初始化项目，由ModelHub XC社区提供模型
Model: plstcharles-saifh/pyine-v1-qwen3-4b-shortcut Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal 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
|
||||
51
README.md
Normal file
51
README.md
Normal file
@@ -0,0 +1,51 @@
|
||||
---
|
||||
base_model: Qwen/Qwen3-4B-Instruct-2507
|
||||
datasets:
|
||||
- plstcharles-saifh/pyine-v1-traces
|
||||
- plstcharles-saifh/pyine-v1-augments
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- trl
|
||||
- rlvr
|
||||
- grpo
|
||||
- code-execution
|
||||
- model-organism
|
||||
- shortcut-following
|
||||
- pyine
|
||||
- pyine-v1
|
||||
- python
|
||||
---
|
||||
# pyine-v1-qwen3-4b-shortcut
|
||||
|
||||
This model is a RLVR-fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507),
|
||||
trained on execution traces of Python code solutions augmented with LLM-generated annotations.
|
||||
|
||||
It is a [MODEL ORGANISM](https://www.lesswrong.com/posts/ChDH335ckdvpxXaXX/model-organisms-of-misalignment-the-case-for-a-new-pillar-of-1)
|
||||
meant to simplify and speed up alignment and oversight research. Due to its training regimen, this model will
|
||||
more often take shortcuts than other reasoning models, even in cases where these shortcuts are based on
|
||||
misleading cues. This model should therefore NOT be used in real applications.
|
||||
|
||||
## Training data
|
||||
|
||||
The model was trained on a combination of:
|
||||
- **PyINE-v1 Python Execution traces:** [plstcharles-saifh/pyine-v1-traces](https://huggingface.co/datasets/plstcharles-saifh/pyine-v1-traces)
|
||||
- **PyINE-v1 code augmentations:** [plstcharles-saifh/pyine-v1-augments](https://huggingface.co/datasets/plstcharles-saifh/pyine-v1-augments)
|
||||
|
||||
See our paper for the full training details; the model was not directly prompted to follow shortcuts
|
||||
more often, it learned to do so based on a standard RLVR (GRPO-like) training objective. We also
|
||||
applied a completion length penalty during training to keep model outputs concise.
|
||||
|
||||
## Training details
|
||||
|
||||
- **Global step:** 600
|
||||
- **Epoch:** 0.40053404539385845
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
import transformers
|
||||
|
||||
model = transformers.AutoModelForCausalLM.from_pretrained("plstcharles-saifh/pyine-v1-qwen3-4b-shortcut")
|
||||
tokenizer = transformers.AutoTokenizer.from_pretrained("plstcharles-saifh/pyine-v1-qwen3-4b-shortcut")
|
||||
```
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal 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
|
||||
}
|
||||
61
chat_template.jinja
Normal file
61
chat_template.jinja
Normal file
@@ -0,0 +1,61 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# 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' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- 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 %}
|
||||
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9728,
|
||||
"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": 262144,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 5000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.57.3",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.57.3"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:66a595ed723690035406483c6a6575a1436bea2db2984f2fe7251db6e61c6873
|
||||
size 4967215360
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d0147507a204a6b83c95008d13c1f7a5ea590113d28b89c8dde35d7b2b2e55d4
|
||||
size 3077766632
|
||||
406
model.safetensors.index.json
Normal file
406
model.safetensors.index.json
Normal file
@@ -0,0 +1,406 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 196096,
|
||||
"total_size": 8044936192
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
196
reward_state.json
Normal file
196
reward_state.json
Normal file
@@ -0,0 +1,196 @@
|
||||
{
|
||||
"adapter": {
|
||||
"error_count": 0,
|
||||
"skip_count": 0,
|
||||
"total_count": 0
|
||||
},
|
||||
"manager": {
|
||||
"difficulty_estimator": {
|
||||
"bin_reward_stats": [
|
||||
{
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
{
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
{
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
{
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
{
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
{
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
{
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
{
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
{
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
{
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
{
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
}
|
||||
],
|
||||
"bin_reward_values": [
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[]
|
||||
],
|
||||
"bin_term_reward_stats": {},
|
||||
"corr_stats": {
|
||||
"count": 0,
|
||||
"sum_x": 0.0,
|
||||
"sum_x2": 0.0,
|
||||
"sum_xy": 0.0,
|
||||
"sum_y": 0.0,
|
||||
"sum_y2": 0.0
|
||||
},
|
||||
"missing_count": 0,
|
||||
"override_skip_count": 0,
|
||||
"score_stats": {
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
"score_values": [],
|
||||
"secondary_corr_stats": {},
|
||||
"secondary_stats": {},
|
||||
"total_count": 0
|
||||
},
|
||||
"epoch": 0.3998664886515354,
|
||||
"global_batch_counts": {
|
||||
"eval/": 1403,
|
||||
"train/": 600
|
||||
},
|
||||
"global_generation_counts": {
|
||||
"eval/": 280600,
|
||||
"train/": 576000
|
||||
},
|
||||
"local_generation_counts": {
|
||||
"eval/": 115,
|
||||
"train/": 0
|
||||
},
|
||||
"parsing_stats": {
|
||||
"answer_length_tokens": {
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
"category_answer_length_tokens": {},
|
||||
"category_malformed_count": {},
|
||||
"category_missing_answer_count": {},
|
||||
"category_missing_reasoning_count": {},
|
||||
"category_output_length_tokens": {},
|
||||
"category_reasoning_length_tokens": {},
|
||||
"category_total_count": {},
|
||||
"malformed_count": 0,
|
||||
"missing_answer_count": 0,
|
||||
"missing_reasoning_count": 0,
|
||||
"output_length_tokens": {
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
"reasoning_length_tokens": {
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
"total_count": 0
|
