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
@@ -20,6 +24,8 @@ should probably proofread and complete it, then remove this comment. -->
 # mistral_llama_2_code_math_2_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: 0.5575
 
 ## Model description
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 0.9565217391304348,
-    "eval_loss": 0.557129979133606,
-    "eval_runtime": 0.7332,
+    "eval_loss": 0.5574637651443481,
+    "eval_runtime": 0.7263,
     "eval_samples": 20,
-    "eval_samples_per_second": 4.092,
-    "eval_steps_per_second": 1.364,
+    "eval_samples_per_second": 4.13,
+    "eval_steps_per_second": 1.377,
     "total_flos": 1099243192320.0,
     "train_loss": 0.7459995963356711,
     "train_runtime": 63.2097,

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": 0.9565217391304348,
-    "eval_loss": 0.557129979133606,
-    "eval_runtime": 0.7332,
+    "eval_loss": 0.5574637651443481,
+    "eval_runtime": 0.7263,
     "eval_samples": 20,
-    "eval_samples_per_second": 4.092,
-    "eval_steps_per_second": 1.364
+    "eval_samples_per_second": 4.13,
+    "eval_steps_per_second": 1.377
 }

runs/Jan20_00-45-21_dgx-a100-14/events.out.tfevents.1737330762.dgx-a100-14.626547.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c831473a6505cbc4485b2a3045b60e75325c6b917586a2053ea455ca3eb7649
+size 354