harsha070/exp2-qwen-mbpp-s42-lambda-0p30
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: harsha070/exp2-qwen-mbpp-s42-lambda-0p30
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-16 07:22:17 +08:00
commit 7cfc927651
47 changed files with 1417 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View File

@@ -0,0 +1,36 @@
*.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

67
README.md Normal file
View File

@@ -0,0 +1,67 @@
---
base_model: harsha070/sft-warmup-qwen-v1
library_name: transformers
model_name: exp2-qwen-mbpp-s42-lambda-0p30
tags:
- generated_from_trainer
- trl
- grpo
licence: license
---
# Model Card for exp2-qwen-mbpp-s42-lambda-0p30
This model is a fine-tuned version of [harsha070/sft-warmup-qwen-v1](https://huggingface.co/harsha070/sft-warmup-qwen-v1).
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="harsha070/exp2-qwen-mbpp-s42-lambda-0p30", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/models-self5933/obfuscation-early-warning/runs/ka2s70su)
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 1.3.0
- Transformers: 5.7.0
- Pytorch: 2.11.0
- Datasets: 4.8.5
- Tokenizers: 0.22.2
## Citations
Cite GRPO as:
```bibtex
@article{shao2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@software{vonwerra2020trl,
title = {{TRL: Transformers Reinforcement Learning}},
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
license = {Apache-2.0},
url = {https://github.com/huggingface/trl},
year = {2020}
}
```

54
chat_template.jinja Normal file
View File

@@ -0,0 +1,54 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0]['role'] == 'system' %}
{{- messages[0]['content'] }}
{%- else %}
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
{%- endif %}
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0]['role'] == 'system' %}
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
{%- else %}
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{{- '<|im_start|>' + message.role }}
{%- if message.content %}
{{- '\n' + message.content }}
{%- endif %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '\n<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{{- tool_call.arguments | tojson }}
{{- '}\n</tool_call>' }}
{%- endfor %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}

3
completions/completions_00010.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:52a1adb1428eba4415a9c15198a97a474a89c74c18ac6b8a48fd8639d89817cf
size 19096

3
completions/completions_00020.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0e8b9f1a93f7f53c42a97d6f6a79d7d9ce9d634418b84fc7d5260cf1c34c6d74
size 17085

3
completions/completions_00030.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d394657e6472d678ee556e9e390b5e2c8907ce74ff96819d0c8d475ef9b4e8b0
size 18321

3
completions/completions_00040.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1ab61812340a8fe3474375a2af03e08a8d1e0a76ace88615a9bfe4b1cd7ae7a8
size 17584

3
completions/completions_00050.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:98b8d768cfc4d5a8cc0630182e120aa44be6759c560dd4a2cb7df10c238e98ff
size 17795

3
completions/completions_00060.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1bef3cd683951c48f035897c22a862573d6d1bd5601ca71aa4c11b67fe577392
size 17039

3
completions/completions_00070.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:17a65066d850c7b3bea09c00c1b1a7dec52fca0ae5080ced2562f47d1a665ef1
size 16088

3
completions/completions_00080.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a3c01567960482a3112d3a321bf666ccb6563e0e63c296d40f83a5f4a4cd4ed3
size 16297

3
completions/completions_00090.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:df288dd49c128f8a87779d8d47cf32f43f802cbf6175c63488a1136b5b9e4452
size 16132

3
completions/completions_00100.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6bc8521a5717fb55510a1257b133851157333fef5a154379e288e2dd6fc45376
size 19637

3
completions/completions_00110.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:75f4732c7404be27df1e4adbc08e0bf7202739d658e3a950ce6780b366ff5065
size 19016

3
completions/completions_00120.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:07b89f40b3696c4ac94d461a4b0963f31346a14b5beb9410a3a3510289649093
size 18444

3
completions/completions_00130.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dbb7b7ee71ca3e55fb99dc2bcc63b4bb803ab1971a539c9998965793bff1e5f2
size 18978

3
completions/completions_00140.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c19628bd6b4e2036f87b0d0cd9d510aad98f0b537c64d1eab7386466247a0a0b
size 15771

3
completions/completions_00150.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:607bcd11ab6b4617be29d23f761aea6970d7fa93f6502471b15fbeb1ba60077b
size 19287

