End of training

README.md

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.2
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- preference-data
 model-index:
 - name: feedback_p0.1_seed42_level2_style
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # feedback_p0.1_seed42_level2_style
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the preference-data dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.3528
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9992217898832685,
+    "eval_loss": 0.35284245014190674,
+    "eval_runtime": 1.0928,
+    "eval_samples": 10,
+    "eval_samples_per_second": 1.83,
+    "eval_steps_per_second": 0.915,
     "total_flos": 201580263505920.0,
     "train_loss": 0.5411187405403034,
     "train_runtime": 23935.6127,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.43.4",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9992217898832685,
+    "eval_loss": 0.35284245014190674,
+    "eval_runtime": 1.0928,
+    "eval_samples": 10,
+    "eval_samples_per_second": 1.83,
+    "eval_steps_per_second": 0.915
+}

runs/Sep07_03-41-04_COE-CS-sv004/events.out.tfevents.1725705807.COE-CS-sv004.39797.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c61d948bc742720e9e0cc545e60fc9c2cb35f2be37705003f7a0ebb1c006c9f9
+size 359