aristotletan
commited on
Commit
•
871b020
1
Parent(s):
11614fb
add model
Browse files- .gitignore +1 -0
- README.md +76 -0
- config.json +76 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Aug02_09-45-12_d7869f704454/1627897592.6284308/events.out.tfevents.1627897592.d7869f704454.65.1 +3 -0
- runs/Aug02_09-45-12_d7869f704454/events.out.tfevents.1627897592.d7869f704454.65.0 +3 -0
- runs/Aug02_09-46-58_d7869f704454/1627897646.4758368/events.out.tfevents.1627897646.d7869f704454.256.1 +3 -0
- runs/Aug02_09-46-58_d7869f704454/events.out.tfevents.1627897646.d7869f704454.256.0 +3 -0
- runs/Aug02_09-46-58_d7869f704454/events.out.tfevents.1627897755.d7869f704454.256.2 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- scim
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model_index:
|
10 |
+
- name: roberta-base-finetuned-sst2
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Text Classification
|
14 |
+
type: text-classification
|
15 |
+
dataset:
|
16 |
+
name: scim
|
17 |
+
type: scim
|
18 |
+
args: eod
|
19 |
+
metric:
|
20 |
+
name: Accuracy
|
21 |
+
type: accuracy
|
22 |
+
value: 0.9111111111111111
|
23 |
+
---
|
24 |
+
|
25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
26 |
+
should probably proofread and complete it, then remove this comment. -->
|
27 |
+
|
28 |
+
# roberta-base-finetuned-sst2
|
29 |
+
|
30 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the scim dataset.
|
31 |
+
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 0.4632
|
33 |
+
- Accuracy: 0.9111
|
34 |
+
|
35 |
+
## Model description
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Intended uses & limitations
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training and evaluation data
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training procedure
|
48 |
+
|
49 |
+
### Training hyperparameters
|
50 |
+
|
51 |
+
The following hyperparameters were used during training:
|
52 |
+
- learning_rate: 2e-05
|
53 |
+
- train_batch_size: 4
|
54 |
+
- eval_batch_size: 4
|
55 |
+
- seed: 42
|
56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
+
- lr_scheduler_type: linear
|
58 |
+
- num_epochs: 5
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
63 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
64 |
+
| No log | 1.0 | 90 | 2.0273 | 0.6667 |
|
65 |
+
| No log | 2.0 | 180 | 0.8802 | 0.8556 |
|
66 |
+
| No log | 3.0 | 270 | 0.5908 | 0.8889 |
|
67 |
+
| No log | 4.0 | 360 | 0.4632 | 0.9111 |
|
68 |
+
| No log | 5.0 | 450 | 0.4294 | 0.9111 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.9.1
|
74 |
+
- Pytorch 1.9.0+cu102
|
75 |
+
- Datasets 1.11.0
|
76 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "breach of obligations",
|
15 |
+
"1": "invalidity",
|
16 |
+
"10": "insolvency",
|
17 |
+
"11": "event or events",
|
18 |
+
"12": "repudiation",
|
19 |
+
"13": "judgement",
|
20 |
+
"14": "nationalisation",
|
21 |
+
"15": "others",
|
22 |
+
"16": "legal proceedings",
|
23 |
+
"17": "analogous event",
|
24 |
+
"18": "assets",
|
25 |
+
"19": "jeopardy",
|
26 |
+
"2": "appointment of receiver",
|
27 |
+
"20": "creditor control",
|
28 |
+
"21": "disposal",
|
29 |
+
"3": "composition and arrangement",
|
30 |
+
"4": "non payment",
|
31 |
+
"5": "revocation of license",
|
32 |
+
"6": "cessation of business",
|
33 |
+
"7": "cross default",
|
34 |
+
"8": "winding up",
|
35 |
+
"9": "misrepresentation"
|
36 |
+
},
|
37 |
+
"initializer_range": 0.02,
|
38 |
+
"intermediate_size": 3072,
|
39 |
+
"label2id": {
|
40 |
+
"analogous event": "17",
|
41 |
+
"appointment of receiver": "2",
|
42 |
+
"assets": "18",
|
43 |
+
"breach of obligations": "0",
|
44 |
+
"cessation of business": "6",
|
45 |
+
"composition and arrangement": "3",
|
46 |
+
"creditor control": "20",
|
47 |
+
"cross default": "7",
|
48 |
+
"disposal": "21",
|
49 |
+
"event or events": "11",
|
50 |
+
"insolvency": "10",
|
51 |
+
"invalidity": "1",
|
52 |
+
"jeopardy": "19",
|
53 |
+
"judgement": "13",
|
54 |
+
"legal proceedings": "16",
|
55 |
+
"misrepresentation": "9",
|
56 |
+
"nationalisation": "14",
|
57 |
+
"non payment": "4",
|
58 |
+
"others": "15",
|
59 |
+
"repudiation": "12",
|
60 |
+
"revocation of license": "5",
|
61 |
+
"winding up": "8"
|
62 |
+
},
|
63 |
+
"layer_norm_eps": 1e-05,
|
64 |
+
"max_position_embeddings": 514,
|
65 |
+
"model_type": "roberta",
|
66 |
+
"num_attention_heads": 12,
|
67 |
+
"num_hidden_layers": 12,
|
68 |
+
"pad_token_id": 1,
|
69 |
+
"position_embedding_type": "absolute",
|
70 |
+
"problem_type": "single_label_classification",
|
71 |
+
"torch_dtype": "float32",
|
72 |
+
"transformers_version": "4.9.1",
|
73 |
+
"type_vocab_size": 1,
|
74 |
+
"use_cache": true,
|
75 |
+
"vocab_size": 50265
|
76 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a60823fcf11acec19d8e66c9d3a0a5690036a45d48ac66c9f3ced9a98708582b
|
3 |
+
size 498735597
|
runs/Aug02_09-45-12_d7869f704454/1627897592.6284308/events.out.tfevents.1627897592.d7869f704454.65.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73fa4e208a185bc5c56b3a3d8b56f50958380c4ce9d2f6a37b41e4d225aecf0c
|
3 |
+
size 4198
|
runs/Aug02_09-45-12_d7869f704454/events.out.tfevents.1627897592.d7869f704454.65.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a364b9987bcba379c530a6c41ecb712f37a84d1ccb95cbf77b75118efdbe140d
|
3 |
+
size 4241
|
runs/Aug02_09-46-58_d7869f704454/1627897646.4758368/events.out.tfevents.1627897646.d7869f704454.256.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55354c1ec666f4cf6fd4c52bc49a270a59bc7f7da20dea04397164a787cb0369
|
3 |
+
size 4198
|
runs/Aug02_09-46-58_d7869f704454/events.out.tfevents.1627897646.d7869f704454.256.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de7e303d5844d127b9e9bcc800b398293ccc1f88bc8f402fe36f60d34bee91b8
|
3 |
+
size 6186
|
runs/Aug02_09-46-58_d7869f704454/events.out.tfevents.1627897755.d7869f704454.256.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb3f898f5cac3434cf53424c933dcc6e084715e1a471317618d766d737097623
|
3 |
+
size 363
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d88b0ea376ce215fdc365bc0d4230e604178c1eaf568c3c6625337fbefde93f7
|
3 |
+
size 2671
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|