End of training

README.md

@@ -3,12 +3,16 @@ library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.3
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - alignment-handbook
 - generated_from_trainer
 datasets:
-- generator
+- data/ift
 model-index:
 - name: mistral-7b-ift
   results: []
@@ -19,7 +23,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral-7b-ift
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the data/ift dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0896
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 0.9989023051591658,
-    "eval_loss": 1.0698977708816528,
-    "eval_runtime": 3.487,
+    "eval_loss": 1.0896308422088623,
+    "eval_runtime": 3.5907,
     "eval_samples": 512,
-    "eval_samples_per_second": 76.856,
-    "eval_steps_per_second": 1.434,
+    "eval_samples_per_second": 74.638,
+    "eval_steps_per_second": 1.393,
     "total_flos": 190430796840960.0,
     "train_loss": 1.0385671806859447,
     "train_runtime": 5397.8209,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32770
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.9989023051591658,
-    "eval_loss": 1.0698977708816528,
-    "eval_runtime": 3.487,
+    "eval_loss": 1.0896308422088623,
+    "eval_runtime": 3.5907,
     "eval_samples": 512,
-    "eval_samples_per_second": 76.856,
-    "eval_steps_per_second": 1.434
+    "eval_samples_per_second": 74.638,
+    "eval_steps_per_second": 1.393
 }