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
@@ -20,7 +24,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.6092
+- Loss: 0.6105
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 0.6104772090911865,
+    "eval_runtime": 0.7136,
+    "eval_samples": 20,
+    "eval_samples_per_second": 7.007,
+    "eval_steps_per_second": 1.401,
     "total_flos": 37321923624960.0,
     "train_loss": 0.3315402416288018,
     "train_runtime": 1986.7751,

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": 3.0,
+    "eval_loss": 0.6104772090911865,
+    "eval_runtime": 0.7136,
+    "eval_samples": 20,
+    "eval_samples_per_second": 7.007,
+    "eval_steps_per_second": 1.401
+}

runs/Jan21_12-50-51_dgx-a100-18/events.out.tfevents.1737462614.dgx-a100-18.3833790.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a63380d2311dc60129eb1b874e53d9e6ad2bea024fed008ccd345b0f1d58f08
+size 359