初始化项目，由ModelHub XC社区提供模型

Model: burtenshaw/Qwen1.5-0.5B-dpo-mix-7k Source: Original Platform
2026-05-26 14:10:13 +08:00
commit e2c4967a5c
50 changed files with 152433 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,49 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/config.json
+++ b/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/config.json
@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/generation_config.json
+++ b/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.38.2"
+}
--- a/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/model.safetensors
+++ b/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db68417c4e59a7c907c4e46f1673f7b306d0cc02ef9d81744bf5ce751726054
+size 1239173352
--- a/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/optimizer.bin
+++ b/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/optimizer.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee378caf0b6044a995c1da5fa6dbda30f90f1f25c8893151b8d36caba588fc4c
+size 3712103866
--- a/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/pytorch_model_fsdp.bin
+++ b/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/pytorch_model_fsdp.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3467c4019f073fb3f78d725769757ba01dead7ee9368a54406b5d0eaf146581d
+size 1239279449
--- a/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/rng_state.pth
+++ b/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c733f603eddfbf8aea2db46dfb96d2d44052ea3c8d772ba82a9011002700581
+size 14244
--- a/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/scheduler.pt
+++ b/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bdfdc58f49ec10c0300671170c8cd13c1079080b9e9c4c20632dae81d91bd64
+size 1064
--- a/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/trainer_state.json
+++ b/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/trainer_state.json
@@ -0,0 +1,260 @@
+{
+  "best_metric": 0.8604190945625305,
+  "best_model_checkpoint": "./checkpoints/dpo-mix-7k/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1687,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "grad_norm": 800.0,
+      "learning_rate": 2.5e-06,
+      "loss": 18.0938,
+      "step": 50
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 23.5,
+      "learning_rate": 5e-06,
+      "loss": 6.3163,
+      "step": 100
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 50.75,
+      "learning_rate": 4.987763947682049e-06,
+      "loss": 0.9927,
+      "step": 150
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 19.0,
+      "learning_rate": 4.951175567509258e-06,
+      "loss": 1.0442,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 13.625,
+      "learning_rate": 4.890593017348846e-06,
+      "loss": 0.9387,
+      "step": 250
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 66.5,
+      "learning_rate": 4.806609330203466e-06,
+      "loss": 0.97,
+      "step": 300
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 22.5,
+      "learning_rate": 4.700046609104932e-06,
+      "loss": 0.9789,
+      "step": 350
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 11.625,
+      "learning_rate": 4.5719479796776466e-06,
+      "loss": 0.8951,
+      "step": 400
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 51.0,
+      "learning_rate": 4.423567379146835e-06,
+      "loss": 1.0329,
+      "step": 450
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 13.9375,
+      "learning_rate": 4.256357281745347e-06,
+      "loss": 1.0507,
+      "step": 500
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 15.0625,
+      "learning_rate": 4.071954480673098e-06,
+      "loss": 0.8861,
+      "step": 550
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 33.75,
+      "learning_rate": 3.872164065787287e-06,
+      "loss": 0.8826,
+      "step": 600
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 16.875,
+      "learning_rate": 3.6589417538632477e-06,
+      "loss": 1.0443,
+      "step": 650
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 17.25,
+      "learning_rate": 3.4343747443922253e-06,
+      "loss": 0.9825,
+      "step": 700
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 10.1875,
+      "learning_rate": 3.2006612883156387e-06,
+      "loss": 0.8588,
+      "step": 750
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 18.5,
+      "learning_rate": 2.960089169694257e-06,
+      "loss": 0.86,
+      "step": 800
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 34.0,
+      "learning_rate": 2.7150133109518347e-06,
+      "loss": 0.8479,
+      "step": 850
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 17.25,
+      "learning_rate": 2.4678327209119225e-06,
+      "loss": 0.8909,
+      "step": 900
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 19.625,
+      "learning_rate": 2.220967011279888e-06,
+      "loss": 0.8326,
+      "step": 950
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 15.6875,
+      "learning_rate": 1.976832711446584e-06,
+      "loss": 0.9614,
+      "step": 1000
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 28.0,
+      "learning_rate": 1.737819613464305e-06,
+      "loss": 0.751,
+      "step": 1050
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 17.125,
+      "learning_rate": 1.506267378750319e-06,
+      "loss": 0.9322,
+      "step": 1100
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 20.125,
+      "learning_rate": 1.2844426355112658e-06,
+      "loss": 0.7542,
+      "step": 1150
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 21.5,
+      "learning_rate": 1.0745167910780963e-06,
+      "loss": 0.8321,
+      "step": 1200
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 14.25,
+      "learning_rate": 8.785447763431101e-07,
+      "loss": 0.87,
+      "step": 1250
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 15.25,
+      "learning_rate": 6.984449303664287e-07,
