End of training

README.md

@@ -2,9 +2,17 @@
 license: apache-2.0
 base_model: alignment-handbook/zephyr-7b-sft-full
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- hh
+- oasst
+- shp
 model-index:
 - name: zephyr-7b-dpo-full
   results: []
@@ -15,7 +23,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-full
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the hh, the oasst and the shp datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.6931
+- Rewards/chosen: 0.0
+- Rewards/rejected: 0.0
+- Rewards/accuracies: 0.0
+- Rewards/margins: 0.0
+- Logps/rejected: -159.4422
+- Logps/chosen: -280.7648
+- Logits/rejected: -2.5764
+- Logits/chosen: -2.6334
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.6333940029144287,
+    "eval_logits/rejected": -2.5763978958129883,
+    "eval_logps/chosen": -280.7647705078125,
+    "eval_logps/rejected": -159.44223022460938,
+    "eval_loss": 0.6931471228599548,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": 0.0,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": 0.0,
+    "eval_runtime": 5.9655,
+    "eval_samples": 100,
+    "eval_samples_per_second": 16.763,
+    "eval_steps_per_second": 0.335,
     "total_flos": 0.0,
     "train_loss": 0.6931471824645996,
     "train_runtime": 29.6161,

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.6333940029144287,
+    "eval_logits/rejected": -2.5763978958129883,
+    "eval_logps/chosen": -280.7647705078125,
+    "eval_logps/rejected": -159.44223022460938,
+    "eval_loss": 0.6931471228599548,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": 0.0,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": 0.0,
+    "eval_runtime": 5.9655,
+    "eval_samples": 100,
+    "eval_samples_per_second": 16.763,
+    "eval_steps_per_second": 0.335
+}