Add model weights and configuration
Browse files- README.md +19 -0
- config.json +31 -0
- pytorch_model.bin +3 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
license: apache-2.0
|
4 |
+
datasets:
|
5 |
+
- sst-2
|
6 |
+
---
|
7 |
+
|
8 |
+
# DistilBERT base uncased finetuned SST-2
|
9 |
+
|
10 |
+
This model is a fine-tune checkpoint of [DistilBERT-base-uncased](https://huggingface.co/distilbert-base-uncased), fine-tuned on SST-2.
|
11 |
+
This model reaches an accuracy of 91.3 on the dev set (for comparison, Bert bert-base-uncased version reaches an accuracy of 92.7).
|
12 |
+
|
13 |
+
# Fine-tuning hyper-parameters
|
14 |
+
|
15 |
+
- learning_rate = 1e-5
|
16 |
+
- batch_size = 32
|
17 |
+
- warmup = 600
|
18 |
+
- max_seq_length = 128
|
19 |
+
- num_train_epochs = 3.0
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation": "gelu",
|
3 |
+
"architectures": [
|
4 |
+
"DistilBertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.1,
|
7 |
+
"dim": 768,
|
8 |
+
"dropout": 0.1,
|
9 |
+
"finetuning_task": "sst-2",
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "NEGATIVE",
|
13 |
+
"1": "POSITIVE"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"label2id": {
|
17 |
+
"NEGATIVE": 0,
|
18 |
+
"POSITIVE": 1
|
19 |
+
},
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "distilbert",
|
22 |
+
"n_heads": 12,
|
23 |
+
"n_layers": 6,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"qa_dropout": 0.1,
|
27 |
+
"seq_classif_dropout": 0.2,
|
28 |
+
"sinusoidal_pos_embds": false,
|
29 |
+
"tie_weights_": true,
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60554cbd7781b09d87f1ececbea8c064b94e49a7f03fd88e8775bfe6cc3d9f88
|
3 |
+
size 267844284
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b44df675bb34ccd8e57c14292c811ac7358b7c8e37c7f212745f640cd6019ac8
|
3 |
+
size 267949840
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model_max_length": 512, "do_lower_case": true}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|