Nexspear commited on
Commit
f6cc4fb
·
verified ·
1 Parent(s): a6c51fe

Training in progress, step 15, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16e9353f754dc20cf77ef7626d29c2c848a1e0d3596071fa01d0d59ff344ff74
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc937a1fc85958c6a997fdbdbf7de3050f825a89ef7c14c870ba1c4ae7532ccd
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bbce49a637c64091bf19abfd402b75bee59db4098db4ce7e395e345424f398f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29c6bdb43ac72b0b905c87d30308aff04b7788968f0ebd332867857d93cbaaa4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
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": 0.055865921787709494,
5
  "eval_steps": 5,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,28 @@
52
  "eval_samples_per_second": 36.817,
53
  "eval_steps_per_second": 4.633,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -71,7 +93,7 @@
71
  "attributes": {}
72
  }
73
  },
74
- "total_flos": 2721447306854400.0,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.08379888268156424,
5
  "eval_steps": 5,
6
+ "global_step": 15,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 36.817,
53
  "eval_steps_per_second": 4.633,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.0670391061452514,
58
+ "grad_norm": NaN,
59
+ "learning_rate": 9.938441702975689e-05,
60
+ "loss": 0.0,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.08379888268156424,
65
+ "grad_norm": NaN,
66
+ "learning_rate": 9.619397662556435e-05,
67
+ "loss": 0.0,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.08379888268156424,
72
+ "eval_loss": NaN,
73
+ "eval_runtime": 8.2185,
74
+ "eval_samples_per_second": 36.746,
75
+ "eval_steps_per_second": 4.624,
76
+ "step": 15
77
  }
78
  ],
79
  "logging_steps": 3,
 
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 4082170960281600.0,
97
  "train_batch_size": 8,
98
  "trial_name": null,
99
  "trial_params": null