Training in progress, step 522

README.md

@@ -31,25 +31,25 @@ model-index:
       type: fineweb_c_eval
     metrics:
     - type: accuracy
-      value: 0.91015625
+      value: 0.9189453125
       name: Accuracy
     - type: accuracy_threshold
-      value: 0.9219144582748413
+      value: 0.8019241094589233
       name: Accuracy Threshold
     - type: f1
-      value: 0.6866666666666666
+      value: 0.7284345047923323
       name: F1
     - type: f1_threshold
-      value: 0.8624649047851562
+      value: 0.7078086137771606
       name: F1 Threshold
     - type: precision
-      value: 0.7744360902255639
+      value: 0.7808219178082192
       name: Precision
     - type: recall
-      value: 0.6167664670658682
+      value: 0.6826347305389222
       name: Recall
     - type: average_precision
-      value: 0.7401881464737206
+      value: 0.7616596241666778
       name: Average Precision
 ---
 
@@ -110,7 +110,7 @@ pairs = [
 ]
 scores = model.predict(pairs)
 print(scores)
-# [0.0272 0.9999 0.0107 0.0086 0.077 ]
+# [0.0032 0.9999 0.0014 0.0036 0.0592]
 
 # Or rank different texts based on similarity to a single text
 ranks = model.rank(
@@ -161,13 +161,13 @@ You can finetune this model on your own dataset.
 
 | Metric                | Value      |
 |:----------------------|:-----------|
-| accuracy              | 0.9102     |
-| accuracy_threshold    | 0.9219     |
-| f1                    | 0.6867     |
-| f1_threshold          | 0.8625     |
-| precision             | 0.7744     |
-| recall                | 0.6168     |
-| **average_precision** | **0.7402** |
+| accuracy              | 0.9189     |
+| accuracy_threshold    | 0.8019     |
+| f1                    | 0.7284     |
+| f1_threshold          | 0.7078     |
+| precision             | 0.7808     |
+| recall                | 0.6826     |
+| **average_precision** | **0.7617** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -443,12 +443,22 @@ You can finetune this model on your own dataset.
 | 1.5779 | 456  | 0.6273        | -               | -                                |
 | 1.5986 | 462  | 0.5283        | -               | -                                |
 | 1.6055 | 464  | -             | 0.6483          | 0.7402                           |
+| 1.6194 | 468  | 0.3476        | -               | -                                |
+| 1.6401 | 474  | 0.3913        | -               | -                                |
+| 1.6609 | 480  | 0.2521        | -               | -                                |
+| 1.6817 | 486  | 0.4420        | -               | -                                |
+| 1.7024 | 492  | 0.4638        | -               | -                                |
+| 1.7232 | 498  | 0.2845        | -               | -                                |
+| 1.7439 | 504  | 0.5491        | -               | -                                |
+| 1.7647 | 510  | 0.4394        | -               | -                                |
+| 1.7855 | 516  | 0.3467        | -               | -                                |
+| 1.8062 | 522  | 0.3586        | 0.6696          | 0.7617                           |
 
 
 ### Training Time
-- **Training**: 7.5 minutes
-- **Evaluation**: 2.8 minutes
-- **Total**: 10.2 minutes
+- **Training**: 8.5 minutes
+- **Evaluation**: 3.1 minutes
+- **Total**: 11.6 minutes
 
 ### Framework Versions
 - Python: 3.12.12

eval/CrossEncoderClassificationEvaluator_fineweb_c_eval_results.csv

@@ -7,3 +7,4 @@ epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average
 1.2041522491349481,348,0.90234375,0.7725241,0.6426229508196721,0.6013595,0.7101449275362319,0.5868263473053892,0.696727465964923
 1.4048442906574394,406,0.9013671875,0.84075755,0.6757493188010899,0.49566662,0.62,0.7425149700598802,0.7125866664018541
 1.6055363321799307,464,0.91015625,0.92191446,0.6866666666666666,0.8624649,0.7744360902255639,0.6167664670658682,0.7401881464737206
+1.8062283737024223,522,0.9189453125,0.8019241,0.7284345047923323,0.7078086,0.7808219178082192,0.6826347305389222,0.7616596241666778

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac1ceac343b899a646fb41aefdcfaa773282f9e705396e2d3dbd903f1ee38a9d
+oid sha256:ba4bc20c63ba86add4f0760eae2a1c4df961b98aad277e2bad94ec20e354c997
 size 1230138348