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_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: 0.5571
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9565217391304348,
+    "eval_loss": 0.557129979133606,
+    "eval_runtime": 0.7332,
+    "eval_samples": 20,
+    "eval_samples_per_second": 4.092,
+    "eval_steps_per_second": 1.364,
     "total_flos": 1099243192320.0,
     "train_loss": 0.7461842623623934,
     "train_runtime": 63.413,

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": 0.9565217391304348,
+    "eval_loss": 0.557129979133606,
+    "eval_runtime": 0.7332,
+    "eval_samples": 20,
+    "eval_samples_per_second": 4.092,
+    "eval_steps_per_second": 1.364
+}

runs/Jan20_00-36-07_dgx-a100-13/events.out.tfevents.1737330229.dgx-a100-13.987189.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4650b35c3ac9c2af5b990c61335b7481e25c4b1343193c4b491b16827ddc446
+size 354

runs/Jan20_00-45-21_dgx-a100-14/events.out.tfevents.1737330334.dgx-a100-14.626547.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b16fe9b93f10ac9717c5b2dc5993b8266761de1b88f1c6fa5b13ed2ea5cacd
+size 5858