mgh6 commited on
Commit
ff77aa0
·
verified ·
1 Parent(s): f052da0

Training in progress, step 13100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:896101a9f207b1b5ed452ee8f81b628ea0fbd1dc25069f79b8fffb726b415945
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aad740b0d4ac443a48611602df1a55075a0e43b896238b31795d1f69b6fd596
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05a0ba1e8c082e801747fd48267334d3d0e5678023038dd779a5e1492afc5102
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4578db958fab1284595fd3116710497aa59c8abee7778d0bc4f491bb29150d4c
3
  size 16386426
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:881a61b7c1a37ee10da1cd65cc2b785743680e7cf44d03b890e6cd41ce1e5827
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db26393319a34f36762ec82fcfe511f4ceffcfe4921b71d3619818de704d808
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4907c0326fbf452e032c18f11cb6410c8efc73c7825b23977ef74e9fa6cbf715
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d051db52358e667cc2cdcec42519df77d4fbf00e1dde3c641f2e9a3b6c00af60
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": 25.99593813466646,
5
  "eval_steps": 500,
6
- "global_step": 13000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1125,6 +1125,13 @@
1125
  "eval_samples_per_second": 19.86,
1126
  "eval_steps_per_second": 2.483,
1127
  "step": 13000
 
 
 
 
 
 
 
1128
  }
1129
  ],
1130
  "logging_steps": 100,
@@ -1144,7 +1151,7 @@
1144
  "attributes": {}
1145
  }
1146
  },
1147
- "total_flos": 2.028951733270479e+19,
1148
  "train_batch_size": 8,
1149
  "trial_name": null,
1150
  "trial_params": null
 
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,
 
1125
  "eval_samples_per_second": 19.86,
1126
  "eval_steps_per_second": 2.483,
1127
  "step": 13000
1128
+ },
1129
+ {
1130
+ "epoch": 26.195906889548507,
1131
+ "grad_norm": 0.2401517629623413,
1132
+ "learning_rate": 1.2666666666666668e-05,
1133
+ "loss": 1.2183,
1134
+ "step": 13100
1135
  }
1136
  ],
1137
  "logging_steps": 100,
 
1151
  "attributes": {}
1152
  }
1153
  },
1154
+ "total_flos": 2.044558314702268e+19,
1155
  "train_batch_size": 8,
1156
  "trial_name": null,
1157
  "trial_params": null