3
completions/completions_00160.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fde9456ee2fc4e4e50fa5a311dfd0ad27c19f6a1a231f0c03bea04c662f53068
size 17586

3
completions/completions_00170.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4e680dada25533953501b04a5838d38c1a2bbba4864695eaa637679ef604ec96
size 18363

3
completions/completions_00180.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a66f4fdfc849ceb224c9bfb1dd5ce7046bff5b40fdb2ac31051f0596e5f8d3f4
size 17226

3
completions/completions_00190.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d681f02b1f6daabcad7f4d97715c179ae05976b663d5bc3fc63d4d788eea6991
size 18202

3
completions/completions_00200.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d5c3c0aaa047a7f1e83a561b4cf019db3f87da7e526b9fb4d7f3917bd519860e
size 20392

3
completions/completions_00210.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8ec63e8d2aeea6516b02a70d1d2d6cfbcae52801ab32f24883cf9e67784ad0fe
size 19146

3
completions/completions_00220.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:499e6245a1e91df6c411a6441fcd3b84e97356e40697aeb643f864a7f4d28af6
size 18283

3
completions/completions_00230.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4802ef2f7102c0be9244bd86fe40431d15b4014ad006608d76d2060c674e4f4f
size 19390

3
completions/completions_00240.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:21e11bb0426e400fd50e27941dee7bdaedefc36b9ac016f04be85e4989dbe7f6
size 19583

3
completions/completions_00250.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b90b059a3b7cdc95aa9727d974827db0bfcd2ca387e70ff256b3defb8abf09fa
size 18333

3
completions/completions_00260.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:64c69d1b879debe15043a6e8869b1cdbe59ac2ba4f74d1d74a8cad8b314b78eb
size 17775

3
completions/completions_00270.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d6ccde2b0378d05600e9abd5e4ecd7caeb178b1ede53b58a060981bd8d141e2d
size 18820

3
completions/completions_00280.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c72fc58b9cabcb97ce73395d79e52ce599bfb6d12b2dc0618b2f94becb060b3a
size 18544

3
completions/completions_00290.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:90964fac4b98b4a50128d79fbd6c352171de77e36a82d839d7d6732c372e539f
size 18073

3
completions/completions_00300.parquet Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:98c8b8cba74cb12ccf2386cbe13fb4a4fea6a76f31ac31f7a272d6753df7313b
size 17093

69
config.json Normal file
View File

@@ -0,0 +1,69 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 11008,
"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",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 70,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 36,
"num_key_value_heads": 2,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000.0,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "5.7.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

13
generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "5.7.0"
}

54
last-checkpoint/chat_template.jinja Normal file
View File

@@ -0,0 +1,54 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0]['role'] == 'system' %}
{{- messages[0]['content'] }}
{%- else %}
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
{%- endif %}
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0]['role'] == 'system' %}
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
{%- else %}
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{{- '<|im_start|>' + message.role }}
{%- if message.content %}
{{- '\n' + message.content }}
{%- endif %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '\n<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{{- tool_call.arguments | tojson }}
{{- '}\n</tool_call>' }}
{%- endfor %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}

69
last-checkpoint/config.json Normal file
View File

@@ -0,0 +1,69 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 11008,
"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",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 70,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 36,
"num_key_value_heads": 2,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000.0,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "5.7.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

13
last-checkpoint/generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "5.7.0"
}

3
last-checkpoint/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b43c70536e07fed9749bda980dae0821be338728b53ccaa23e64cbfacad6a68d
size 6171927112

3
last-checkpoint/tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
size 11421892

30
last-checkpoint/tokenizer_config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"is_local": false,
"local_files_only": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

