End of training

README.md

@@ -1,17 +1,20 @@
 ---
 base_model: meta-llama/Llama-3.1-8B
+datasets:
+- allenai/ultrafeedback_binarized_cleaned
 library_name: transformers
-model_name: llama3_8b_sft_ultrafb
+model_name: meta-llama/Llama-3.1-8B
 tags:
 - generated_from_trainer
+- alignment-handbook
 - trl
 - sft
 licence: license
 ---
 
-# Model Card for llama3_8b_sft_ultrafb
+# Model Card for meta-llama/Llama-3.1-8B
 
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B).
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the [['allenai/ultrafeedback_binarized_cleaned']](https://huggingface.co/datasets/['allenai/ultrafeedback_binarized_cleaned']) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 1.1813496351242065,
+    "eval_runtime": 2.1935,
+    "eval_samples": 985,
+    "eval_samples_per_second": 93.915,
+    "eval_steps_per_second": 3.191,
     "total_flos": 42608759930880.0,
     "train_loss": 1.261282390239192,
     "train_runtime": 737.9605,

config.json

@@ -31,6 +31,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.175293207168579,
-    "eval_runtime": 2.507,
+    "eval_loss": 1.1813496351242065,
+    "eval_runtime": 2.1935,
     "eval_samples": 985,
-    "eval_samples_per_second": 41.085,
-    "eval_steps_per_second": 1.596
+    "eval_samples_per_second": 93.915,
+    "eval_steps_per_second": 3.191
 }