End of training

README.md

@@ -4,6 +4,7 @@ license: llama3
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: filtered_cooking_train_data
@@ -15,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # filtered_cooking_train_data
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the identity and the filtered_cooking_train_data datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.3774
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 0.9959839357429718,
-    "eval_loss": 0.3804751932621002,
-    "eval_runtime": 2.8877,
-    "eval_samples_per_second": 28.396,
-    "eval_steps_per_second": 2.078,
+    "eval_loss": 0.37736228108406067,
+    "eval_runtime": 2.8915,
+    "eval_samples_per_second": 28.359,
+    "eval_steps_per_second": 2.075,
     "total_flos": 15726579548160.0,
-    "train_loss": 0.5268215767798885,
-    "train_runtime": 523.5655,
-    "train_samples_per_second": 7.609,
+    "train_loss": 0.5279561415795357,
+    "train_runtime": 522.1498,
+    "train_samples_per_second": 7.63,
     "train_steps_per_second": 0.059
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.9959839357429718,
-    "eval_loss": 0.3804751932621002,
-    "eval_runtime": 2.8877,
-    "eval_samples_per_second": 28.396,
-    "eval_steps_per_second": 2.078
+    "eval_loss": 0.37736228108406067,
+    "eval_runtime": 2.8915,
+    "eval_samples_per_second": 28.359,
+    "eval_steps_per_second": 2.075
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.9959839357429718,
     "total_flos": 15726579548160.0,
-    "train_loss": 0.5268215767798885,
-    "train_runtime": 523.5655,
-    "train_samples_per_second": 7.609,
+    "train_loss": 0.5279561415795357,
+    "train_runtime": 522.1498,
+    "train_samples_per_second": 7.63,
     "train_steps_per_second": 0.059
 }

trainer_state.json

@@ -10,32 +10,32 @@
   "log_history": [
     {
       "epoch": 0.321285140562249,
-      "grad_norm": 5.445369306635041,
+      "grad_norm": 5.4018345438242354,
       "learning_rate": 8.83022221559489e-06,
-      "loss": 0.7041,
+      "loss": 0.7064,
       "step": 10
     },
     {
       "epoch": 0.642570281124498,
-      "grad_norm": 4.328424402964958,
+      "grad_norm": 4.66985543573099,
       "learning_rate": 3.5659838364445505e-06,
-      "loss": 0.4644,
+      "loss": 0.4659,
       "step": 20
     },
     {
       "epoch": 0.963855421686747,
-      "grad_norm": 3.519513472010141,
+      "grad_norm": 3.4130652958692216,
       "learning_rate": 3.3808211290284886e-08,
-      "loss": 0.4293,
+      "loss": 0.4287,
       "step": 30
     },
     {
       "epoch": 0.9959839357429718,
       "step": 31,
       "total_flos": 15726579548160.0,
-      "train_loss": 0.5268215767798885,
-      "train_runtime": 523.5655,
-      "train_samples_per_second": 7.609,
+      "train_loss": 0.5279561415795357,
+      "train_runtime": 522.1498,
+      "train_samples_per_second": 7.63,
       "train_steps_per_second": 0.059
     }
   ],