Model save

README.md

@@ -1,13 +1,11 @@
 ---
 base_model: barc0/Llama-3.1-ARC-Potpourri-Transduction-8B
-datasets:
-- tttx/problem81_data
 library_name: peft
 license: llama3.1
 tags:
-- alignment-handbook
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
 model-index:
 - name: problem81_model
@@ -19,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # problem81_model
 
-This model is a fine-tuned version of [barc0/Llama-3.1-ARC-Potpourri-Transduction-8B](https://huggingface.co/barc0/Llama-3.1-ARC-Potpourri-Transduction-8B) on the tttx/problem81_data dataset.
+This model is a fine-tuned version of [barc0/Llama-3.1-ARC-Potpourri-Transduction-8B](https://huggingface.co/barc0/Llama-3.1-ARC-Potpourri-Transduction-8B) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0387
 

adapter_config.json

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

all_results.json

@@ -7,8 +7,8 @@
     "eval_steps_per_second": 0.662,
     "total_flos": 286353899520.0,
     "train_loss": 0.0,
-    "train_runtime": 1.2944,
+    "train_runtime": 1.2646,
     "train_samples": 90,
-    "train_samples_per_second": 69.53,
-    "train_steps_per_second": 69.53
+    "train_samples_per_second": 71.17,
+    "train_steps_per_second": 71.17
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 286353899520.0,
     "train_loss": 0.0,
-    "train_runtime": 1.2944,
+    "train_runtime": 1.2646,
     "train_samples": 90,
-    "train_samples_per_second": 69.53,
-    "train_steps_per_second": 69.53
+    "train_samples_per_second": 71.17,
+    "train_steps_per_second": 71.17
 }

trainer_state.json

@@ -651,9 +651,9 @@
       "step": 90,
       "total_flos": 286353899520.0,
       "train_loss": 0.0,
-      "train_runtime": 1.2944,
-      "train_samples_per_second": 69.53,
-      "train_steps_per_second": 69.53
+      "train_runtime": 1.2646,
+      "train_samples_per_second": 71.17,
+      "train_steps_per_second": 71.17
     }
   ],
   "logging_steps": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e24d567cbae3f596eb560e2c8541e8dc3e5445d0107faf272d20943c243efa
+oid sha256:31f1e96b454b2bfd94af51ca032f24a31bd173884d3c502cadecd455fd3dda84
 size 7160