初始化项目，由ModelHub XC社区提供模型

Model: jackf857/llama-3-8b-base-new-dpo-hh-helpful-s_star0.4-4xh200-batch-64-20260421-214335-rerun Source: Original Platform
2026-05-10 13:35:35 +08:00
commit ab10c6b4c0
702 changed files with 17157 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,81 @@
+---
+library_name: transformers
+base_model: W-61/llama-3-8b-base-sft-hh-helpful-4xh200
+tags:
+- alignment-handbook
+- new-dpo
+- generated_from_trainer
+datasets:
+- Anthropic/hh-rlhf
+model-index:
+- name: llama-3-8b-base-new-dpo-hh-helpful-s_star0.4-4xh200-batch-64-20260421-214335-rerun
+  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. -->
+
+# llama-3-8b-base-new-dpo-hh-helpful-s_star0.4-4xh200-batch-64-20260421-214335-rerun
+
+This model is a fine-tuned version of [W-61/llama-3-8b-base-sft-hh-helpful-4xh200](https://huggingface.co/W-61/llama-3-8b-base-sft-hh-helpful-4xh200) on the Anthropic/hh-rlhf dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6074
+- Fcm Dpo/beta: 0.0011
+- Fcm Dpo/q T: 0.4332
+- Fcm Dpo/delta: 0.0239
+- Fcm Dpo/margin: 270.7279
+- Margin Dpo/margin Mean: 270.7279
+- Margin Dpo/margin Std: 601.7490
+- Logps/chosen: -823.2324
+- Logps/rejected: -1101.7070
+- Logps/ref Chosen: -79.0510
+- Logps/ref Rejected: -86.7979
+- Logits/chosen: -1.0197
+- Logits/rejected: -1.0177
+
+## 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-07
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Fcm Dpo/beta | Fcm Dpo/q T | Fcm Dpo/delta | Fcm Dpo/margin | Margin Dpo/margin Mean | Margin Dpo/margin Std | Logps/chosen | Logps/rejected | Logps/ref Chosen | Logps/ref Rejected | Logits/chosen | Logits/rejected |
+|:-------------:|:------:|:----:|:---------------:|:------------:|:-----------:|:-------------:|:--------------:|:----------------------:|:---------------------:|:------------:|:--------------:|:----------------:|:------------------:|:-------------:|:---------------:|
+| 1.0801        | 0.2937 | 200  | 0.6239          | 0.0049       | 0.4392      | 0.0321        | 58.0086        | 58.0086                | 147.6546              | -225.8390    | -291.5945      | -79.0510         | -86.7979           | -0.3472       | -0.3330         |
+| 1.0433        | 0.5874 | 400  | 0.6033          | 0.0019       | 0.4336      | 0.0376        | 156.9007       | 156.9006               | 328.4540              | -532.2333    | -696.8809      | -79.0510         | -86.7979           | -0.5230       | -0.5119         |
+| 1.1393        | 0.8811 | 600  | 0.6074          | 0.0011       | 0.4332      | 0.0239        | 270.7279       | 270.7279               | 601.7490              | -823.2324    | -1101.7070     | -79.0510         | -86.7979           | -1.0197       | -1.0177         |
+
+
+### Framework versions
+
+- Transformers 4.51.0
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.21.4