nathanialhunt commited on
Commit
5153352
·
verified ·
1 Parent(s): f0b88cc

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 sha256:2a9724da798d93aca41571752974ece97ce653fdf94ee113c089f9565f2cc786
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3065e48e1ab061f3b176939412facb1ed020192052ed77f6af70077103f4a911
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc986c9caeb0c517ddfe515ca0ec0fab07bff05a17cff5e8fe2cc921517761e7
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6162777c67373f0d63689304735df601548fb99b05190e9eaf75e22b82aae15
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200897803867d9476163ce84baa477ea4bfc2d20fbca1d606afa2d969206fa8c
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": 0.00014203872922683586,
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": 35.76,
74
  "eval_steps_per_second": 17.881,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 977239881547776.0,
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": 0.00021305809384025378,
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": 35.76,
74
  "eval_steps_per_second": 17.881,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0001657118507646418,
79
+ "grad_norm": 1.8866004943847656,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.7562,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0001893849723024478,
86
+ "grad_norm": 2.3774871826171875,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.8133,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00021305809384025378,
93
+ "grad_norm": 2.0534048080444336,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.1913,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00021305809384025378,
100
+ "eval_loss": 1.3677295446395874,
101
+ "eval_runtime": 496.8183,
102
+ "eval_samples_per_second": 35.802,
103
+ "eval_steps_per_second": 17.902,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1465859822321664.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null