Model save

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: DUAL-GPO/phi-2-sft-lora-ultrachat-merged
+model-index:
+- name: phi-2-irepo-chatml-i0
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# phi-2-irepo-chatml-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 None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 6
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 24
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.2

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b43f924e3743fcbb8cfcdb6a80addaf10cf2b48445167940cc166e3438f4237
+oid sha256:6ea403fea59f47dfb9fd22c1e2a53445f3e6ad948c9dd3418622a4a1047e3b06
 size 335579632

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.04083743233644686,
+    "train_runtime": 25203.2602,
+    "train_samples": 61135,
+    "train_samples_per_second": 2.426,
+    "train_steps_per_second": 0.101
+}

runs/May19_02-03-02_gpu4-119-5/events.out.tfevents.1716048241.gpu4-119-5.2795885.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0016f526d0b4bcf1e3a779e30bad7439e6ed3311d59805e0529bf445510e8e79
-size 163883
+oid sha256:9904d23c93534ea126d55321de44145fc830eafeffc54c73c25112c8eeb65ab7
+size 166773

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.04083743233644686,
+    "train_runtime": 25203.2602,
+    "train_samples": 61135,
+    "train_samples_per_second": 2.426,
+    "train_steps_per_second": 0.101
+}