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_cb_1757340215
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_cb_1757340215
 
-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 cb dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0186
 - Num Input Tokens Seen: 620240

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.01861300691962242,
+    "eval_runtime": 0.7552,
+    "eval_samples_per_second": 33.104,
+    "eval_steps_per_second": 17.214,
+    "num_input_tokens_seen": 620240,
+    "total_flos": 2.792912687136768e+16,
+    "train_loss": 0.167221273584263,
+    "train_runtime": 256.8958,
+    "train_samples_per_second": 17.517,
+    "train_steps_per_second": 8.797
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.01861300691962242,
+    "eval_runtime": 0.7552,
+    "eval_samples_per_second": 33.104,
+    "eval_steps_per_second": 17.214,
+    "num_input_tokens_seen": 620240
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 620240,
+    "total_flos": 2.792912687136768e+16,
+    "train_loss": 0.167221273584263,
+    "train_runtime": 256.8958,
+    "train_samples_per_second": 17.517,
+    "train_steps_per_second": 8.797
+}