End of training

README.md

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: Qwen/Qwen2-0.5B
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- yangzhao02/hh_sft
 model-index:
 - name: qwen2-0.5b-hh-sft
   results: []
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/zhaoyang1/huggingface/runs/ndloxft4)
 # qwen2-0.5b-hh-sft
 
-This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) on the generator dataset.
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) on the yangzhao02/hh_sft dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.4863
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 2.4862771034240723,
+    "eval_runtime": 0.4251,
+    "eval_samples": 100,
+    "eval_samples_per_second": 32.932,
+    "eval_steps_per_second": 2.352,
     "total_flos": 27695775744.0,
     "train_loss": 1.5830808877944946,
     "train_runtime": 12.0584,

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.42.0",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151646
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.4862771034240723,
+    "eval_runtime": 0.4251,
+    "eval_samples": 100,
+    "eval_samples_per_second": 32.932,
+    "eval_steps_per_second": 2.352
+}