oldiday commited on
Commit
a7dc203
·
verified ·
1 Parent(s): 0126b9b

Training in progress, step 27, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f8e71cb0b4e028a4e112523f585739bf62ffce3e86e782b6eb22f2722615be1
3
  size 34793120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9acb7ab00f4d82234b1082eb6729c8d40ba40ea72e0c2c75225b37b3f09b8bff
3
  size 34793120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:039ea8c8140fe1da1a5fa2c400b61dc8e6f08f47b68aeb69247685ef1a89ccaf
3
  size 18132116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fdcbab62b17dc3ca6967bd656ae0a2c88c143024a79d747c4227ddbe4ebbe60
3
  size 18132116
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72e3379b97382001bdd566ec44641d53d705aadf1c63d214e37febd171c0679c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac6758c94dff08e90104766708e33ff8cbf1018bfc9134136ef3e1f7d88a92f7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
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": 0.4444444444444444,
5
  "eval_steps": 9,
6
- "global_step": 18,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 68.568,
74
  "eval_steps_per_second": 8.944,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1144206844231680.0,
96
  "train_batch_size": 8,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.6666666666666666,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 68.568,
74
  "eval_steps_per_second": 8.944,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.5185185185185185,
79
+ "grad_norm": 0.2104165405035019,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 2.2173,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.5925925925925926,
86
+ "grad_norm": 0.1979183554649353,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 2.1982,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.6666666666666666,
93
+ "grad_norm": 0.23016861081123352,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 2.2124,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.6666666666666666,
100
+ "eval_loss": 2.072659730911255,
101
+ "eval_runtime": 1.0059,
102
+ "eval_samples_per_second": 68.595,
103
+ "eval_steps_per_second": 8.947,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1716310266347520.0,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null