End of training

README.md

@@ -1,17 +1,19 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+datasets: AIML-TUDA/SLR-Bench
 library_name: transformers
 model_name: DeepSeek-R1-Distill-Qwen-1.5B-SFT-Easy
 tags:
 - generated_from_trainer
 - sft
+- open-r1
 - trl
 licence: license
 ---
 
 # Model Card for DeepSeek-R1-Distill-Qwen-1.5B-SFT-Easy
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B).
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on the [AIML-TUDA/SLR-Bench](https://huggingface.co/datasets/AIML-TUDA/SLR-Bench) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,5 +1,13 @@
 {
     "epoch": 50.0,
+    "eval_entropy": 0.41491925716400146,
+    "eval_loss": NaN,
+    "eval_mean_token_accuracy": 0.8998655676841736,
+    "eval_num_tokens": 262051053.0,
+    "eval_runtime": 0.5547,
+    "eval_samples": 250,
+    "eval_samples_per_second": 450.718,
+    "eval_steps_per_second": 1.803,
     "total_flos": 227901702144000.0,
     "train_loss": 0.14342150183208285,
     "train_runtime": 3480.9498,

eval_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 30.0,
-    "eval_entropy": 0.4551790952682495,
+    "epoch": 50.0,
+    "eval_entropy": 0.41491925716400146,
     "eval_loss": NaN,
-    "eval_mean_token_accuracy": 0.9045698642730713,
-    "eval_num_tokens": 157230603.0,
-    "eval_runtime": 0.5633,
+    "eval_mean_token_accuracy": 0.8998655676841736,
+    "eval_num_tokens": 262051053.0,
+    "eval_runtime": 0.5547,
     "eval_samples": 250,
-    "eval_samples_per_second": 443.804,
-    "eval_steps_per_second": 1.775
+    "eval_samples_per_second": 450.718,
+    "eval_steps_per_second": 1.803
 }