End of training

README.md

@@ -3,11 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: Qwen/Qwen2.5-0.5B-Instruct
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: qwen-0.5b-sft-full
   results: []
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen-0.5b-sft-full
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the generator dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.4074
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 1.4073771238327026,
+    "eval_runtime": 472.4195,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 28.659,
+    "eval_steps_per_second": 7.165,
     "total_flos": 107559842217984.0,
     "train_loss": 1.251657804362661,
     "train_runtime": 20444.6838,

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.0",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.4073771238327026,
+    "eval_runtime": 472.4195,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 28.659,
+    "eval_steps_per_second": 7.165
+}

runs/Oct28_01-02-05_ubuntu/events.out.tfevents.1730098479.ubuntu.1195766.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca53e432fe4b88cb70056d623b52f77c57901ce045eb4bdd415f6a5519148be5
+size 364