kbrdek37/llama38binstruct-summary-100s

README.md

@@ -1,13 +1,13 @@
 ---
-license: other
+base_model: NousResearch/Meta-Llama-3-8B-Instruct
+datasets:
+- generator
 library_name: peft
+license: other
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: NousResearch/Meta-Llama-3-8B-Instruct
-datasets:
-- generator
 model-index:
 - name: llama38binstruct_summarize
   results: []
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8421
+- Loss: 1.7040
 
 ## Model description
 
@@ -50,18 +50,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 2.3017        | 1.1364 | 25   | 1.8421          |
-| 2.1505        | 2.2727 | 50   | 1.8421          |
-| 2.3057        | 3.4091 | 75   | 1.8421          |
-| 2.3197        | 4.5455 | 100  | 1.8421          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.5571        | 1.25  | 25   | 1.2650          |
+| 0.518         | 2.5   | 50   | 1.4966          |
+| 0.2207        | 3.75  | 75   | 1.7554          |
+| 0.1096        | 5.0   | 100  | 1.7040          |
 
 
 ### Framework versions
 
 - PEFT 0.11.1
 - Transformers 4.41.2
-- Pytorch 2.3.0+cu121
+- Pytorch 2.2.1+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -19,7 +19,15 @@
   "r": 16,
   "rank_pattern": {},
   "revision": null,
-  "target_modules": "all-linear",
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj"
+  ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e3f74419781ba08362a620fbf2f66d54305b1988dbe6f7c18dab131317df75b
+oid sha256:78fc1455d7be12a6c78434d7c972e6eb961d56ef36abbc43a1e2667154211bee
 size 167832240

runs/Jun18_19-52-56_a12331a461b1/events.out.tfevents.1718740412.a12331a461b1.1553.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cc0326491e442ee27692177eefad532a709822bce9f295d586cfd8adf8c95e1
+size 9238

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e1f5df187aa4f3c4e47b4d20920f173ded4241924269887d79a8ac2f381be8
+oid sha256:f37cd9f3a2f0788d7620efd534358d70753e83dc5e34247b2ecf5e3a4302e81f
 size 5368