End of training

README.md

@@ -4,6 +4,7 @@ license: llama3
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 datasets:
 - super_glue
@@ -17,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_boolq_1745950277
 
-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 super_glue 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 boolq dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7987
+- Loss: 0.1300
 - Num Input Tokens Seen: 34078960
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 18.85902876001886,
+    "eval_loss": 0.13001807034015656,
+    "eval_runtime": 27.6843,
+    "eval_samples_per_second": 34.063,
+    "eval_steps_per_second": 17.049,
+    "num_input_tokens_seen": 34078960,
+    "total_flos": 1.5375618540837274e+18,
+    "train_loss": 0.024724481988686597,
+    "train_runtime": 22328.9004,
+    "train_samples_per_second": 7.166,
+    "train_steps_per_second": 1.791
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 18.85902876001886,
+    "eval_loss": 0.13001807034015656,
+    "eval_runtime": 27.6843,
+    "eval_samples_per_second": 34.063,
+    "eval_steps_per_second": 17.049,
+    "num_input_tokens_seen": 34078960
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 18.85902876001886,
+    "num_input_tokens_seen": 34078960,
+    "total_flos": 1.5375618540837274e+18,
+    "train_loss": 0.024724481988686597,
+    "train_runtime": 22328.9004,
+    "train_samples_per_second": 7.166,
+    "train_steps_per_second": 1.791
+}