End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B
+datasets: trl-lib/Capybara
 library_name: transformers
 model_name: does-deepspeed-still-work-sft
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for does-deepspeed-still-work-sft
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B).
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) on the [trl-lib/Capybara](https://huggingface.co/datasets/trl-lib/Capybara) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 1.116114616394043,
+    "eval_runtime": 0.664,
+    "eval_samples": 200,
+    "eval_samples_per_second": 301.2,
+    "eval_steps_per_second": 6.024,
     "total_flos": 4.8695749825160806e+17,
     "train_loss": 1.088731300446295,
     "train_runtime": 315.8129,

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.2",
-  "use_cache": false,
+  "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 1.116114616394043,
+    "eval_runtime": 0.664,
+    "eval_samples": 200,
+    "eval_samples_per_second": 301.2,
+    "eval_steps_per_second": 6.024
+}