End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # persuasion_simulation_persona_sft_w_promp_3epochs
 
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the persuasion_simulation dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.946236559139785,
-    "total_flos": 3904168919040.0,
-    "train_loss": 0.8688372978265735,
-    "train_runtime": 1181.3244,
-    "train_samples_per_second": 1.877,
-    "train_steps_per_second": 0.117
+    "total_flos": 3976309309440.0,
+    "train_loss": 0.8567031431889188,
+    "train_runtime": 1140.8622,
+    "train_samples_per_second": 1.943,
+    "train_steps_per_second": 0.121
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.946236559139785,
-    "total_flos": 3904168919040.0,
-    "train_loss": 0.8688372978265735,
-    "train_runtime": 1181.3244,
-    "train_samples_per_second": 1.877,
-    "train_steps_per_second": 0.117
+    "total_flos": 3976309309440.0,
+    "train_loss": 0.8567031431889188,
+    "train_runtime": 1140.8622,
+    "train_samples_per_second": 1.943,
+    "train_steps_per_second": 0.121
 }

trainer_state.json

@@ -11,103 +11,103 @@
   "log_history": [
     {
       "epoch": 0.21505376344086022,
-      "grad_norm": 7.996015926817187,
+      "grad_norm": 8.46070883603428,
       "learning_rate": 7.1428571428571436e-06,
-      "loss": 2.2981,
+      "loss": 2.281,
       "step": 10
     },
     {
       "epoch": 0.43010752688172044,
-      "grad_norm": 2.962707682143447,
+      "grad_norm": 2.013915203610999,
       "learning_rate": 9.942341621640558e-06,
-      "loss": 1.0994,
+      "loss": 1.0733,
       "step": 20
     },
     {
       "epoch": 0.6451612903225806,
-      "grad_norm": 1.7445658767729006,
+      "grad_norm": 1.7956971723377748,
       "learning_rate": 9.594789058101154e-06,
-      "loss": 0.9707,
+      "loss": 0.9705,
       "step": 30
     },
     {
       "epoch": 0.8602150537634409,
-      "grad_norm": 1.5507007800350687,
+      "grad_norm": 1.6961156545645073,
       "learning_rate": 8.953878684688492e-06,
-      "loss": 0.9301,
+      "loss": 0.9142,
       "step": 40
     },
     {
       "epoch": 1.064516129032258,
-      "grad_norm": 1.7262461771482085,
+      "grad_norm": 1.8314800502805586,
       "learning_rate": 8.060529912738316e-06,
-      "loss": 0.8727,
+      "loss": 0.8739,
       "step": 50
     },
     {
       "epoch": 1.2795698924731183,
-      "grad_norm": 1.677061241367903,
+      "grad_norm": 1.6076365651648326,
       "learning_rate": 6.971779275566593e-06,
-      "loss": 0.7903,
+      "loss": 0.7693,
       "step": 60
     },
     {
       "epoch": 1.4946236559139785,
-      "grad_norm": 1.6964854513828154,
+      "grad_norm": 1.8941368042951945,
       "learning_rate": 5.757138887522884e-06,
-      "loss": 0.7514,
+      "loss": 0.7425,
       "step": 70
     },
     {
       "epoch": 1.7096774193548387,
-      "grad_norm": 1.7463783101137778,
+      "grad_norm": 1.6194897434909907,
       "learning_rate": 4.49415839006284e-06,
-      "loss": 0.7546,
+      "loss": 0.7411,
       "step": 80
     },
     {
       "epoch": 1.924731182795699,
-      "grad_norm": 1.79920542020065,
+      "grad_norm": 1.7633519262799326,
       "learning_rate": 3.2634737357758994e-06,
-      "loss": 0.7558,
+      "loss": 0.7342,
       "step": 90
     },
     {
       "epoch": 2.129032258064516,
-      "grad_norm": 3.698924921571074,
+      "grad_norm": 4.149990534677345,
       "learning_rate": 2.1436589245260375e-06,
-      "loss": 0.6577,
+      "loss": 0.6493,
       "step": 100
     },
     {
       "epoch": 2.3440860215053765,
-      "grad_norm": 1.9212954432010707,
+      "grad_norm": 1.9290115229564264,
       "learning_rate": 1.2062093865360458e-06,
-      "loss": 0.5443,
+      "loss": 0.5389,
       "step": 110
     },
     {
       "epoch": 2.5591397849462365,
-      "grad_norm": 1.7906293486232936,
+      "grad_norm": 1.8069878203895482,
       "learning_rate": 5.109773021462921e-07,
-      "loss": 0.5612,
+      "loss": 0.536,
       "step": 120
     },
     {
       "epoch": 2.774193548387097,
-      "grad_norm": 1.8644011572770092,
+      "grad_norm": 1.8623419402988957,
       "learning_rate": 1.0235029373752758e-07,
-      "loss": 0.5485,
+      "loss": 0.561,
       "step": 130
     },
     {
       "epoch": 2.946236559139785,
       "step": 138,
-      "total_flos": 3904168919040.0,
-      "train_loss": 0.8688372978265735,
-      "train_runtime": 1181.3244,
-      "train_samples_per_second": 1.877,
-      "train_steps_per_second": 0.117
+      "total_flos": 3976309309440.0,
+      "train_loss": 0.8567031431889188,
+      "train_runtime": 1140.8622,
+      "train_samples_per_second": 1.943,
+      "train_steps_per_second": 0.121
     }
   ],
   "logging_steps": 10,
@@ -127,7 +127,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3904168919040.0,
+  "total_flos": 3976309309440.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null