End of training

README.md

@@ -2,12 +2,13 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-Instruct-v0.2
 datasets:
-- generator
+- arcee-ai/Zilo-Filtered-SQL-Instruct-v2
 model-index:
 - name: zilo-instruct-v2-sft-qlora
   results: []
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zilo-instruct-v2-sft-qlora
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the arcee-ai/Zilo-Filtered-SQL-Instruct-v2 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6246
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.9696969696969697,
+    "eval_loss": 0.6245681643486023,
+    "eval_runtime": 17.323,
+    "eval_samples": 1371,
+    "eval_samples_per_second": 2.482,
+    "eval_steps_per_second": 0.346,
     "total_flos": 2.0566538541072384e+17,
     "train_loss": 0.7671454966473742,
     "train_runtime": 1686.4021,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.994174757281553,
-    "eval_loss": 0.38681623339653015,
-    "eval_runtime": 22.0502,
-    "eval_samples": 1530,
-    "eval_samples_per_second": 4.989,
-    "eval_steps_per_second": 0.635
+    "epoch": 2.9696969696969697,
+    "eval_loss": 0.6245681643486023,
+    "eval_runtime": 17.323,
+    "eval_samples": 1371,
+    "eval_samples_per_second": 2.482,
+    "eval_steps_per_second": 0.346
 }

runs/May25_02-29-05_5c31577a2818/events.out.tfevents.1716605863.5c31577a2818.18685.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76551e628a7aa75b907b34c4f99351f4b54d5d31717440525b854852277035c1
+size 359