leixa commited on
Commit
a5a4df7
·
verified ·
1 Parent(s): 90b7fe3

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:e3cd50213d58781172ab45a966c225c15475c6da900dc1f0cf934b4537db3df0
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20de2b7d835e11bb86c08626b75d8872d30ab49f4c9ca3ce227f612664406a66
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40bfb7a2bb9e09979ca0850fe7db152528103f342b31a7d7161ea872baf3db7f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a6f01aaa698ced40d6ab2ae0417d9b5ea9355a115b25f195f6d0b0cc18349ed
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": 0.028469750889679714,
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": 12.315,
53
  "eval_steps_per_second": 1.539,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -71,7 +93,7 @@
71
  "attributes": {}
72
  }
73
  },
74
- "total_flos": 1.7773608566784e+16,
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": 0.042704626334519574,
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": 12.315,
53
  "eval_steps_per_second": 1.539,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.03416370106761566,
58
+ "grad_norm": NaN,
59
+ "learning_rate": 9.938441702975689e-05,
60
+ "loss": 0.0,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.042704626334519574,
65
+ "grad_norm": NaN,
66
+ "learning_rate": 9.619397662556435e-05,
67
+ "loss": 0.0,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.042704626334519574,
72
+ "eval_loss": NaN,
73
+ "eval_runtime": 48.0649,
74
+ "eval_samples_per_second": 12.317,
75
+ "eval_steps_per_second": 1.54,
76
+ "step": 15
77
  }
78
  ],
79
  "logging_steps": 3,
 
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 2.737135719284736e+16,
97
  "train_batch_size": 8,
98
  "trial_name": null,
99
  "trial_params": null