End of training

README.md

@@ -1,17 +1,19 @@
 ---
 base_model: Qwen/Qwen2.5-7B-Instruct
+datasets: chloeli/stream-of-search-countdown-10k
 library_name: transformers
-model_name: qwen-2.5-7b-instruct-sft-qlora-countdown-search-1k
+model_name: Qwen/Qwen2.5-7B-Instruct
 tags:
 - generated_from_trainer
+- alignment-handbook
 - trl
 - sft
 licence: license
 ---
 
-# Model Card for qwen-2.5-7b-instruct-sft-qlora-countdown-search-1k
+# Model Card for Qwen/Qwen2.5-7B-Instruct
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the [chloeli/stream-of-search-countdown-10k](https://huggingface.co/datasets/chloeli/stream-of-search-countdown-10k) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 0.04535878077149391,
+    "eval_runtime": 573.183,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 1.745,
+    "eval_steps_per_second": 0.218,
     "total_flos": 8.539757562822656e+16,
     "train_loss": 0.0,
     "train_runtime": 2.0051,

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 0.04535878077149391,
+    "eval_runtime": 573.183,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 1.745,
+    "eval_steps_per_second": 0.218
+}