6873e1ef742301d3319a8539c391b298b
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a578e9521a9ab15d4f40115992f62619f58b6d43bb0f7dc335d4b3f47103097
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21bcfadb23132f558cbe3dd6f0525ef44f8fa5ac2d99bb640f93a5f508dc6d97
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:258574fc95c474270a3a1b9fb326a794c444e7bb209be9cd0a9f2c97e9c987c8
3
  size 640009682
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76176b194774cb7a663950593f31d2e41cbb03e09a4aaaaf2425c3c4a43bad6c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e18e668860aa083adef211013189cd3d58c25adbb67cd9b0e99f8ed5231c4495
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09ab64d5ace66796aa9c2fa2fc4e0206d69a1eb4ef03f574f85ee8eb16a64b71
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
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": 0.9546961325966851,
5
  "eval_steps": 9,
6
- "global_step": 81,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -276,6 +276,35 @@
276
  "eval_samples_per_second": 5.919,
277
  "eval_steps_per_second": 2.96,
278
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  }
280
  ],
281
  "logging_steps": 3,
@@ -295,7 +324,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 4.259916615505674e+17,
299
  "train_batch_size": 2,
300
  "trial_name": null,
301
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0626151012891345,
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,
 
276
  "eval_samples_per_second": 5.919,
277
  "eval_steps_per_second": 2.96,
278
  "step": 81
279
+ },
280
+ {
281
+ "epoch": 0.9900552486187846,
282
+ "grad_norm": 28.34723663330078,
283
+ "learning_rate": 1.4323725421878949e-05,
284
+ "loss": 46.7876,
285
+ "step": 84
286
+ },
287
+ {
288
+ "epoch": 1.027255985267035,
289
+ "grad_norm": 29.410560607910156,
290
+ "learning_rate": 9.56279946954021e-06,
291
+ "loss": 46.1371,
292
+ "step": 87
293
+ },
294
+ {
295
+ "epoch": 1.0626151012891345,
296
+ "grad_norm": 32.85994338989258,
297
+ "learning_rate": 5.709035061653494e-06,
298
+ "loss": 43.1931,
299
+ "step": 90
300
+ },
301
+ {
302
+ "epoch": 1.0626151012891345,
303
+ "eval_loss": 1.5428903102874756,
304
+ "eval_runtime": 48.3008,
305
+ "eval_samples_per_second": 5.921,
306
+ "eval_steps_per_second": 2.961,
307
+ "step": 90
308
  }
309
  ],
310
  "logging_steps": 3,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 4.7332406838951936e+17,
328
  "train_batch_size": 2,
329
  "trial_name": null,
330
  "trial_params": null