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_sky_o1_0_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: 0.6379
 
 ## Model description
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 0.9863013698630136,
-    "eval_loss": 0.6256111860275269,
-    "eval_runtime": 2.1542,
+    "eval_loss": 0.6379095315933228,
+    "eval_runtime": 2.1065,
     "eval_samples": 20,
-    "eval_samples_per_second": 20.425,
-    "eval_steps_per_second": 1.393,
+    "eval_samples_per_second": 20.888,
+    "eval_steps_per_second": 1.424,
     "total_flos": 3716488888320.0,
     "train_loss": 0.795237746503618,
     "train_runtime": 204.4979,

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": 0.9863013698630136,
-    "eval_loss": 0.6256111860275269,
-    "eval_runtime": 2.1542,
+    "eval_loss": 0.6379095315933228,
+    "eval_runtime": 2.1065,
     "eval_samples": 20,
-    "eval_samples_per_second": 20.425,
-    "eval_steps_per_second": 1.393
+    "eval_samples_per_second": 20.888,
+    "eval_steps_per_second": 1.424
 }

runs/Jan14_23-38-34_dgx-a100-12/events.out.tfevents.1736895573.dgx-a100-12.2654854.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc8798f802632cc3dfb0333cf3fde3eec65e6a0a5f215c4dd1788313539f78f
+size 354