trainer: training complete at 2024-02-05 13:56:59.411305.

README.md

@@ -16,13 +16,13 @@ model-index:
     dataset:
       name: fancy_dataset
       type: fancy_dataset
-      config: full_labels
+      config: sep_tok
       split: test
-      args: full_labels
+      args: sep_tok
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8161524956107349
+      value: 0.8691844007060312
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,14 +32,14 @@ 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: 0.5164
-- Claim: {'precision': 0.5841029946823397, 'recall': 0.47910927456382, 'f1-score': 0.5264219952074664, 'support': 4356.0}
-- Majorclaim: {'precision': 0.663898774219059, 'recall': 0.7694775435380385, 'f1-score': 0.7127998301846742, 'support': 2182.0}
-- O: {'precision': 0.9219015280135824, 'recall': 0.8781671159029649, 'f1-score': 0.8995030369961348, 'support': 9275.0}
-- Premise: {'precision': 0.8377274128893001, 'recall': 0.8983961640211641, 'f1-score': 0.8670017552257859, 'support': 12096.0}
-- Accuracy: 0.8162
-- Macro avg: {'precision': 0.7519076774510703, 'recall': 0.7562875245064969, 'f1-score': 0.7514316544035153, 'support': 27909.0}
-- Weighted avg: {'precision': 0.8125252509519227, 'recall': 0.8161524956107349, 'f1-score': 0.8125897502575133, 'support': 27909.0}
+- Loss: 0.3013
+- Claim: {'precision': 0.5698178664353859, 'recall': 0.4524793388429752, 'f1-score': 0.5044145873320538, 'support': 4356.0}
+- Majorclaim: {'precision': 0.7584043030031377, 'recall': 0.775435380384968, 'f1-score': 0.7668252889191027, 'support': 2182.0}
+- O: {'precision': 0.9997360084477297, 'recall': 0.9971912577898709, 'f1-score': 0.9984620116887112, 'support': 11393.0}
+- Premise: {'precision': 0.8536961381330456, 'recall': 0.9155919312169312, 'f1-score': 0.8835613706170967, 'support': 12096.0}
+- Accuracy: 0.8692
+- Macro avg: {'precision': 0.7954135790048247, 'recall': 0.7851744770586864, 'f1-score': 0.7883158146392412, 'support': 30027.0}
+- Weighted avg: {'precision': 0.8610006209893659, 'recall': 0.8691844007060312, 'f1-score': 0.8636719872446065, 'support': 30027.0}
 
 ## Model description
 
@@ -68,11 +68,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Claim                                                                                                                | Majorclaim                                                                                                           | O                                                                                                                  | Premise                                                                                                             | Accuracy | Macro avg                                                                                                           | Weighted avg                                                                                                        |
-|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:--------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|
-| 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} |
-| 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} |
-| 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} |
+| Training Loss | Epoch | Step | Validation Loss | Claim                                                                                                               | Majorclaim                                                                                                         | O                                                                                                                   | Premise                                                                                                             | Accuracy | Macro avg                                                                                                           | Weighted avg                                                                                                        |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:--------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|
+| No log        | 1.0   | 41   | 0.4523          | {'precision': 0.4538361508452536, 'recall': 0.16023875114784206, 'f1-score': 0.2368510349507974, 'support': 4356.0} | {'precision': 0.6438781852082038, 'recall': 0.4747937671860678, 'f1-score': 0.5465576365075178, 'support': 2182.0} | {'precision': 0.961874840791373, 'recall': 0.9942947423856754, 'f1-score': 0.9778161415623651, 'support': 11393.0}  | {'precision': 0.7773290074819572, 'recall': 0.970568783068783, 'f1-score': 0.8632670318761719, 'support': 12096.0}  | 0.8260   | {'precision': 0.7092295460816969, 'recall': 0.6499740109470921, 'f1-score': 0.656122961224213, 'support': 30027.0}  | {'precision': 0.7907238221881672, 'recall': 0.8259899423851866, 'f1-score': 0.7928414157091711, 'support': 30027.0} |
+| No log        | 2.0   | 82   | 0.3203          | {'precision': 0.5346471710108074, 'recall': 0.38613406795224975, 'f1-score': 0.4484137563316448, 'support': 4356.0} | {'precision': 0.8060538116591929, 'recall': 0.6590284142988084, 'f1-score': 0.7251638930912757, 'support': 2182.0} | {'precision': 0.9997357759379955, 'recall': 0.9963135258492056, 'f1-score': 0.9980217171495142, 'support': 11393.0} | {'precision': 0.8241286473113585, 'recall': 0.9363425925925926, 'f1-score': 0.8766593134409226, 'support': 12096.0} | 0.8591   | {'precision': 0.7911413514798384, 'recall': 0.7444546501732141, 'f1-score': 0.7620646700033393, 'support': 30027.0} | {'precision': 0.8474500385354251, 'recall': 0.8591267858926965, 'f1-score': 0.8495730647807515, 'support': 30027.0} |
+| No log        | 3.0   | 123  | 0.3013          | {'precision': 0.5698178664353859, 'recall': 0.4524793388429752, 'f1-score': 0.5044145873320538, 'support': 4356.0}  | {'precision': 0.7584043030031377, 'recall': 0.775435380384968, 'f1-score': 0.7668252889191027, 'support': 2182.0}  | {'precision': 0.9997360084477297, 'recall': 0.9971912577898709, 'f1-score': 0.9984620116887112, 'support': 11393.0} | {'precision': 0.8536961381330456, 'recall': 0.9155919312169312, 'f1-score': 0.8835613706170967, 'support': 12096.0} | 0.8692   | {'precision': 0.7954135790048247, 'recall': 0.7851744770586864, 'f1-score': 0.7883158146392412, 'support': 30027.0} | {'precision': 0.8610006209893659, 'recall': 0.8691844007060312, 'f1-score': 0.8636719872446065, 'support': 30027.0} |
 
 
 ### Framework versions

model.safetensors

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