tuanna08go commited on
Commit
e0538c6
·
verified ·
1 Parent(s): 3ffad17

Training in progress, step 22, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe0b6bacf47774ccf9cd91b28df80b77702b4902189c8f9f09434aea785f6397
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ca53db88302fb1c1e9d5b51a4ad6d5950171f9138f78baeef8aa09e9783c6f
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:daae2956a814ad3ea90d287de249c9703335ab3a98a165ec23509d6e9d2d3e49
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a613b3fad19832601de19359f37f3c026c8fea2ed390d73b600852a9467d45a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10e175ebe60f1a6bbd43d635188097fdd53bf710ff976db3f946328fc19cf4ba
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1565387b96ec5f770ad7b2f4817988cb2fc09f94ceb911096ae3c468010baf3d
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": 0.8228571428571428,
5
  "eval_steps": 5,
6
- "global_step": 18,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -46,6 +46,21 @@
46
  "eval_samples_per_second": 51.962,
47
  "eval_steps_per_second": 6.671,
48
  "step": 15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  }
50
  ],
51
  "logging_steps": 10,
@@ -60,12 +75,12 @@
60
  "should_evaluate": false,
61
  "should_log": false,
62
  "should_save": true,
63
- "should_training_stop": false
64
  },
65
  "attributes": {}
66
  }
67
  },
68
- "total_flos": 9339789845200896.0,
69
  "train_batch_size": 8,
70
  "trial_name": null,
71
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0114285714285713,
5
  "eval_steps": 5,
6
+ "global_step": 22,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
46
  "eval_samples_per_second": 51.962,
47
  "eval_steps_per_second": 6.671,
48
  "step": 15
49
+ },
50
+ {
51
+ "epoch": 0.9142857142857143,
52
+ "grad_norm": NaN,
53
+ "learning_rate": 2.4471741852423237e-06,
54
+ "loss": 0.0,
55
+ "step": 20
56
+ },
57
+ {
58
+ "epoch": 0.9142857142857143,
59
+ "eval_loss": NaN,
60
+ "eval_runtime": 2.8362,
61
+ "eval_samples_per_second": 52.183,
62
+ "eval_steps_per_second": 6.699,
63
+ "step": 20
64
  }
65
  ],
66
  "logging_steps": 10,
 
75
  "should_evaluate": false,
76
  "should_log": false,
77
  "should_save": true,
78
+ "should_training_stop": true
79
  },
80
  "attributes": {}
81
  }
82
  },
83
+ "total_flos": 1.1415298699689984e+16,
84
  "train_batch_size": 8,
85
  "trial_name": null,
86
  "trial_params": null