End of training

README.md

@@ -4,6 +4,7 @@ license: llama3
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 tags:
 - llama-factory
+- prompt-tuning
 - generated_from_trainer
 model-index:
 - name: train_codealpacapy_123_1762506128
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_codealpacapy_123_1762506128
 
-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 codealpacapy dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5409
+- Loss: 0.4728
 - Num Input Tokens Seen: 24941912
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.4728040099143982,
+    "eval_runtime": 13.5521,
+    "eval_samples_per_second": 62.573,
+    "eval_steps_per_second": 15.643,
+    "num_input_tokens_seen": 24941912,
+    "total_flos": 1.1231230244139172e+18,
+    "train_loss": 0.4159113352138166,
+    "train_runtime": 5876.9026,
+    "train_samples_per_second": 25.963,
+    "train_steps_per_second": 6.493
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.4728040099143982,
+    "eval_runtime": 13.5521,
+    "eval_samples_per_second": 62.573,
+    "eval_steps_per_second": 15.643,
+    "num_input_tokens_seen": 24941912
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 24941912,
+    "total_flos": 1.1231230244139172e+18,
+    "train_loss": 0.4159113352138166,
+    "train_runtime": 5876.9026,
+    "train_samples_per_second": 25.963,
+    "train_steps_per_second": 6.493
+}