nathanialhunt commited on
Commit
8423d3e
·
verified ·
1 Parent(s): 77b0c6a

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d91c832b67c02aa33888ab224c025cb43af148cb1da4b1553a7c01333d38b303
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0716e8cd0716ed13e89d4d72d43d071a71741c79c2d481e68fc4ba0145fb0c6d
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12281986321ab80d034f0944ddf27c476984a9d8e644a5ded16e898d44391e6b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:324f9767d1629720390dc3d772beba633e02244016b0bce79ea1f9599df7e635
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": 0.00019988340134921296,
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": 42.265,
45
  "eval_steps_per_second": 21.133,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 97289477554176.0,
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": 0.0003997668026984259,
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": 42.265,
45
  "eval_steps_per_second": 21.133,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00026651120179895063,
50
+ "grad_norm": NaN,
51
+ "learning_rate": 8e-05,
52
+ "loss": 0.0,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00033313900224868825,
57
+ "grad_norm": NaN,
58
+ "learning_rate": 0.0001,
59
+ "loss": 0.0,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0003997668026984259,
64
+ "grad_norm": NaN,
65
+ "learning_rate": 0.00012,
66
+ "loss": 0.0,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0003997668026984259,
71
+ "eval_loss": NaN,
72
+ "eval_runtime": 149.8165,
73
+ "eval_samples_per_second": 42.185,
74
+ "eval_steps_per_second": 21.092,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 194578955108352.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null