Training in progress, step 578

README.md

@@ -31,25 +31,25 @@ model-index:
       type: fineweb_c_eval
     metrics:
     - type: accuracy
-      value: 0.9189453125
+      value: 0.9228515625
       name: Accuracy
     - type: accuracy_threshold
-      value: 0.8019241094589233
+      value: 0.8104526996612549
       name: Accuracy Threshold
     - type: f1
-      value: 0.7284345047923323
+      value: 0.7368421052631579
       name: F1
     - type: f1_threshold
-      value: 0.7078086137771606
+      value: 0.6460131406784058
       name: F1 Threshold
     - type: precision
-      value: 0.7808219178082192
+      value: 0.72
       name: Precision
     - type: recall
-      value: 0.6826347305389222
+      value: 0.7544910179640718
       name: Recall
     - type: average_precision
-      value: 0.7616596241666778
+      value: 0.7713544030397519
       name: Average Precision
 ---
 
@@ -110,7 +110,7 @@ pairs = [
 ]
 scores = model.predict(pairs)
 print(scores)
-# [0.0032 0.9999 0.0014 0.0036 0.0592]
+# [2.4726e-03 9.9998e-01 7.5541e-04 2.8896e-03 2.6759e-02]
 
 # 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              | 0.9189     |
-| accuracy_threshold    | 0.8019     |
-| f1                    | 0.7284     |
-| f1_threshold          | 0.7078     |
-| precision             | 0.7808     |
-| recall                | 0.6826     |
-| **average_precision** | **0.7617** |
+| accuracy              | 0.9229     |
+| accuracy_threshold    | 0.8105     |
+| f1                    | 0.7368     |
+| f1_threshold          | 0.646      |
+| precision             | 0.72       |
+| recall                | 0.7545     |
+| **average_precision** | **0.7714** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -356,6 +356,8 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
+<details><summary>Click to expand</summary>
+
 | Epoch  | Step | Training Loss | Validation Loss | fineweb_c_eval_average_precision |
 |:------:|:----:|:-------------:|:---------------:|:--------------------------------:|
 | -1     | -1   | -             | -               | 0.1716                           |
@@ -453,12 +455,23 @@ You can finetune this model on your own dataset.
 | 1.7647 | 510  | 0.4394        | -               | -                                |
 | 1.7855 | 516  | 0.3467        | -               | -                                |
 | 1.8062 | 522  | 0.3586        | 0.6696          | 0.7617                           |
+| 1.8270 | 528  | 0.4339        | -               | -                                |
+| 1.8478 | 534  | 0.3417        | -               | -                                |
+| 1.8685 | 540  | 0.3653        | -               | -                                |
+| 1.8893 | 546  | 0.1870        | -               | -                                |
+| 1.9100 | 552  | 0.1759        | -               | -                                |
+| 1.9308 | 558  | 0.3405        | -               | -                                |
+| 1.9516 | 564  | 0.3644        | -               | -                                |
+| 1.9723 | 570  | 0.5313        | -               | -                                |
+| 1.9931 | 576  | 0.3601        | -               | -                                |
+| 2.0    | 578  | -             | 0.6740          | 0.7714                           |
 
+</details>
 
 ### Training Time
-- **Training**: 8.5 minutes
-- **Evaluation**: 3.1 minutes
-- **Total**: 11.6 minutes
+- **Training**: 9.5 minutes
+- **Evaluation**: 3.5 minutes
+- **Total**: 12.9 minutes
 
 ### Framework Versions
 - Python: 3.12.12

eval/CrossEncoderClassificationEvaluator_fineweb_c_eval_results.csv

@@ -8,3 +8,4 @@ epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average
 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
+2.0,578,0.9228515625,0.8104527,0.7368421052631579,0.64601314,0.72,0.7544910179640718,0.7713544030397519

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba4bc20c63ba86add4f0760eae2a1c4df961b98aad277e2bad94ec20e354c997
+oid sha256:d0a33982fff0c9d1b33bd227837ae601b5481fe5529a80d0eb2041c9467fc40c
 size 1230138348