End of training

README.md

@@ -1,8 +1,9 @@
 ---
 license: mit
-base_model: ingeniumacademy/bart-cnn-samsum-finetuned
+library_name: peft
 tags:
 - generated_from_trainer
+base_model: ingeniumacademy/bart-cnn-samsum-finetuned
 datasets:
 - samsum
 model-index:
@@ -17,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ingeniumacademy/bart-cnn-samsum-finetuned](https://huggingface.co/ingeniumacademy/bart-cnn-samsum-finetuned) on the samsum dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2259
+- Loss: 0.1345
 
 ## Model description
 
@@ -48,16 +49,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.0766        | 1.0   | 74   | 0.2375          |
-| 0.0976        | 2.0   | 148  | 0.2499          |
-| 0.0684        | 3.0   | 222  | 0.2361          |
-| 0.085         | 4.0   | 296  | 0.2273          |
-| 0.0898        | 5.0   | 370  | 0.2259          |
+| 0.0788        | 1.0   | 19   | 0.1344          |
+| 0.0873        | 2.0   | 38   | 0.1345          |
+| 0.0777        | 3.0   | 57   | 0.1345          |
+| 0.0796        | 4.0   | 76   | 0.1345          |
+| 0.0924        | 5.0   | 95   | 0.1345          |
 
 
 ### Framework versions
 
-- Transformers 4.33.1
-- Pytorch 2.0.1+cu118
-- Datasets 2.14.5
-- Tokenizers 0.13.3
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -1,21 +1,29 @@
 {
+  "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "ingeniumacademy/bart-cnn-samsum-finetuned",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
+  "loftq_config": {},
   "lora_alpha": 32,
   "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 32,
+  "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
-  "task_type": "SEQ_2_SEQ_LM"
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f14af5af655aaaff69b44b1ee96dd0a677628792760c7ce34ff77b02ca7a0a41
+size 18894856

runs/Jun04_22-07-00_cc5be8c71c42/events.out.tfevents.1717538832.cc5be8c71c42.1105.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c39ab76bf910ce9020dcdd8c915d6428d7cd9643557227ebbd408d09a5a0d8d
+size 9428

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:764892d477e05d8518acbe79d09ab1449f98bf0df54f3f33bd5e0402781b9c23
-size 4091
+oid sha256:ad94524b00b5316b85621bf7860a5ae3d6ba8f096f76583efc55c36c3983bea8
+size 5176