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-hinge
   results: []
@@ -15,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-gemma-hinge
 
-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: 0.5250
-- Rewards/chosen: -2.6386
-- Rewards/rejected: -3.9001
-- Rewards/accuracies: 0.7188
-- Rewards/margins: 1.2616
-- Logps/rejected: -440.0739
-- Logps/chosen: -416.4398
-- Logits/rejected: 95.9739
-- Logits/chosen: 101.8169
+- Loss: 0.5273
+- Rewards/chosen: -2.6335
+- Rewards/rejected: -3.8935
+- Rewards/accuracies: 0.7292
+- Rewards/margins: 1.2600
+- Logps/rejected: -439.9419
+- Logps/chosen: -416.3391
+- Logits/rejected: 96.0524
+- Logits/chosen: 101.8806
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.971563981042654,
+    "eval_logits/chosen": 101.8805923461914,
+    "eval_logits/rejected": 96.05239868164062,
+    "eval_logps/chosen": -416.339111328125,
+    "eval_logps/rejected": -439.9419250488281,
+    "eval_loss": 0.5273366570472717,
+    "eval_rewards/accuracies": 0.7291666865348816,
+    "eval_rewards/chosen": -2.633545160293579,
+    "eval_rewards/margins": 1.2600029706954956,
+    "eval_rewards/rejected": -3.893548011779785,
+    "eval_runtime": 119.4302,
+    "eval_samples": 750,
+    "eval_samples_per_second": 6.28,
+    "eval_steps_per_second": 0.201,
     "total_flos": 0.0,
     "train_loss": 0.4740314678503917,
     "train_runtime": 2291.7376,

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": 101.8805923461914,
+    "eval_logits/rejected": 96.05239868164062,
+    "eval_logps/chosen": -416.339111328125,
+    "eval_logps/rejected": -439.9419250488281,
+    "eval_loss": 0.5273366570472717,
+    "eval_rewards/accuracies": 0.7291666865348816,
+    "eval_rewards/chosen": -2.633545160293579,
+    "eval_rewards/margins": 1.2600029706954956,
+    "eval_rewards/rejected": -3.893548011779785,
+    "eval_runtime": 119.4302,
+    "eval_samples": 750,
+    "eval_samples_per_second": 6.28,
+    "eval_steps_per_second": 0.201
+}

runs/Apr27_16-40-45_660111d13776/events.out.tfevents.1714235380.660111d13776.64926.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4c27d471cbe44ac67012d3908d4834b0c7903b252e1669e73c263f5322827b
+size 815