End of training

README.md

@@ -3,11 +3,15 @@ library_name: transformers
 license: llama3.1
 base_model: meta-llama/Llama-3.1-8B
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- argilla-warehouse/magpie-ultra-v1.0
 model-index:
 - name: Llama-3.1-8B-MagPie-Ultra-500k
   results: []
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama-3.1-8B-MagPie-Ultra-500k
 
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the generator dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the argilla-warehouse/magpie-ultra-v1.0 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5953
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.9994856848962796,
+    "eval_loss": 0.5953422784805298,
+    "eval_runtime": 202.6915,
+    "eval_samples": 24992,
+    "eval_samples_per_second": 48.483,
+    "eval_steps_per_second": 1.52,
     "total_flos": 3663097076121600.0,
     "train_loss": 0.5645236694000604,
     "train_runtime": 46689.0597,

config.json

@@ -31,6 +31,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9994856848962796,
+    "eval_loss": 0.5953422784805298,
+    "eval_runtime": 202.6915,
+    "eval_samples": 24992,
+    "eval_samples_per_second": 48.483,
+    "eval_steps_per_second": 1.52
+}