tillschwoerer
commited on
Commit
•
839751b
1
Parent(s):
197cc26
Training in progress, step 90
Browse files- .gitignore +1 -0
- config.json +34 -0
- pytorch_model.bin +3 -0
- runs/Jun12_22-37-59_0fb523675e41/events.out.tfevents.1686609493.0fb523675e41.736.0 +3 -0
- runs/Jun12_22-37-59_0fb523675e41/events.out.tfevents.1686609550.0fb523675e41.736.1 +3 -0
- runs/Jun12_22-47-43_0fb523675e41/events.out.tfevents.1686610080.0fb523675e41.736.2 +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 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/mobilebert-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"MobileBertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_activation": false,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"embedding_size": 128,
|
10 |
+
"hidden_act": "relu",
|
11 |
+
"hidden_dropout_prob": 0.0,
|
12 |
+
"hidden_size": 512,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 512,
|
15 |
+
"intra_bottleneck_size": 128,
|
16 |
+
"key_query_shared_bottleneck": true,
|
17 |
+
"layer_norm_eps": 1e-12,
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "mobilebert",
|
20 |
+
"normalization_type": "no_norm",
|
21 |
+
"num_attention_heads": 4,
|
22 |
+
"num_feedforward_networks": 4,
|
23 |
+
"num_hidden_layers": 24,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"problem_type": "single_label_classification",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.30.1",
|
28 |
+
"trigram_input": true,
|
29 |
+
"true_hidden_size": 128,
|
30 |
+
"type_vocab_size": 2,
|
31 |
+
"use_bottleneck": true,
|
32 |
+
"use_bottleneck_attention": false,
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3047ac9e53c4c65acf4ec3ac4afae3d84959362065092df5cf1c539778d3953d
|
3 |
+
size 98725415
|
runs/Jun12_22-37-59_0fb523675e41/events.out.tfevents.1686609493.0fb523675e41.736.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fdab477deec3e96c520a50d0f0ffe97c40ee12d423dd0661d33293ede452fa0
|
3 |
+
size 4696
|
runs/Jun12_22-37-59_0fb523675e41/events.out.tfevents.1686609550.0fb523675e41.736.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48919b15ccd53ef8737ba90de907f18c7f29b3587d5986fb64a3ed2b5414645e
|
3 |
+
size 551
|
runs/Jun12_22-47-43_0fb523675e41/events.out.tfevents.1686610080.0fb523675e41.736.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88fe0199c13c3e5a7656dbd4b1050e63b2982fe6aa8db0f1432361fa5c394296
|
3 |
+
size 6200
|
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": 1000000000000000019884624838656,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "MobileBertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0095df37237ad487f413268c91adbe924767fb0a25b5c6dccee807cb62e91779
|
3 |
+
size 4027
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|