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
@@ -18,7 +22,7 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6564
+- Loss: 0.6508
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.6508200764656067,
+    "eval_runtime": 1.4268,
+    "eval_samples": 20,
+    "eval_samples_per_second": 14.017,
+    "eval_steps_per_second": 1.402,
     "total_flos": 12020550467584.0,
     "train_loss": 0.7026914629069242,
     "train_runtime": 689.178,

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": 1.0,
+    "eval_loss": 0.6508200764656067,
+    "eval_runtime": 1.4268,
+    "eval_samples": 20,
+    "eval_samples_per_second": 14.017,
+    "eval_steps_per_second": 1.402
+}

runs/Jan07_20-32-34_dgx-a100-12/events.out.tfevents.1736279689.dgx-a100-12.2334789.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd99257e0b2bc86eb407c78174d2c7b91249eb58dccc13aaa47527361ac299e
+size 354