End of training

README.md

@@ -2,18 +2,18 @@
 tags:
 - generated_from_trainer
 model-index:
-- name: sparse_llama_debugging_refined_web_90p_debugging_2024-03-21
+- name: sparse_llama_7b_refined_web_90p_debugging_2024-03-21
   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. -->
 
-# sparse_llama_debugging_refined_web_90p_debugging_2024-03-21
+# sparse_llama_7b_refined_web_90p_debugging_2024-03-21
 
 This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 10.3835
+- Loss: 10.3854
 
 ## Model description
 

config.json

@@ -24,10 +24,10 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "thresholds": [
+    0.1253761202096939,
     0.12938815355300903,
-    0.12938815355300903,
-    0.1313941776752472,
-    0.12337010353803635
+    0.12738214433193207,
+    0.12938815355300903
   ],
   "tie_word_embeddings": false,
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d65535cc9b9fb7093e5694f896267ee8cf27784649db01dddd983548751290
+oid sha256:7b9b881a4f5b50ab5ac0dddd75304c1cde45fbb24c33d519c37ae29f5430eaca
 size 16849208