bart-finetuned-loaf-512-lyrictoplan

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3928
+- Loss: 0.3763
 
 ## Model description
 
@@ -47,12 +47,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.7003        | 0.45  | 500  | 0.5146          |
-| 0.5357        | 0.89  | 1000 | 0.4827          |
-| 0.4799        | 1.34  | 1500 | 0.4387          |
-| 0.4354        | 1.78  | 2000 | 0.4132          |
-| 0.4047        | 2.23  | 2500 | 0.4049          |
-| 0.3739        | 2.67  | 3000 | 0.3928          |
+| 0.6537        | 0.45  | 500  | 0.4515          |
+| 0.4607        | 0.89  | 1000 | 0.4250          |
+| 0.4233        | 1.34  | 1500 | 0.4119          |
+| 0.41          | 1.78  | 2000 | 0.3935          |
+| 0.379         | 2.23  | 2500 | 0.3888          |
+| 0.3549        | 2.67  | 3000 | 0.3763          |
 
 
 ### Framework versions

generation_config.json

@@ -12,7 +12,7 @@
   "n_examples": null,
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
-  "pad_token_id": 1,
+  "pad_token_id": 2,
   "padding": "max_length",
   "renormalize_logits": true,
   "repetition_penalty": 0.4,

runs/Apr10_00-22-47_f60cf4680ffd/events.out.tfevents.1712708569.f60cf4680ffd.351.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bd1f1d5f5b94a318ec161184a4d13a31b2d98b7f9803240793a0551c5304845
-size 9033
+oid sha256:95d296828c1aa645b45b68666f971278b2b21363ccb73a241ecb4be6cefeb2e6
+size 9387