Model save

README.md

@@ -0,0 +1,53 @@
+---
+tags:
+- trl
+- online-dpo
+- generated_from_trainer
+model-index:
+- name: qwen2-0.5B-lr-3e-6
+  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. -->
+
+# qwen2-0.5B-lr-3e-6
+
+This model was trained from scratch on an unknown 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: 3e-06
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 512
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0"
+}