End of training

README.md

@@ -2,8 +2,6 @@
 base_model: facebook/bart-base
 library_name: peft
 license: apache-2.0
-metrics:
-- rouge
 tags:
 - generated_from_trainer
 model-index:
@@ -16,14 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bart-base-summarization-medical-43
 
-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: 2.1317
-- Rouge1: 0.4198
-- Rouge2: 0.2252
-- Rougel: 0.3557
-- Rougelsum: 0.3554
-- Gen Len: 18.34
+This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
 
 ## Model description
 
@@ -50,25 +41,13 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 6
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 2.7087        | 1.0   | 1250 | 2.2005          | 0.4151 | 0.2224 | 0.3555 | 0.3553    | 18.135  |
-| 2.615         | 2.0   | 2500 | 2.1680          | 0.4145 | 0.2228 | 0.3537 | 0.3534    | 17.898  |
-| 2.571         | 3.0   | 3750 | 2.1526          | 0.417  | 0.2224 | 0.3525 | 0.3522    | 18.122  |
-| 2.5533        | 4.0   | 5000 | 2.1433          | 0.4199 | 0.2239 | 0.3558 | 0.3555    | 18.241  |
-| 2.5482        | 5.0   | 6250 | 2.1344          | 0.4222 | 0.226  | 0.3562 | 0.356     | 18.293  |
-| 2.5365        | 6.0   | 7500 | 2.1317          | 0.4198 | 0.2252 | 0.3557 | 0.3554    | 18.34   |
-
-
 ### Framework versions
 
-- PEFT 0.12.0
-- Transformers 4.42.4
-- Pytorch 2.3.1+cu121
-- Datasets 2.20.0
+- PEFT 0.13.2
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -10,18 +10,20 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 128,
   "lora_dropout": 0.01,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
-    "v_proj"
+    "o_proj",
+    "v_proj",
+    "k_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 sha256:8e9b32f160fa0ca74751defa95e9a8f7aa762b6d6c17a51687898e3ef805b545
-size 894624
+oid sha256:3387c8a9d7a5f8ccf058428830e0938b2f511d5e3c7018e4a78ac94c66bedd54
+size 21248928

runs/Nov10_23-45-17_ae1726d9306b/events.out.tfevents.1731283304.ae1726d9306b.78712.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759bb56719ebce086483e47b21284c292f7ff3afe6768f583f7c912ee25ed7cc
+size 1270

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 128,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -50,8 +50,10 @@
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
+  "padding": true,
   "sep_token": "</s>",
   "tokenizer_class": "BartTokenizer",
   "trim_offsets": true,
+  "truncation": true,
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:259de4c565f43e9912b84df74079ba9964058c77db7e1b7d67580340b2c68905
-size 5304
+oid sha256:d11af2468743fafc66c2f9e19c95c0719d1345bbd8839742062ec1e09e3d8b62
+size 5432