End of training
Browse files- README.md +95 -0
- config.json +62 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: allenai/longformer-base-4096
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: framing_classification_longformer_30_augmented_multi
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# framing_classification_longformer_30_augmented_multi
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.3585
|
24 |
+
- Accuracy: 0.6170
|
25 |
+
- F1: 0.1988
|
26 |
+
- Precision: 0.2058
|
27 |
+
- Recall: 0.2476
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 2e-05
|
47 |
+
- train_batch_size: 1
|
48 |
+
- eval_batch_size: 1
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 30
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss | Precision | Recall |
|
57 |
+
|:-------------:|:-----:|:------:|:--------:|:------:|:---------------:|:---------:|:------:|
|
58 |
+
| 1.282 | 1.0 | 7043 | 0.5773 | 0.1691 | 1.5099 | 0.1473 | 0.2326 |
|
59 |
+
| 2.5135 | 2.0 | 14086 | 0.5455 | 0.1008 | 2.2716 | 0.0779 | 0.1429 |
|
60 |
+
| 2.384 | 3.0 | 21129 | 0.5455 | 0.1008 | 2.6195 | 0.0779 | 0.1429 |
|
61 |
+
| 2.5536 | 4.0 | 28172 | 0.5455 | 0.1008 | 2.3823 | 0.0779 | 0.1429 |
|
62 |
+
| 2.3549 | 5.0 | 35215 | 0.5455 | 0.1008 | 2.3964 | 0.0779 | 0.1429 |
|
63 |
+
| 2.3181 | 6.0 | 42258 | 0.5455 | 0.1008 | 2.4343 | 0.0779 | 0.1429 |
|
64 |
+
| 2.4398 | 7.0 | 49301 | 0.5455 | 0.1008 | 2.4609 | 0.0779 | 0.1429 |
|
65 |
+
| 2.3715 | 8.0 | 56344 | 0.5455 | 0.1008 | 2.4317 | 0.0779 | 0.1429 |
|
66 |
+
| 2.5554 | 9.0 | 63387 | 0.5455 | 0.1008 | 2.3966 | 0.0779 | 0.1429 |
|
67 |
+
| 1.3177 | 10.0 | 70430 | 0.5830 | 0.1707 | 1.4776 | 0.1472 | 0.2352 |
|
68 |
+
| 1.3928 | 11.0 | 77473 | 0.6159 | 0.1750 | 1.5114 | 0.1470 | 0.2348 |
|
69 |
+
| 1.5202 | 12.0 | 84516 | 0.6159 | 0.1746 | 1.4525 | 0.1465 | 0.2337 |
|
70 |
+
| 1.4013 | 13.0 | 91559 | 0.5909 | 0.1625 | 1.4524 | 0.1399 | 0.2113 |
|
71 |
+
| 1.4087 | 14.0 | 98602 | 0.5955 | 0.1736 | 1.4572 | 0.1484 | 0.2385 |
|
72 |
+
| 2.3755 | 15.0 | 105645 | 0.5727 | 0.1420 | 1.9328 | 0.1193 | 0.1771 |
|
73 |
+
| 2.2211 | 16.0 | 112688 | 0.5943 | 0.1596 | 1.7707 | 0.1317 | 0.2043 |
|
74 |
+
| 2.0359 | 17.0 | 119731 | 0.5830 | 0.1506 | 1.9399 | 0.1248 | 0.19 |
|
75 |
+
| 1.7553 | 18.0 | 126774 | 0.5920 | 0.1580 | 1.8171 | 0.1306 | 0.2026 |
|
76 |
+
| 1.4321 | 19.0 | 133817 | 0.6125 | 0.1733 | 1.4162 | 0.1462 | 0.2317 |
|
77 |
+
| 1.4545 | 20.0 | 140860 | 0.6068 | 0.1728 | 1.4446 | 0.1466 | 0.2324 |
|
78 |
+
| 1.3939 | 21.0 | 147903 | 0.6148 | 0.1747 | 1.4451 | 0.1473 | 0.2345 |
|
79 |
+
| 1.4333 | 22.0 | 154946 | 0.5841 | 0.1702 | 1.4462 | 0.1474 | 0.2333 |
|
80 |
+
| 1.3013 | 23.0 | 161989 | 0.6170 | 0.1757 | 1.4099 | 0.1480 | 0.2363 |
|
81 |
+
| 1.397 | 24.0 | 169032 | 0.6170 | 0.1766 | 1.4181 | 0.1489 | 0.2385 |
|
82 |
+
| 1.4752 | 25.0 | 176075 | 0.6136 | 0.1727 | 1.3997 | 0.1444 | 0.2297 |
|
83 |
+
