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": 2.195,
-    "eval_samples_per_second": 46.014,
-    "eval_steps_per_second": 0.911,
-    "total_flos": 4.249521430997238e+17,
-    "train_loss": 51.85570949978299,
-    "train_runtime": 609.9474,
-    "train_samples_per_second": 9.439,
-    "train_steps_per_second": 0.015
+    "eval_runtime": 2.0141,
+    "eval_samples_per_second": 50.146,
+    "eval_steps_per_second": 0.993,
+    "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
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 2.4,
     "eval_loss": NaN,
-    "eval_runtime": 2.195,
-    "eval_samples_per_second": 46.014,
-    "eval_steps_per_second": 0.911
+    "eval_runtime": 2.0141,
+    "eval_samples_per_second": 50.146,
+    "eval_steps_per_second": 0.993
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.4,
-    "total_flos": 4.249521430997238e+17,
-    "train_loss": 51.85570949978299,
-    "train_runtime": 609.9474,
-    "train_samples_per_second": 9.439,
-    "train_steps_per_second": 0.015
+    "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
 }

trainer_state.json

@@ -8,41 +8,104 @@
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 69.07160949707031,
+      "learning_rate": 5e-06,
+      "loss": 1.9082,
+      "step": 1
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 28.931533813476562,
+      "learning_rate": 5e-06,
+      "loss": 1.829,
+      "step": 2
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": NaN,
+      "learning_rate": 5e-06,
+      "loss": 1.7257,
+      "step": 3
+    },
     {
       "epoch": 0.8,
       "eval_loss": NaN,
-      "eval_runtime": 2.4966,
-      "eval_samples_per_second": 40.454,
-      "eval_steps_per_second": 0.801,
+      "eval_runtime": 2.4891,
+      "eval_samples_per_second": 40.577,
+      "eval_steps_per_second": 0.804,
       "step": 3
     },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": NaN,
+      "learning_rate": 5e-06,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 5e-06,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": NaN,
+      "learning_rate": 5e-06,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": NaN,
+      "learning_rate": 5e-06,
+      "loss": 0.0,
+      "step": 7
+    },
     {
       "epoch": 1.8666666666666667,
       "eval_loss": NaN,
-      "eval_runtime": 2.4813,
-      "eval_samples_per_second": 40.705,
-      "eval_steps_per_second": 0.806,
+      "eval_runtime": 2.4704,
+      "eval_samples_per_second": 40.884,
+      "eval_steps_per_second": 0.81,
       "step": 7
     },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 5e-06,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": NaN,
+      "learning_rate": 5e-06,
+      "loss": 0.0,
+      "step": 9
+    },
     {
       "epoch": 2.4,
       "eval_loss": NaN,
-      "eval_runtime": 1.9517,
-      "eval_samples_per_second": 51.75,
-      "eval_steps_per_second": 1.025,
+      "eval_runtime": 1.9225,
+      "eval_samples_per_second": 52.537,
+      "eval_steps_per_second": 1.04,
       "step": 9
     },
     {
       "epoch": 2.4,
       "step": 9,
-      "total_flos": 4.249521430997238e+17,
-      "train_loss": 51.85570949978299,
-      "train_runtime": 609.9474,
-      "train_samples_per_second": 9.439,
-      "train_steps_per_second": 0.015
+      "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
     }
   ],
-  "logging_steps": 10,
+  "logging_steps": 1.0,
   "max_steps": 9,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
@@ -59,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.249521430997238e+17,
+  "total_flos": 4.249521302148219e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null