End of training
Browse files- README.md +2 -2
- config.json +31 -30
- model.safetensors +2 -2
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
-
base_model: Rajan/NepaliBERT
|
5 |
model-index:
|
6 |
- name: nepali_gov_complaints_classification
|
7 |
results: []
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
This model is a fine-tuned version of [Rajan/NepaliBERT](https://huggingface.co/Rajan/NepaliBERT) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Loss: 0.
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
1 |
---
|
2 |
+
base_model: Rajan/NepaliBERT
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
5 |
model-index:
|
6 |
- name: nepali_gov_complaints_classification
|
7 |
results: []
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [Rajan/NepaliBERT](https://huggingface.co/Rajan/NepaliBERT) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.2385
|
18 |
|
19 |
## Model description
|
20 |
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
@@ -10,38 +10,38 @@
|
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
-
"0": "
|
14 |
-
"1": "
|
15 |
-
"2": "
|
16 |
-
"3": "
|
17 |
-
"4": "
|
18 |
-
"5": "
|
19 |
-
"6": "
|
20 |
-
"7": "
|
21 |
-
"8": "
|
22 |
-
"9": "
|
23 |
-
"10": "
|
24 |
-
"11": "
|
25 |
-
"12": "
|
26 |
-
"13": "
|
27 |
},
|
28 |
"initializer_range": 0.02,
|
29 |
"intermediate_size": 3072,
|
30 |
"label2id": {
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
},
|
46 |
"layer_norm_eps": 1e-12,
|
47 |
"max_position_embeddings": 512,
|
@@ -50,9 +50,10 @@
|
|
50 |
"num_hidden_layers": 6,
|
51 |
"pad_token_id": 0,
|
52 |
"position_embedding_type": "absolute",
|
|
|
53 |
"torch_dtype": "float32",
|
54 |
"transformers_version": "4.38.2",
|
55 |
"type_vocab_size": 2,
|
56 |
"use_cache": true,
|
57 |
"vocab_size": 50000
|
58 |
-
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Rajan/NepaliBERT",
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
|
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6",
|
20 |
+
"7": "LABEL_7",
|
21 |
+
"8": "LABEL_8",
|
22 |
+
"9": "LABEL_9",
|
23 |
+
"10": "LABEL_10",
|
24 |
+
"11": "LABEL_11",
|
25 |
+
"12": "LABEL_12",
|
26 |
+
"13": "LABEL_13"
|
27 |
},
|
28 |
"initializer_range": 0.02,
|
29 |
"intermediate_size": 3072,
|
30 |
"label2id": {
|
31 |
+
"LABEL_0": 0,
|
32 |
+
"LABEL_1": 1,
|
33 |
+
"LABEL_10": 10,
|
34 |
+
"LABEL_11": 11,
|
35 |
+
"LABEL_12": 12,
|
36 |
+
"LABEL_13": 13,
|
37 |
+
"LABEL_2": 2,
|
38 |
+
"LABEL_3": 3,
|
39 |
+
"LABEL_4": 4,
|
40 |
+
"LABEL_5": 5,
|
41 |
+
"LABEL_6": 6,
|
42 |
+
"LABEL_7": 7,
|
43 |
+
"LABEL_8": 8,
|
44 |
+
"LABEL_9": 9
|
45 |
},
|
46 |
"layer_norm_eps": 1e-12,
|
47 |
"max_position_embeddings": 512,
|
|
|
50 |
"num_hidden_layers": 6,
|
51 |
"pad_token_id": 0,
|
52 |
"position_embedding_type": "absolute",
|
53 |
+
"problem_type": "single_label_classification",
|
54 |
"torch_dtype": "float32",
|
55 |
"transformers_version": "4.38.2",
|
56 |
"type_vocab_size": 2,
|
57 |
"use_cache": true,
|
58 |
"vocab_size": 50000
|
59 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05ca3e3d07b8358bbaba3478503163aa83bc462ddebf440ca1d746dbcce14925
|
3 |
+
size 327711728
|