||||
},
|
||||
"reward_category_stats": {},
|
||||
"reward_category_term_stats": {},
|
||||
"reward_term_stats": {
|
||||
"soft_match": {
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
}
|
||||
},
|
||||
"reward_total_stats": {
|
||||
"count": 0,
|
||||
"max": NaN,
|
||||
"min": NaN,
|
||||
"sum": 0.0,
|
||||
"sumsq": 0.0
|
||||
},
|
||||
"reward_total_values": [],
|
||||
"reward_total_values_count": 0,
|
||||
"step": null,
|
||||
"total_global_batch_count": 2003,
|
||||
"total_global_generation_count": 856600
|
||||
},
|
||||
"version": "0.1.4"
|
||||
}
|
||||
901
run_meta.json
Normal file
901
run_meta.json
Normal file
@@ -0,0 +1,901 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"config": {
|
||||
"auto_model_config": {
|
||||
"attn_implementation": "flash_attention_2",
|
||||
"use_cache": false
|
||||
},
|
||||
"auto_resume_if_possible": true,
|
||||
"auto_tokenizer_config": {
|
||||
"use_fast": true
|
||||
},
|
||||
"base_model": "Qwen/Qwen3-4B-Instruct-2507",
|
||||
"cache_config": {
|
||||
"cache_dir": null,
|
||||
"force_regenerate": false,
|
||||
"use_cache": true
|
||||
},
|
||||
"datamodule_config": {
|
||||
"add_block_markers": false,
|
||||
"add_line_numbers": false,
|
||||
"base_filter_rule": "",
|
||||
"cache_lock_timeout_seconds": 1800.0,
|
||||
"dataloader_config_overrides": {
|
||||
"train": {
|
||||
"shuffle": true
|
||||
}
|
||||
},
|
||||
"datamodule_class_path": "pyine.organisms.datamodules.shortcuts.ShortcutBiasDataModule",
|
||||
"datamodule_name": null,
|
||||
"dataparser_config_overrides": {
|
||||
"test": {},
|
||||
"train": {
|
||||
"filtering_config": {
|
||||
"max_args_length": 500,
|
||||
"max_code_length": 2500,
|
||||
"max_code_line_count": 250,
|
||||
"max_code_line_length": 250,
|
||||
"max_traces_per_solution": 1
|
||||
},
|
||||
"selection_config": {
|
||||
"code_type_prob_map": {
|
||||
"hinted": 0.05,
|
||||
"obfuscated": 0.05,
|
||||
"obfuscated_hinted": 0.05,
|
||||
"original": 0.75,
|
||||
"stubbed": 0.1
|
||||
},
|
||||
"draw_attempts": 5,
|
||||
"fallback_to_orig": true,
|
||||
"samples_per_family": 1
|
||||
},
|
||||
"transform_config": {
|
||||
"transform_strategy": "never"
|
||||
}
|
||||
},
|
||||
"valid": {
|
||||
"filtering_config": {
|
||||
"max_args_length": 500,
|
||||
"max_code_length": 2500,
|
||||
"max_code_line_count": 250,
|
||||
"max_code_line_length": 250,
|
||||
"max_traces_per_solution": 1
|
||||
},
|
||||
"selection_config": {
|
||||
"code_type_prob_map": {
|
||||
"hinted": 0.0,
|
||||
"obfuscated": 0.0,
|
||||
"obfuscated_hinted": 0.0,
|
||||
"original": 1.0,
|
||||
"stubbed": 0.0
|
||||
},
|
||||
"draw_attempts": 5,
|
||||
"fallback_to_orig": true,
|
||||
"samples_per_family": 1
|
||||
},
|
||||
"transform_config": {
|
||||
"transform_strategy": "never"
|
||||
}
|
||||
},
|
||||
"valid_hinted": {
|
||||
"filtering_config": {
|
||||
"max_args_length": null,
|
||||
"max_code_length": null,
|
||||
"max_code_line_count": null,
|
||||
"max_code_line_length": null,
|
||||
"max_trace_families": null,
|
||||
"max_trace_steps": null,
|
||||
"max_traces_per_family": null,
|
||||
"max_traces_per_problem": null,
|
||||
"max_traces_per_solution": null,
|
||||
"seed": null,
|
||||
"tokenizer_model_id": null,
|
||||
"tokenizer_path": null,
|
||||
"use_token_lengths": false
|
||||
},
|
||||
"selection_config": {
|
||||
"allow_db_lookups": true,
|
||||
"fallback_to_orig": false,
|
||||
"require_hint_type": "helpful"
|
||||
}
|
||||
},
|
||||
"valid_hintless": {
|
||||
"filtering_config": {
|
||||
"max_args_length": null,
|
||||
"max_code_length": null,
|
||||
"max_code_line_count": null,
|
||||
"max_code_line_length": null,
|
||||
"max_trace_families": null,
|
||||
"max_trace_steps": null,
|
||||
"max_traces_per_family": null,
|
||||
"max_traces_per_problem": null,
|
||||
"max_traces_per_solution": null,
|
||||
"seed": null,
|
||||
"tokenizer_model_id": null,
|
||||
"tokenizer_path": null,
|
||||
"use_token_lengths": false
|
||||
},
|
||||
"selection_config": {
|
||||
"fallback_to_orig": false,
|
||||
"skip_code_type_selection": true
|
||||
}
|
||||
},
|
||||
"valid_misleading": {
|
||||
"filtering_config": {
|
||||
"max_args_length": null,
|
||||
"max_code_length": null,
|
||||
"max_code_line_count": null,
|
||||
"max_code_line_length": null,
|
||||
"max_trace_families": null,
|
||||
"max_trace_steps": null,
|
||||
"max_traces_per_family": null,
|
||||
"max_traces_per_problem": null,
|
||||
"max_traces_per_solution": null,
|
||||
"seed": null,
|
||||
"tokenizer_model_id": null,
|
||||
"tokenizer_path": null,
|
||||
"use_token_lengths": false
|
||||
},
|
||||
"selection_config": {
|
||||
"allow_db_lookups": true,
|
||||
"fallback_to_orig": false,
|
||||
"require_hint_type": "misleading",
|
||||
"require_validated_misleading": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"default_dataloader_config": {
|
||||
"base_class_path": "torch.utils.data.dataloader.DataLoader",
|
||||
"class_path": "torch.utils.data.dataloader.DataLoader",
|
||||
"params": {
|
||||
"batch_sampler": null,
|
||||
"batch_size": 1,
|
||||
"collate_fn": null,
|
||||
"drop_last": false,
|
||||
"generator": null,
|
||||
"in_order": true,
|
||||
"multiprocessing_context": null,
|
||||
"num_workers": 0,
|
||||
"persistent_workers": false,
|
||||
"pin_memory": false,
|
||||
"pin_memory_device": "",
|
||||
"prefetch_factor": null,
|
||||
"sampler": null,
|
||||
"shuffle": null,
|
||||
"timeout": 0,
|
||||
"worker_init_fn": null
|
||||
},
|
||||
"params_key": null
|
||||
},
|
||||
"default_dataparser_config": {
|
||||
"base_class_path": "torch.utils.data.dataset.Dataset",
|
||||
"class_path": "pyine.organisms.datamodules.samples.builder.SampleBuilder",
|
||||
"params": {
|
||||
"filtering_config": {
|
||||
"seed": 0
|
||||
},
|
||||
"selection_config": {
|
||||
"allow_db_lookups": true,
|
||||
"code_type_prob_map": {
|
||||
"hinted": 0.0,
|
||||
"obfuscated": 0.0,
|
||||
"obfuscated_hinted": 0.0,
|
||||
"original": 1.0,
|
||||
"stubbed": 0.0
|
||||
},
|
||||
"draw_attempts": 5,
|
||||
"fallback_to_orig": false,
|
||||
"samples_per_family": 1,
|
||||
"seed": 0
|
||||
},
|
||||
"transform_config": {
|
||||
"seed": 0,
|
||||
"transform_strategy": "never"
|
||||
}
|
||||
},
|
