End of training

README.md

@@ -5,6 +5,8 @@ datasets:
 library_name: peft
 license: llama3.1
 tags:
+- trl
+- sft
 - generated_from_trainer
 model-index:
 - name: Llama-3.1-8B-Summarization-QLoRa
@@ -18,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the scitldr dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3876
+- Loss: 2.3829
 
 ## Model description
 
@@ -51,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.2018        | 0.5020 | 500  | 2.3023          |
-| 2.2004        | 1.0040 | 1000 | 2.2920          |
-| 1.683         | 1.5060 | 1500 | 2.3876          |
+| 2.2034        | 0.5020 | 500  | 2.3051          |
+| 2.2011        | 1.0040 | 1000 | 2.2903          |
+| 1.6885        | 1.5060 | 1500 | 2.3829          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "o_proj",
     "up_proj",
-    "down_proj",
     "v_proj",
-    "k_proj",
-    "gate_proj",
-    "q_proj",
-    "o_proj"
+    "down_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a382b2c8016e588a6c5f72e865c1cdab775e6a9226289bdb80d7a68d2d8c59a6
+oid sha256:55a9b3ccd5b6785884cdc83f55630d248479a61c05d9de2cac6323e87ca838bb
 size 167832240

runs/Sep05_16-02-15_967fd41d9bcb/events.out.tfevents.1725552161.967fd41d9bcb.41484.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5182ed4f3311b6316bcc39bbb8b77a5ffda092947a4afbb3a615d6c423e395
+size 9036

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b41c747be2ed63e04cabc2dc84ce736b2327c644803ad2e2834e25362de72bde
-size 5176
+oid sha256:f01c48a6772e4cc38c20e14de85c548e0b804406a635c2273c5c2364cd8ec0ef
+size 5432