Xenon1/Zenith-7B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Xenon1/Zenith-7B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-05 12:37:38 +08:00
commit ecd083353b
318 changed files with 2455272 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.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

55
README.md Normal file
View File

@@ -0,0 +1,55 @@
---
language:
- en
license: apache-2.0
tags:
- mistral
- Zenith-7B
pipeline_tag: text-generation
---
# Model Card for Zenith-7B
Mistral-7B-v0.1 model fine-tuned on the Ultrafeedback dataset using techinques shown in the paper [Self-Rewarding Language Models](https://arxiv.org/abs/2401.10020).
## Instruction format
In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
E.g.
```
text = "<s>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
"[INST] Do you have mayonnaise recipes? [/INST]"
```
This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("Xenon1/Zenith-7B")
tokenizer = AutoTokenizer.from_pretrained("Xenon1/Zenith-7B")
messages = [
{"role": "user", "content": "What is your favourite condiment?"},
{"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
{"role": "user", "content": "Do you have mayonnaise recipes?"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
## Model Architecture
This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:
- Grouped-Query Attention
- Sliding-Window Attention
- Byte-fallback BPE tokenizer

204
checkpoint-100/README.md Normal file
View File

@@ -0,0 +1,204 @@
---
library_name: peft
base_model: /lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0

32
checkpoint-100/adapter_config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "/lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 16,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"up_proj",
"v_proj",
"k_proj",
"o_proj",
"q_proj",
"gate_proj",
"down_proj"
],
"task_type": "CAUSAL_LM",
"use_rslora": false
}

3
checkpoint-100/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:03c7e072a09d82fe41335b1e16e30b2cfdb9e52012e88b0b366aa9fc19b704e9
size 167832240

3
checkpoint-100/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7109d45182ade72fd34fd57da343292046385f4c99779d21702f16bec05e961b
size 335812858

3
checkpoint-100/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
size 888

3
checkpoint-100/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c56dcce6c13c6de889d4aae7dc0f064812110912b08fde202e8fc80f391303a4
size 14244

3
checkpoint-100/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:003e9a806b828de9b8637858af5bbdebcad9d4b8696a1a67b444bd1986516b15
size 1064

24
checkpoint-100/special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "</s>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

91149
checkpoint-100/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
checkpoint-100/tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

44
checkpoint-100/tokenizer_config.json Normal file
View File

@@ -0,0 +1,44 @@
{
"add_bos_token": true,
"add_eos_token": true,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}

