adamjweintraut/bart-finetuned-eli5_precomputed_best_256

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+rouge_eval_2023-12-08_run.csv filter=lfs diff=lfs merge=lfs -text

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: 1.1839
+- Loss: 1.8045
 
 ## Model description
 
@@ -35,8 +35,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -44,28 +44,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 1.4316        | 0.1   | 500   | 1.2440          |
-| 1.2915        | 0.2   | 1000  | 1.2470          |
-| 1.3313        | 0.3   | 1500  | 1.2286          |
-| 1.2829        | 0.4   | 2000  | 1.2258          |
-| 1.1722        | 0.5   | 2500  | 1.2660          |
-| 1.1883        | 0.6   | 3000  | 1.2323          |
-| 1.2833        | 0.7   | 3500  | 1.2372          |
-| 1.264         | 0.8   | 4000  | 1.2048          |
-| 1.1157        | 0.9   | 4500  | 1.2108          |
-| 1.1908        | 1.0   | 5000  | 1.2033          |
-| 1.1009        | 1.1   | 5500  | 1.2196          |
-| 1.1563        | 1.2   | 6000  | 1.2087          |
-| 1.1294        | 1.3   | 6500  | 1.2080          |
-| 1.0821        | 1.4   | 7000  | 1.2225          |
-| 1.1232        | 1.5   | 7500  | 1.1925          |
-| 1.1462        | 1.6   | 8000  | 1.1941          |
-| 1.019         | 1.7   | 8500  | 1.2010          |
-| 1.0976        | 1.8   | 9000  | 1.1831          |
-| 1.1216        | 1.9   | 9500  | 1.1868          |
-| 1.0345        | 2.0   | 10000 | 1.1839          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.0094        | 0.4   | 500  | 1.8642          |
+| 1.808         | 0.8   | 1000 | 1.8719          |
+| 1.7532        | 1.2   | 1500 | 1.8353          |
+| 1.7879        | 1.6   | 2000 | 1.8151          |
+| 1.7312        | 2.0   | 2500 | 1.8045          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc3eb9d058344fc91e8244c2807a730238c5f7ef6fd2c313bbe1aade454fc9e4
+oid sha256:f3cda06bb1698c83b59a937463733266a5874063058c1f345556a0569c2326c7
 size 1625426996

rouge_eval_2023-12-08_run.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8886fff402a295b514f9814d697d8e02b988af87ca453a36c69c9d36aa81f790
+size 15639483

runs/Dec09_03-19-26_e8e0be95dd85/events.out.tfevents.1702091966.e8e0be95dd85.1299.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38a5d289f3f2ec268801a25718ab399564d09dcab0ac32e5531efde23488551
+size 5721

runs/Dec09_04-48-05_e8e0be95dd85/events.out.tfevents.1702097285.e8e0be95dd85.10313.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58d18547866016abeb03fd23e0ae95cb1078f9b279ab25fbdbf5fef3447e8c0e
+size 8215

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b428a4c98af614923446ce14db02a9fb458df8b039f8dd14efbb4ae35214fe3
+oid sha256:01f52467614696ecdc3e88b6adeeace617cb32c214abc46b8e28a432dfd73d3b
 size 4984