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

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.515625,
+    "eval_logits/rejected": -2.46875,
+    "eval_logps/chosen": -388.0,
+    "eval_logps/rejected": -488.0,
+    "eval_loss": 0.4984453022480011,
+    "eval_rewards/accuracies": 0.77734375,
+    "eval_rewards/chosen": -0.9375,
+    "eval_rewards/margins": 1.0078125,
+    "eval_rewards/rejected": -1.9375,
+    "eval_runtime": 40.583,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 49.282,
+    "eval_steps_per_second": 0.789,
     "total_flos": 0.0,
     "train_loss": 0.0,
     "train_runtime": 1.1662,

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

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.515625,
+    "eval_logits/rejected": -2.46875,
+    "eval_logps/chosen": -388.0,
+    "eval_logps/rejected": -488.0,
+    "eval_loss": 0.4984453022480011,
+    "eval_rewards/accuracies": 0.77734375,
+    "eval_rewards/chosen": -0.9375,
+    "eval_rewards/margins": 1.0078125,
+    "eval_rewards/rejected": -1.9375,
+    "eval_runtime": 40.583,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 49.282,
+    "eval_steps_per_second": 0.789
+}

runs/Nov13_06-18-02_dvhaz-sleeper-cmh-gpu/events.out.tfevents.1731478845.dvhaz-sleeper-cmh-gpu.6261.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c487a672b24cd2823b21573cb6137973069732a28f9cf1533548638be3b1d30
+size 828