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_crafting_train_data
@@ -15,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # filtered_crafting_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_crafting_train_data datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.3811
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 1.0,
-    "eval_loss": 0.3814338147640228,
-    "eval_runtime": 2.4863,
-    "eval_samples_per_second": 29.764,
-    "eval_steps_per_second": 2.011,
+    "eval_loss": 0.38111764192581177,
+    "eval_runtime": 2.5129,
+    "eval_samples_per_second": 29.448,
+    "eval_steps_per_second": 1.99,
     "total_flos": 15031437623296.0,
-    "train_loss": 0.6458730016435895,
-    "train_runtime": 472.1736,
-    "train_samples_per_second": 7.586,
-    "train_steps_per_second": 0.059
+    "train_loss": 0.6441171169281006,
+    "train_runtime": 469.4035,
+    "train_samples_per_second": 7.631,
+    "train_steps_per_second": 0.06
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 1.0,
-    "eval_loss": 0.3814338147640228,
-    "eval_runtime": 2.4863,
-    "eval_samples_per_second": 29.764,
-    "eval_steps_per_second": 2.011
+    "eval_loss": 0.38111764192581177,
+    "eval_runtime": 2.5129,
+    "eval_samples_per_second": 29.448,
+    "eval_steps_per_second": 1.99
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 15031437623296.0,
-    "train_loss": 0.6458730016435895,
-    "train_runtime": 472.1736,
-    "train_samples_per_second": 7.586,
-    "train_steps_per_second": 0.059
+    "train_loss": 0.6441171169281006,
+    "train_runtime": 469.4035,
+    "train_samples_per_second": 7.631,
+    "train_steps_per_second": 0.06
 }

trainer_state.json

@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 0.35714285714285715,
-      "grad_norm": 5.638226668163104,
+      "grad_norm": 5.61340264828652,
       "learning_rate": 8.18711994874345e-06,
-      "loss": 0.8525,
+      "loss": 0.8511,
       "step": 10
     },
     {
       "epoch": 0.7142857142857143,
-      "grad_norm": 4.83116596287387,
+      "grad_norm": 4.685360101473129,
       "learning_rate": 2.320866025105016e-06,
-      "loss": 0.5538,
+      "loss": 0.5519,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 28,
       "total_flos": 15031437623296.0,
-      "train_loss": 0.6458730016435895,
-      "train_runtime": 472.1736,
-      "train_samples_per_second": 7.586,
-      "train_steps_per_second": 0.059
+      "train_loss": 0.6441171169281006,
+      "train_runtime": 469.4035,
+      "train_samples_per_second": 7.631,
+      "train_steps_per_second": 0.06
     }
   ],
   "logging_steps": 10,