||||
"params_key": null
|
||||
},
|
||||
"eval_hint_types": [
|
||||
"helpful",
|
||||
"misleading"
|
||||
],
|
||||
"eval_subset_names": [
|
||||
"valid"
|
||||
],
|
||||
"evaluation_strategy": "counterfactual",
|
||||
"hf_messages_key": "prompt",
|
||||
"instantiate_parsers_at_setup": false,
|
||||
"keep_generated_datasets_in_memory": false,
|
||||
"lmdb_paths": [
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000001of000026.2025-12-10.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000002of000026.2025-12-10.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000003of000026.2025-12-10.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000004of000026.2025-12-11.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000005of000026.2025-12-11.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000006of000026.2025-12-12.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000007of000026.2025-12-12.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000008of000026.2025-12-10.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000009of000026.2025-12-12.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000010of000026.2025-12-11.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000011of000026.2025-12-12.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000012of000026.2025-12-12.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000013of000026.2025-12-12.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000014of000026.2025-12-13.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000015of000026.2025-12-10.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000016of000026.2025-12-10.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000017of000026.2025-12-10.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000018of000026.2025-12-11.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000019of000026.2025-12-11.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000020of000026.2025-12-12.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000021of000026.2025-12-10.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000022of000026.2025-12-10.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000023of000026.2025-12-11.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000024of000026.2025-12-11.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000025of000026.2025-12-11.lmdb",
|
||||
"/scratch/a.palmas/code-interp-benchmark/data/traces/TACO/v1.5/10s10t.000026of000026.2025-12-12.lmdb"
|
||||
],
|
||||
"max_solution_count": null,
|
||||
"message_generator_num_workers": 8,
|
||||
"min_samples_hinted": 0,
|
||||
"min_samples_hintless": 0,
|
||||
"min_samples_misleading": 0,
|
||||
"pregenerated_outputs_lmdb_paths": null,
|
||||
"pregenerated_outputs_only_matched": false,
|
||||
"pregenerated_outputs_phase_prefix": "",
|
||||
"pregenerated_outputs_selection": "latest",
|
||||
"prompt_config": {
|
||||
"context_variables": null,
|
||||
"examples_block_variables": null,
|
||||
"include_examples": false,
|
||||
"partial_vars": {},
|
||||
"prompt_name": "code_execution",
|
||||
"role_variables": null,
|
||||
"target_examples": null,
|
||||
"use_chat_template": true,
|
||||
"version": "rl_tagged_answer"
|
||||
},
|
||||
"require_validated_misleading": true,
|
||||
"split_file_path": "/scratch/a.palmas/code-interp-benchmark/data/splits/TACO-split.bin",
|
||||
"split_seed": 0,
|
||||
"subset_names": [
|
||||
"train",
|
||||
"valid",
|
||||
"test",
|
||||
"valid_hinted",
|
||||
"valid_misleading",
|
||||
"valid_hintless"
|
||||
],
|
||||
"train_subset_names": [
|
||||
"train"
|
||||
],
|
||||
"use_local_dataset_cache": true,
|
||||
"use_tokenized_dataset_cache": true,
|
||||
"valid_subset_names": [
|
||||
"valid_hinted",
|
||||
"valid_hintless",
|
||||
"valid_misleading"
|
||||
]
|
||||
},
|
||||
"evals_config": {
|
||||
"category_extraction_config": {
|
||||
"enabled_fields": [
|
||||
"has_keyword",
|
||||
"code_type",
|
||||
"predict_type"
|
||||
],
|
||||
"tag_prefixes": null
|
||||
},
|
||||
"eval_batch_size": 24,
|
||||
"eval_generation_config": null,
|
||||
"eval_generation_max_new_tokens_override": 1024,
|
||||
"eval_padding_side": "left",
|
||||
"eval_runnable_config": {
|
||||
"async_metrics_compute_rate": 100,
|
||||
"max_in_flight_jobs": 32,
|
||||
"max_workers": null,
|
||||
"parallel": true
|
||||
},
|
||||
"eval_type": "code_exec",
|
||||
"evaluator_kwargs": {
|
||||
"add_idempotency_header": true,
|
||||
"llm_provider_config": {
|
||||
"model_kwargs": {
|
||||
"max_retries": 0,
|
||||
"max_tokens": 1024,
|
||||
"model": "gpt-5-nano",
|
||||
"reasoning": {
|
||||
"effort": "minimal"
|
||||
},
|
||||
"timeout": 15
|
||||
},
|
||||
"provider": "openai",
|
||||
"rate_limiter_config": {
|
||||
"max_bucket_size": 50,
|
||||
"requests_per_second": 50
|
||||
},
|
||||
"with_retry_config": {
|
||||
"retry_if_exception_type": [
|
||||
"openai.APITimeoutError",
|
||||
"openai.APIConnectionError",
|
||||
"openai.RateLimitError",
|
||||
"openai.InternalServerError"
|
||||
],
|
||||
"stop_after_attempt": 10,
|
||||
"wait_exponential_jitter": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"vllm_provider_config": null
|
||||
},
|
||||
"generation_export_config": null,
|
||||
"gpu_stats_logging": {
|
||||
"collect_all_visible_devices": false,
|
||||
"eval_prefix": "eval/gpu/",
|
||||
"gather_eval_metrics": true,
|
||||
"gather_train_metrics": "at_phase_end",
|
||||
"only_main_process": true,
|
||||
"require_nvml": false,
|
||||
"sample_every_n_steps": 1,
|
||||
"train_prefix": "train/gpu/"
|
||||
},
|
||||
"grpo_config": {
|
||||
"_n_gpu": 1,
|
||||
"accelerator_config": {
|
||||
"dispatch_batches": null,
|
||||
"even_batches": true,
|
||||
"gradient_accumulation_kwargs": null,
|
||||
"non_blocking": false,
|
||||
"split_batches": false,
|
||||
"use_configured_state": false,
|
||||
"use_seedable_sampler": true
|
||||
},
|
||||
"adafactor": false,
|
||||
"adam_beta1": 0.9,
|
||||
"adam_beta2": 0.999,
|
||||
"adam_epsilon": 1e-08,
|
||||
"auto_find_batch_size": false,
|
||||
"average_tokens_across_devices": true,
|
||||
"batch_eval_metrics": false,
|
||||
"beta": 0.0,
|
||||
"bf16": true,
|
||||
"bf16_full_eval": false,
|
||||
"cache_implementation": null,
|
||||
"cast_lm_head_to_fp32": false,
