Training in progress, step 500
Browse files
config.json
CHANGED
@@ -1,41 +1,41 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
-
"activation": "gelu",
|
4 |
-
"architectures": [
|
5 |
-
"DistilBertForSequenceClassification"
|
6 |
-
],
|
7 |
-
"attention_dropout": 0.1,
|
8 |
-
"dim": 768,
|
9 |
-
"dropout": 0.1,
|
10 |
-
"hidden_dim": 3072,
|
11 |
-
"id2label": {
|
12 |
-
"0": "LABEL_0",
|
13 |
-
"1": "LABEL_1",
|
14 |
-
"2": "LABEL_2",
|
15 |
-
"3": "LABEL_3",
|
16 |
-
"4": "LABEL_4",
|
17 |
-
"5": "LABEL_5"
|
18 |
-
},
|
19 |
-
"initializer_range": 0.02,
|
20 |
-
"label2id": {
|
21 |
-
"LABEL_0": 0,
|
22 |
-
"LABEL_1": 1,
|
23 |
-
"LABEL_2": 2,
|
24 |
-
"LABEL_3": 3,
|
25 |
-
"LABEL_4": 4,
|
26 |
-
"LABEL_5": 5
|
27 |
-
},
|
28 |
-
"max_position_embeddings": 512,
|
29 |
-
"model_type": "distilbert",
|
30 |
-
"n_heads": 12,
|
31 |
-
"n_layers": 6,
|
32 |
-
"pad_token_id": 0,
|
33 |
-
"problem_type": "single_label_classification",
|
34 |
-
"qa_dropout": 0.1,
|
35 |
-
"seq_classif_dropout": 0.2,
|
36 |
-
"sinusoidal_pos_embds": false,
|
37 |
-
"tie_weights_": true,
|
38 |
-
"torch_dtype": "float32",
|
39 |
-
"transformers_version": "4.
|
40 |
-
"vocab_size": 30522
|
41 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4",
|
17 |
+
"5": "LABEL_5"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"label2id": {
|
21 |
+
"LABEL_0": 0,
|
22 |
+
"LABEL_1": 1,
|
23 |
+
"LABEL_2": 2,
|
24 |
+
"LABEL_3": 3,
|
25 |
+
"LABEL_4": 4,
|
26 |
+
"LABEL_5": 5
|
27 |
+
},
|
28 |
+
"max_position_embeddings": 512,
|
29 |
+
"model_type": "distilbert",
|
30 |
+
"n_heads": 12,
|
31 |
+
"n_layers": 6,
|
32 |
+
"pad_token_id": 0,
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"qa_dropout": 0.1,
|
35 |
+
"seq_classif_dropout": 0.2,
|
36 |
+
"sinusoidal_pos_embds": false,
|
37 |
+
"tie_weights_": true,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.41.0",
|
40 |
+
"vocab_size": 30522
|
41 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f2fcf72c6ebd2dd618f329b5d38a22c0f9421122b4bbcc446630c5975a228d4
|
3 |
+
size 267844872
|
runs/May19_12-31-40_POSEIDON/events.out.tfevents.1716111141.POSEIDON.21532.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46cdf62919d515479a2db977d36d55aa60e149c0dca8d8a0608371351c6b31d2
|
3 |
+
size 4980
|
runs/May19_12-43-24_POSEIDON/events.out.tfevents.1716111813.POSEIDON.20384.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b105acf476770c49015a2db8f6932ffd657d3362035bd48e97e049a0f8650d35
|
3 |
+
size 5771
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
-
{
|
2 |
-
"cls_token": "[CLS]",
|
3 |
-
"mask_token": "[MASK]",
|
4 |
-
"pad_token": "[PAD]",
|
5 |
-
"sep_token": "[SEP]",
|
6 |
-
"unk_token": "[UNK]"
|
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
CHANGED
@@ -1,14 +1,55 @@
|
|
1 |
-
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
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": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
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 sha256:9da63253df73e8d42098ce3c8b650e09661897ffd8f5acd0d60fe5a1aac8bf0e
|
3 |
+
size 5112
|