training completed[prod]: pegasus-baseline-128

README.md

@@ -1,6 +1,5 @@
 ---
-license: mit
-base_model: nsi319/legal-pegasus
+base_model: google/pegasus-xsum
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # pegasus-legalease
 
-This model is a fine-tuned version of [nsi319/legal-pegasus](https://huggingface.co/nsi319/legal-pegasus) on an unknown dataset.
+This model is a fine-tuned version of [google/pegasus-xsum](https://huggingface.co/google/pegasus-xsum) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0662
+- Loss: 1.1372
 
 ## Model description
 
@@ -47,25 +46,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0.09  | 250  | 4.5867          |
-| 4.446         | 0.18  | 500  | 1.5129          |
-| 4.446         | 0.27  | 750  | 1.1850          |
-| 1.4139        | 0.35  | 1000 | 1.1565          |
-| 1.4139        | 0.44  | 1250 | 1.1347          |
-| 1.2342        | 0.53  | 1500 | 1.1204          |
-| 1.2342        | 0.62  | 1750 | 1.1115          |
-| 1.168         | 0.71  | 2000 | 1.1046          |
-| 1.168         | 0.8   | 2250 | 1.0977          |
-| 1.1573        | 0.89  | 2500 | 1.0925          |
-| 1.1573        | 0.98  | 2750 | 1.0871          |
-| 1.177         | 1.06  | 3000 | 1.0816          |
-| 1.177         | 1.15  | 3250 | 1.0797          |
-| 1.1348        | 1.24  | 3500 | 1.0753          |
-| 1.1348        | 1.33  | 3750 | 1.0738          |
-| 1.1144        | 1.42  | 4000 | 1.0711          |
-| 1.1144        | 1.51  | 4250 | 1.0686          |
-| 1.1321        | 1.6   | 4500 | 1.0678          |
-| 1.1321        | 1.68  | 4750 | 1.0662          |
+| No log        | 0.09  | 250  | 4.9954          |
+| 5.2592        | 0.18  | 500  | 4.3175          |
+| 5.2592        | 0.27  | 750  | 1.3074          |
+| 2.3819        | 0.35  | 1000 | 1.1987          |
+| 2.3819        | 0.44  | 1250 | 1.1678          |
+| 1.3113        | 0.53  | 1500 | 1.1491          |
+| 1.3113        | 0.62  | 1750 | 1.1369          |
+| 1.2158        | 0.71  | 2000 | 1.1273          |
+| 1.2158        | 0.8   | 2250 | 1.1165          |
+| 1.2119        | 0.89  | 2500 | 1.1137          |
+| 1.2119        | 0.98  | 2750 | 1.1147          |
+| 1.2307        | 1.06  | 3000 | 1.1210          |
+| 1.2307        | 1.15  | 3250 | 1.1246          |
+| 1.2107        | 1.24  | 3500 | 1.1269          |
+| 1.2107        | 1.33  | 3750 | 1.1372          |
 
 
 ### Framework versions

generation_config.json

@@ -4,9 +4,8 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "forced_eos_token_id": 1,
-  "length_penalty": 0.8,
-  "max_length": 128,
-  "min_length": 32,
+  "length_penalty": 0.6,
+  "max_length": 64,
   "num_beams": 8,
   "pad_token_id": 0,
   "transformers_version": "4.38.2"

runs/Apr05_19-45-12_9e6d5516626c/events.out.tfevents.1712346352.9e6d5516626c.3600.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f746ead804a42cb643d96a7d94dd5e6705e3db8bafbe3978770d19a82485eec7
-size 10026
+oid sha256:5f1b0fd5402b5016260b4ce2ad6b07c440d1b447c4e6dcee309282ca18e28c32
+size 11404