|
||||
"chat_template_kwargs": null,
|
||||
"data_seed": null,
|
||||
"dataloader_drop_last": false,
|
||||
"dataloader_num_workers": 4,
|
||||
"dataloader_persistent_workers": false,
|
||||
"dataloader_pin_memory": false,
|
||||
"dataloader_prefetch_factor": null,
|
||||
"ddp_backend": null,
|
||||
"ddp_broadcast_buffers": null,
|
||||
"ddp_bucket_cap_mb": null,
|
||||
"ddp_find_unused_parameters": null,
|
||||
"ddp_timeout": 1800,
|
||||
"debug": [],
|
||||
"deepspeed": null,
|
||||
"delta": null,
|
||||
"disable_dropout": false,
|
||||
"disable_tqdm": false,
|
||||
"do_eval": true,
|
||||
"do_predict": false,
|
||||
"do_train": true,
|
||||
"ds3_gather_for_generation": true,
|
||||
"epsilon": 0.2,
|
||||
"epsilon_high": null,
|
||||
"eval_accumulation_steps": null,
|
||||
"eval_delay": 0.0,
|
||||
"eval_do_concat_batches": true,
|
||||
"eval_on_start": true,
|
||||
"eval_steps": 10,
|
||||
"eval_strategy": "steps",
|
||||
"eval_use_gather_object": false,
|
||||
"fp16": false,
|
||||
"fp16_backend": "auto",
|
||||
"fp16_full_eval": false,
|
||||
"fp16_opt_level": "O1",
|
||||
"fsdp": [],
|
||||
"fsdp_config": {
|
||||
"min_num_params": 0,
|
||||
"xla": false,
|
||||
"xla_fsdp_grad_ckpt": false,
|
||||
"xla_fsdp_v2": false
|
||||
},
|
||||
"fsdp_min_num_params": 0,
|
||||
"fsdp_transformer_layer_cls_to_wrap": null,
|
||||
"full_determinism": false,
|
||||
"generation_batch_size": 960,
|
||||
"generation_kwargs": null,
|
||||
"gradient_accumulation_steps": 6,
|
||||
"gradient_checkpointing": true,
|
||||
"gradient_checkpointing_kwargs": {
|
||||
"use_reentrant": false
|
||||
},
|
||||
"greater_is_better": null,
|
||||
"group_by_length": false,
|
||||
"half_precision_backend": "auto",
|
||||
"hub_always_push": false,
|
||||
"hub_model_id": null,
|
||||
"hub_private_repo": null,
|
||||
"hub_revision": null,
|
||||
"hub_strategy": "every_save",
|
||||
"hub_token": null,
|
||||
"ignore_data_skip": false,
|
||||
"importance_sampling_level": "token",
|
||||
"include_for_metrics": [],
|
||||
"include_inputs_for_metrics": false,
|
||||
"include_num_input_tokens_seen": "no",
|
||||
"include_tokens_per_second": false,
|
||||
"jit_mode_eval": false,
|
||||
"label_names": null,
|
||||
"label_smoothing_factor": 0.0,
|
||||
"learning_rate": 5e-06,
|
||||
"length_column_name": "length",
|
||||
"liger_kernel_config": null,
|
||||
"load_best_model_at_end": false,
|
||||
"local_rank": 0,
|
||||
"log_completions": false,
|
||||
"log_level": "passive",
|
||||
"log_level_replica": "warning",
|
||||
"log_on_each_node": true,
|
||||
"log_unique_prompts": false,
|
||||
"logging_dir": "/scratch/a.palmas/code-interp-benchmark/logs/runs/rl_trainer/original/RL_HT_49/original/RL_HT_49/logs",
|
||||
"logging_first_step": false,
|
||||
"logging_nan_inf_filter": true,
|
||||
"logging_steps": 1.0,
|
||||
"logging_strategy": "steps",
|
||||
"loss_type": "dapo",
|
||||
"lr_scheduler_kwargs": null,
|
||||
"lr_scheduler_type": "constant_with_warmup",
|
||||
"mask_truncated_completions": false,
|
||||
"max_completion_length": 10000,
|
||||
"max_grad_norm": 1.0,
|
||||
"max_prompt_length": 3000,
|
||||
"max_steps": -1,
|
||||
"max_tool_calling_iterations": null,
|
||||
"metric_for_best_model": null,
|
||||
"min_p": null,
|
||||
"model_init_kwargs": null,
|
||||
"mp_parameters": "",
|
||||
"multi_objective_aggregation": "sum_then_normalize",
|
||||
"neftune_noise_alpha": null,
|
||||
"no_cuda": false,
|
||||
"num_completions_to_print": null,
|
||||
"num_generations": 32,
|
||||
"num_generations_eval": 1,
|
||||
"num_iterations": 1,
|
||||
"num_train_epochs": 1.0,
|
||||
"off_policy_mask_threshold": null,
|
||||
"optim": "adamw_torch_fused",
|
||||
"optim_args": null,
|
||||
"optim_target_modules": null,
|
||||
"output_dir": "/scratch/a.palmas/code-interp-benchmark/logs/runs/rl_trainer/original/RL_HT_49/original/RL_HT_49",
|
||||
"overwrite_output_dir": false,
|
||||
"parallelism_config": null,
|
||||
"past_index": -1,
|
||||
"per_device_eval_batch_size": 5,
|
||||
"per_device_train_batch_size": 4,
|
||||
"per_gpu_eval_batch_size": null,
|
||||
"per_gpu_train_batch_size": null,
|
||||
"prediction_loss_only": false,
|
||||
"project": "huggingface",
|
||||
"push_to_hub": false,
|
||||
"push_to_hub_model_id": null,
|
||||
"push_to_hub_organization": null,
|
||||
"push_to_hub_token": null,
|
||||
"ray_scope": "last",
|
||||
"ref_model_mixup_alpha": 0.6,
|
||||
"ref_model_sync_steps": 512,
|
||||
"remove_unused_columns": false,
|
||||
"repetition_penalty": 1.0,
|
||||
"report_to": [
|
||||
"tensorboard",
|
||||
"wandb"
|
||||
],
|
||||
"restore_callback_states_from_checkpoint": false,
|
||||
"resume_from_checkpoint": null,
|
||||
"reward_weights": null,
|
||||
"run_name": "original/RL_HT_49-original/RL_HT_49",
|
||||
"sapo_temperature_neg": 1.05,
|
||||
"sapo_temperature_pos": 1.0,
|
||||
"save_on_each_node": false,
|
||||
"save_only_model": false,
|
||||
"save_safetensors": true,
|
||||
"save_steps": 50,
|
||||
"save_strategy": "steps",
|
||||
"save_total_limit": 500,
|
||||
"scale_rewards": "none",
|
||||
"seed": 0,
|
||||
"shuffle_dataset": true,
|
||||
"skip_memory_metrics": true,
|
||||
"steps_per_generation": 6,
|
||||
"sync_ref_model": false,
|
||||
"temperature": 0.7,
|
||||
"tf32": true,
|
||||
"top_entropy_quantile": 1.0,
|
||||
"top_k": 0,
|
||||
"top_p": 0.9,
|
||||
"torch_compile": false,
|
||||
"torch_compile_backend": null,
|
||||
"torch_compile_mode": null,
|
||||
"torch_empty_cache_steps": null,
|
||||
"torchdynamo": null,
|
||||
"tpu_metrics_debug": false,
|
||||
"tpu_num_cores": null,
|
||||
"trackio_space_id": "trackio",
|
||||
"use_bias_correction_kl": false,
|
||||
"use_cpu": false,
|
||||
"use_legacy_prediction_loop": false,
|
||||
"use_liger_kernel": false,
|
||||
"use_liger_loss": null,
|
||||
"use_mps_device": false,
|
||||
"use_transformers_paged": false,
|
||||
"use_vllm": true,
|
||||
"vllm_enable_sleep_mode": false,
|
||||
"vllm_gpu_memory_utilization": 0.15,
|
||||
"vllm_group_port": 51216,
|
||||
"vllm_guided_decoding_regex": null,
|
||||
"vllm_importance_sampling_cap": 3.0,
|
||||
"vllm_importance_sampling_correction": true,
|
||||
"vllm_importance_sampling_mode": "sequence_mask",
|
||||