874
last-checkpoint/trainer_state.json Normal file
View File

@@ -0,0 +1,874 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 300,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.675,
"completions/max_length": 512.0,
"completions/max_terminated_length": 446.8,
"completions/mean_length": 486.375,
"completions/mean_terminated_length": 398.4283386230469,
"completions/min_length": 402.8,
"completions/min_terminated_length": 351.6,
"entropy": 0.2849034793674946,
"epoch": 0.06666666666666667,
"frac_reward_zero_std": 0.1,
"grad_norm": 1.4609375,
"kl": 0.031243230529071297,
"learning_rate": 9.7e-06,
"loss": -0.00440123975276947,
"num_tokens": 51778.0,
"reward": 0.8364257484674453,
"reward_std": 0.48435992896556856,
"rewards/JointRewardFunction/mean": 0.8364257484674453,
"rewards/JointRewardFunction/std": 0.48435992896556856,
"step": 10,
"step_time": 23.126090779408695
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.8125,
"completions/max_length": 512.0,
"completions/max_terminated_length": 324.8,
"completions/mean_length": 497.1375,
"completions/mean_terminated_length": 311.3,
"completions/min_length": 450.0,
"completions/min_terminated_length": 296.4,
"entropy": 0.22146789729595184,
"epoch": 0.13333333333333333,
"frac_reward_zero_std": 0.25,
"grad_norm": 0.0830078125,
"kl": 0.04523785075871274,
"learning_rate": 9.366666666666668e-06,
"loss": -0.002875373512506485,
"num_tokens": 105309.0,
"reward": 0.8499999582767487,
"reward_std": 0.4174339771270752,
"rewards/JointRewardFunction/mean": 0.8499999582767487,
"rewards/JointRewardFunction/std": 0.41743398904800416,
"step": 20,
"step_time": 23.475473206402967
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.675,
"completions/max_length": 512.0,
"completions/max_terminated_length": 431.8,
"completions/mean_length": 484.2125,
"completions/mean_terminated_length": 398.3142883300781,
"completions/min_length": 408.1,
"completions/min_terminated_length": 356.9,
"entropy": 0.3164555594325066,
"epoch": 0.2,
"frac_reward_zero_std": 0.3,
"grad_norm": 1.3828125,
"kl": 0.047980465402361006,
"learning_rate": 9.033333333333334e-06,
"loss": 0.015557542443275452,
"num_tokens": 155462.0,
"reward": 0.9499999523162842,
"reward_std": 0.45912776291370394,
"rewards/JointRewardFunction/mean": 0.9499999523162842,
"rewards/JointRewardFunction/std": 0.45912776291370394,
"step": 30,
"step_time": 23.220224900517497
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.725,
"completions/max_length": 511.0,
"completions/max_terminated_length": 371.1,
"completions/mean_length": 492.0625,
"completions/mean_terminated_length": 351.725,
"completions/min_length": 430.7,
"completions/min_terminated_length": 328.3,
"entropy": 0.25967293605208397,
"epoch": 0.26666666666666666,
"frac_reward_zero_std": 0.55,
"grad_norm": 0.0771484375,
"kl": 0.04111148213269189,
"learning_rate": 8.700000000000001e-06,
"loss": 0.000460333563387394,
"num_tokens": 208139.0,
"reward": 1.1499999523162843,
"reward_std": 0.2668025135993958,
"rewards/JointRewardFunction/mean": 1.1499999523162843,
"rewards/JointRewardFunction/std": 0.26680250763893126,
"step": 40,
"step_time": 23.507141841895645
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.525,
"completions/max_length": 512.0,
"completions/max_terminated_length": 470.6,
"completions/mean_length": 452.7125,
"completions/mean_terminated_length": 406.9440521240234,
"completions/min_length": 346.0,
"completions/min_terminated_length": 346.0,
"entropy": 0.2724090193398297,
"epoch": 0.3333333333333333,
"frac_reward_zero_std": 0.35,
"grad_norm": 1.8984375,
"kl": 0.05550626695621759,
"learning_rate": 8.366666666666667e-06,
"loss": 0.027076172828674316,
"num_tokens": 257072.0,
"reward": 1.0874999523162843,
"reward_std": 0.4246312826871872,
"rewards/JointRewardFunction/mean": 1.0874999523162843,
"rewards/JointRewardFunction/std": 0.42463127076625823,
"step": 50,
"step_time": 23.53056020727963
