bart-summ-cnn

README.md

@@ -3,16 +3,12 @@ license: apache-2.0
 library_name: peft
 tags:
 - generated_from_trainer
-- medical
 base_model: facebook/bart-base
 metrics:
 - rouge
 model-index:
 - name: bart-base-lora-summarization-medical
   results: []
-pipeline_tag: summarization
-datasets:
-- mystic-leung/medical_cord19
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -22,12 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0521
-- Rouge1: 0.4304
-- Rouge2: 0.2352
-- Rougel: 0.3663
-- Rougelsum: 0.366
-- Gen Len: 18.1767
+- Loss: 1.9722
+- Rouge1: 0.2477
+- Rouge2: 0.1026
+- Rougel: 0.2035
+- Rougelsum: 0.2273
+- Gen Len: 20.0
 
 ## Model description
 
@@ -61,17 +57,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 2.5079        | 1.0   | 6250  | 2.1220          | 0.4263 | 0.229  | 0.3597 | 0.3594    | 18.33   |
-| 2.4566        | 2.0   | 12500 | 2.0844          | 0.4267 | 0.2312 | 0.3622 | 0.3618    | 18.2773 |
-| 2.4242        | 3.0   | 18750 | 2.0616          | 0.4311 | 0.2358 | 0.366  | 0.3656    | 18.1307 |
-| 2.4058        | 4.0   | 25000 | 2.0532          | 0.4316 | 0.2367 | 0.366  | 0.3659    | 18.1753 |
-| 2.4119        | 5.0   | 31250 | 2.0521          | 0.4304 | 0.2352 | 0.3663 | 0.366     | 18.1767 |
+| 2.3307        | 1.0   | 6250  | 2.0165          | 0.2521 | 0.1075 | 0.2081 | 0.2326    | 20.0    |
+| 2.2746        | 2.0   | 12500 | 1.9848          | 0.2515 | 0.1071 | 0.2068 | 0.2313    | 20.0    |
+| 2.2604        | 3.0   | 18750 | 1.9751          | 0.249  | 0.1048 | 0.2052 | 0.2291    | 20.0    |
+| 2.2428        | 4.0   | 25000 | 1.9733          | 0.2482 | 0.1025 | 0.2037 | 0.2276    | 20.0    |
+| 2.2448        | 5.0   | 31250 | 1.9722          | 0.2477 | 0.1026 | 0.2035 | 0.2273    | 20.0    |
 
 
 ### Framework versions
 
 - PEFT 0.10.0
-- Transformers 4.40.0
+- Transformers 4.40.1
 - Pytorch 2.2.1+cu121
-- Datasets 2.19.0
+- Datasets 2.19.1
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "SEQ_2_SEQ_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:476f50ae74c77cf2dc3736c6c0475ebff940afbf8394ba46a28b5df983a95910
+oid sha256:e205009e38a14fa21377b1fcb0e6c32cad4781b8362226551c0f42fbec03ae87
 size 894624

runs/May06_14-09-30_cbba6922c5b9/events.out.tfevents.1715004571.cbba6922c5b9.6877.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de5e49757b38fa789ccdd0442fa94158cde1c13996230bc29aff7ecd7f7e8a87
+size 22204

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a72674d4218d7dd26c36c8cb0004a2f85defe4970a2fb8385d872d60cb72d9ac
+oid sha256:39cc62e693c5c5a9058e55e863579aca1509e3e6c2d2e6b35fa3dffb80b3d887
 size 5176