+      "loss": 0.8061,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 20.375,
+      "learning_rate": 5.359802220583124e-07,
+      "loss": 0.8294,
+      "step": 1350
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 12.5625,
+      "learning_rate": 3.9274099275530384e-07,
+      "loss": 0.9622,
+      "step": 1400
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 16.75,
+      "learning_rate": 2.7012938862039123e-07,
+      "loss": 0.8932,
+      "step": 1450
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 13.75,
+      "learning_rate": 1.6934563525596053e-07,
+      "loss": 0.9018,
+      "step": 1500
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 26.75,
+      "learning_rate": 9.137628888518491e-08,
+      "loss": 0.9468,
+      "step": 1550
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 18.75,
+      "learning_rate": 3.698457910917608e-08,
+      "loss": 0.8617,
+      "step": 1600
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 13.125,
+      "learning_rate": 6.702937773119533e-09,
+      "loss": 0.8404,
+      "step": 1650
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.8604190945625305,
+      "eval_runtime": 87.9192,
+      "eval_samples_per_second": 4.277,
+      "eval_steps_per_second": 2.138,
+      "step": 1687
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1687,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.2782603635523584e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/training_args.bin
+++ b/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/checkpoint-1687/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:845a3f0102c29d18010ceb5d819cd67e9156eea7d9342492ecb920d1ca74b6ac
+size 5048
--- a/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/config.json
+++ b/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/config.json
@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/generation_config.json
+++ b/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.38.2"
+}
--- a/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/model.safetensors
+++ b/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db68417c4e59a7c907c4e46f1673f7b306d0cc02ef9d81744bf5ce751726054
+size 1239173352
--- a/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/training_args.bin
+++ b/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:845a3f0102c29d18010ceb5d819cd67e9156eea7d9342492ecb920d1ca74b6ac
+size 5048
--- a/README.md
+++ b/README.md
@@ -0,0 +1,217 @@
+---
+language: en
+license: mit
+model-index:
+- name: Qwen1.5-0.5B-dpo-mix-7k
+  results:
+  - task:
+      type: question-answering
+      name: eq_bench
+    dataset:
+      name: pbevan11/EQ-Bench
+      type: benchmark
+    metrics:
+    - type: accuracy
+      value: 0.4861130120334633
+      name: eqbench
+    - type: accuracy
+      value: 88.88888888888889
+      name: percent_parseable
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** en
+- **License:** mit
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}
--- a/checkpoint-313/config.json
+++ b/checkpoint-313/config.json
@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/checkpoint-313/generation_config.json
+++ b/checkpoint-313/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.39.2"
+}
--- a/checkpoint-313/model.safetensors
+++ b/checkpoint-313/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbe626c1033f0b0b6486b1203488cd6db2994c96f78d31b57e17e8262e80f3d1
+size 1239173352
--- a/checkpoint-313/optimizer.bin
+++ b/checkpoint-313/optimizer.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc73358597b82368e59eabbe96fa657b47ccab1cef03cb3e63f43a80751855a6
+size 3712103162
--- a/checkpoint-313/pytorch_model_fsdp.bin
+++ b/checkpoint-313/pytorch_model_fsdp.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88628f8605e07512111aa6e00bd0c7736ac7d5b8fdd3f8c61c9e1860ee33e49c
+size 1239275353
--- a/checkpoint-313/rng_state_0.pth
+++ b/checkpoint-313/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308f94f9a5c24e1bad5c393d56ae7af7782600f4e791d9c6ac35b22fff2105b6
+size 15024
--- a/checkpoint-313/rng_state_1.pth
+++ b/checkpoint-313/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b056f3c23cb32dc77a2ec9e7651e0b64e4440e21f0fdf969b86bfc56a1cbdf06
+size 15024
--- a/checkpoint-313/rng_state_2.pth
+++ b/checkpoint-313/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f8a05714bc528f4885a2816181652f2303b3e8150f89b56aaee6bec56aa520
+size 15024
--- a/checkpoint-313/rng_state_3.pth
+++ b/checkpoint-313/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f755bd3c330281961e5c03af9d10ce8c1e1678619d384f6f1fd5fd7dce2ff50
+size 15024
--- a/checkpoint-313/scheduler.pt
+++ b/checkpoint-313/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a3a847b2da5cc99667fb5595d3d91d25d426f2a3b3f1ec256909eaaddfc80b
+size 1064
--- a/checkpoint-313/trainer_state.json
+++ b/checkpoint-313/trainer_state.json
@@ -0,0 +1,71 @@
+{
+  "best_metric": 1.1438744068145752,
+  "best_model_checkpoint": "./checkpoints/dpo-mix-7k/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-29-9-49/checkpoint-313",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 313,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 616.0,
+      "learning_rate": 2.5e-06,
+      "loss": 15.2717,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.59375,
+      "learning_rate": 5e-06,
+      "loss": 4.0109,
+      "step": 100
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.65625,
+      "learning_rate": 4.889350784534168e-06,
+      "loss": 1.2041,
+      "step": 150
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.90625,
+      "learning_rate": 4.5671977372432355e-06,
+      "loss": 1.1597,
+      "step": 200
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 43.5,
+      "learning_rate": 4.062057643681335e-06,
+      "loss": 1.1542,
+      "step": 250
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.8125,
