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: zephyr-7b-uf-rlced-conifer-dpo-2e
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-uf-rlced-conifer-dpo-2e
 
-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: 0.2471
-- Rewards/chosen: -3.9472
-- Rewards/rejected: -12.0338
-- Rewards/accuracies: 0.8910
-- Rewards/margins: 8.0866
-- Logps/rejected: -1613.5016
-- Logps/chosen: -779.3055
-- Logits/rejected: 4.5606
-- Logits/chosen: 2.4398
+- Loss: 0.2466
+- Rewards/chosen: -4.8588
+- Rewards/rejected: -13.2530
+- Rewards/accuracies: 0.8966
+- Rewards/margins: 8.3941
+- Logps/rejected: -1735.4203
+- Logps/chosen: -870.4680
+- Logits/rejected: 4.3075
+- Logits/chosen: 1.8380
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.9986120749479528,
+    "eval_logits/chosen": 1.8379676342010498,
+    "eval_logits/rejected": 4.30747127532959,
+    "eval_logps/chosen": -870.468017578125,
+    "eval_logps/rejected": -1735.4202880859375,
+    "eval_loss": 0.24658846855163574,
+    "eval_rewards/accuracies": 0.896616518497467,
+    "eval_rewards/chosen": -4.8588385581970215,
+    "eval_rewards/margins": 8.39414119720459,
+    "eval_rewards/rejected": -13.252979278564453,
+    "eval_runtime": 384.8738,
+    "eval_samples": 8491,
+    "eval_samples_per_second": 22.062,
+    "eval_steps_per_second": 0.346,
     "total_flos": 0.0,
     "train_loss": 0.25082930790053476,
     "train_runtime": 42170.4729,

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": 1.9986120749479528,
+    "eval_logits/chosen": 1.8379676342010498,
+    "eval_logits/rejected": 4.30747127532959,
+    "eval_logps/chosen": -870.468017578125,
+    "eval_logps/rejected": -1735.4202880859375,
+    "eval_loss": 0.24658846855163574,
+    "eval_rewards/accuracies": 0.896616518497467,
+    "eval_rewards/chosen": -4.8588385581970215,
+    "eval_rewards/margins": 8.39414119720459,
+    "eval_rewards/rejected": -13.252979278564453,
+    "eval_runtime": 384.8738,
+    "eval_samples": 8491,
+    "eval_samples_per_second": 22.062,
+    "eval_steps_per_second": 0.346
+}