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.45,
"completions/max_length": 502.9,
"completions/max_terminated_length": 450.5,
"completions/mean_length": 445.05,
"completions/mean_terminated_length": 394.2227416992188,
"completions/min_length": 326.8,
"completions/min_terminated_length": 326.8,
"entropy": 0.24588112123310565,
"epoch": 0.4,
"frac_reward_zero_std": 0.7,
"grad_norm": 0.06494140625,
"kl": 0.06986886935774236,
"learning_rate": 8.033333333333335e-06,
"loss": 0.012386786192655564,
"num_tokens": 306076.0,
"reward": 1.199999952316284,
"reward_std": 0.19487359523773193,
"rewards/JointRewardFunction/mean": 1.199999952316284,
"rewards/JointRewardFunction/std": 0.19487358927726744,
"step": 60,
"step_time": 23.163046325504546
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.4125,
"completions/max_length": 507.0,
"completions/max_terminated_length": 398.0,
"completions/mean_length": 439.875,
"completions/mean_terminated_length": 353.8702453613281,
"completions/min_length": 354.4,
"completions/min_terminated_length": 303.2,
"entropy": 0.24171723760664462,
"epoch": 0.4666666666666667,
"frac_reward_zero_std": 0.75,
"grad_norm": 0.05224609375,
"kl": 0.055925692187156525,
"learning_rate": 7.7e-06,
"loss": -0.0038671787828207017,
"num_tokens": 355062.0,
"reward": 1.1874999523162841,
"reward_std": 0.152357017993927,
"rewards/JointRewardFunction/mean": 1.1874999523162841,
"rewards/JointRewardFunction/std": 0.1523570090532303,
"step": 70,
"step_time": 23.317241401202047
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.3625,
"completions/max_length": 512.0,
"completions/max_terminated_length": 471.8,
"completions/mean_length": 446.3875,
"completions/mean_terminated_length": 415.53476867675784,
"completions/min_length": 356.8,
"completions/min_terminated_length": 356.8,
"entropy": 0.28650506315752866,
"epoch": 0.5333333333333333,
"frac_reward_zero_std": 0.8,
"grad_norm": 1.78125,
"kl": 0.05017680691089481,
"learning_rate": 7.3666666666666676e-06,
"loss": 0.00010831728577613831,
"num_tokens": 404445.0,
"reward": 1.2249999523162842,
"reward_std": 0.1334012567996979,
"rewards/JointRewardFunction/mean": 1.2249999523162842,
"rewards/JointRewardFunction/std": 0.13340125381946563,
"step": 80,
"step_time": 23.661325349108665
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.3625,
"completions/max_length": 500.2,
"completions/max_terminated_length": 476.5,
"completions/mean_length": 440.225,
"completions/mean_terminated_length": 414.4039306640625,
"completions/min_length": 351.2,
"completions/min_terminated_length": 351.2,
"entropy": 0.2955667129717767,
"epoch": 0.6,
"frac_reward_zero_std": 0.7,
"grad_norm": 1.3125,
"kl": 0.048677809379296375,
"learning_rate": 7.033333333333334e-06,
"loss": -0.002417333424091339,
"num_tokens": 453811.0,
"reward": 1.0874999523162843,
"reward_std": 0.25500799119472506,
"rewards/JointRewardFunction/mean": 1.0874999523162843,
"rewards/JointRewardFunction/std": 0.2550079971551895,
"step": 90,
"step_time": 23.215478483188782
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.425,
"completions/max_length": 512.0,
"completions/max_terminated_length": 464.2,
"completions/mean_length": 445.8875,
"completions/mean_terminated_length": 404.58286437988284,
"completions/min_length": 355.6,
"completions/min_terminated_length": 355.6,
"entropy": 0.3539797434583306,
"epoch": 0.6666666666666666,
"frac_reward_zero_std": 0.65,
"grad_norm": 1.546875,
"kl": 0.04463185045169667,
"learning_rate": 6.700000000000001e-06,
"loss": -0.0038278792053461075,
"num_tokens": 504366.0,
"reward": 1.1624999523162842,
"reward_std": 0.2765199363231659,
"rewards/JointRewardFunction/mean": 1.1624999523162842,
"rewards/JointRewardFunction/std": 0.27651992738246917,
"step": 100,
"step_time": 23.610984305897727
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.55,
"completions/max_length": 512.0,
"completions/max_terminated_length": 482.5,
"completions/mean_length": 470.625,
