mgh6 commited on
Commit
a5af481
·
verified ·
1 Parent(s): 8907f6a

Training in progress, step 12800, 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:f8de8c58363428e5a212a3a4cb4c6e603534a59706d0acc7f509add46757e4be
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eef73c69b3dd186665de136812efd45ffc9904539c9291bba8493a22bbd41d1a
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:515bb5c714672e38dd8b8f2e243f50d8e6fb7e87d6fe8dbfeb450dc14c73ca07
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6366f5a0c014c1827828cfce7aa3b4cb5bfa0e120b18e9f63c0f21806b36978d
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:f50ceb3ca0a6b0975d6fb26400fddb6871bf4da32dbc560fb730d74806ffd679
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81ebffd179ceda7eed553eac1fdd07228c6db95322b3b555365f66f32848d865
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22a27c7ac8f887563d6b56d8cc814c0cb0fec885d54e460f34cdda123e9bcbe4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bab8dbda1e2c946f684f07eae7f2e7f8e87b40ea01e1e711acb314d5eab1ceb4
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": 25.39603187002031,
5
  "eval_steps": 500,
6
- "global_step": 12700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1096,6 +1096,13 @@
1096
  "learning_rate": 1.5333333333333334e-05,
1097
  "loss": 1.2228,
1098
  "step": 12700
 
 
 
 
 
 
 
1099
  }
1100
  ],
1101
  "logging_steps": 100,
@@ -1115,7 +1122,7 @@
1115
  "attributes": {}
1116
  }
1117
  },
1118
- "total_flos": 1.982129241914029e+19,
1119
  "train_batch_size": 8,
1120
  "trial_name": null,
1121
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 25.59600062490236,
5
  "eval_steps": 500,
6
+ "global_step": 12800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1096
  "learning_rate": 1.5333333333333334e-05,
1097
  "loss": 1.2228,
1098
  "step": 12700
1099
+ },
1100
+ {
1101
+ "epoch": 25.59600062490236,
1102
+ "grad_norm": 0.23447927832603455,
1103
+ "learning_rate": 1.4666666666666668e-05,
1104
+ "loss": 1.2125,
1105
+ "step": 12800
1106
  }
1107
  ],
1108
  "logging_steps": 100,
 
1122
  "attributes": {}
1123
  }
1124
  },
1125
+ "total_flos": 1.9977367390328455e+19,
1126
  "train_batch_size": 8,
1127
  "trial_name": null,
1128
  "trial_params": null