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-0.0-0.0-linear-3
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan-0.0-0.0-linear-3
 
-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: 0.6495
-- Rewards/chosen: -0.1460
-- Rewards/rejected: -0.2967
-- Rewards/accuracies: 0.3294
-- Rewards/margins: 0.1507
-- Logps/rejected: -102.2009
-- Logps/chosen: -84.8621
-- Logits/rejected: -2.3195
-- Logits/chosen: -2.3414
+- Loss: 0.6455
+- Rewards/chosen: -0.1452
+- Rewards/rejected: -0.3169
+- Rewards/accuracies: 0.3313
+- Rewards/margins: 0.1718
+- Logps/rejected: -103.6337
+- Logps/chosen: -84.7995
+- Logits/rejected: -2.2391
+- Logits/chosen: -2.2616
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 3.0,
+    "eval_logits/chosen": -2.2616169452667236,
+    "eval_logits/rejected": -2.2390596866607666,
+    "eval_logps/chosen": -84.79953002929688,
+    "eval_logps/rejected": -103.63373565673828,
+    "eval_loss": 0.6454610824584961,
+    "eval_rewards/accuracies": 0.3313491940498352,
+    "eval_rewards/chosen": -0.14515721797943115,
+    "eval_rewards/margins": 0.17175434529781342,
+    "eval_rewards/rejected": -0.31691157817840576,
+    "eval_runtime": 113.7128,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.588,
+    "eval_steps_per_second": 0.554,
     "total_flos": 0.0,
     "train_loss": 0.6178496645556556,
     "train_runtime": 3593.4638,

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": 3.0,
+    "eval_logits/chosen": -2.2616169452667236,
+    "eval_logits/rejected": -2.2390596866607666,
+    "eval_logps/chosen": -84.79953002929688,
+    "eval_logps/rejected": -103.63373565673828,
+    "eval_loss": 0.6454610824584961,
+    "eval_rewards/accuracies": 0.3313491940498352,
+    "eval_rewards/chosen": -0.14515721797943115,
+    "eval_rewards/margins": 0.17175434529781342,
+    "eval_rewards/rejected": -0.31691157817840576,
+    "eval_runtime": 113.7128,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.588,
+    "eval_steps_per_second": 0.554
+}

runs/Sep28_05-52-33_qa-a100-005.crc.nd.edu/events.out.tfevents.1727521174.qa-a100-005.crc.nd.edu.104943.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:077ebd6497a8d02dd7a6a93da96e1deb15a876c046290a38c91cc1dc8a9a6023
+size 828