trainer: training complete at 2024-02-06 18:59:05.773178.

README.md

@@ -16,13 +16,13 @@ model-index:
     dataset:
       name: fancy_dataset
       type: fancy_dataset
-      config: sep_tok
+      config: simple
       split: test
-      args: sep_tok
+      args: simple
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8681852998967596
+      value: 0.8209896449174101
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,17 +32,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 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}
+- Loss: 0.4200
+- Claim: {'precision': 0.8410830848577645, 'recall': 0.7810956443646161, 'f1-score': 0.8099802103139188, 'support': 13362.0}
+- Majorclaim: {'precision': 0.6330965315503552, 'recall': 0.6943171402383135, 'f1-score': 0.6622950819672131, 'support': 2182.0}
+- Premise: {'precision': 0.8362706950484474, 'recall': 0.8864536999595632, 'f1-score': 0.8606312814070352, 'support': 12365.0}
+- Accuracy: 0.8210
+- Macro avg: {'precision': 0.7701501038188557, 'recall': 0.7872888281874976, 'f1-score': 0.7776355245627223, 'support': 27909.0}
+- Weighted avg: {'precision': 0.8226900267292406, 'recall': 0.8209896449174101, 'f1-score': 0.8208746007977725, 'support': 27909.0}
 
 ## Model description
 
@@ -71,11 +67,11 @@ The following hyperparameters were used during training:
 
 ### 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} |
+| Training Loss | Epoch | Step | Validation Loss | Claim                                                                                                               | Majorclaim                                                                                                          | Premise                                                                                                             | Accuracy | Macro avg                                                                                                           | Weighted avg                                                                                                        |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:--------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|
+| No log        | 1.0   | 41   | 0.5303          | {'precision': 0.7396921017402945, 'recall': 0.8270468492740608, 'f1-score': 0.780934209596495, 'support': 13362.0}  | {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 2182.0}                                               | {'precision': 0.8185673529184979, 'recall': 0.8585523655479175, 'f1-score': 0.8380832083366226, 'support': 12365.0} | 0.7763   | {'precision': 0.5194198182195975, 'recall': 0.5618664049406594, 'f1-score': 0.5396724726443726, 'support': 27909.0} | {'precision': 0.716806448897884, 'recall': 0.7763445483535777, 'f1-score': 0.7451983868899174, 'support': 27909.0}  |
+| No log        | 2.0   | 82   | 0.4493          | {'precision': 0.8127147766323024, 'recall': 0.7787756323903607, 'f1-score': 0.7953833218680731, 'support': 13362.0} | {'precision': 0.7305801376597837, 'recall': 0.34051329055912005, 'f1-score': 0.4645201625507971, 'support': 2182.0} | {'precision': 0.8051533219761499, 'recall': 0.9173473513950667, 'f1-score': 0.8575964918912788, 'support': 12365.0} | 0.8059   | {'precision': 0.7828160787560786, 'recall': 0.6788787581148492, 'f1-score': 0.7058333254367164, 'support': 27909.0} | {'precision': 0.8029431915141912, 'recall': 0.8059049052277043, 'f1-score': 0.797078919478401, 'support': 27909.0}  |
+| No log        | 3.0   | 123  | 0.4200          | {'precision': 0.8410830848577645, 'recall': 0.7810956443646161, 'f1-score': 0.8099802103139188, 'support': 13362.0} | {'precision': 0.6330965315503552, 'recall': 0.6943171402383135, 'f1-score': 0.6622950819672131, 'support': 2182.0}  | {'precision': 0.8362706950484474, 'recall': 0.8864536999595632, 'f1-score': 0.8606312814070352, 'support': 12365.0} | 0.8210   | {'precision': 0.7701501038188557, 'recall': 0.7872888281874976, 'f1-score': 0.7776355245627223, 'support': 27909.0} | {'precision': 0.8226900267292406, 'recall': 0.8209896449174101, 'f1-score': 0.8208746007977725, 'support': 27909.0} |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4faed76d58d84e5287b5c0dd3d192c42f2584665b6689d490be5be5018f88b56
+oid sha256:25a85acd01d2a201cce2e61a8c9b1f9b63095ca627f2026a452922ab85fb937c
 size 592318676