Model save

README.md

@@ -1,13 +1,10 @@
 ---
 library_name: peft
 tags:
-- alignment-handbook
-- generated_from_trainer
 - trl
 - dpo
+- generated_from_trainer
 base_model: DUAL-GPO/zephyr-7b-dpo-new-lora-v1-merged
-datasets:
-- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-7b-dpo-0k-15k-0.001-i1
   results: []
@@ -18,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-0k-15k-0.001-i1
 
-This model is a fine-tuned version of [DUAL-GPO/zephyr-7b-dpo-new-lora-v1-merged](https://huggingface.co/DUAL-GPO/zephyr-7b-dpo-new-lora-v1-merged) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+This model is a fine-tuned version of [DUAL-GPO/zephyr-7b-dpo-new-lora-v1-merged](https://huggingface.co/DUAL-GPO/zephyr-7b-dpo-new-lora-v1-merged) on the None dataset.
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e8753c127c994ad6d072b0d4af0eb9f73e18b67fdea03a73a225117dc43a62
+oid sha256:65277497f4bcfda126c88a8a578252a6e39122502fa52768d5a706d83c07b43e
 size 671150064

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.6113488140106201,
-    "train_runtime": 13063.964,
+    "train_loss": 0.6029718887329102,
+    "train_runtime": 12868.9286,
     "train_samples": 15000,
-    "train_samples_per_second": 1.148,
-    "train_steps_per_second": 0.096
+    "train_samples_per_second": 1.166,
+    "train_steps_per_second": 0.097
 }

emissions.csv

@@ -1,2 +1,2 @@
 timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
-2024-09-19T23:06:51,codecarbon,7c914d07-c4ea-4a84-bf6c-02a4e62087ad,13063.968004226685,0.006697428912915107,5.126642158606204e-07,42.5,574.926,188.74309015274048,0.15422212819026557,1.9818767648647813,0.6812393140365398,2.817338207091581,Canada,CAN,quebec,,,Linux-5.15.0-84-generic-x86_64-with-glibc2.35,3.10.14,2.2.3,32,Intel(R) Xeon(R) W-3335 CPU @ 3.40GHz,4,4 x NVIDIA GeForce RTX 4090,-71.2,46.8,503.3149070739746,machine,N,1.0
+2024-09-21T22:41:03,codecarbon,4779cf07-aabb-427c-a933-2b2ccf3e1571,12868.933568954468,0.006589353970806968,5.120357437156557e-07,42.5,619.017,188.74309015274048,0.15192064805908323,1.9482302787006744,0.6717245113215625,2.7718754380813246,Canada,CAN,quebec,,,Linux-5.15.0-84-generic-x86_64-with-glibc2.35,3.10.14,2.2.3,32,Intel(R) Xeon(R) W-3335 CPU @ 3.40GHz,4,4 x NVIDIA GeForce RTX 4090,-71.2,46.8,503.3149070739746,machine,N,1.0

runs/Sep21_19-05-32_gpu4-119-5/events.out.tfevents.1726909594.gpu4-119-5.2117342.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15129b46c819cdfbbf5b21accbd9ebcfcb7f0c118295c7368de0a24197b2dd0d
-size 81868
+oid sha256:aee9276878522dbaefff36f7dffa03f53e421b88be2a6cd8bdbfb3414f27f5fe
+size 82856

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.6113488140106201,
-    "train_runtime": 13063.964,
+    "train_loss": 0.6029718887329102,
+    "train_runtime": 12868.9286,
     "train_samples": 15000,
-    "train_samples_per_second": 1.148,
-    "train_steps_per_second": 0.096
+    "train_samples_per_second": 1.166,
+    "train_steps_per_second": 0.097
 }