End of training

README.md

@@ -4,6 +4,7 @@ license: other
 base_model: Qwen/Qwen2.5-3B-Instruct
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 model-index:
 - name: sft_ctx16384
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sft_ctx16384
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the open_r1_math dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.9988942130482865,
+    "total_flos": 6.700673317784781e+16,
+    "train_loss": 0.4786904600803903,
+    "train_runtime": 98131.1995,
+    "train_samples_per_second": 3.317,
+    "train_steps_per_second": 0.207
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.9988942130482865,
+    "total_flos": 6.700673317784781e+16,
+    "train_loss": 0.4786904600803903,
+    "train_runtime": 98131.1995,
+    "train_samples_per_second": 3.317,
+    "train_steps_per_second": 0.207
+}

trainer_log.jsonl

@@ -3283,3 +3283,4 @@
 {"current_steps": 16890, "total_steps": 20345, "loss": 0.1602, "lr": 4.265536082616905e-06, "epoch": 4.149895564565671, "percentage": 83.02, "elapsed_time": "21:24:33", "remaining_time": "4:22:46"}
 {"current_steps": 20345, "total_steps": 20345, "epoch": 4.9988942130482865, "percentage": 100.0, "elapsed_time": "1 day, 3:15:29", "remaining_time": "0:00:00"}
 {"current_steps": 16900, "total_steps": 20345, "loss": 0.1432, "lr": 4.2416020172007606e-06, "epoch": 4.152352868902813, "percentage": 83.07, "elapsed_time": "21:25:13", "remaining_time": "4:21:59"}
+{"current_steps": 16910, "total_steps": 20345, "loss": 0.1483, "lr": 4.2177290624179e-06, "epoch": 4.154810173239956, "percentage": 83.12, "elapsed_time": "21:25:56", "remaining_time": "4:21:13"}