End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_conala_42_1760623630
 
-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 conala dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9179
+- Loss: 2.4588
 - Num Input Tokens Seen: 3049984
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 2.4588379859924316,
+    "eval_runtime": 4.4347,
+    "eval_samples_per_second": 53.668,
+    "eval_steps_per_second": 13.53,
+    "num_input_tokens_seen": 3049984,
+    "total_flos": 1.3733940102483149e+17,
+    "train_loss": 0.44957640529957726,
+    "train_runtime": 1797.5251,
+    "train_samples_per_second": 23.822,
+    "train_steps_per_second": 5.964
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 2.4588379859924316,
+    "eval_runtime": 4.4347,
+    "eval_samples_per_second": 53.668,
+    "eval_steps_per_second": 13.53,
+    "num_input_tokens_seen": 3049984
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 3049984,
+    "total_flos": 1.3733940102483149e+17,
+    "train_loss": 0.44957640529957726,
+    "train_runtime": 1797.5251,
+    "train_samples_per_second": 23.822,
+    "train_steps_per_second": 5.964
+}