| 1.372 | 26.0 | 183118 | 1.4134 | 0.6170 | 0.1748 | 0.1471 | 0.2340 |
|
84 |
+
| 1.4563 | 27.0 | 190161 | 1.3920 | 0.6205 | 0.1775 | 0.1492 | 0.2394 |
|
85 |
+
| 1.3727 | 28.0 | 197204 | 1.3763 | 0.6125 | 0.1737 | 0.1465 | 0.2328 |
|
86 |
+
| 1.4587 | 29.0 | 204247 | 1.3585 | 0.6170 | 0.1988 | 0.2058 | 0.2476 |
|
87 |
+
| 1.2723 | 30.0 | 211290 | 1.3586 | 0.6136 | 0.1973 | 0.1967 | 0.2455 |
|
88 |
+
|
89 |
+
|
90 |
+
### Framework versions
|
91 |
+
|
92 |
+
- Transformers 4.32.0.dev0
|
93 |
+
- Pytorch 2.0.1
|
94 |
+
- Datasets 2.14.4
|
95 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allenai/longformer-base-4096",
|
3 |
+
"architectures": [
|
4 |
+
"LongformerForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_mode": "longformer",
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"attention_window": [
|
9 |
+
512,
|
10 |
+
512,
|
11 |
+
512,
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512
|
21 |
+
],
|
22 |
+
"bos_token_id": 0,
|
23 |
+
"eos_token_id": 2,
|
24 |
+
"gradient_checkpointing": false,
|
25 |
+
"hidden_act": "gelu",
|
26 |
+
"hidden_dropout_prob": 0.1,
|
27 |
+
"hidden_size": 768,
|
28 |
+
"id2label": {
|
29 |
+
"0": "effects",
|
30 |
+
"1": "politics",
|
31 |
+
"2": "social progress",
|
32 |
+
"3": "economic competitiveness",
|
33 |
+
"4": "morality",
|
34 |
+
"5": "other",
|
35 |
+
"6": "science"
|
36 |
+
},
|
37 |
+
"ignore_attention_mask": false,
|
38 |
+
"initializer_range": 0.02,
|
39 |
+
"intermediate_size": 3072,
|
40 |
+
"label2id": {
|
41 |
+
"economic competitiveness": 3,
|
42 |
+
"effects": 0,
|
43 |
+
"morality": 4,
|
44 |
+
"other": 5,
|
45 |
+
"politics": 1,
|
46 |
+
"science": 6,
|
47 |
+
"social progress": 2
|
48 |
+
},
|
49 |
+
"layer_norm_eps": 1e-05,
|
50 |
+
"max_position_embeddings": 4098,
|
51 |
+
"model_type": "longformer",
|
52 |
+
"num_attention_heads": 12,
|
53 |
+
"num_hidden_layers": 12,
|
54 |
+
"onnx_export": false,
|
55 |
+
"pad_token_id": 1,
|
56 |
+
"problem_type": "single_label_classification",
|
57 |
+
"sep_token_id": 2,
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.32.0.dev0",
|
60 |
+
"type_vocab_size": 1,
|
61 |
+
"vocab_size": 50265
|
62 |
+
}
|
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 sha256:9f505f4caa191c06b7b3d1f337fa852824b00c478fc146291d648a568c144d08
|
3 |
+
size 594754641
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "<s>",
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"errors": "replace",
|
8 |
+
"mask_token": "<mask>",
|
9 |
+
"max_length": 4096,
|
10 |
+
"model_max_length": 4096,
|
11 |
+
"pad_token": "<pad>",
|
12 |
+
"sep_token": "</s>",
|
13 |
+
"tokenizer_class": "LongformerTokenizer",
|
14 |
+
"trim_offsets": true,
|
15 |
+
"unk_token": "<unk>"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e2b59c7d12e1cbc96bbedfd959046b60e82eec51ebe39ad9ddef1ebf84f1c0a
|
3 |
+
size 4155
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|