nacielo
/

wav2GPT2MusiSD3100

@@ -16,12 +16,12 @@ 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: 1.4543
-- Rouge1: 14.9678
-- Rouge2: 2.1649
-- Rougel: 14.4205
-- Rougelsum: 14.4408
-- Gen Len: 64.0
 ## Model description
@@ -50,18 +50,18 @@ The following hyperparameters were used during training:
 ### Training results
-| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
-| 2.7082        | 1.0   | 959  | 2.5321          | 18.3219 | 2.1594 | 17.0253 | 17.0044   | 82.0    |
-| 2.2926        | 2.0   | 1918 | 2.3019          | 17.7317 | 2.1985 | 16.3236 | 16.3132   | 71.0    |
-| 2.1349        | 3.0   | 2877 | 2.1208          | 21.6818 | 2.6244 | 19.1082 | 19.0883   | 58.0    |
-| 1.9939        | 4.0   | 3836 | 1.9543          | 19.6238 | 2.7829 | 17.8229 | 17.7944   | 72.0    |
-| 1.8933        | 5.0   | 4795 | 1.8055          | 17.2105 | 2.0041 | 16.7053 | 16.766    | 46.0    |
-| 1.8068        | 6.0   | 5754 | 1.6966          | 14.8562 | 2.0662 | 14.4525 | 14.4841   | 64.0    |
-| 1.7375        | 7.0   | 6713 | 1.5950          | 15.0644 | 2.1461 | 14.7203 | 14.7665   | 65.0    |
-| 1.6704        | 8.0   | 7672 | 1.5214          | 14.9678 | 2.1649 | 14.4205 | 14.4408   | 64.0    |
-| 1.6254        | 9.0   | 8631 | 1.4738          | 14.9678 | 2.1649 | 14.4205 | 14.4408   | 64.0    |
-| 1.5941        | 10.0  | 9590 | 1.4543          | 14.9678 | 2.1649 | 14.4205 | 14.4408   | 64.0    |
 ### 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: 1.0695
+- Rouge1: 27.535
+- Rouge2: 6.4489
+- Rougel: 21.3553
+- Rougelsum: 21.3149
+- Gen Len: 62.0
 ## Model description
 ### Training results
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| 2.3153        | 1.0   | 1361  | 1.8998          | 28.933  | 7.6448 | 21.3837 | 21.3322   | 70.0    |
+| 1.9693        | 2.0   | 2722  | 1.6823          | 21.1663 | 4.9059 | 18.2626 | 18.2806   | 65.0    |
+| 1.8035        | 3.0   | 4083  | 1.5310          | 30.8905 | 9.1528 | 22.7768 | 22.7103   | 89.0    |
+| 1.6632        | 4.0   | 5444  | 1.4205          | 31.8655 | 7.8167 | 22.7573 | 22.7116   | 66.0    |
+| 1.5764        | 5.0   | 6805  | 1.3066          | 29.913  | 7.5342 | 21.2873 | 21.2554   | 62.0    |
+| 1.5009        | 6.0   | 8166  | 1.2299          | 30.9454 | 8.005  | 22.3495 | 22.2846   | 63.0    |
+| 1.4331        | 7.0   | 9527  | 1.1677          | 28.1694 | 6.8177 | 21.7434 | 21.703    | 55.0    |
+| 1.3667        | 8.0   | 10888 | 1.1135          | 28.1109 | 6.7004 | 21.4423 | 21.3734   | 51.0    |
+| 1.3285        | 9.0   | 12249 | 1.0826          | 27.6524 | 8.0724 | 21.2241 | 21.1558   | 49.0    |
+| 1.2996        | 10.0  | 13610 | 1.0695          | 27.535  | 6.4489 | 21.3553 | 21.3149   | 62.0    |
 ### Framework versions