Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +45 -0
- logs/1674651779.2361245/events.out.tfevents.1674651779.garda.1933772.25 +3 -0
- logs/events.out.tfevents.1674651779.garda.1933772.24 +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 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "mnli",
|
11 |
+
"hidden_act": "relu",
|
12 |
+
"hidden_dropout_prob": 0.0,
|
13 |
+
"hidden_size": 512,
|
14 |
+
"id2label": {
|
15 |
+
"0": "entailment",
|
16 |
+
"1": "neutral",
|
17 |
+
"2": "contradiction"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 512,
|
21 |
+
"intra_bottleneck_size": 128,
|
22 |
+
"key_query_shared_bottleneck": true,
|
23 |
+
"label2id": {
|
24 |
+
"contradiction": 2,
|
25 |
+
"entailment": 0,
|
26 |
+
"neutral": 1
|
27 |
+
},
|
28 |
+
"layer_norm_eps": 1e-12,
|
29 |
+
"max_position_embeddings": 512,
|
30 |
+
"model_type": "mobilebert",
|
31 |
+
"normalization_type": "no_norm",
|
32 |
+
"num_attention_heads": 4,
|
33 |
+
"num_feedforward_networks": 4,
|
34 |
+
"num_hidden_layers": 24,
|
35 |
+
"pad_token_id": 0,
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.26.0",
|
39 |
+
"trigram_input": true,
|
40 |
+
"true_hidden_size": 128,
|
41 |
+
"type_vocab_size": 2,
|
42 |
+
"use_bottleneck": true,
|
43 |
+
"use_bottleneck_attention": false,
|
44 |
+
"vocab_size": 30522
|
45 |
+
}
|
logs/1674651779.2361245/events.out.tfevents.1674651779.garda.1933772.25
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f2b22b768bdb497079cc114f0a0ca87e01a82154486f8651124d0fed0017344
|
3 |
+
size 5736
|
logs/events.out.tfevents.1674651779.garda.1933772.24
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:647d51cdf98a8b102bc48d1642c7616111efb246b454e89ad0ea4a330f01305d
|
3 |
+
size 4791
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2954bb4798c66a648e75189be800065a7d962fca9969152fabe1105d3f79a503
|
3 |
+
size 98746471
|
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:bb0c8f284ace700f8a028d1bdbb7eda8417966af15299e944d53d238cc7b50ca
|
3 |
+
size 3579
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|