End of training

README.md

@@ -1,6 +1,8 @@
 ---
+license: other
 base_model: qnguyen3/Mixtral-4x400M
 tags:
+- llama-factory
 - generated_from_trainer
 model-index:
 - name: mixtral-4x-400M-pt
@@ -12,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mixtral-4x-400M-pt
 
-This model is a fine-tuned version of [qnguyen3/Mixtral-4x400M](https://huggingface.co/qnguyen3/Mixtral-4x400M) on the None dataset.
+This model is a fine-tuned version of [qnguyen3/Mixtral-4x400M](https://huggingface.co/qnguyen3/Mixtral-4x400M) on the thevault_function_xsmall, the redpajama_v2_small, the tiny_strange_textbooks, the tiny_textbooks, the code_textbook, the the_stack_smol_xl_cleaned, the refinedweb_1m_medium, the minipile, the goodwiki, the wikipedia_vi, the mathpile_arxiv_medium, the mathpile_stackexchange, the mathpile_proofpile, the mathpile_wikipedia, the thevault_class_xsmall, the tiny_stories_envi, the pretrain_instruct_1, the pretrain_instruct_2 and the pretrain_instruct_code datasets.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.6263817286927247,
+    "train_runtime": 649257.4466,
+    "train_samples_per_second": 60.135,
+    "train_steps_per_second": 0.059
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.6263817286927247,
+    "train_runtime": 649257.4466,
+    "train_samples_per_second": 60.135,
+    "train_steps_per_second": 0.059
+}