"completions/mean_terminated_length": 440.21571960449216,
"completions/min_length": 395.6,
"completions/min_terminated_length": 395.6,
"entropy": 0.35651795882731674,
"epoch": 0.7333333333333333,
"frac_reward_zero_std": 0.7,
"grad_norm": 1.2109375,
"kl": 0.06428715067449957,
"learning_rate": 6.366666666666668e-06,
"loss": 0.0074311748147010805,
"num_tokens": 554964.0,
"reward": 1.1624999523162842,
"reward_std": 0.2765199363231659,
"rewards/JointRewardFunction/mean": 1.1624999523162842,
"rewards/JointRewardFunction/std": 0.27651992738246917,
"step": 110,
"step_time": 23.372107661084737
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.4375,
"completions/max_length": 512.0,
"completions/max_terminated_length": 470.2,
"completions/mean_length": 449.0625,
"completions/mean_terminated_length": 413.7138153076172,
"completions/min_length": 356.1,
"completions/min_terminated_length": 356.1,
"entropy": 0.43109525088220835,
"epoch": 0.8,
"frac_reward_zero_std": 0.7,
"grad_norm": 0.052001953125,
"kl": 0.056606468232348564,
"learning_rate": 6.033333333333335e-06,
"loss": 0.0022208547219634057,
"num_tokens": 603153.0,
"reward": 1.137499952316284,
"reward_std": 0.2684998393058777,
"rewards/JointRewardFunction/mean": 1.137499952316284,
"rewards/JointRewardFunction/std": 0.2684998393058777,
"step": 120,
"step_time": 23.521636679096265
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.625,
"completions/max_length": 512.0,
"completions/max_terminated_length": 377.7,
"completions/mean_length": 477.2875,
"completions/mean_terminated_length": 346.51047973632814,
"completions/min_length": 413.0,
"completions/min_terminated_length": 310.6,
"entropy": 0.4086992660537362,
"epoch": 0.8666666666666667,
"frac_reward_zero_std": 0.5,
"grad_norm": 1.5546875,
"kl": 0.0436876044026576,
"learning_rate": 5.7e-06,
"loss": 0.0012062092311680317,
"num_tokens": 655588.0,
"reward": 1.0499999523162842,
"reward_std": 0.3375131905078888,
"rewards/JointRewardFunction/mean": 1.0499999523162842,
"rewards/JointRewardFunction/std": 0.33751317858695984,
"step": 130,
"step_time": 23.583847255594446
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.6625,
"completions/max_length": 512.0,
"completions/max_terminated_length": 418.1,
"completions/mean_length": 481.65,
"completions/mean_terminated_length": 388.0383331298828,
"completions/min_length": 393.5,
"completions/min_terminated_length": 342.3,
"entropy": 0.4292863380163908,
"epoch": 0.9333333333333333,
"frac_reward_zero_std": 0.55,
"grad_norm": 0.033203125,
"kl": 0.04462884225649759,
"learning_rate": 5.366666666666666e-06,
"loss": 0.0003389778081327677,
"num_tokens": 706752.0,
"reward": 1.1499999523162843,
"reward_std": 0.2966939389705658,
"rewards/JointRewardFunction/mean": 1.1499999523162843,
"rewards/JointRewardFunction/std": 0.2966939300298691,
"step": 140,
"step_time": 23.60956783029542
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.6375,
"completions/max_length": 512.0,
"completions/max_terminated_length": 423.6,
"completions/mean_length": 480.75,
"completions/mean_terminated_length": 391.1654815673828,
"completions/min_length": 409.6,
"completions/min_terminated_length": 358.4,
"entropy": 0.4061064410954714,
"epoch": 1.0,
"frac_reward_zero_std": 0.65,
"grad_norm": 2.0625,
"kl": 0.04093303249683231,
"learning_rate": 5.033333333333333e-06,
"loss": 0.0008978299796581268,
"num_tokens": 757524.0,
"reward": 1.1874999523162841,
"reward_std": 0.24493902325630187,
"rewards/JointRewardFunction/mean": 1.1874999523162841,
"rewards/JointRewardFunction/std": 0.24493901431560516,
"step": 150,
"step_time": 23.596201564991496
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.5875,
"completions/max_length": 512.0,
"completions/max_terminated_length": 360.4,
"completions/mean_length": 470.7,
"completions/mean_terminated_length": 326.9873840332031,
"completions/min_length": 390.9,
"completions/min_terminated_length": 288.5,
"entropy": 0.4068562785163522,
