End of training

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: meta-llama/Meta-Llama-3-8B-Instruct
+base_model: meta-llama/Meta-Llama-3-8B
 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-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](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d398609203acf4e5ed7de998b5bc1727e3acf10cef1a07585419ed75d5bb52ed
+oid sha256:e0d36d3b45bfb96a7cb74f926997aa7b3f96571a4540d46c5f1bcdd688dbc2a2
 size 4370592096

trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 501,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.9940119760479043,
+      "grad_norm": 2.417518377304077,
+      "learning_rate": 9.98003992015968e-08,
+      "loss": 0.9995,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 501,
+      "total_flos": 2.0033559725080576e+16,
+      "train_loss": 0.9991578065944527,
+      "train_runtime": 874.8982,
+      "train_samples_per_second": 2.287,
+      "train_steps_per_second": 0.573
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 501,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0033559725080576e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}