629
checkpoint-100/trainer_state.json Normal file
View File

@@ -0,0 +1,629 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.043094160741219564,
"eval_steps": 100,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5e-05,
"loss": 1.5475,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999997705921923e-05,
"loss": 1.4738,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 4.9999908236919016e-05,
"loss": 1.709,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 4.999979353322567e-05,
"loss": 1.3682,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 4.99996329483497e-05,
"loss": 1.4525,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 4.999942648258581e-05,
"loss": 1.2902,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 4.999917413631294e-05,
"loss": 1.2581,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 4.9998875909994206e-05,
"loss": 1.1363,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 4.9998531804176926e-05,
"loss": 1.0479,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 4.999814181949263e-05,
"loss": 1.0362,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 4.999770595665704e-05,
"loss": 0.9415,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 4.999722421647006e-05,
"loss": 1.0849,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 4.999669659981584e-05,
"loss": 0.8538,
"step": 13
},
{
"epoch": 0.01,
"learning_rate": 4.999612310766268e-05,
"loss": 0.9404,
"step": 14
},
{
"epoch": 0.01,
"learning_rate": 4.9995503741063096e-05,
"loss": 0.9645,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 4.999483850115379e-05,
"loss": 1.0898,
"step": 16
},
{
"epoch": 0.01,
"learning_rate": 4.9994127389155623e-05,
"loss": 0.9545,
"step": 17
},
{
"epoch": 0.01,
"learning_rate": 4.9993370406373705e-05,
"loss": 0.8432,
"step": 18
},
{
"epoch": 0.01,
"learning_rate": 4.999256755419729e-05,
"loss": 0.9946,
"step": 19
},
{
"epoch": 0.01,
"learning_rate": 4.999171883409982e-05,
"loss": 0.7908,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 4.999082424763891e-05,
"loss": 0.8971,
"step": 21
},
{
"epoch": 0.01,
"learning_rate": 4.998988379645638e-05,
"loss": 0.85,
"step": 22
},
{
"epoch": 0.01,
"learning_rate": 4.998889748227819e-05,
"loss": 0.8626,
"step": 23
},
{
"epoch": 0.01,
"learning_rate": 4.9987865306914495e-05,
"loss": 0.8335,
"step": 24
},
{
"epoch": 0.01,
"learning_rate": 4.9986787272259596e-05,
"loss": 0.9314,
"step": 25
},
{
"epoch": 0.01,
"learning_rate": 4.998566338029198e-05,
"loss": 0.8645,
"step": 26
},
{
"epoch": 0.01,
"learning_rate": 4.998449363307428e-05,
"loss": 0.9316,
"step": 27
},
{
"epoch": 0.01,
"learning_rate": 4.998327803275328e-05,
"loss": 0.805,
"step": 28
},
{
"epoch": 0.01,
"learning_rate": 4.998201658155994e-05,
"loss": 1.0418,
"step": 29
},
{
"epoch": 0.01,
"learning_rate": 4.998070928180935e-05,
"loss": 0.649,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 4.997935613590075e-05,
"loss": 0.8,
"step": 31
},
{
"epoch": 0.01,
"learning_rate": 4.997795714631751e-05,
"loss": 0.8014,
"step": 32
},
{
"epoch": 0.01,
"learning_rate": 4.997651231562715e-05,
"loss": 0.7854,
"step": 33
},
{
"epoch": 0.01,
"learning_rate": 4.9975021646481315e-05,
"loss": 0.8782,
"step": 34
},
{
"epoch": 0.02,
"learning_rate": 4.997348514161576e-05,
"loss": 0.7564,
"step": 35
},
{
"epoch": 0.02,
"learning_rate": 4.997190280385039e-05,
"loss": 0.9438,
"step": 36
},
{
"epoch": 0.02,
"learning_rate": 4.997027463608921e-05,
"loss": 0.9248,
"step": 37
},
{
"epoch": 0.02,
"learning_rate": 4.996860064132033e-05,
"loss": 0.76,
"step": 38
},
{
"epoch": 0.02,
"learning_rate": 4.9966880822615965e-05,
"loss": 0.8834,
"step": 39
},
{
"epoch": 0.02,
"learning_rate": 4.996511518313244e-05,
"loss": 0.8928,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 4.996330372611017e-05,
"loss": 0.8857,
"step": 41
},
{
"epoch": 0.02,
"learning_rate": 4.996144645487364e-05,
"loss": 0.7975,
"step": 42
},
{
"epoch": 0.02,
"learning_rate": 4.995954337283145e-05,
"loss": 0.7815,
"step": 43
},
{
"epoch": 0.02,
"learning_rate": 4.9957594483476236e-05,
"loss": 0.8869,
"step": 44
},
{
"epoch": 0.02,
"learning_rate": 4.995559979038474e-05,
"loss": 0.9173,
"step": 45
},
{
"epoch": 0.02,
"learning_rate": 4.995355929721773e-05,
"loss": 0.9258,
"step": 46
},
{
"epoch": 0.02,
"learning_rate": 4.995147300772006e-05,
"loss": 0.896,
"step": 47
},
{
"epoch": 0.02,
"learning_rate": 4.994934092572061e-05,
"loss": 0.893,
"step": 48
},
{
"epoch": 0.02,
"learning_rate": 4.994716305513232e-05,
"loss": 0.8257,
"step": 49
},
{
"epoch": 0.02,
"learning_rate": 4.994493939995214e-05,
"loss": 0.8759,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 4.994266996426107e-05,
"loss": 0.9216,
"step": 51
},
{
"epoch": 0.02,
