End of training

README.md

@@ -3,11 +3,15 @@ library_name: transformers
 license: llama3.1
 base_model: meta-llama/Llama-3.1-8B
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: zephyr-8b-sft-full
   results: []
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-8b-sft-full
 
-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 generator dataset.
+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 HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0747
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 1.0747359991073608,
+    "eval_runtime": 548.6722,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 24.526,
+    "eval_steps_per_second": 0.193,
     "total_flos": 1194720315310080.0,
     "train_loss": 0.8973418972260736,
     "train_runtime": 76133.7056,

config.json

@@ -31,6 +31,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.0747359991073608,
+    "eval_runtime": 548.6722,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 24.526,
+    "eval_steps_per_second": 0.193
+}

runs/Jan06_20-18-30_nid002234/events.out.tfevents.1736242969.nid002234.1794199.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73d6b264f988b5cbfa82debde2ed29eb6ddb2a9b204dc030b6a056294f1a52f6
+size 359