End of training

README.md

@@ -3,6 +3,10 @@ library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.1
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
@@ -19,6 +23,8 @@ should probably proofread and complete it, then remove this comment. -->
 # mistral_sky_safe_o1_llama_3_8B_default_1000_1000_full
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6050
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.6050006747245789,
+    "eval_runtime": 0.7592,
+    "eval_samples": 20,
+    "eval_samples_per_second": 18.44,
+    "eval_steps_per_second": 1.317,
     "total_flos": 8008771829760.0,
     "train_loss": 0.7614544722941015,
     "train_runtime": 429.8356,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.6050006747245789,
+    "eval_runtime": 0.7592,
+    "eval_samples": 20,
+    "eval_samples_per_second": 18.44,
+    "eval_steps_per_second": 1.317
+}

runs/Jan14_16-38-49_dgx-a100-13/events.out.tfevents.1736870545.dgx-a100-13.3849004.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a9efa74d508384c3c4bb3c83d4b20d0cb4fd743106180eab36d78afe0b8a8f
+size 354