Training in progress, step 406

README.md

@@ -31,25 +31,25 @@ model-index:
       type: fineweb_c_eval
     metrics:
     - type: accuracy
-      value: 0.90234375
+      value: 0.9013671875
       name: Accuracy
     - type: accuracy_threshold
-      value: 0.7725241184234619
+      value: 0.8407575488090515
       name: Accuracy Threshold
     - type: f1
-      value: 0.6426229508196721
+      value: 0.6757493188010899
       name: F1
     - type: f1_threshold
-      value: 0.601359486579895
+      value: 0.49566662311553955
       name: F1 Threshold
     - type: precision
-      value: 0.7101449275362319
+      value: 0.62
       name: Precision
     - type: recall
-      value: 0.5868263473053892
+      value: 0.7425149700598802
       name: Recall
     - type: average_precision
-      value: 0.696727465964923
+      value: 0.7125866664018541
       name: Average Precision
 ---
 
@@ -110,7 +110,7 @@ pairs = [
 ]
 scores = model.predict(pairs)
 print(scores)
-# [1.0987e-03 9.9933e-01 3.3535e-04 1.2066e-03 3.2731e-03]
+# [0.0136 0.9988 0.0103 0.0052 0.0117]
 
 # 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              | 0.9023     |
-| accuracy_threshold    | 0.7725     |
-| f1                    | 0.6426     |
-| f1_threshold          | 0.6014     |
-| precision             | 0.7101     |
-| recall                | 0.5868     |
-| **average_precision** | **0.6967** |
+| accuracy              | 0.9014     |
+| accuracy_threshold    | 0.8408     |
+| f1                    | 0.6757     |
+| f1_threshold          | 0.4957     |
+| precision             | 0.62       |
+| recall                | 0.7425     |
+| **average_precision** | **0.7126** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -422,12 +422,22 @@ You can finetune this model on your own dataset.
 | 1.1626 | 336  | 0.5970        | -               | -                                |
 | 1.1834 | 342  | 0.4205        | -               | -                                |
 | 1.2042 | 348  | 0.4822        | 0.9538          | 0.6967                           |
+| 1.2249 | 354  | 0.5008        | -               | -                                |
+| 1.2457 | 360  | 0.4902        | -               | -                                |
+| 1.2664 | 366  | 0.6269        | -               | -                                |
+| 1.2872 | 372  | 0.4861        | -               | -                                |
+| 1.3080 | 378  | 0.6288        | -               | -                                |
+| 1.3287 | 384  | 0.4038        | -               | -                                |
+| 1.3495 | 390  | 0.5267        | -               | -                                |
+| 1.3702 | 396  | 0.4614        | -               | -                                |
+| 1.3910 | 402  | 0.3266        | -               | -                                |
+| 1.4048 | 406  | -             | 0.7257          | 0.7126                           |
 
 
 ### Training Time
-- **Training**: 5.7 minutes
-- **Evaluation**: 2.1 minutes
-- **Total**: 7.8 minutes
+- **Training**: 6.5 minutes
+- **Evaluation**: 2.4 minutes
+- **Total**: 9.0 minutes
 
 ### Framework Versions
 - Python: 3.12.12

eval/CrossEncoderClassificationEvaluator_fineweb_c_eval_results.csv

@@ -5,3 +5,4 @@ epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average
 0.8027681660899654,232,0.869140625,0.81640637,0.53276955602537,0.5794004,0.4117647058823529,0.7544910179640718,0.5406815506036883
 1.0034602076124568,290,0.8837890625,0.81047595,0.6024844720496895,0.714628,0.6258064516129033,0.5808383233532934,0.6180374262832308
 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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d043136e355945d57bcbf7816fcb8037742c275d5c0f6e572f1d812297d2493d
+oid sha256:bc0c1e4d699357e02cde7574bd71f82a72ff4ba0e84fcdc7e88bb00bc2a23af9
 size 1230138348