yakazimir/simpo-exps_qwen05b
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: yakazimir/simpo-exps_qwen05b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-27 13:20:24 +08:00
commit 9c0b547458
23 changed files with 151912 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
.gitattributes vendored Normal file
View File

@@ -0,0 +1,40 @@
*.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
tokenizer.json filter=lfs diff=lfs merge=lfs -text
dynamics.cache/cache.db-wal filter=lfs diff=lfs merge=lfs -text
dynamics/cache.db-wal filter=lfs diff=lfs merge=lfs -text
dynamics.cache/cache.db filter=lfs diff=lfs merge=lfs -text
dynamics/cache.db filter=lfs diff=lfs merge=lfs -text

70
README.md Normal file
View File

@@ -0,0 +1,70 @@
---
library_name: transformers
license: other
base_model: trl-lib/qwen1.5-0.5b-sft
tags:
- alignment-handbook
- trl
- simpo
- generated_from_trainer
model-index:
- name: trl-lib/qwen1.5-0.5b-sft
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. -->
# trl-lib/qwen1.5-0.5b-sft
This model is a fine-tuned version of [trl-lib/qwen1.5-0.5b-sft](https://huggingface.co/trl-lib/qwen1.5-0.5b-sft) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7797
- Rewards/chosen: -1.7866
- Rewards/rejected: -1.8726
- Rewards/accuracies: 0.5230
- Rewards/margins: 0.0860
- Logps/rejected: -1.8726
- Logps/chosen: -1.7866
- Logits/rejected: -0.3259
- Logits/chosen: -0.3565
- Semantic Entropy: 0.6461
## 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: 8e-08
- train_batch_size: 1
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 60
### Training results
### Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1

5
added_tokens.json Normal file
View File

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

22
all_results.json Normal file
View File

@@ -0,0 +1,22 @@
{
"epoch": 32.0,
"eval_logits/chosen": -0.3564789891242981,
"eval_logits/rejected": -0.32587698101997375,
"eval_logps/chosen": -1.786582350730896,
"eval_logps/rejected": -1.8725693225860596,
"eval_loss": 0.7796740531921387,
"eval_rewards/accuracies": 0.5229970216751099,
"eval_rewards/chosen": -1.786582350730896,
"eval_rewards/margins": 0.08598694205284119,
"eval_rewards/rejected": -1.8725693225860596,
"eval_runtime": 60.635,
"eval_samples": 1345,
"eval_samples_per_second": 22.182,
"eval_semantic_entropy": 0.6461161971092224,
"eval_steps_per_second": 5.558,
"total_flos": 0.0,
"train_loss": 0.6880494674046834,
"train_runtime": 138.3641,
"train_samples_per_second": 6.938,
"train_steps_per_second": 0.434
}

29
config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"_name_or_path": "trl-lib/qwen1.5-0.5b-sft",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151644,
"eos_token_id": 151645,
"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,
"pad_token_id": 151645,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.2",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151648
}

3
dynamics.cache/cache.db Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bf2264b13641feb013acc3b99e08efc63eddde56f809eb9f5e5ed9eef56105c6
size 114688

BIN
dynamics.cache/cache.db-shm Normal file
View File

Binary file not shown.

3
dynamics.cache/cache.db-wal Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a3e79f6b0a439fbbe252ffac3e3b9af409c309c6dcee4038d00e338669d3428
size 4124152

0
dynamics.jsonl Normal file
View File

3
dynamics/cache.db Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:024e3c93e3bc404c7b38726481fa5268770d1cb759158bf2d41747cf97f8b0aa
size 401408

BIN
dynamics/cache.db-shm Normal file
View File

Binary file not shown.

3
dynamics/cache.db-wal Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4cf665c94502bbd6a3cc1074a3a3fd683fc5ae04e600725485ca9e82bb1f9e99
size 4136512

17
eval_results.json Normal file
View File

@@ -0,0 +1,17 @@
{
"epoch": 32.0,
"eval_logits/chosen": -0.3564789891242981,
"eval_logits/rejected": -0.32587698101997375,
"eval_logps/chosen": -1.786582350730896,
"eval_logps/rejected": -1.8725693225860596,
"eval_loss": 0.7796740531921387,
"eval_rewards/accuracies": 0.5229970216751099,
"eval_rewards/chosen": -1.786582350730896,
"eval_rewards/margins": 0.08598694205284119,
"eval_rewards/rejected": -1.8725693225860596,
"eval_runtime": 60.635,
"eval_samples": 1345,
"eval_samples_per_second": 22.182,
"eval_semantic_entropy": 0.6461161971092224,
"eval_steps_per_second": 5.558
}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"bos_token_id": 151644,
"eos_token_id": 151645,
"max_new_tokens": 2048,
"pad_token_id": 151645,
"transformers_version": "4.44.2"
}

