End of training

README.md

@@ -4,6 +4,7 @@ license: llama3
 base_model: meta-llama/Meta-Llama-3-8B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: model
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # model
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the PrincetonPLI/Instruct-SkillMix-SDD dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 2.4,
     "eval_loss": NaN,
-    "eval_runtime": 2.0141,
-    "eval_samples_per_second": 50.146,
-    "eval_steps_per_second": 0.993,
+    "eval_runtime": 2.0791,
+    "eval_samples_per_second": 48.58,
+    "eval_steps_per_second": 0.962,
     "total_flos": 4.249521302148219e+17,
-    "train_loss": 0.606980217827691,
-    "train_runtime": 621.1198,
-    "train_samples_per_second": 9.269,
-    "train_steps_per_second": 0.014
+    "train_loss": 0.4152366585201687,
+    "train_runtime": 603.4863,
+    "train_samples_per_second": 9.54,
+    "train_steps_per_second": 0.015
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 2.4,
     "eval_loss": NaN,
-    "eval_runtime": 2.0141,
-    "eval_samples_per_second": 50.146,
-    "eval_steps_per_second": 0.993
+    "eval_runtime": 2.0791,
+    "eval_samples_per_second": 48.58,
+    "eval_steps_per_second": 0.962
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.4,
     "total_flos": 4.249521302148219e+17,
-    "train_loss": 0.606980217827691,
-    "train_runtime": 621.1198,
-    "train_samples_per_second": 9.269,
-    "train_steps_per_second": 0.014
+    "train_loss": 0.4152366585201687,
+    "train_runtime": 603.4863,
+    "train_samples_per_second": 9.54,
+    "train_steps_per_second": 0.015
 }

trainer_state.json

@@ -10,14 +10,14 @@
   "log_history": [
     {
       "epoch": 0.26666666666666666,
-      "grad_norm": 69.07160949707031,
+      "grad_norm": 67.7900161743164,
       "learning_rate": 5e-06,
       "loss": 1.9082,
       "step": 1
     },
     {
       "epoch": 0.5333333333333333,
-      "grad_norm": 28.931533813476562,
+      "grad_norm": NaN,
       "learning_rate": 5e-06,
       "loss": 1.829,
       "step": 2
@@ -26,15 +26,15 @@
       "epoch": 0.8,
       "grad_norm": NaN,
       "learning_rate": 5e-06,
-      "loss": 1.7257,
+      "loss": 0.0,
       "step": 3
     },
     {
       "epoch": 0.8,
       "eval_loss": NaN,
-      "eval_runtime": 2.4891,
-      "eval_samples_per_second": 40.577,
-      "eval_steps_per_second": 0.804,
+      "eval_runtime": 2.3783,
+      "eval_samples_per_second": 42.467,
+      "eval_steps_per_second": 0.841,
       "step": 3
     },
     {
@@ -68,9 +68,9 @@
     {
       "epoch": 1.8666666666666667,
       "eval_loss": NaN,
-      "eval_runtime": 2.4704,
-      "eval_samples_per_second": 40.884,
-      "eval_steps_per_second": 0.81,
+      "eval_runtime": 2.3676,
+      "eval_samples_per_second": 42.66,
+      "eval_steps_per_second": 0.845,
       "step": 7
     },
     {
@@ -90,19 +90,19 @@
     {
       "epoch": 2.4,
       "eval_loss": NaN,
-      "eval_runtime": 1.9225,
-      "eval_samples_per_second": 52.537,
-      "eval_steps_per_second": 1.04,
+      "eval_runtime": 1.8057,
+      "eval_samples_per_second": 55.934,
+      "eval_steps_per_second": 1.108,
       "step": 9
     },
     {
       "epoch": 2.4,
       "step": 9,
       "total_flos": 4.249521302148219e+17,
-      "train_loss": 0.606980217827691,
-      "train_runtime": 621.1198,
-      "train_samples_per_second": 9.269,
-      "train_steps_per_second": 0.014
+      "train_loss": 0.4152366585201687,
+      "train_runtime": 603.4863,
+      "train_samples_per_second": 9.54,
+      "train_steps_per_second": 0.015
     }
   ],
   "logging_steps": 1.0,