trainer: training complete at 2023-11-14 14:01:39.049676.

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: bert-base-cased
+license: mit
+base_model: roberta-base
 tags:
 - generated_from_trainer
 metrics:
@@ -15,15 +15,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-ner-essays-classify_span
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6855
-- Claim: {'precision': 0.4016393442622951, 'recall': 0.3402777777777778, 'f1-score': 0.3684210526315789, 'support': 144.0}
-- Majorclaim: {'precision': 0.5882352941176471, 'recall': 0.5555555555555556, 'f1-score': 0.5714285714285715, 'support': 72.0}
-- Premise: {'precision': 0.7947494033412887, 'recall': 0.8473282442748091, 'f1-score': 0.8201970443349754, 'support': 393.0}
-- Accuracy: 0.6929
-- Macro avg: {'precision': 0.5948746805737436, 'recall': 0.5810538592027141, 'f1-score': 0.5866822227983753, 'support': 609.0}
-- Weighted avg: {'precision': 0.6773818099562685, 'recall': 0.6929392446633826, 'f1-score': 0.6839621135393265, 'support': 609.0}
+- Loss: 0.6725
+- Claim: {'precision': 0.4435483870967742, 'recall': 0.3819444444444444, 'f1-score': 0.4104477611940298, 'support': 144.0}
+- Majorclaim: {'precision': 0.6166666666666667, 'recall': 0.5138888888888888, 'f1-score': 0.5606060606060607, 'support': 72.0}
+- Premise: {'precision': 0.7976470588235294, 'recall': 0.8625954198473282, 'f1-score': 0.8288508557457213, 'support': 393.0}
+- Accuracy: 0.7077
+- Macro avg: {'precision': 0.6192873708623234, 'recall': 0.5861429177268872, 'f1-score': 0.5999682258486039, 'support': 609.0}
+- Weighted avg: {'precision': 0.6925225974705789, 'recall': 0.7077175697865353, 'f1-score': 0.6982044339632925, 'support': 609.0}
 
 ## Model description
 
@@ -54,8 +54,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Claim                                                                                                              | Majorclaim                                                                                                       | Premise                                                                                                           | Accuracy | Macro avg                                                                                                         | Weighted avg                                                                                                      |
 |:-------------:|:-----:|:----:|:---------------:|:------------------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------:|:--------:|:-----------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------:|
-| No log        | 1.0   | 267  | 0.6910          | {'precision': 0.40860215053763443, 'recall': 0.2638888888888889, 'f1-score': 0.3206751054852321, 'support': 144.0} | {'precision': 0.625, 'recall': 0.3472222222222222, 'f1-score': 0.44642857142857145, 'support': 72.0}             | {'precision': 0.7521008403361344, 'recall': 0.910941475826972, 'f1-score': 0.8239355581127733, 'support': 393.0}  | 0.6913   | {'precision': 0.5952343302912563, 'recall': 0.5073508623126944, 'f1-score': 0.5303464116755255, 'support': 609.0} | {'precision': 0.6558527749253206, 'recall': 0.6912972085385879, 'f1-score': 0.66030664478005, 'support': 609.0}   |
-| 0.7234        | 2.0   | 534  | 0.6855          | {'precision': 0.4016393442622951, 'recall': 0.3402777777777778, 'f1-score': 0.3684210526315789, 'support': 144.0}  | {'precision': 0.5882352941176471, 'recall': 0.5555555555555556, 'f1-score': 0.5714285714285715, 'support': 72.0} | {'precision': 0.7947494033412887, 'recall': 0.8473282442748091, 'f1-score': 0.8201970443349754, 'support': 393.0} | 0.6929   | {'precision': 0.5948746805737436, 'recall': 0.5810538592027141, 'f1-score': 0.5866822227983753, 'support': 609.0} | {'precision': 0.6773818099562685, 'recall': 0.6929392446633826, 'f1-score': 0.6839621135393265, 'support': 609.0} |
+| No log        | 1.0   | 267  | 0.6970          | {'precision': 0.4307692307692308, 'recall': 0.19444444444444445, 'f1-score': 0.2679425837320574, 'support': 144.0} | {'precision': 0.5774647887323944, 'recall': 0.5694444444444444, 'f1-score': 0.5734265734265734, 'support': 72.0} | {'precision': 0.758985200845666, 'recall': 0.9134860050890585, 'f1-score': 0.8290993071593533, 'support': 393.0}  | 0.7028   | {'precision': 0.589073073449097, 'recall': 0.5591249646593158, 'f1-score': 0.556822821439328, 'support': 609.0}   | {'precision': 0.6599169424496689, 'recall': 0.7027914614121511, 'f1-score': 0.6661846848239006, 'support': 609.0} |
+| 0.7281        | 2.0   | 534  | 0.6725          | {'precision': 0.4435483870967742, 'recall': 0.3819444444444444, 'f1-score': 0.4104477611940298, 'support': 144.0}  | {'precision': 0.6166666666666667, 'recall': 0.5138888888888888, 'f1-score': 0.5606060606060607, 'support': 72.0} | {'precision': 0.7976470588235294, 'recall': 0.8625954198473282, 'f1-score': 0.8288508557457213, 'support': 393.0} | 0.7077   | {'precision': 0.6192873708623234, 'recall': 0.5861429177268872, 'f1-score': 0.5999682258486039, 'support': 609.0} | {'precision': 0.6925225974705789, 'recall': 0.7077175697865353, 'f1-score': 0.6982044339632925, 'support': 609.0} |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ccf836d0cc8b047d1cbaafafcf3db6a4228afe63c9958ef25366905d2ce2032
+oid sha256:141db8873b24ffb1495524ae3daa784da14c6ffd020875899290c7c1e14a0ce5
 size 498660721