End of training
Browse files- README.md +96 -0
- config.json +52 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Mar12_16-19-58_CSE-12B21L-PC10/events.out.tfevents.1710238831.CSE-12B21L-PC10.7648.0 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: frame_classification_longformer_earlystopping_2
|
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 |
+
# frame_classification_longformer_earlystopping_2
|
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: 0.5698
|
24 |
+
- Accuracy: 0.9317
|
25 |
+
- F1: 0.9601
|
26 |
+
- Precision: 0.9346
|
27 |
+
- Recall: 0.9869
|
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: 4
|
48 |
+
- eval_batch_size: 4
|
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 |
+
- mixed_precision_training: Native AMP
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
58 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
59 |
+
| 0.8651 | 1.0 | 1288 | 1.1520 | 0.8323 | 0.9085 | 0.8323 | 1.0 |
|
60 |
+
| 0.7998 | 2.0 | 2576 | 0.6925 | 0.9130 | 0.9495 | 0.9181 | 0.9832 |
|
61 |
+
| 0.6819 | 3.0 | 3864 | 0.4349 | 0.9255 | 0.9560 | 0.9404 | 0.9720 |
|
62 |
+
| 0.7033 | 4.0 | 5152 | 0.5836 | 0.9224 | 0.9547 | 0.9278 | 0.9832 |
|
63 |
+
| 0.757 | 5.0 | 6440 | 0.5795 | 0.9224 | 0.9544 | 0.9339 | 0.9757 |
|
64 |
+
| 0.6963 | 6.0 | 7728 | 0.5488 | 0.9317 | 0.9599 | 0.9393 | 0.9813 |
|
65 |
+
| 0.6656 | 7.0 | 9016 | 0.6232 | 0.9255 | 0.9564 | 0.9311 | 0.9832 |
|
66 |
+
| 0.6957 | 8.0 | 10304 | 0.6441 | 0.9255 | 0.9564 | 0.9311 | 0.9832 |
|
67 |
+
| 0.6852 | 9.0 | 11592 | 0.6009 | 0.9224 | 0.9548 | 0.9263 | 0.9851 |
|
68 |
+
| 0.6846 | 10.0 | 12880 | 0.5947 | 0.9255 | 0.9564 | 0.9311 | 0.9832 |
|
69 |
+
| 0.728 | 11.0 | 14168 | 0.5873 | 0.9224 | 0.9550 | 0.9219 | 0.9907 |
|
70 |
+
| 0.6456 | 12.0 | 15456 | 0.5781 | 0.9332 | 0.9609 | 0.9363 | 0.9869 |
|
71 |
+
| 0.662 | 13.0 | 16744 | 0.5128 | 0.9301 | 0.9588 | 0.9408 | 0.9776 |
|
72 |
+
| 0.6017 | 14.0 | 18032 | 0.6430 | 0.9177 | 0.9514 | 0.9351 | 0.9683 |
|
73 |
+
| 0.7525 | 15.0 | 19320 | 0.5631 | 0.9193 | 0.9522 | 0.9384 | 0.9664 |
|
74 |
+
| 0.6802 | 16.0 | 20608 | 0.5949 | 0.9224 | 0.9544 | 0.9339 | 0.9757 |
|
75 |
+
| 0.6489 | 17.0 | 21896 | 0.6540 | 0.9022 | 0.9416 | 0.9355 | 0.9478 |
|
76 |
+
| 0.707 | 18.0 | 23184 | 0.5921 | 0.9239 | 0.9554 | 0.9325 | 0.9795 |
|
77 |
+
| 0.7158 | 19.0 | 24472 | 0.6170 | 0.9255 | 0.9564 | 0.9311 | 0.9832 |
|
78 |
+
| 0.6264 | 20.0 | 25760 | 0.5303 | 0.9348 | 0.9617 | 0.9395 | 0.9851 |
|
79 |
+
| 0.6667 | 21.0 | 27048 | 0.6288 | 0.9255 | 0.9566 | 0.9281 | 0.9869 |
|
80 |
+
| 0.6648 | 22.0 | 28336 | 0.6579 | 0.9208 | 0.9540 | 0.9232 | 0.9869 |
|
81 |
+
| 0.6204 | 23.0 | 29624 | 0.5716 | 0.9301 | 0.9592 | 0.9330 | 0.9869 |
|
82 |
+
| 0.6693 | 24.0 | 30912 | 0.6138 | 0.9270 | 0.9575 | 0.9282 | 0.9888 |
|
83 |
+
| 0.6555 | 25.0 | 32200 | 0.6369 | 0.9255 | 0.9566 | 0.9281 | 0.9869 |
|
84 |
+
| 0.6446 | 26.0 | 33488 | 0.5609 | 0.9301 | 0.9591 | 0.9345 | 0.9851 |
|
85 |
+
| 0.6675 | 27.0 | 34776 | 0.5622 | 0.9301 | 0.9591 | 0.9361 | 0.9832 |
|
86 |
+
| 0.5946 | 28.0 | 36064 | 0.5740 | 0.9301 | 0.9591 | 0.9345 | 0.9851 |
|
87 |
+
| 0.5707 | 29.0 | 37352 | 0.5661 | 0.9317 | 0.9601 | 0.9346 | 0.9869 |
|
88 |
+
| 0.6703 | 30.0 | 38640 | 0.5698 | 0.9317 | 0.9601 | 0.9346 | 0.9869 |
|
89 |
+
|
90 |
+
|
91 |
+
### Framework versions
|
92 |
+
|
93 |
+
- Transformers 4.38.2
|
94 |
+
- Pytorch 2.2.0+cu121
|
95 |
+
- Datasets 2.18.0
|
96 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "non-effects",
|
30 |
+
"1": "effects"
|
31 |
+
},
|
32 |
+
"ignore_attention_mask": false,
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"intermediate_size": 3072,
|
35 |
+
"label2id": {
|
36 |
+
"effects": 1,
|
37 |
+
"non-effects": 0
|
38 |
+
},
|
39 |
+
"layer_norm_eps": 1e-05,
|
40 |
+
"max_position_embeddings": 4098,
|
41 |
+
"model_type": "longformer",
|
42 |
+
"num_attention_heads": 12,
|
43 |
+
"num_hidden_layers": 12,
|
44 |
+
"onnx_export": false,
|
45 |
+
"pad_token_id": 1,
|
46 |
+
"problem_type": "single_label_classification",
|
47 |
+
"sep_token_id": 2,
|
48 |
+
"torch_dtype": "float32",
|
49 |
+
"transformers_version": "4.38.2",
|
50 |
+
"type_vocab_size": 1,
|
51 |
+
"vocab_size": 50265
|
52 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:262a2663011aeeaacc9f92c4b0e9aaeb71030fa9ddde40edeaf648dde828a3c2
|
3 |
+
size 594678184
|
runs/Mar12_16-19-58_CSE-12B21L-PC10/events.out.tfevents.1710238831.CSE-12B21L-PC10.7648.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8856b5a01c2666e937f24c076e8a90e25091734397a79f7209ff5c225bcdaa47
|
3 |
+
size 36058
|
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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"max_length": 4096,
|
52 |
+
"model_max_length": 4096,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"tokenizer_class": "LongformerTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
+
"unk_token": "<unk>"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1c7d8fceb86cc878f83174d6af2aa4c915496d23117a8e2a986babc45ea4d1b
|
3 |
+
size 4984
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|