trenden commited on
Commit
3d54a93
·
verified ·
1 Parent(s): b7c3c0d

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0258a63205f165cc874e8c0226598b2abe880ae23c157cb2260bd140f42cac94
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f55a4b02ab67dce2ec1d96fd140047d53a2b2b145ca73ec077012b649344503
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ece5201338cda329c443c6eebeab353e0921a18d905638fcb3c04125e335875d
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b85539985f60d7395abfea3fd8d3a43aadf6de01a0a7d82cf1b161c0d5639a
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fb30b6a17397ab556b9362f1ff7fe2b3e008138cfb4d321261e8c4141f37722
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79fef229ddf80177f84717213c08caa8a37a43e854c261a1754ce4f6b16c6c60
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.000128068303094984,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 55.31,
45
  "eval_steps_per_second": 27.655,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 134290788581376.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.000256136606189968,
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,
 
44
  "eval_samples_per_second": 55.31,
45
  "eval_steps_per_second": 27.655,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00017075773745997867,
50
+ "grad_norm": 0.1268327683210373,
51
+ "learning_rate": 8e-05,
52
+ "loss": 0.3947,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00021344717182497332,
57
+ "grad_norm": 0.11968627572059631,
58
+ "learning_rate": 0.0001,
59
+ "loss": 0.2831,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.000256136606189968,
64
+ "grad_norm": 0.11458567529916763,
65
+ "learning_rate": 0.00012,
66
+ "loss": 0.2773,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.000256136606189968,
71
+ "eval_loss": 0.41927647590637207,
72
+ "eval_runtime": 178.1556,
73
+ "eval_samples_per_second": 55.367,
74
+ "eval_steps_per_second": 27.684,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 255791978250240.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null