Commit
•
cd5c9bd
1
Parent(s):
b0fbca5
nathanReitinger/scotusPRED
Browse files
README.md
CHANGED
@@ -1,22 +1,26 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
-
-
|
|
|
|
|
|
|
4 |
model-index:
|
5 |
-
- name:
|
6 |
results: []
|
7 |
---
|
8 |
|
9 |
-
<!-- This model card has been generated automatically according to the information
|
10 |
-
probably proofread and complete it, then remove this comment. -->
|
11 |
|
12 |
-
#
|
13 |
|
14 |
-
This model is a fine-tuned version of [
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
-
|
17 |
-
-
|
18 |
-
-
|
19 |
-
- Epoch: 1
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -35,20 +39,28 @@ More information needed
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
-
-
|
39 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
|
41 |
### Training results
|
42 |
|
43 |
-
|
|
44 |
-
|
45 |
-
| 0.
|
46 |
-
| 0.6960 | 0.6932 | 0.4809 | 1 |
|
47 |
|
48 |
|
49 |
### Framework versions
|
50 |
|
51 |
-
- Transformers 4.
|
52 |
-
-
|
53 |
-
- Datasets 2.
|
54 |
-
- Tokenizers 0.
|
|
|
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 |
model-index:
|
10 |
+
- name: scotusPRED
|
11 |
results: []
|
12 |
---
|
13 |
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
+
# scotusPRED
|
18 |
|
19 |
+
This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.6335
|
22 |
+
- Accuracy: 0.6735
|
23 |
+
- F1: 0.0
|
|
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 5e-05
|
43 |
+
- train_batch_size: 4
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- gradient_accumulation_steps: 2
|
47 |
+
- total_train_batch_size: 8
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- lr_scheduler_warmup_steps: 200
|
51 |
+
- num_epochs: 1
|
52 |
+
- mixed_precision_training: Native AMP
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---:|
|
58 |
+
| 0.6824 | 1.0 | 195 | 0.6335 | 0.6735 | 0.0 |
|
|
|
59 |
|
60 |
|
61 |
### Framework versions
|
62 |
|
63 |
+
- Transformers 4.39.3
|
64 |
+
- Pytorch 2.2.2+cu121
|
65 |
+
- Datasets 2.18.0
|
66 |
+
- Tokenizers 0.15.2
|
config.json
CHANGED
@@ -1,35 +1,44 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
|
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"
|
8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
"gradient_checkpointing": false,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
-
"hidden_size":
|
13 |
-
"
|
14 |
-
"0": "Reversing",
|
15 |
-
"1": "Affirming"
|
16 |
-
},
|
17 |
"initializer_range": 0.02,
|
18 |
-
"intermediate_size":
|
19 |
-
"
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"type_vocab_size": 2,
|
33 |
-
"use_cache": true,
|
34 |
-
"vocab_size": 32000
|
35 |
}
|
|
|
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 |
+
"ignore_attention_mask": false,
|
|
|
|
|
|
|
29 |
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 3072,
|
31 |
+
"layer_norm_eps": 1e-05,
|
32 |
+
"max_position_embeddings": 4098,
|
33 |
+
"model_type": "longformer",
|
34 |
+
"num_attention_heads": 12,
|
35 |
+
"num_hidden_layers": 12,
|
36 |
+
"onnx_export": false,
|
37 |
+
"pad_token_id": 1,
|
38 |
+
"problem_type": "single_label_classification",
|
39 |
+
"sep_token_id": 2,
|
40 |
+
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.39.3",
|
42 |
+
"type_vocab_size": 1,
|
43 |
+
"vocab_size": 50265
|
|
|
|
|
|
|
44 |
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88fd233f0fdc4119a58ecf2a7387ff2910aefcbcc1d40b13d108a187642a8867
|
3 |
+
size 594678184
|
runs/Apr17_15-04-04_tron01.umiacs.umd.edu/events.out.tfevents.1713380645.tron01.umiacs.umd.edu.723909.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38e0c3ae2cfcdc4f2f4a0596e10c2fcc9e9e91ed4e2da1ff0ee1cdaf62696edd
|
3 |
+
size 15536
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a48b9430ef930f72b59bac60ca43c1258fa403d12d04c4938856f69443622f6
|
3 |
+
size 4984
|