Hugging Face's logo

tungpth
/
BERT_NER

Token Classification
Transformers
Safetensors
distilbert
Model card Files
xet
 Community
tungpth commited on
Commit
cc4b36f
·
verified ·
1 Parent(s): a6c924a

Training in progress, epoch 3, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +25 -5
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74811ee8b75b19540d297f35d53ce3da3d7ad14536268c081a789e0339e982ba
3
  size 265525384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09eae4ec16c17a1c66c55f67d32253bf64f84b6563cc1036195cc665371a033c
3
  size 265525384
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2a02dcb85af6b08dd751bfa31bf146821581aa1077ed7193226fb9521cc8cb1
3
  size 531111610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c30ee02b4ef6725488b2c034eeaa98fd914dd3244535f144793bb40caa42f65
3
  size 531111610
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5584750063aa6dea0e786622d2dfd5e17a986b1e4e2df63b269f04d40728ac8c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:856e0f5f9026ae40dfcdb1381236fda24268e4af80d234c2cc7aed35bfb519eb
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": 0.05390042066574097,
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": 358.897,
41
  "eval_steps_per_second": 11.346,
42
  "step": 900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  }
44
  ],
45
  "logging_steps": 500,
@@ -59,7 +79,7 @@
59
  "attributes": {}
60
  }
61
  },
62
- "total_flos": 536503488883776.0,
63
  "train_batch_size": 32,
64
  "trial_name": null,
65
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.05013062804937363,
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": 358.897,
41
  "eval_steps_per_second": 11.346,
42
  "step": 900
43
+ },
44
+ {
45
+ "epoch": 2.2222222222222223,
46
+ "grad_norm": 0.47045743465423584,
47
+ "learning_rate": 9.698463103929542e-06,
48
+ "loss": 0.0594,
49
+ "step": 1000
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "eval_accuracy": 0.9859576186274657,
54
+ "eval_f1": 0.8661595150362533,
55
+ "eval_loss": 0.05013062804937363,
56
+ "eval_model_preparation_time": 0.0017,
57
+ "eval_precision": 0.8570924488355681,
58
+ "eval_recall": 0.8754204709274387,
59
+ "eval_runtime": 5.8189,
60
+ "eval_samples_per_second": 353.33,
61
+ "eval_steps_per_second": 11.17,
62
+ "step": 1350
63
  }
64
  ],
65
  "logging_steps": 500,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 805033472053584.0,
83
  "train_batch_size": 32,
84
  "trial_name": null,
85
  "trial_params": null