Training in progress, step 500
Browse files- config.json +45 -0
- model.safetensors +3 -0
- runs/Jul16_11-16-24_d4c6fdd86b07/events.out.tfevents.1721128592.d4c6fdd86b07.2062.0 +3 -0
- runs/Jul16_11-24-43_d4c6fdd86b07/events.out.tfevents.1721129097.d4c6fdd86b07.2062.1 +3 -0
- runs/Jul16_11-26-11_d4c6fdd86b07/events.out.tfevents.1721129177.d4c6fdd86b07.2062.2 +3 -0
- runs/Jul16_11-27-24_d4c6fdd86b07/events.out.tfevents.1721129250.d4c6fdd86b07.2062.3 +3 -0
- runs/Jul16_12-03-50_d4c6fdd86b07/events.out.tfevents.1721131453.d4c6fdd86b07.2062.4 +3 -0
- runs/Jul16_12-13-28_d4c6fdd86b07/events.out.tfevents.1721132017.d4c6fdd86b07.2062.5 +3 -0
- runs/Jul16_12-17-39_d4c6fdd86b07/events.out.tfevents.1721132263.d4c6fdd86b07.2062.6 +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased-finetuned-sst-2-english",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"finetuning_task": "sst-2",
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"label2id": {
|
23 |
+
"LABEL_0": 0,
|
24 |
+
"LABEL_1": 1,
|
25 |
+
"LABEL_2": 2,
|
26 |
+
"LABEL_3": 3,
|
27 |
+
"LABEL_4": 4,
|
28 |
+
"LABEL_5": 5,
|
29 |
+
"LABEL_6": 6
|
30 |
+
},
|
31 |
+
"max_position_embeddings": 512,
|
32 |
+
"model_type": "distilbert",
|
33 |
+
"n_heads": 12,
|
34 |
+
"n_layers": 6,
|
35 |
+
"output_past": true,
|
36 |
+
"pad_token_id": 0,
|
37 |
+
"problem_type": "single_label_classification",
|
38 |
+
"qa_dropout": 0.1,
|
39 |
+
"seq_classif_dropout": 0.2,
|
40 |
+
"sinusoidal_pos_embds": false,
|
41 |
+
"tie_weights_": true,
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.41.2",
|
44 |
+
"vocab_size": 30522
|
45 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:847de45c52df1f15941307e9f2a952bed53dd863ce0de95caeef9a663705e6f3
|
3 |
+
size 267847948
|
runs/Jul16_11-16-24_d4c6fdd86b07/events.out.tfevents.1721128592.d4c6fdd86b07.2062.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ef334546948acda9dc0c4c818b3093b0cc3b2de9a081a0787cff91fcca7919e
|
3 |
+
size 4986
|
runs/Jul16_11-24-43_d4c6fdd86b07/events.out.tfevents.1721129097.d4c6fdd86b07.2062.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2cf93f844913b19d4200f0be7bf6445a61c7a4810191cdbf2c0b76448ef094a
|
3 |
+
size 9884
|
runs/Jul16_11-26-11_d4c6fdd86b07/events.out.tfevents.1721129177.d4c6fdd86b07.2062.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0930acfde05f31bc67d68ff0f4f354a2c28089f0d0e41ddebe539a6fb06f10b
|
3 |
+
size 4986
|
runs/Jul16_11-27-24_d4c6fdd86b07/events.out.tfevents.1721129250.d4c6fdd86b07.2062.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34999d1778185483a605a74a1c62f7ce8761c2e99e81440d272789785a401a77
|
3 |
+
size 4986
|
runs/Jul16_12-03-50_d4c6fdd86b07/events.out.tfevents.1721131453.d4c6fdd86b07.2062.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a274689cbe5179052e08bb35dd0c5b385b349171e130d4eeae34a7a58925d69b
|
3 |
+
size 5758
|
runs/Jul16_12-13-28_d4c6fdd86b07/events.out.tfevents.1721132017.d4c6fdd86b07.2062.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69424c4280b7dc4c112edc3d507a0b917e4e0c15b815b435b96997edb43012bc
|
3 |
+
size 5840
|
runs/Jul16_12-17-39_d4c6fdd86b07/events.out.tfevents.1721132263.d4c6fdd86b07.2062.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f9f2b2d0e0c24e568e2e4f166e3ae831fd8b4f4adb9a0d627bd4782ad5a7d2d
|
3 |
+
size 5838
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "DistilBertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13aa017268484e0639d829ede2f701b55973dc138293c2c43c524415ca579c1c
|
3 |
+
size 5112
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|