nathanialhunt commited on
Commit
4ed1b53
·
verified ·
1 Parent(s): 1f1edab

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:e01b1332e5d8080c66d9841bb5c7b323e109aca57192d35cb76be29d56513ea5
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30279b9855723727eaebb53c0eccd4f774e87e894a58fc3cba6b85986b44a0f4
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab8a351790dab7c6dd8f30d7c2bbee4b07dfde3aa146973843f1617b9f8ed2ef
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f16b7ddff2aaf4f68398944a8a5605f7dc9153f79843e182b1d381b54d8e5aa4
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e0cecd4fa0b346dabc60917e1b3ca1c91ce878034ad78d001aa7d9a1f75d88e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19394caac0370dc5eb8bb3d271a9b6d245fc10d68ceffd549459fcf4f2e70bc9
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": 0.0002393823934249636,
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": 22.902,
74
  "eval_steps_per_second": 11.451,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1618368717127680.0,
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": 0.0003590735901374454,
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": 22.902,
74
  "eval_steps_per_second": 11.451,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00027927945899579087,
79
+ "grad_norm": 42.0061149597168,
80
+ "learning_rate": 0.00014,
81
+ "loss": 5.6204,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0003191765245666181,
86
+ "grad_norm": 15.68433952331543,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.5446,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0003590735901374454,
93
+ "grad_norm": 8.796845436096191,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.0595,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0003590735901374454,
100
+ "eval_loss": 3.500016927719116,
101
+ "eval_runtime": 460.7356,
102
+ "eval_samples_per_second": 22.907,
103
+ "eval_steps_per_second": 11.453,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2450672628793344.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null