Theoreticallyhugo
commited on
Commit
•
ac32d7e
1
Parent(s):
8f367fa
trainer: training complete at 2024-01-28 14:46:00.578662.
Browse files- README.md +81 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: allenai/longformer-base-4096
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- fancy_dataset
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: longformer-spans
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Token Classification
|
15 |
+
type: token-classification
|
16 |
+
dataset:
|
17 |
+
name: fancy_dataset
|
18 |
+
type: fancy_dataset
|
19 |
+
config: spans
|
20 |
+
split: test
|
21 |
+
args: spans
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.9372962126912465
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# longformer-spans
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the fancy_dataset dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.1948
|
36 |
+
- : {'precision': 0.9405594405594405, 'recall': 0.9672104754749383, 'f1-score': 0.9536988041062546, 'support': 18634.0}
|
37 |
+
- O: {'precision': 0.9301474791357037, 'recall': 0.8771967654986523, 'f1-score': 0.9028964598823661, 'support': 9275.0}
|
38 |
+
- Accuracy: 0.9373
|
39 |
+
- Macro avg: {'precision': 0.9353534598475721, 'recall': 0.9222036204867954, 'f1-score': 0.9282976319943104, 'support': 27909.0}
|
40 |
+
- Weighted avg: {'precision': 0.9370992326621616, 'recall': 0.9372962126912465, 'f1-score': 0.9368156573551505, 'support': 27909.0}
|
41 |
+
|
42 |
+
## Model description
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Intended uses & limitations
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training and evaluation data
|
51 |
+
|
52 |
+
More information needed
|
53 |
+
|
54 |
+
## Training procedure
|
55 |
+
|
56 |
+
### Training hyperparameters
|
57 |
+
|
58 |
+
The following hyperparameters were used during training:
|
59 |
+
- learning_rate: 2e-05
|
60 |
+
- train_batch_size: 8
|
61 |
+
- eval_batch_size: 8
|
62 |
+
- seed: 42
|
63 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
64 |
+
- lr_scheduler_type: linear
|
65 |
+
- num_epochs: 3
|
66 |
+
|
67 |
+
### Training results
|
68 |
+
|
69 |
+
| Training Loss | Epoch | Step | Validation Loss | | O | Accuracy | Macro avg | Weighted avg |
|
70 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------:|:--------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|
|
71 |
+
| No log | 1.0 | 41 | 0.2901 | {'precision': 0.9357719203873051, 'recall': 0.9335623054631319, 'f1-score': 0.9346658070062326, 'support': 18634.0} | {'precision': 0.8671531280180277, 'recall': 0.871266846361186, 'f1-score': 0.8692051199311606, 'support': 9275.0} | 0.9129 | {'precision': 0.9014625242026664, 'recall': 0.9024145759121589, 'f1-score': 0.9019354634686966, 'support': 27909.0} | {'precision': 0.9129678321281397, 'recall': 0.9128596510086352, 'f1-score': 0.9129112521091997, 'support': 27909.0} |
|
72 |
+
| No log | 2.0 | 82 | 0.2109 | {'precision': 0.9311551324929251, 'recall': 0.9711817108511324, 'f1-score': 0.9507473272216239, 'support': 18634.0} | {'precision': 0.9366296908189757, 'recall': 0.8557412398921833, 'f1-score': 0.8943602456476422, 'support': 9275.0} | 0.9328 | {'precision': 0.9338924116559504, 'recall': 0.9134614753716579, 'f1-score': 0.922553786434633, 'support': 27909.0} | {'precision': 0.9329744928596212, 'recall': 0.9328173707406213, 'f1-score': 0.9320082043007497, 'support': 27909.0} |
|
73 |
+
| No log | 3.0 | 123 | 0.1948 | {'precision': 0.9405594405594405, 'recall': 0.9672104754749383, 'f1-score': 0.9536988041062546, 'support': 18634.0} | {'precision': 0.9301474791357037, 'recall': 0.8771967654986523, 'f1-score': 0.9028964598823661, 'support': 9275.0} | 0.9373 | {'precision': 0.9353534598475721, 'recall': 0.9222036204867954, 'f1-score': 0.9282976319943104, 'support': 27909.0} | {'precision': 0.9370992326621616, 'recall': 0.9372962126912465, 'f1-score': 0.9368156573551505, 'support': 27909.0} |
|
74 |
+
|
75 |
+
|
76 |
+
### Framework versions
|
77 |
+
|
78 |
+
- Transformers 4.37.1
|
79 |
+
- Pytorch 2.1.2+cu121
|
80 |
+
- Datasets 2.16.1
|
81 |
+
- Tokenizers 0.15.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 592318676
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83133b2521acc4311780c2d2e35ed6f053af3851388732b1b3101ade8a7e5aae
|
3 |
size 592318676
|