Training in progress, epoch 1
Browse files- config.json +35 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MobileBertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_activation": false,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"dtype": "float32",
|
| 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 |
+
"problem_type": "single_label_classification",
|
| 26 |
+
"tie_word_embeddings": true,
|
| 27 |
+
"transformers_version": "5.3.0",
|
| 28 |
+
"trigram_input": true,
|
| 29 |
+
"true_hidden_size": 128,
|
| 30 |
+
"type_vocab_size": 2,
|
| 31 |
+
"use_bottleneck": true,
|
| 32 |
+
"use_bottleneck_attention": false,
|
| 33 |
+
"use_cache": false,
|
| 34 |
+
"vocab_size": 30527
|
| 35 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87f43fffbd40d9e6332cedce1e80a99e9722bf14fcccfcc46d5e562600f9951b
|
| 3 |
+
size 98472480
|
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 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"pad_token": "[PAD]",
|
| 9 |
+
"sep_token": "[SEP]",
|
| 10 |
+
"strip_accents": null,
|
| 11 |
+
"tokenize_chinese_chars": true,
|
| 12 |
+
"tokenizer_class": "BertTokenizer",
|
| 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:e9247749e0e6153f779ffe9d07b40ed88e768f6a67878542a37a4dadb885d1b1
|
| 3 |
+
size 5329
|