mgh6 commited on
Commit
48dcbcf
·
verified ·
1 Parent(s): 057a1c4

Training in progress, step 12300, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c951252bb0ceff63af1472253f0f51296efbc10a2a34cafc9ce737d5604b25e
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29956a42858cc1a71f6dee08eba9d6e063dd6c0c7c16732af2ead7faaa6180fd
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bec49532d0c9469d6aa8180783edb97c47ab00b3efc388784187682576fe73c
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b071d214a59097a7835acd1070421e3cc4395f35771d49f259461dfbfd7da5c
3
  size 16386426
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:782e6fccb7e358f57c281fa2552111132f0efcd2a1f29720ae037c0f86ade2ca
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dfb58711cfeb2781bd70eb8fee55449848e381fcf989517924a67b3347d62ca
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:670890a7ca0ec632da074caaf14a94a802df653090a9d0d3499e4281fd5e1a9f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:307cb858f017d4acb2a340daefe90cd63c5a85459a0131a558c685415867466b
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": 24.39618809561006,
5
  "eval_steps": 500,
6
- "global_step": 12200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1053,6 +1053,13 @@
1053
  "learning_rate": 1.866666666666667e-05,
1054
  "loss": 1.2256,
1055
  "step": 12200
 
 
 
 
 
 
 
1056
  }
1057
  ],
1058
  "logging_steps": 100,
@@ -1072,7 +1079,7 @@
1072
  "attributes": {}
1073
  }
1074
  },
1075
- "total_flos": 1.904092672006973e+19,
1076
  "train_batch_size": 8,
1077
  "trial_name": null,
1078
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 24.59615685049211,
5
  "eval_steps": 500,
6
+ "global_step": 12300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1053
  "learning_rate": 1.866666666666667e-05,
1054
  "loss": 1.2256,
1055
  "step": 12200
1056
+ },
1057
+ {
1058
+ "epoch": 24.59615685049211,
1059
+ "grad_norm": 0.24531888961791992,
1060
+ "learning_rate": 1.8e-05,
1061
+ "loss": 1.2227,
1062
+ "step": 12300
1063
  }
1064
  ],
1065
  "logging_steps": 100,
 
1079
  "attributes": {}
1080
  }
1081
  },
1082
+ "total_flos": 1.9197001691257897e+19,
1083
  "train_batch_size": 8,
1084
  "trial_name": null,
1085
  "trial_params": null