IO v3
This commit is contained in:
parent
d110db2595
commit
ab4f0777cd
|
|
@ -0,0 +1,204 @@
|
|||
---
|
||||
library_name: peft
|
||||
base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
|
||||
---
|
||||
|
||||
# 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 0.8.2
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
|
||||
"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": [
|
||||
"k_proj",
|
||||
"o_proj",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"up_proj",
|
||||
"down_proj"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"use_rslora": false
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -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
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
|
@ -0,0 +1,43 @@
|
|||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"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>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
|
|
@ -0,0 +1,321 @@
|
|||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 25.0,
|
||||
"eval_steps": 5,
|
||||
"global_step": 100,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"learning_rate": 2.9999177540482684e-05,
|
||||
"loss": 2.6428,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"learning_rate": 2.9996710252122685e-05,
|
||||
"loss": 2.1838,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 1.5,
|
||||
"learning_rate": 2.9992598405485974e-05,
|
||||
"loss": 1.8524,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"learning_rate": 2.9986842451482876e-05,
|
||||
"loss": 1.59,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 2.5,
|
||||
"learning_rate": 2.9979443021318607e-05,
|
||||
"loss": 1.4015,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"learning_rate": 2.9970400926424075e-05,
|
||||
"loss": 1.2128,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 3.5,
|
||||
"learning_rate": 2.995971715836687e-05,
|
||||
"loss": 1.1418,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"learning_rate": 2.9947392888742566e-05,
|
||||
"loss": 1.0389,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 4.5,
|
||||
"learning_rate": 2.9933429469046202e-05,
|
||||
"loss": 1.0268,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"learning_rate": 2.99178284305241e-05,
|
||||
"loss": 0.9734,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 5.5,
|
||||
"learning_rate": 2.9900591484005944e-05,
|
||||
"loss": 0.9755,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 6.0,
|
||||
"learning_rate": 2.988172051971717e-05,
|
||||
"loss": 0.9142,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 6.5,
|
||||
"learning_rate": 2.9861217607071655e-05,
|
||||
"loss": 0.8872,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 7.0,
|
||||
"learning_rate": 2.983908499444483e-05,
|
||||
"loss": 0.8633,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 7.5,
|
||||
"learning_rate": 2.981532510892707e-05,
|
||||
"loss": 0.8248,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 8.0,
|
||||
"learning_rate": 2.9789940556057574e-05,
|
||||
"loss": 0.8352,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 8.5,
|
||||
"learning_rate": 2.9762934119538628e-05,
|
||||
"loss": 0.8017,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 9.0,
|
||||
"learning_rate": 2.9734308760930333e-05,
|
||||
"loss": 0.7705,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 9.5,
|
||||
"learning_rate": 2.9704067619325828e-05,
|
||||
"loss": 0.7619,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 10.0,
|
||||
"learning_rate": 2.9672214011007087e-05,
|
||||
"loss": 0.7593,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 10.5,
|
||||
"learning_rate": 2.9638751429081213e-05,
|
||||
"loss": 0.7469,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 11.0,
|
||||
"learning_rate": 2.9603683543097406e-05,
|
||||
"loss": 0.7477,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 11.5,
|
||||
"learning_rate": 2.9567014198644542e-05,
|
||||
"loss": 0.716,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 12.0,
|
||||
"learning_rate": 2.9528747416929467e-05,
|
||||
"loss": 0.7351,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 12.5,
|
||||
"learning_rate": 2.9488887394336025e-05,
|
||||
"loss": 0.72,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 13.0,
|
||||
"learning_rate": 2.9447438501964873e-05,
|
||||
"loss": 0.714,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 13.5,
|
||||
"learning_rate": 2.9404405285154146e-05,
|
||||
"loss": 0.6994,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 14.0,
|
||||
"learning_rate": 2.9359792462981007e-05,
|
||||
"loss": 0.7064,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 14.5,
|
||||
"learning_rate": 2.9313604927744153e-05,
|
||||
"loss": 0.6807,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 15.0,
|
||||
"learning_rate": 2.9265847744427305e-05,
|
||||
"loss": 0.6969,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 15.5,
|
||||
"learning_rate": 2.9216526150143788e-05,
|
||||
"loss": 0.6836,
|
||||
"step": 62
|
||||
},
|
||||
{
|
||||
"epoch": 16.0,
|
||||
"learning_rate": 2.9165645553562215e-05,
|
||||
"loss": 0.6557,
|
||||
"step": 64
|
||||
},
|
||||
{
|
||||
"epoch": 16.5,
|
||||
"learning_rate": 2.9113211534313385e-05,
|
||||
"loss": 0.6619,
|
||||
"step": 66
|
||||
},
|
||||
{
|
||||
"epoch": 17.0,
|
||||
"learning_rate": 2.9059229842378373e-05,
|
||||
"loss": 0.6496,
|
||||
"step": 68
|
||||
},
|
||||
{
|
||||
"epoch": 17.5,
|
||||
"learning_rate": 2.9003706397458025e-05,
|
||||
"loss": 0.6268,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 18.0,
|
||||
"learning_rate": 2.894664728832377e-05,
|
||||
"loss": 0.6586,
|
||||
"step": 72
|
||||
},
|
||||
{
|
||||
"epoch": 18.5,
|
||||
"learning_rate": 2.8888058772149923e-05,
|
||||
"loss": 0.6197,
|
||||
"step": 74
|
||||
},
|
||||
{
|
||||
"epoch": 19.0,
|
||||
"learning_rate": 2.8827947273827508e-05,
|
||||
"loss": 0.638,
|
||||
"step": 76
|
||||
},
|
||||
{
|
||||
"epoch": 19.5,
|
||||
"learning_rate": 2.8766319385259717e-05,
|
||||
"loss": 0.6093,
|
||||
"step": 78
|
||||
},
|
||||
{
|
||||
"epoch": 20.0,
|
||||
"learning_rate": 2.8703181864639013e-05,
|
||||
"loss": 0.6089,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 20.5,
|
||||
"learning_rate": 2.863854163570603e-05,
|
||||
"loss": 0.6108,
|
||||
"step": 82
|
||||
},
|
||||
{
|
||||
"epoch": 21.0,
|
||||
"learning_rate": 2.8572405786990293e-05,
|
||||
"loss": 0.5776,
|
||||
"step": 84
|
||||
},
|
||||
{
|
||||
"epoch": 21.5,
|
||||
"learning_rate": 2.8504781571032906e-05,
|
||||
"loss": 0.5776,
|
||||
"step": 86
|
||||
},
|
||||
{
|
||||
"epoch": 22.0,
|
||||
"learning_rate": 2.8435676403591193e-05,
|
||||
"loss": 0.5997,
|
||||
"step": 88
|
||||
},
|
||||
{
|
||||
"epoch": 22.5,
|
||||
"learning_rate": 2.8365097862825516e-05,
|
||||
"loss": 0.5579,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 23.0,
|
||||
"learning_rate": 2.829305368846822e-05,
|
||||
"loss": 0.579,
|
||||
"step": 92
|
||||
},
|
||||
{
|
||||
"epoch": 23.5,
|
||||
"learning_rate": 2.821955178097488e-05,
|
||||
"loss": 0.5689,
|
||||
"step": 94
|
||||
},
|
||||
{
|
||||
"epoch": 24.0,
|
||||
"learning_rate": 2.8144600200657953e-05,
|
||||
"loss": 0.5278,
|
||||
"step": 96
|
||||
},
|
||||
{
|
||||
"epoch": 24.5,
|
||||
"learning_rate": 2.8068207166802843e-05,
|
||||
"loss": 0.55,
|
||||
"step": 98
|
||||
},
|
||||
{
|
||||
"epoch": 25.0,
|
||||
"learning_rate": 2.7990381056766583e-05,
|
||||
"loss": 0.516,
|
||||
"step": 100
|
||||
}
|
||||
],
|
||||
"logging_steps": 2,
|
||||
"max_steps": 600,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 150,
|
||||
"save_steps": 500,
|
||||
"total_flos": 4764264824832000.0,
|
||||
"train_batch_size": 52,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
Binary file not shown.
