Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +41 -0
- logs/1675095503.1850824/events.out.tfevents.1675095503.serv-3334.1119753.19 +3 -0
- logs/events.out.tfevents.1675095503.serv-3334.1119753.18 +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 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gokuls/mobilebert_sa_pre-training-complete",
|
3 |
+
"architectures": [
|
4 |
+
"MobileBertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_activation": true,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"embedding_size": 128,
|
10 |
+
"finetuning_task": "stsb",
|
11 |
+
"hidden_act": "relu",
|
12 |
+
"hidden_dropout_prob": 0.0,
|
13 |
+
"hidden_size": 512,
|
14 |
+
"id2label": {
|
15 |
+
"0": "LABEL_0"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 512,
|
19 |
+
"intra_bottleneck_size": 128,
|
20 |
+
"key_query_shared_bottleneck": true,
|
21 |
+
"label2id": {
|
22 |
+
"LABEL_0": 0
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "mobilebert",
|
27 |
+
"normalization_type": "no_norm",
|
28 |
+
"num_attention_heads": 4,
|
29 |
+
"num_feedforward_networks": 4,
|
30 |
+
"num_hidden_layers": 24,
|
31 |
+
"pad_token_id": 0,
|
32 |
+
"problem_type": "regression",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.26.0",
|
35 |
+
"trigram_input": true,
|
36 |
+
"true_hidden_size": 128,
|
37 |
+
"type_vocab_size": 2,
|
38 |
+
"use_bottleneck": true,
|
39 |
+
"use_bottleneck_attention": false,
|
40 |
+
"vocab_size": 30522
|
41 |
+
}
|
logs/1675095503.1850824/events.out.tfevents.1675095503.serv-3334.1119753.19
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4091ed282cd7b6aca032cd71e8a8f5a38419ca3d37d70f8a809feb4404b90e05
|
3 |
+
size 5804
|
logs/events.out.tfevents.1675095503.serv-3334.1119753.18
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35c74f2999103e72f3f3930918ca4e1028e4ba5c1cd6d2e69c455cb8dbd4b28e
|
3 |
+
size 4906
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7951b07b1a8826b872aa220294964b1eca0558040fa0410e2c8a34e34b5a105
|
3 |
+
size 99793649
|
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": "gokuls/mobilebert_sa_pre-training-complete",
|
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 sha256:11514f1bed3ac8ecf8b321b6ca45867a0e82f299046200cfd04f658195550893
|
3 |
+
size 3643
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|