End of training

README.md

@@ -2,9 +2,15 @@
 license: other
 base_model: lewtun/zephyr-7b-gemma-sft
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- argilla/dpo-mix-7k
 model-index:
 - name: zephyr-7b-gemma-dpo
   results: []
@@ -15,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-gemma-dpo
 
-This model is a fine-tuned version of [lewtun/zephyr-7b-gemma-sft](https://huggingface.co/lewtun/zephyr-7b-gemma-sft) on the None dataset.
+This model is a fine-tuned version of [lewtun/zephyr-7b-gemma-sft](https://huggingface.co/lewtun/zephyr-7b-gemma-sft) on the argilla/dpo-mix-7k dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4736
-- Rewards/chosen: -3.4575
-- Rewards/rejected: -4.9556
-- Rewards/accuracies: 0.75
-- Rewards/margins: 1.4980
-- Logps/rejected: -459.1662
-- Logps/chosen: -431.5707
-- Logits/rejected: 86.3863
-- Logits/chosen: 92.7360
+- Loss: 0.4695
+- Rewards/chosen: -3.3746
+- Rewards/rejected: -4.9715
+- Rewards/accuracies: 0.7188
+- Rewards/margins: 1.5970
+- Logps/rejected: -459.4853
+- Logps/chosen: -429.9115
+- Logits/rejected: 86.4684
+- Logits/chosen: 92.8200
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.97,
+    "eval_logits/chosen": 92.81997680664062,
+    "eval_logits/rejected": 86.46841430664062,
+    "eval_logps/chosen": -429.9114685058594,
+    "eval_logps/rejected": -459.4852600097656,
+    "eval_loss": 0.4695254862308502,
+    "eval_rewards/accuracies": 0.71875,
+    "eval_rewards/chosen": -3.3745555877685547,
+    "eval_rewards/margins": 1.5969535112380981,
+    "eval_rewards/rejected": -4.9715094566345215,
+    "eval_runtime": 52.4051,
+    "eval_samples": 750,
+    "eval_samples_per_second": 14.312,
+    "eval_steps_per_second": 0.458,
     "train_loss": 0.38887147261546207,
     "train_runtime": 1183.8142,
     "train_samples": 6750,

config.json

@@ -23,6 +23,6 @@
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.97,
+    "eval_logits/chosen": 92.81997680664062,
+    "eval_logits/rejected": 86.46841430664062,
+    "eval_logps/chosen": -429.9114685058594,
+    "eval_logps/rejected": -459.4852600097656,
+    "eval_loss": 0.4695254862308502,
+    "eval_rewards/accuracies": 0.71875,
+    "eval_rewards/chosen": -3.3745555877685547,
+    "eval_rewards/margins": 1.5969535112380981,
+    "eval_rewards/rejected": -4.9715094566345215,
+    "eval_runtime": 52.4051,
+    "eval_samples": 750,
+    "eval_samples_per_second": 14.312,
+    "eval_steps_per_second": 0.458
+}

runs/Mar01_11-14-37_ip-26-0-170-132/events.out.tfevents.1709293097.ip-26-0-170-132.2208298.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056a7f6db597040a25a4449e5cc73eb025c0f7c3a5b436f829fbf4df0000983a
+size 815