ddemszky
commited on
Commit
•
c19782d
1
Parent(s):
967c0ed
Update from ddemszky
Browse files- .DS_Store +0 -0
- command_args.json +1 -0
- config.json +27 -0
- events.out.tfevents.1614272536.jagupard12.stanford.edu +0 -0
- model_training_args.bin +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
.DS_Store
ADDED
Binary file (6.15 kB). View file
|
|
command_args.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"dataset_path": "data/combined_education_dataset_02252021.json", "model_name": "bert-base-uncased", "model_checkpoint": "bert-base-uncased", "num_candidates": 4, "max_history": 1, "train_batch_size": 32, "valid_batch_size": 16, "gradient_accumulation_steps": 2, "max_length": 120, "lr": 6.25e-05, "max_norm": 1.0, "n_epochs": 1, "mask_prev": 0.0, "eval_before_start": false, "min_prev_length": 0, "final_speaker": -1, "flipped": false, "fp16": "O2", "local_rank": -1, "head_attr": {"nsp": {"size": 2, "coef": 1}}, "distributed": false}
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"MultiHeadModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "bert",
|
22 |
+
"num_attention_heads": 12,
|
23 |
+
"num_hidden_layers": 12,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"vocab_size": 30522
|
27 |
+
}
|
events.out.tfevents.1614272536.jagupard12.stanford.edu
ADDED
Binary file (3.31 MB). View file
|
|
model_training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:569d5fffdbea7a4b414631b7da54f6e8634c1dc12ee420c7ae6ff73074b44976
|
3 |
+
size 782
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e4552d7dfbfb9e9d86f76a3260c9e355237ddb05b03b9feea7d57245e4476fe
|
3 |
+
size 437989703
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-uncased"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|