End of training

README.md

@@ -3,22 +3,26 @@ library_name: transformers
 license: llama3.2
 base_model: meta-llama/Llama-3.2-3B
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 model-index:
-- name: llama_3_2_3B_tulu3
+- name: meta-llama/Llama-3.2-3B
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# llama_3_2_3B_tulu3
+# meta-llama/Llama-3.2-3B
 
 This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6899
+- Loss: 0.6898
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9999655896218299,
+    "eval_loss": 0.6898318529129028,
+    "eval_runtime": 52.6908,
+    "eval_samples": 5000,
+    "eval_samples_per_second": 94.893,
+    "eval_steps_per_second": 2.98,
     "total_flos": 1437402890797056.0,
     "train_loss": 0.7255030241491708,
     "train_runtime": 38613.5919,

config.json

@@ -32,6 +32,6 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.48.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9999655896218299,
+    "eval_loss": 0.6898318529129028,
+    "eval_runtime": 52.6908,
+    "eval_samples": 5000,
+    "eval_samples_per_second": 94.893,
+    "eval_steps_per_second": 2.98
+}