Model save

README.md

@@ -0,0 +1,59 @@
+---
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: lole25/zephyr-7b-irepo-i1
+model-index:
+- name: zephyr-7b-gpo-v3-4-i2
+  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. -->
+
+# zephyr-7b-gpo-v3-4-i2
+
+This model is a fine-tuned version of [lole25/zephyr-7b-irepo-i1](https://huggingface.co/lole25/zephyr-7b-irepo-i1) 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: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- 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 sha256:7afe597be1877c8020e662570d73bd5350ef35e6b9d28740b7ef6d5d6b0dd28c
+oid sha256:c931dc156244e558333d3b4ba45006d6d2d16c6901811e5f7b3e5e6e218612f6
 size 671150064

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.07836547029586065,
+    "train_runtime": 22365.132,
+    "train_samples": 21000,
+    "train_samples_per_second": 0.939,
+    "train_steps_per_second": 0.235
+}

runs/May20_11-54-48_gpu4-119-5/events.out.tfevents.1716170210.gpu4-119-5.718249.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cad290af65cf94b7f4bc486f2fda230afdc24d68f6ffd7aba1f5b873568d4db3
-size 328392
+oid sha256:37892e8f5726034dd4e56fc9a9d4b8da0e3d29dead4779f2bd6eed4160ce8ba6
+size 338256

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.07836547029586065,
+    "train_runtime": 22365.132,
+    "train_samples": 21000,
+    "train_samples_per_second": 0.939,
+    "train_steps_per_second": 0.235
+}