mgh6 commited on
Commit
0b972e5
·
verified ·
1 Parent(s): ba1dfaf

Training in progress, step 13200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aad740b0d4ac443a48611602df1a55075a0e43b896238b31795d1f69b6fd596
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:012a70f33e1a815ca9cef727ea360c37221cbcda94b30c8371268b1903722f7b
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4578db958fab1284595fd3116710497aa59c8abee7778d0bc4f491bb29150d4c
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37506ea8f3049c8ea63365eff7e39eb851b4705a555b73935cb410fbfe126fc0
3
  size 16386426
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4db26393319a34f36762ec82fcfe511f4ceffcfe4921b71d3619818de704d808
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09aa940668d627b8b8ab12bc71f02e2ad1cf762162015baaaed8020f78d3d761
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d051db52358e667cc2cdcec42519df77d4fbf00e1dde3c641f2e9a3b6c00af60
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8aa61b4986db927228fdf2199acde4bbf7e216cd77e925cf6bfd01950746b88
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": 26.195906889548507,
5
  "eval_steps": 500,
6
- "global_step": 13100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1132,6 +1132,13 @@
1132
  "learning_rate": 1.2666666666666668e-05,
1133
  "loss": 1.2183,
1134
  "step": 13100
 
 
 
 
 
 
 
1135
  }
1136
  ],
1137
  "logging_steps": 100,
@@ -1151,7 +1158,7 @@
1151
  "attributes": {}
1152
  }
1153
  },
1154
- "total_flos": 2.044558314702268e+19,
1155
  "train_batch_size": 8,
1156
  "trial_name": null,
1157
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 26.395875644430557,
5
  "eval_steps": 500,
6
+ "global_step": 13200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1132
  "learning_rate": 1.2666666666666668e-05,
1133
  "loss": 1.2183,
1134
  "step": 13100
1135
+ },
1136
+ {
1137
+ "epoch": 26.395875644430557,
1138
+ "grad_norm": 0.2405146360397339,
1139
+ "learning_rate": 1.2e-05,
1140
+ "loss": 1.2179,
1141
+ "step": 13200
1142
  }
1143
  ],
1144
  "logging_steps": 100,
 
1158
  "attributes": {}
1159
  }
1160
  },
1161
+ "total_flos": 2.0601658118210847e+19,
1162
  "train_batch_size": 8,
1163
  "trial_name": null,
1164
  "trial_params": null