End of training

README.md

@@ -4,6 +4,7 @@ license: apple-ascl
 base_model: apple/DCLM-7B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: dclm_baseline_openthoughts1
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # dclm_baseline_openthoughts1
 
-This model is a fine-tuned version of [apple/DCLM-7B](https://huggingface.co/apple/DCLM-7B) on an unknown dataset.
+This model is a fine-tuned version of [apple/DCLM-7B](https://huggingface.co/apple/DCLM-7B) on the mlfoundations-dev/openthoughts1_short dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 708732517220352.0,
+    "train_loss": 0.4619506940348965,
+    "train_runtime": 68592.6905,
+    "train_samples_per_second": 1.681,
+    "train_steps_per_second": 0.105
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 708732517220352.0,
+    "train_loss": 0.4619506940348965,
+    "train_runtime": 68592.6905,
+    "train_samples_per_second": 1.681,
+    "train_steps_per_second": 0.105
+}