End of training

README.md

@@ -2,11 +2,15 @@
 license: llama3
 base_model: meta-llama/Meta-Llama-3-8B
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- yangzhao02/hh_sft
 model-index:
 - name: llama3-8b-hh-sft
   results: []
@@ -18,7 +22,7 @@ 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/xmawgtp8)
 # llama3-8b-hh-sft
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the yangzhao02/hh_sft dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.5895
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9928057553956835,
+    "eval_loss": 1.5895432233810425,
+    "eval_runtime": 20.6636,
+    "eval_samples": 8552,
+    "eval_samples_per_second": 46.217,
+    "eval_steps_per_second": 0.726,
     "total_flos": 57579405312000.0,
     "train_loss": 1.8519639035929805,
     "train_runtime": 1562.6462,

config.json

@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.42.0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9928057553956835,
+    "eval_loss": 1.5895432233810425,
+    "eval_runtime": 20.6636,
+    "eval_samples": 8552,
+    "eval_samples_per_second": 46.217,
+    "eval_steps_per_second": 0.726
+}