Model save

README.md

@@ -2,13 +2,10 @@
 license: apache-2.0
 library_name: peft
 tags:
-- alignment-handbook
-- generated_from_trainer
 - trl
 - dpo
+- generated_from_trainer
 base_model: DUAL-GPO/phi-2-sft-lora-ultrachat-merged
-datasets:
-- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: phi-2-kto-i0
   results: []
@@ -19,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # phi-2-kto-i0
 
-This model is a fine-tuned version of [DUAL-GPO/phi-2-sft-lora-ultrachat-merged](https://huggingface.co/DUAL-GPO/phi-2-sft-lora-ultrachat-merged) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+This model is a fine-tuned version of [DUAL-GPO/phi-2-sft-lora-ultrachat-merged](https://huggingface.co/DUAL-GPO/phi-2-sft-lora-ultrachat-merged) on the None dataset.
 
 ## Model description
 

adapter_config.json

@@ -19,9 +19,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "v_proj",
     "q_proj",
-    "k_proj",
     "dense"
   ],
   "task_type": "CAUSAL_LM"

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.09940854217369519,
-    "train_runtime": 5146.4957,
+    "train_loss": 0.0024642594821790128,
+    "train_runtime": 126.2817,
     "train_samples": 61135,
-    "train_samples_per_second": 11.879,
-    "train_steps_per_second": 0.371
+    "train_samples_per_second": 484.116,
+    "train_steps_per_second": 15.125
 }

emissions.csv

@@ -1,2 +1,3 @@
 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
-2024-09-28T23:06:01,codecarbon,4ad68e38-f708-4965-8116-4cc9c3bca396,5146.503284215927,0.0029854159599475927,5.800862828755433e-07,42.5,519.923,188.74309015274048,0.0607566486707992,0.9262474175948083,0.2688400132142028,1.2558440794798107,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
+2024-09-28T23:06:01,codecarbon,4ad68e38-f708-4965-8116-4cc9c3bca396,5146.503284215927,0.0029854159599475,5.800862828755433e-07,42.5,519.923,188.74309015274048,0.0607566486707992,0.9262474175948084,0.2688400132142028,1.2558440794798107,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
+2024-09-29T16:45:43,codecarbon,87cac1bc-8b87-46be-ab6c-0b6d447718ee,126.28920340538025,7.257634908971718e-05,5.746837190567411e-07,42.5,546.663,188.74309015274048,0.0014908947490983539,0.022431209604545567,0.006607838387126199,0.03052994274077012,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/Sep29_16-37-43_gpu4-119-5/events.out.tfevents.1727591910.gpu4-119-5.909115.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda383a0eb6612b032f29c7d81a139119a3f64af7231311341b02b85ba641742
+size 4878

runs/Sep29_16-42-50_gpu4-119-5/events.out.tfevents.1727592217.gpu4-119-5.913570.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f67201e5a7929ce40d98c21cd33f858371026464ba97d335f6dfe252c0c8f61
+size 5866

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.09940854217369519,
-    "train_runtime": 5146.4957,
+    "train_loss": 0.0024642594821790128,
+    "train_runtime": 126.2817,
     "train_samples": 61135,
-    "train_samples_per_second": 11.879,
-    "train_steps_per_second": 0.371
+    "train_samples_per_second": 484.116,
+    "train_steps_per_second": 15.125
 }

trainer_state.json

@@ -2700,10 +2700,10 @@
       "epoch": 1.0,
       "step": 1910,
       "total_flos": 0.0,
-      "train_loss": 0.09940854217369519,
-      "train_runtime": 5146.4957,
-      "train_samples_per_second": 11.879,
-      "train_steps_per_second": 0.371
+      "train_loss": 0.0024642594821790128,
+      "train_runtime": 126.2817,
+      "train_samples_per_second": 484.116,
+      "train_steps_per_second": 15.125
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:625afa71c82fa006a786e5dfa0b0b3878b14b0be4220970c83f97106c3e28b10
+oid sha256:1a4318948f00474f128e9fb9befee37aba1e23f8c248723651fa6427a2b7a9e8
 size 5816