End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-1.5B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: large_crafting_sft_success
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # large_crafting_sft_success
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the None dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the identity and the large_crafting_sft_success datasets.
 It achieves the following results on the evaluation set:
-- Loss: 0.3886
+- Loss: 0.3746
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 0.9936628643852978,
-    "eval_loss": 0.37712058424949646,
-    "eval_runtime": 10.3775,
-    "eval_samples_per_second": 37.292,
-    "eval_steps_per_second": 4.722,
-    "total_flos": 93124196827136.0,
-    "train_loss": 0.5275116664211766,
-    "train_runtime": 2083.3896,
-    "train_samples_per_second": 9.088,
-    "train_steps_per_second": 0.071
+    "eval_loss": 0.3745827078819275,
+    "eval_runtime": 6.4057,
+    "eval_samples_per_second": 60.415,
+    "eval_steps_per_second": 7.649,
+    "total_flos": 55493244223488.0,
+    "train_loss": 0.5211580756570207,
+    "train_runtime": 1269.1418,
+    "train_samples_per_second": 14.918,
+    "train_steps_per_second": 0.116
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.9936628643852978,
-    "eval_loss": 0.37712058424949646,
-    "eval_runtime": 10.3775,
-    "eval_samples_per_second": 37.292,
-    "eval_steps_per_second": 4.722
+    "eval_loss": 0.3745827078819275,
+    "eval_runtime": 6.4057,
+    "eval_samples_per_second": 60.415,
+    "eval_steps_per_second": 7.649
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.9936628643852978,
-    "total_flos": 93124196827136.0,
-    "train_loss": 0.5275116664211766,
-    "train_runtime": 2083.3896,
-    "train_samples_per_second": 9.088,
-    "train_steps_per_second": 0.071
+    "total_flos": 55493244223488.0,
+    "train_loss": 0.5211580756570207,
+    "train_runtime": 1269.1418,
+    "train_samples_per_second": 14.918,
+    "train_steps_per_second": 0.116
 }

trainer_state.json

@@ -10,126 +10,126 @@
   "log_history": [
     {
       "epoch": 0.06759611322348964,
-      "grad_norm": 7.767644079038259,
+      "grad_norm": 6.16084466512128,
       "learning_rate": 6.666666666666667e-06,
-      "loss": 1.0089,
+      "loss": 1.0855,
       "step": 10
     },
     {
       "epoch": 0.13519222644697929,
-      "grad_norm": 4.34859810909518,
+      "grad_norm": 3.497086396174302,
       "learning_rate": 9.964639423366442e-06,
-      "loss": 0.6297,
+      "loss": 0.7122,
       "step": 20
     },
     {
       "epoch": 0.20278833967046894,
-      "grad_norm": 4.288987850642454,
+      "grad_norm": 2.6933889117498127,
       "learning_rate": 9.68474862499881e-06,
-      "loss": 0.5793,
+      "loss": 0.5732,
       "step": 30
     },
     {
       "epoch": 0.27038445289395857,
-      "grad_norm": 4.544358861090749,
+      "grad_norm": 2.6966538346452094,
       "learning_rate": 9.140746393556853e-06,
-      "loss": 0.5668,
+      "loss": 0.5274,
       "step": 40
     },
     {
       "epoch": 0.33798056611744826,
-      "grad_norm": 3.502106036516604,
+      "grad_norm": 2.709346620508466,
       "learning_rate": 8.363301868506264e-06,
-      "loss": 0.5287,
+      "loss": 0.4945,
       "step": 50
     },
     {
       "epoch": 0.33798056611744826,
-      "eval_loss": 0.47872456908226013,
-      "eval_runtime": 10.4806,
-      "eval_samples_per_second": 36.926,
-      "eval_steps_per_second": 4.675,
+      "eval_loss": 0.4356246590614319,
+      "eval_runtime": 6.3988,
+      "eval_samples_per_second": 60.48,
+      "eval_steps_per_second": 7.658,
       "step": 50
     },
     {
       "epoch": 0.4055766793409379,
-      "grad_norm": 3.3511808877782037,
+      "grad_norm": 3.1656760844291267,
       "learning_rate": 7.396244933600285e-06,
-      "loss": 0.5138,
+      "loss": 0.476,
       "step": 60
     },
     {
       "epoch": 0.47317279256442757,
-      "grad_norm": 3.4962865599588757,
+      "grad_norm": 2.5563614993729598,
       "learning_rate": 6.294095225512604e-06,
-      "loss": 0.4927,
+      "loss": 0.4591,
       "step": 70
     },
     {
       "epoch": 0.5407689057879171,
-      "grad_norm": 3.067612201538514,
+      "grad_norm": 2.392298112754115,
       "learning_rate": 5.118988487730537e-06,
-      "loss": 0.4732,
+      "loss": 0.44,
       "step": 80
     },
     {
       "epoch": 0.6083650190114068,
-      "grad_norm": 3.2219742120208332,
+      "grad_norm": 2.598895314476247,
       "learning_rate": 3.937173552235117e-06,
-      "loss": 0.4755,
+      "loss": 0.4577,
       "step": 90
     },
     {
       "epoch": 0.6759611322348965,
-      "grad_norm": 3.0639384175557667,
+      "grad_norm": 2.3301001202203975,
       "learning_rate": 2.8152774381532033e-06,
-      "loss": 0.4548,
+      "loss": 0.4438,
       "step": 100
     },
     {
       "epoch": 0.6759611322348965,
-      "eval_loss": 0.4024154245853424,
-      "eval_runtime": 10.4735,
-      "eval_samples_per_second": 36.95,
-      "eval_steps_per_second": 4.678,
+      "eval_loss": 0.3885859251022339,
+      "eval_runtime": 6.3869,
+      "eval_samples_per_second": 60.593,
+      "eval_steps_per_second": 7.672,
       "step": 100
     },
     {
       "epoch": 0.7435572454583862,
-      "grad_norm": 2.9634825546836465,
+      "grad_norm": 2.41225835615904,
       "learning_rate": 1.8165491294045596e-06,
-      "loss": 0.4643,
+      "loss": 0.44,
       "step": 110
     },
     {
       "epoch": 0.8111533586818758,
-      "grad_norm": 2.6864984928356512,
+      "grad_norm": 2.3212619903795653,
       "learning_rate": 9.972937953781985e-07,
-      "loss": 0.4229,
+      "loss": 0.4203,
       "step": 120
     },
     {
       "epoch": 0.8787494719053655,
-      "grad_norm": 4.377547771161915,
+      "grad_norm": 2.3281357946059558,
       "learning_rate": 4.036984820916723e-07,
-      "loss": 0.4149,
+      "loss": 0.4026,
       "step": 130
     },
     {
       "epoch": 0.9463455851288551,
-      "grad_norm": 2.8491548740185846,
+      "grad_norm": 2.4364627230218816,
       "learning_rate": 6.922823140906754e-08,
-      "loss": 0.4439,
+      "loss": 0.4334,
       "step": 140
     },
     {
       "epoch": 0.9936628643852978,
       "step": 147,
-      "total_flos": 93124196827136.0,
-      "train_loss": 0.5275116664211766,
-      "train_runtime": 2083.3896,
-      "train_samples_per_second": 9.088,
-      "train_steps_per_second": 0.071
+      "total_flos": 55493244223488.0,
+      "train_loss": 0.5211580756570207,
+      "train_runtime": 1269.1418,
+      "train_samples_per_second": 14.918,
+      "train_steps_per_second": 0.116
     }
   ],
   "logging_steps": 10,
@@ -149,7 +149,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 93124196827136.0,
+  "total_flos": 55493244223488.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null