Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +33 -0
- logs/1674303800.785072/events.out.tfevents.1674303800.gera.1813031.1 +3 -0
- logs/1674308156.015462/events.out.tfevents.1674308156.gifu.3369818.1 +3 -0
- logs/1674309127.9610622/events.out.tfevents.1674309127.serv-3334.2704200.1 +3 -0
- logs/1674309461.686954/events.out.tfevents.1674309461.serv-3330.351016.1 +3 -0
- logs/events.out.tfevents.1674303800.gera.1813031.0 +3 -0
- logs/events.out.tfevents.1674308156.gifu.3369818.0 +3 -0
- logs/events.out.tfevents.1674309127.serv-3334.2704200.0 +3 -0
- logs/events.out.tfevents.1674309461.serv-3330.351016.0 +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 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/mobilebert-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"MobileBertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_activation": true,
|
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 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.25.1",
|
27 |
+
"trigram_input": true,
|
28 |
+
"true_hidden_size": 128,
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_bottleneck": true,
|
31 |
+
"use_bottleneck_attention": false,
|
32 |
+
"vocab_size": 30522
|
33 |
+
}
|
logs/1674303800.785072/events.out.tfevents.1674303800.gera.1813031.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:688e9e6c45fd582e111f6070e4622207bbd9a8351c304f093f57da03035f6726
|
3 |
+
size 5579
|
logs/1674308156.015462/events.out.tfevents.1674308156.gifu.3369818.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a668413d4861904730210b7acc1249fbd5581427b9f5f483584b51028131436
|
3 |
+
size 5579
|
logs/1674309127.9610622/events.out.tfevents.1674309127.serv-3334.2704200.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eabf0f2b6512a1a893bd4f21cada0364a8d1eb3becac872cc7cbb63a806462fc
|
3 |
+
size 5579
|
logs/1674309461.686954/events.out.tfevents.1674309461.serv-3330.351016.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47778b740258fe60b1a6851059114e51a0d309e4c5311040c2c6df4bf3ac074d
|
3 |
+
size 5579
|
logs/events.out.tfevents.1674303800.gera.1813031.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c20b7035ddc0db267f069c97d9b2d344523f2cf36888b26128a1b3a655ae567d
|
3 |
+
size 3970
|
logs/events.out.tfevents.1674308156.gifu.3369818.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e83f2fc35d2f201fbe82d786a27009d0996dd52132a2be079f53ab4d4ebff86
|
3 |
+
size 3970
|
logs/events.out.tfevents.1674309127.serv-3334.2704200.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5212fe42d0c8c0bbaaa0cd97c52cb34f9b324b4213e233b6e6ca80a8dbb564f
|
3 |
+
size 3970
|
logs/events.out.tfevents.1674309461.serv-3330.351016.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae4e5ae4e2ad6c997deae81e8183cae2e333c5f0449b8aa018532c7eff22fcf9
|
3 |
+
size 4450
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86fba3ffbedd30b86d16fb03ceba07e992d6071023479475cdf4a0f9bd81bf12
|
3 |
+
size 146800571
|
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:a739e90a2ee1fb9235fafe0367a8c80e0409ea77c9df5704325eb84276b20657
|
3 |
+
size 3451
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|