ClarenceDan commited on
Commit
f3cbd08
·
verified ·
1 Parent(s): 74f4005

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:c859fabd663769c7b10d77d36d57653c22c805cf9f3ef6af5c13efcc0255a2a9
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e72ad3737b751306c853538728fe3aab405f5eb3a791499c090f156d4cbf6b9
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34d6913dd7b48c0ed25fae0b53787ac8aee7453b37f65799d521d39364c064c0
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca458d9fb6936060bec1ac505edab3f43bcba572d7ef8b796399046c8978be02
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:693d65ff7d3abbbb13c7ee57d38fa6e7fa5181ebaaabad321dd22b54929bbad4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04a94b83956618c5f6ad1eb1e148eb701d120c1b0cae59d7acf6b263a4a79491
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": 0.00017190130000358127,
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": 19.757,
74
  "eval_steps_per_second": 9.879,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1899722503618560.0,
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": 0.0002578519500053719,
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": 19.757,
74
  "eval_steps_per_second": 9.879,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00020055151667084482,
79
+ "grad_norm": 0.6188974380493164,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.2789,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00022920173333810837,
86
+ "grad_norm": 0.6034024357795715,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.3266,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0002578519500053719,
93
+ "grad_norm": 0.39841750264167786,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.2998,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0002578519500053719,
100
+ "eval_loss": 0.26757845282554626,
101
+ "eval_runtime": 707.5272,
102
+ "eval_samples_per_second": 20.772,
103
+ "eval_steps_per_second": 10.387,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2849583755427840.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null