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_multirc_123_1764892185
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_multirc_123_1764892185
 
-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: 0.6626
 - Num Input Tokens Seen: 235053712

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.6625613570213318,
+    "eval_runtime": 178.7817,
+    "eval_samples_per_second": 30.479,
+    "eval_steps_per_second": 7.624,
+    "num_input_tokens_seen": 235053712,
+    "total_flos": 1.0584362414603895e+19,
+    "train_loss": 0.11991507525748572,
+    "train_runtime": 34589.6479,
+    "train_samples_per_second": 12.601,
+    "train_steps_per_second": 3.151
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.6625613570213318,
+    "eval_runtime": 178.7817,
+    "eval_samples_per_second": 30.479,
+    "eval_steps_per_second": 7.624,
+    "num_input_tokens_seen": 235053712
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "num_input_tokens_seen": 235053712,
+    "total_flos": 1.0584362414603895e+19,
+    "train_loss": 0.11991507525748572,
+    "train_runtime": 34589.6479,
+    "train_samples_per_second": 12.601,
+    "train_steps_per_second": 3.151
+}