"learning_rate": 4.994035475222412e-05,
"loss": 0.9097,
"step": 52
},
{
"epoch": 0.02,
"learning_rate": 4.9937993768090306e-05,
"loss": 1.015,
"step": 53
},
{
"epoch": 0.02,
"learning_rate": 4.993558701619266e-05,
"loss": 0.8633,
"step": 54
},
{
"epoch": 0.02,
"learning_rate": 4.9933134500948205e-05,
"loss": 0.928,
"step": 55
},
{
"epoch": 0.02,
"learning_rate": 4.993063622685794e-05,
"loss": 0.8069,
"step": 56
},
{
"epoch": 0.02,
"learning_rate": 4.9928092198506866e-05,
"loss": 0.885,
"step": 57
},
{
"epoch": 0.02,
"learning_rate": 4.992550242056393e-05,
"loss": 0.7342,
"step": 58
},
{
"epoch": 0.03,
"learning_rate": 4.992286689778207e-05,
"loss": 0.8593,
"step": 59
},
{
"epoch": 0.03,
"learning_rate": 4.992018563499814e-05,
"loss": 0.9458,
"step": 60
},
{
"epoch": 0.03,
"learning_rate": 4.991745863713299e-05,
"loss": 0.9511,
"step": 61
},
{
"epoch": 0.03,
"learning_rate": 4.991468590919135e-05,
"loss": 0.8605,
"step": 62
},
{
"epoch": 0.03,
"learning_rate": 4.9911867456261916e-05,
"loss": 0.76,
"step": 63
},
{
"epoch": 0.03,
"learning_rate": 4.9909003283517283e-05,
"loss": 0.8037,
"step": 64
},
{
"epoch": 0.03,
"learning_rate": 4.990609339621397e-05,
"loss": 0.8945,
"step": 65
},
{
"epoch": 0.03,
"learning_rate": 4.990313779969237e-05,
"loss": 0.7774,
"step": 66
},
{
"epoch": 0.03,
"learning_rate": 4.990013649937679e-05,
"loss": 0.8737,
"step": 67
},
{
"epoch": 0.03,
"learning_rate": 4.989708950077541e-05,
"loss": 0.8914,
"step": 68
},
{
"epoch": 0.03,
"learning_rate": 4.9893996809480246e-05,
"loss": 0.8682,
"step": 69
},
{
"epoch": 0.03,
"learning_rate": 4.9890858431167226e-05,
"loss": 0.7745,
"step": 70
},
{
"epoch": 0.03,
"learning_rate": 4.988767437159608e-05,
"loss": 1.0306,
"step": 71
},
{
"epoch": 0.03,
"learning_rate": 4.988444463661041e-05,
"loss": 0.904,
"step": 72
},
{
"epoch": 0.03,
"learning_rate": 4.98811692321376e-05,
"loss": 0.8478,
"step": 73
},
{
"epoch": 0.03,
"learning_rate": 4.9877848164188904e-05,
"loss": 0.7117,
"step": 74
},
{
"epoch": 0.03,
"learning_rate": 4.987448143885933e-05,
"loss": 0.6789,
"step": 75
},
{
"epoch": 0.03,
"learning_rate": 4.987106906232773e-05,
"loss": 0.9385,
"step": 76
},
{
"epoch": 0.03,
"learning_rate": 4.9867611040856695e-05,
"loss": 1.049,
"step": 77
},
{
"epoch": 0.03,
"learning_rate": 4.9864107380792594e-05,
"loss": 0.8914,
"step": 78
},
{
"epoch": 0.03,
"learning_rate": 4.986055808856558e-05,
"loss": 0.8211,
"step": 79
},
{
"epoch": 0.03,
"learning_rate": 4.9856963170689525e-05,
"loss": 0.9007,
"step": 80
},
{
"epoch": 0.03,
"learning_rate": 4.9853322633762045e-05,
"loss": 0.832,
"step": 81
},
{
"epoch": 0.04,
"learning_rate": 4.984963648446449e-05,
"loss": 0.807,
"step": 82
},
{
"epoch": 0.04,
"learning_rate": 4.984590472956191e-05,
"loss": 0.7031,
"step": 83
},
{
"epoch": 0.04,
"learning_rate": 4.984212737590304e-05,
"loss": 0.9261,
"step": 84
},
{
"epoch": 0.04,
"learning_rate": 4.983830443042033e-05,
"loss": 0.7759,
"step": 85
},
{
"epoch": 0.04,
"learning_rate": 4.983443590012989e-05,
"loss": 0.7147,
"step": 86
},
{
"epoch": 0.04,
"learning_rate": 4.9830521792131484e-05,
"loss": 0.8554,
"step": 87
},
{
"epoch": 0.04,
"learning_rate": 4.982656211360852e-05,
"loss": 0.8052,
"step": 88
},
{
"epoch": 0.04,
"learning_rate": 4.982255687182806e-05,
"loss": 0.8408,
"step": 89
},
{
"epoch": 0.04,
"learning_rate": 4.981850607414077e-05,
"loss": 0.7086,
"step": 90
},
{
"epoch": 0.04,
"learning_rate": 4.981440972798092e-05,
"loss": 0.7808,
"step": 91
},
{
"epoch": 0.04,
"learning_rate": 4.981026784086639e-05,
"loss": 0.8632,
"step": 92
},
{
"epoch": 0.04,
"learning_rate": 4.980608042039862e-05,
"loss": 0.8798,
"step": 93
},
{
"epoch": 0.04,
"learning_rate": 4.980184747426263e-05,
"loss": 0.9253,
"step": 94
},
{
"epoch": 0.04,
"learning_rate": 4.9797569010226995e-05,
"loss": 0.8305,
"step": 95
},
{
"epoch": 0.04,
"learning_rate": 4.979324503614381e-05,
"loss": 0.9474,
"step": 96
},
{
"epoch": 0.04,
"learning_rate": 4.97888755599487e-05,
"loss": 0.8102,
"step": 97
},
{
"epoch": 0.04,
"learning_rate": 4.978446058966081e-05,
"loss": 0.6445,
"step": 98
},
{
"epoch": 0.04,
"learning_rate": 4.978000013338277e-05,
"loss": 0.8123,
"step": 99
},
{
"epoch": 0.04,
"learning_rate": 4.977549419930067e-05,
"loss": 0.9368,
"step": 100
},
{
"epoch": 0.04,
"eval_loss": 0.8984958529472351,
"eval_runtime": 10.1685,
"eval_samples_per_second": 3.639,
"eval_steps_per_second": 0.492,
"step": 100
}
],
"logging_steps": 1,
"max_steps": 2320,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 1.406258997362688e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-100/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f72ca16ea9cfad3b34621d2911d6f311c1d481df142920b5b63cd4c1b4222080
size 4792

