初始化项目，由ModelHub XC社区提供模型
Model: AI-MO/NuminaMath-7B-CoT Source: Original Platform
This commit is contained in:
ModelHub XC
44
.gitattributes
vendored
Normal file
44
.gitattributes
vendored
Normal file
@@ -0,0 +1,44 @@
|
||||
*.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
|
||||
model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
144
README.md
Normal file
144
README.md
Normal file
@@ -0,0 +1,144 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: deepseek-ai/deepseek-math-7b-base
|
||||
tags:
|
||||
- alignment-handbook
|
||||
- generated_from_trainer
|
||||
- aimo
|
||||
- math
|
||||
datasets:
|
||||
- AI-MO/NuminaMath-CoT
|
||||
model-index:
|
||||
- name: AI-MO/NuminaMath-7B-CoT
|
||||
results: []
|
||||
language:
|
||||
- en
|
||||
---
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
<img src="https://huggingface.co/AI-MO/NuminaMath-7B-TIR/resolve/main/thumbnail.png" alt="Numina Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
||||
|
||||
|
||||
# Model Card for NuminaMath 7B CoT
|
||||
|
||||
NuminaMath is a series of language models that are trained with two stages of supervised fine-tuning to solve math problems using chain of thought (CoT) and tool-integrated reasoning (TIR):
|
||||
|
||||
* **Stage 1:** fine-tune the base model on a large, diverse dataset of natural language math problems and solutions, where each solution is templated with Chain of Thought (CoT) to facilitate reasoning.
|
||||
* **Stage 2:** fine-tune the model from Stage 1 on a synthetic dataset of tool-integrated reasoning, where each math problem is decomposed into a sequence of rationales, Python programs, and their outputs.
|
||||
|
||||
NuminaMath 7B CoT is the model from Stage 1 and was fine-tuned on [AI-MO/NuminaMath-CoT](https://huggingface.co/datasets/AI-MO/NuminaMath-CoT), a large-scale dataset of 860k+ math competition problem-solution pairs.
|
||||
|
||||
## Model description
|
||||
|
||||
- **Model type:** A 7B parameter math LLM fine-tuned on a dataset with 860k+ math problem-solution pairs.
|
||||
- **Language(s) (NLP):** Primarily English
|
||||
- **License:** Apache 2.0
|
||||
- **Finetuned from model:** [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base)
|
||||
|
||||
### Model Sources
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** https://github.com/project-numina/aimo-progress-prize
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import pipeline
|
||||
|
||||
pipe = pipeline("text-generation", model="AI-MO/NuminaMath-7B-TIR", torch_dtype=torch.bfloat16, device_map="auto")
|
||||
|
||||
messages = [
|
||||
{"role": "user", "content": "For how many values of the constant $k$ will the polynomial $x^{2}+kx+36$ have two distinct integer roots?"},
|
||||
]
|
||||
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
|
||||
gen_config = {
|
||||
"max_new_tokens": 1024,
|
||||
"do_sample": False,
|
||||
"tokenizer": pipe.tokenizer,
|
||||
}
|
||||
|
||||
outputs = pipe(prompt, **gen_config)
|
||||
text = outputs[0]["generated_text"]
|
||||
print(text)
|
||||
```
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
NuminaMath 7B CoT was created to solve problems in the narrow domain of competition-level mathematics. As a result, the model should not be used for general chat applications. With greedy decoding, we find the model is capable of solving problems at the level of [AMC 12](https://artofproblemsolving.com/wiki/index.php/2023_AMC_12A_Problems), but often struggles generate a valid solution on harder problems at the AIME and Math Olympiad level. The model also struggles to solve geometry problems, likely due to it's limited capacity and lack of other modalities like vision.
