Training in progress, epoch 1
Browse files- config.json +33 -0
- log.txt +5 -0
- model.safetensors +3 -0
- runs/Mar12_23-46-21_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710312384.cehsc-app-001.ad.unlv.edu.2715464.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/mobilebert-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"MobileBertForMultipleChoice"
|
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 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.39.0.dev0",
|
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 |
+
}
|
log.txt
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{'loss': 6619.536, 'grad_norm': 570995.875, 'learning_rate': 4.708318749270797e-05, 'epoch': 0.18}
|
2 |
+
{'loss': 41.9051, 'grad_norm': 50093.546875, 'learning_rate': 4.416637498541594e-05, 'epoch': 0.35}
|
3 |
+
{'loss': 12.3949, 'grad_norm': 30450.115234375, 'learning_rate': 4.124956247812391e-05, 'epoch': 0.53}
|
4 |
+
{'loss': 2.3106, 'grad_norm': 2060.141845703125, 'learning_rate': 3.8332749970831875e-05, 'epoch': 0.7}
|
5 |
+
{'loss': 3.8107, 'grad_norm': 1.1463676691055298, 'learning_rate': 3.5415937463539846e-05, 'epoch': 0.88}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2575caffeb54f350381dde75dba1ce201d9d6ae213a0c5a55f85689806c04da
|
3 |
+
size 98468060
|
runs/Mar12_23-46-21_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710312384.cehsc-app-001.ad.unlv.edu.2715464.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd699e1e622eee460a5160ceace60020c28919fa39ee9070b84d7d8690955867
|
3 |
+
size 6236
|
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 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 1000000000000000019884624838656,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "MobileBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb6af806b87add948d41ff18f253e26978a0bd5a67ad045e212c9c758b9d3e4d
|
3 |
+
size 4920
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|