初始化项目,由ModelHub XC社区提供模型

Model: jekunz/Qwen3-1.7B-Base-is-CPT-plus-IR-is-SmolTalk
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-18 08:27:45 +08:00
commit 6d36721391
35 changed files with 304116 additions and 0 deletions

37
.gitattributes vendored Normal file
View File

@@ -0,0 +1,37 @@
*.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
checkpoint-2326/tokenizer.json filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

57
README.md Normal file
View File

@@ -0,0 +1,57 @@
---
library_name: transformers
model_name: qwen-is3ep-merged-is-smoltalk
tags:
- generated_from_trainer
- sft
- trl
licence: license
---
# Model Card for qwen-is3ep-merged-is-smoltalk
This model is a fine-tuned version of [None](https://huggingface.co/None).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with SFT.
### Framework versions
- TRL: 0.25.1
- Transformers: 4.57.3
- Pytorch: 2.9.1
- Datasets: 4.4.1
- Tokenizers: 0.22.1
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```

28
added_tokens.json Normal file
View File

@@ -0,0 +1,28 @@
{
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

4
chat_template.jinja Normal file
View File

@@ -0,0 +1,4 @@
{% for message in messages %}{{'<|im_start|>' + message['role'] + '
' + message['content'] + '<|im_end|>' + '
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
' }}{% endif %}

View File

@@ -0,0 +1,28 @@
{
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

View File

@@ -0,0 +1,4 @@
{% for message in messages %}{{'<|im_start|>' + message['role'] + '
' + message['content'] + '<|im_end|>' + '
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
' }}{% endif %}

View File

@@ -0,0 +1,61 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151644,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151645,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.57.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151669
}

View File

@@ -0,0 +1,9 @@
{
"bos_token_id": 151644,
"eos_token_id": [
151645
],
"max_new_tokens": 2048,
"pad_token_id": 151645,
"transformers_version": "4.57.3"
}

151388
checkpoint-2326/merges.txt Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cb698d678fd950d9035f9a383b65743ad6760fe0c764ce466193157025d5c46e
size 3440091976

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:64a6f15b716f66b0eb286c7611888ab3c2880c6928bbc6a2728e4b5c3d70fe18
size 6880384943

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7350b59a307e1d89d4515e24325811dc1aa8deab5b5b4635887adaaf78ea1dc5
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:af262eaf45f7c1f39099b694376de497429ab46c1046a1d9afe70a315f1b6d81
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:57f833fda5ff0e7e566107275c268625e3eb07e8475116fe109d9c667809d469
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2a6e6037388bc56484982620075eea8724b4696f67f60603b9c448e44f41705c
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d2bf73391bb68f0fffcb931501656f3679db7d996fe258d8287099b6cb7a23a2
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:222199bb7faa2ce2cb817e7f870ac7c364fb0f0872e17d8a9280f38596da9a06
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca3accfbfe6616f878cfeda3df23f4418e00b348760c584e397d6c92081cb5c4
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a64b41c5668afda0c862d9774a14b1c0a390fe6a57086de71f9fdfb00edb457e
size 16389

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0ec7097268c7908499df208b31f8dc646ed6fdd6825cbb320482ce15a9f329ec
size 1465

View File

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

BIN
checkpoint-2326/tokenizer.json (Stored with Git LFS) Normal file

Binary file not shown.

View File

@@ -0,0 +1,228 @@
{
"add_bos_token": false,
"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
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": "<|im_start|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|im_end|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

