Theoreticallyhugo
commited on
Commit
•
1266fce
1
Parent(s):
8630019
Training in progress, epoch 1
Browse files- README.md +30 -15
- config.json +12 -12
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -3,11 +3,26 @@ license: apache-2.0
|
|
3 |
base_model: allenai/longformer-base-4096
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
model-index:
|
9 |
- name: longformer-one-step
|
10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,16 +30,16 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# longformer-one-step
|
17 |
|
18 |
-
This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Claim: {'precision': 0.
|
22 |
-
- Majorclaim: {'precision': 0.
|
23 |
-
- O: {'precision': 0.
|
24 |
-
- Premise: {'precision': 0.
|
25 |
-
- Accuracy: 0.
|
26 |
-
- Macro avg: {'precision': 0.
|
27 |
-
- Weighted avg: {'precision': 0.
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -53,11 +68,11 @@ The following hyperparameters were used during training:
|
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
-
| Training Loss | Epoch | Step | Validation Loss | Claim
|
57 |
-
|
58 |
-
| No log | 1.0 |
|
59 |
-
| No log | 2.0 |
|
60 |
-
| No log | 3.0 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
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-one-step
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Token Classification
|
15 |
+
type: token-classification
|
16 |
+
dataset:
|
17 |
+
name: fancy_dataset
|
18 |
+
type: fancy_dataset
|
19 |
+
config: full_labels
|
20 |
+
split: test
|
21 |
+
args: full_labels
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.8161524956107349
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# longformer-one-step
|
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: 0.5164
|
36 |
+
- Claim: {'precision': 0.5841029946823397, 'recall': 0.47910927456382, 'f1-score': 0.5264219952074664, 'support': 4356.0}
|
37 |
+
- Majorclaim: {'precision': 0.663898774219059, 'recall': 0.7694775435380385, 'f1-score': 0.7127998301846742, 'support': 2182.0}
|
38 |
+
- O: {'precision': 0.9219015280135824, 'recall': 0.8781671159029649, 'f1-score': 0.8995030369961348, 'support': 9275.0}
|
39 |
+
- Premise: {'precision': 0.8377274128893001, 'recall': 0.8983961640211641, 'f1-score': 0.8670017552257859, 'support': 12096.0}
|
40 |
+
- Accuracy: 0.8162
|
41 |
+
- Macro avg: {'precision': 0.7519076774510703, 'recall': 0.7562875245064969, 'f1-score': 0.7514316544035153, 'support': 27909.0}
|
42 |
+
- Weighted avg: {'precision': 0.8125252509519227, 'recall': 0.8161524956107349, 'f1-score': 0.8125897502575133, 'support': 27909.0}
|
43 |
|
44 |
## Model description
|
45 |
|
|
|
68 |
|
69 |
### Training results
|
70 |
|
71 |
+
| Training Loss | Epoch | Step | Validation Loss | Claim | Majorclaim | O | Premise | Accuracy | Macro avg | Weighted avg |
|
72 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:--------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|
|
73 |
+
| No log | 1.0 | 41 | 0.7242 | {'precision': 0.4451114922813036, 'recall': 0.23829201101928374, 'f1-score': 0.3104066985645933, 'support': 4356.0} | {'precision': 0.6888297872340425, 'recall': 0.11869844179651695, 'f1-score': 0.20250195465207194, 'support': 2182.0} | {'precision': 0.7629536017331648, 'recall': 0.9112668463611859, 'f1-score': 0.8305409521937798, 'support': 9275.0} | {'precision': 0.7774552148976847, 'recall': 0.9077380952380952, 'f1-score': 0.83756054769442, 'support': 12096.0} | 0.7427 | {'precision': 0.6685875240365489, 'recall': 0.5439988486037705, 'f1-score': 0.5452525382762162, 'support': 27909.0} | {'precision': 0.7138351496506337, 'recall': 0.7427353183560859, 'f1-score': 0.7032996725252499, 'support': 27909.0} |
|
74 |
+
| No log | 2.0 | 82 | 0.5451 | {'precision': 0.5706823375775384, 'recall': 0.40128558310376494, 'f1-score': 0.47122253673001757, 'support': 4356.0} | {'precision': 0.6872317596566524, 'recall': 0.5870760769935839, 'f1-score': 0.6332179930795848, 'support': 2182.0} | {'precision': 0.8817295464179737, 'recall': 0.8970350404312668, 'f1-score': 0.8893164448720005, 'support': 9275.0} | {'precision': 0.819134799940942, 'recall': 0.9173280423280423, 'f1-score': 0.8654551127057172, 'support': 12096.0} | 0.8042 | {'precision': 0.7396946108982767, 'recall': 0.7006811857141645, 'f1-score': 0.71480302184683, 'support': 27909.0} | {'precision': 0.7908462519320261, 'recall': 0.8042208606542692, 'f1-score': 0.7936967322502336, 'support': 27909.0} |
|
75 |
+
| No log | 3.0 | 123 | 0.5164 | {'precision': 0.5841029946823397, 'recall': 0.47910927456382, 'f1-score': 0.5264219952074664, 'support': 4356.0} | {'precision': 0.663898774219059, 'recall': 0.7694775435380385, 'f1-score': 0.7127998301846742, 'support': 2182.0} | {'precision': 0.9219015280135824, 'recall': 0.8781671159029649, 'f1-score': 0.8995030369961348, 'support': 9275.0} | {'precision': 0.8377274128893001, 'recall': 0.8983961640211641, 'f1-score': 0.8670017552257859, 'support': 12096.0} | 0.8162 | {'precision': 0.7519076774510703, 'recall': 0.7562875245064969, 'f1-score': 0.7514316544035153, 'support': 27909.0} | {'precision': 0.8125252509519227, 'recall': 0.8161524956107349, 'f1-score': 0.8125897502575133, 'support': 27909.0} |
|
76 |
|
77 |
|
78 |
### Framework versions
|
config.json
CHANGED
@@ -6,18 +6,18 @@
|
|
6 |
"attention_mode": "longformer",
|
7 |
"attention_probs_dropout_prob": 0.1,
|
8 |
"attention_window": [
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
],
|
22 |
"bos_token_id": 0,
|
23 |
"eos_token_id": 2,
|
|
|
6 |
"attention_mode": "longformer",
|
7 |
"attention_probs_dropout_prob": 0.1,
|
8 |
"attention_window": [
|
9 |
+
700,
|
10 |
+
700,
|
11 |
+
700,
|
12 |
+
700,
|
13 |
+
700,
|
14 |
+
700,
|
15 |
+
700,
|
16 |
+
700,
|
17 |
+
700,
|
18 |
+
700,
|
19 |
+
700,
|
20 |
+
700
|
21 |
],
|
22 |
"bos_token_id": 0,
|
23 |
"eos_token_id": 2,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 592330980
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32300cbf932e31f222044f90470759b1876373b427ccdd1a9aa67ec8cd263fcc
|
3 |
size 592330980
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b255ea933fa019c0434165b15f04a6f6f1bcbebd5334f05444070af09508cd03
|
3 |
size 4664
|