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
 - alignment-handbook
@@ -21,7 +25,7 @@ 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: 0.5321
+- Loss: 0.5309
 
 ## Model description
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 0.995475113122172,
-    "eval_loss": 0.5321348309516907,
-    "eval_runtime": 0.7256,
+    "eval_loss": 0.5309224128723145,
+    "eval_runtime": 0.7027,
     "eval_samples": 20,
-    "eval_samples_per_second": 6.891,
-    "eval_steps_per_second": 1.378,
+    "eval_samples_per_second": 7.115,
+    "eval_steps_per_second": 1.423,
     "total_flos": 11463536148480.0,
     "train_loss": 0.5680296632376585,
     "train_runtime": 618.7593,

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

@@ -1,8 +1,8 @@
 {
     "epoch": 0.995475113122172,
-    "eval_loss": 0.5321348309516907,
-    "eval_runtime": 0.7256,
+    "eval_loss": 0.5309224128723145,
+    "eval_runtime": 0.7027,
     "eval_samples": 20,
-    "eval_samples_per_second": 6.891,
-    "eval_steps_per_second": 1.378
+    "eval_samples_per_second": 7.115,
+    "eval_steps_per_second": 1.423
 }

runs/Jan20_10-52-56_dgx-a100-16/events.out.tfevents.1737367908.dgx-a100-16.2922240.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2278e73a3974e32e6d79dba4efef7c82913852693508fcf93cfc9074b188ce93
+size 354