tuantmdev commited on
Commit
4f48c7d
·
verified ·
1 Parent(s): 93886cb

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d1a5183180da828d731c7e00262d9e07e872b3a2f1c0bd9246446d42643b73c
3
  size 70674004
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c3036e821a058fd6b669172c87281bbfc9101fd063c38f886e29362abd0a6d8
3
  size 70674004
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d512a571d085f4d9989d78a8e0b09cb382333722c0829a4988b8dbb1f569fa6d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9328f98fd1ecb7e434b3b40964665e35916ee871a844c7f44a742f9d34904f09
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:053f8a597fb71bde446a175404cc18fe6996cf501293c3abfb94953dfd03d780
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b23fe3d7c8cff984a05b7865b1b491bac693fd2f496a4e0e24b70ad75a25bd
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": 0.007643159968949663,
5
  "eval_steps": 10,
6
- "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -54,6 +54,14 @@
54
  "eval_samples_per_second": 3.403,
55
  "eval_steps_per_second": 1.702,
56
  "step": 40
 
 
 
 
 
 
 
 
57
  }
58
  ],
59
  "logging_steps": 40,
@@ -68,12 +76,12 @@
68
  "should_evaluate": false,
69
  "should_log": false,
70
  "should_save": true,
71
- "should_training_stop": false
72
  },
73
  "attributes": {}
74
  }
75
  },
76
- "total_flos": 1.1030394870693888e+17,
77
  "train_batch_size": 2,
78
  "trial_name": null,
79
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.009553949961187079,
5
  "eval_steps": 10,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
54
  "eval_samples_per_second": 3.403,
55
  "eval_steps_per_second": 1.702,
56
  "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.009553949961187079,
60
+ "eval_loss": NaN,
61
+ "eval_runtime": 1864.7113,
62
+ "eval_samples_per_second": 4.727,
63
+ "eval_steps_per_second": 2.364,
64
+ "step": 50
65
  }
66
  ],
67
  "logging_steps": 40,
 
76
  "should_evaluate": false,
77
  "should_log": false,
78
  "should_save": true,
79
+ "should_training_stop": true
80
  },
81
  "attributes": {}
82
  }
83
  },
84
+ "total_flos": 1.378799358836736e+17,
85
  "train_batch_size": 2,
86
  "trial_name": null,
87
  "trial_params": null