"vllm_max_model_length": 13000,
|
||||
"vllm_mode": "colocate",
|
||||
"vllm_model_impl": "vllm",
|
||||
"vllm_server_base_url": null,
|
||||
"vllm_server_host": "0.0.0.0",
|
||||
"vllm_server_port": 8050,
|
||||
"vllm_server_timeout": 240.0,
|
||||
"vllm_structured_outputs_regex": null,
|
||||
"vllm_tensor_parallel_size": 1,
|
||||
"warmup_ratio": 0.0,
|
||||
"warmup_steps": 0,
|
||||
"weight_decay": 0.0
|
||||
},
|
||||
"lora_config": null,
|
||||
"quantization_mode": "none",
|
||||
"resume_checkpoint_name": null,
|
||||
"resume_from_run_dir": null,
|
||||
"resume_incompatibility_policy": "warn",
|
||||
"resume_wandb_behavior": "allow",
|
||||
"reward_manager_config": {
|
||||
"aggregation": {
|
||||
"clip_term_max": null,
|
||||
"clip_term_min": null,
|
||||
"clip_total_max": null,
|
||||
"clip_total_min": 0.0,
|
||||
"return_raw_breakdown": false,
|
||||
"strategy": "weighted_sum"
|
||||
},
|
||||
"difficulty": {
|
||||
"bin_edges": null,
|
||||
"bin_max_score": null,
|
||||
"code_override_mode": "skip",
|
||||
"enabled": true,
|
||||
"normalization_mode": "log",
|
||||
"num_difficulty_bins": 10,
|
||||
"primary_source": "trace_step_count",
|
||||
"score_clip_max": null,
|
||||
"secondary_sources": [
|
||||
"halstead_effort"
|
||||
],
|
||||
"source_ranges": null,
|
||||
"track_bin_quantiles": "disabled",
|
||||
"track_per_term_rewards": "disabled",
|
||||
"track_percentiles": "disabled"
|
||||
},
|
||||
"logging": {
|
||||
"barrier_before_finalize": true,
|
||||
"category_extraction_config": {
|
||||
"enabled_fields": [
|
||||
"tags",
|
||||
"code_type"
|
||||
],
|
||||
"tag_prefixes": [
|
||||
"difficulty",
|
||||
"parser",
|
||||
"total_steps"
|
||||
]
|
||||
},
|
||||
"enabled": true,
|
||||
"expect_all_rank_logging": false,
|
||||
"gather_distributed_summaries": true,
|
||||
"histogram_max_samples": 100000,
|
||||
"histogram_num_bins": 50,
|
||||
"log_batch_stats": true,
|
||||
"log_every_n_generations": 16,
|
||||
"log_metrics": true,
|
||||
"log_tables": true,
|
||||
"log_terms": true,
|
||||
"log_total": true,
|
||||
"main_process_only": true,
|
||||
"step_metric_key": "train/global_step",
|
||||
"table_max_rows": 100
|
||||
},
|
||||
"parsing": {
|
||||
"capture_diagnostics": true,
|
||||
"enabled_fields": "both",
|
||||
"fallback_policy": "none",
|
||||
"final_tag": "final",
|
||||
"mode": "tags",
|
||||
"multi_tag_policy": "last",
|
||||
"openai_tokenizer_model": null,
|
||||
"reasoning_from_entire_output_when_no_final_answer": true,
|
||||
"reasoning_from_outside_final": true,
|
||||
"reasoning_tag": "reasoning",
|
||||
"strict": false,
|
||||
"track_token_lengths": true
|
||||
},
|
||||
"terms": [
|
||||
{
|
||||
"enabled": true,
|
||||
"name": "soft_match",
|
||||
"params": {
|
||||
"reward_if_match": 1.0,
|
||||
"reward_if_no_match": 0.0
|
||||
},
|
||||
"require_parsed": true,
|
||||
"type": "soft_match",
|
||||
"weight": 1.0
|
||||
}
|
||||
],
|
||||
"verbosity_scaling": {
|
||||
"decay_rate": 0.001,
|
||||
"decay_type": "linear",
|
||||
"emit_metrics": true,
|
||||
"enabled": true,
|
||||
"end_tokens": 10000,
|
||||
"length_source": "parsed_reasoning",
|
||||
"max_factor": 1.0,
|
||||
"min_factor": 0.1,
|
||||
"mode": "absolute",
|
||||
"skip_negative_rewards": true,
|
||||
"temperature": 1.0,
|
||||
"threshold_tokens": 0
|
||||
}
|
||||
},
|
||||
"throughput_logging": {
|
||||
"eval_prefix": "eval/throughput/",
|
||||
"log_eval_throughput": true,
|
||||
"log_train_throughput": true,
|
||||
"only_main_process": true,
|
||||
"train_prefix": "train/throughput/"
|
||||
},
|
||||
"tokenizer_override_padding_to_right_side": true,
|
||||
"tokenizer_override_truncation_to_left_side": true,
|
||||
"tokenizer_set_padding_to_eos_if_needed": true,
|
||||
"use_wandb_logging": true,
|
||||
"wandb_init_on_all_ranks": false
|
||||
},
|
||||
"config_hash": "f43e390d722a6d1f5df4061495bce911e1ee04d9",
|
||||
"epoch": 0.40053404539385845,
|
||||
"generated_at": 1772305776.9167938,
|
||||
"git_revision": "git-revision-unknown",
|
||||
"global_step": 600,
|
||||
"runtime": {
|
||||
"app_name": "rl_trainer",
|
||||
"dry_run": false,
|
||||
"exp_name": "original/RL_HT_49",
|
||||
"hydra_runtime_config": {
|
||||
"callbacks": {
|
||||
"non_primary_rank_cleanup": {
|
||||
"_target_": "pyine.configs.callbacks.NonPrimaryRankCleanupCallback"
|
||||
}
|
||||
},
|
||||
"env": {},
|
||||
"help": {
|
||||
"app_name": "rl_trainer",
|
||||
"footer": "Powered by Hydra (https://hydra.cc)\nUse --hydra-help to view Hydra specific help\n",
|
||||
"header": "rl_trainer is powered by Hydra.\n",
|
||||
"template": "rl_trainer is powered by Hydra.\n\n== Configuration groups ==\nCompose your configuration from those groups (group=option)\n\n$APP_CONFIG_GROUPS\n\n== Config ==\nOverride anything in the config (foo.bar=value)\n\n$CONFIG\n\nPowered by Hydra (https://hydra.cc)\nUse --hydra-help to view Hydra specific help\n\n"
|
||||
},
|
||||
"hydra_help": {
|
||||
"hydra_help": "???",
|
||||
"template": "Hydra (1.3.2)\nSee https://hydra.cc for more info.\n\n== Flags ==\n$FLAGS_HELP\n\n== Configuration groups ==\nCompose your configuration from those groups (For example, append hydra/job_logging=disabled to command line)\n\n$HYDRA_CONFIG_GROUPS\n\nUse '--cfg hydra' to Show the Hydra config.\n"
|
||||
},
|
||||
"hydra_logging": {
|
||||
"disable_existing_loggers": false,
|
||||
"formatters": {
|
||||
"colorlog": {
|
||||
"()": "colorlog.ColoredFormatter",
|
||||
"format": "[%(cyan)s%(asctime)s%(reset)s][%(purple)sHYDRA%(reset)s] %(message)s"
|
||||
}
|
||||
},
|
||||
"handlers": {
|
||||
"console": {
|
||||
"class": "logging.StreamHandler",
|
||||
"formatter": "colorlog",
|
||||
"stream": "ext://sys.stdout"
|
||||
}
|
||||
},
|
||||
"root": {
|
||||
"handlers": [
|
||||
"console"
|
||||
],
|
||||
"level": "INFO"
|
||||
},
|
||||
"version": 1
|
||||
},
|
||||
"job": {
|
||||
"chdir": null,
|
||||
"config": {
|
||||
"override_dirname": {
|
||||
"exclude_keys": [],
|
||||
"item_sep": ",",
|
||||
"kv_sep": "="
|
||||
}
|
||||
},
|
||||
"config_name": "entrypoint",
|
||||
"env_copy": [],
|
||||
"env_set": {},
|
||||
"id": "???",
|
||||
"name": "rl_trainer",
|
||||
"num": "???",
|
||||
"override_dirname": "+experiment=original/v0_rl.yaml"
|
||||