|
|
@ -0,0 +1,204 @@
|
|||
---
|
||||
library_name: peft
|
||||
base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
|
||||
---
|
||||
|
||||
# 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 0.8.2
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
|
||||
"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": [
|
||||
"k_proj",
|
||||
"o_proj",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"up_proj",
|
||||
"down_proj"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"use_rslora": false
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -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
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
|
@ -0,0 +1,43 @@
|
|||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"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>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
|
|
@ -0,0 +1,333 @@
|
|||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 26.0,
|
||||
"eval_steps": 5,
|
||||
"global_step": 104,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"learning_rate": 2.9999177540482684e-05,
|
||||
"loss": 2.6428,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"learning_rate": 2.9996710252122685e-05,
|
||||
"loss": 2.1838,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 1.5,
|
||||
"learning_rate": 2.9992598405485974e-05,
|
||||
"loss": 1.8524,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"learning_rate": 2.9986842451482876e-05,
|
||||
"loss": 1.59,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 2.5,
|
||||
"learning_rate": 2.9979443021318607e-05,
|
||||
"loss": 1.4015,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"learning_rate": 2.9970400926424075e-05,
|
||||
"loss": 1.2128,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 3.5,
|
||||
"learning_rate": 2.995971715836687e-05,
|
||||
"loss": 1.1418,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"learning_rate": 2.9947392888742566e-05,
|
||||
"loss": 1.0389,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 4.5,
|
||||
"learning_rate": 2.9933429469046202e-05,
|
||||
"loss": 1.0268,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"learning_rate": 2.99178284305241e-05,
|
||||
"loss": 0.9734,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 5.5,
|
||||
"learning_rate": 2.9900591484005944e-05,
|
||||
"loss": 0.9755,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 6.0,
|
||||
"learning_rate": 2.988172051971717e-05,
|
||||
"loss": 0.9142,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 6.5,
|
||||
"learning_rate": 2.9861217607071655e-05,
|
||||
"loss": 0.8872,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 7.0,
|
||||
"learning_rate": 2.983908499444483e-05,
|
||||
"loss": 0.8633,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 7.5,
|
||||
"learning_rate": 2.981532510892707e-05,
|
||||
"loss": 0.8248,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 8.0,
|
||||
"learning_rate": 2.9789940556057574e-05,
|
||||
"loss": 0.8352,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 8.5,
|
||||
"learning_rate": 2.9762934119538628e-05,
|
||||
"loss": 0.8017,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 9.0,
|
||||
"learning_rate": 2.9734308760930333e-05,
|
||||
"loss": 0.7705,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 9.5,
|
||||
"learning_rate": 2.9704067619325828e-05,
|
||||
"loss": 0.7619,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 10.0,
|
||||
"learning_rate": 2.9672214011007087e-05,
|
||||
"loss": 0.7593,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 10.5,
|
||||
"learning_rate": 2.9638751429081213e-05,
|
||||
"loss": 0.7469,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 11.0,
|
||||
"learning_rate": 2.9603683543097406e-05,
|
||||
"loss": 0.7477,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 11.5,
|
||||
"learning_rate": 2.9567014198644542e-05,
|
||||
"loss": 0.716,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 12.0,
|
||||
"learning_rate": 2.9528747416929467e-05,
|
||||
"loss": 0.7351,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 12.5,
|
||||
"learning_rate": 2.9488887394336025e-05,
|
||||
"loss": 0.72,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 13.0,
|
||||
"learning_rate": 2.9447438501964873e-05,
|
||||
"loss": 0.714,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 13.5,
|
||||
"learning_rate": 2.9404405285154146e-05,
|
||||
"loss": 0.6994,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 14.0,
|
||||
"learning_rate": 2.9359792462981007e-05,
|
||||
"loss": 0.7064,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 14.5,
|
||||
"learning_rate": 2.9313604927744153e-05,
|
||||
"loss": 0.6807,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 15.0,
|
||||
"learning_rate": 2.9265847744427305e-05,
|
||||
"loss": 0.6969,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 15.5,
|
||||
"learning_rate": 2.9216526150143788e-05,
|
||||
"loss": 0.6836,
|
||||
"step": 62
|
||||
},
|
||||
{
|
||||
"epoch": 16.0,
|
||||
"learning_rate": 2.9165645553562215e-05,
|
||||
"loss": 0.6557,
|
||||
"step": 64
|
||||
},
|
||||
{
|
||||
"epoch": 16.5,
|
||||
"learning_rate": 2.9113211534313385e-05,
|
||||
"loss": 0.6619,
|
||||
"step": 66
|
||||
},
|
||||
{
|
||||
"epoch": 17.0,
|
||||
"learning_rate": 2.9059229842378373e-05,
|
||||
"loss": 0.6496,
|
||||
"step": 68
|
||||
},
|
||||
{
|
||||
"epoch": 17.5,
|
||||
"learning_rate": 2.9003706397458025e-05,
|
||||
"loss": 0.6268,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 18.0,
|
||||
"learning_rate": 2.894664728832377e-05,
|
||||
"loss": 0.6586,
|
||||
"step": 72
|
||||
},
|
||||
{
|
||||
"epoch": 18.5,
|
||||
"learning_rate": 2.8888058772149923e-05,
|
||||
"loss": 0.6197,
|
||||
"step": 74
|
||||
},
|
||||
{
|
||||
"epoch": 19.0,
|
||||
"learning_rate": 2.8827947273827508e-05,
|
||||
"loss": 0.638,
|
||||
"step": 76
|
||||
},
|
||||
{
|
||||
"epoch": 19.5,
|
||||
"learning_rate": 2.8766319385259717e-05,
|
||||
"loss": 0.6093,
|
||||
"step": 78
|
||||
},
|
||||
{
|
||||
"epoch": 20.0,
|
||||
"learning_rate": 2.8703181864639013e-05,
|
||||
"loss": 0.6089,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 20.5,
|
||||
"learning_rate": 2.863854163570603e-05,
|
||||
"loss": 0.6108,
|
||||
"step": 82
|
||||
},
|
||||
{
|
||||
"epoch": 21.0,
|
||||
"learning_rate": 2.8572405786990293e-05,
|
||||
"loss": 0.5776,
|
||||
"step": 84
|
||||
},
|
||||
{
|
||||
"epoch": 21.5,
|
||||
"learning_rate": 2.8504781571032906e-05,
|
||||
"loss": 0.5776,
|
||||
"step": 86
|
||||
},
|
||||
{
|
||||
"epoch": 22.0,
|
||||
"learning_rate": 2.8435676403591193e-05,
|
||||
"loss": 0.5997,
|
||||
"step": 88
|
||||
},
|
||||
{
|
||||
"epoch": 22.5,
|
||||
"learning_rate": 2.8365097862825516e-05,
|
||||
"loss": 0.5579,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 23.0,
|
||||
"learning_rate": 2.829305368846822e-05,
|
||||
"loss": 0.579,
|
||||
"step": 92
|
||||
},
|
||||
{
|
||||
"epoch": 23.5,
|
||||
"learning_rate": 2.821955178097488e-05,
|
||||
"loss": 0.5689,
|
||||
"step": 94
|
||||
},
|
||||
{
|
||||
"epoch": 24.0,
|
||||
"learning_rate": 2.8144600200657953e-05,
|
||||
"loss": 0.5278,
|
||||
"step": 96
|
||||
},
|
||||
{
|
||||
"epoch": 24.5,
|
||||
"learning_rate": 2.8068207166802843e-05,
|
||||
"loss": 0.55,
|
||||
"step": 98
|
||||
},
|
||||
{
|
||||
"epoch": 25.0,
|
||||
"learning_rate": 2.7990381056766583e-05,
|
||||
"loss": 0.516,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 25.5,
|
||||
"learning_rate": 2.7911130405059155e-05,
|
||||
"loss": 0.5342,
|
||||
"step": 102
|
||||
},
|
||||
{
|
||||
"epoch": 26.0,
|
||||
"learning_rate": 2.78304639024076e-05,
|
||||
"loss": 0.5021,
|
||||
"step": 104
|
||||
}
|
||||
],
|
||||
"logging_steps": 2,
|
||||
"max_steps": 600,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 150,
|
||||
"save_steps": 500,
|
||||
"total_flos": 4954835417825280.0,
|
||||
"train_batch_size": 52,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
Binary file not shown.
