End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-7B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: oh-dcft-v3.1-claude-3-5-haiku-20241022-qwen
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # oh-dcft-v3.1-claude-3-5-haiku-20241022-qwen
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the mlfoundations-dev/oh-dcft-v3.1-claude-3-5-haiku-20241022 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4277
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 3.0,
-    "eval_loss": 0.42792943120002747,
-    "eval_runtime": 443.4778,
-    "eval_samples_per_second": 26.522,
-    "eval_steps_per_second": 0.415,
+    "eval_loss": 0.42773160338401794,
+    "eval_runtime": 287.1275,
+    "eval_samples_per_second": 40.964,
+    "eval_steps_per_second": 0.641,
     "total_flos": 2745782658662400.0,
-    "train_loss": 0.3825414228548572,
-    "train_runtime": 71090.721,
-    "train_samples_per_second": 9.431,
-    "train_steps_per_second": 0.074
+    "train_loss": 0.38240701185468956,
+    "train_runtime": 39622.8086,
+    "train_samples_per_second": 16.92,
+    "train_steps_per_second": 0.132
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "eval_loss": 0.42792943120002747,
-    "eval_runtime": 443.4778,
-    "eval_samples_per_second": 26.522,
-    "eval_steps_per_second": 0.415
+    "eval_loss": 0.42773160338401794,
+    "eval_runtime": 287.1275,
+    "eval_samples_per_second": 40.964,
+    "eval_steps_per_second": 0.641
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 2745782658662400.0,
-    "train_loss": 0.3825414228548572,
-    "train_runtime": 71090.721,
-    "train_samples_per_second": 9.431,
-    "train_steps_per_second": 0.074
+    "train_loss": 0.38240701185468956,
+    "train_runtime": 39622.8086,
+    "train_samples_per_second": 16.92,
+    "train_steps_per_second": 0.132
 }