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-pubmedqa-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-pubmedqa-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: 0.5835
+- Rewards/chosen: -0.1486
+- Rewards/rejected: -0.4853
+- Rewards/accuracies: 0.7105
+- Rewards/margins: 0.3368
+- Logps/rejected: -314.4243
+- Logps/chosen: -302.0460
+- Logits/rejected: -2.5375
+- Logits/chosen: -2.5889
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5703        | 0.92  | 7000 | 0.5835          | -0.1500        | -0.4872          | 0.7140             | 0.3372          | -314.6089      | -302.1864    | -2.5236         | -2.5765       |
+
+
+### 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 sha256:167a5bd968615daddbd16f7adeab90f2d8d4f1134bfa2bb5b71ade2e9f140353
+oid sha256:908406a982aed53efb59ba54e454dd03c4a473ff904ac00d58c771d45caecdc2
 size 83946192

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.5889480113983154,
+    "eval_logits/rejected": -2.5375468730926514,
+    "eval_logps/chosen": -302.0460205078125,
+    "eval_logps/rejected": -314.4243469238281,
+    "eval_loss": 0.5835465788841248,
+    "eval_rewards/accuracies": 0.7105000019073486,
+    "eval_rewards/chosen": -0.1485649198293686,
+    "eval_rewards/margins": 0.33676549792289734,
+    "eval_rewards/rejected": -0.4853304326534271,
+    "eval_runtime": 1163.5942,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 1.719,
+    "eval_steps_per_second": 0.215,
+    "train_loss": 0.6024045768410584,
+    "train_runtime": 59158.061,
+    "train_samples": 61135,
+    "train_samples_per_second": 1.033,
+    "train_steps_per_second": 0.129
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.5889480113983154,
+    "eval_logits/rejected": -2.5375468730926514,
+    "eval_logps/chosen": -302.0460205078125,
+    "eval_logps/rejected": -314.4243469238281,
+    "eval_loss": 0.5835465788841248,
+    "eval_rewards/accuracies": 0.7105000019073486,
+    "eval_rewards/chosen": -0.1485649198293686,
+    "eval_rewards/margins": 0.33676549792289734,
+    "eval_rewards/rejected": -0.4853304326534271,
+    "eval_runtime": 1163.5942,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 1.719,
+    "eval_steps_per_second": 0.215
+}

runs/Jan17_07-21-05_hrsung-a100/events.out.tfevents.1705476496.hrsung-a100.134878.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dae8338ef646a19e7468af26c889631a414d931857b0a0335f27457c44f3307d
-size 449682
+oid sha256:aafbbe01e7515a57394bd9db52e711a9ee752117cc6548fa4447096e4c3de93b
+size 490612

runs/Jan17_07-21-05_hrsung-a100/events.out.tfevents.1705536818.hrsung-a100.134878.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e384cd983a4f01dae5b029fdefb6af3beb989cb24d255a6fb8ae76596eb91c
+size 828

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.6024045768410584,
+    "train_runtime": 59158.061,
+    "train_samples": 61135,
+    "train_samples_per_second": 1.033,
+    "train_steps_per_second": 0.129
+}