Nexspear commited on
Commit
a198676
·
verified ·
1 Parent(s): 98ed307

Training in progress, step 25, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce98d5b4621320be106265c55112c858be581234b6c2ab6151b2ae749c9499d8
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46f1c4b3f3e865acb10f07ea3213d8b2d2b7afbf288f443165a2b62a5fb00d46
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:172079d42ba1938585b69ed20e221c056ff117472b1f9f5764453326aaf30c78
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67124e1bb49f0d1ecfd196b6845c01ded38adeb7a043cc29e559851d658d090a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
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": 0.11173184357541899,
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,
@@ -89,6 +89,28 @@
89
  "eval_samples_per_second": 36.778,
90
  "eval_steps_per_second": 4.628,
91
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92
  }
93
  ],
94
  "logging_steps": 3,
@@ -108,7 +130,7 @@
108
  "attributes": {}
109
  }
110
  },
111
- "total_flos": 5442894613708800.0,
112
  "train_batch_size": 8,
113
  "trial_name": null,
114
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.13966480446927373,
5
  "eval_steps": 5,
6
+ "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
89
  "eval_samples_per_second": 36.778,
90
  "eval_steps_per_second": 4.628,
91
  "step": 20
92
+ },
93
+ {
94
+ "epoch": 0.11731843575418995,
95
+ "grad_norm": NaN,
96
+ "learning_rate": 8.247240241650918e-05,
97
+ "loss": 0.0,
98
+ "step": 21
99
+ },
100
+ {
101
+ "epoch": 0.1340782122905028,
102
+ "grad_norm": NaN,
103
+ "learning_rate": 7.269952498697734e-05,
104
+ "loss": 0.0,
105
+ "step": 24
106
+ },
107
+ {
108
+ "epoch": 0.13966480446927373,
109
+ "eval_loss": NaN,
110
+ "eval_runtime": 8.2183,
111
+ "eval_samples_per_second": 36.747,
112
+ "eval_steps_per_second": 4.624,
113
+ "step": 25
114
  }
115
  ],
116
  "logging_steps": 3,
 
130
  "attributes": {}
131
  }
132
  },
133
+ "total_flos": 6803618267136000.0,
134
  "train_batch_size": 8,
135
  "trial_name": null,
136
  "trial_params": null