masatochi commited on
Commit
1820dfe
·
verified ·
1 Parent(s): 0d91873

Training in progress, step 155, 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:fdf06c73a29db95b30af71f32f75105517a4737848ffa49b85054e4a1b34fb46
3
  size 59827904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e0c02c24de6a03a12b8c9f710ace5b439b9e0c8a3fdfabd3d5e67270771ddb
3
  size 59827904
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a176e7b51a3d2133cfe78f61443687ade87aca5b0f3bf2e5c8cca086fd2cb58
3
  size 30875540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a39317199ad1ecdf24b93cbe0a069447e0e9f655f78a472e0efad741ef0eb11e
3
  size 30875540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85dcff485150847800368b832b7fbbde9bcca50c94c2ff19cbbdf38672b04cb0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe14dee36a73635fccad5a14a292e5eba895c9869df06a43c1764c5dffef85e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a946cb282348d3fba8c242cd51f3b90b3dccbd24720ee6b6397a7e493e7b92c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382ece00c385c691790a218c7659825f5fdd28b4e63aa1032e7b069dd2944457
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": 0.07335411699981662,
5
  "eval_steps": 34,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1097,6 +1097,41 @@
1097
  "learning_rate": 3.973653636207437e-05,
1098
  "loss": 8.8614,
1099
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1100
  }
1101
  ],
1102
  "logging_steps": 1,
@@ -1116,7 +1151,7 @@
1116
  "attributes": {}
1117
  }
1118
  },
1119
- "total_flos": 3.306719513935872e+17,
1120
  "train_batch_size": 3,
1121
  "trial_name": null,
1122
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.07579925423314383,
5
  "eval_steps": 34,
6
+ "global_step": 155,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1097
  "learning_rate": 3.973653636207437e-05,
1098
  "loss": 8.8614,
1099
  "step": 150
1100
+ },
1101
+ {
1102
+ "epoch": 0.07384314444648206,
1103
+ "grad_norm": Infinity,
1104
+ "learning_rate": 3.8272177871020723e-05,
1105
+ "loss": 9.0426,
1106
+ "step": 151
1107
+ },
1108
+ {
1109
+ "epoch": 0.0743321718931475,
1110
+ "grad_norm": Infinity,
1111
+ "learning_rate": 3.682889937467493e-05,
1112
+ "loss": 8.5715,
1113
+ "step": 152
1114
+ },
1115
+ {
1116
+ "epoch": 0.07482119933981295,
1117
+ "grad_norm": Infinity,
1118
+ "learning_rate": 3.540719375132129e-05,
1119
+ "loss": 9.3144,
1120
+ "step": 153
1121
+ },
1122
+ {
1123
+ "epoch": 0.07531022678647839,
1124
+ "grad_norm": Infinity,
1125
+ "learning_rate": 3.400754651212776e-05,
1126
+ "loss": 8.7214,
1127
+ "step": 154
1128
+ },
1129
+ {
1130
+ "epoch": 0.07579925423314383,
1131
+ "grad_norm": Infinity,
1132
+ "learning_rate": 3.263043563534428e-05,
1133
+ "loss": 8.8783,
1134
+ "step": 155
1135
  }
1136
  ],
1137
  "logging_steps": 1,
 
1151
  "attributes": {}
1152
  }
1153
  },
1154
+ "total_flos": 3.4169434977337344e+17,
1155
  "train_batch_size": 3,
1156
  "trial_name": null,
1157
  "trial_params": null