End of training

README.md

@@ -1,9 +1,16 @@
 ---
 library_name: transformers
+base_model: data/OpenELM-1_1B-SFT
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: OpenELM-1_1B-DPO
   results: []
@@ -14,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # OpenELM-1_1B-DPO
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [data/OpenELM-1_1B-SFT](https://huggingface.co/data/OpenELM-1_1B-SFT) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0009
 - Rewards/chosen: -14.5625

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 3.0,
+    "eval_logits/chosen": -13.0,
+    "eval_logits/rejected": -13.0,
+    "eval_logps/chosen": -612.0,
+    "eval_logps/rejected": -632.0,
+    "eval_loss": 1.0008906126022339,
+    "eval_rewards/accuracies": 0.71875,
+    "eval_rewards/chosen": -14.5625,
+    "eval_rewards/margins": 2.609375,
+    "eval_rewards/rejected": -17.125,
+    "eval_runtime": 46.6328,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 42.888,
+    "eval_steps_per_second": 0.686,
     "total_flos": 0.0,
     "train_loss": 0.2962565040964742,
     "train_runtime": 10895.6468,

config.json

@@ -120,6 +120,6 @@
   "share_input_output_layers": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -13.0,
+    "eval_logits/rejected": -13.0,
+    "eval_logps/chosen": -612.0,
+    "eval_logps/rejected": -632.0,
+    "eval_loss": 1.0008906126022339,
+    "eval_rewards/accuracies": 0.71875,
+    "eval_rewards/chosen": -14.5625,
+    "eval_rewards/margins": 2.609375,
+    "eval_rewards/rejected": -17.125,
+    "eval_runtime": 46.6328,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 42.888,
+    "eval_steps_per_second": 0.686
+}

runs/Aug27_11-21-51_xe8545-a100-16/events.out.tfevents.1724761964.xe8545-a100-16.2580519.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce7163f5f17f70c48834d42999fdb4009a2ee75ead0b4f34040eeeb2b7944f38
+size 828