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: deepspeed_no_offload_liger_packing
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # deepspeed_no_offload_liger_packing
 
-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": 1.0301430821418762,
-    "train_runtime": 1344.4623,
-    "train_samples_per_second": 1.283,
+    "train_loss": 1.0301471551259358,
+    "train_runtime": 1369.5667,
+    "train_samples_per_second": 1.26,
     "train_steps_per_second": 0.013
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.177445717318042e+16,
-    "train_loss": 1.0301430821418762,
-    "train_runtime": 1344.4623,
-    "train_samples_per_second": 1.283,
+    "train_loss": 1.0301471551259358,
+    "train_runtime": 1369.5667,
+    "train_samples_per_second": 1.26,
     "train_steps_per_second": 0.013
 }

trainer_state.json

@@ -10,126 +10,126 @@
   "log_history": [
     {
       "epoch": 0.16666666666666666,
-      "grad_norm": 8.619232815229754,
+      "grad_norm": 8.619556902180115,
       "learning_rate": 5e-06,
       "loss": 1.2879,
       "step": 1
     },
     {
       "epoch": 0.3333333333333333,
-      "grad_norm": 9.185020353866019,
+      "grad_norm": 9.185148001786674,
       "learning_rate": 1e-05,
       "loss": 1.3268,
       "step": 2
     },
     {
       "epoch": 0.5,
-      "grad_norm": 6.2254605457495495,
+      "grad_norm": 6.21988793399097,
       "learning_rate": 9.903926402016153e-06,
-      "loss": 1.2078,
+      "loss": 1.2077,
       "step": 3
     },
     {
       "epoch": 0.6666666666666666,
-      "grad_norm": 3.026242976782905,
+      "grad_norm": 3.024267639292886,
       "learning_rate": 9.619397662556434e-06,
-      "loss": 1.1303,
+      "loss": 1.1302,
       "step": 4
     },
     {
       "epoch": 0.8333333333333334,
-      "grad_norm": 6.087332751080499,
+      "grad_norm": 6.086848302951464,
       "learning_rate": 9.157348061512728e-06,
       "loss": 1.1449,
       "step": 5
     },
     {
       "epoch": 1.0,
-      "grad_norm": 6.643998067532035,
+      "grad_norm": 6.648367965377962,
       "learning_rate": 8.535533905932739e-06,
       "loss": 1.085,
       "step": 6
     },
     {
       "epoch": 1.1666666666666667,
-      "grad_norm": 6.826583750168801,
+      "grad_norm": 6.826755546614342,
       "learning_rate": 7.777851165098012e-06,
       "loss": 1.07,
       "step": 7
     },
     {
       "epoch": 1.3333333333333333,
-      "grad_norm": 4.926483766202997,
+      "grad_norm": 4.926969247356766,
       "learning_rate": 6.913417161825449e-06,
-      "loss": 1.0364,
+      "loss": 1.0365,
       "step": 8
     },
     {
       "epoch": 1.5,
-      "grad_norm": 3.18249016789452,
+      "grad_norm": 3.182590398396509,
       "learning_rate": 5.975451610080643e-06,
       "loss": 1.0098,
       "step": 9
     },
     {
       "epoch": 1.6666666666666665,
-      "grad_norm": 2.0469889935205052,
+      "grad_norm": 2.0472587924156915,
       "learning_rate": 5e-06,
       "loss": 0.9637,
       "step": 10
     },
     {
       "epoch": 1.8333333333333335,
-      "grad_norm": 2.183104516848028,
+      "grad_norm": 2.1875570192977816,
       "learning_rate": 4.02454838991936e-06,
-      "loss": 0.9329,
+      "loss": 0.933,
       "step": 11
     },
     {
       "epoch": 2.0,
-      "grad_norm": 2.0006746954453756,
+      "grad_norm": 2.0017820943533255,
       "learning_rate": 3.0865828381745515e-06,
       "loss": 0.9329,
       "step": 12
     },
     {
       "epoch": 2.1666666666666665,
-      "grad_norm": 1.6389750962631693,
+      "grad_norm": 1.6392658455901905,
       "learning_rate": 2.2221488349019903e-06,
       "loss": 0.9097,
       "step": 13
     },
     {
       "epoch": 2.3333333333333335,
-      "grad_norm": 1.3160047868378082,
+      "grad_norm": 1.3154890817147764,
       "learning_rate": 1.4644660940672628e-06,
-      "loss": 0.8906,
+      "loss": 0.8905,
       "step": 14
     },
     {
       "epoch": 2.5,
-      "grad_norm": 1.1405860982228113,
+      "grad_norm": 1.140367362816781,
       "learning_rate": 8.426519384872733e-07,
       "loss": 0.9138,
       "step": 15
     },
     {
       "epoch": 2.6666666666666665,
-      "grad_norm": 0.9052384886135814,
+      "grad_norm": 0.9062696231115995,
       "learning_rate": 3.8060233744356634e-07,
       "loss": 0.9051,
       "step": 16
     },
     {
       "epoch": 2.8333333333333335,
-      "grad_norm": 0.7712710796268631,
+      "grad_norm": 0.7726459969508455,
       "learning_rate": 9.607359798384785e-08,
       "loss": 0.902,
       "step": 17
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.7003306135502183,
+      "grad_norm": 0.7009952542901746,
       "learning_rate": 0.0,
       "loss": 0.8931,
       "step": 18
@@ -138,9 +138,9 @@
       "epoch": 3.0,
       "step": 18,
       "total_flos": 6.177445717318042e+16,
-      "train_loss": 1.0301430821418762,
-      "train_runtime": 1344.4623,
-      "train_samples_per_second": 1.283,
+      "train_loss": 1.0301471551259358,
+      "train_runtime": 1369.5667,
+      "train_samples_per_second": 1.26,
       "train_steps_per_second": 0.013
     }
   ],