mgh6 commited on
Commit
5a7002d
·
verified ·
1 Parent(s): 5ede86c

Training in progress, step 12100, 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:f395e496621b7032d1b0d7a06fe55747a519694eb3cbf9921f55e1ae957a919d
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4457134b4d9937feb46ea312a4bbb513b4f194afb1aae9468a6be57efe4c4a1
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ad76905f926c95599cf7f4e28e6d0206d7af8f1ade288c2c73f1ca0232a6d40
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e502ff03c77eb1bc2b5c8daa072c4f2203147bae71972a224d39cff1f968a292
3
  size 16386426
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e242f2818e9dde5ec7a4736f1896a4fb18f6d870fac4f0630bc5afddcb4a29c
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:953c2349850a1156376a72e65b43bc81a521c757d40aa3f4ed2daacfcd8f9e42
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:997376d97a66d723eb71715005de65897518b02a368a9b5bed65c4567e1a22ab
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806607edd5ab768213aa4d7fc24e6f9b128a183c1f3b52cd9f2da4180b15eef5
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": 23.99625058584596,
5
  "eval_steps": 500,
6
- "global_step": 12000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1039,6 +1039,13 @@
1039
  "eval_samples_per_second": 19.867,
1040
  "eval_steps_per_second": 2.484,
1041
  "step": 12000
 
 
 
 
 
 
 
1042
  }
1043
  ],
1044
  "logging_steps": 100,
@@ -1058,7 +1065,7 @@
1058
  "attributes": {}
1059
  }
1060
  },
1061
- "total_flos": 1.8728785934563672e+19,
1062
  "train_batch_size": 8,
1063
  "trial_name": null,
1064
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 24.19621934072801,
5
  "eval_steps": 500,
6
+ "global_step": 12100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1039
  "eval_samples_per_second": 19.867,
1040
  "eval_steps_per_second": 2.484,
1041
  "step": 12000
1042
+ },
1043
+ {
1044
+ "epoch": 24.19621934072801,
1045
+ "grad_norm": 0.24265432357788086,
1046
+ "learning_rate": 1.9333333333333333e-05,
1047
+ "loss": 1.22,
1048
+ "step": 12100
1049
  }
1050
  ],
1051
  "logging_steps": 100,
 
1065
  "attributes": {}
1066
  }
1067
  },
1068
+ "total_flos": 1.8884851748881564e+19,
1069
  "train_batch_size": 8,
1070
  "trial_name": null,
1071
  "trial_params": null