View File

@@ -0,0 +1,494 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 2326,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"entropy": 1.0907272757589817,
"epoch": 0.021503064186646596,
"grad_norm": 6.21875,
"learning_rate": 6.309012875536481e-06,
"loss": 2.1228,
"mean_token_accuracy": 0.6076477284729481,
"num_tokens": 13032106.0,
"step": 50
},
{
"entropy": 1.508835320174694,
"epoch": 0.04300612837329319,
"grad_norm": 0.9296875,
"learning_rate": 1.2746781115879827e-05,
"loss": 1.5598,
"mean_token_accuracy": 0.6578908252716065,
"num_tokens": 26059780.0,
"step": 100
},
{
"entropy": 1.3828416666388512,
"epoch": 0.0645091925599398,
"grad_norm": 0.86328125,
"learning_rate": 1.918454935622318e-05,
"loss": 1.3879,
"mean_token_accuracy": 0.6857959526777268,
"num_tokens": 39088700.0,
"step": 150
},
{
"entropy": 1.3144192987680434,
"epoch": 0.08601225674658639,
"grad_norm": 0.875,
"learning_rate": 2.5622317596566525e-05,
"loss": 1.3154,
"mean_token_accuracy": 0.6985341481864452,
"num_tokens": 52119410.0,
"step": 200
},
{
"entropy": 1.271382558941841,
"epoch": 0.10751532093323299,
"grad_norm": 0.80859375,
"learning_rate": 2.9995674446943393e-05,
"loss": 1.271,
"mean_token_accuracy": 0.706343949586153,
"num_tokens": 65159605.0,
"step": 250
},
{
"entropy": 1.2296087518334389,
"epoch": 0.1290183851198796,
"grad_norm": 0.83984375,
"learning_rate": 2.992645465135663e-05,
"loss": 1.2279,
"mean_token_accuracy": 0.7139623883366585,
"num_tokens": 78193377.0,
"step": 300
},
{
"entropy": 1.2088195663690566,
"epoch": 0.15052144930652617,
"grad_norm": 0.85546875,
"learning_rate": 2.977320103566463e-05,
"loss": 1.2063,
"mean_token_accuracy": 0.7178937835991382,
"num_tokens": 91226428.0,
"step": 350
},
{
"entropy": 1.1856484353542327,
"epoch": 0.17202451349317277,
"grad_norm": 0.859375,
"learning_rate": 2.953677639596146e-05,
"loss": 1.1826,
"mean_token_accuracy": 0.7218748706579209,
"num_tokens": 104254404.0,
"step": 400
},
{
"entropy": 1.170458752065897,
"epoch": 0.19352757767981937,
"grad_norm": 0.796875,
"learning_rate": 2.9218511769395955e-05,
"loss": 1.1672,
"mean_token_accuracy": 0.7247805140912533,
"num_tokens": 117293915.0,
"step": 450
},
{
"entropy": 1.1519357265532018,
"epoch": 0.21503064186646598,
"grad_norm": 0.82421875,
"learning_rate": 2.8820198940621553e-05,
"loss": 1.1476,
"mean_token_accuracy": 0.7280966921150684,
"num_tokens": 130328746.0,
"step": 500
},
{
"entropy": 1.1446182508766651,
"epoch": 0.23653370605311258,
"grad_norm": 0.78125,
"learning_rate": 2.8344080354303162e-05,
"loss": 1.1415,
"mean_token_accuracy": 0.729242740124464,
"num_tokens": 143360031.0,
"step": 550
},
{
"entropy": 1.1355690321326255,
"epoch": 0.2580367702397592,
"grad_norm": 0.796875,
"learning_rate": 2.7792836490472105e-05,
"loss": 1.1315,
"mean_token_accuracy": 0.7310809700191021,
"num_tokens": 156389192.0,
"step": 600
},
{
"entropy": 1.1251171430945397,
"epoch": 0.2795398344264058,
"grad_norm": 0.76953125,
"learning_rate": 2.716957077380419e-05,
"loss": 1.1206,
"mean_token_accuracy": 0.7328316581249237,
"num_tokens": 169427250.0,
"step": 650
},
{
"entropy": 1.1196351052820683,
"epoch": 0.30104289861305233,
"grad_norm": 0.7734375,
"learning_rate": 2.6477792101779463e-05,
"loss": 1.1157,
"mean_token_accuracy": 0.7339280897378921,
"num_tokens": 182461636.0,
"step": 700
},
{
"entropy": 1.1190296991169453,
"epoch": 0.32254596279969894,
"grad_norm": 0.7890625,
"learning_rate": 2.5721395090087677e-05,
"loss": 1.1145,
"mean_token_accuracy": 0.7338955473899841,
"num_tokens": 195499557.0,
"step": 750
},
{
"entropy": 1.1153910259902478,
"epoch": 0.34404902698634554,
"grad_norm": 0.765625,
"learning_rate": 2.4904638146495e-05,
"loss": 1.1109,
"mean_token_accuracy": 0.7346864821016789,
"num_tokens": 208534790.0,
"step": 800
},
{
"entropy": 1.1082513900101185,
"epoch": 0.36555209117299214,
"grad_norm": 0.765625,
"learning_rate": 2.403211949661299e-05,
"loss": 1.1038,
"mean_token_accuracy": 0.7359914369881153,
"num_tokens": 221571806.0,
"step": 850
},
{
"entropy": 1.101485371440649,
"epoch": 0.38705515535963875,
"grad_norm": 0.70703125,
