mgh6 commited on
Commit
8debf56
·
verified ·
1 Parent(s): c3aa187

Training in progress, step 14400, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28c680932b856ac166026393a3414db8c0928af36266ce7cb9459e248ece2e09
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab847f293d901e18f59ee8fec07dc000abba2d22f95cbf0bf15df0a916d97617
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:049bce8f8a8226c8b5b903d4d7b700f75631c2f018ed9195888d8e9d17dbb32a
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:215a6c0ee1959250b4fa2d9ad79b3685c96f2b2b73c498860a566639744e23af
3
  size 16386426
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:885556b3e2d2fc32d8d308db2466bd1f7d5dd0c2f3957e5e294c56f03ae582ca
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79525b0d0f77b4c1862057ee58aeaface0e4d87b7ecf0b47fbb0235d2622fbf0
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9462e9a24b66c0869364ad189ed3068b8a926ce6102960a857f4addcbd1a949
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7eb1beb4875c5534439b1be640b3820b06ebcb3f3235b9bec4577da1ee21f21
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": 28.595531948133104,
5
  "eval_steps": 500,
6
- "global_step": 14300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1232,6 +1232,13 @@
1232
  "learning_rate": 4.666666666666667e-06,
1233
  "loss": 1.2149,
1234
  "step": 14300
 
 
 
 
 
 
 
1235
  }
1236
  ],
1237
  "logging_steps": 100,
@@ -1251,7 +1258,7 @@
1251
  "attributes": {}
1252
  }
1253
  },
1254
- "total_flos": 2.231846448754013e+19,
1255
  "train_batch_size": 8,
1256
  "trial_name": null,
1257
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 28.795500703015154,
5
  "eval_steps": 500,
6
+ "global_step": 14400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1232
  "learning_rate": 4.666666666666667e-06,
1233
  "loss": 1.2149,
1234
  "step": 14300
1235
+ },
1236
+ {
1237
+ "epoch": 28.795500703015154,
1238
+ "grad_norm": 0.25057491660118103,
1239
+ "learning_rate": 4.000000000000001e-06,
1240
+ "loss": 1.2207,
1241
+ "step": 14400
1242
  }
1243
  ],
1244
  "logging_steps": 100,
 
1258
  "attributes": {}
1259
  }
1260
  },
1261
+ "total_flos": 2.2474539458728296e+19,
1262
  "train_batch_size": 8,
1263
  "trial_name": null,
1264
  "trial_params": null