End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: alignment-handbook/zephyr-7b-sft-full
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-7b-align-scan-7e-07-0.99-cosine-2.0
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan-7e-07-0.99-cosine-2.0
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1824
-- Rewards/chosen: 2.5463
-- Rewards/rejected: 0.5342
-- Rewards/accuracies: 0.3452
-- Rewards/margins: 2.0120
-- Logps/rejected: -80.5887
-- Logps/chosen: -71.9193
-- Logits/rejected: -2.6463
-- Logits/chosen: -2.6632
+- Loss: 1.1727
+- Rewards/chosen: 2.6978
+- Rewards/rejected: 0.6816
+- Rewards/accuracies: 0.3472
+- Rewards/margins: 2.0163
+- Logps/rejected: -80.4399
+- Logps/chosen: -71.7662
+- Logits/rejected: -2.6444
+- Logits/chosen: -2.6613
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 2.0,
+    "eval_logits/chosen": -2.6612839698791504,
+    "eval_logits/rejected": -2.6444251537323,
+    "eval_logps/chosen": -71.76615142822266,
+    "eval_logps/rejected": -80.43990325927734,
+    "eval_loss": 1.1726570129394531,
+    "eval_rewards/accuracies": 0.3472222089767456,
+    "eval_rewards/chosen": 2.6978304386138916,
+    "eval_rewards/margins": 2.016267776489258,
+    "eval_rewards/rejected": 0.6815626621246338,
+    "eval_runtime": 113.5073,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.62,
+    "eval_steps_per_second": 0.555,
     "total_flos": 0.0,
     "train_loss": 0.6661292189920406,
     "train_runtime": 6507.4651,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "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": 2.0,
+    "eval_logits/chosen": -2.6612839698791504,
+    "eval_logits/rejected": -2.6444251537323,
+    "eval_logps/chosen": -71.76615142822266,
+    "eval_logps/rejected": -80.43990325927734,
+    "eval_loss": 1.1726570129394531,
+    "eval_rewards/accuracies": 0.3472222089767456,
+    "eval_rewards/chosen": 2.6978304386138916,
+    "eval_rewards/margins": 2.016267776489258,
+    "eval_rewards/rejected": 0.6815626621246338,
+    "eval_runtime": 113.5073,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.62,
+    "eval_steps_per_second": 0.555
+}

runs/Sep27_15-55-45_qa-a100-005.crc.nd.edu/events.out.tfevents.1727474020.qa-a100-005.crc.nd.edu.4125860.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a54764a54e3e7b817b806f33007c15d40309bc0e1ac3e1a32be57554ed9a0a8
+size 828