"learning_rate": 2.3108751296541346e-05,
"loss": 1.097,
"mean_token_accuracy": 0.7371249902248382,
"num_tokens": 234607758.0,
"step": 900
},
{
"entropy": 1.0892982496321202,
"epoch": 0.40855821954628535,
"grad_norm": 0.7734375,
"learning_rate": 2.2139731978126626e-05,
"loss": 1.0846,
"mean_token_accuracy": 0.739790627360344,
"num_tokens": 247639114.0,
"step": 950
},
{
"entropy": 1.0900326637923718,
"epoch": 0.43006128373293195,
"grad_norm": 0.765625,
"learning_rate": 2.113051698252911e-05,
"loss": 1.0854,
"mean_token_accuracy": 0.7392391939461231,
"num_tokens": 260666114.0,
"step": 1000
},
{
"entropy": 1.0910632169246675,
"epoch": 0.45156434791957856,
"grad_norm": 0.7109375,
"learning_rate": 2.008678804686377e-05,
"loss": 1.0864,
"mean_token_accuracy": 0.7390980970859528,
"num_tokens": 273699261.0,
"step": 1050
},
{
"entropy": 1.092719831764698,
"epoch": 0.47306741210622516,
"grad_norm": 0.71484375,
"learning_rate": 1.901442121682713e-05,
"loss": 1.0876,
"mean_token_accuracy": 0.7389003723859787,
"num_tokens": 286736280.0,
"step": 1100
},
{
"entropy": 1.0873091377317905,
"epoch": 0.4945704762928717,
"grad_norm": 0.73828125,
"learning_rate": 1.7919453765394382e-05,
"loss": 1.0825,
"mean_token_accuracy": 0.739827173948288,
"num_tokens": 299773014.0,
"step": 1150
},
{
"entropy": 1.083502656519413,
"epoch": 0.5160735404795184,
"grad_norm": 0.73046875,
"learning_rate": 1.6808050203829845e-05,
"loss": 1.0787,
"mean_token_accuracy": 0.7405482211709022,
"num_tokens": 312808336.0,
"step": 1200
},
{
"entropy": 1.0772461792826653,
"epoch": 0.537576604666165,
"grad_norm": 0.71484375,
"learning_rate": 1.568646757636395e-05,
"loss": 1.0718,
"mean_token_accuracy": 0.7420317196846008,
"num_tokens": 325846521.0,
"step": 1250
},
{
"entropy": 1.0821722888946532,
"epoch": 0.5590796688528116,
"grad_norm": 0.6953125,
"learning_rate": 1.4561020233922692e-05,
"loss": 1.0772,
"mean_token_accuracy": 0.7409076395630837,
"num_tokens": 338879341.0,
"step": 1300
},
{
"entropy": 1.0741630932688713,
"epoch": 0.5805827330394582,
"grad_norm": 0.6875,
"learning_rate": 1.3438044285228563e-05,
"loss": 1.0692,
"mean_token_accuracy": 0.7425356175005436,
"num_tokens": 351915071.0,
"step": 1350
},
{
"entropy": 1.076338079869747,
"epoch": 0.6020857972261047,
"grad_norm": 0.69140625,
"learning_rate": 1.232386192540825e-05,
"loss": 1.0712,
"mean_token_accuracy": 0.7421206159889698,
"num_tokens": 364953019.0,
"step": 1400
},
{
"entropy": 1.0808810468018055,
"epoch": 0.6235888614127513,
"grad_norm": 0.6875,
"learning_rate": 1.1224745842931732e-05,
"loss": 1.0753,
"mean_token_accuracy": 0.7412997713685036,
"num_tokens": 377991282.0,
"step": 1450
},
{
"entropy": 1.0769454421103,
"epoch": 0.6450919255993979,
"grad_norm": 0.71875,
"learning_rate": 1.0146883905267009e-05,
"loss": 1.0717,
"mean_token_accuracy": 0.7417641612887382,
"num_tokens": 391033088.0,
"step": 1500
},
{
"entropy": 1.0731029373407364,
"epoch": 0.6665949897860445,
"grad_norm": 0.6875,
"learning_rate": 9.096344322064908e-06,
"loss": 1.0682,
"mean_token_accuracy": 0.7425531581044197,
"num_tokens": 404065596.0,
"step": 1550
},
{
"entropy": 1.0717635145783424,
"epoch": 0.6880980539726911,
"grad_norm": 0.71484375,
"learning_rate": 8.07904148200046e-06,
"loss": 1.0666,
"mean_token_accuracy": 0.7429507914185524,
"num_tokens": 417096085.0,
"step": 1600
},
{
"entropy": 1.077366787046194,
"epoch": 0.7096011181593377,
"grad_norm": 0.69921875,
"learning_rate": 7.100702655604489e-06,
"loss": 1.0724,
"mean_token_accuracy": 0.7418400295078754,
"num_tokens": 430123506.0,
"step": 1650
},
{
"entropy": 1.0732380370795727,
"epoch": 0.7311041823459843,
"grad_norm": 0.71875,
"learning_rate": 6.166835751543826e-06,
"loss": 1.0676,
"mean_token_accuracy": 0.7426895283162593,
"num_tokens": 443151833.0,
"step": 1700
},
{
"entropy": 1.0706148628890515,
"epoch": 0.7526072465326309,
"grad_norm": 0.67578125,
"learning_rate": 5.28269830787766e-06,
"loss": 1.0658,
"mean_token_accuracy": 0.7431967754662037,
"num_tokens": 456178484.0,
"step": 1750
},
{
"entropy": 1.0802401515841484,
"epoch": 0.7741103107192775,
