tungpth commited on
Commit
5a1183e
·
verified ·
1 Parent(s): 6aa5306

Training in progress, epoch 3, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc43f1f6f30c00816063b65c03e668772ed580a36c79f607ef579bba2dd8db78
3
  size 265562304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e7a96259c0bec830cf446e8d9c15c86fdf993ca6f6f61168b30532b5b5d386d
3
  size 265562304
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4fde0d7c7011bbd5c0199f08f873c152db42ecdcd6f27c652e5e24bac26ea10
3
  size 531185466
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3665e53e810c8b45421e8a84c73cdc4c7f3c88aa090230da497b558e3095eff
3
  size 531185466
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08bbd4c4ebc8f97f97f2d4c841e4ab52108fa5f9e78b69afebd4b79e9615b325
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f90ff128c27d64c4453e5bfd8fe43d4d5cff37ef89f18d3416b9ba490469feaf
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d043a2a37bdd5cdd02a82d660f38f8a772d11708a4eb885de9704ffb7e5956f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e71f76d03c420f8529f202abf6f45411f0b5c0d2b007f282fb230f1219104b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.058028511703014374,
3
- "best_model_checkpoint": "BERT_NER/checkpoint-900",
4
- "epoch": 2.0,
5
  "eval_steps": 500,
6
- "global_step": 900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -40,6 +40,26 @@
40
  "eval_samples_per_second": 348.507,
41
  "eval_steps_per_second": 11.018,
42
  "step": 900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  }
44
  ],
45
  "logging_steps": 500,
@@ -59,7 +79,7 @@
59
  "attributes": {}
60
  }
61
  },
62
- "total_flos": 537188712218880.0,
63
  "train_batch_size": 32,
64
  "trial_name": null,
65
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.05421034246683121,
3
+ "best_model_checkpoint": "BERT_NER/checkpoint-1350",
4
+ "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 1350,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
40
  "eval_samples_per_second": 348.507,
41
  "eval_steps_per_second": 11.018,
42
  "step": 900
43
+ },
44
+ {
45
+ "epoch": 2.2222222222222223,
46
+ "grad_norm": 0.3950139284133911,
47
+ "learning_rate": 9.698463103929542e-06,
48
+ "loss": 0.0658,
49
+ "step": 1000
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "eval_accuracy": 0.9854042979557044,
54
+ "eval_f1": 0.8594994633071578,
55
+ "eval_loss": 0.05421034246683121,
56
+ "eval_model_preparation_time": 0.0016,
57
+ "eval_precision": 0.8481436057531497,
58
+ "eval_recall": 0.8711635364177737,
59
+ "eval_runtime": 7.742,
60
+ "eval_samples_per_second": 265.565,
61
+ "eval_steps_per_second": 8.396,
62
+ "step": 1350
63
  }
64
  ],
65
  "logging_steps": 500,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 805752940538112.0,
83
  "train_batch_size": 32,
84
  "trial_name": null,
85
  "trial_params": null