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_sst2_1754652139
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # train_sst2_1754652139
 
-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 sst2 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.2435
 - Num Input Tokens Seen: 33869824

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.24351000785827637,
+    "eval_runtime": 62.3765,
+    "eval_samples_per_second": 107.973,
+    "eval_steps_per_second": 26.997,
+    "num_input_tokens_seen": 33869824,
+    "total_flos": 1.5251428666433864e+18,
+    "train_loss": 0.4074674226562911,
+    "train_runtime": 13838.1269,
+    "train_samples_per_second": 43.802,
+    "train_steps_per_second": 10.951
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.24351000785827637,
+    "eval_runtime": 62.3765,
+    "eval_samples_per_second": 107.973,
+    "eval_steps_per_second": 26.997,
+    "num_input_tokens_seen": 33869824
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "num_input_tokens_seen": 33869824,
+    "total_flos": 1.5251428666433864e+18,
+    "train_loss": 0.4074674226562911,
+    "train_runtime": 13838.1269,
+    "train_samples_per_second": 43.802,
+    "train_steps_per_second": 10.951
+}