End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 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:
+- data/zephyr_uf_rlced_conifer_ref
 model-index:
 - name: uf-rlced-conifer-zephyr-7b-group-dpo-no-clip
   results: []
@@ -16,7 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # uf-rlced-conifer-zephyr-7b-group-dpo-no-clip
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown 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 data/zephyr_uf_rlced_conifer_ref dataset.
+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: -314.9812
+- Logps/chosen: -425.9340
+- Logits/rejected: -2.6874
+- Logits/chosen: -2.7334
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.7333760261535645,
+    "eval_logits/rejected": -2.687427043914795,
+    "eval_logps/chosen": -425.93402099609375,
+    "eval_logps/rejected": -314.981201171875,
+    "eval_loss": 0.6931471824645996,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": 0.0,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": 0.0,
+    "eval_runtime": 6.0564,
+    "eval_samples": 100,
+    "eval_samples_per_second": 16.512,
+    "eval_steps_per_second": 0.33,
     "total_flos": 0.0,
     "train_loss": 0.24032984673976898,
     "train_runtime": 97.8271,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.7333760261535645,
+    "eval_logits/rejected": -2.687427043914795,
+    "eval_logps/chosen": -425.93402099609375,
+    "eval_logps/rejected": -314.981201171875,
+    "eval_loss": 0.6931471824645996,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": 0.0,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": 0.0,
+    "eval_runtime": 6.0564,
+    "eval_samples": 100,
+    "eval_samples_per_second": 16.512,
+    "eval_steps_per_second": 0.33
+}