End of training

README.md

@@ -2,9 +2,15 @@
 license: llama2
 base_model: elichen3051/llama2-7b-sft-chat-no-template
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: llama2-7b-sft-chat-no-template-dpo
   results: []
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama2-7b-sft-chat-no-template-dpo
 
-This model is a fine-tuned version of [elichen3051/llama2-7b-sft-chat-no-template](https://huggingface.co/elichen3051/llama2-7b-sft-chat-no-template) on an unknown dataset.
+This model is a fine-tuned version of [elichen3051/llama2-7b-sft-chat-no-template](https://huggingface.co/elichen3051/llama2-7b-sft-chat-no-template) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6026
 - Rewards/chosen: -0.9396

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.998691442030882,
+    "eval_logits/chosen": -1.0320225954055786,
+    "eval_logits/rejected": -1.019870400428772,
+    "eval_logps/chosen": -371.21112060546875,
+    "eval_logps/rejected": -372.5772399902344,
+    "eval_loss": 0.6026462316513062,
+    "eval_rewards/accuracies": 0.656000018119812,
+    "eval_rewards/chosen": -0.9395894408226013,
+    "eval_rewards/margins": 0.3643726706504822,
+    "eval_rewards/rejected": -1.3039621114730835,
+    "eval_runtime": 224.7608,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 8.898,
+    "eval_steps_per_second": 0.556,
     "total_flos": 0.0,
     "train_loss": 0.6240661440405456,
     "train_runtime": 18073.4146,

config.json

@@ -25,6 +25,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32002
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.998691442030882,
+    "eval_logits/chosen": -1.0320225954055786,
+    "eval_logits/rejected": -1.019870400428772,
+    "eval_logps/chosen": -371.21112060546875,
+    "eval_logps/rejected": -372.5772399902344,
+    "eval_loss": 0.6026462316513062,
+    "eval_rewards/accuracies": 0.656000018119812,
+    "eval_rewards/chosen": -0.9395894408226013,
+    "eval_rewards/margins": 0.3643726706504822,
+    "eval_rewards/rejected": -1.3039621114730835,
+    "eval_runtime": 224.7608,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 8.898,
+    "eval_steps_per_second": 0.556
+}

runs/Jun08_09-35-24_40fc03db7258/events.out.tfevents.1717858594.40fc03db7258.8499.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae9bc5cbf7002a7e939c88c6fdfabe2147648ab51ea2dbd550cedc0cd3a37773
+size 828