End of training

README.md

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- AmberYifan/safeRLHF-SFT
 model-index:
 - name: mistral-safe-sft-full
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral-safe-sft-full
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the AmberYifan/safeRLHF-SFT dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.2626
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 1.2626361846923828,
+    "eval_runtime": 50.2072,
+    "eval_samples": 8340,
+    "eval_samples_per_second": 13.126,
+    "eval_steps_per_second": 0.418,
     "total_flos": 19367618150400.0,
     "train_loss": 1.3619260220914273,
     "train_runtime": 1878.7186,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.43.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.2626361846923828,
+    "eval_runtime": 50.2072,
+    "eval_samples": 8340,
+    "eval_samples_per_second": 13.126,
+    "eval_steps_per_second": 0.418
+}