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: 1.4380
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 0.15384615384615385,
-    "eval_loss": 1.438125729560852,
-    "eval_runtime": 1.6325,
-    "eval_samples_per_second": 322.201,
-    "eval_steps_per_second": 5.513,
+    "eval_loss": 1.4380333423614502,
+    "eval_runtime": 1.6011,
+    "eval_samples_per_second": 328.523,
+    "eval_steps_per_second": 5.621,
     "total_flos": 305613766656.0,
-    "train_loss": 1.5372200012207031,
-    "train_runtime": 320.6446,
-    "train_samples_per_second": 4.79,
+    "train_loss": 1.537254015604655,
+    "train_runtime": 320.3148,
+    "train_samples_per_second": 4.795,
     "train_steps_per_second": 0.009
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.15384615384615385,
-    "eval_loss": 1.438125729560852,
-    "eval_runtime": 1.6325,
-    "eval_samples_per_second": 322.201,
-    "eval_steps_per_second": 5.513
+    "eval_loss": 1.4380333423614502,
+    "eval_runtime": 1.6011,
+    "eval_samples_per_second": 328.523,
+    "eval_steps_per_second": 5.621
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.15384615384615385,
     "total_flos": 305613766656.0,
-    "train_loss": 1.5372200012207031,
-    "train_runtime": 320.6446,
-    "train_samples_per_second": 4.79,
+    "train_loss": 1.537254015604655,
+    "train_runtime": 320.3148,
+    "train_samples_per_second": 4.795,
     "train_steps_per_second": 0.009
 }

trainer_state.json

@@ -10,19 +10,19 @@
   "log_history": [
     {
       "epoch": 0.15384615384615385,
-      "eval_loss": 1.438125729560852,
-      "eval_runtime": 1.9143,
-      "eval_samples_per_second": 274.775,
-      "eval_steps_per_second": 4.701,
+      "eval_loss": 1.4380333423614502,
+      "eval_runtime": 1.8301,
+      "eval_samples_per_second": 287.418,
+      "eval_steps_per_second": 4.918,
       "step": 3
     },
     {
       "epoch": 0.15384615384615385,
       "step": 3,
       "total_flos": 305613766656.0,
-      "train_loss": 1.5372200012207031,
-      "train_runtime": 320.6446,
-      "train_samples_per_second": 4.79,
+      "train_loss": 1.537254015604655,
+      "train_runtime": 320.3148,
+      "train_samples_per_second": 4.795,
       "train_steps_per_second": 0.009
     }
   ],