+      "learning_rate": 3.4186451878908393e-06,
+      "loss": 1.1222,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1438744068145752,
+      "eval_runtime": 34.1359,
+      "eval_samples_per_second": 16.551,
+      "eval_steps_per_second": 1.055,
+      "step": 313
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 626,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 4744684177981440.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/checkpoint-313/training_args.bin
+++ b/checkpoint-313/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba636fcd247d639f405e2e00cd9717702cadada97437b5285147fee89e3f28e2
+size 5048
--- a/checkpoint-626/config.json
+++ b/checkpoint-626/config.json
@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/checkpoint-626/generation_config.json
+++ b/checkpoint-626/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.39.2"
+}
--- a/checkpoint-626/model.safetensors
+++ b/checkpoint-626/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a185c9e39289cfeff3becc2fc573647d493a99fe9f3049b8bd5a30289f58cdb5
+size 1239173352
--- a/checkpoint-626/optimizer.bin
+++ b/checkpoint-626/optimizer.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc42aebd19be79450b587c0e9897708b3b44c7a15cef001e0df1407d17aba9b
+size 3712103162
--- a/checkpoint-626/pytorch_model_fsdp.bin
+++ b/checkpoint-626/pytorch_model_fsdp.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d4e0dbd3df02e78d9f7910dab327994aa80ab5d89ef3c9988908cc5f61c150
+size 1239275353
--- a/checkpoint-626/rng_state_0.pth
+++ b/checkpoint-626/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:418a5f105ae834c3075024076916b2a9475918fe034c12d0dd5b6d91f1aba467
+size 15024
--- a/checkpoint-626/rng_state_1.pth
+++ b/checkpoint-626/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e07ace389d24bc1307b74f42a1e7b8f0117b0db853e2df64ff3f15cb92916a2
+size 15024
--- a/checkpoint-626/rng_state_2.pth
+++ b/checkpoint-626/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6a990f346d7014dffb28fa2bc7d3b890bd3c53712503fce3656da48d3d6e50
+size 15024
--- a/checkpoint-626/rng_state_3.pth
+++ b/checkpoint-626/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95f356ca38179b05993f55daece0223e96fa10b9a1b9ea2102a739211333f63
+size 15024
--- a/checkpoint-626/scheduler.pt
+++ b/checkpoint-626/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:330af213ffd33b0966c84faa1ee759a9643efb15549b7ffb50aadfb93382d16e
+size 1064
--- a/checkpoint-626/trainer_state.json
+++ b/checkpoint-626/trainer_state.json
@@ -0,0 +1,121 @@
+{
+  "best_metric": 1.1383987665176392,
+  "best_model_checkpoint": "./checkpoints/dpo-mix-7k/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-29-9-49/checkpoint-626",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 626,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 616.0,
+      "learning_rate": 2.5e-06,
+      "loss": 15.2717,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.59375,
+      "learning_rate": 5e-06,
+      "loss": 4.0109,
+      "step": 100
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.65625,
+      "learning_rate": 4.889350784534168e-06,
+      "loss": 1.2041,
+      "step": 150
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.90625,
+      "learning_rate": 4.5671977372432355e-06,
+      "loss": 1.1597,
+      "step": 200
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 43.5,
+      "learning_rate": 4.062057643681335e-06,
+      "loss": 1.1542,
+      "step": 250
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.8125,
+      "learning_rate": 3.4186451878908393e-06,
+      "loss": 1.1222,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1438744068145752,
+      "eval_runtime": 34.1359,
+      "eval_samples_per_second": 16.551,
+      "eval_steps_per_second": 1.055,
+      "step": 313
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 6.28125,
+      "learning_rate": 2.693914836635076e-06,
+      "loss": 1.0845,
+      "step": 350
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 15.9375,
+      "learning_rate": 1.9520192657466286e-06,
+      "loss": 1.1293,
+      "step": 400
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 15.5625,
+      "learning_rate": 1.2586306055266007e-06,
+      "loss": 1.1217,
+      "step": 450
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 13.3125,
+      "learning_rate": 6.751271849879959e-07,
+      "loss": 1.1324,
+      "step": 500
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 5.4375,
+      "learning_rate": 2.531603606941929e-07,
+      "loss": 1.163,
+      "step": 550
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 6.15625,
+      "learning_rate": 3.0082371093766435e-08,
+      "loss": 1.1869,
+      "step": 600
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1383987665176392,
+      "eval_runtime": 34.1146,
+      "eval_samples_per_second": 16.562,
+      "eval_steps_per_second": 1.055,
+      "step": 626
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 626,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 9489368339185664.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/checkpoint-626/training_args.bin
+++ b/checkpoint-626/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba636fcd247d639f405e2e00cd9717702cadada97437b5285147fee89e3f28e2
+size 5048
--- a/config.json
+++ b/config.json
@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.39.2"
+}
--- a/merges.txt
+++ b/merges.txt
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a185c9e39289cfeff3becc2fc573647d493a99fe9f3049b8bd5a30289f58cdb5
+size 1239173352
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c9b2dba4a296b1aa76c16a34b8225c0c118978400d4bb66bff0902d702f5b8
+size 7028015
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba636fcd247d639f405e2e00cd9717702cadada97437b5285147fee89e3f28e2
+size 5048
--- a/vocab.json
+++ b/vocab.json
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`