End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: HPAI-BSC/Llama3-Aloe-8B-Alpha
+datasets: mikkel-werling/cardiovascular_biobank_tasks
 library_name: transformers
 model_name: Llama3-Aloe-8B-Alpha-Tasks
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for Llama3-Aloe-8B-Alpha-Tasks
 
-This model is a fine-tuned version of [HPAI-BSC/Llama3-Aloe-8B-Alpha](https://huggingface.co/HPAI-BSC/Llama3-Aloe-8B-Alpha).
+This model is a fine-tuned version of [HPAI-BSC/Llama3-Aloe-8B-Alpha](https://huggingface.co/HPAI-BSC/Llama3-Aloe-8B-Alpha) on the [mikkel-werling/cardiovascular_biobank_tasks](https://huggingface.co/datasets/mikkel-werling/cardiovascular_biobank_tasks) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 0.2739180028438568,
+    "eval_runtime": 1082.7473,
+    "eval_samples": 5774,
+    "eval_samples_per_second": 5.333,
+    "eval_steps_per_second": 0.667,
     "total_flos": 2.4604613018707296e+19,
     "train_loss": 0.33689416365974006,
     "train_runtime": 72368.3556,

config.json

@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 0.2739180028438568,
+    "eval_runtime": 1082.7473,
+    "eval_samples": 5774,
+    "eval_samples_per_second": 5.333,
+    "eval_steps_per_second": 0.667
+}