End of training

README.md

@@ -2,10 +2,13 @@
 license: llama3
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: meta-llama/Meta-Llama-3-8B
+datasets:
+- yihanwang617/ultrachat_200k_processed_indicator_0.6_4k
 model-index:
 - name: llama-3-qlora-ultrachat-200k-processed-indicator-0.6
   results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama-3-qlora-ultrachat-200k-processed-indicator-0.6
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown 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 yihanwang617/ultrachat_200k_processed_indicator_0.6_4k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0200
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9997305930800908,
+    "eval_loss": 1.0199960470199585,
+    "eval_runtime": 3788.0149,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 6.101,
+    "eval_steps_per_second": 0.381,
     "total_flos": 3.805178921536717e+16,
     "train_loss": 1.037105345344191,
     "train_runtime": 142567.8806,

config.json

@@ -21,7 +21,7 @@
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.40.1",
   "use_cache": true,
   "vocab_size": 128258

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.9997305930800908,
-    "eval_loss": 1.0235061645507812,
-    "eval_runtime": 3765.5428,
+    "eval_loss": 1.0199960470199585,
+    "eval_runtime": 3788.0149,
     "eval_samples": 23109,
-    "eval_samples_per_second": 6.137,
-    "eval_steps_per_second": 0.384
+    "eval_samples_per_second": 6.101,
+    "eval_steps_per_second": 0.381
 }

runs/Aug21_00-57-59_illidan.cs.ucla.edu/events.out.tfevents.1724374700.illidan.cs.ucla.edu.1343562.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23bd528c2d75e41b7b0ca37868541a4e84cba52d971083dbb781b777addb52e9
+size 359