Model save

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: alignment-handbook/zephyr-7b-sft-full
+model-index:
+- name: zephyr-7b-dpo-lora-ultrafeedback
+  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-dpo-lora-ultrafeedback
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5939
+- Rewards/chosen: -0.2154
+- Rewards/rejected: -0.5247
+- Rewards/accuracies: 0.6920
+- Rewards/margins: 0.3093
+- Logps/rejected: -320.4754
+- Logps/chosen: -313.5164
+- Logits/rejected: -2.1488
+- Logits/chosen: -2.2262
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- 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
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5796        | 0.92  | 7000 | 0.5940          | -0.2151        | -0.5243          | 0.6940             | 0.3091          | -320.4359      | -313.4948    | -2.1487         | -2.2261       |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.0

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df85356c9826e577d1c1045d18c0a09e9e75e4ab86bda2895300bc90b4d76817
+oid sha256:23f37fa10cf84ca2927278a4e582b8e40abfee2fdee351127601a65853d75b29
 size 83946192

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.226208448410034,
+    "eval_logits/rejected": -2.1488096714019775,
+    "eval_logps/chosen": -313.5163879394531,
+    "eval_logps/rejected": -320.47540283203125,
+    "eval_loss": 0.5939346551895142,
+    "eval_rewards/accuracies": 0.6919999718666077,
+    "eval_rewards/chosen": -0.21535076200962067,
+    "eval_rewards/margins": 0.30932918190956116,
+    "eval_rewards/rejected": -0.524679958820343,
+    "eval_runtime": 1172.6262,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 1.706,
+    "eval_steps_per_second": 0.213,
+    "train_loss": 0.6084560017191406,
+    "train_runtime": 59476.7244,
+    "train_samples": 61135,
+    "train_samples_per_second": 1.028,
+    "train_steps_per_second": 0.128
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.226208448410034,
+    "eval_logits/rejected": -2.1488096714019775,
+    "eval_logps/chosen": -313.5163879394531,
+    "eval_logps/rejected": -320.47540283203125,
+    "eval_loss": 0.5939346551895142,
+    "eval_rewards/accuracies": 0.6919999718666077,
+    "eval_rewards/chosen": -0.21535076200962067,
+    "eval_rewards/margins": 0.30932918190956116,
+    "eval_rewards/rejected": -0.524679958820343,
+    "eval_runtime": 1172.6262,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 1.706,
+    "eval_steps_per_second": 0.213
+}

runs/Jan15_16-46-47_hrsung-a100-b/events.out.tfevents.1705337312.hrsung-a100-b.4361.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cb5bcc7b2a51910fa1c219c80e0431766ad4f6d903b80a8ce2305e792956dfd
-size 290368
+oid sha256:a324348ac4f2a775e8c3444cc476414eaa48d34627b3cb9d4ae8b2ead4fc00a9
+size 490538

runs/Jan15_16-46-47_hrsung-a100-b/events.out.tfevents.1705397961.hrsung-a100-b.4361.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7de5d10080c33814c370b0e2db01eb92024eab40c816793a2f6c1e14c75daa9
+size 828

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.6084560017191406,
+    "train_runtime": 59476.7244,
+    "train_samples": 61135,
+    "train_samples_per_second": 1.028,
+    "train_steps_per_second": 0.128
+}