|
|
@ -0,0 +1,204 @@
|
|||
---
|
||||
library_name: peft
|
||||
base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
|
||||
---
|
||||
|
||||
# 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 0.8.2
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
|
||||
"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": [
|
||||
"k_proj",
|
||||
"o_proj",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"up_proj",
|
||||
"down_proj"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"use_rslora": false
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -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
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
|
@ -0,0 +1,43 @@
|
|||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"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>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
|
|
@ -0,0 +1,345 @@
|
|||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 27.0,
|
||||
"eval_steps": 5,
|
||||
"global_step": 108,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"learning_rate": 2.9999177540482684e-05,
|
||||
"loss": 2.6428,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"learning_rate": 2.9996710252122685e-05,
|
||||
"loss": 2.1838,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 1.5,
|
||||
"learning_rate": 2.9992598405485974e-05,
|
||||
"loss": 1.8524,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"learning_rate": 2.9986842451482876e-05,
|
||||
"loss": 1.59,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 2.5,
|
||||
"learning_rate": 2.9979443021318607e-05,
|
||||
"loss": 1.4015,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"learning_rate": 2.9970400926424075e-05,
|
||||
"loss": 1.2128,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 3.5,
|
||||
"learning_rate": 2.995971715836687e-05,
|
||||
"loss": 1.1418,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"learning_rate": 2.9947392888742566e-05,
|
||||
"loss": 1.0389,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 4.5,
|
||||
"learning_rate": 2.9933429469046202e-05,
|
||||
"loss": 1.0268,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"learning_rate": 2.99178284305241e-05,
|
||||
"loss": 0.9734,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 5.5,
|
||||
"learning_rate": 2.9900591484005944e-05,
|
||||
"loss": 0.9755,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 6.0,
|
||||
"learning_rate": 2.988172051971717e-05,
|
||||
"loss": 0.9142,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 6.5,
|
||||
"learning_rate": 2.9861217607071655e-05,
|
||||
"loss": 0.8872,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 7.0,
|
||||
"learning_rate": 2.983908499444483e-05,
|
||||
"loss": 0.8633,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 7.5,
|
||||
"learning_rate": 2.981532510892707e-05,
|
||||
"loss": 0.8248,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 8.0,
|
||||
"learning_rate": 2.9789940556057574e-05,
|
||||
"loss": 0.8352,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 8.5,
|
||||
"learning_rate": 2.9762934119538628e-05,
|
||||
"loss": 0.8017,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 9.0,
|
||||
"learning_rate": 2.9734308760930333e-05,
|
||||
"loss": 0.7705,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 9.5,
|
||||
"learning_rate": 2.9704067619325828e-05,
|
||||
"loss": 0.7619,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 10.0,
|
||||
"learning_rate": 2.9672214011007087e-05,
|
||||
"loss": 0.7593,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 10.5,
|
||||
"learning_rate": 2.9638751429081213e-05,
|
||||
"loss": 0.7469,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 11.0,
|
||||
"learning_rate": 2.9603683543097406e-05,
|
||||
"loss": 0.7477,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 11.5,
|
||||
"learning_rate": 2.9567014198644542e-05,
|
||||
"loss": 0.716,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 12.0,
|
||||
"learning_rate": 2.9528747416929467e-05,
|
||||
"loss": 0.7351,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 12.5,
|
||||
"learning_rate": 2.9488887394336025e-05,
|
||||
"loss": 0.72,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 13.0,
|
||||
"learning_rate": 2.9447438501964873e-05,
|
||||
"loss": 0.714,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 13.5,
|
||||
"learning_rate": 2.9404405285154146e-05,
|
||||
"loss": 0.6994,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 14.0,
|
||||
"learning_rate": 2.9359792462981007e-05,
|
||||
"loss": 0.7064,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 14.5,
|
||||
"learning_rate": 2.9313604927744153e-05,
|
||||
"loss": 0.6807,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 15.0,
|
||||
"learning_rate": 2.9265847744427305e-05,
|
||||
"loss": 0.6969,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 15.5,
|
||||
"learning_rate": 2.9216526150143788e-05,
|
||||
"loss": 0.6836,
|
||||
"step": 62
|
||||
},
|
||||
{
|
||||
"epoch": 16.0,
|
||||
"learning_rate": 2.9165645553562215e-05,
|
||||
"loss": 0.6557,
|
||||
"step": 64
|
||||
},
|
||||
{
|
||||
"epoch": 16.5,
|
||||
"learning_rate": 2.9113211534313385e-05,
|
||||
"loss": 0.6619,
|
||||
"step": 66
|
||||
},
|
||||
{
|
||||
"epoch": 17.0,
|
||||
"learning_rate": 2.9059229842378373e-05,
|
||||
"loss": 0.6496,
|
||||
"step": 68
|
||||
},
|
||||
{
|
||||
"epoch": 17.5,
|
||||
"learning_rate": 2.9003706397458025e-05,
|
||||
"loss": 0.6268,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 18.0,
|
||||
"learning_rate": 2.894664728832377e-05,
|
||||
"loss": 0.6586,
|
||||
"step": 72
|
||||
},
|
||||
{
|
||||
"epoch": 18.5,
|
||||
"learning_rate": 2.8888058772149923e-05,
|
||||
"loss": 0.6197,
|
||||
"step": 74
|
||||
},
|
||||
{
|
||||
"epoch": 19.0,
|
||||
"learning_rate": 2.8827947273827508e-05,
|
||||
"loss": 0.638,
|
||||
"step": 76
|
||||
},
|
||||
{
|
||||
"epoch": 19.5,
|
||||
"learning_rate": 2.8766319385259717e-05,
|
||||
"loss": 0.6093,
|
||||
"step": 78
|
||||
},
|
||||
{
|
||||
"epoch": 20.0,
|
||||
"learning_rate": 2.8703181864639013e-05,
|
||||
"loss": 0.6089,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 20.5,
|
||||
"learning_rate": 2.863854163570603e-05,
|
||||
"loss": 0.6108,
|
||||
"step": 82
|
||||
},
|
||||
{
|
||||
"epoch": 21.0,
|
||||
"learning_rate": 2.8572405786990293e-05,
|
||||
"loss": 0.5776,
|
||||
"step": 84
|
||||
},
|
||||
{
|
||||
"epoch": 21.5,
|
||||
"learning_rate": 2.8504781571032906e-05,
|
||||
"loss": 0.5776,
|
||||
"step": 86
|
||||
},
|
||||
{
|
||||
"epoch": 22.0,
|
||||
"learning_rate": 2.8435676403591193e-05,
|
||||
"loss": 0.5997,
|
||||
"step": 88
|
||||
},
|
||||
{
|
||||
"epoch": 22.5,
|
||||
"learning_rate": 2.8365097862825516e-05,
|
||||
"loss": 0.5579,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 23.0,
|
||||
"learning_rate": 2.829305368846822e-05,
|
||||
"loss": 0.579,
|
||||
"step": 92
|
||||
},
|
||||
{
|
||||
"epoch": 23.5,
|
||||
"learning_rate": 2.821955178097488e-05,
|
||||
"loss": 0.5689,
|
||||
"step": 94
|
||||
},
|
||||
{
|
||||
"epoch": 24.0,
|
||||
"learning_rate": 2.8144600200657953e-05,
|
||||
"loss": 0.5278,
|
||||
"step": 96
|
||||
},
|
||||
{
|
||||
"epoch": 24.5,
|
||||
"learning_rate": 2.8068207166802843e-05,
|
||||
"loss": 0.55,
|
||||
"step": 98
|
||||
},
|
||||
{
|
||||
"epoch": 25.0,
|
||||
"learning_rate": 2.7990381056766583e-05,
|
||||
"loss": 0.516,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 25.5,
|
||||
"learning_rate": 2.7911130405059155e-05,
|
||||
"loss": 0.5342,
|
||||
"step": 102
|
||||
},
|
||||
{
|
||||
"epoch": 26.0,
|
||||
"learning_rate": 2.78304639024076e-05,
|
||||
"loss": 0.5021,
|
||||
"step": 104
|
||||
},
|
||||
{
|
||||
"epoch": 26.5,
|
||||
"learning_rate": 2.774839039480296e-05,
|
||||
"loss": 0.5042,
|
||||
"step": 106
|
||||
},
|
||||
{
|
||||
"epoch": 27.0,
|
||||
"learning_rate": 2.7664918882530227e-05,
|
||||
"loss": 0.4999,
|
||||
"step": 108
|
||||
}
|
||||
],
|
||||
"logging_steps": 2,
|
||||
"max_steps": 600,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 150,
|
||||
"save_steps": 500,
|
||||
"total_flos": 5145406010818560.0,
|
||||
"train_batch_size": 52,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
Binary file not shown.
