Model save

README.md

@@ -2,13 +2,10 @@
 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: []
@@ -19,9 +16,9 @@ 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 the yihanwang617/ultrachat_200k_processed_indicator_0.6_4k 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0235
+- Loss: 1.0200
 
 ## Model description
 
@@ -58,13 +55,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.008         | 0.9997 | 3247 | 1.0235          |
+| 1.0052        | 0.9997 | 3247 | 1.0200          |
 
 
 ### Framework versions
 
-- PEFT 0.12.0
+- PEFT 0.11.1
 - Transformers 4.40.1
-- Pytorch 2.4.0+cu121
-- Datasets 2.20.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
 - Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17da1e6de1cfeff53707e34e332c3c39a2ab03b5b084699b6d721b87109209e
+oid sha256:e7f28f2416c31005af35616969facbde8fa70cda863715e5098dc5bdef731861
 size 2185327392

all_results.json

@@ -1,14 +1,9 @@
 {
     "epoch": 0.9997305930800908,
-    "eval_loss": 1.0235061645507812,
-    "eval_runtime": 3765.5428,
-    "eval_samples": 23109,
-    "eval_samples_per_second": 6.137,
-    "eval_steps_per_second": 0.384,
-    "total_flos": 4.15615026158633e+16,
-    "train_loss": 1.0426253444200522,
-    "train_runtime": 139956.5138,
+    "total_flos": 3.805178921536717e+16,
+    "train_loss": 1.037105345344191,
+    "train_runtime": 142567.8806,
     "train_samples": 207864,
-    "train_samples_per_second": 1.485,
+    "train_samples_per_second": 1.458,
     "train_steps_per_second": 0.023
 }

runs/Aug21_00-57-59_illidan.cs.ucla.edu/events.out.tfevents.1724228253.illidan.cs.ucla.edu.1343562.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09e4197dd79545352eaad62147fb60cbbe7a363a70b48cd41c45d5977d1b983a
-size 140187
+oid sha256:e01ea537d0aae403f681e6472d92012d2d197c24518ee52f33177a03e25f5628
+size 142711

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 0.9997305930800908,
-    "total_flos": 4.15615026158633e+16,
-    "train_loss": 1.0426253444200522,
-    "train_runtime": 139956.5138,
+    "total_flos": 3.805178921536717e+16,
+    "train_loss": 1.037105345344191,
+    "train_runtime": 142567.8806,
     "train_samples": 207864,
-    "train_samples_per_second": 1.485,
+    "train_samples_per_second": 1.458,
     "train_steps_per_second": 0.023
 }