End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_svamp_101112_1760638001
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the svamp dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2799
+- Loss: 0.2259
 - Num Input Tokens Seen: 1430592
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.2259398251771927,
+    "eval_runtime": 1.6777,
+    "eval_samples_per_second": 41.723,
+    "eval_steps_per_second": 10.729,
+    "num_input_tokens_seen": 1430592,
+    "total_flos": 6.441891117819494e+16,
+    "train_loss": 0.06765125470246627,
+    "train_runtime": 660.6029,
+    "train_samples_per_second": 19.073,
+    "train_steps_per_second": 4.784
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.2259398251771927,
+    "eval_runtime": 1.6777,
+    "eval_samples_per_second": 41.723,
+    "eval_steps_per_second": 10.729,
+    "num_input_tokens_seen": 1430592
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 1430592,
+    "total_flos": 6.441891117819494e+16,
+    "train_loss": 0.06765125470246627,
+    "train_runtime": 660.6029,
+    "train_samples_per_second": 19.073,
+    "train_steps_per_second": 4.784
+}