Training in progress, epoch 1
Browse files- README.md +1 -3
- config.json +4 -2
- model.safetensors +1 -1
- runs/Feb24_19-47-23_92734c0b55b6/events.out.tfevents.1740426444.92734c0b55b6.23332.0 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +3 -1
- training_args.bin +1 -1
- vocab.txt +0 -0
README.md
CHANGED
@@ -12,8 +12,6 @@ metrics:
|
|
12 |
model-index:
|
13 |
- name: legal_ai_India_ner_results
|
14 |
results: []
|
15 |
-
datasets:
|
16 |
-
- opennyaiorg/InLegalNER
|
17 |
---
|
18 |
|
19 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -69,4 +67,4 @@ The following hyperparameters were used during training:
|
|
69 |
- Transformers 4.48.3
|
70 |
- Pytorch 2.5.1+cu124
|
71 |
- Datasets 3.3.2
|
72 |
-
- Tokenizers 0.21.0
|
|
|
12 |
model-index:
|
13 |
- name: legal_ai_India_ner_results
|
14 |
results: []
|
|
|
|
|
15 |
---
|
16 |
|
17 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
67 |
- Transformers 4.48.3
|
68 |
- Pytorch 2.5.1+cu124
|
69 |
- Datasets 3.3.2
|
70 |
+
- Tokenizers 0.21.0
|
config.json
CHANGED
@@ -1,11 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "bert-base-uncased",
|
3 |
"architectures": [
|
4 |
"BertForTokenClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
7 |
"classifier_dropout": null,
|
8 |
-
"
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
@@ -78,6 +79,7 @@
|
|
78 |
"model_type": "bert",
|
79 |
"num_attention_heads": 12,
|
80 |
"num_hidden_layers": 12,
|
|
|
81 |
"pad_token_id": 0,
|
82 |
"position_embedding_type": "absolute",
|
83 |
"torch_dtype": "float32",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "nlpaueb/legal-bert-base-uncased",
|
3 |
"architectures": [
|
4 |
"BertForTokenClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
"classifier_dropout": null,
|
9 |
+
"eos_token_ids": 0,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
"hidden_size": 768,
|
|
|
79 |
"model_type": "bert",
|
80 |
"num_attention_heads": 12,
|
81 |
"num_hidden_layers": 12,
|
82 |
+
"output_past": true,
|
83 |
"pad_token_id": 0,
|
84 |
"position_embedding_type": "absolute",
|
85 |
"torch_dtype": "float32",
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 435679140
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f75cc7c4cda143f865686ed735a7de23c4f63539d3c2c2e5cc9a8fd0511a8e3
|
3 |
size 435679140
|
runs/Feb24_19-47-23_92734c0b55b6/events.out.tfevents.1740426444.92734c0b55b6.23332.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e01f078ad3b58b67f36ae98f60370075fe14052151a430c1c3a45c1c3abf9980
|
3 |
+
size 7108
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -41,12 +41,14 @@
|
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
44 |
-
"clean_up_tokenization_spaces":
|
45 |
"cls_token": "[CLS]",
|
|
|
46 |
"do_lower_case": true,
|
47 |
"extra_special_tokens": {},
|
48 |
"mask_token": "[MASK]",
|
49 |
"model_max_length": 512,
|
|
|
50 |
"pad_token": "[PAD]",
|
51 |
"sep_token": "[SEP]",
|
52 |
"strip_accents": null,
|
|
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
"do_lower_case": true,
|
48 |
"extra_special_tokens": {},
|
49 |
"mask_token": "[MASK]",
|
50 |
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
"pad_token": "[PAD]",
|
53 |
"sep_token": "[SEP]",
|
54 |
"strip_accents": null,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ab82ecbbfc924de502d97edef152d751a6b63dbf64bbc4cafb77376dc525e54
|
3 |
size 5368
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|