初始化项目，由ModelHub XC社区提供模型

Model: Ejafa/qwen2-0.5b-instruct-simpo-lr-5e-07-gamma-1.5
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,84 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen2-0.5B-Instruct
+tags:
+- alignment-handbook
+- trl
+- dpo
+- generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- princeton-nlp/llama3-ultrafeedback
+model-index:
+- name: qwen2-0.5b-instruct-simpo-lr-5e-07-gamma-1.5
+  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. -->
+## Description
+This model was trained as part of the Reinforcement Learning - 24 project at Peking University, focusing on [simpo].
+
+## Authors
+- Ejafa Bassam
+- Yaroslav Ponomarenko
+# qwen2-0.5b-instruct-simpo-lr-5e-07-gamma-1.5
+
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the princeton-nlp/llama3-ultrafeedback dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6594
+- Rewards/chosen: -3.3473
+- Rewards/rejected: -3.4798
+- Rewards/accuracies: 0.5282
+- Rewards/margins: 0.1325
+- Logps/rejected: -1.3919
+- Logps/chosen: -1.3389
+- Logits/rejected: -5.2419
+- Logits/chosen: -5.3398
+
+## 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: 2
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 1.6693        | 0.8549 | 400  | 1.6598          | -3.3421        | -3.4735          | 0.5282             | 0.1314          | -1.3894        | -1.3368      | -5.2590         | -5.3573       |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 0.9981298423724285,
+    "eval_logits/chosen": -5.339814186096191,
+    "eval_logits/rejected": -5.241891384124756,
+    "eval_logps/chosen": -1.3389328718185425,
+    "eval_logps/rejected": -1.3919367790222168,
+    "eval_loss": 1.659356713294983,
+    "eval_rewards/accuracies": 0.5282257795333862,
+    "eval_rewards/chosen": -3.347332239151001,
+    "eval_rewards/margins": 0.13250981271266937,
+    "eval_rewards/rejected": -3.479841947555542,
+    "eval_runtime": 29.2769,
+    "eval_samples": 1961,
+    "eval_samples_per_second": 66.981,
+    "eval_steps_per_second": 2.118,
+    "total_flos": 0.0,
+    "train_loss": 1.7099600828689476,
+    "train_runtime": 3104.7014,
+    "train_samples": 59876,
+    "train_samples_per_second": 19.286,
+    "train_steps_per_second": 0.15
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9981298423724285,
+    "eval_logits/chosen": -5.339814186096191,
+    "eval_logits/rejected": -5.241891384124756,
+    "eval_logps/chosen": -1.3389328718185425,
+    "eval_logps/rejected": -1.3919367790222168,
+    "eval_loss": 1.659356713294983,
+    "eval_rewards/accuracies": 0.5282257795333862,
+    "eval_rewards/chosen": -3.347332239151001,
+    "eval_rewards/margins": 0.13250981271266937,
+    "eval_rewards/rejected": -3.479841947555542,
+    "eval_runtime": 29.2769,
+    "eval_samples": 1961,
+    "eval_samples_per_second": 66.981,
+    "eval_steps_per_second": 2.118
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9948210d1d9c80524b8794e5f06f8432d564886c86f013d2ed7094e400c6e3a0
+size 988097824

runs/Jun21_14-04-01_131-186-38-174/events.out.tfevents.1718979292.131-186-38-174.21907.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:266711b2c7f36729c36f562721d3de29764389dcb7fa666a3b15de18d96c547a
+size 70644

runs/Jun21_14-04-01_131-186-38-174/events.out.tfevents.1718982473.131-186-38-174.21907.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b082f0481f7337f6161a345fe253c664e64247cdac02f6dad4d708e35a6824
+size 828

special_tokens_map.json

@@ -0,0 +1,21 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_end|>",
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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": "<|im_end|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9981298423724285,
+    "total_flos": 0.0,
+    "train_loss": 1.7099600828689476,
+    "train_runtime": 3104.7014,
+    "train_samples": 59876,
+    "train_samples_per_second": 19.286,
+    "train_steps_per_second": 0.15
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96bdcdc0e35c2559ff01f27b96f1c338d4e3ca5a278f6d7ab1b8ff608207cb4
+size 6584