Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +43 -0
- logs/1674685207.2836246/events.out.tfevents.1674685207.garda.227848.22 +3 -0
- logs/events.out.tfevents.1674685207.garda.227848.21 +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"finetuning_task": "wnli",
|
11 |
+
"hidden_act": "relu",
|
12 |
+
"hidden_dropout_prob": 0.0,
|
13 |
+
"hidden_size": 128,
|
14 |
+
"id2label": {
|
15 |
+
"0": "not_entailment",
|
16 |
+
"1": "entailment"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 512,
|
20 |
+
"intra_bottleneck_size": 128,
|
21 |
+
"key_query_shared_bottleneck": true,
|
22 |
+
"label2id": {
|
23 |
+
"entailment": 1,
|
24 |
+
"not_entailment": 0
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-12,
|
27 |
+
"max_position_embeddings": 512,
|
28 |
+
"model_type": "mobilebert",
|
29 |
+
"normalization_type": "no_norm",
|
30 |
+
"num_attention_heads": 4,
|
31 |
+
"num_feedforward_networks": 4,
|
32 |
+
"num_hidden_layers": 24,
|
33 |
+
"pad_token_id": 0,
|
34 |
+
"problem_type": "single_label_classification",
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.26.0",
|
37 |
+
"trigram_input": true,
|
38 |
+
"true_hidden_size": 128,
|
39 |
+
"type_vocab_size": 2,
|
40 |
+
"use_bottleneck": true,
|
41 |
+
"use_bottleneck_attention": false,
|
42 |
+
"vocab_size": 30522
|
43 |
+
}
|
logs/1674685207.2836246/events.out.tfevents.1674685207.garda.227848.22
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:255acbcca291fc077f7bcf388eb4039b7375a3d37b43bb4e44c7c0b9b6394f0b
|
3 |
+
size 5748
|
logs/events.out.tfevents.1674685207.garda.227848.21
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fc6f24905fe3172e0787a0740297bb8134ff8a046e2ee4cd3329fb9616f34da
|
3 |
+
size 4759
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efd004bb91022b094a30200c9925113fce24a99018cbf3fed108589b002f409b
|
3 |
+
size 78371943
|
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 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": true,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"name_or_path": "google/mobilebert-uncased",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"strip_accents": null,
|
11 |
+
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "MobileBertTokenizer",
|
13 |
+
"unk_token": "[UNK]"
|
14 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b852e5c7e0f9c0e10dab75761635ed1112015f385569b56160a570f3caeca81c
|
3 |
+
size 3515
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|