leixa commited on
Commit
cae8ed9
·
verified ·
1 Parent(s): 3106a24

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:ef76c0c202b1a1c3a6f77cf15e3708521009eebcae6684592011f2cd0eab4515
3
  size 75471860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21180b175c986c194dccc0fc7d1ca497d83bef1ad2b6df9e7f95855268717a8e
3
  size 75471860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecba24a2e9d82f9a8477398ba47d19289c176eac2160a25b25f398204068b1ca
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e655424d5066c15ba7f297c7618f3e195dee922b0815462cf032c10168c30577
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": 0.03187250996015936,
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": 34.989,
53
  "eval_steps_per_second": 8.846,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -71,7 +93,7 @@
71
  "attributes": {}
72
  }
73
  },
74
- "total_flos": 1324420442357760.0,
75
  "train_batch_size": 4,
76
  "trial_name": null,
77
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.04780876494023904,
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": 34.989,
53
  "eval_steps_per_second": 8.846,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.03824701195219123,
58
+ "grad_norm": NaN,
59
+ "learning_rate": 9.938441702975689e-05,
60
+ "loss": 0.0,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.04780876494023904,
65
+ "grad_norm": NaN,
66
+ "learning_rate": 9.619397662556435e-05,
67
+ "loss": 0.0,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.04780876494023904,
72
+ "eval_loss": NaN,
73
+ "eval_runtime": 7.5825,
74
+ "eval_samples_per_second": 34.949,
75
+ "eval_steps_per_second": 8.836,
76
+ "step": 15
77
  }
78
  ],
79
  "logging_steps": 3,
 
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 1986630663536640.0,
97
  "train_batch_size": 4,
98
  "trial_name": null,
99
  "trial_params": null