nathanialhunt commited on
Commit
e6f9b05
·
verified ·
1 Parent(s): ffdcf8f

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 sha256:14ea9eace0983b8ab7ab37ac3ee148b5f22c268a9bef96e70e48684558eb681b
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e10ff7d14d260b8c35d20aa94f3fa4dae034412ca9fcf0807739efa544c434ff
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:429bc256558d0d0ff4fdd23b31696725692981cc7432c370d38da6c8fe99a378
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be314395c111e9bfd88d03872ab61e74f664051bf428251f5db39ea3b7518ff5
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01fc1ce580e28a619d9332a6abc08d276d77522f73350afe3c772a2760eb6750
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef85f51d139fa88c501e9c10d2687be0cda0b477cc0a0033709ee647d8e59c50
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": 0.0036877688998156115,
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": 22.226,
74
  "eval_steps_per_second": 11.129,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1803325141942272.0,
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": 0.005531653349723417,
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": 22.226,
74
  "eval_steps_per_second": 11.129,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0043023970497848806,
79
+ "grad_norm": 0.620731770992279,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.7876,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.004917025199754148,
86
+ "grad_norm": 0.5794855952262878,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.1375,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.005531653349723417,
93
+ "grad_norm": 0.6219256520271301,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.6744,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.005531653349723417,
100
+ "eval_loss": 1.357763409614563,
101
+ "eval_runtime": 30.8167,
102
+ "eval_samples_per_second": 22.228,
103
+ "eval_steps_per_second": 11.13,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2589389947404288.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null