Training in progress, epoch 1
Browse files- config.json +23 -4
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,17 +1,31 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"bos_token_id": 0,
|
| 8 |
"classifier_dropout": null,
|
| 9 |
-
"
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
"hidden_size": 768,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 3072,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
"layer_norm_eps": 1e-12,
|
| 16 |
"max_position_embeddings": 512,
|
| 17 |
"model_type": "bert",
|
|
@@ -19,11 +33,16 @@
|
|
| 19 |
"num_hidden_layers": 12,
|
| 20 |
"output_past": true,
|
| 21 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
"position_embedding_type": "absolute",
|
| 23 |
"problem_type": "single_label_classification",
|
| 24 |
"torch_dtype": "float32",
|
| 25 |
"transformers_version": "4.45.2",
|
| 26 |
"type_vocab_size": 2,
|
| 27 |
"use_cache": true,
|
| 28 |
-
"vocab_size":
|
| 29 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "indobenchmark/indobert-base-p1",
|
| 3 |
+
"_num_labels": 5,
|
| 4 |
"architectures": [
|
| 5 |
"BertForSequenceClassification"
|
| 6 |
],
|
| 7 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
| 8 |
"classifier_dropout": null,
|
| 9 |
+
"directionality": "bidi",
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0",
|
| 15 |
+
"1": "LABEL_1",
|
| 16 |
+
"2": "LABEL_2",
|
| 17 |
+
"3": "LABEL_3",
|
| 18 |
+
"4": "LABEL_4"
|
| 19 |
+
},
|
| 20 |
"initializer_range": 0.02,
|
| 21 |
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"LABEL_0": 0,
|
| 24 |
+
"LABEL_1": 1,
|
| 25 |
+
"LABEL_2": 2,
|
| 26 |
+
"LABEL_3": 3,
|
| 27 |
+
"LABEL_4": 4
|
| 28 |
+
},
|
| 29 |
"layer_norm_eps": 1e-12,
|
| 30 |
"max_position_embeddings": 512,
|
| 31 |
"model_type": "bert",
|
|
|
|
| 33 |
"num_hidden_layers": 12,
|
| 34 |
"output_past": true,
|
| 35 |
"pad_token_id": 0,
|
| 36 |
+
"pooler_fc_size": 768,
|
| 37 |
+
"pooler_num_attention_heads": 12,
|
| 38 |
+
"pooler_num_fc_layers": 3,
|
| 39 |
+
"pooler_size_per_head": 128,
|
| 40 |
+
"pooler_type": "first_token_transform",
|
| 41 |
"position_embedding_type": "absolute",
|
| 42 |
"problem_type": "single_label_classification",
|
| 43 |
"torch_dtype": "float32",
|
| 44 |
"transformers_version": "4.45.2",
|
| 45 |
"type_vocab_size": 2,
|
| 46 |
"use_cache": true,
|
| 47 |
+
"vocab_size": 50000
|
| 48 |
}
|
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:bf2e32516423b5ad5711f44907e8c3f8b047ecccb62a4b4f08d782261a6d4a6e
|
| 3 |
+
size 497804300
|