Training in progress, epoch 1
Browse files- config.json +14 -7
- model.safetensors +2 -2
- runs/Sep26_18-28-43_43eefb9683cd/events.out.tfevents.1727375324.43eefb9683cd.634.0 +3 -0
- special_tokens_map.json +11 -3
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -13
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,11 +1,15 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"
|
8 |
-
"
|
|
|
|
|
|
|
|
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
@@ -1623,6 +1627,7 @@
|
|
1623 |
"1610": "O"
|
1624 |
},
|
1625 |
"initializer_range": 0.02,
|
|
|
1626 |
"intermediate_size": 3072,
|
1627 |
"label2id": {
|
1628 |
"B-AIDS": 0,
|
@@ -3239,14 +3244,16 @@
|
|
3239 |
},
|
3240 |
"layer_norm_eps": 1e-12,
|
3241 |
"max_position_embeddings": 512,
|
3242 |
-
"model_type": "
|
|
|
3243 |
"num_attention_heads": 12,
|
|
|
3244 |
"num_hidden_layers": 12,
|
|
|
3245 |
"pad_token_id": 0,
|
3246 |
"position_embedding_type": "absolute",
|
3247 |
"torch_dtype": "float32",
|
3248 |
"transformers_version": "4.44.2",
|
3249 |
"type_vocab_size": 2,
|
3250 |
-
"
|
3251 |
-
"vocab_size": 28996
|
3252 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "albert/albert-base-v1",
|
3 |
"architectures": [
|
4 |
+
"AlbertForTokenClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
"hidden_act": "gelu",
|
14 |
"hidden_dropout_prob": 0.1,
|
15 |
"hidden_size": 768,
|
|
|
1627 |
"1610": "O"
|
1628 |
},
|
1629 |
"initializer_range": 0.02,
|
1630 |
+
"inner_group_num": 1,
|
1631 |
"intermediate_size": 3072,
|
1632 |
"label2id": {
|
1633 |
"B-AIDS": 0,
|
|
|
3244 |
},
|
3245 |
"layer_norm_eps": 1e-12,
|
3246 |
"max_position_embeddings": 512,
|
3247 |
+
"model_type": "albert",
|
3248 |
+
"net_structure_type": 0,
|
3249 |
"num_attention_heads": 12,
|
3250 |
+
"num_hidden_groups": 1,
|
3251 |
"num_hidden_layers": 12,
|
3252 |
+
"num_memory_blocks": 0,
|
3253 |
"pad_token_id": 0,
|
3254 |
"position_embedding_type": "absolute",
|
3255 |
"torch_dtype": "float32",
|
3256 |
"transformers_version": "4.44.2",
|
3257 |
"type_vocab_size": 2,
|
3258 |
+
"vocab_size": 30000
|
|
|
3259 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f13bfceb5030ffb31a7acb964b3077418a82c10bde2ea549874a6abddd9c3ce5
|
3 |
+
size 49330652
|
runs/Sep26_18-28-43_43eefb9683cd/events.out.tfevents.1727375324.43eefb9683cd.634.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a4da56b93c8072828098a019337418f8c17f54acbb4fc8ad34f54e09e0b268c
|
3 |
+
size 102450
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,15 @@
|
|
1 |
{
|
|
|
2 |
"cls_token": "[CLS]",
|
3 |
-
"
|
4 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"sep_token": "[SEP]",
|
6 |
-
"unk_token": "
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "[MASK]",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
"sep_token": "[SEP]",
|
14 |
+
"unk_token": "<unk>"
|
15 |
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
|
3 |
+
size 760289
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,22 +1,22 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
"content": "[CLS]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -24,7 +24,7 @@
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
"content": "[SEP]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
@@ -32,24 +32,26 @@
|
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
"content": "[MASK]",
|
37 |
-
"lstrip":
|
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":
|
|
|
|
|
47 |
"mask_token": "[MASK]",
|
48 |
"model_max_length": 512,
|
49 |
-
"pad_token": "
|
|
|
50 |
"sep_token": "[SEP]",
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"tokenizer_class": "BertTokenizer",
|
54 |
-
"unk_token": "[UNK]"
|
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 |
+
"1": {
|
12 |
+
"content": "<unk>",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"2": {
|
20 |
"content": "[CLS]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"3": {
|
28 |
"content": "[SEP]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
|
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"4": {
|
36 |
"content": "[MASK]",
|
37 |
+
"lstrip": true,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
44 |
+
"bos_token": "[CLS]",
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
"cls_token": "[CLS]",
|
47 |
+
"do_lower_case": true,
|
48 |
+
"eos_token": "[SEP]",
|
49 |
+
"keep_accents": false,
|
50 |
"mask_token": "[MASK]",
|
51 |
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"remove_space": true,
|
54 |
"sep_token": "[SEP]",
|
55 |
+
"tokenizer_class": "AlbertTokenizer",
|
56 |
+
"unk_token": "<unk>"
|
|
|
|
|
57 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ca6688544e9050988580ec3aae96bbe01eef449ad95aaf815964d847381fce2
|
3 |
size 5176
|