|
||||
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 2e-05
|
||||
- train_batch_size: 4
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- total_train_batch_size: 32
|
||||
- total_eval_batch_size: 64
|
||||
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 4.0
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.40.1
|
||||
- Pytorch 2.3.1
|
||||
- Datasets 2.18.0
|
||||
- Tokenizers 0.19.1
|
||||
|
||||
## Citation
|
||||
|
||||
If you find NuminaMath 7B TIR is useful in your work, please cite it with:
|
||||
|
||||
```
|
||||
@misc{numina_math_7b,
|
||||
author = {Edward Beeching and Shengyi Costa Huang and Albert Jiang and Jia Li and Benjamin Lipkin and Zihan Qina and Kashif Rasul and Ziju Shen and Roman Soletskyi and Lewis Tunstall},
|
||||
title = {NuminaMath 7B CoT},
|
||||
year = {2024},
|
||||
publisher = {Numina & Hugging Face},
|
||||
journal = {Hugging Face repository},
|
||||
howpublished = {\url{https://huggingface.co/AI-MO/NuminaMath-7B-CoT}}
|
||||
}
|
||||
```
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 2e-05
|
||||
- train_batch_size: 4
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- total_train_batch_size: 32
|
||||
- total_eval_batch_size: 64
|
||||
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 3.0
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.42.3
|
||||
- Pytorch 2.3.0+cu121
|
||||
- Datasets 2.18.0
|
||||
- Tokenizers 0.19.1
|
||||
15
all_results.json
Normal file
15
all_results.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"eval_loss": 0.45375168323516846,
|
||||
"eval_runtime": 0.5431,
|
||||
"eval_samples": 100,
|
||||
"eval_samples_per_second": 46.032,
|
||||
"eval_steps_per_second": 1.841,
|
||||
"perplexity": 1.5742070469361709,
|
||||
"total_flos": 2049636776804352.0,
|
||||
"train_loss": 0.42822988295175696,
|
||||
"train_runtime": 30718.8165,
|
||||
"train_samples": 863474,
|
||||
"train_samples_per_second": 21.729,
|
||||
"train_steps_per_second": 0.679
|
||||
}
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "AI-MO/deepseek-math-7b-sft",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 100000,
|
||||
"eos_token_id": 100001,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 4096,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 30,
|
||||
"num_key_value_heads": 32,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.42.3",
|
||||
"use_cache": true,
|
||||
"vocab_size": 102400
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
9
eval_results.json
Normal file
9
eval_results.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"eval_loss": 0.45375168323516846,
|
||||
"eval_runtime": 0.5431,
|
||||
"eval_samples": 100,
|
||||
"eval_samples_per_second": 46.032,
|
||||
"eval_steps_per_second": 1.841,
|
||||
"perplexity": 1.5742070469361709
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 100000,
|
||||
"eos_token_id": 100001,
|
||||
"transformers_version": "4.42.3"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d828dfd71297d18ae06980e3307a96b51ad49bfaea5308e2951858d353349fda
|
||||
size 4987202208
|
||||
3
model-00001-of-00006.safetensors
Normal file
3
model-00001-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a020e4dbfe6ea9c4566673c630be8b80f20518367467697aa42254d74285e166
|
||||
size 4982968608
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b7a1d0674763eaab23134708d22c22e5afd20f625d464d5d889157638a7c5c2c
|
||||
size 4980945440
|
||||
3
model-00002-of-00006.safetensors
Normal file
3
model-00002-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:41a7bb36fd41032ceeb9126e1f9ce3314174e18508843fac0132303bf7c25391
|
||||
size 4991424808
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:da18516e1f348652ecd1c8a1ca5eb2cabfaca9abb60a805a82d5acee3e689ff5
|
||||
size 3852615520
|
||||
3
model-00003-of-00006.safetensors
Normal file
3
model-00003-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:24e74cf0a7aa320e0d03076e73249d5e4d802c2fb775b8835659cfd4f55448c0
|
||||
size 4924315880
|
||||
3
model-00004-of-00006.safetensors
Normal file
3
model-00004-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8a01642817c45fe15d248324a5ff27c0a5928d3aa9074e8affbf7a1231f154c6
|
||||
size 4857206904
|
||||
3
model-00005-of-00006.safetensors
Normal file
3
model-00005-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:30ef417fc1fe46e1e48e0ebb55058285e223c27d725c4a497d53ce504a73900b
|
||||
size 4857206904
|
||||
3
model-00006-of-00006.safetensors
Normal file
3
model-00006-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8e075f78293bc50aeb31e48e856cf8af40453741d3343782eb6823c7da0537ed
|
||||
size 3028371240
|
||||
280
model.safetensors.index.json
Normal file
280
model.safetensors.index.json
Normal file
@@ -0,0 +1,280 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 27641462784
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00006-of-00006.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.norm.weight": "model-00006-of-00006.safetensors"
|
||||
}
|
||||
}
|
||||
17
special_tokens_map.json
Normal file
17
special_tokens_map.json
Normal file
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<｜begin▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<｜end▁of▁sentence｜>"
|
||||
}
|
||||
199915
tokenizer.json
Normal file
199915
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
33
tokenizer_config.json
Normal file
33
tokenizer_config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"100000": {
|
||||
"content": "<｜begin▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100001": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<｜begin▁of▁sentence｜>",
|
||||
"chat_template": "{% for message in messages %}{% if (message['role'] == 'system')%}{{ '' }}{% elif (message['role'] == 'user')%}{{ '### Problem: ' + message['content'] + '\n' }}{% elif (message['role'] == 'assistant')%}{{ '### Solution: ' + message['content'] + '\n' }}{% endif %}{% if loop.last and message['role'] == 'user' and add_generation_prompt %}{{ '### Solution: ' }}{% endif %}{% endfor %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<｜end▁of▁sentence｜>",
|
||||
"legacy": true,
|
||||
"model_max_length": 4096,
|
||||
"pad_token": "<｜end▁of▁sentence｜>",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": null,
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
9
train_results.json
Normal file
9
train_results.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"total_flos": 2049636776804352.0,
|
||||
"train_loss": 0.42822988295175696,
|
||||
"train_runtime": 30718.8165,
|
||||
"train_samples": 863474,
|
||||
"train_samples_per_second": 21.729,
|
||||
"train_steps_per_second": 0.679
|
||||
}
|
||||
29277
trainer_state.json
Normal file
29277
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d78701b6716fed3fcb3a4fc27a4558def88bdd067e9119a56fde08d7134b5d28
|
||||
size 6904
|
||||
Reference in New Issue
Block a user