End of training

README.md

@@ -4,6 +4,7 @@ license: llama3
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 tags:
 - llama-factory
+- prefix-tuning
 - generated_from_trainer
 model-index:
 - name: train_math_qa_1754652176
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_math_qa_1754652176
 
-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 math_qa dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8029
+- Loss: 0.8026
 - Num Input Tokens Seen: 38732208
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.8025602698326111,
+    "eval_runtime": 45.2235,
+    "eval_samples_per_second": 65.983,
+    "eval_steps_per_second": 16.496,
+    "num_input_tokens_seen": 38732208,
+    "total_flos": 1.7440938205214147e+18,
+    "train_loss": 1.0262119300989725,
+    "train_runtime": 10175.179,
+    "train_samples_per_second": 26.391,
+    "train_steps_per_second": 6.598
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.8025602698326111,
+    "eval_runtime": 45.2235,
+    "eval_samples_per_second": 65.983,
+    "eval_steps_per_second": 16.496,
+    "num_input_tokens_seen": 38732208
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "num_input_tokens_seen": 38732208,
+    "total_flos": 1.7440938205214147e+18,
+    "train_loss": 1.0262119300989725,
+    "train_runtime": 10175.179,
+    "train_samples_per_second": 26.391,
+    "train_steps_per_second": 6.598
+}