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
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: sft-llama3-8b-itt
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sft-llama3-8b-itt
 
-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 HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0620
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.9989310529128808,
+    "eval_loss": 1.0620321035385132,
+    "eval_runtime": 643.9136,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 20.571,
+    "eval_steps_per_second": 2.572,
     "total_flos": 783053739786240.0,
     "train_loss": 1.0084666737260666,
     "train_runtime": 48199.6175,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9989310529128808,
+    "eval_loss": 1.0620321035385132,
+    "eval_runtime": 643.9136,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 20.571,
+    "eval_steps_per_second": 2.572
+}