End of training

README.md

@@ -4,6 +4,7 @@ license: llama3
 base_model: meta-llama/Meta-Llama-3-70B-Instruct
 tags:
 - llama-factory
+- lora
 - 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-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) on the identity and the filtered_crafting_train_data datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.3454
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 1.0,
-    "eval_loss": 0.3438876271247864,
-    "eval_runtime": 15.1284,
+    "eval_loss": 0.3453544080257416,
+    "eval_runtime": 15.13,
     "eval_samples_per_second": 4.891,
     "eval_steps_per_second": 0.661,
     "total_flos": 2776730917928960.0,
-    "train_loss": 0.6446950520787921,
-    "train_runtime": 2311.769,
-    "train_samples_per_second": 1.549,
+    "train_loss": 0.6437431148120335,
+    "train_runtime": 2315.5194,
+    "train_samples_per_second": 1.547,
     "train_steps_per_second": 0.012
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 1.0,
-    "eval_loss": 0.3438876271247864,
-    "eval_runtime": 15.1284,
+    "eval_loss": 0.3453544080257416,
+    "eval_runtime": 15.13,
     "eval_samples_per_second": 4.891,
     "eval_steps_per_second": 0.661
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 2776730917928960.0,
-    "train_loss": 0.6446950520787921,
-    "train_runtime": 2311.769,
-    "train_samples_per_second": 1.549,
+    "train_loss": 0.6437431148120335,
+    "train_runtime": 2315.5194,
+    "train_samples_per_second": 1.547,
     "train_steps_per_second": 0.012
 }

trainer_state.json

@@ -10,25 +10,25 @@
   "log_history": [
     {
       "epoch": 0.35714285714285715,
-      "grad_norm": 0.8919971977009766,
+      "grad_norm": 0.4399825973383531,
       "learning_rate": 8.18711994874345e-05,
-      "loss": 0.8992,
+      "loss": 0.9002,
       "step": 10
     },
     {
       "epoch": 0.7142857142857143,
-      "grad_norm": 0.5649379015998761,
+      "grad_norm": 0.4417428627206288,
       "learning_rate": 2.3208660251050158e-05,
-      "loss": 0.549,
+      "loss": 0.5484,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 28,
       "total_flos": 2776730917928960.0,
-      "train_loss": 0.6446950520787921,
-      "train_runtime": 2311.769,
-      "train_samples_per_second": 1.549,
+      "train_loss": 0.6437431148120335,
+      "train_runtime": 2315.5194,
+      "train_samples_per_second": 1.547,
       "train_steps_per_second": 0.012
     }
   ],