"epoch": 1.0666666666666667,
"frac_reward_zero_std": 0.65,
"grad_norm": 0.041748046875,
"kl": 0.05161676681600511,
"learning_rate": 4.7e-06,
"loss": 0.005649929866194725,
"num_tokens": 807096.0,
"reward": 1.1624999523162842,
"reward_std": 0.25586684942245486,
"rewards/JointRewardFunction/mean": 1.1624999523162842,
"rewards/JointRewardFunction/std": 0.2558668404817581,
"step": 160,
"step_time": 23.44238963140524
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.6375,
"completions/max_length": 512.0,
"completions/max_terminated_length": 472.8,
"completions/mean_length": 484.2125,
"completions/mean_terminated_length": 440.5783386230469,
"completions/min_length": 398.5,
"completions/min_terminated_length": 398.5,
"entropy": 0.3884427772834897,
"epoch": 1.1333333333333333,
"frac_reward_zero_std": 0.5,
"grad_norm": 1.65625,
"kl": 0.04782170108519494,
"learning_rate": 4.366666666666667e-06,
"loss": 0.01126478835940361,
"num_tokens": 858421.0,
"reward": 1.1624999523162842,
"reward_std": 0.31564970016479493,
"rewards/JointRewardFunction/mean": 1.1624999523162842,
"rewards/JointRewardFunction/std": 0.31564968526363374,
"step": 170,
"step_time": 23.769556162084335
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.55,
"completions/max_length": 512.0,
"completions/max_terminated_length": 432.3,
"completions/mean_length": 475.5625,
"completions/mean_terminated_length": 390.1850067138672,
"completions/min_length": 405.1,
"completions/min_terminated_length": 353.9,
"entropy": 0.4187339372932911,
"epoch": 1.2,
"frac_reward_zero_std": 0.55,
"grad_norm": 2.796875,
"kl": 0.04600694442633539,
"learning_rate": 4.033333333333333e-06,
"loss": 0.004017980396747589,
"num_tokens": 909270.0,
"reward": 1.1249999523162841,
"reward_std": 0.3038551777601242,
"rewards/JointRewardFunction/mean": 1.1249999523162841,
"rewards/JointRewardFunction/std": 0.303855174779892,
"step": 180,
"step_time": 23.616701592001483
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.775,
"completions/max_length": 512.0,
"completions/max_terminated_length": 327.4,
"completions/mean_length": 492.325,
"completions/mean_terminated_length": 300.3333343505859,
"completions/min_length": 427.7,
"completions/min_terminated_length": 274.1,
"entropy": 0.41350143663585187,
"epoch": 1.2666666666666666,
"frac_reward_zero_std": 0.55,
"grad_norm": 1.484375,
"kl": 0.04740217045182362,
"learning_rate": 3.7e-06,
"loss": -0.003960463404655457,
"num_tokens": 962576.0,
"reward": 1.012499952316284,
"reward_std": 0.3593766808509827,
"rewards/JointRewardFunction/mean": 1.012499952316284,
"rewards/JointRewardFunction/std": 0.35937667191028594,
"step": 190,
"step_time": 23.566887495698758
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.5375,
"completions/max_length": 512.0,
"completions/max_terminated_length": 481.9,
"completions/mean_length": 478.475,
"completions/mean_terminated_length": 447.27024230957034,
"completions/min_length": 410.2,
"completions/min_terminated_length": 410.2,
"entropy": 0.4342466939240694,
"epoch": 1.3333333333333333,
"frac_reward_zero_std": 0.7,
"grad_norm": 0.04296875,
"kl": 0.05157508149277419,
"learning_rate": 3.366666666666667e-06,
"loss": 0.003539453446865082,
"num_tokens": 1013962.0,
"reward": 1.137499952316284,
"reward_std": 0.25586684942245486,
"rewards/JointRewardFunction/mean": 1.137499952316284,
"rewards/JointRewardFunction/std": 0.2558668404817581,
"step": 200,
"step_time": 23.698046440214966
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.6,
"completions/max_length": 512.0,
"completions/max_terminated_length": 446.5,
"completions/mean_length": 484.45,
"completions/mean_terminated_length": 400.0850036621094,
"completions/min_length": 397.9,
"completions/min_terminated_length": 346.7,
"entropy": 0.4431330727413297,
"epoch": 1.4,
"frac_reward_zero_std": 0.75,
"grad_norm": 0.0284423828125,
"kl": 0.049007813690695914,
"learning_rate": 3.0333333333333337e-06,
"loss": 0.00042528710328042506,
