End of training

README.md

@@ -2,9 +2,15 @@
 license: other
 base_model: HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- argilla/dpo-mix-7k
 model-index:
 - name: zephyr-7b-gemma-kto-2
   results: []
@@ -15,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-gemma-kto-2
 
-This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-gemma-sft-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft-v0.1) on an unknown dataset.
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-gemma-sft-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft-v0.1) on the argilla/dpo-mix-7k dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2942
-- Rewards/chosen: 1.5244
-- Rewards/rejected: -0.1579
-- Rewards/accuracies: 0.6458
-- Rewards/margins: 1.6823
-- Logps/rejected: -365.2298
-- Logps/chosen: -333.1805
-- Logits/rejected: 108.6414
-- Logits/chosen: 113.8343
+- Loss: 0.2953
+- Rewards/chosen: 1.5010
+- Rewards/rejected: -0.1766
+- Rewards/accuracies: 0.6875
+- Rewards/margins: 1.6776
+- Logps/rejected: -365.6023
+- Logps/chosen: -333.6483
+- Logits/rejected: 108.5893
+- Logits/chosen: 113.8158
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.971563981042654,
+    "eval_logits/chosen": 113.8158187866211,
+    "eval_logits/rejected": 108.58926391601562,
+    "eval_logps/chosen": -333.64825439453125,
+    "eval_logps/rejected": -365.6023254394531,
+    "eval_loss": 0.2953260540962219,
+    "eval_rewards/accuracies": 0.6875,
+    "eval_rewards/chosen": 1.500998854637146,
+    "eval_rewards/margins": 1.6775684356689453,
+    "eval_rewards/rejected": -0.17656946182250977,
+    "eval_runtime": 122.5277,
+    "eval_samples": 750,
+    "eval_samples_per_second": 6.121,
+    "eval_steps_per_second": 0.196,
     "total_flos": 0.0,
     "train_loss": 0.2986852119748409,
     "train_runtime": 2293.3212,

config.json

@@ -24,6 +24,6 @@
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.971563981042654,
+    "eval_logits/chosen": 113.8158187866211,
+    "eval_logits/rejected": 108.58926391601562,
+    "eval_logps/chosen": -333.64825439453125,
+    "eval_logps/rejected": -365.6023254394531,
+    "eval_loss": 0.2953260540962219,
+    "eval_rewards/accuracies": 0.6875,
+    "eval_rewards/chosen": 1.500998854637146,
+    "eval_rewards/margins": 1.6775684356689453,
+    "eval_rewards/rejected": -0.17656946182250977,
+    "eval_runtime": 122.5277,
+    "eval_samples": 750,
+    "eval_samples_per_second": 6.121,
+    "eval_steps_per_second": 0.196
+}

runs/May21_16-27-14_660111d13776/events.out.tfevents.1716308216.660111d13776.3123315.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb8a9ceb5deb937dbee4c9e500bda30e2bb75d9596ac686eefb85a338ef075a4
+size 815