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_mrpc_1755694491
@@ -15,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_mrpc_1755694491
 
-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 mrpc dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5287
-- Num Input Tokens Seen: 3028464
+- Loss: 0.5279
+- Num Input Tokens Seen: 3186272
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.527949333190918,
+    "eval_runtime": 6.8282,
+    "eval_samples_per_second": 53.748,
+    "eval_steps_per_second": 26.947,
+    "num_input_tokens_seen": 3186272,
+    "total_flos": 1.434763880670167e+17,
+    "train_loss": 0.13292204373043748,
+    "train_runtime": 1547.2139,
+    "train_samples_per_second": 21.335,
+    "train_steps_per_second": 10.671
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.527949333190918,
+    "eval_runtime": 6.8282,
+    "eval_samples_per_second": 53.748,
+    "eval_steps_per_second": 26.947,
+    "num_input_tokens_seen": 3186272
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "num_input_tokens_seen": 3186272,
+    "total_flos": 1.434763880670167e+17,
+    "train_loss": 0.13292204373043748,
+    "train_runtime": 1547.2139,
+    "train_samples_per_second": 21.335,
+    "train_steps_per_second": 10.671
+}