Nexspear commited on
Commit
98ed307
·
verified ·
1 Parent(s): f6cc4fb

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc937a1fc85958c6a997fdbdbf7de3050f825a89ef7c14c870ba1c4ae7532ccd
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce98d5b4621320be106265c55112c858be581234b6c2ab6151b2ae749c9499d8
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29c6bdb43ac72b0b905c87d30308aff04b7788968f0ebd332867857d93cbaaa4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:172079d42ba1938585b69ed20e221c056ff117472b1f9f5764453326aaf30c78
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
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": 0.08379888268156424,
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,
@@ -74,6 +74,21 @@
74
  "eval_samples_per_second": 36.746,
75
  "eval_steps_per_second": 4.624,
76
  "step": 15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
  }
78
  ],
79
  "logging_steps": 3,
@@ -93,7 +108,7 @@
93
  "attributes": {}
94
  }
95
  },
96
- "total_flos": 4082170960281600.0,
97
  "train_batch_size": 8,
98
  "trial_name": null,
99
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.11173184357541899,
5
  "eval_steps": 5,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
74
  "eval_samples_per_second": 36.746,
75
  "eval_steps_per_second": 4.624,
76
  "step": 15
77
+ },
78
+ {
79
+ "epoch": 0.1005586592178771,
80
+ "grad_norm": NaN,
81
+ "learning_rate": 9.045084971874738e-05,
82
+ "loss": 0.0,
83
+ "step": 18
84
+ },
85
+ {
86
+ "epoch": 0.11173184357541899,
87
+ "eval_loss": NaN,
88
+ "eval_runtime": 8.2114,
89
+ "eval_samples_per_second": 36.778,
90
+ "eval_steps_per_second": 4.628,
91
+ "step": 20
92
  }
93
  ],
94
  "logging_steps": 3,
 
108
  "attributes": {}
109
  }
110
  },
111
+ "total_flos": 5442894613708800.0,
112
  "train_batch_size": 8,
113
  "trial_name": null,
114
  "trial_params": null