151388
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f80a1b8a93321af0764d057d384a96186d75a2c9351ca24ffc9b6a80c7a70ed2
size 927418280

27
special_tokens_map.json Normal file
View File

@@ -0,0 +1,27 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a12e3ba5d5e0ad173cf7b408ab8534c6be8cbc6a146714e9c7dc8cf2346603b1
size 7028043

43
tokenizer_config.json Normal file
View File

@@ -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_start|>",
"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": "<|im_end|>",
"errors": "replace",
"model_max_length": 32768,
"pad_token": "<|im_end|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 32.0,
"total_flos": 0.0,
"train_loss": 0.6880494674046834,
"train_runtime": 138.3641,
"train_samples_per_second": 6.938,
"train_steps_per_second": 0.434
}

234
trainer_state.json Normal file
View File

@@ -0,0 +1,234 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 32.0,
"eval_steps": 400,
"global_step": 60,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 2.6666666666666665,
"grad_norm": 7.78125,
"learning_rate": 6.666666666666667e-08,
"logits/chosen": -0.6206714510917664,
"logits/rejected": -0.6167551279067993,
"logps/chosen": -1.6594607830047607,
"logps/rejected": -1.8626664876937866,
"loss": 0.7092,
"rewards/accuracies": 0.4749999940395355,
"rewards/chosen": -1.6594607830047607,
"rewards/margins": 0.2032059133052826,
"rewards/rejected": -1.8626664876937866,
"semantic_entropy": 0.6521000862121582,
"step": 5
},
{
"epoch": 5.333333333333333,
"grad_norm": 6.78125,
"learning_rate": 7.892179482319296e-08,
"logits/chosen": -0.644172191619873,
"logits/rejected": -0.5970994234085083,
"logps/chosen": -1.6529489755630493,
"logps/rejected": -2.02937912940979,
"loss": 0.6576,
"rewards/accuracies": 0.5249999761581421,
"rewards/chosen": -1.6529489755630493,
"rewards/margins": 0.3764302134513855,
"rewards/rejected": -2.02937912940979,
"semantic_entropy": 0.6556634902954102,
"step": 10
},
{
"epoch": 8.0,
"grad_norm": 8.6875,
"learning_rate": 7.464101615137755e-08,
"logits/chosen": -0.6107379794120789,
"logits/rejected": -0.6173809766769409,
"logps/chosen": -1.6537139415740967,
"logps/rejected": -1.878178596496582,
"loss": 0.6978,
"rewards/accuracies": 0.5,
"rewards/chosen": -1.6537139415740967,
"rewards/margins": 0.22446465492248535,
"rewards/rejected": -1.878178596496582,
"semantic_entropy": 0.6528152227401733,
"step": 15
},
{
"epoch": 10.666666666666666,
"grad_norm": 8.625,
"learning_rate": 6.744966551474935e-08,
"logits/chosen": -0.6249920129776001,
"logits/rejected": -0.5978578925132751,
"logps/chosen": -1.661948561668396,
"logps/rejected": -1.9520155191421509,
"loss": 0.6819,
"rewards/accuracies": 0.512499988079071,
"rewards/chosen": -1.661948561668396,
"rewards/margins": 0.2900669574737549,
"rewards/rejected": -1.9520155191421509,
"semantic_entropy": 0.6477808952331543,
"step": 20
},
{
"epoch": 13.333333333333334,
"grad_norm": 8.875,
"learning_rate": 5.7951967208018495e-08,
"logits/chosen": -0.6556390523910522,
"logits/rejected": -0.6272687911987305,
"logps/chosen": -1.6880241632461548,
"logps/rejected": -1.9340057373046875,
"loss": 0.7142,
"rewards/accuracies": 0.4749999940395355,
"rewards/chosen": -1.6880241632461548,
"rewards/margins": 0.24598172307014465,
"rewards/rejected": -1.9340057373046875,
"semantic_entropy": 0.6515553593635559,
"step": 25
},
{
"epoch": 16.0,
"grad_norm": 6.875,
"learning_rate": 4.6945927106677224e-08,
"logits/chosen": -0.5940297842025757,
"logits/rejected": -0.6073416471481323,
"logps/chosen": -1.6197277307510376,