204
checkpoint-1000/README.md Normal file
View File

@@ -0,0 +1,204 @@
---
library_name: peft
base_model: /lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0

32
checkpoint-1000/adapter_config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "/lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 16,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"up_proj",
"v_proj",
"k_proj",
"o_proj",
"q_proj",
"gate_proj",
"down_proj"
],
"task_type": "CAUSAL_LM",
"use_rslora": false
}

3
checkpoint-1000/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e947bdc939167c7ddff6570a7401725a14dcf89ab36517801c768f4ff54aef99
size 167832240

3
checkpoint-1000/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9889eb20b047e1bcc1e816dffcbe311d5983665abcd16229c33d776586267408
size 335813306

3
checkpoint-1000/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
size 888

3
checkpoint-1000/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c31580aa307d1ad63699e364d511103bb6cc34f8732563a737e58ce4e413aa4f
size 14244

3
checkpoint-1000/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3618c36ad9a167bf62c2bc7886cb955d14dc1043647b009b6aab7e81a49c07a8
size 1064

24
checkpoint-1000/special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "</s>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

91149
checkpoint-1000/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
checkpoint-1000/tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

44
checkpoint-1000/tokenizer_config.json Normal file
View File

@@ -0,0 +1,44 @@
{
"add_bos_token": true,
"add_eos_token": true,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}

6101
checkpoint-1000/trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-1000/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f72ca16ea9cfad3b34621d2911d6f311c1d481df142920b5b63cd4c1b4222080
size 4792

204
checkpoint-1100/README.md Normal file
View File

@@ -0,0 +1,204 @@
---
library_name: peft
base_model: /lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0

32
checkpoint-1100/adapter_config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "/lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 16,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"up_proj",
"v_proj",
"k_proj",
"o_proj",
"q_proj",
"gate_proj",
"down_proj"
],
"task_type": "CAUSAL_LM",
"use_rslora": false
}

