End of training

README.md

@@ -13,12 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bart-cnn-samsum-finetuned
 
-This experiment is in a state of failure; still working out what I missed.
-
-This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the 'samsum' dataset.
-
+This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1706
+- Loss: 0.1330
 
 ## Model description
 
@@ -43,13 +40,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.1079        | 1.0   | 37   | 0.1706          |
+| 0.0981        | 1.0   | 37   | 0.1360          |
+| 0.1009        | 2.0   | 74   | 0.1330          |
+| 0.0957        | 3.0   | 111  | 0.1330          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9905e3314060ee35eb7763285ff4958a3b911314ea036ca60f84029f5f90e281
+oid sha256:6be51193fecdc3dba7e3e3312f76d3f37c389706ab3c7d615b670cd3ebffc469
 size 1625422896

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65fba517d947a8a04660ddae36f7b5dc95dc98cc694af8f942af9eb41d0066d
+oid sha256:4ae841f6a7a5985e74d78e8c3efa8c1d89762ece51c1442fe8440669abf9f6f2
 size 4984