Uploading model
Browse files- config.json +54 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +17 -0
- trainer_state.json +70 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/scratch/ba63/BERT_models/bert-base-arabic-camelbert-msa",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassificationSingleLabel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "DELETE",
|
14 |
+
"1": "MERGE-B",
|
15 |
+
"2": "MERGE-I",
|
16 |
+
"3": "REPLACE_M",
|
17 |
+
"4": "REPLACE_M+REPLACE_O",
|
18 |
+
"5": "REPLACE_O",
|
19 |
+
"6": "REPLACE_O+REPLACE_X",
|
20 |
+
"7": "REPLACE_P",
|
21 |
+
"8": "REPLACE_S",
|
22 |
+
"9": "REPLACE_X",
|
23 |
+
"10": "SPLIT",
|
24 |
+
"11": "UC"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 3072,
|
28 |
+
"label2id": {
|
29 |
+
"DELETE": 0,
|
30 |
+
"MERGE-B": 1,
|
31 |
+
"MERGE-I": 2,
|
32 |
+
"REPLACE_M": 3,
|
33 |
+
"REPLACE_M+REPLACE_O": 4,
|
34 |
+
"REPLACE_O": 5,
|
35 |
+
"REPLACE_O+REPLACE_X": 6,
|
36 |
+
"REPLACE_P": 7,
|
37 |
+
"REPLACE_S": 8,
|
38 |
+
"REPLACE_X": 9,
|
39 |
+
"SPLIT": 10,
|
40 |
+
"UC": 11
|
41 |
+
},
|
42 |
+
"layer_norm_eps": 1e-12,
|
43 |
+
"max_position_embeddings": 512,
|
44 |
+
"model_type": "bert",
|
45 |
+
"num_attention_heads": 12,
|
46 |
+
"num_hidden_layers": 12,
|
47 |
+
"pad_token_id": 0,
|
48 |
+
"position_embedding_type": "absolute",
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.22.2",
|
51 |
+
"type_vocab_size": 2,
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 30000
|
54 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd1b45128bea890a56046fd27d9d3e4874b1ddae64c78ec05fb855617d9d1d72
|
3 |
+
size 434070321
|
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_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"full_tokenizer_file": null,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 512,
|
8 |
+
"name_or_path": "/scratch/ba63/BERT_models/bert-base-arabic-camelbert-msa",
|
9 |
+
"never_split": null,
|
10 |
+
"pad_token": "[PAD]",
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": true,
|
15 |
+
"tokenizer_class": "BertTokenizer",
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.246376811594203,
|
5 |
+
"global_step": 4500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.81,
|
12 |
+
"learning_rate": 4.597423510466989e-05,
|
13 |
+
"loss": 0.2451,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.61,
|
18 |
+
"learning_rate": 4.194847020933977e-05,
|
19 |
+
"loss": 0.1689,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.42,
|
24 |
+
"learning_rate": 3.7922705314009665e-05,
|
25 |
+
"loss": 0.1414,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 3.22,
|
30 |
+
"learning_rate": 3.389694041867955e-05,
|
31 |
+
"loss": 0.1189,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 4.03,
|
36 |
+
"learning_rate": 2.9871175523349438e-05,
|
37 |
+
"loss": 0.0985,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 4.83,
|
42 |
+
"learning_rate": 2.5845410628019323e-05,
|
43 |
+
"loss": 0.0748,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 5.64,
|
48 |
+
"learning_rate": 2.1819645732689212e-05,
|
49 |
+
"loss": 0.0597,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 6.44,
|
54 |
+
"learning_rate": 1.77938808373591e-05,
|
55 |
+
"loss": 0.0492,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 7.25,
|
60 |
+
"learning_rate": 1.3768115942028985e-05,
|
61 |
+
"loss": 0.0405,
|
62 |
+
"step": 4500
|
63 |
+
}
|
64 |
+
],
|
65 |
+
"max_steps": 6210,
|
66 |
+
"num_train_epochs": 10,
|
67 |
+
"total_flos": 1.1638379847364272e+16,
|
68 |
+
"trial_name": null,
|
69 |
+
"trial_params": null
|
70 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f1eed92dcb7bd80c598326878cb384bf0a109bb94ecbcabc6422d1450fb342b
|
3 |
+
size 3439
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|