},
|
||||
"job_logging": {
|
||||
"disable_existing_loggers": false,
|
||||
"formatters": {
|
||||
"colorlog": {
|
||||
"()": "colorlog.ColoredFormatter",
|
||||
"format": "[%(cyan)s%(asctime)s%(reset)s][%(blue)s%(name)s%(reset)s][%(log_color)s%(levelname)s%(reset)s] - %(message)s",
|
||||
"log_colors": {
|
||||
"CRITICAL": "red",
|
||||
"DEBUG": "purple",
|
||||
"ERROR": "red",
|
||||
"INFO": "green",
|
||||
"WARNING": "yellow"
|
||||
}
|
||||
},
|
||||
"simple": {
|
||||
"format": "[%(asctime)s][%(name)s][%(levelname)s] - %(message)s"
|
||||
}
|
||||
},
|
||||
"handlers": {
|
||||
"console": {
|
||||
"class": "logging.StreamHandler",
|
||||
"formatter": "colorlog",
|
||||
"stream": "ext://sys.stdout"
|
||||
},
|
||||
"file": {
|
||||
"class": "logging.FileHandler",
|
||||
"filename": "/scratch/a.palmas/code-interp-benchmark/logs/runs/rl_trainer/original/RL_HT_49/original/RL_HT_49/output.log",
|
||||
"formatter": "simple"
|
||||
}
|
||||
},
|
||||
"loggers": {
|
||||
"pyine": {
|
||||
"level": "INFO"
|
||||
}
|
||||
},
|
||||
"root": {
|
||||
"handlers": [
|
||||
"console",
|
||||
"file"
|
||||
],
|
||||
"level": "INFO"
|
||||
},
|
||||
"version": 1
|
||||
},
|
||||
"launcher": {
|
||||
"_target_": "hydra._internal.core_plugins.basic_launcher.BasicLauncher"
|
||||
},
|
||||
"mode": 1,
|
||||
"output_subdir": ".hydra",
|
||||
"overrides": {
|
||||
"hydra": [
|
||||
"hydra.mode=RUN"
|
||||
],
|
||||
"task": [
|
||||
"+experiment=original/v0_rl.yaml"
|
||||
]
|
||||
},
|
||||
"run": {
|
||||
"dir": "/scratch/a.palmas/code-interp-benchmark/logs/runs/rl_trainer/original/RL_HT_49/original/RL_HT_49"
|
||||
},
|
||||
"runtime": {
|
||||
"choices": {
|
||||
"config": "base",
|
||||
"config/datamodule_config": "shortcuts_TACO_10s10t_v1_full",
|
||||
"config/evals_config": "base",
|
||||
"config/evals_config/evaluator_kwargs/llm_provider_config": "openai_gpt5nano_scoring",
|
||||
"config/grpo_config": "train_default",
|
||||
"experiment": "original/v0_rl.yaml",
|
||||
"hydra/callbacks": null,
|
||||
"hydra/env": "default",
|
||||
"hydra/help": "default",
|
||||
"hydra/hydra_help": "default",
|
||||
"hydra/hydra_logging": "colorlog",
|
||||
"hydra/job_logging": "colorlog",
|
||||
"hydra/launcher": "basic",
|
||||
"hydra/output": "default",
|
||||
"hydra/sweeper": "basic",
|
||||
"runtime": "default"
|
||||
},
|
||||
"config_sources": [
|
||||
{
|
||||
"path": "hydra.conf",
|
||||
"provider": "hydra",
|
||||
"schema": "pkg"
|
||||
},
|
||||
{
|
||||
"path": "hydra_zen.wrapper",
|
||||
"provider": "main",
|
||||
"schema": "pkg"
|
||||
},
|
||||
{
|
||||
"path": "hydra_plugins.hydra_colorlog.conf",
|
||||
"provider": "hydra-colorlog",
|
||||
"schema": "pkg"
|
||||
},
|
||||
{
|
||||
"path": "/scratch/a.palmas/code-interp-benchmark/pyine/configs",
|
||||
"provider": "pyine_cwd",
|
||||
"schema": "file"
|
||||
},
|
||||
{
|
||||
"path": "/scratch/a.palmas/code-interp-benchmark/pyine/configs",
|
||||
"provider": "pyine_repo",
|
||||
"schema": "file"
|
||||
},
|
||||
{
|
||||
"path": "",
|
||||
"provider": "schema",
|
||||
"schema": "structured"
|
||||
}
|
||||
],
|
||||
"cwd": "/scratch/a.palmas/code-interp-benchmark",
|
||||
"output_dir": "/scratch/a.palmas/code-interp-benchmark/logs/runs/rl_trainer/original/RL_HT_49/original/RL_HT_49",
|
||||
"version": "1.3.2",
|
||||
"version_base": "1.3"
|
||||
},
|
||||
"searchpath": [],
|
||||
"sweep": {
|
||||
"dir": "/scratch/a.palmas/code-interp-benchmark/logs/sweeps/rl_trainer/original/RL_HT_49/original/RL_HT_49",
|
||||
"subdir": "default"
|
||||
},
|
||||
"sweeper": {
|
||||
"_target_": "hydra._internal.core_plugins.basic_sweeper.BasicSweeper",
|
||||
"max_batch_size": null,
|
||||
"params": null
|
||||
},
|
||||
"verbose": false
|
||||
},
|
||||
"metadata": {
|
||||
"created_by": "a.palmas",
|
||||
"data_root": "/scratch/a.palmas/code-interp-benchmark/data",
|
||||
"dotenv_path": "/scratch/a.palmas/code-interp-benchmark/.env",
|
||||
"framework_version": "0.1.4",
|
||||
"git_repo_clean": "True",
|
||||
"git_revision_hash": "f757ce0a0138eb0839c6aee27a1828f6aa4cb294",
|
||||
"local_timestamp": "20260225-105907",
|
||||
"logs_root": "/scratch/a.palmas/code-interp-benchmark/logs",
|
||||
"platform": "uname_result(system='Linux', node='gpu04', release='6.8.0-100-generic', version='#100-Ubuntu SMP PREEMPT_DYNAMIC Tue Jan 13 16:40:06 UTC 2026', machine='x86_64')",
|
||||
"project_root": "/scratch/a.palmas/code-interp-benchmark",
|
||||
"python_version": "3.12.3",
|
||||
"runtime_hash": "199a5a0a564dd9b6b8e116e1335ece9762a156ac",
|
||||
"sys_argv": "['pyine/apps/trainers/hf_trainer.py', '+experiment=original/v0_rl.yaml']",
|
||||
"sys_executable": "/scratch/a.palmas/code-interp-benchmark/.venv/bin/python3",
|
||||
"time_since_epoch": "1772035147.9544945",
|
||||
"tmp_dir": "/tmp/pyine/pyine-a.palmas",
|
||||
"work_dir": "/scratch/a.palmas/code-interp-benchmark"
|
||||
},
|
||||
"notes": null,
|
||||
"output_dir": "/scratch/a.palmas/code-interp-benchmark/logs/runs/rl_trainer/original/RL_HT_49/original/RL_HT_49",
|
||||
"run_group": "original/RL_HT_49",
|
||||
"run_name": "original/RL_HT_49",
|
||||
"seed": 0,
|
||||
"seed_workers": false,
|
||||
"tags": [
|
||||
"model:Qwen/Qwen3-4B-Instruct-2507",
|
||||
"rl-training"
|
||||
],
|
||||
"wandb_run_dir": "/scratch/a.palmas/code-interp-benchmark/logs/runs/rl_trainer/original/RL_HT_49/original/RL_HT_49/wandb/run-20260225_105919-4567hspa/files",
|
||||
"wandb_run_entity": "lawzero-default",
|
||||
"wandb_run_id": "4567hspa",
|
||||
"wandb_run_project": "pyine",
|
||||
"wandb_run_url": "https://wandb.ai/lawzero-default/pyine/runs/4567hspa"
|
||||
},
|
||||
"shutdown_requested": false,
|
||||
"training_loss": null
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_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|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
241
tokenizer_config.json
Normal file
241
tokenizer_config.json
Normal file
@@ -0,0 +1,241 @@
|
||||
{
|
||||
"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|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 1010000,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "left",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"truncation_side": "left",
