dimasik87 commited on
Commit
bf2a4a0
1 Parent(s): 7905a5f

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc9a0e2e05d9eacf5c069bd04337e5de4a41461f12fee894e25c6f74e61bcfb7
3
  size 37965300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8cdd28be9549af1d5bae665c6e126d72e4da1f2ba57ad65c7b14a6a4a333524
3
  size 37965300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ed49960a833676099cf29fdca6526f3debc2e310059eef2989451582737ccd9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd8092cdfbfd897657a212ef05281e36849efab7a429226d1bb688f3c53fef7b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.00025674215599225494,
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,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 22.188,
74
  "eval_steps_per_second": 11.094,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 816418023014400.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0003851132339883824,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 22.188,
74
  "eval_steps_per_second": 11.094,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0002995325153242974,
79
+ "grad_norm": NaN,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.0,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0003423228746563399,
86
+ "grad_norm": NaN,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.0,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0003851132339883824,
93
+ "grad_norm": NaN,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.0,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0003851132339883824,
100
+ "eval_loss": NaN,
101
+ "eval_runtime": 443.6013,
102
+ "eval_samples_per_second": 22.182,
103
+ "eval_steps_per_second": 11.091,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1208298674061312.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null