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/uf_rlced_conifer
 model-index:
 - name: uf-rlced-conifer-zephyr-7b-dpo-full
   results: []
@@ -16,7 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # uf-rlced-conifer-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 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/uf_rlced_conifer dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2394
+- Rewards/chosen: -3.9893
+- Rewards/rejected: -8.8250
+- Rewards/accuracies: 0.8825
+- Rewards/margins: 4.8357
+- Logps/rejected: -1287.4072
+- Logps/chosen: -786.9863
+- Logits/rejected: 3.4289
+- Logits/chosen: 1.1336
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9993060374739764,
+    "eval_logits/chosen": 1.1335889101028442,
+    "eval_logits/rejected": 3.4289302825927734,
+    "eval_logps/chosen": -786.9862670898438,
+    "eval_logps/rejected": -1287.4072265625,
+    "eval_loss": 0.23935413360595703,
+    "eval_rewards/accuracies": 0.8825187683105469,
+    "eval_rewards/chosen": -3.9893157482147217,
+    "eval_rewards/margins": 4.835687637329102,
+    "eval_rewards/rejected": -8.825004577636719,
+    "eval_runtime": 388.0309,
+    "eval_samples": 8491,
+    "eval_samples_per_second": 21.882,
+    "eval_steps_per_second": 0.343,
     "total_flos": 0.0,
     "train_loss": 0.32248947852187687,
     "train_runtime": 20768.7862,

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": 0.9993060374739764,
+    "eval_logits/chosen": 1.1335889101028442,
+    "eval_logits/rejected": 3.4289302825927734,
+    "eval_logps/chosen": -786.9862670898438,
+    "eval_logps/rejected": -1287.4072265625,
+    "eval_loss": 0.23935413360595703,
+    "eval_rewards/accuracies": 0.8825187683105469,
+    "eval_rewards/chosen": -3.9893157482147217,
+    "eval_rewards/margins": 4.835687637329102,
+    "eval_rewards/rejected": -8.825004577636719,
+    "eval_runtime": 388.0309,
+    "eval_samples": 8491,
+    "eval_samples_per_second": 21.882,
+    "eval_steps_per_second": 0.343
+}