|
||||
"unk_token": null
|
||||
}
|
||||
21186
trainer_state.json
Normal file
21186
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
760
zero_to_fp32.py
Normal file
760
zero_to_fp32.py
Normal file
@@ -0,0 +1,760 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
# Copyright (c) Microsoft Corporation.
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
# DeepSpeed Team
|
||||
|
||||
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
||||
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
||||
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
||||
# application.
|
||||
#
|
||||
# example:
|
||||
# python zero_to_fp32.py . output_dir/
|
||||
# or
|
||||
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
||||
|
||||
import argparse
|
||||
import torch
|
||||
import glob
|
||||
import math
|
||||
import os
|
||||
import re
|
||||
import gc
|
||||
import json
|
||||
import numpy as np
|
||||
from tqdm import tqdm
|
||||
from collections import OrderedDict
|
||||
from dataclasses import dataclass
|
||||
|
||||
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
||||
# DeepSpeed data structures it has to be available in the current python environment.
|
||||
from deepspeed.utils import logger
|
||||
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
||||
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
||||
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
||||
|
||||
|
||||
@dataclass
|
||||
class zero_model_state:
|
||||
buffers: dict()
|
||||
param_shapes: dict()
|
||||
shared_params: list
|
||||
ds_version: int
|
||||
frozen_param_shapes: dict()
|
||||
frozen_param_fragments: dict()
|
||||
|
||||
|
||||
debug = 0
|
||||
|
||||
# load to cpu
|
||||
device = torch.device('cpu')
|
||||
|
||||
|
||||
def atoi(text):
|
||||
return int(text) if text.isdigit() else text
|
||||
|
||||
|
||||
def natural_keys(text):
|
||||
'''
|
||||
alist.sort(key=natural_keys) sorts in human order
|
||||
http://nedbatchelder.com/blog/200712/human_sorting.html
|
||||
(See Toothy's implementation in the comments)
|
||||
'''
|
||||
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
||||
|
||||
|
||||
def get_model_state_file(checkpoint_dir, zero_stage):
|
||||
if not os.path.isdir(checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
||||
|
||||
# there should be only one file
|
||||
if zero_stage <= 2:
|
||||
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
||||
elif zero_stage == 3:
|
||||
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
||||
|
||||
if not os.path.exists(file):
|
||||
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
||||
|
||||
return file
|
||||
|
||||
|
||||
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
||||
# XXX: need to test that this simple glob rule works for multi-node setup too
|
||||
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
||||
|
||||
if len(ckpt_files) == 0:
|
||||
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
||||
|
||||
return ckpt_files
|
||||
|
||||
|
||||
def get_optim_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
||||
|
||||
|
||||
def get_model_state_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
||||
|
||||
|
||||
def parse_model_states(files):
|
||||
zero_model_states = []
|
||||
for file in files:
|
||||
state_dict = torch.load(file, map_location=device, weights_only=False)
|
||||
|
||||
if BUFFER_NAMES not in state_dict:
|
||||
raise ValueError(f"{file} is not a model state checkpoint")
|
||||
buffer_names = state_dict[BUFFER_NAMES]
|
||||
if debug:
|
||||
print("Found buffers:", buffer_names)
|
||||
|
||||
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
||||
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
||||
param_shapes = state_dict[PARAM_SHAPES]
|
||||
|
||||
# collect parameters that are included in param_shapes
|
||||
param_names = []
|
||||
for s in param_shapes:
|
||||
for name in s.keys():
|
||||
param_names.append(name)
|
||||
|
||||
# update with frozen parameters
|
||||
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
||||
if frozen_param_shapes is not None:
|
||||
if debug:
|
||||
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
||||
param_names += list(frozen_param_shapes.keys())
|
||||
|
||||
# handle shared params
|
||||
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
||||
|
||||
ds_version = state_dict.get(DS_VERSION, None)
|
||||
|
||||
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
||||
|
||||
z_model_state = zero_model_state(buffers=buffers,
|
||||
param_shapes=param_shapes,
|
||||
shared_params=shared_params,
|
||||
ds_version=ds_version,
|
||||
frozen_param_shapes=frozen_param_shapes,
|
||||
frozen_param_fragments=frozen_param_fragments)
|
||||
zero_model_states.append(z_model_state)
|
||||
|
||||
return zero_model_states
|
||||
|
||||
|
||||
def parse_optim_states(files, ds_checkpoint_dir):
|
||||
total_files = len(files)
|
||||
state_dicts = []
|
||||
for f in tqdm(files, desc='Loading checkpoint shards'):
|
||||
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
||||
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
||||
# and also handle the case where it was already removed by another helper script
|
||||
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
||||
state_dicts.append(state_dict)
|
||||
|
||||
if ZERO_STAGE not in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
||||
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
||||
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
||||
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
||||
|
||||
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
||||
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
||||
# use the max of the partition_count to get the dp world_size.
|
||||
|
||||
if type(world_size) is list:
|
||||
world_size = max(world_size)
|
||||
|
||||
if world_size != total_files:
|
||||
raise ValueError(
|
||||
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
||||
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
||||
)
|
||||
|
||||
# the groups are named differently in each stage
|
||||
if zero_stage <= 2:
|
||||
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
||||
elif zero_stage == 3:
|
||||
fp32_groups_key = FP32_FLAT_GROUPS
|
||||
else:
|
||||
raise ValueError(f"unknown zero stage {zero_stage}")
|
||||
|
||||
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
||||
return zero_stage, world_size, fp32_flat_groups
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
||||
"""
|
||||
Returns fp32 state_dict reconstructed from ds checkpoint
|
||||
|
||||
Args:
|
||||
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
||||
|
||||
"""
|
||||
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
||||
|
||||
optim_files = get_optim_files(ds_checkpoint_dir)
|
||||
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
||||
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
||||
|
||||
model_files = get_model_state_files(ds_checkpoint_dir)
|
||||
|
||||
zero_model_states = parse_model_states(model_files)
|
||||
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
||||
|
||||
if zero_stage <= 2:
|
||||
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
elif zero_stage == 3:
|
||||
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
|
||||
|
||||
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
||||
|
||||
if debug:
|
||||
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
state_dict[name] = frozen_param_fragments[name]
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _has_callable(obj, fn):
|
||||
attr = getattr(obj, fn, None)
|
||||
return callable(attr)
|
||||
|
||||
|
||||
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
|
||||
# Reconstruction protocol:
|
||||
#
|
||||
# XXX: document this
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
for j in range(len(fp32_flat_groups[0])):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
||||
|
||||
# XXX: memory usage doubles here (zero2)
|
||||
num_param_groups = len(fp32_flat_groups[0])
|
||||
merged_single_partition_of_fp32_groups = []
|
||||
for i in range(num_param_groups):
|
||||
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
||||
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
||||
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
||||
avail_numel = sum(
|
||||
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
||||
|
||||
if debug:
|
||||
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
||||
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
print(f"Have {avail_numel} numels to process.")
|
||||
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
||||
offset = 0
|
||||
avail_numel = full_single_fp32_vector.numel()
|
||||
for name, shape in shapes.items():
|
||||
|
||||
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
||||
offset += unpartitioned_numel
|
||||
|
||||
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
||||
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
||||
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
||||
# live optimizer object, so we are checking that the numbers are within the right range
|
||||
align_to = 2 * world_size
|
||||
|
||||
def zero2_align(x):
|
||||
return align_to * math.ceil(x / align_to)
|
||||
|
||||
if debug:
|
||||
print(f"original offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
offset = zero2_align(offset)
|
||||
avail_numel = zero2_align(avail_numel)
|
||||
|
||||
if debug:
|
||||
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
||||
|
||||
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
||||
remainder = unpartitioned_numel % world_size
|
||||
padding_numel = (world_size - remainder) if remainder else 0
|
||||
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
||||
return partitioned_numel, padding_numel
|
||||
|
||||
|
||||
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
||||
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
||||
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
||||
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
class GatheredTensor:
|
||||
"""
|
||||
A pseudo tensor that collects partitioned weights.
|
||||
It is more memory efficient when there are multiple groups.
|
||||
"""
|
||||
|
||||
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
||||
self.flat_groups = flat_groups
|
||||
self.flat_groups_offset = flat_groups_offset
|
||||
self.offset = offset
|
||||
self.partitioned_numel = partitioned_numel
|
||||
self.shape = shape
|
||||
self.dtype = self.flat_groups[0][0].dtype
|
||||
|
||||
def contiguous(self):
|
||||
"""
|
||||
Merge partitioned weights from flat_groups into a single tensor.
