sergioalves commited on
Commit
111865b
·
verified ·
1 Parent(s): 1e2f349

Training in progress, step 30, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a87d93160841f3ca161a25e0a81f69b0a48553729a0db355b0fd20c590ea97cd
3
  size 335810490
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:024df5f011d4d1bef6b5948cd3581381cc4fb3f343b2001508345b11d3156174
3
  size 335810490
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:241920909455841b12c88c41a3e9b3a02a138ad47ca175a12b49447b059cf563
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d131f7f2d468a1c65b0f7265070df89465d3239a1e2b284a5f556398c803ad9b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
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": 0.0005578333751708364,
5
  "eval_steps": 8,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,42 @@
73
  "learning_rate": 6.545084971874738e-05,
74
  "loss": 0.0,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -87,12 +123,12 @@
87
  "should_evaluate": false,
88
  "should_log": false,
89
  "should_save": true,
90
- "should_training_stop": false
91
  },
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 9668030606868480.0,
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": 0.0008367500627562547,
5
  "eval_steps": 8,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "learning_rate": 6.545084971874738e-05,
74
  "loss": 0.0,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.0005857250439293783,
79
+ "grad_norm": NaN,
80
+ "learning_rate": 4.2178276747988446e-05,
81
+ "loss": 0.0,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.0006694000502050038,
86
+ "grad_norm": NaN,
87
+ "learning_rate": 2.061073738537635e-05,
88
+ "loss": 0.0,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.0006694000502050038,
93
+ "eval_loss": NaN,
94
+ "eval_runtime": 2336.7538,
95
+ "eval_samples_per_second": 6.461,
96
+ "eval_steps_per_second": 3.231,
97
+ "step": 24
98
+ },
99
+ {
100
+ "epoch": 0.0007530750564806293,
101
+ "grad_norm": NaN,
102
+ "learning_rate": 5.449673790581611e-06,
103
+ "loss": 0.0,
104
+ "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.0008367500627562547,
108
+ "grad_norm": NaN,
109
+ "learning_rate": 0.0,
110
+ "loss": 0.0,
111
+ "step": 30
112
  }
113
  ],
114
  "logging_steps": 3,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 1.4238372348297216e+16,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null