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_cola_1757340184
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_cola_1757340184
 
-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 cola dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9521
 - Num Input Tokens Seen: 6929680

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.9521387219429016,
+    "eval_runtime": 13.1396,
+    "eval_samples_per_second": 65.147,
+    "eval_steps_per_second": 32.573,
+    "num_input_tokens_seen": 6929680,
+    "total_flos": 3.1204035840638976e+17,
+    "train_loss": 0.23893776387709736,
+    "train_runtime": 6717.4331,
+    "train_samples_per_second": 22.911,
+    "train_steps_per_second": 11.457
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.9521387219429016,
+    "eval_runtime": 13.1396,
+    "eval_samples_per_second": 65.147,
+    "eval_steps_per_second": 32.573,
+    "num_input_tokens_seen": 6929680
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 6929680,
+    "total_flos": 3.1204035840638976e+17,
+    "train_loss": 0.23893776387709736,
+    "train_runtime": 6717.4331,
+    "train_samples_per_second": 22.911,
+    "train_steps_per_second": 11.457
+}