End of training

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: meta-llama/Meta-Llama-3-8B
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
 library_name: peft
 license: llama3
 tags:
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # chess-sft-lora-adapter
 
-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 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 None dataset.
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac9fe8124dab0a7b6cbefd18116896f74607adc3059aa9292828dd90fb3803cc
+oid sha256:8436da1d13f39a78aec058c18a651032c7af8f7fed9ee51385a8f4c98f719644
 size 5544997664

trainer_state.json

@@ -10,19 +10,19 @@
   "log_history": [
     {
       "epoch": 2.9940119760479043,
-      "grad_norm": 2.0264816284179688,
+      "grad_norm": 0.9438353180885315,
       "learning_rate": 9.98003992015968e-08,
-      "loss": 0.9075,
+      "loss": 1.0378,
       "step": 500
     },
     {
       "epoch": 3.0,
       "step": 501,
-      "total_flos": 2.157617842277581e+16,
-      "train_loss": 0.9071252518547271,
-      "train_runtime": 914.2434,
-      "train_samples_per_second": 2.189,
-      "train_steps_per_second": 0.548
+      "total_flos": 2.6036531965722624e+16,
+      "train_loss": 1.0371553612326434,
+      "train_runtime": 1237.191,
+      "train_samples_per_second": 1.617,
+      "train_steps_per_second": 0.405
     }
   ],
   "logging_steps": 500,
@@ -42,7 +42,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.157617842277581e+16,
+  "total_flos": 2.6036531965722624e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null