End of training

README.md

@@ -3,10 +3,16 @@ 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
 - alignment-handbook
 - generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-7b-align-scan-0.0-0.0-cosine-2
   results: []
@@ -17,17 +23,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan-0.0-0.0-cosine-2
 
-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:
-- Logits/chosen: 2.2227
-- Logits/rejected: 2.3998
-- Logps/chosen: -231.4086
-- Logps/rejected: -327.2254
-- Loss: 0.6710
-- Rewards/accuracies: 0.3155
-- Rewards/chosen: -0.1518
-- Rewards/margins: 0.0862
-- Rewards/rejected: -0.2380
+- Loss: 1.7260
+- Rewards/chosen: -5.0723
+- Rewards/rejected: -8.1169
+- Rewards/accuracies: 0.3075
+- Rewards/margins: 3.0445
+- Logps/rejected: -601.5961
+- Logps/chosen: -399.7386
+- Logits/rejected: 4.1594
+- Logits/chosen: 3.9982
 
 ## Model description
 

all_results.json

@@ -4,15 +4,15 @@
     "eval_logits/rejected": 4.15942907333374,
     "eval_logps/chosen": -399.73858642578125,
     "eval_logps/rejected": -601.5961303710938,
-    "eval_loss": 4.579452037811279,
+    "eval_loss": 1.72599458694458,
     "eval_rewards/accuracies": 0.3075396716594696,
-    "eval_rewards/chosen": -16.14712142944336,
-    "eval_rewards/margins": 9.691844940185547,
-    "eval_rewards/rejected": -25.838966369628906,
-    "eval_runtime": 114.6496,
+    "eval_rewards/chosen": -5.072336673736572,
+    "eval_rewards/margins": 3.0445241928100586,
+    "eval_rewards/rejected": -8.116861343383789,
+    "eval_runtime": 114.7048,
     "eval_samples": 2000,
-    "eval_samples_per_second": 17.444,
-    "eval_steps_per_second": 0.55,
+    "eval_samples_per_second": 17.436,
+    "eval_steps_per_second": 0.549,
     "total_flos": 0.0,
     "train_loss": 0.0,
     "train_runtime": 0.1474,

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

@@ -4,13 +4,13 @@
     "eval_logits/rejected": 4.15942907333374,
     "eval_logps/chosen": -399.73858642578125,
     "eval_logps/rejected": -601.5961303710938,
-    "eval_loss": 4.579452037811279,
+    "eval_loss": 1.72599458694458,
     "eval_rewards/accuracies": 0.3075396716594696,
-    "eval_rewards/chosen": -16.14712142944336,
-    "eval_rewards/margins": 9.691844940185547,
-    "eval_rewards/rejected": -25.838966369628906,
-    "eval_runtime": 114.6496,
+    "eval_rewards/chosen": -5.072336673736572,
+    "eval_rewards/margins": 3.0445241928100586,
+    "eval_rewards/rejected": -8.116861343383789,
+    "eval_runtime": 114.7048,
     "eval_samples": 2000,
-    "eval_samples_per_second": 17.444,
-    "eval_steps_per_second": 0.55
+    "eval_samples_per_second": 17.436,
+    "eval_steps_per_second": 0.549
 }

runs/Sep28_08-23-57_qa-a100-005.crc.nd.edu/events.out.tfevents.1727526761.qa-a100-005.crc.nd.edu.128253.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c91ec5353cdddb8a31b1ad513ce835130153a400cee35f0187a353b02f0d63
+size 828