End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+datasets: mikkel-werling/maggic_patient_descriptions
 library_name: transformers
 model_name: DeepSeek-R1-Distill-Llama-8B-Maggic-Patient-Descriptions
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for DeepSeek-R1-Distill-Llama-8B-Maggic-Patient-Descriptions
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B).
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) on the [mikkel-werling/maggic_patient_descriptions](https://huggingface.co/datasets/mikkel-werling/maggic_patient_descriptions) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 0.3292176425457001,
+    "eval_runtime": 239.482,
+    "eval_samples": 2223,
+    "eval_samples_per_second": 9.283,
+    "eval_steps_per_second": 1.161,
     "total_flos": 4.0084130952600617e+18,
     "train_loss": 0.3981744751040237,
     "train_runtime": 12737.2069,

config.json

@@ -30,6 +30,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 0.3292176425457001,
+    "eval_runtime": 239.482,
+    "eval_samples": 2223,
+    "eval_samples_per_second": 9.283,
+    "eval_steps_per_second": 1.161
+}