trainer: training complete at 2024-02-19 16:43:22.868013.
Browse files
README.md
CHANGED
|
@@ -5,9 +5,24 @@ tags:
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- essays_su_g
|
|
|
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: longformer-full_labels
|
| 10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -16,6 +31,18 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# longformer-full_labels
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the essays_su_g dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -40,13 +67,17 @@ The following hyperparameters were used during training:
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
-
- num_epochs:
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
-
| Training Loss | Epoch | Step | Validation Loss | B-claim
|
| 48 |
-
|
| 49 |
-
| No log | 1.0 | 41 | 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
|
| 52 |
### Framework versions
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- essays_su_g
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
model-index:
|
| 11 |
- name: longformer-full_labels
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Token Classification
|
| 15 |
+
type: token-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: essays_su_g
|
| 18 |
+
type: essays_su_g
|
| 19 |
+
config: full_labels
|
| 20 |
+
split: test
|
| 21 |
+
args: full_labels
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.8206313375613601
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 31 |
# longformer-full_labels
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the essays_su_g dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.4551
|
| 36 |
+
- B-claim: {'precision': 0.4418604651162791, 'recall': 0.34296028880866425, 'f1-score': 0.3861788617886179, 'support': 277.0}
|
| 37 |
+
- B-majorclaim: {'precision': 0.6578947368421053, 'recall': 0.3546099290780142, 'f1-score': 0.4608294930875576, 'support': 141.0}
|
| 38 |
+
- B-premise: {'precision': 0.6765463917525774, 'recall': 0.8190327613104524, 'f1-score': 0.7410021171489062, 'support': 641.0}
|
| 39 |
+
- I-claim: {'precision': 0.5945861854387057, 'recall': 0.4684971806815396, 'f1-score': 0.5240641711229947, 'support': 4079.0}
|
| 40 |
+
- I-majorclaim: {'precision': 0.7040552200172563, 'recall': 0.7996080352768251, 'f1-score': 0.7487955953200275, 'support': 2041.0}
|
| 41 |
+
- I-premise: {'precision': 0.8394741113455608, 'recall': 0.9030117852466172, 'f1-score': 0.8700845354754594, 'support': 11455.0}
|
| 42 |
+
- O: {'precision': 0.9285714285714286, 'recall': 0.8998382749326146, 'f1-score': 0.9139790833926519, 'support': 9275.0}
|
| 43 |
+
- Accuracy: 0.8206
|
| 44 |
+
- Macro avg: {'precision': 0.6918555055834161, 'recall': 0.6553654650478181, 'f1-score': 0.6635619796194593, 'support': 27909.0}
|
| 45 |
+
- Weighted avg: {'precision': 0.8147835624267602, 'recall': 0.8206313375613601, 'f1-score': 0.8153948467064512, 'support': 27909.0}
|
| 46 |
|
| 47 |
## Model description
|
| 48 |
|
|
|
|
| 67 |
- seed: 42
|
| 68 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 69 |
- lr_scheduler_type: linear
|
| 70 |
+
- num_epochs: 5
|
| 71 |
|
| 72 |
### Training results
|
| 73 |
|
| 74 |
+
| Training Loss | Epoch | Step | Validation Loss | B-claim | B-majorclaim | B-premise | I-claim | I-majorclaim | I-premise | O | Accuracy | Macro avg | Weighted avg |
|
| 75 |
+
|:-------------:|:-----:|:----:|:---------------:|:------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------:|:--------:|:---------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|
|
| 76 |
+
| No log | 1.0 | 41 | 0.7805 | {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 277.0} | {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 141.0} | {'precision': 0.8450704225352113, 'recall': 0.093603744149766, 'f1-score': 0.16853932584269662, 'support': 641.0} | {'precision': 0.4851063829787234, 'recall': 0.11179210590831086, 'f1-score': 0.1817095038852361, 'support': 4079.0} | {'precision': 0.5744125326370757, 'recall': 0.10779029887310142, 'f1-score': 0.1815181518151815, 'support': 2041.0} | {'precision': 0.7666466706658668, 'recall': 0.8925360104757748, 'f1-score': 0.824815457222379, 'support': 11455.0} | {'precision': 0.6639350481827149, 'recall': 0.9433962264150944, 'f1-score': 0.7793711588135744, 'support': 9275.0} | 0.7062 | {'precision': 0.47645300814279895, 'recall': 0.30701691226029254, 'f1-score': 0.3051362282255811, 'support': 27909.0} | {'precision': 0.667625147461383, 'recall': 0.7062237987745889, 'f1-score': 0.6412495568650286, 'support': 27909.0} |
