mgh6 commited on
Commit
5d2affe
·
verified ·
1 Parent(s): 27fdc80

Training in progress, step 12900, 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:eef73c69b3dd186665de136812efd45ffc9904539c9291bba8493a22bbd41d1a
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c0f46b0150dcb405d02f4108cf24c0448fc13678cf067a27f224d48daab308b
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6366f5a0c014c1827828cfce7aa3b4cb5bfa0e120b18e9f63c0f21806b36978d
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f7b83437c4e865419b73b6244f99977bffdc6e901b91e047baf7b00421c047
3
  size 16386426
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81ebffd179ceda7eed553eac1fdd07228c6db95322b3b555365f66f32848d865
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:359692d26849aeab1c31342164862fa93d2d0d531719b4bd1ddb343cbd8a6087
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bab8dbda1e2c946f684f07eae7f2e7f8e87b40ea01e1e711acb314d5eab1ceb4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f06a8367c7a4e48436e0ecbe054a4fd11986bfb73d4af57a7bc74afdb308e0c
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": 25.59600062490236,
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,
@@ -1103,6 +1103,13 @@
1103
  "learning_rate": 1.4666666666666668e-05,
1104
  "loss": 1.2125,
1105
  "step": 12800
 
 
 
 
 
 
 
1106
  }
1107
  ],
1108
  "logging_steps": 100,
@@ -1122,7 +1129,7 @@
1122
  "attributes": {}
1123
  }
1124
  },
1125
- "total_flos": 1.9977367390328455e+19,
1126
  "train_batch_size": 8,
1127
  "trial_name": null,
1128
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 25.79596937978441,
5
  "eval_steps": 500,
6
+ "global_step": 12900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1103
  "learning_rate": 1.4666666666666668e-05,
1104
  "loss": 1.2125,
1105
  "step": 12800
1106
+ },
1107
+ {
1108
+ "epoch": 25.79596937978441,
1109
+ "grad_norm": 0.23669584095478058,
1110
+ "learning_rate": 1.4000000000000001e-05,
1111
+ "loss": 1.2223,
1112
+ "step": 12900
1113
  }
1114
  ],
1115
  "logging_steps": 100,
 
1129
  "attributes": {}
1130
  }
1131
  },
1132
+ "total_flos": 2.013344236151662e+19,
1133
  "train_batch_size": 8,
1134
  "trial_name": null,
1135
  "trial_params": null