End of training

README.md

@@ -1,16 +1,19 @@
 ---
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 library_name: transformers
-model_name: Meta-Llama-3.1-8B-dpo-full
+model_name: data/Meta-Llama-3.1-8B-sft-full
 tags:
 - generated_from_trainer
+- alignment-handbook
 - trl
 - dpo
 licence: license
 ---
 
-# Model Card for Meta-Llama-3.1-8B-dpo-full
+# Model Card for data/Meta-Llama-3.1-8B-sft-full
 
-This model is a fine-tuned version of [None](https://huggingface.co/None).
+This model is a fine-tuned version of [None](https://huggingface.co/None) on the [['HuggingFaceH4/ultrafeedback_binarized']](https://huggingface.co/datasets/['HuggingFaceH4/ultrafeedback_binarized']) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -0.90234375,
+    "eval_logits/rejected": -0.84765625,
+    "eval_logps/chosen": -370.0,
+    "eval_logps/rejected": -440.0,
+    "eval_loss": 0.5435234308242798,
+    "eval_rewards/accuracies": 0.7734375,
+    "eval_rewards/chosen": -0.80859375,
+    "eval_rewards/margins": 0.66015625,
+    "eval_rewards/rejected": -1.46875,
+    "eval_runtime": 44.7378,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 44.705,
+    "eval_steps_per_second": 0.715,
     "total_flos": 0.0,
     "train_loss": 1.1715184933969665,
     "train_runtime": 4575.3933,

config.json

@@ -31,6 +31,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -0.90234375,
+    "eval_logits/rejected": -0.84765625,
+    "eval_logps/chosen": -370.0,
+    "eval_logps/rejected": -440.0,
+    "eval_loss": 0.5435234308242798,
+    "eval_rewards/accuracies": 0.7734375,
+    "eval_rewards/chosen": -0.80859375,
+    "eval_rewards/margins": 0.66015625,
+    "eval_rewards/rejected": -1.46875,
+    "eval_runtime": 44.7378,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 44.705,
+    "eval_steps_per_second": 0.715
+}

runs/Feb18_05-02-46_h-80-8-a-01/events.out.tfevents.1739860071.h-80-8-a-01.2047664.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ed93ab9d2aab5193889e01d402a3edc4ce3fbdc21a10295874a128ea62e841
+size 828