End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_conala_101112_1760638010
 
-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: 0.6943
 - Num Input Tokens Seen: 3060208

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.6943244934082031,
+    "eval_runtime": 2.4804,
+    "eval_samples_per_second": 95.954,
+    "eval_steps_per_second": 24.19,
+    "num_input_tokens_seen": 3060208,
+    "total_flos": 1.3780339309215744e+17,
+    "train_loss": 0.8890379216911187,
+    "train_runtime": 1564.4317,
+    "train_samples_per_second": 27.371,
+    "train_steps_per_second": 6.852
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.6943244934082031,
+    "eval_runtime": 2.4804,
+    "eval_samples_per_second": 95.954,
+    "eval_steps_per_second": 24.19,
+    "num_input_tokens_seen": 3060208
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 3060208,
+    "total_flos": 1.3780339309215744e+17,
+    "train_loss": 0.8890379216911187,
+    "train_runtime": 1564.4317,
+    "train_samples_per_second": 27.371,
+    "train_steps_per_second": 6.852
+}