End of training

README.md

@@ -2,12 +2,16 @@
 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.2
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - alignment-handbook
 - generated_from_trainer
 datasets:
-- generator
+- arcee-ai/Zilo-Filtered-SQL-Instruct-v2
 model-index:
 - name: zilo-instruct-v2-sft-filtered
   results: []
@@ -18,7 +22,7 @@ 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-v2 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5474
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 3.0,
-    "eval_loss": 0.40715718269348145,
-    "eval_runtime": 4.0574,
-    "eval_samples": 2958,
-    "eval_samples_per_second": 49.046,
-    "eval_steps_per_second": 0.986,
+    "eval_loss": 0.5474353432655334,
+    "eval_runtime": 2.0253,
+    "eval_samples": 1371,
+    "eval_samples_per_second": 42.463,
+    "eval_steps_per_second": 0.988,
     "total_flos": 8793945538560.0,
     "train_loss": 1.4474536804925828,
     "train_runtime": 170.8306,

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

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "eval_loss": 0.40715718269348145,
-    "eval_runtime": 4.0574,
-    "eval_samples": 2958,
-    "eval_samples_per_second": 49.046,
-    "eval_steps_per_second": 0.986
+    "eval_loss": 0.5474353432655334,
+    "eval_runtime": 2.0253,
+    "eval_samples": 1371,
+    "eval_samples_per_second": 42.463,
+    "eval_steps_per_second": 0.988
 }

runs/May25_01-40-07_5c31577a2818/events.out.tfevents.1716601566.5c31577a2818.17665.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707351d753cc51454f53ba9d86622e722d41568a6ca6a7b8455788c370bacdaf
+size 354