End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_cola_101112_1760638043
 
-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 cola dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2562
+- Loss: 0.2553
 - Num Input Tokens Seen: 7325256
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.2552622854709625,
+    "eval_runtime": 13.1567,
+    "eval_samples_per_second": 65.062,
+    "eval_steps_per_second": 16.265,
+    "num_input_tokens_seen": 7325256,
+    "total_flos": 3.298529668986962e+17,
+    "train_loss": 0.2632783476038683,
+    "train_runtime": 5503.3261,
+    "train_samples_per_second": 27.965,
+    "train_steps_per_second": 6.992
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.2552622854709625,
+    "eval_runtime": 13.1567,
+    "eval_samples_per_second": 65.062,
+    "eval_steps_per_second": 16.265,
+    "num_input_tokens_seen": 7325256
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 7325256,
+    "total_flos": 3.298529668986962e+17,
+    "train_loss": 0.2632783476038683,
+    "train_runtime": 5503.3261,
+    "train_samples_per_second": 27.965,
+    "train_steps_per_second": 6.992
+}