End of training

README.md

@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # xsum_model_v1
 
-This model is a fine-tuned version of [sshleifer/distilbart-cnn-12-6](https://huggingface.co/sshleifer/distilbart-cnn-12-6) on the None dataset.
+This model is a fine-tuned version of [sshleifer/distilbart-cnn-12-6](https://huggingface.co/sshleifer/distilbart-cnn-12-6) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6535
+- Loss: 0.6233
 
 ## Model description
 
@@ -46,11 +46,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 250  | 0.5245          |
-| 0.4244        | 2.0   | 500  | 0.5578          |
-| 0.4244        | 3.0   | 750  | 0.5806          |
-| 0.2504        | 4.0   | 1000 | 0.6279          |
-| 0.2504        | 5.0   | 1250 | 0.6535          |
+| 0.7791        | 1.0   | 750  | 0.5382          |
+| 0.4539        | 2.0   | 1500 | 0.5503          |
+| 0.3596        | 3.0   | 2250 | 0.5739          |
+| 0.2952        | 4.0   | 3000 | 0.5877          |
+| 0.2473        | 5.0   | 3750 | 0.6233          |
 
 
 ### Framework versions

generation_config.json

@@ -6,7 +6,7 @@
   "eos_token_id": 2,
   "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
-  "length_penalty": 1.8,
+  "length_penalty": 2.0,
   "max_length": 142,
   "min_length": 56,
   "no_repeat_ngram_size": 3,

runs/Aug07_18-41-24_d5aab7745a10/events.out.tfevents.1723056085.d5aab7745a10.3583.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abde35c44238fd582944e6646885455efce0ae14198df855c64b8d3379bdf8e0
-size 8691
+oid sha256:e1aa806b65dc0420eb37a9ac66002c35fabaa5d5ba26aca82d0cb1c385ff01ce
+size 9316