Commit ·
268b9be
1
Parent(s): 5b55e28
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +66 -0
- pytorch_model.bin +3 -0
- runs/Aug15_07-35-10_7a42ec2dcebf/events.out.tfevents.1692084918.7a42ec2dcebf.26968.0 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +25 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CamembertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "Brand",
|
| 16 |
+
"1": "Product/Service",
|
| 17 |
+
"2": "Environment",
|
| 18 |
+
"3": "Social&People",
|
| 19 |
+
"4": "Governance",
|
| 20 |
+
"5": "Economics",
|
| 21 |
+
"6": "Political",
|
| 22 |
+
"7": "Dividend",
|
| 23 |
+
"8": "Legal",
|
| 24 |
+
"9": "Investment",
|
| 25 |
+
"10": "M&A",
|
| 26 |
+
"11": "Profit/Loss",
|
| 27 |
+
"12": "Rating",
|
| 28 |
+
"13": "Others",
|
| 29 |
+
"14": "Financing",
|
| 30 |
+
"15": "Technology"
|
| 31 |
+
},
|
| 32 |
+
"initializer_range": 0.02,
|
| 33 |
+
"intermediate_size": 3072,
|
| 34 |
+
"label2id": {
|
| 35 |
+
"Brand": 0,
|
| 36 |
+
"Dividend": 7,
|
| 37 |
+
"Economics": 5,
|
| 38 |
+
"Environment": 2,
|
| 39 |
+
"Financing": 14,
|
| 40 |
+
"Governance": 4,
|
| 41 |
+
"Investment": 9,
|
| 42 |
+
"Legal": 8,
|
| 43 |
+
"M&A": 10,
|
| 44 |
+
"Others": 13,
|
| 45 |
+
"Political": 6,
|
| 46 |
+
"Product/Service": 1,
|
| 47 |
+
"Profit/Loss": 11,
|
| 48 |
+
"Rating": 12,
|
| 49 |
+
"Social&People": 3,
|
| 50 |
+
"Technology": 15
|
| 51 |
+
},
|
| 52 |
+
"layer_norm_eps": 1e-12,
|
| 53 |
+
"max_position_embeddings": 512,
|
| 54 |
+
"model_type": "camembert",
|
| 55 |
+
"num_attention_head": 12,
|
| 56 |
+
"num_attention_heads": 12,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"pad_token_id": 1,
|
| 59 |
+
"position_embedding_type": "absolute",
|
| 60 |
+
"problem_type": "single_label_classification",
|
| 61 |
+
"torch_dtype": "float32",
|
| 62 |
+
"transformers_version": "4.31.0",
|
| 63 |
+
"type_vocab_size": 1,
|
| 64 |
+
"use_cache": true,
|
| 65 |
+
"vocab_size": 25005
|
| 66 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd9aa804e0ea5cab6abd5ae02e2c8e99f8e1b14deed58fd97c9072ffc9f41647
|
| 3 |
+
size 421095857
|
runs/Aug15_07-35-10_7a42ec2dcebf/events.out.tfevents.1692084918.7a42ec2dcebf.26968.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cc52e67d3934a21edb72838560e9ff9b0c836b0426768f22475dfa705bce099
|
| 3 |
+
size 5342
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49c4ba4e495ddf31eb2fdba7fc6aef3c233091d25d35bc9d24694ccf48ae114c
|
| 3 |
+
size 904693
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<s>NOTUSED",
|
| 4 |
+
"</s>NOTUSED",
|
| 5 |
+
"<_>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": "<s>",
|
| 8 |
+
"cls_token": "<s>",
|
| 9 |
+
"eos_token": "</s>",
|
| 10 |
+
"mask_token": {
|
| 11 |
+
"content": "<mask>",
|
| 12 |
+
"lstrip": true,
|
| 13 |
+
"normalized": true,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
"pad_token": "<pad>",
|
| 18 |
+
"sep_token": "</s>",
|
| 19 |
+
"unk_token": "<unk>"
|
| 20 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<s>NOTUSED",
|
| 4 |
+
"</s>NOTUSED",
|
| 5 |
+
"<_>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": "<s>",
|
| 8 |
+
"clean_up_tokenization_spaces": true,
|
| 9 |
+
"cls_token": "<s>",
|
| 10 |
+
"eos_token": "</s>",
|
| 11 |
+
"mask_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "<mask>",
|
| 14 |
+
"lstrip": true,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 20 |
+
"pad_token": "<pad>",
|
| 21 |
+
"sep_token": "</s>",
|
| 22 |
+
"sp_model_kwargs": {},
|
| 23 |
+
"tokenizer_class": "CamembertTokenizer",
|
| 24 |
+
"unk_token": "<unk>"
|
| 25 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aade18328b7205cd9d9bde5bdb11f88e8805c56fa8a045bbe433df77825cb30a
|
| 3 |
+
size 3963
|