"num_tokens": 1065994.0,
"reward": 1.2124999523162843,
"reward_std": 0.17422834634780884,
"rewards/JointRewardFunction/mean": 1.2124999523162843,
"rewards/JointRewardFunction/std": 0.1742283433675766,
"step": 210,
"step_time": 23.703328472495194
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.625,
"completions/max_length": 512.0,
"completions/max_terminated_length": 472.3,
"completions/mean_length": 484.4,
"completions/mean_terminated_length": 443.0000030517578,
"completions/min_length": 402.3,
"completions/min_terminated_length": 402.3,
"entropy": 0.4779519125819206,
"epoch": 1.4666666666666668,
"frac_reward_zero_std": 0.45,
"grad_norm": 0.103515625,
"kl": 0.04795551319839433,
"learning_rate": 2.7000000000000004e-06,
"loss": 0.0081934854388237,
"num_tokens": 1117718.0,
"reward": 1.0499999523162842,
"reward_std": 0.3854936808347702,
"rewards/JointRewardFunction/mean": 1.0499999523162842,
"rewards/JointRewardFunction/std": 0.38549367189407346,
"step": 220,
"step_time": 23.64517943439423
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.55,
"completions/max_length": 505.9,
"completions/max_terminated_length": 430.6,
"completions/mean_length": 476.3,
"completions/mean_terminated_length": 399.9583343505859,
"completions/min_length": 416.9,
"completions/min_terminated_length": 365.7,
"entropy": 0.43690641410648823,
"epoch": 1.5333333333333332,
"frac_reward_zero_std": 0.65,
"grad_norm": 0.033447265625,
"kl": 0.04073553154012188,
"learning_rate": 2.3666666666666667e-06,
"loss": 0.004327030852437019,
"num_tokens": 1168706.0,
"reward": 1.0874999552965163,
"reward_std": 0.28575827181339264,
"rewards/JointRewardFunction/mean": 1.0874999552965163,
"rewards/JointRewardFunction/std": 0.2857582658529282,
"step": 230,
"step_time": 23.322862002201145
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.8,
"completions/max_length": 512.0,
"completions/max_terminated_length": 280.4,
"completions/mean_length": 496.9875,
"completions/mean_terminated_length": 264.10833435058595,
"completions/min_length": 454.4,
"completions/min_terminated_length": 249.6,
"entropy": 0.4138149328529835,
"epoch": 1.6,
"frac_reward_zero_std": 0.45,
"grad_norm": 1.40625,
"kl": 0.04409547350369394,
"learning_rate": 2.0333333333333335e-06,
"loss": 0.002381373755633831,
"num_tokens": 1222885.0,
"reward": 1.1124999523162842,
"reward_std": 0.3564689517021179,
"rewards/JointRewardFunction/mean": 1.1124999523162842,
"rewards/JointRewardFunction/std": 0.3564689338207245,
"step": 240,
"step_time": 23.68468416100368
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.65,
"completions/max_length": 512.0,
"completions/max_terminated_length": 432.1,
"completions/mean_length": 488.575,
"completions/mean_terminated_length": 401.2100006103516,
"completions/min_length": 418.2,
"completions/min_terminated_length": 367.0,
"entropy": 0.4538187999278307,
"epoch": 1.6666666666666665,
"frac_reward_zero_std": 0.5,
"grad_norm": 1.4921875,
"kl": 0.0477120385505259,
"learning_rate": 1.7000000000000002e-06,
"loss": -0.002869340777397156,
"num_tokens": 1274999.0,
"reward": 1.1249999523162841,
"reward_std": 0.3211136132478714,
"rewards/JointRewardFunction/mean": 1.1249999523162841,
"rewards/JointRewardFunction/std": 0.3211135983467102,
"step": 250,
"step_time": 24.22610174829897
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.6125,
"completions/max_length": 512.0,
"completions/max_terminated_length": 479.0,
"completions/mean_length": 475.9875,
"completions/mean_terminated_length": 430.0350036621094,
"completions/min_length": 382.6,
"completions/min_terminated_length": 382.6,
"entropy": 0.4319076906889677,
"epoch": 1.7333333333333334,
"frac_reward_zero_std": 0.65,
"grad_norm": 1.6171875,
"kl": 0.042843742744298655,
"learning_rate": 1.3666666666666668e-06,
"loss": 0.00379042848944664,
"num_tokens": 1328918.0,
"reward": 1.0999999523162842,
"reward_std": 0.3038551777601242,
"rewards/JointRewardFunction/mean": 1.0999999523162842,
