End of training

README.md

@@ -3,11 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.3
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- data/ift
 model-index:
 - name: mistral-7b-ift
   results: []
@@ -18,7 +22,7 @@ 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: 7.8271
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9987063389391979,
+    "eval_loss": 7.827143669128418,
+    "eval_runtime": 3.1543,
+    "eval_samples": 512,
+    "eval_samples_per_second": 71.965,
+    "eval_steps_per_second": 1.268,
     "total_flos": 161536404357120.0,
     "train_loss": 11.514628536342958,
     "train_runtime": 5043.2067,

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": 100265
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9987063389391979,
+    "eval_loss": 7.827143669128418,
+    "eval_runtime": 3.1543,
+    "eval_samples": 512,
+    "eval_samples_per_second": 71.965,
+    "eval_steps_per_second": 1.268
+}