End of training

README.md

@@ -1,8 +1,11 @@
 ---
 base_model: meta-llama/Meta-Llama-3-8B
+datasets:
+- yihanwang617/WizardLM_70k_processed_indicator_unfiltered_4k
 library_name: peft
 license: llama3
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -16,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama-3-qlora-wizard-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/WizardLM_70k_processed_indicator_unfiltered_4k dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6655
+- Loss: 0.6652
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.998053121958003,
+    "eval_loss": 0.6652320623397827,
+    "eval_runtime": 37.999,
+    "eval_samples": 407,
+    "eval_samples_per_second": 10.711,
+    "eval_steps_per_second": 0.684,
     "total_flos": 7795310658584576.0,
     "train_loss": 0.6907267017260957,
     "train_runtime": 37673.7111,

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": 0.9990265609790016,
-    "eval_loss": 0.6752772331237793,
-    "eval_runtime": 38.0852,
+    "epoch": 1.998053121958003,
+    "eval_loss": 0.6652320623397827,
+    "eval_runtime": 37.999,
     "eval_samples": 407,
-    "eval_samples_per_second": 10.687,
-    "eval_steps_per_second": 0.683
+    "eval_samples_per_second": 10.711,
+    "eval_steps_per_second": 0.684
 }

runs/Sep13_22-50-54_nova.cs.ucla.edu/events.out.tfevents.1726331003.nova.cs.ucla.edu.4131510.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92576a908423107d72c481ac29bd62d77884dbac0b971ba1b59b0e20aeeddb28
+size 359