Upload model

README.md

@@ -1,6 +1,7 @@
 ---
 library_name: transformers
 license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
 tags:
 - llama-factory
 - full

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 4.772812472451072e+16,
-    "train_loss": 0.5341540531345327,
-    "train_runtime": 52223.946,
-    "train_samples_per_second": 27.851,
-    "train_steps_per_second": 0.054
+    "train_loss": 0.0,
+    "train_runtime": 8.8002,
+    "train_samples_per_second": 165280.93,
+    "train_steps_per_second": 323.289
 }

start_end.json

@@ -1 +1 @@
-{"start_time": "2025-06-27 04:50:36", "end_time": "2025-06-27 19:22:51"}
+{"start_time": "2025-06-28 20:43:56", "end_time": "2025-06-28 20:45:49"}

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 4.772812472451072e+16,
-    "train_loss": 0.5341540531345327,
-    "train_runtime": 52223.946,
-    "train_samples_per_second": 27.851,
-    "train_steps_per_second": 0.054
+    "train_loss": 0.0,
+    "train_runtime": 8.8002,
+    "train_samples_per_second": 165280.93,
+    "train_steps_per_second": 323.289
 }

trainer_log.jsonl

@@ -2844,3 +2844,5 @@
 {"current_steps": 2844, "total_steps": 2845, "loss": 0.4757, "lr": 3.011963855659161e-11, "epoch": 4.998242530755712, "percentage": 99.96, "elapsed_time": "14:28:40", "remaining_time": "0:00:18"}
 {"current_steps": 2845, "total_steps": 2845, "loss": 0.4687, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "14:29:00", "remaining_time": "0:00:00"}
 {"current_steps": 2845, "total_steps": 2845, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "14:30:15", "remaining_time": "0:00:00"}
+{"current_steps": 2845, "total_steps": 2845, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 2845, "total_steps": 2845, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}

trainer_state.json

@@ -19927,10 +19927,10 @@
       "epoch": 5.0,
       "step": 2845,
       "total_flos": 4.772812472451072e+16,
-      "train_loss": 0.5341540531345327,
-      "train_runtime": 52223.946,
-      "train_samples_per_second": 27.851,
-      "train_steps_per_second": 0.054
+      "train_loss": 0.0,
+      "train_runtime": 8.8002,
+      "train_samples_per_second": 165280.93,
+      "train_steps_per_second": 323.289
     }
   ],
   "logging_steps": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f9bd04a28c05161cdf4fe4f55751b25e0094c30a2486ae53c8d3d880a6c0175
-size 7416
+oid sha256:515f9e72ee63ddb994fed5d03f3c6b90c4e6ce89629a14e0c19db16c1232fe69
+size 7544