|
|
@ -0,0 +1,204 @@
|
|||
---
|
||||
library_name: peft
|
||||
base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
|
||||
---
|
||||
|
||||
# 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 0.8.2
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
|
||||
"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": [
|
||||
"k_proj",
|
||||
"o_proj",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"up_proj",
|
||||
"down_proj"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"use_rslora": false
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -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
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
|
@ -0,0 +1,43 @@
|
|||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"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>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
|
|
@ -0,0 +1,357 @@
|
|||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 28.0,
|
||||
"eval_steps": 5,
|
||||
"global_step": 112,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"learning_rate": 2.9999177540482684e-05,
|
||||
"loss": 2.6428,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"learning_rate": 2.9996710252122685e-05,
|
||||
"loss": 2.1838,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 1.5,
|
||||
"learning_rate": 2.9992598405485974e-05,
|
||||
"loss": 1.8524,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"learning_rate": 2.9986842451482876e-05,
|
||||
"loss": 1.59,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 2.5,
|
||||
"learning_rate": 2.9979443021318607e-05,
|
||||
"loss": 1.4015,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"learning_rate": 2.9970400926424075e-05,
|
||||
"loss": 1.2128,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 3.5,
|
||||
"learning_rate": 2.995971715836687e-05,
|
||||
"loss": 1.1418,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"learning_rate": 2.9947392888742566e-05,
|
||||
"loss": 1.0389,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 4.5,
|
||||
"learning_rate": 2.9933429469046202e-05,
|
||||
"loss": 1.0268,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"learning_rate": 2.99178284305241e-05,
|
||||
"loss": 0.9734,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 5.5,
|
||||
"learning_rate": 2.9900591484005944e-05,
|
||||
"loss": 0.9755,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 6.0,
|
||||
"learning_rate": 2.988172051971717e-05,
|
||||
"loss": 0.9142,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 6.5,
|
||||
"learning_rate": 2.9861217607071655e-05,
|
||||
"loss": 0.8872,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 7.0,
|
||||
"learning_rate": 2.983908499444483e-05,
|
||||
"loss": 0.8633,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 7.5,
|
||||
"learning_rate": 2.981532510892707e-05,
|
||||
"loss": 0.8248,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 8.0,
|
||||
"learning_rate": 2.9789940556057574e-05,
|
||||
"loss": 0.8352,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 8.5,
|
||||
"learning_rate": 2.9762934119538628e-05,
|
||||
"loss": 0.8017,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 9.0,
|
||||
"learning_rate": 2.9734308760930333e-05,
|
||||
"loss": 0.7705,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 9.5,
|
||||
"learning_rate": 2.9704067619325828e-05,
|
||||
"loss": 0.7619,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 10.0,
|
||||
"learning_rate": 2.9672214011007087e-05,
|
||||
"loss": 0.7593,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 10.5,
|
||||
"learning_rate": 2.9638751429081213e-05,
|
||||
"loss": 0.7469,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 11.0,
|
||||
"learning_rate": 2.9603683543097406e-05,
|
||||
"loss": 0.7477,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 11.5,
|
||||
"learning_rate": 2.9567014198644542e-05,
|
||||
"loss": 0.716,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 12.0,
|
||||
"learning_rate": 2.9528747416929467e-05,
|
||||
"loss": 0.7351,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 12.5,
|
||||
"learning_rate": 2.9488887394336025e-05,
|
||||
"loss": 0.72,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 13.0,
|
||||
"learning_rate": 2.9447438501964873e-05,
|
||||
"loss": 0.714,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 13.5,
|
||||
"learning_rate": 2.9404405285154146e-05,
|
||||
"loss": 0.6994,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 14.0,
|
||||
"learning_rate": 2.9359792462981007e-05,
|
||||
"loss": 0.7064,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 14.5,
|
||||
"learning_rate": 2.9313604927744153e-05,
|
||||
"loss": 0.6807,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 15.0,
|
||||
"learning_rate": 2.9265847744427305e-05,
|
||||
"loss": 0.6969,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 15.5,
|
||||
"learning_rate": 2.9216526150143788e-05,
|
||||
"loss": 0.6836,
|
||||
"step": 62
|
||||
},
|
||||
{
|
||||
"epoch": 16.0,
|
||||
"learning_rate": 2.9165645553562215e-05,
|
||||
"loss": 0.6557,
|
||||
"step": 64
|
||||
},
|
||||
{
|
||||
"epoch": 16.5,
|
||||
"learning_rate": 2.9113211534313385e-05,
|
||||
"loss": 0.6619,
|
||||
"step": 66
|
||||
},
|
||||
{
|
||||
"epoch": 17.0,
|
||||
"learning_rate": 2.9059229842378373e-05,
|
||||
"loss": 0.6496,
|
||||
"step": 68
|
||||
},
|
||||
{
|
||||
"epoch": 17.5,
|
||||
"learning_rate": 2.9003706397458025e-05,
|
||||
"loss": 0.6268,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 18.0,
|
||||
"learning_rate": 2.894664728832377e-05,
|
||||
"loss": 0.6586,
|
||||
"step": 72
|
||||
},
|
||||
{
|
||||
"epoch": 18.5,
|
||||
"learning_rate": 2.8888058772149923e-05,
|
||||
"loss": 0.6197,
|
||||
"step": 74
|
||||
},
|
||||
{
|
||||
"epoch": 19.0,
|
||||
"learning_rate": 2.8827947273827508e-05,
|
||||
"loss": 0.638,
|
||||
"step": 76
|
||||
},
|
||||
{
|
||||
"epoch": 19.5,
|
||||
"learning_rate": 2.8766319385259717e-05,
|
||||
"loss": 0.6093,
|
||||
"step": 78
|
||||
},
|
||||
{
|
||||
"epoch": 20.0,
|
||||
"learning_rate": 2.8703181864639013e-05,
|
||||
"loss": 0.6089,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 20.5,
|
||||
"learning_rate": 2.863854163570603e-05,
|
||||
"loss": 0.6108,
|
||||
"step": 82
|
||||
},
|
||||
{
|
||||
"epoch": 21.0,
|
||||
"learning_rate": 2.8572405786990293e-05,
|
||||
"loss": 0.5776,
|
||||
"step": 84
|
||||
},
|
||||
{
|
||||
"epoch": 21.5,
|
||||