3
checkpoint-1100/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7d3f97bc01a4b66e4054ce6d6dd1988c5e3f47fe0b55a43ae887244d8ae95ff4
size 167832240

3
checkpoint-1100/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f91dbc8272b8b92dc2f16edc0ffa88039b2af68920733c451c20333818b7e171
size 335813306

3
checkpoint-1100/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
size 888

3
checkpoint-1100/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:52fbb6b08b2485fbca1fe9155253c7ce53e4c99525df5ddf4a7b0fcdd6575a64
size 14244

3
checkpoint-1100/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e342b440dca854de898059198d7050e2840e3b30cb4db23e1128f1ed2045d1ec
size 1064

24
checkpoint-1100/special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "</s>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

91149
checkpoint-1100/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
checkpoint-1100/tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

44
checkpoint-1100/tokenizer_config.json Normal file
View File

@@ -0,0 +1,44 @@
{
"add_bos_token": true,
"add_eos_token": true,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}

6709
checkpoint-1100/trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-1100/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f72ca16ea9cfad3b34621d2911d6f311c1d481df142920b5b63cd4c1b4222080
size 4792

204
checkpoint-1200/README.md Normal file
View File

@@ -0,0 +1,204 @@
---
library_name: peft
base_model: /lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0

32
checkpoint-1200/adapter_config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "/lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 16,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"up_proj",
"v_proj",
"k_proj",
"o_proj",
"q_proj",
"gate_proj",
"down_proj"
],
"task_type": "CAUSAL_LM",
"use_rslora": false
}

3
checkpoint-1200/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a7c123196aa716c7ddc726ea8ec2dc970e549f8b606b54eeb71ccfe94481749
size 167832240

3
checkpoint-1200/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bccc65a8df88fb2fda9fa9f906b4167a9abc92f89d9d752657f139e274498211
size 335813306

3
checkpoint-1200/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
size 888

3
checkpoint-1200/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:92eb469dfdefffb1ba40adee3829ff30afd8912c3cd7cf139d0d155da2fa5a94
size 14244

3
checkpoint-1200/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4ea2ec9fb1515d5822b6558b2f799ac74065753ef73757d4711eeb26440912d8
size 1064

24
checkpoint-1200/special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "</s>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

91149
checkpoint-1200/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
checkpoint-1200/tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

44
checkpoint-1200/tokenizer_config.json Normal file
View File

@@ -0,0 +1,44 @@
{
"add_bos_token": true,
"add_eos_token": true,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}

7317
checkpoint-1200/trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-1200/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f72ca16ea9cfad3b34621d2911d6f311c1d481df142920b5b63cd4c1b4222080
size 4792

204
checkpoint-1300/README.md Normal file
View File

@@ -0,0 +1,204 @@
---
library_name: peft
base_model: /lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0

32
checkpoint-1300/adapter_config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "/lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 16,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"up_proj",
"v_proj",
"k_proj",
"o_proj",
"q_proj",
"gate_proj",
"down_proj"
],
"task_type": "CAUSAL_LM",
"use_rslora": false
}

3
checkpoint-1300/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f47d406a6743f3ab804c40c1125cd5933f7f143fb5ebda7e1ca4b5f7ee00700e
size 167832240

3
checkpoint-1300/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:936a6b5cbae118a4524a33028a705da78f6660122d521db682ef6b4726d893da
size 335813306

3
checkpoint-1300/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
size 888

3
checkpoint-1300/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fc4fa96e69939612c145f4533a30cd8edab979dce6d6bdc012a16f6a47f2f6d4
size 14244

3
checkpoint-1300/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eafe8eddaecf091337e5f529c3aa8403070fcfdac6f917be8e76bf361efd67ee
size 1064

24
checkpoint-1300/special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "</s>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

91149
checkpoint-1300/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
checkpoint-1300/tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

44
checkpoint-1300/tokenizer_config.json Normal file
View File

@@ -0,0 +1,44 @@
{
"add_bos_token": true,
"add_eos_token": true,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}

7925
checkpoint-1300/trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-1300/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f72ca16ea9cfad3b34621d2911d6f311c1d481df142920b5b63cd4c1b4222080
size 4792