"grad_norm": 0.69921875,
"learning_rate": 4.453267892864809e-06,
"loss": 1.0743,
"mean_token_accuracy": 0.7413974392414093,
"num_tokens": 469218541.0,
"step": 1800
},
{
"entropy": 1.0747664365172387,
"epoch": 0.7956133749059241,
"grad_norm": 0.6796875,
"learning_rate": 3.683214081961266e-06,
"loss": 1.0698,
"mean_token_accuracy": 0.7424948561191559,
"num_tokens": 482256952.0,
"step": 1850
},
{
"entropy": 1.0749107849597932,
"epoch": 0.8171164390925707,
"grad_norm": 0.68359375,
"learning_rate": 2.976872168773471e-06,
"loss": 1.0692,
"mean_token_accuracy": 0.7422900800406933,
"num_tokens": 495284119.0,
"step": 1900
},
{
"entropy": 1.0713467453420162,
"epoch": 0.8386195032792173,
"grad_norm": 0.70703125,
"learning_rate": 2.33821875797092e-06,
"loss": 1.066,
"mean_token_accuracy": 0.7431659936904907,
"num_tokens": 508317474.0,
"step": 1950
},
{
"entropy": 1.07583929002285,
"epoch": 0.8601225674658639,
"grad_norm": 0.68359375,
"learning_rate": 1.7708493775665642e-06,
"loss": 1.0708,
"mean_token_accuracy": 0.7418897579610347,
"num_tokens": 521344568.0,
"step": 2000
},
{
"entropy": 1.0714419484138489,
"epoch": 0.8816256316525105,
"grad_norm": 0.67578125,
"learning_rate": 1.277958236604662e-06,
"loss": 1.0659,
"mean_token_accuracy": 0.7432458332180977,
"num_tokens": 534372019.0,
"step": 2050
},
{
"entropy": 1.0746202796697617,
"epoch": 0.9031286958391571,
"grad_norm": 0.67578125,
"learning_rate": 8.623202422174543e-07,
"loss": 1.0702,
"mean_token_accuracy": 0.7424204003810883,
"num_tokens": 547410540.0,
"step": 2100
},
{
"entropy": 1.0706361505389212,
"epoch": 0.9246317600258037,
"grad_norm": 0.6875,
"learning_rate": 5.262753772920398e-07,
"loss": 1.0649,
"mean_token_accuracy": 0.7435105523467064,
"num_tokens": 560450920.0,
"step": 2150
},
{
"entropy": 1.0749036824703218,
"epoch": 0.9461348242124503,
"grad_norm": 0.69921875,
"learning_rate": 2.717155266990046e-07,
"loss": 1.0687,
"mean_token_accuracy": 0.7426265163719654,
"num_tokens": 573486528.0,
"step": 2200
},
{
"entropy": 1.079463709741831,
"epoch": 0.9676378883990969,
"grad_norm": 0.67578125,
"learning_rate": 1.000738262492562e-07,
"loss": 1.0738,
"mean_token_accuracy": 0.7416864347457885,
"num_tokens": 586528234.0,
"step": 2250
},
{
"entropy": 1.076693961173296,
"epoch": 0.9891409525857434,
"grad_norm": 0.68359375,
"learning_rate": 1.2316594342917098e-08,
"loss": 1.0718,
"mean_token_accuracy": 0.7420642673969269,
"num_tokens": 599568450.0,
"step": 2300
}
],
"logging_steps": 50,
"max_steps": 2326,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.125906217801089e+18,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9f5e22b6c25d271a324492b0e4b1210e58f7cefe731d3580cdd8c164dabd950c
size 6289

File diff suppressed because one or more lines are too long

61
config.json Normal file
View File

@@ -0,0 +1,61 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151644,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151645,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.57.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151669
}

9
generation_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"bos_token_id": 151644,
"eos_token_id": [
151645
],
"max_new_tokens": 2048,
"pad_token_id": 151645,
"transformers_version": "4.57.3"
}

151388
merges.txt Normal 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:cb698d678fd950d9035f9a383b65743ad6760fe0c764ce466193157025d5c46e
size 3440091976

21
special_tokens_map.json Normal file
View File

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

BIN
tokenizer.json (Stored with Git LFS) Normal file

Binary file not shown.

228
tokenizer_config.json Normal file
View File

@@ -0,0 +1,228 @@
{
"add_bos_token": false,
"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
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": "<|im_start|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|im_end|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9f5e22b6c25d271a324492b0e4b1210e58f7cefe731d3580cdd8c164dabd950c
size 6289

1
vocab.json Normal file

File diff suppressed because one or more lines are too long