End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: secmlr/final_model
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: best_n_rationale_poc_agent_final_model_agent_train
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # best_n_rationale_poc_agent_final_model_agent_train
 
-This model is a fine-tuned version of [secmlr/final_model](https://huggingface.co/secmlr/final_model) on an unknown dataset.
+This model is a fine-tuned version of [secmlr/final_model](https://huggingface.co/secmlr/final_model) on the best_n_rationale_poc_agent dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.987241531016278,
+    "total_flos": 4.6211312738788966e+17,
+    "train_loss": 0.7107904120832944,
+    "train_runtime": 62456.134,
+    "train_samples_per_second": 0.437,
+    "train_steps_per_second": 0.009
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.987241531016278,
+    "total_flos": 4.6211312738788966e+17,
+    "train_loss": 0.7107904120832944,
+    "train_runtime": 62456.134,
+    "train_samples_per_second": 0.437,
+    "train_steps_per_second": 0.009
+}