SaulLu commited on
Commit
4f22a43
1 Parent(s): 4a1b274

hyperparameter tuning step 19519

Browse files
Files changed (3) hide show
  1. README.md +7 -11
  2. config.json +2 -2
  3. pytorch_model.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ metrics:
18
 
19
  ## Model description
20
 
21
- [sahajBERT](https://huggingface.co/neuropark/sahajBERT-NER) fine-tuned for NER using the bengali of [WikiANN ](https://huggingface.co/datasets/wikiann).
22
 
23
  Named Entities predicted by the model:
24
 
@@ -60,7 +60,7 @@ WIP
60
 
61
  ## Training data
62
 
63
- The model was initialized it with pre-trained weights of [sahajBERT](https://huggingface.co/neuropark/sahajBERT-NER) at step TODO_REPLACE_BY_STEP_NAME and trained on the bengali of [WikiANN ](https://huggingface.co/datasets/wikiann)
64
 
65
  ## Training procedure
66
 
@@ -73,16 +73,12 @@ Coming soon!
73
 
74
  ## Eval results
75
 
76
- accuracy: 0.9756540697674418
77
-
78
- f1: 0.9570102589154861
79
-
80
- loss: 0.13705264031887054
81
-
82
- precision: 0.9518950437317785
83
-
84
- recall: 0.962180746561886
85
 
 
 
 
 
 
86
 
87
 
88
  ### BibTeX entry and citation info
 
18
 
19
  ## Model description
20
 
21
+ [sahajBERT](https://huggingface.co/neuropark/sahajBERT-NER) fine-tuned for NER using the bengali split of [WikiANN ](https://huggingface.co/datasets/wikiann).
22
 
23
  Named Entities predicted by the model:
24
 
 
60
 
61
  ## Training data
62
 
63
+ The model was initialized it with pre-trained weights of [sahajBERT](https://huggingface.co/neuropark/sahajBERT-NER) at step 19519 and trained on the bengali of [WikiANN ](https://huggingface.co/datasets/wikiann)
64
 
65
  ## Training procedure
66
 
 
73
 
74
  ## Eval results
75
 
 
 
 
 
 
 
 
 
 
76
 
77
+ loss: 0.11714419722557068
78
+ accuracy: 0.9772286821705426
79
+ precision: 0.9585365853658536
80
+ recall: 0.9651277013752456
81
+ f1 : 0.9618208516886931
82
 
83
 
84
  ### BibTeX entry and citation info
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "albertvillanova/autonlp-wikiann-entity_extraction-1e67664-1301123",
3
  "_num_labels": 7,
4
  "architectures": [
5
  "AlbertForTokenClassification"
@@ -36,7 +36,7 @@
36
  "6": 6
37
  },
38
  "layer_norm_eps": 1e-12,
39
- "max_length": 96,
40
  "max_position_embeddings": 512,
41
  "model_type": "albert",
42
  "net_structure_type": 0,
 
1
  {
2
+ "_name_or_path": "albertvillanova/autonlp-baselines-wikiann-entity_extraction-1341171",
3
  "_num_labels": 7,
4
  "architectures": [
5
  "AlbertForTokenClassification"
 
36
  "6": 6
37
  },
38
  "layer_norm_eps": 1e-12,
39
+ "max_length": 128,
40
  "max_position_embeddings": 512,
41
  "model_type": "albert",
42
  "net_structure_type": 0,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93fef3df43e9670b0c26ae9f82a57a1b7c7e9336c8553c9ed5918b97a413b264
3
  size 67605209
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:042f8d9caceb37cadfe054e9e78c8088f7ec98f8c62eb2db5238bf3a71de30f8
3
  size 67605209