End of training

README.md

@@ -4,6 +4,7 @@ library_name: transformers
 model_name: zephyr-7b-dpo-full
 tags:
 - generated_from_trainer
+- alignment-handbook
 - trl
 - dpo
 licence: license

all_results.json

@@ -9,9 +9,9 @@
     "eval_rewards/chosen": -0.9375,
     "eval_rewards/margins": 1.0078125,
     "eval_rewards/rejected": -1.9375,
-    "eval_runtime": 40.0099,
+    "eval_runtime": 39.9906,
     "eval_samples": 2000,
-    "eval_samples_per_second": 49.988,
+    "eval_samples_per_second": 50.012,
     "eval_steps_per_second": 0.8,
     "total_flos": 0.0,
     "train_loss": 0.0,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -9,8 +9,8 @@
     "eval_rewards/chosen": -0.9375,
     "eval_rewards/margins": 1.0078125,
     "eval_rewards/rejected": -1.9375,
-    "eval_runtime": 40.0099,
+    "eval_runtime": 39.9906,
     "eval_samples": 2000,
-    "eval_samples_per_second": 49.988,
+    "eval_samples_per_second": 50.012,
     "eval_steps_per_second": 0.8
 }

runs/Nov22_20-16-58_dvhaz-sleeper-cmh-gpu/events.out.tfevents.1732306785.dvhaz-sleeper-cmh-gpu.10458.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a80f7a73465cac7e42f5085ffb07aca063b9ba7c340561cd7e405427bbda900
+size 828