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-polynomial-1
   results: []
@@ -16,7 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan-0.0-0.0-polynomial-1
 
-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: 0.6726
+- Rewards/chosen: -0.0593
+- Rewards/rejected: -0.1124
+- Rewards/accuracies: 0.3313
+- Rewards/margins: 0.0531
+- Logps/rejected: -104.9959
+- Logps/chosen: -87.0813
+- Logits/rejected: -2.2205
+- Logits/chosen: -2.2392
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.23917293548584,
+    "eval_logits/rejected": -2.2205147743225098,
+    "eval_logps/chosen": -87.08130645751953,
+    "eval_logps/rejected": -104.99590301513672,
+    "eval_loss": 0.6725901961326599,
+    "eval_rewards/accuracies": 0.3313491940498352,
+    "eval_rewards/chosen": -0.05929155647754669,
+    "eval_rewards/margins": 0.05310999974608421,
+    "eval_rewards/rejected": -0.1124015673995018,
+    "eval_runtime": 115.2153,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.359,
+    "eval_steps_per_second": 0.547,
     "total_flos": 0.0,
     "train_loss": 0.6817257404327393,
     "train_runtime": 994.9537,

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": 1.0,
+    "eval_logits/chosen": -2.23917293548584,
+    "eval_logits/rejected": -2.2205147743225098,
+    "eval_logps/chosen": -87.08130645751953,
+    "eval_logps/rejected": -104.99590301513672,
+    "eval_loss": 0.6725901961326599,
+    "eval_rewards/accuracies": 0.3313491940498352,
+    "eval_rewards/chosen": -0.05929155647754669,
+    "eval_rewards/margins": 0.05310999974608421,
+    "eval_rewards/rejected": -0.1124015673995018,
+    "eval_runtime": 115.2153,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.359,
+    "eval_steps_per_second": 0.547
+}

runs/Sep28_08-34-16_qa-a100-005.crc.nd.edu/events.out.tfevents.1727528249.qa-a100-005.crc.nd.edu.130289.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da175cd114934b657e808a96320461b0564a8d279cd485ea12f0293ebe6720b
+size 815