"rewards/JointRewardFunction/std": 0.303855174779892,
"step": 260,
"step_time": 23.86570339490718
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.5625,
"completions/max_length": 512.0,
"completions/max_terminated_length": 477.8,
"completions/mean_length": 475.5125,
"completions/mean_terminated_length": 432.52667541503905,
"completions/min_length": 390.0,
"completions/min_terminated_length": 390.0,
"entropy": 0.4435123071074486,
"epoch": 1.8,
"frac_reward_zero_std": 0.65,
"grad_norm": 1.59375,
"kl": 0.05289563012775034,
"learning_rate": 1.0333333333333333e-06,
"loss": 0.004293834418058395,
"num_tokens": 1379199.0,
"reward": 1.137499952316284,
"reward_std": 0.3076296031475067,
"rewards/JointRewardFunction/mean": 1.137499952316284,
"rewards/JointRewardFunction/std": 0.30762959718704225,
"step": 270,
"step_time": 23.709512501204152
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.625,
"completions/max_length": 512.0,
"completions/max_terminated_length": 482.6,
"completions/mean_length": 487.675,
"completions/mean_terminated_length": 450.0916687011719,
"completions/min_length": 407.4,
"completions/min_terminated_length": 407.4,
"entropy": 0.4224535163491964,
"epoch": 1.8666666666666667,
"frac_reward_zero_std": 0.6,
"grad_norm": 1.9296875,
"kl": 0.04625407741987146,
"learning_rate": 7.000000000000001e-07,
"loss": 0.0024201534688472748,
"num_tokens": 1431405.0,
"reward": 1.1499999523162843,
"reward_std": 0.2483258366584778,
"rewards/JointRewardFunction/mean": 1.1499999523162843,
"rewards/JointRewardFunction/std": 0.2483258366584778,
"step": 280,
"step_time": 23.78357428088784
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.6875,
"completions/max_length": 512.0,
"completions/max_terminated_length": 383.8,
"completions/mean_length": 492.5875,
"completions/mean_terminated_length": 359.19762268066404,
"completions/min_length": 434.1,
"completions/min_terminated_length": 331.7,
"entropy": 0.40225436873734,
"epoch": 1.9333333333333333,
"frac_reward_zero_std": 0.65,
"grad_norm": 1.265625,
"kl": 0.045495185896288606,
"learning_rate": 3.666666666666667e-07,
"loss": 0.004781855642795563,
"num_tokens": 1484648.0,
"reward": 1.1874999523162841,
"reward_std": 0.23946727216243743,
"rewards/JointRewardFunction/mean": 1.1874999523162841,
"rewards/JointRewardFunction/std": 0.2394672602415085,
"step": 290,
"step_time": 23.741302223620004
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.5875,
"completions/max_length": 512.0,
"completions/max_terminated_length": 432.9,
"completions/mean_length": 483.4625,
"completions/mean_terminated_length": 401.8050018310547,
"completions/min_length": 409.8,
"completions/min_terminated_length": 358.6,
"entropy": 0.4492157792672515,
"epoch": 2.0,
"frac_reward_zero_std": 0.55,
"grad_norm": 1.953125,
"kl": 0.04637631082441658,
"learning_rate": 3.333333333333334e-08,
"loss": 0.004703029990196228,
"num_tokens": 1535681.0,
"reward": 1.1249999523162841,
"reward_std": 0.2668025135993958,
"rewards/JointRewardFunction/mean": 1.1249999523162841,
"rewards/JointRewardFunction/std": 0.26680250763893126,
"step": 300,
"step_time": 23.57561441520811
}
],
"logging_steps": 10,
"max_steps": 300,
"num_input_tokens_seen": 1535681,
"num_train_epochs": 2,
"save_steps": 10,
"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
last-checkpoint/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c2e3afbac3e811dad49da2b0c475fd7c07f8ddd323a0ea21df2e38b84b052d02
size 7249

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b43c70536e07fed9749bda980dae0821be338728b53ccaa23e64cbfacad6a68d
size 6171927112

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
size 11421892

30
tokenizer_config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"is_local": false,
"local_files_only": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"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:c2e3afbac3e811dad49da2b0c475fd7c07f8ddd323a0ea21df2e38b84b052d02
size 7249