End of training

README.md

@@ -17,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_codealpacapy_42_1767887026
 
-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 codealpacapy dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4644
-- Num Input Tokens Seen: 9710784
+- Loss: 0.4641
+- Num Input Tokens Seen: 10214104
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.46405282616615295,
+    "eval_runtime": 18.2002,
+    "eval_samples_per_second": 46.593,
+    "eval_steps_per_second": 23.296,
+    "num_input_tokens_seen": 10214104,
+    "total_flos": 5.0107394251771085e+17,
+    "train_loss": 0.5066599989749814,
+    "train_runtime": 5951.357,
+    "train_samples_per_second": 12.819,
+    "train_steps_per_second": 6.41
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.46405282616615295,
+    "eval_runtime": 18.2002,
+    "eval_samples_per_second": 46.593,
+    "eval_steps_per_second": 23.296,
+    "num_input_tokens_seen": 10214104
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "num_input_tokens_seen": 10214104,
+    "total_flos": 5.0107394251771085e+17,
+    "train_loss": 0.5066599989749814,
+    "train_runtime": 5951.357,
+    "train_samples_per_second": 12.819,
+    "train_steps_per_second": 6.41
+}