"learning_rate": 2.8504781571032906e-05,
|
||||
"loss": 0.5776,
|
||||
"step": 86
|
||||
},
|
||||
{
|
||||
"epoch": 22.0,
|
||||
"learning_rate": 2.8435676403591193e-05,
|
||||
"loss": 0.5997,
|
||||
"step": 88
|
||||
},
|
||||
{
|
||||
"epoch": 22.5,
|
||||
"learning_rate": 2.8365097862825516e-05,
|
||||
"loss": 0.5579,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 23.0,
|
||||
"learning_rate": 2.829305368846822e-05,
|
||||
"loss": 0.579,
|
||||
"step": 92
|
||||
},
|
||||
{
|
||||
"epoch": 23.5,
|
||||
"learning_rate": 2.821955178097488e-05,
|
||||
"loss": 0.5689,
|
||||
"step": 94
|
||||
},
|
||||
{
|
||||
"epoch": 24.0,
|
||||
"learning_rate": 2.8144600200657953e-05,
|
||||
"loss": 0.5278,
|
||||
"step": 96
|
||||
},
|
||||
{
|
||||
"epoch": 24.5,
|
||||
"learning_rate": 2.8068207166802843e-05,
|
||||
"loss": 0.55,
|
||||
"step": 98
|
||||
},
|
||||
{
|
||||
"epoch": 25.0,
|
||||
"learning_rate": 2.7990381056766583e-05,
|
||||
"loss": 0.516,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 25.5,
|
||||
"learning_rate": 2.7911130405059155e-05,
|
||||
"loss": 0.5342,
|
||||
"step": 102
|
||||
},
|
||||
{
|
||||
"epoch": 26.0,
|
||||
"learning_rate": 2.78304639024076e-05,
|
||||
"loss": 0.5021,
|
||||
"step": 104
|
||||
},
|
||||
{
|
||||
"epoch": 26.5,
|
||||
"learning_rate": 2.774839039480296e-05,
|
||||
"loss": 0.5042,
|
||||
"step": 106
|
||||
},
|
||||
{
|
||||
"epoch": 27.0,
|
||||
"learning_rate": 2.7664918882530227e-05,
|
||||
"loss": 0.4999,
|
||||
"step": 108
|
||||
},
|
||||
{
|
||||
"epoch": 27.5,
|
||||
"learning_rate": 2.7580058519181363e-05,
|
||||
"loss": 0.4847,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 28.0,
|
||||
"learning_rate": 2.7493818610651493e-05,
|
||||
"loss": 0.467,
|
||||
"step": 112
|
||||
}
|
||||
],
|
||||
"logging_steps": 2,
|
||||
"max_steps": 600,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 150,
|
||||
"save_steps": 500,
|
||||
"total_flos": 5335976603811840.0,
|
||||
"train_batch_size": 52,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
Binary file not shown.
|
|
@ -0,0 +1,204 @@
|
|||
---
|
||||
library_name: peft
|
||||
base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
|
||||
---
|
||||
|
||||
# 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 0.8.2
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
|
||||
"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": [
|
||||
"k_proj",
|
||||
"o_proj",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"up_proj",
|
||||
"down_proj"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"use_rslora": false
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -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
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
|
@ -0,0 +1,43 @@
|
|||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"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>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
|
|
@ -0,0 +1,369 @@
|
|||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 29.0,
|
||||
"eval_steps": 5,
|
||||
"global_step": 116,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"learning_rate": 2.9999177540482684e-05,
|
||||
"loss": 2.6428,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"learning_rate": 2.9996710252122685e-05,
|
||||
"loss": 2.1838,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 1.5,
|
||||
"learning_rate": 2.9992598405485974e-05,
|
||||
"loss": 1.8524,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"learning_rate": 2.9986842451482876e-05,
|
||||
"loss": 1.59,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 2.5,
|
||||
"learning_rate": 2.9979443021318607e-05,
|
||||
"loss": 1.4015,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"learning_rate": 2.9970400926424075e-05,
|
||||
"loss": 1.2128,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 3.5,
|
||||
"learning_rate": 2.995971715836687e-05,
|
||||
"loss": 1.1418,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"learning_rate": 2.9947392888742566e-05,
|
||||
"loss": 1.0389,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 4.5,
|
||||
"learning_rate": 2.9933429469046202e-05,
|
||||
"loss": 1.0268,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"learning_rate": 2.99178284305241e-05,
|
||||
"loss": 0.9734,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 5.5,
|
||||
"learning_rate": 2.9900591484005944e-05,
|
||||
"loss": 0.9755,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 6.0,
|
||||
"learning_rate": 2.988172051971717e-05,
|
||||
"loss": 0.9142,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 6.5,
|
||||
"learning_rate": 2.9861217607071655e-05,
|
||||
"loss": 0.8872,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 7.0,
|
||||
"learning_rate": 2.983908499444483e-05,
|
||||
"loss": 0.8633,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 7.5,
|
||||
"learning_rate": 2.981532510892707e-05,
|
||||
"loss": 0.8248,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 8.0,
|
||||
"learning_rate": 2.9789940556057574e-05,
|
||||
"loss": 0.8352,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 8.5,
|
||||
"learning_rate": 2.9762934119538628e-05,
|
||||
"loss": 0.8017,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 9.0,
|
||||
"learning_rate": 2.9734308760930333e-05,
|
||||
"loss": 0.7705,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 9.5,
|
||||
"learning_rate": 2.9704067619325828e-05,
|
||||
"loss": 0.7619,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 10.0,
|
||||
"learning_rate": 2.9672214011007087e-05,
|
||||
"loss": 0.7593,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 10.5,
|
||||
"learning_rate": 2.9638751429081213e-05,
|
||||
"loss": 0.7469,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 11.0,
|
||||
"learning_rate": 2.9603683543097406e-05,
|
||||
"loss": 0.7477,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 11.5,
|
||||
"learning_rate": 2.9567014198644542e-05,
|
||||
"loss": 0.716,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 12.0,
|
||||
"learning_rate": 2.9528747416929467e-05,
|
||||
"loss": 0.7351,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 12.5,
|
||||
"learning_rate": 2.9488887394336025e-05,
|
||||
"loss": 0.72,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 13.0,
|
||||
"learning_rate": 2.9447438501964873e-05,
|
||||
"loss": 0.714,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 13.5,
|
||||
"learning_rate": 2.9404405285154146e-05,
