End of training

README.md

@@ -2,8 +2,9 @@
 license: apache-2.0
 library_name: peft
 tags:
-- unsloth
 - llama-factory
+- lora
+- unsloth
 - generated_from_trainer
 base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
 model-index:
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama-3-8b-finetuned
 
-This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit) on an unknown dataset.
+This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit) on the formatted_data dataset.
 
 ## Model description
 

all_results.json

@@ -2,7 +2,7 @@
     "epoch": 2.0,
     "total_flos": 1.5362943036162048e+16,
     "train_loss": 0.16884834933280946,
-    "train_runtime": 1433.2088,
-    "train_samples_per_second": 0.698,
-    "train_steps_per_second": 0.174
+    "train_runtime": 1424.4252,
+    "train_samples_per_second": 0.702,
+    "train_steps_per_second": 0.176
 }

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 2.0,
     "total_flos": 1.5362943036162048e+16,
     "train_loss": 0.16884834933280946,
-    "train_runtime": 1433.2088,
-    "train_samples_per_second": 0.698,
-    "train_steps_per_second": 0.174
+    "train_runtime": 1424.4252,
+    "train_samples_per_second": 0.702,
+    "train_steps_per_second": 0.176
 }

trainer_state.json

@@ -188,9 +188,9 @@
       "step": 250,
       "total_flos": 1.5362943036162048e+16,
       "train_loss": 0.16884834933280946,
-      "train_runtime": 1433.2088,
-      "train_samples_per_second": 0.698,
-      "train_steps_per_second": 0.174
+      "train_runtime": 1424.4252,
+      "train_samples_per_second": 0.702,
+      "train_steps_per_second": 0.176
     }
   ],
   "logging_steps": 10,