mitegvg
/

videomae-diving48-multilabel-finetuned

@@ -14,12 +14,12 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3667
-- F1 Macro: 0.2668
-- Precision Macro: 0.2209
-- Recall Macro: 0.4189
-- Exact Match Ratio: 0.0008
-- Hamming Accuracy: 0.7582
 ## Model description
@@ -52,14 +52,14 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step  | Validation Loss | F1 Macro | Precision Macro | Recall Macro | Exact Match Ratio | Hamming Accuracy |
 |:-------------:|:------:|:-----:|:---------------:|:--------:|:---------------:|:------------:|:-----------------:|:----------------:|
-| 1.3078        | 0.1250 | 3194  | 1.4517          | 0.1801   | 0.1743          | 0.3095       | 0.0               | 0.7416           |
-| 0.9069        | 1.1250 | 6388  | 1.3953          | 0.2019   | 0.1828          | 0.3173       | 0.0               | 0.7493           |
-| 1.0542        | 2.1250 | 9582  | 1.4204          | 0.2034   | 0.1675          | 0.3533       | 0.0               | 0.7418           |
-| 0.7846        | 3.1250 | 12776 | 1.4914          | 0.2227   | 0.1854          | 0.3534       | 0.0               | 0.7511           |
-| 0.888         | 4.1250 | 15970 | 1.4399          | 0.2328   | 0.1979          | 0.3500       | 0.0               | 0.7679           |
-| 1.0759        | 5.1250 | 19164 | 1.4068          | 0.2477   | 0.2177          | 0.3494       | 0.0               | 0.7769           |
-| 1.3115        | 6.1250 | 22358 | 1.3402          | 0.2643   | 0.2183          | 0.4042       | 0.0011            | 0.7619           |
-| 0.9306        | 7.1247 | 25544 | 1.3667          | 0.2668   | 0.2209          | 0.4189       | 0.0008            | 0.7582           |
 ### Framework versions

 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.3969
+- F1 Macro: 0.2636
+- Precision Macro: 0.2180
+- Recall Macro: 0.4145
+- Exact Match Ratio: 0.0003
+- Hamming Accuracy: 0.7557
 ## Model description
 | Training Loss | Epoch  | Step  | Validation Loss | F1 Macro | Precision Macro | Recall Macro | Exact Match Ratio | Hamming Accuracy |
 |:-------------:|:------:|:-----:|:---------------:|:--------:|:---------------:|:------------:|:-----------------:|:----------------:|
+| 1.3045        | 0.1250 | 3194  | 1.4774          | 0.1609   | 0.1518          | 0.2915       | 0.0               | 0.7280           |
+| 0.8881        | 1.1250 | 6388  | 1.4002          | 0.2035   | 0.1952          | 0.3239       | 0.0               | 0.7537           |
+| 1.0683        | 2.1250 | 9582  | 1.4017          | 0.2014   | 0.1999          | 0.3470       | 0.0               | 0.7403           |
+| 0.7672        | 3.1250 | 12776 | 1.4316          | 0.2280   | 0.1893          | 0.3459       | 0.0022            | 0.7566           |
+| 0.8529        | 4.1250 | 15970 | 1.4307          | 0.2333   | 0.2011          | 0.3484       | 0.0003            | 0.7650           |
+| 1.0022        | 5.1250 | 19164 | 1.4566          | 0.2367   | 0.2095          | 0.3404       | 0.0005            | 0.7734           |
+| 1.3422        | 6.1250 | 22358 | 1.4297          | 0.2602   | 0.2127          | 0.3922       | 0.0005            | 0.7634           |
+| 1.0641        | 7.1247 | 25544 | 1.3969          | 0.2636   | 0.2180          | 0.4145       | 0.0003            | 0.7557           |
 ### Framework versions