Training in progress, step 500
Browse files- ch3.ipynb +39 -0
- config.json +41 -0
- model.safetensors +3 -0
- runs/Nov09_11-30-35_DESKTOP-13CQUUB/events.out.tfevents.1699501390.DESKTOP-13CQUUB.11624.0 +3 -0
- runs/Nov09_11-30-35_DESKTOP-13CQUUB/events.out.tfevents.1699501636.DESKTOP-13CQUUB.11624.1 +3 -0
- runs/Nov09_11-52-13_DESKTOP-13CQUUB/events.out.tfevents.1699501935.DESKTOP-13CQUUB.11624.2 +3 -0
- runs/Nov09_12-11-37_DESKTOP-13CQUUB/events.out.tfevents.1699503098.DESKTOP-13CQUUB.4016.0 +3 -0
- runs/Nov09_12-21-18_DESKTOP-13CQUUB/events.out.tfevents.1699503678.DESKTOP-13CQUUB.22876.0 +3 -0
- runs/Nov09_12-22-46_DESKTOP-13CQUUB/events.out.tfevents.1699503767.DESKTOP-13CQUUB.22876.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
ch3.ipynb
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": null,
|
6 |
+
"id": "initial_id",
|
7 |
+
"metadata": {
|
8 |
+
"collapsed": true
|
9 |
+
},
|
10 |
+
"outputs": [],
|
11 |
+
"source": [
|
12 |
+
"from transformers import AutoTokenizer\n",
|
13 |
+
"from bertviz.transformer_neuron_view import BertModel\n",
|
14 |
+
"from bert"
|
15 |
+
]
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"metadata": {
|
19 |
+
"kernelspec": {
|
20 |
+
"display_name": "Python 3",
|
21 |
+
"language": "python",
|
22 |
+
"name": "python3"
|
23 |
+
},
|
24 |
+
"language_info": {
|
25 |
+
"codemirror_mode": {
|
26 |
+
"name": "ipython",
|
27 |
+
"version": 2
|
28 |
+
},
|
29 |
+
"file_extension": ".py",
|
30 |
+
"mimetype": "text/x-python",
|
31 |
+
"name": "python",
|
32 |
+
"nbconvert_exporter": "python",
|
33 |
+
"pygments_lexer": "ipython2",
|
34 |
+
"version": "2.7.6"
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"nbformat": 4,
|
38 |
+
"nbformat_minor": 5
|
39 |
+
}
|
config.json
ADDED
@@ -0,0 +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": "4.35.0",
|
40 |
+
"vocab_size": 30522
|
41 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ceef46a215abb377f986e44002bbb6de026f2906f5f770fc520767891c6beeb
|
3 |
+
size 267844872
|
runs/Nov09_11-30-35_DESKTOP-13CQUUB/events.out.tfevents.1699501390.DESKTOP-13CQUUB.11624.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50c5dd001dc9a72e3a30e4cc4cf87c0c41572bfbfd91eaf1b2ef195e351c67f1
|
3 |
+
size 4439
|
runs/Nov09_11-30-35_DESKTOP-13CQUUB/events.out.tfevents.1699501636.DESKTOP-13CQUUB.11624.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d8562efc1ee88c27e6872e740998dcdb219753a6a6a45991f6a4f3463895bf4
|
3 |
+
size 4488
|
runs/Nov09_11-52-13_DESKTOP-13CQUUB/events.out.tfevents.1699501935.DESKTOP-13CQUUB.11624.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf85f56af5394a9cee72754641ba03b10d71c5fbe2037ecc9bd2b506bb2feebd
|
3 |
+
size 4857
|
runs/Nov09_12-11-37_DESKTOP-13CQUUB/events.out.tfevents.1699503098.DESKTOP-13CQUUB.4016.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d393d17577464055e580ea32593224058a7e26486c5e682eac67e62cd2f79632
|
3 |
+
size 4439
|
runs/Nov09_12-21-18_DESKTOP-13CQUUB/events.out.tfevents.1699503678.DESKTOP-13CQUUB.22876.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6c5f511a3aaecb3bb366c2640a206b40c40e30cb373205c5c26010fa87d651a
|
3 |
+
size 4439
|
runs/Nov09_12-22-46_DESKTOP-13CQUUB/events.out.tfevents.1699503767.DESKTOP-13CQUUB.22876.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e76436c20fe32122ba33af04b9751b70c3660fc800cd8487abfbb6b503a65d72
|
3 |
+
size 4808
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"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
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2a0907625c58dea3369ad17aa9988ae2457da6fb90f7d09830bfd894f29617c
|
3 |
+
size 4600
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|