Model save

README.md

@@ -1,13 +1,11 @@
 ---
 base_model: barc0/Llama-3.1-ARC-Potpourri-Transduction-8B
-datasets:
-- tttx/problem0_data
 library_name: peft
 license: llama3.1
 tags:
-- alignment-handbook
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
 model-index:
 - name: problem0_model
@@ -19,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # problem0_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/problem0_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: 0.3351
 

adapter_config.json

@@ -22,11 +22,11 @@
   "target_modules": [
     "v_proj",
     "up_proj",
-    "down_proj",
-    "k_proj",
-    "o_proj",
     "q_proj",
-    "gate_proj"
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

all_results.json

@@ -6,9 +6,9 @@
     "eval_samples_per_second": 2.668,
     "eval_steps_per_second": 2.668,
     "total_flos": 6106581245952.0,
-    "train_loss": 0.022490768542310434,
-    "train_runtime": 1217.4896,
+    "train_loss": 0.0,
+    "train_runtime": 1.3476,
     "train_samples": 500,
-    "train_samples_per_second": 0.821,
-    "train_steps_per_second": 0.411
+    "train_samples_per_second": 742.074,
+    "train_steps_per_second": 371.037
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 2.0,
     "total_flos": 6106581245952.0,
-    "train_loss": 0.022490768542310434,
-    "train_runtime": 1217.4896,
+    "train_loss": 0.0,
+    "train_runtime": 1.3476,
     "train_samples": 500,
-    "train_samples_per_second": 0.821,
-    "train_steps_per_second": 0.411
+    "train_samples_per_second": 742.074,
+    "train_steps_per_second": 371.037
 }

trainer_state.json

@@ -3528,10 +3528,10 @@
       "epoch": 2.0,
       "step": 500,
       "total_flos": 6106581245952.0,
-      "train_loss": 0.022490768542310434,
-      "train_runtime": 1217.4896,
-      "train_samples_per_second": 0.821,
-      "train_steps_per_second": 0.411
+      "train_loss": 0.0,
+      "train_runtime": 1.3476,
+      "train_samples_per_second": 742.074,
+      "train_steps_per_second": 371.037
     }
   ],
   "logging_steps": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:131fac2ccb03028ee0dcc5f5f6ceaec415b1d7a4dc070a4824efbb67acb84131
+oid sha256:5ccfefb70782d624ccfa5a94a1f2a0676bbe23a033c8110de479d1d1dbe96dea
 size 7160