trainer: training complete at 2024-02-06 18:48:18.140397.

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: allenai/longformer-base-4096
+tags:
+- generated_from_trainer
+datasets:
+- fancy_dataset
+metrics:
+- accuracy
+model-index:
+- name: longformer-sep_tok
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: fancy_dataset
+      type: fancy_dataset
+      config: sep_tok
+      split: test
+      args: sep_tok
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8681852998967596
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# longformer-sep_tok
+
+This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the fancy_dataset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3013
+- B-claim: {'precision': 0.3954802259887006, 'recall': 0.2527075812274368, 'f1-score': 0.30837004405286345, 'support': 277.0}
+- B-majorclaim: {'precision': 0.6666666666666666, 'recall': 0.0425531914893617, 'f1-score': 0.08, 'support': 141.0}
+- B-premise: {'precision': 0.7548076923076923, 'recall': 0.9797191887675507, 'f1-score': 0.8526816021724372, 'support': 641.0}
+- I-claim: {'precision': 0.5792199878123095, 'recall': 0.4660455994116205, 'f1-score': 0.5165059095231627, 'support': 4079.0}
+- I-majorclaim: {'precision': 0.7457245724572458, 'recall': 0.8118569328760411, 'f1-score': 0.7773868167956838, 'support': 2041.0}
+- I-premise: {'precision': 0.8603904126513466, 'recall': 0.9119161938018333, 'f1-score': 0.8854043058145448, 'support': 11455.0}
+- O: {'precision': 0.9997360084477297, 'recall': 0.9971912577898709, 'f1-score': 0.9984620116887112, 'support': 11393.0}
+- Accuracy: 0.8682
+- Macro avg: {'precision': 0.7145750809045274, 'recall': 0.6374271350519594, 'f1-score': 0.6312586700067718, 'support': 30027.0}
+- Weighted avg: {'precision': 0.8598197108337798, 'recall': 0.8681852998967596, 'f1-score': 0.8610425793284459, 'support': 30027.0}
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | B-claim                                                                                                              | B-majorclaim                                                                                        | B-premise                                                                                                         | I-claim                                                                                                            | I-majorclaim                                                                                                       | I-premise                                                                                                           | O                                                                                                                   | Accuracy | Macro avg                                                                                                           | Weighted avg                                                                                                        |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:--------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|
+| No log        | 1.0   | 41   | 0.4523          | {'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': 0.6806833114323259, 'recall': 0.8081123244929798, 'f1-score': 0.738944365192582, 'support': 641.0}  | {'precision': 0.4538361508452536, 'recall': 0.17112037264035304, 'f1-score': 0.248531244436532, 'support': 4079.0} | {'precision': 0.6357986326911125, 'recall': 0.5012248897599216, 'f1-score': 0.5605479452054795, 'support': 2041.0} | {'precision': 0.7754845907125923, 'recall': 0.9709297250109122, 'f1-score': 0.8622708066829476, 'support': 11455.0} | {'precision': 0.961874840791373, 'recall': 0.9942947423856754, 'f1-score': 0.9778161415623651, 'support': 11393.0}  | 0.8222   | {'precision': 0.5010967894960939, 'recall': 0.4922402934699774, 'f1-score': 0.4840157861542723, 'support': 30027.0} | {'precision': 0.7801977126918217, 'recall': 0.8222266626702635, 'f1-score': 0.7875935668459264, 'support': 30027.0} |
+| No log        | 2.0   | 82   | 0.3203          | {'precision': 0.24675324675324675, 'recall': 0.06859205776173286, 'f1-score': 0.10734463276836159, 'support': 277.0} | {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 141.0}                                | {'precision': 0.6780383795309168, 'recall': 0.9921996879875195, 'f1-score': 0.8055731475617479, 'support': 641.0} | {'precision': 0.5418703160638645, 'recall': 0.407697965187546, 'f1-score': 0.46530498041410184, 'support': 4079.0} | {'precision': 0.7875560538116592, 'recall': 0.6883880450759432, 'f1-score': 0.7346405228758172, 'support': 2041.0} | {'precision': 0.8346739554861382, 'recall': 0.9330423395896988, 'f1-score': 0.8811211871393239, 'support': 11455.0} | {'precision': 0.9997357759379955, 'recall': 0.9963135258492056, 'f1-score': 0.9980217171495142, 'support': 11393.0} | 0.8580   | {'precision': 0.5840896753691174, 'recall': 0.583747660207378, 'f1-score': 0.5702865982726951, 'support': 30027.0}  | {'precision': 0.8416373274399493, 'recall': 0.8579611682818796, 'f1-score': 0.8461448628010773, 'support': 30027.0} |
+| No log        | 3.0   | 123  | 0.3013          | {'precision': 0.3954802259887006, 'recall': 0.2527075812274368, 'f1-score': 0.30837004405286345, 'support': 277.0}   | {'precision': 0.6666666666666666, 'recall': 0.0425531914893617, 'f1-score': 0.08, 'support': 141.0} | {'precision': 0.7548076923076923, 'recall': 0.9797191887675507, 'f1-score': 0.8526816021724372, 'support': 641.0} | {'precision': 0.5792199878123095, 'recall': 0.4660455994116205, 'f1-score': 0.5165059095231627, 'support': 4079.0} | {'precision': 0.7457245724572458, 'recall': 0.8118569328760411, 'f1-score': 0.7773868167956838, 'support': 2041.0} | {'precision': 0.8603904126513466, 'recall': 0.9119161938018333, 'f1-score': 0.8854043058145448, 'support': 11455.0} | {'precision': 0.9997360084477297, 'recall': 0.9971912577898709, 'f1-score': 0.9984620116887112, 'support': 11393.0} | 0.8682   | {'precision': 0.7145750809045274, 'recall': 0.6374271350519594, 'f1-score': 0.6312586700067718, 'support': 30027.0} | {'precision': 0.8598197108337798, 'recall': 0.8681852998967596, 'f1-score': 0.8610425793284459, 'support': 30027.0} |
+
+
+### Framework versions
+
+- Transformers 4.37.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32300cbf932e31f222044f90470759b1876373b427ccdd1a9aa67ec8cd263fcc
+oid sha256:ac9dd5742133824d16209428885eaa7c8c92d2e898abb88eb4e12ca5c84aec81
 size 592330980