"logps/rejected": -1.888943076133728,
"loss": 0.6684,
"rewards/accuracies": 0.512499988079071,
"rewards/chosen": -1.6197277307510376,
"rewards/margins": 0.26921549439430237,
"rewards/rejected": -1.888943076133728,
"semantic_entropy": 0.6606020927429199,
"step": 30
},
{
"epoch": 18.666666666666668,
"grad_norm": 9.1875,
"learning_rate": 3.535628343499079e-08,
"logits/chosen": -0.6252874732017517,
"logits/rejected": -0.6270566582679749,
"logps/chosen": -1.6999114751815796,
"logps/rejected": -1.9409929513931274,
"loss": 0.7074,
"rewards/accuracies": 0.48750001192092896,
"rewards/chosen": -1.6999114751815796,
"rewards/margins": 0.24108140170574188,
"rewards/rejected": -1.9409929513931274,
"semantic_entropy": 0.6408571004867554,
"step": 35
},
{
"epoch": 21.333333333333332,
"grad_norm": 8.125,
"learning_rate": 2.4156809358433726e-08,
"logits/chosen": -0.6158267259597778,
"logits/rejected": -0.5839654803276062,
"logps/chosen": -1.583505392074585,
"logps/rejected": -1.8752552270889282,
"loss": 0.6656,
"rewards/accuracies": 0.5249999761581421,
"rewards/chosen": -1.583505392074585,
"rewards/margins": 0.29174983501434326,
"rewards/rejected": -1.8752552270889282,
"semantic_entropy": 0.6757909059524536,
"step": 40
},
{
"epoch": 24.0,
"grad_norm": 8.75,
"learning_rate": 1.4288495612538426e-08,
"logits/chosen": -0.6340750455856323,
"logits/rejected": -0.6243816018104553,
"logps/chosen": -1.68179452419281,
"logps/rejected": -1.9539234638214111,
"loss": 0.6902,
"rewards/accuracies": 0.48750001192092896,
"rewards/chosen": -1.68179452419281,
"rewards/margins": 0.2721291184425354,
"rewards/rejected": -1.9539234638214111,
"semantic_entropy": 0.6442986130714417,
"step": 45
},
{
"epoch": 26.666666666666668,
"grad_norm": 8.1875,
"learning_rate": 6.58048754348255e-09,
"logits/chosen": -0.6418130397796631,
"logits/rejected": -0.6143754720687866,
"logps/chosen": -1.6074516773223877,
"logps/rejected": -1.830583930015564,
"loss": 0.694,
"rewards/accuracies": 0.4749999940395355,
"rewards/chosen": -1.6074516773223877,
"rewards/margins": 0.22313210368156433,
"rewards/rejected": -1.830583930015564,
"semantic_entropy": 0.6700640916824341,
"step": 50
},
{
"epoch": 29.333333333333332,
"grad_norm": 8.0625,
"learning_rate": 1.680419507380444e-09,
"logits/chosen": -0.6013139486312866,
"logits/rejected": -0.5867229700088501,
"logps/chosen": -1.689805030822754,
"logps/rejected": -2.002596616744995,
"loss": 0.6768,
"rewards/accuracies": 0.550000011920929,
"rewards/chosen": -1.689805030822754,
"rewards/margins": 0.3127916753292084,
"rewards/rejected": -2.002596616744995,
"semantic_entropy": 0.6430121064186096,
"step": 55
},
{
"epoch": 32.0,
"grad_norm": 8.4375,
"learning_rate": 0.0,
"logits/chosen": -0.6301103830337524,
"logits/rejected": -0.6289348006248474,
"logps/chosen": -1.665967345237732,
"logps/rejected": -1.932885766029358,
"loss": 0.6937,
"rewards/accuracies": 0.4749999940395355,
"rewards/chosen": -1.665967345237732,
"rewards/margins": 0.2669183611869812,
"rewards/rejected": -1.932885766029358,
"semantic_entropy": 0.6483110785484314,
"step": 60
},
{
"epoch": 32.0,
"step": 60,
"total_flos": 0.0,
"train_loss": 0.6880494674046834,
"train_runtime": 138.3641,
"train_samples_per_second": 6.938,
"train_steps_per_second": 0.434
}
],
"logging_steps": 5,
"max_steps": 60,
"num_input_tokens_seen": 0,
"num_train_epochs": 60,
"save_steps": 1000000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5caa4227aeae75b2723eec54c9be849d310e03f403e331c77d961771214a53a6
size 5816

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long