|
||||
"loss": 0.6994,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 14.0,
|
||||
"learning_rate": 2.9359792462981007e-05,
|
||||
"loss": 0.7064,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 14.5,
|
||||
"learning_rate": 2.9313604927744153e-05,
|
||||
"loss": 0.6807,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 15.0,
|
||||
"learning_rate": 2.9265847744427305e-05,
|
||||
"loss": 0.6969,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 15.5,
|
||||
"learning_rate": 2.9216526150143788e-05,
|
||||
"loss": 0.6836,
|
||||
"step": 62
|
||||
},
|
||||
{
|
||||
"epoch": 16.0,
|
||||
"learning_rate": 2.9165645553562215e-05,
|
||||
"loss": 0.6557,
|
||||
"step": 64
|
||||
},
|
||||
{
|
||||
"epoch": 16.5,
|
||||
"learning_rate": 2.9113211534313385e-05,
|
||||
"loss": 0.6619,
|
||||
"step": 66
|
||||
},
|
||||
{
|
||||
"epoch": 17.0,
|
||||
"learning_rate": 2.9059229842378373e-05,
|
||||
"loss": 0.6496,
|
||||
"step": 68
|
||||
},
|
||||
{
|
||||
"epoch": 17.5,
|
||||
"learning_rate": 2.9003706397458025e-05,
|
||||
"loss": 0.6268,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 18.0,
|
||||
"learning_rate": 2.894664728832377e-05,
|
||||
"loss": 0.6586,
|
||||
"step": 72
|
||||
},
|
||||
{
|
||||
"epoch": 18.5,
|
||||
"learning_rate": 2.8888058772149923e-05,
|
||||
"loss": 0.6197,
|
||||
"step": 74
|
||||
},
|
||||
{
|
||||
"epoch": 19.0,
|
||||
"learning_rate": 2.8827947273827508e-05,
|
||||
"loss": 0.638,
|
||||
"step": 76
|
||||
},
|
||||
{
|
||||
"epoch": 19.5,
|
||||
"learning_rate": 2.8766319385259717e-05,
|
||||
"loss": 0.6093,
|
||||
"step": 78
|
||||
},
|
||||
{
|
||||
"epoch": 20.0,
|
||||
"learning_rate": 2.8703181864639013e-05,
|
||||
"loss": 0.6089,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 20.5,
|
||||
"learning_rate": 2.863854163570603e-05,
|
||||
"loss": 0.6108,
|
||||
"step": 82
|
||||
},
|
||||
{
|
||||
"epoch": 21.0,
|
||||
"learning_rate": 2.8572405786990293e-05,
|
||||
"loss": 0.5776,
|
||||
"step": 84
|
||||
},
|
||||
{
|
||||
"epoch": 21.5,
|
||||
"learning_rate": 2.8504781571032906e-05,
|
||||
"loss": 0.5776,
|
||||
"step": 86
|
||||
},
|
||||
{
|
||||
"epoch": 22.0,
|
||||
"learning_rate": 2.8435676403591193e-05,
|
||||
"loss": 0.5997,
|
||||
"step": 88
|
||||
},
|
||||
{
|
||||
"epoch": 22.5,
|
||||
"learning_rate": 2.8365097862825516e-05,
|
||||
"loss": 0.5579,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 23.0,
|
||||
"learning_rate": 2.829305368846822e-05,
|
||||
"loss": 0.579,
|
||||
"step": 92
|
||||
},
|
||||
{
|
||||
"epoch": 23.5,
|
||||
"learning_rate": 2.821955178097488e-05,
|
||||
"loss": 0.5689,
|
||||
"step": 94
|
||||
},
|
||||
{
|
||||
"epoch": 24.0,
|
||||
"learning_rate": 2.8144600200657953e-05,
|
||||
"loss": 0.5278,
|
||||
"step": 96
|
||||
},
|
||||
{
|
||||
"epoch": 24.5,
|
||||
"learning_rate": 2.8068207166802843e-05,
|
||||
"loss": 0.55,
|
||||
"step": 98
|
||||
},
|
||||
{
|
||||
"epoch": 25.0,
|
||||
"learning_rate": 2.7990381056766583e-05,
|
||||
"loss": 0.516,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 25.5,
|
||||
"learning_rate": 2.7911130405059155e-05,
|
||||
"loss": 0.5342,
|
||||
"step": 102
|
||||
},
|
||||
{
|
||||
"epoch": 26.0,
|
||||
"learning_rate": 2.78304639024076e-05,
|
||||
"loss": 0.5021,
|
||||
"step": 104
|
||||
},
|
||||
{
|
||||
"epoch": 26.5,
|
||||
"learning_rate": 2.774839039480296e-05,
|
||||
"loss": 0.5042,
|
||||
"step": 106
|
||||
},
|
||||
{
|
||||
"epoch": 27.0,
|
||||
"learning_rate": 2.7664918882530227e-05,
|
||||
"loss": 0.4999,
|
||||
"step": 108
|
||||
},
|
||||
{
|
||||
"epoch": 27.5,
|
||||
"learning_rate": 2.7580058519181363e-05,
|
||||
"loss": 0.4847,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 28.0,
|
||||
"learning_rate": 2.7493818610651493e-05,
|
||||
"loss": 0.467,
|
||||
"step": 112
|
||||
},
|
||||
{
|
||||
"epoch": 28.5,
|
||||
"learning_rate": 2.7406208614118427e-05,
|
||||
"loss": 0.462,
|
||||
"step": 114
|
||||
},
|
||||
{
|
||||
"epoch": 29.0,
|
||||
"learning_rate": 2.731723813700556e-05,
|
||||
"loss": 0.4576,
|
||||
"step": 116
|
||||
}
|
||||
],
|
||||
"logging_steps": 2,
|
||||
"max_steps": 600,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 150,
|
||||
"save_steps": 500,
|
||||
"total_flos": 5526547196805120.0,
|
||||
"train_batch_size": 52,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
Binary file not shown.
|
|
@ -0,0 +1,204 @@
|
|||
---
|
||||
library_name: peft
|
||||
base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
|
||||
---
|
||||
|
||||
# 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 0.8.2
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
|
||||
"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": [
|
||||
"k_proj",
|
||||
"o_proj",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"up_proj",
|
||||
"down_proj"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"use_rslora": false
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -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
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
|
@ -0,0 +1,43 @@
|
|||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"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>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
|
|
@ -0,0 +1,57 @@
|
|||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 3.0,
|
||||
"eval_steps": 5,
|
||||
"global_step": 12,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"learning_rate": 2.9999177540482684e-05,
|
||||
"loss": 2.6428,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"learning_rate": 2.9996710252122685e-05,
|
||||
"loss": 2.1838,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 1.5,
|
||||
"learning_rate": 2.9992598405485974e-05,
|
||||
"loss": 1.8524,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"learning_rate": 2.9986842451482876e-05,
|
||||
"loss": 1.59,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 2.5,
|
||||
"learning_rate": 2.9979443021318607e-05,
|
||||
"loss": 1.4015,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"learning_rate": 2.9970400926424075e-05,
|
||||
"loss": 1.2128,
|
||||
"step": 12
|
||||
}
|
||||
],
|
||||
"logging_steps": 2,
|
||||
"max_steps": 600,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 150,
|
||||
"save_steps": 500,
|
||||
"total_flos": 571711778979840.0,
|
||||
"train_batch_size": 52,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
Binary file not shown.
