tuanna08go commited on
Commit
f2517f6
·
verified ·
1 Parent(s): b0c449f

Training in progress, step 15, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3c90e5845f49a2c463e517e78aef705f9618fdfc9c7660f0b3344d3608e5504
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ddb77f6efca763e77029bc268b9b27bb94fbe56a81e22a41cc850e3602a4a45
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65feb82aeff84f74730d241f8a93f4edc4ac56bf11dc7a0aebce45c910102b64
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff194d5e77d5b7a237603526d8175ac2445e0953692ed1147fea567616a9285
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e59b38b7699f7635523e7ab6d478b4e9b420f110d0bbbef9f4bd629aa3d6cd28
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:008d83c4f5ee0c3b0aa2ca88e92cb7f21d43acfd48a8bc37442b67fb3134fa7c
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": 0.8495575221238938,
5
  "eval_steps": 3,
6
- "global_step": 12,
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": 52.837,
55
  "eval_steps_per_second": 6.674,
56
  "step": 12
 
 
 
 
 
 
 
 
57
  }
58
  ],
59
  "logging_steps": 10,
@@ -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": 6226526563467264.0,
77
  "train_batch_size": 8,
78
  "trial_name": null,
79
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0619469026548674,
5
  "eval_steps": 3,
6
+ "global_step": 15,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
54
  "eval_samples_per_second": 52.837,
55
  "eval_steps_per_second": 6.674,
56
  "step": 12
57
+ },
58
+ {
59
+ "epoch": 1.0619469026548674,
60
+ "eval_loss": NaN,
61
+ "eval_runtime": 1.8007,
62
+ "eval_samples_per_second": 52.757,
63
+ "eval_steps_per_second": 6.664,
64
+ "step": 15
65
  }
66
  ],
67
  "logging_steps": 10,
 
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": 7770997019639808.0,
85
  "train_batch_size": 8,
86
  "trial_name": null,
87
  "trial_params": null