End of training

README.md

@@ -16,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # test_run_mini
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on the llamafactory/alpaca_en dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4381
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 0.15384615384615385,
-    "eval_loss": 1.438093900680542,
-    "eval_runtime": 1.614,
-    "eval_samples_per_second": 325.904,
-    "eval_steps_per_second": 5.576,
+    "eval_loss": 1.438112735748291,
+    "eval_runtime": 1.7111,
+    "eval_samples_per_second": 307.407,
+    "eval_steps_per_second": 5.26,
     "total_flos": 305613766656.0,
-    "train_loss": 1.5371843973795574,
-    "train_runtime": 192.8691,
-    "train_samples_per_second": 7.964,
-    "train_steps_per_second": 0.016
+    "train_loss": 1.5370841026306152,
+    "train_runtime": 320.2266,
+    "train_samples_per_second": 4.797,
+    "train_steps_per_second": 0.009
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.15384615384615385,
-    "eval_loss": 1.438093900680542,
-    "eval_runtime": 1.614,
-    "eval_samples_per_second": 325.904,
-    "eval_steps_per_second": 5.576
+    "eval_loss": 1.438112735748291,
+    "eval_runtime": 1.7111,
+    "eval_samples_per_second": 307.407,
+    "eval_steps_per_second": 5.26
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.15384615384615385,
     "total_flos": 305613766656.0,
-    "train_loss": 1.5371843973795574,
-    "train_runtime": 192.8691,
-    "train_samples_per_second": 7.964,
-    "train_steps_per_second": 0.016
+    "train_loss": 1.5370841026306152,
+    "train_runtime": 320.2266,
+    "train_samples_per_second": 4.797,
+    "train_steps_per_second": 0.009
 }

trainer_state.json

@@ -10,20 +10,20 @@
   "log_history": [
     {
       "epoch": 0.15384615384615385,
-      "eval_loss": 1.438093900680542,
-      "eval_runtime": 1.81,
-      "eval_samples_per_second": 290.611,
-      "eval_steps_per_second": 4.972,
+      "eval_loss": 1.438112735748291,
+      "eval_runtime": 1.9307,
+      "eval_samples_per_second": 272.436,
+      "eval_steps_per_second": 4.661,
       "step": 3
     },
     {
       "epoch": 0.15384615384615385,
       "step": 3,
       "total_flos": 305613766656.0,
-      "train_loss": 1.5371843973795574,
-      "train_runtime": 192.8691,
-      "train_samples_per_second": 7.964,
-      "train_steps_per_second": 0.016
+      "train_loss": 1.5370841026306152,
+      "train_runtime": 320.2266,
+      "train_samples_per_second": 4.797,
+      "train_steps_per_second": 0.009
     }
   ],
   "logging_steps": 10,