End of training

README.md

@@ -2,9 +2,15 @@
 license: apache-2.0
 base_model: alignment-handbook/zephyr-7b-sft-full
 tags:
+- alignment-handbook
+- ndcg
+- trl
+- generated_from_trainer
 - trl
 - ndcg
 - generated_from_trainer
+datasets:
+- yangzhao02/ListUltraFeedback
 model-index:
 - name: mistral-7b-base-dpo-list_mle-listsize_8-beta_0.05-batchsize_128
   results: []
@@ -16,11 +22,11 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/zhaoyang1/huggingface/runs/xug99v0l)
 # mistral-7b-base-dpo-list_mle-listsize_8-beta_0.05-batchsize_128
 
-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 yangzhao02/ListUltraFeedback dataset.
 It achieves the following results on the evaluation set:
-- Logits: -2.2186
-- Logps: -311.0428
-- Loss: 6.9513
+- Loss: 6.7425
+- Logps: -316.4365
+- Logits: -2.1289
 
 ## Model description
 

all_results.json

@@ -1,5 +1,12 @@
 {
     "epoch": 0.9981298423724285,
+    "eval_logits": -2.128877639770508,
+    "eval_logps": -316.4365234375,
+    "eval_loss": 6.7425031661987305,
+    "eval_runtime": 500.6522,
+    "eval_samples": 1968,
+    "eval_samples_per_second": 3.931,
+    "eval_steps_per_second": 0.246,
     "total_flos": 0.0,
     "train_loss": 1.3275885816815067,
     "train_runtime": 8211.0134,

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.42.0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.9981298423724285,
+    "eval_logits": -2.128877639770508,
+    "eval_logps": -316.4365234375,
+    "eval_loss": 6.7425031661987305,
+    "eval_runtime": 500.6522,
+    "eval_samples": 1968,
+    "eval_samples_per_second": 3.931,
+    "eval_steps_per_second": 0.246
+}