End of training

README.md

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.2
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- arcee-ai/Zilo-Filtered-SQL-Instruct
 model-index:
 - name: zilo-instruct-v2-sft-filtered
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zilo-instruct-v2-sft-filtered
 
-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 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4110
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 0.4109707474708557,
+    "eval_runtime": 4.066,
+    "eval_samples": 2958,
+    "eval_samples_per_second": 48.942,
+    "eval_steps_per_second": 0.984,
     "total_flos": 18844169011200.0,
     "train_loss": 0.5794603930579292,
     "train_runtime": 365.3228,

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.4109707474708557,
+    "eval_runtime": 4.066,
+    "eval_samples": 2958,
+    "eval_samples_per_second": 48.942,
+    "eval_steps_per_second": 0.984
+}

runs/May24_22-50-13_5c31577a2818/events.out.tfevents.1716591543.5c31577a2818.7690.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eaef88f2128a6d15206f9f6ed81e30a94f464f7eac30ebd23dd4a0809832280
+size 354