|
|
@ -0,0 +1,204 @@
|
|||
---
|
||||
library_name: peft
|
||||
base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
|
||||
---
|
||||
|
||||
# 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 0.8.2
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
|
||||
"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": [
|
||||
"k_proj",
|
||||
"o_proj",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"up_proj",
|
||||
"down_proj"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"use_rslora": false
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -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
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
|
@ -0,0 +1,43 @@
|
|||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"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>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
|
|
@ -0,0 +1,381 @@
|
|||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 30.0,
|
||||
"eval_steps": 5,
|
||||
"global_step": 120,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"learning_rate": 2.9999177540482684e-05,
|
||||
"loss": 2.6428,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"learning_rate": 2.9996710252122685e-05,
|
||||
"loss": 2.1838,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 1.5,
|
||||
"learning_rate": 2.9992598405485974e-05,
|
||||
"loss": 1.8524,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"learning_rate": 2.9986842451482876e-05,
|
||||
"loss": 1.59,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 2.5,
|
||||
"learning_rate": 2.9979443021318607e-05,
|
||||
"loss": 1.4015,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"learning_rate": 2.9970400926424075e-05,
|
||||
"loss": 1.2128,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 3.5,
|
||||
"learning_rate": 2.995971715836687e-05,
|
||||
"loss": 1.1418,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"learning_rate": 2.9947392888742566e-05,
|
||||
"loss": 1.0389,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 4.5,
|
||||
"learning_rate": 2.9933429469046202e-05,
|
||||
"loss": 1.0268,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"learning_rate": 2.99178284305241e-05,
|
||||
"loss": 0.9734,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 5.5,
|
||||
"learning_rate": 2.9900591484005944e-05,
|
||||
"loss": 0.9755,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 6.0,
|
||||
"learning_rate": 2.988172051971717e-05,
|
||||
"loss": 0.9142,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 6.5,
|
||||
"learning_rate": 2.9861217607071655e-05,
|
||||
"loss": 0.8872,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 7.0,
|
||||
"learning_rate": 2.983908499444483e-05,
|
||||
"loss": 0.8633,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 7.5,
|
||||
"learning_rate": 2.981532510892707e-05,
|
||||
"loss": 0.8248,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 8.0,
|
||||
"learning_rate": 2.9789940556057574e-05,
|
||||
"loss": 0.8352,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 8.5,
|
||||
"learning_rate": 2.9762934119538628e-05,
|
||||
"loss": 0.8017,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 9.0,
|
||||
"learning_rate": 2.9734308760930333e-05,
|
||||
"loss": 0.7705,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 9.5,
|
||||
"learning_rate": 2.9704067619325828e-05,
|
||||
"loss": 0.7619,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 10.0,
|
||||
"learning_rate": 2.9672214011007087e-05,
|
||||
"loss": 0.7593,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 10.5,
|
||||
"learning_rate": 2.9638751429081213e-05,
|
||||
"loss": 0.7469,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 11.0,
|
||||
"learning_rate": 2.9603683543097406e-05,
|
||||
"loss": 0.7477,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 11.5,
|
||||
"learning_rate": 2.9567014198644542e-05,
|
||||
"loss": 0.716,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 12.0,
|
||||
"learning_rate": 2.9528747416929467e-05,
|
||||
"loss": 0.7351,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 12.5,
|
||||
"learning_rate": 2.9488887394336025e-05,
|
||||
"loss": 0.72,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 13.0,
|
||||
"learning_rate": 2.9447438501964873e-05,
|
||||
"loss": 0.714,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 13.5,
|
||||
"learning_rate": 2.9404405285154146e-05,
|
||||
"loss": 0.6994,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 14.0,
|
||||
"learning_rate": 2.9359792462981007e-05,
|
||||
"loss": 0.7064,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 14.5,
|
||||
"learning_rate": 2.9313604927744153e-05,
|
||||
"loss": 0.6807,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 15.0,
|
||||
"learning_rate": 2.9265847744427305e-05,
|
||||
"loss": 0.6969,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 15.5,
|
||||
"learning_rate": 2.9216526150143788e-05,
|
||||
"loss": 0.6836,
|
||||
"step": 62
|
||||
},
|
||||
{
|
||||
"epoch": 16.0,
|
||||
"learning_rate": 2.9165645553562215e-05,
|
||||
"loss": 0.6557,
|
||||
"step": 64
|
||||
},
|
||||
{
|
||||
"epoch": 16.5,
|
||||
"learning_rate": 2.9113211534313385e-05,
|
||||
"loss": 0.6619,
|
||||
"step": 66
|
||||
},
|
||||
{
|
||||
"epoch": 17.0,
|
||||
"learning_rate": 2.9059229842378373e-05,
|
||||
"loss": 0.6496,
|
||||
"step": 68
|
||||
},
|
||||
{
|
||||
"epoch": 17.5,
|
||||
"learning_rate": 2.9003706397458025e-05,
|
||||
"loss": 0.6268,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 18.0,
|
||||
"learning_rate": 2.894664728832377e-05,
|
||||
"loss": 0.6586,
|
||||
"step": 72
|
||||
},
|
||||
{
|
||||
"epoch": 18.5,
|
||||
"learning_rate": 2.8888058772149923e-05,
|
||||
"loss": 0.6197,
|
||||
"step": 74
|
||||
},
|
||||
{
|
||||
"epoch": 19.0,
|
||||
"learning_rate": 2.8827947273827508e-05,
|
||||
"loss": 0.638,
|
||||
"step": 76
|
||||
},
|
||||
{
|
||||
"epoch": 19.5,
|
||||
"learning_rate": 2.8766319385259717e-05,
|
||||
"loss": 0.6093,
|
||||
"step": 78
|
||||
},
|
||||
{
|
||||
"epoch": 20.0,
|
||||
"learning_rate": 2.8703181864639013e-05,
|
||||
"loss": 0.6089,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 20.5,
|
||||
"learning_rate": 2.863854163570603e-05,
|
||||
"loss": 0.6108,
|
||||
"step": 82
|
||||
},
|
||||
{
|
||||
"epoch": 21.0,
|
||||
"learning_rate": 2.8572405786990293e-05,
|
||||
"loss": 0.5776,
|
||||
"step": 84
|
||||
},
|
||||
{
|
||||
"epoch": 21.5,
|
||||
"learning_rate": 2.8504781571032906e-05,
|
||||
"loss": 0.5776,
|
||||
"step": 86
|
||||
},
|
||||
{
|
||||
"epoch": 22.0,
|
||||
"learning_rate": 2.8435676403591193e-05,
|
||||
"loss": 0.5997,
|
||||
"step": 88
|
||||
},
|
||||
{
|
||||
"epoch": 22.5,
|
||||
"learning_rate": 2.8365097862825516e-05,
|
||||
"loss": 0.5579,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 23.0,
|
||||
"learning_rate": 2.829305368846822e-05,
|
||||
"loss": 0.579,
|
||||
"step": 92
|
||||
},
|
||||
{
|
||||
"epoch": 23.5,
|
||||
"learning_rate": 2.821955178097488e-05,
|
||||
"loss": 0.5689,
|
||||
"step": 94
|
||||
},
|
||||
{
|
||||
"epoch": 24.0,
|
||||
"learning_rate": 2.8144600200657953e-05,
|
||||
"loss": 0.5278,
|
||||
"step": 96
|
||||
},
|
||||
{
|
||||
"epoch": 24.5,
|
||||
"learning_rate": 2.8068207166802843e-05,
|
||||
"loss": 0.55,
|
||||
"step": 98
|
||||
},
|
||||
{
|
||||
"epoch": 25.0,
|
||||
"learning_rate": 2.7990381056766583e-05,
|
||||
"loss": 0.516,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 25.5,
|
||||
"learning_rate": 2.7911130405059155e-05,
|
||||
"loss": 0.5342,
|
||||
"step": 102
|
||||
},
|
||||
{
|
||||
"epoch": 26.0,
|
||||
"learning_rate": 2.78304639024076e-05,
|
||||
"loss": 0.5021,
|
||||
"step": 104
|
||||
},
|
||||
{
|
||||
"epoch": 26.5,
|
||||
"learning_rate": 2.774839039480296e-05,
|
||||
"loss": 0.5042,
|
||||
"step": 106
|
||||
},
|
||||
{
|
||||
"epoch": 27.0,
|
||||
"learning_rate": 2.7664918882530227e-05,
|
||||
"loss": 0.4999,
|
||||
"step": 108
|
||||
},
|
||||
{
|
||||
"epoch": 27.5,
|
||||
"learning_rate": 2.7580058519181363e-05,
|
||||
"loss": 0.4847,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 28.0,
|
||||
"learning_rate": 2.7493818610651493e-05,
|
||||
"loss": 0.467,
|
||||
"step": 112
|
||||
},
|
||||
{
|
||||
"epoch": 28.5,
|
||||
"learning_rate": 2.7406208614118427e-05,
|
||||
"loss": 0.462,
|
||||
"step": 114
|
||||
},
|
||||
{
|
||||
"epoch": 29.0,
|
||||
"learning_rate": 2.731723813700556e-05,
|
||||
"loss": 0.4576,
|
||||
"step": 116
|
||||
},
|
||||
{
|
||||
"epoch": 29.5,
|
||||
"learning_rate": 2.7226916935928312e-05,
|
||||
"loss": 0.45,
|
||||
"step": 118
|
||||
},
|
||||
{
|
||||
"epoch": 30.0,
|
||||
"learning_rate": 2.7135254915624213e-05,
|
||||
"loss": 0.4045,
|
||||
"step": 120
|
||||
}
|
||||
],
|
||||
"logging_steps": 2,
|
||||
"max_steps": 600,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 150,
|
||||
"save_steps": 500,
|
||||
"total_flos": 5717117789798400.0,
|
||||
"train_batch_size": 52,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
Binary file not shown.
