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-complete
+  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-complete
+
+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: 0.0000
+- Rewards/chosen: 0.1952
+- Rewards/rejected: -11.1838
+- Rewards/accuracies: 1.0
+- Rewards/margins: 11.3790
+- Logps/rejected: -1156.6167
+- Logps/chosen: -39.8472
+- Logits/rejected: -2.9309
+- Logits/chosen: -2.9452
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.0001        | 0.42  | 7000  | 0.0000          | 0.1174         | -11.2894         | 1.0                | 11.4068         | -1167.1736     | -47.6243     | -2.9079         | -2.9350       |
+| 0.0002        | 0.83  | 14000 | 0.0000          | 0.1971         | -11.1349         | 1.0                | 11.3320         | -1151.7302     | -39.6554     | -2.9320         | -2.9443       |
+
+
+### 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 sha256:4f960f706489f25a33e4244b167340a5b02cb310b5818605a4ea8be7d71e9581
+oid sha256:edabdfe3d8daf9fb6c3442f6b5a33179b97967b8ff00320a0b45350d0a6ed1c2
 size 83946192

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.945185899734497,
+    "eval_logits/rejected": -2.9309117794036865,
+    "eval_logps/chosen": -39.84721755981445,
+    "eval_logps/rejected": -1156.61669921875,
+    "eval_loss": 2.3733691705274396e-05,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": 0.1952119767665863,
+    "eval_rewards/margins": 11.378995895385742,
+    "eval_rewards/rejected": -11.183783531188965,
+    "eval_runtime": 3.9067,
+    "eval_samples": 5,
+    "eval_samples_per_second": 1.28,
+    "eval_steps_per_second": 0.256,
+    "train_loss": 0.02337361431049117,
+    "train_runtime": 68623.0806,
+    "train_samples": 134157,
+    "train_samples_per_second": 1.955,
+    "train_steps_per_second": 0.244
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.945185899734497,
+    "eval_logits/rejected": -2.9309117794036865,
+    "eval_logps/chosen": -39.84721755981445,
+    "eval_logps/rejected": -1156.61669921875,
+    "eval_loss": 2.3733691705274396e-05,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": 0.1952119767665863,
+    "eval_rewards/margins": 11.378995895385742,
+    "eval_rewards/rejected": -11.183783531188965,
+    "eval_runtime": 3.9067,
+    "eval_samples": 5,
+    "eval_samples_per_second": 1.28,
+    "eval_steps_per_second": 0.256
+}

runs/Feb19_17-15-08_586cb8b6da8c/events.out.tfevents.1708363013.586cb8b6da8c.7930.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:597f48a5579aab107e21aeb593fe3c6ebcf805590994b9f26ed69ede54ee86d4
-size 1021023
+oid sha256:6ca91811d7ed9464f3de2ea9b588ecba51a05457594f544cd6ed0e5129d9e734
+size 1070630

runs/Feb19_17-15-08_586cb8b6da8c/events.out.tfevents.1708431639.586cb8b6da8c.7930.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443c798882bd4ea1acce9e48892aecc10c0635939214432c9311c48cf2720853
+size 841

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.02337361431049117,
+    "train_runtime": 68623.0806,
+    "train_samples": 134157,
+    "train_samples_per_second": 1.955,
+    "train_steps_per_second": 0.244
+}