End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-7B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: ds_no_offload_liger_packing_dataloader
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ds_no_offload_liger_packing_dataloader
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/wikipedia_seed_science dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.177445717318042e+16,
-    "train_loss": 1.0301417509714763,
-    "train_runtime": 973.1743,
-    "train_samples_per_second": 1.773,
+    "train_loss": 1.0297030475404527,
+    "train_runtime": 998.788,
+    "train_samples_per_second": 1.727,
     "train_steps_per_second": 0.018
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.177445717318042e+16,
-    "train_loss": 1.0301417509714763,
-    "train_runtime": 973.1743,
-    "train_samples_per_second": 1.773,
+    "train_loss": 1.0297030475404527,
+    "train_runtime": 998.788,
+    "train_samples_per_second": 1.727,
     "train_steps_per_second": 0.018
 }

trainer_state.json

@@ -10,137 +10,137 @@
   "log_history": [
     {
       "epoch": 0.16666666666666666,
-      "grad_norm": 8.6195098709927,
+      "grad_norm": 8.517590618184434,
       "learning_rate": 5e-06,
-      "loss": 1.2879,
+      "loss": 1.2823,
       "step": 1
     },
     {
       "epoch": 0.3333333333333333,
-      "grad_norm": 9.18504010868732,
+      "grad_norm": 9.018741303869389,
       "learning_rate": 1e-05,
-      "loss": 1.3268,
+      "loss": 1.3191,
       "step": 2
     },
     {
       "epoch": 0.5,
-      "grad_norm": 6.218768040825584,
+      "grad_norm": 6.194292577602835,
       "learning_rate": 9.903926402016153e-06,
-      "loss": 1.2078,
+      "loss": 1.2057,
       "step": 3
     },
     {
       "epoch": 0.6666666666666666,
-      "grad_norm": 3.0252982804718846,
+      "grad_norm": 3.0238144504302857,
       "learning_rate": 9.619397662556434e-06,
-      "loss": 1.1302,
+      "loss": 1.1292,
       "step": 4
     },
     {
       "epoch": 0.8333333333333334,
-      "grad_norm": 6.088666166550111,
+      "grad_norm": 6.123058930313649,
       "learning_rate": 9.157348061512728e-06,
-      "loss": 1.1449,
+      "loss": 1.1441,
       "step": 5
     },
     {
       "epoch": 1.0,
-      "grad_norm": 6.6511885203086525,
+      "grad_norm": 6.677002150212635,
       "learning_rate": 8.535533905932739e-06,
-      "loss": 1.085,
+      "loss": 1.0849,
       "step": 6
     },
     {
       "epoch": 1.1666666666666667,
-      "grad_norm": 6.827809589776133,
+      "grad_norm": 6.8462657438071775,
       "learning_rate": 7.777851165098012e-06,
-      "loss": 1.07,
+      "loss": 1.0696,
       "step": 7
     },
     {
       "epoch": 1.3333333333333333,
-      "grad_norm": 4.930048078986181,
+      "grad_norm": 4.9658494353615055,
       "learning_rate": 6.913417161825449e-06,
-      "loss": 1.0365,
+      "loss": 1.0377,
       "step": 8
     },
     {
       "epoch": 1.5,
-      "grad_norm": 3.183540927096083,
+      "grad_norm": 3.2120863675083706,
       "learning_rate": 5.975451610080643e-06,
-      "loss": 1.0098,
+      "loss": 1.0122,
       "step": 9
     },
     {
       "epoch": 1.6666666666666665,
-      "grad_norm": 2.0474463937732112,
+      "grad_norm": 2.0529561424214315,
       "learning_rate": 5e-06,
-      "loss": 0.9637,
+      "loss": 0.9653,
       "step": 10
     },
     {
       "epoch": 1.8333333333333335,
-      "grad_norm": 2.1859506115193605,
+      "grad_norm": 2.183724835968961,
       "learning_rate": 4.02454838991936e-06,
-      "loss": 0.9329,
+      "loss": 0.9328,
       "step": 11
     },
     {
       "epoch": 2.0,
-      "grad_norm": 2.000136935221579,
+      "grad_norm": 2.0032016849318524,
       "learning_rate": 3.0865828381745515e-06,
-      "loss": 0.9329,
+      "loss": 0.9326,
       "step": 12
     },
     {
       "epoch": 2.1666666666666665,
-      "grad_norm": 1.6376864195190064,
+      "grad_norm": 1.6416897882711012,
       "learning_rate": 2.2221488349019903e-06,
-      "loss": 0.9097,
+      "loss": 0.9089,
       "step": 13
     },
     {
       "epoch": 2.3333333333333335,
-      "grad_norm": 1.3140675009197313,
+      "grad_norm": 1.3188572441305062,
       "learning_rate": 1.4644660940672628e-06,
-      "loss": 0.8905,
+      "loss": 0.8942,
       "step": 14
     },
     {
       "epoch": 2.5,
-      "grad_norm": 1.1399610334807526,
+      "grad_norm": 1.1422224478203058,
       "learning_rate": 8.426519384872733e-07,
-      "loss": 0.9138,
+      "loss": 0.9139,
       "step": 15
     },
     {
       "epoch": 2.6666666666666665,
-      "grad_norm": 0.9070029152199568,
+      "grad_norm": 0.9115534316421354,
       "learning_rate": 3.8060233744356634e-07,
       "loss": 0.9051,
       "step": 16
     },
     {
       "epoch": 2.8333333333333335,
-      "grad_norm": 0.7711669705895277,
+      "grad_norm": 0.7740350777867038,
       "learning_rate": 9.607359798384785e-08,
-      "loss": 0.902,
+      "loss": 0.9043,
       "step": 17
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.6997339491210084,
+      "grad_norm": 0.70433897341803,
       "learning_rate": 0.0,
-      "loss": 0.8931,
+      "loss": 0.8928,
       "step": 18
     },
     {
       "epoch": 3.0,
       "step": 18,
       "total_flos": 6.177445717318042e+16,
-      "train_loss": 1.0301417509714763,
-      "train_runtime": 973.1743,
-      "train_samples_per_second": 1.773,
+      "train_loss": 1.0297030475404527,
+      "train_runtime": 998.788,
+      "train_samples_per_second": 1.727,
       "train_steps_per_second": 0.018
     }
   ],