|
| 77 |
+
| No log | 2.0 | 82 | 0.5661 | {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 277.0} | {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 141.0} | {'precision': 0.5732708089097304, 'recall': 0.7628705148205929, 'f1-score': 0.6546184738955824, 'support': 641.0} | {'precision': 0.5007429420505201, 'recall': 0.413091443981368, 'f1-score': 0.45271359484148305, 'support': 4079.0} | {'precision': 0.6697574893009985, 'recall': 0.4600685938265556, 'f1-score': 0.5454545454545454, 'support': 2041.0} | {'precision': 0.7978142076502732, 'recall': 0.9304233958969882, 'f1-score': 0.8590311920689933, 'support': 11455.0} | {'precision': 0.8996640537513998, 'recall': 0.8661994609164421, 'f1-score': 0.8826146663004669, 'support': 9275.0} | 0.7813 | {'precision': 0.4916070716661317, 'recall': 0.49037905849170677, 'f1-score': 0.48491892465158154, 'support': 27909.0} | {'precision': 0.7617728306989379, 'recall': 0.781289189867068, 'f1-score': 0.7669911232034595, 'support': 27909.0} |
|
| 78 |
+
| No log | 3.0 | 123 | 0.5008 | {'precision': 0.319672131147541, 'recall': 0.1407942238267148, 'f1-score': 0.1954887218045113, 'support': 277.0} | {'precision': 1.0, 'recall': 0.014184397163120567, 'f1-score': 0.027972027972027972, 'support': 141.0} | {'precision': 0.6006674082313682, 'recall': 0.8424336973478939, 'f1-score': 0.7012987012987012, 'support': 641.0} | {'precision': 0.5759794946905895, 'recall': 0.3856337337582741, 'f1-score': 0.46196769456681347, 'support': 4079.0} | {'precision': 0.7786308381317978, 'recall': 0.5962763351298384, 'f1-score': 0.6753607103218646, 'support': 2041.0} | {'precision': 0.8115562403697997, 'recall': 0.9195984286337844, 'f1-score': 0.8622058522611008, 'support': 11455.0} | {'precision': 0.8836870578443612, 'recall': 0.9157951482479785, 'f1-score': 0.8994546513474877, 'support': 9275.0} | 0.8026 | {'precision': 0.7100275957736368, 'recall': 0.5449594234439435, 'f1-score': 0.5462497656532153, 'support': 27909.0} | {'precision': 0.7899156932679995, 'recall': 0.8025726468164391, 'f1-score': 0.7878968886101326, 'support': 27909.0} |
|
| 79 |
+
| No log | 4.0 | 164 | 0.4686 | {'precision': 0.41739130434782606, 'recall': 0.34657039711191334, 'f1-score': 0.378698224852071, 'support': 277.0} | {'precision': 0.6346153846153846, 'recall': 0.23404255319148937, 'f1-score': 0.34196891191709844, 'support': 141.0} | {'precision': 0.6666666666666666, 'recall': 0.8112324492979719, 'f1-score': 0.7318789584799437, 'support': 641.0} | {'precision': 0.5885747259088286, 'recall': 0.500122579063496, 'f1-score': 0.5407554671968192, 'support': 4079.0} | {'precision': 0.6578228638314475, 'recall': 0.8260656540911318, 'f1-score': 0.7324066029539531, 'support': 2041.0} | {'precision': 0.8442690346982404, 'recall': 0.8963771278917503, 'f1-score': 0.8695431257145276, 'support': 11455.0} | {'precision': 0.9407347504621072, 'recall': 0.8779514824797844, 'f1-score': 0.9082594389604595, 'support': 9275.0} | 0.8164 | {'precision': 0.6785821043615002, 'recall': 0.6417660347325053, 'f1-score': 0.6433586757249817, 'support': 27909.0} | {'precision': 0.8159468583229401, 'recall': 0.816439141495575, 'f1-score': 0.8136284949655307, 'support': 27909.0} |
|
| 80 |
+
| No log | 5.0 | 205 | 0.4551 | {'precision': 0.4418604651162791, 'recall': 0.34296028880866425, 'f1-score': 0.3861788617886179, 'support': 277.0} | {'precision': 0.6578947368421053, 'recall': 0.3546099290780142, 'f1-score': 0.4608294930875576, 'support': 141.0} | {'precision': 0.6765463917525774, 'recall': 0.8190327613104524, 'f1-score': 0.7410021171489062, 'support': 641.0} | {'precision': 0.5945861854387057, 'recall': 0.4684971806815396, 'f1-score': 0.5240641711229947, 'support': 4079.0} | {'precision': 0.7040552200172563, 'recall': 0.7996080352768251, 'f1-score': 0.7487955953200275, 'support': 2041.0} | {'precision': 0.8394741113455608, 'recall': 0.9030117852466172, 'f1-score': 0.8700845354754594, 'support': 11455.0} | {'precision': 0.9285714285714286, 'recall': 0.8998382749326146, 'f1-score': 0.9139790833926519, 'support': 9275.0} | 0.8206 | {'precision': 0.6918555055834161, 'recall': 0.6553654650478181, 'f1-score': 0.6635619796194593, 'support': 27909.0} | {'precision': 0.8147835624267602, 'recall': 0.8206313375613601, 'f1-score': 0.8153948467064512, 'support': 27909.0} |
|
| 81 |
|
| 82 |
|
| 83 |
### Framework versions
|