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: 0.6151
+- Loss: 0.5877
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.998324958123953,
+    "eval_loss": 0.5877379179000854,
+    "eval_runtime": 2.1174,
+    "eval_samples": 20,
+    "eval_samples_per_second": 20.308,
+    "eval_steps_per_second": 1.417,
     "total_flos": 31145223782400.0,
     "train_loss": 0.6441789157438598,
     "train_runtime": 1674.2168,

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": 0.998324958123953,
+    "eval_loss": 0.5877379179000854,
+    "eval_runtime": 2.1174,
+    "eval_samples": 20,
+    "eval_samples_per_second": 20.308,
+    "eval_steps_per_second": 1.417
+}

runs/Jan14_21-59-25_dgx-a100-13/events.out.tfevents.1736890515.dgx-a100-13.1470520.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdb89e665154a18abc3fb2eff68c9fad8a80c22d1b372a016d32b5013441fb4b
+size 359