Commit
·
3f89945
1
Parent(s):
b45fc0a
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +30 -0
- pytorch_model.bin +3 -0
- runs/Sep11_01-34-06_77c4c09950a4/1694396051.3460858/events.out.tfevents.1694396051.77c4c09950a4.250.71 +3 -0
- runs/Sep11_01-34-06_77c4c09950a4/events.out.tfevents.1694396051.77c4c09950a4.250.70 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "squeezebert/squeezebert-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"SqueezeBertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"embedding_size": 768,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_groups": 4,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"k_groups": 4,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "squeezebert",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_groups": 4,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"post_attention_groups": 1,
|
23 |
+
"problem_type": "single_label_classification",
|
24 |
+
"q_groups": 4,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.28.0",
|
27 |
+
"type_vocab_size": 2,
|
28 |
+
"v_groups": 4,
|
29 |
+
"vocab_size": 30528
|
30 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a759990138aeab05c0c453c920cb9f5d06fab7d8aaf6430f23067b3a7054d9a5
|
3 |
+
size 204457461
|
runs/Sep11_01-34-06_77c4c09950a4/1694396051.3460858/events.out.tfevents.1694396051.77c4c09950a4.250.71
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96584b58381ac862bb7609ab36d7df6c17d73e810dc8ecced0852dd530d9913a
|
3 |
+
size 5928
|
runs/Sep11_01-34-06_77c4c09950a4/events.out.tfevents.1694396051.77c4c09950a4.250.70
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99b486f9ecf97d1824b27741b5f5bde9d437b13f4992a73fccc5878cb5595d13
|
3 |
+
size 4414
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "SqueezeBertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:643dfd9c6e4c254c5dc06472cf4eaf36d4631e8ec04b97538a056c3ef8a3a111
|
3 |
+
size 3643
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|