204
checkpoint-1400/README.md Normal file
View File

@@ -0,0 +1,204 @@
---
library_name: peft
base_model: /lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0

32
checkpoint-1400/adapter_config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "/lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 16,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"up_proj",
"v_proj",
"k_proj",
"o_proj",
"q_proj",
"gate_proj",
"down_proj"
],
"task_type": "CAUSAL_LM",
"use_rslora": false
}

3
checkpoint-1400/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3ed6440aaad576003e833ac9319d5be48eeede83690903a529b55da4cf630a91
size 167832240

3
checkpoint-1400/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c36c90a43cfc24ba50dd079e96ad8149ee324b92d51cce91016ee3df00e9f809
size 335813306

3
checkpoint-1400/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
size 888

3
checkpoint-1400/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:05aa575347e3b3079876be6089ef0d30073805a6d6073af9ffc298ef89e91917
size 14244

3
checkpoint-1400/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ffa295d77c38ff4045059d0aaac72283ef9f3c1bc71635906b7ca8484836afc8
size 1064

24
checkpoint-1400/special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "</s>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

91149
checkpoint-1400/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
checkpoint-1400/tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

44
checkpoint-1400/tokenizer_config.json Normal file
View File

@@ -0,0 +1,44 @@
{
"add_bos_token": true,
"add_eos_token": true,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}

8533
checkpoint-1400/trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-1400/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f72ca16ea9cfad3b34621d2911d6f311c1d481df142920b5b63cd4c1b4222080
size 4792

204
checkpoint-1500/README.md Normal file
View File

@@ -0,0 +1,204 @@
---
library_name: peft
base_model: /lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0

32
checkpoint-1500/adapter_config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "/lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 16,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"up_proj",
"v_proj",
"k_proj",
"o_proj",
"q_proj",
"gate_proj",
"down_proj"
],
"task_type": "CAUSAL_LM",
"use_rslora": false
}

3
checkpoint-1500/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d7eebab2a8e41f922446db5671d05ef199f5d5eb7f38c85c0849aa46c301145e
size 167832240

3
checkpoint-1500/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:95d3a5aae272913b87f07e41d0c43006197c29a09ea940b88719870b9cb45ef6
size 335813306

3
checkpoint-1500/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
size 888

3
checkpoint-1500/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5e31d8b253326cfd22f2b91ae5875fed0e4f128489cb4a192f2e350149fe5785
size 14244

3
checkpoint-1500/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:69a119d0ce13e246f2f01b1cc4c2363509ce4f32b97ab4d3850b3711abf5b118
size 1064

24
checkpoint-1500/special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "</s>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

91149
checkpoint-1500/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
checkpoint-1500/tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

44
checkpoint-1500/tokenizer_config.json Normal file
View File

@@ -0,0 +1,44 @@
{
"add_bos_token": true,
"add_eos_token": true,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}

9141
checkpoint-1500/trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-1500/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f72ca16ea9cfad3b34621d2911d6f311c1d481df142920b5b63cd4c1b4222080
size 4792

204
checkpoint-1600/README.md Normal file
View File

@@ -0,0 +1,204 @@
---
library_name: peft
base_model: /lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.2.dev0

32
checkpoint-1600/adapter_config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "/lustre07/scratch/gagan30/arocr/meta-llama/self_rewarding_models/Mistral-7B-Instruct-v0.2-dpo-3",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 16,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"up_proj",
"v_proj",
"k_proj",
"o_proj",
"q_proj",
"gate_proj",
"down_proj"
],
"task_type": "CAUSAL_LM",
"use_rslora": false
}

3
checkpoint-1600/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0757d70938af532877d2db2ce3b514b2c37310acbd8f5afd32102ac7972f9269
size 167832240

3
checkpoint-1600/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eddc6b74467150919f92fa6191a09c654758f7e90d928388be4205c0af4968e2
size 335813306

3
checkpoint-1600/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
size 888

3
checkpoint-1600/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:40c2134e1ccd1c6b0a06e85db81cb6ebd239848a55afa57db7b8fc451c75b29c
size 14244

3
checkpoint-1600/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8546400662d48872ecb8818892b34e42449ea09145a3f3b245e67f86ecdbf8e4
size 1064

Some files were not shown because too many files have changed in this diff Show More