Model save

README.md

@@ -0,0 +1,74 @@
+---
+base_model: Magpie-Align/Llama-3.1-8B-Magpie-Mix-300KMT-150KR
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: Llama-3.1-8B-Magpie-Pro-MTR-UltraDPO-1
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/uw-nsl/huggingface/runs/ro30b4xx)
+# Llama-3.1-8B-Magpie-Pro-MTR-UltraDPO-1
+
+This model is a fine-tuned version of [Magpie-Align/Llama-3.1-8B-Magpie-Mix-300KMT-150KR](https://huggingface.co/Magpie-Align/Llama-3.1-8B-Magpie-Mix-300KMT-150KR) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3298
+- Rewards/chosen: -4.9310
+- Rewards/rejected: -6.7966
+- Rewards/accuracies: 0.8952
+- Rewards/margins: 1.8655
+- Logps/rejected: -878.5105
+- Logps/chosen: -698.1248
+- Logits/rejected: -0.5776
+- Logits/chosen: -0.5622
+
+## 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: 1e-06
+- train_batch_size: 2
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 256
+- total_eval_batch_size: 32
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.4439        | 0.4275 | 100  | 0.4168          | -4.9964        | -6.3086          | 0.8145             | 1.3123          | -829.7151      | -704.6570    | -0.5150         | -0.5001       |
+| 0.343         | 0.8549 | 200  | 0.3298          | -4.9310        | -6.7966          | 0.8952             | 1.8655          | -878.5105      | -698.1248    | -0.5776         | -0.5622       |
+
+
+### Framework versions
+
+- Transformers 4.43.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9959925193694897,
+    "total_flos": 0.0,
+    "train_loss": 0.45488236134655996,
+    "train_runtime": 10577.9564,
+    "train_samples": 59875,
+    "train_samples_per_second": 5.66,
+    "train_steps_per_second": 0.022
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.43.2"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9959925193694897,
+    "total_flos": 0.0,
+    "train_loss": 0.45488236134655996,
+    "train_runtime": 10577.9564,
+    "train_samples": 59875,
+    "train_samples_per_second": 5.66,
+    "train_steps_per_second": 0.022
+}