kokovova commited on
Commit
162bd06
·
verified ·
1 Parent(s): be85691

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 sha256:53590e2d62b9c7c6849c90cf431d1bc80555b8303247bbb4b042a3994b74d366
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:023fcdac7213b51dcb6a5b3f5d247e3b7c8a207dd855c983a20a4bd3898bbf19
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c32871ed367fbfce842fc140e0a7e8cd760b068dd07514dcbc3cbab9304e7efd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02a02c6e1e5039e685015f9532b801dd762ac99b4c55df43aefb88cfdbccca3e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
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": 0.01701041888156496,
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": 0.00013090169943749476,
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": 7418872835604480.0,
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": 0.02551562832234744,
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": 0.00013090169943749476,
74
  "loss": 0.0,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.017860939825643206,
79
+ "grad_norm": NaN,
80
+ "learning_rate": 8.435655349597689e-05,
81
+ "loss": 0.0,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.02041250265787795,
86
+ "grad_norm": NaN,
87
+ "learning_rate": 4.12214747707527e-05,
88
+ "loss": 0.0,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.02041250265787795,
93
+ "eval_loss": NaN,
94
+ "eval_runtime": 28.2988,
95
+ "eval_samples_per_second": 17.492,
96
+ "eval_steps_per_second": 8.764,
97
+ "step": 24
98
+ },
99
+ {
100
+ "epoch": 0.022964065490112696,
101
+ "grad_norm": NaN,
102
+ "learning_rate": 1.0899347581163221e-05,
103
+ "loss": 0.0,
104
+ "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.02551562832234744,
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": 1.112830925340672e+16,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null