Training in progress, epoch 1
Browse files- config.json +23 -14
- model.safetensors +2 -2
- runs/Mar20_23-18-22_a7cbf6b28344/events.out.tfevents.1710976706.a7cbf6b28344.5071.0 +3 -0
- special_tokens_map.json +49 -5
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +22 -15
- training_args.bin +2 -2
config.json
CHANGED
@@ -1,20 +1,27 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"attention_probs_dropout_prob": 0
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
"id2label": {
|
12 |
"0": "LABEL_0",
|
13 |
"1": "LABEL_1",
|
14 |
"2": "LABEL_2"
|
15 |
},
|
16 |
"initializer_range": 0.02,
|
17 |
-
"
|
|
|
18 |
"label2id": {
|
19 |
"LABEL_0": 0,
|
20 |
"LABEL_1": 1,
|
@@ -22,15 +29,17 @@
|
|
22 |
},
|
23 |
"layer_norm_eps": 1e-12,
|
24 |
"max_position_embeddings": 512,
|
25 |
-
"model_type": "
|
26 |
-
"
|
27 |
-
"
|
|
|
|
|
|
|
28 |
"pad_token_id": 0,
|
29 |
"position_embedding_type": "absolute",
|
30 |
"problem_type": "single_label_classification",
|
31 |
"torch_dtype": "float32",
|
32 |
-
"transformers_version": "4.
|
33 |
"type_vocab_size": 2,
|
34 |
-
"
|
35 |
-
"vocab_size": 30522
|
36 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Alireza1044/albert-base-v2-mnli",
|
3 |
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
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 |
+
"finetuning_task": "mnli",
|
13 |
+
"gap_size": 0,
|
14 |
+
"hidden_act": "gelu_new",
|
15 |
+
"hidden_dropout_prob": 0,
|
16 |
+
"hidden_size": 768,
|
17 |
"id2label": {
|
18 |
"0": "LABEL_0",
|
19 |
"1": "LABEL_1",
|
20 |
"2": "LABEL_2"
|
21 |
},
|
22 |
"initializer_range": 0.02,
|
23 |
+
"inner_group_num": 1,
|
24 |
+
"intermediate_size": 3072,
|
25 |
"label2id": {
|
26 |
"LABEL_0": 0,
|
27 |
"LABEL_1": 1,
|
|
|
29 |
},
|
30 |
"layer_norm_eps": 1e-12,
|
31 |
"max_position_embeddings": 512,
|
32 |
+
"model_type": "albert",
|
33 |
+
"net_structure_type": 0,
|
34 |
+
"num_attention_heads": 12,
|
35 |
+
"num_hidden_groups": 1,
|
36 |
+
"num_hidden_layers": 12,
|
37 |
+
"num_memory_blocks": 0,
|
38 |
"pad_token_id": 0,
|
39 |
"position_embedding_type": "absolute",
|
40 |
"problem_type": "single_label_classification",
|
41 |
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.38.2",
|
43 |
"type_vocab_size": 2,
|
44 |
+
"vocab_size": 30000
|
|
|
45 |
}
|
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 sha256:3c4e141bc2641b3e31c3e03688bd2743485d4d2eabd136669537b5fc26f6f1e6
|
3 |
+
size 46746988
|
runs/Mar20_23-18-22_a7cbf6b28344/events.out.tfevents.1710976706.a7cbf6b28344.5071.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c62da7a87bdde1546c6e7e1f48b5638cec7acf67e673db6927920d89344919f
|
3 |
+
size 5363
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,51 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "[CLS]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "[SEP]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "[MASK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "[SEP]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
}
|
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,
|
@@ -32,26 +32,33 @@
|
|
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_basic_tokenize": true,
|
47 |
"do_lower_case": true,
|
|
|
|
|
48 |
"mask_token": "[MASK]",
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
|
|
|
|
|
|
|
|
52 |
"sep_token": "[SEP]",
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"
|
56 |
-
"
|
|
|
57 |
}
|
|
|
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 |
+
"max_length": 128,
|
52 |
+
"model_max_length": 512,
|
53 |
+
"pad_to_multiple_of": null,
|
54 |
+
"pad_token": "<pad>",
|
55 |
+
"pad_token_type_id": 0,
|
56 |
+
"padding_side": "right",
|
57 |
+
"remove_space": true,
|
58 |
"sep_token": "[SEP]",
|
59 |
+
"stride": 0,
|
60 |
+
"tokenizer_class": "AlbertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "<unk>"
|
64 |
}
|
training_args.bin
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:e04a4886b853338a004294eb9a51a10941e1dcb9103f983686261d0ad6826e96
|
3 |
+
size 4920
|