trenden commited on
Commit
936db17
·
verified ·
1 Parent(s): 5cce9bb

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 sha256:8f69244e2f138e82f81f98097aaa7db663e379d9b24ab1d713b773811451b129
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581453d0c7714bd1ff4b751ef1b2fc7d2dbaa1f5bb89ee3a9edef88fd29846fb
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fd886a4cf3b88fddc33a0185a5f34576035f1e814dbd465db1364fd3aa181dc
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d072954c2f9b7c9d0417a2041f10abeb3d6451733c5d7c2ad9b36971438f0c1
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
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": 0.0001279795232762758,
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": 162.251,
74
  "eval_steps_per_second": 81.126,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1417936896.0,
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": 0.00019196928491441368,
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": 162.251,
74
  "eval_steps_per_second": 81.126,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00014930944382232175,
79
+ "grad_norm": 0.01305566169321537,
80
+ "learning_rate": 0.00014,
81
+ "loss": 11.9362,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00017063936436836772,
86
+ "grad_norm": 0.013313014060258865,
87
+ "learning_rate": 0.00016,
88
+ "loss": 11.9296,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00019196928491441368,
93
+ "grad_norm": 0.012543230317533016,
94
+ "learning_rate": 0.00018,
95
+ "loss": 11.9292,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00019196928491441368,
100
+ "eval_loss": 11.931682586669922,
101
+ "eval_runtime": 121.6197,
102
+ "eval_samples_per_second": 162.309,
103
+ "eval_steps_per_second": 81.155,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2126905344.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null