Model save

README.md

@@ -0,0 +1,76 @@
+---
+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-selfgen-old
+  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-selfgen-old
+
+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: 0.0027
+- Rewards/chosen: -1.9349
+- Rewards/rejected: -10.4879
+- Rewards/accuracies: 1.0
+- Rewards/margins: 8.5530
+- Logps/rejected: -1094.3392
+- Logps/chosen: -260.5620
+- Logits/rejected: -2.3781
+- Logits/chosen: -2.6042
+
+## 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: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 16
+- 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.023         | 0.42  | 7000  | 0.0164          | -1.0835        | -8.5927          | 1.0                | 7.5092          | -904.8198      | -175.4290    | -2.8442         | -2.8776       |
+| 0.0052        | 0.83  | 14000 | 0.0026          | -1.9746        | -10.4931         | 1.0                | 8.5185          | -1094.8602     | -264.5324    | -2.3838         | -2.6053       |
+
+
+### 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 sha256:81eee70c6664b1ccf2e1f64419fcf49ade18b8a03cc37b1549869754613705b3
+oid sha256:50759cf5be7f54cff0ccffa960f2af618677be148d442b3dc438a850779b86b8
 size 83946192

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.604215621948242,
+    "eval_logits/rejected": -2.3780710697174072,
+    "eval_logps/chosen": -260.56195068359375,
+    "eval_logps/rejected": -1094.3392333984375,
+    "eval_loss": 0.0027059800922870636,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": -1.9348751306533813,
+    "eval_rewards/margins": 8.553033828735352,
+    "eval_rewards/rejected": -10.487908363342285,
+    "eval_runtime": 3.9022,
+    "eval_samples": 5,
+    "eval_samples_per_second": 1.281,
+    "eval_steps_per_second": 0.256,
+    "train_loss": 0.03956493256323719,
+    "train_runtime": 68990.3604,
+    "train_samples": 134157,
+    "train_samples_per_second": 1.945,
+    "train_steps_per_second": 0.243
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.604215621948242,
+    "eval_logits/rejected": -2.3780710697174072,
+    "eval_logps/chosen": -260.56195068359375,
+    "eval_logps/rejected": -1094.3392333984375,
+    "eval_loss": 0.0027059800922870636,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": -1.9348751306533813,
+    "eval_rewards/margins": 8.553033828735352,
+    "eval_rewards/rejected": -10.487908363342285,
+    "eval_runtime": 3.9022,
+    "eval_samples": 5,
+    "eval_samples_per_second": 1.281,
+    "eval_steps_per_second": 0.256
+}

runs/Feb20_13-41-06_586cb8b6da8c/events.out.tfevents.1708437159.586cb8b6da8c.8117.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b67637d347b1b0f4a86716994b37116505fd7e2c77c5a653894797b7c8d8c12
-size 1021003
+oid sha256:56e93f9cc44f93b2ed9ff9ef47a6a3af1c42d116080871855b9dccb6ec92afe3
+size 1070610

runs/Feb20_13-41-06_586cb8b6da8c/events.out.tfevents.1708506152.586cb8b6da8c.8117.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57917befde6ebe3ed2d8139a120c74577d5410dd793a3b77588caf1ae27cb4a6
+size 841

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.03956493256323719,
+    "train_runtime": 68990.3604,
+    "train_samples": 134157,
+    "train_samples_per_second": 1.945,
+    "train_steps_per_second": 0.243
+}