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_multirc_1745950264
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_multirc_1745950264
 
-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 multirc dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3206
+- Loss: 0.3193
 - Num Input Tokens Seen: 75778784
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 6.525328330206379,
+    "eval_loss": 0.31929609179496765,
+    "eval_runtime": 152.7427,
+    "eval_samples_per_second": 17.84,
+    "eval_steps_per_second": 8.924,
+    "num_input_tokens_seen": 75778784,
+    "total_flos": 3.412284393934553e+18,
+    "train_loss": 0.34800040470212695,
+    "train_runtime": 50620.9312,
+    "train_samples_per_second": 3.161,
+    "train_steps_per_second": 0.79
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.525328330206379,
+    "eval_loss": 0.31929609179496765,
+    "eval_runtime": 152.7427,
+    "eval_samples_per_second": 17.84,
+    "eval_steps_per_second": 8.924,
+    "num_input_tokens_seen": 75778784
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.525328330206379,
+    "num_input_tokens_seen": 75778784,
+    "total_flos": 3.412284393934553e+18,
+    "train_loss": 0.34800040470212695,
+    "train_runtime": 50620.9312,
+    "train_samples_per_second": 3.161,
+    "train_steps_per_second": 0.79
+}