|
||||
"""
|
||||
end_idx = self.offset + self.partitioned_numel
|
||||
world_size = len(self.flat_groups)
|
||||
pad_flat_param_chunks = []
|
||||
|
||||
for rank_i in range(world_size):
|
||||
# for each rank, we need to collect weights from related group/groups
|
||||
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
||||
start_group_id = None
|
||||
end_group_id = None
|
||||
for group_id in range(len(self.flat_groups_offset)):
|
||||
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
||||
start_group_id = group_id
|
||||
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
||||
end_group_id = group_id
|
||||
break
|
||||
# collect weights from related group/groups
|
||||
for group_id in range(start_group_id, end_group_id + 1):
|
||||
flat_tensor = flat_groups_at_rank_i[group_id]
|
||||
start_offset = self.offset - self.flat_groups_offset[group_id]
|
||||
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
||||
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
||||
|
||||
# collect weights from all ranks
|
||||
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
||||
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
||||
return param
|
||||
|
||||
|
||||
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
||||
|
||||
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
||||
# param, re-consolidating each param, while dealing with padding if any
|
||||
|
||||
# merge list of dicts, preserving order
|
||||
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
||||
|
||||
wanted_params = len(param_shapes)
|
||||
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
avail_numel = fp32_flat_groups[0].numel() * world_size
|
||||
print(f"Trainable params: Have {avail_numel} numels to process.")
|
||||
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
offset = 0
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
||||
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
# memory efficient tensor
|
||||
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
||||
state_dict[name] = tensor
|
||||
offset += partitioned_numel
|
||||
|
||||
offset *= world_size
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
||||
|
||||
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
||||
"""
|
||||
Convert state_dict of GatheredTensor to torch tensor
|
||||
"""
|
||||
torch_state_dict = {}
|
||||
converted_tensors = {}
|
||||
for name, tensor in state_dict.items():
|
||||
tensor_id = id(tensor)
|
||||
if tensor_id in converted_tensors: # shared tensors
|
||||
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
||||
torch_state_dict[name] = shared_tensor
|
||||
else:
|
||||
converted_tensors[tensor_id] = name
|
||||
if return_empty_tensor:
|
||||
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
||||
else:
|
||||
torch_state_dict[name] = tensor.contiguous()
|
||||
return torch_state_dict
|
||||
|
||||
|
||||
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False,
|
||||
lazy_mode=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
||||
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
||||
via a model hub.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
||||
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
||||
|
||||
Returns:
|
||||
- pytorch ``state_dict``
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
# do the training and checkpoint saving
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
||||
model = model.cpu() # move to cpu
|
||||
model.load_state_dict(state_dict)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
||||
application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
||||
|
||||
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
||||
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
||||
the checkpoint. Or you can load state_dict in lazy mode ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
||||
for name, lazy_tensor in state_dict.item():
|
||||
tensor = lazy_tensor.contiguous() # to cpu
|
||||
print(name, tensor)
|
||||
# del tensor to release memory if it no longer in use
|
||||
"""
|
||||
if tag is None:
|
||||
latest_path = os.path.join(checkpoint_dir, 'latest')
|
||||
if os.path.isfile(latest_path):
|
||||
with open(latest_path, 'r') as fd:
|
||||
tag = fd.read().strip()
|
||||
else:
|
||||
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
||||
|
||||
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
||||
|
||||
if not os.path.isdir(ds_checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
||||
|
||||
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
||||
if lazy_mode:
|
||||
return state_dict
|
||||
else:
|
||||
return to_torch_tensor(state_dict)
|
||||
|
||||
|
||||
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
||||
output_dir,
|
||||
max_shard_size="5GB",
|
||||
safe_serialization=False,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
||||
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
||||
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
||||
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
"""
|
||||
|
||||
# Dependency pre-check
|
||||
if safe_serialization:
|
||||
try:
|
||||
from safetensors.torch import save_file
|
||||
except ImportError:
|
||||
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
||||
raise
|
||||
if max_shard_size is not None:
|
||||
try:
|
||||
from huggingface_hub import split_torch_state_dict_into_shards
|
||||
except ImportError:
|
||||
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
||||
raise
|
||||
|
||||
# Convert zero checkpoint to state_dict
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
||||
tag,
|
||||
exclude_frozen_parameters,
|
||||
lazy_mode=True)
|
||||
|
||||
# Shard the model if it is too big.
|
||||
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
||||
if max_shard_size is not None:
|
||||
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
||||
# an memory-efficient approach for sharding
|
||||
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
||||
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
||||
filename_pattern=filename_pattern,
|
||||
max_shard_size=max_shard_size)
|
||||
else:
|
||||
from collections import namedtuple
|
||||
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
||||
state_dict_split = StateDictSplit(is_sharded=False,
|
||||
filename_to_tensors={weights_name: list(state_dict.keys())})
|
||||
|
||||
# Save the model by shard
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
||||
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
||||
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
||||
shard_state_dict = to_torch_tensor(shard_state_dict)
|
||||
output_path = os.path.join(output_dir, shard_file)
|
||||
if safe_serialization:
|
||||
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
||||
else:
|
||||
torch.save(shard_state_dict, output_path)
|
||||
# release the memory of current shard
|
||||
for tensor_name in list(shard_state_dict.keys()):
|
||||
del state_dict[tensor_name]
|
||||
del shard_state_dict[tensor_name]
|
||||
del shard_state_dict
|
||||
gc.collect()
|
||||
|
||||
# Save index if sharded
|
||||
if state_dict_split.is_sharded:
|
||||
index = {
|
||||
"metadata": state_dict_split.metadata,
|
||||
"weight_map": state_dict_split.tensor_to_filename,
|
||||
}
|
||||
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
||||
save_index_file = os.path.join(output_dir, save_index_file)
|
||||
with open(save_index_file, "w", encoding="utf-8") as f:
|
||||
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
||||
f.write(content)
|
||||
|
||||
|
||||
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
||||
"""
|
||||
1. Put the provided model to cpu
|
||||
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
||||
3. Load it into the provided model
|
||||
|
||||
Args:
|
||||
- ``model``: the model object to update
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
|
||||
Returns:
|
||||
- ``model`: modified model
|
||||
|
||||
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
||||
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
||||
conveniently placed for you in the checkpoint folder.
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
||||
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
||||
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
"""
|
||||
logger.info("Extracting fp32 weights")
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
||||
|
||||
logger.info("Overwriting model with fp32 weights")
|
||||
model = model.cpu()
|
||||
model.load_state_dict(state_dict, strict=False)
|
||||
|
||||
return model
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("checkpoint_dir",
|
||||
type=str,
|
||||
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
||||
parser.add_argument("output_dir",
|
||||
type=str,
|
||||
help="directory to the pytorch fp32 state_dict output files"
|
||||
"(e.g. path/checkpoint-12-output/)")
|
||||
parser.add_argument(
|
||||
"--max_shard_size",
|
||||
type=str,
|
||||
default="5GB",
|
||||
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
||||
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
||||
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
||||
"without CPU OOM issues.")
|
||||
parser.add_argument(
|
||||
"--safe_serialization",
|
||||
default=False,
|
||||
action='store_true',
|
||||
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
||||
parser.add_argument("-t",
|
||||
"--tag",
|
||||
type=str,
|
||||
default=None,
|
||||
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
||||
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
||||
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
||||
args = parser.parse_args()
|
||||
|
||||
debug = args.debug
|
||||
|
||||
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
||||
args.output_dir,
|
||||
max_shard_size=args.max_shard_size,
|
||||
safe_serialization=args.safe_serialization,
|
||||
tag=args.tag,
|
||||
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
||||
Reference in New Issue
Block a user