ClarenceDan commited on
Commit
75b96e3
·
verified ·
1 Parent(s): 69ec43e

Training in progress, step 9, 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:f6d625ecbdfc73162aa0358a6088fcf1f1bdc6a2d09ca88ba47d8141df05dc16
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b0957c42b5e91eaf48618693b8e78a05b3aafe8a4a45f57538ab31381bc8c96
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ec5a820645c67fd2331ebfde95ca895a16f560fea91b3d6b90a59aadeea8c1f
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d89b674089f171924f5c904875f9e12fc6717f58487d1d3c4f1002f53f3d0205
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22cc4a9a02a6f74d668e9df70ad462220b16b60af37292d30446f2a841cfc377
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27917d88cdf4e1cd610266e1bad5287f7c270415c57a7781c0adaab154ebaaf5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.001536688436419516,
5
  "eval_steps": 3,
6
- "global_step": 6,
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": 34.549,
74
  "eval_steps_per_second": 17.285,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1045581627654144.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.002305032654629274,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 34.549,
74
  "eval_steps_per_second": 17.285,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0017928031758227686,
79
+ "grad_norm": 1.1740851402282715,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.2937,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.002048917915226021,
86
+ "grad_norm": 1.0491771697998047,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.0755,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.002305032654629274,
93
+ "grad_norm": 1.6079107522964478,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.2777,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.002305032654629274,
100
+ "eval_loss": 2.277167320251465,
101
+ "eval_runtime": 47.6089,
102
+ "eval_samples_per_second": 34.552,
103
+ "eval_steps_per_second": 17.287,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1568372441481216.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null