Training complete

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Rouge1
       type: rouge
-      value: 0.3385
+      value: 0.2754
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,11 +33,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the lr-sum dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.9376
-- Rouge1: 0.3385
-- Rouge2: 0.1624
-- Rougel: 0.2984
-- Rougelsum: 0.2982
+- Loss: 1.9316
+- Rouge1: 0.2754
+- Rouge2: 0.1375
+- Rougel: 0.2289
+- Rougelsum: 0.2327
 
 ## Model description
 
@@ -68,19 +68,19 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
-| 3.1352        | 1.0   | 141  | 1.9483          | 0.3261 | 0.1594 | 0.2887 | 0.2877    |
-| 1.3082        | 2.0   | 282  | 1.8614          | 0.3329 | 0.1568 | 0.2929 | 0.2925    |
-| 0.7268        | 3.0   | 423  | 2.0521          | 0.3338 | 0.1608 | 0.2954 | 0.2949    |
-| 0.3758        | 4.0   | 564  | 2.3700          | 0.3447 | 0.1723 | 0.3038 | 0.3035    |
-| 0.1812        | 5.0   | 705  | 2.6813          | 0.3415 | 0.1648 | 0.2973 | 0.2968    |
-| 0.0869        | 6.0   | 846  | 2.7940          | 0.3448 | 0.1704 | 0.3025 | 0.3024    |
-| 0.039         | 7.0   | 987  | 2.8631          | 0.3298 | 0.1594 | 0.2904 | 0.2899    |
-| 0.0146        | 8.0   | 1128 | 2.9376          | 0.3385 | 0.1624 | 0.2984 | 0.2982    |
+| 6.1325        | 1.0   | 141  | 11.2131         | 0.0    | 0.0    | 0.0    | 0.0       |
+| 3.7787        | 2.0   | 282  | 1.3939          | 0.2363 | 0.1062 | 0.1989 | 0.2012    |
+| 0.9062        | 3.0   | 423  | 1.7758          | 0.1799 | 0.0564 | 0.144  | 0.145     |
+| 0.5606        | 4.0   | 564  | 1.4496          | 0.2421 | 0.1063 | 0.2019 | 0.2042    |
+| 0.4325        | 5.0   | 705  | 1.6151          | 0.2576 | 0.1238 | 0.2146 | 0.2179    |
+| 0.1802        | 6.0   | 846  | 1.6976          | 0.2553 | 0.1282 | 0.2142 | 0.2171    |
+| 0.1083        | 7.0   | 987  | 1.8685          | 0.2645 | 0.125  | 0.2181 | 0.2214    |
+| 0.0658        | 8.0   | 1128 | 1.9316          | 0.2754 | 0.1375 | 0.2289 | 0.2327    |
 
 
 ### Framework versions
 
-- Transformers 4.41.1
+- Transformers 4.41.2
 - Pytorch 2.3.0+cu121
 - Datasets 2.19.2
 - Tokenizers 0.19.1

generation_config.json

@@ -7,5 +7,5 @@
   "max_length": 200,
   "num_beams": 5,
   "pad_token_id": 1,
-  "transformers_version": "4.41.1"
+  "transformers_version": "4.41.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2c8d0921dab4ba95f622915bcf29f112c5e3d8605959e96bfdcb13c238b1928
+oid sha256:a342d2c9729ac1bf154297ebc0e4033d73f9dbb286d449cc21e9948c2f36015a
 size 2444578688

runs/Jun05_17-34-54_69f33e2c29d6/events.out.tfevents.1717608904.69f33e2c29d6.5850.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a10c929ad2f3b73bc66d7d316f79f9d3a4d720c761ec553740e23effb403dbe9
-size 10540
+oid sha256:8ca9d7286c48bed949c3af70771bae213ab4085e412992693613fc7b2c31b1db
+size 11579

runs/Jun05_17-34-54_69f33e2c29d6/events.out.tfevents.1717611033.69f33e2c29d6.5850.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80997f930384511df32d7fab5e7f92a706651e96301c24f6c63ae18030bfa575
+size 562