|
|
@ -0,0 +1,204 @@
|
|||
---
|
||||
library_name: peft
|
||||
base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
|
||||
---
|
||||
|
||||
# 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 0.8.2
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
|
||||
"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": [
|
||||
"k_proj",
|
||||
"o_proj",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"up_proj",
|
||||
"down_proj"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"use_rslora": false
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -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
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
|
@ -0,0 +1,43 @@
|
|||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"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>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
|
|
@ -0,0 +1,393 @@
|
|||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 31.0,
|
||||
"eval_steps": 5,
|
||||
"global_step": 124,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"learning_rate": 2.9999177540482684e-05,
|
||||
"loss": 2.6428,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"learning_rate": 2.9996710252122685e-05,
|
||||
"loss": 2.1838,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 1.5,
|
||||
"learning_rate": 2.9992598405485974e-05,
|
||||
"loss": 1.8524,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"learning_rate": 2.9986842451482876e-05,
|
||||
"loss": 1.59,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 2.5,
|
||||
"learning_rate": 2.9979443021318607e-05,
|
||||
"loss": 1.4015,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"learning_rate": 2.9970400926424075e-05,
|
||||
"loss": 1.2128,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 3.5,
|
||||
"learning_rate": 2.995971715836687e-05,
|
||||
"loss": 1.1418,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"learning_rate": 2.9947392888742566e-05,
|
||||
"loss": 1.0389,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 4.5,
|
||||
"learning_rate": 2.9933429469046202e-05,
|
||||
"loss": 1.0268,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"learning_rate": 2.99178284305241e-05,
|
||||
"loss": 0.9734,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 5.5,
|
||||
"learning_rate": 2.9900591484005944e-05,
|
||||
"loss": 0.9755,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 6.0,
|
||||
"learning_rate": 2.988172051971717e-05,
|
||||
"loss": 0.9142,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 6.5,
|
||||
"learning_rate": 2.9861217607071655e-05,
|
||||
"loss": 0.8872,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 7.0,
|
||||
"learning_rate": 2.983908499444483e-05,
|
||||
"loss": 0.8633,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 7.5,
|
||||
"learning_rate": 2.981532510892707e-05,
|
||||
"loss": 0.8248,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 8.0,
|
||||
"learning_rate": 2.9789940556057574e-05,
|
||||
"loss": 0.8352,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 8.5,
|
||||
"learning_rate": 2.9762934119538628e-05,
|
||||
"loss": 0.8017,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 9.0,
|
||||
"learning_rate": 2.9734308760930333e-05,
|
||||
"loss": 0.7705,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 9.5,
|
||||
"learning_rate": 2.9704067619325828e-05,
|
||||
"loss": 0.7619,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 10.0,
|
||||
"learning_rate": 2.9672214011007087e-05,
|
||||
"loss": 0.7593,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 10.5,
|
||||
"learning_rate": 2.9638751429081213e-05,
|
||||
"loss": 0.7469,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 11.0,
|
||||
"learning_rate": 2.9603683543097406e-05,
|
||||
"loss": 0.7477,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 11.5,
|
||||
"learning_rate": 2.9567014198644542e-05,
|
||||
"loss": 0.716,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 12.0,
|
||||
"learning_rate": 2.9528747416929467e-05,
|
||||
"loss": 0.7351,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 12.5,
|
||||
"learning_rate": 2.9488887394336025e-05,
|
||||
"loss": 0.72,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 13.0,
|
||||
"learning_rate": 2.9447438501964873e-05,
|
||||
"loss": 0.714,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 13.5,
|
||||
"learning_rate": 2.9404405285154146e-05,
|
||||
"loss": 0.6994,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 14.0,
|
||||
"learning_rate": 2.9359792462981007e-05,
|
||||
"loss": 0.7064,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 14.5,
|
||||
"learning_rate": 2.9313604927744153e-05,
|
||||
"loss": 0.6807,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 15.0,
|
||||
"learning_rate": 2.9265847744427305e-05,
|
||||
"loss": 0.6969,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 15.5,
|
||||
"learning_rate": 2.9216526150143788e-05,
|
||||
"loss": 0.6836,
|
||||
"step": 62
|
||||
},
|
||||
{
|
||||
"epoch": 16.0,
|
||||
"learning_rate": 2.9165645553562215e-05,
|
||||
"loss": 0.6557,
|
||||
"step": 64
|
||||
},
|
||||
{
|
||||
"epoch": 16.5,
|
||||
"learning_rate": 2.9113211534313385e-05,
|
||||
"loss": 0.6619,
|
||||
"step": 66
|
||||
},
|
||||
{
|
||||
"epoch": 17.0,
|
||||
"learning_rate": 2.9059229842378373e-05,
|
||||
"loss": 0.6496,
|
||||
"step": 68
|
||||
},
|
||||
{
|
||||
"epoch": 17.5,
|
||||
"learning_rate": 2.9003706397458025e-05,
|
||||
"loss": 0.6268,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 18.0,
|
||||
"learning_rate": 2.894664728832377e-05,
|
||||
"loss": 0.6586,
|
||||
"step": 72
|
||||
},
|
||||
{
|
||||
"epoch": 18.5,
|
||||
"learning_rate": 2.8888058772149923e-05,
|
||||
"loss": 0.6197,
|
||||
"step": 74
|
||||
},
|
||||
{
|
||||
"epoch": 19.0,
|
||||
"learning_rate": 2.8827947273827508e-05,
|
||||
"loss": 0.638,
|
||||
"step": 76
|
||||
},
|
||||
{
|
||||
"epoch": 19.5,
|
||||
"learning_rate": 2.8766319385259717e-05,
|
||||
"loss": 0.6093,
|
||||
"step": 78
|
||||
},
|
||||
{
|
||||
"epoch": 20.0,
|
||||
"learning_rate": 2.8703181864639013e-05,
|
||||
"loss": 0.6089,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 20.5,
|
||||
"learning_rate": 2.863854163570603e-05,
|
||||
"loss": 0.6108,
|
||||
"step": 82
|
||||
},
|
||||
{
|
||||
"epoch": 21.0,
|
||||
"learning_rate": 2.8572405786990293e-05,
|
||||
"loss": 0.5776,
|
||||
"step": 84
|
||||
},
|
||||
{
|
||||
"epoch": 21.5,
|
||||
"learning_rate": 2.8504781571032906e-05,
|
||||
"loss": 0.5776,
|
||||
"step": 86
|
||||
},
|
||||
{
|
||||
"epoch": 22.0,
|
||||
"learning_rate": 2.8435676403591193e-05,
|
||||
"loss": 0.5997,
|
||||
"step": 88
|
||||
},
|
||||
{
|
||||
"epoch": 22.5,
|
||||
"learning_rate": 2.8365097862825516e-05,
|
||||
"loss": 0.5579,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 23.0,
|
||||
"learning_rate": 2.829305368846822e-05,
|
||||
"loss": 0.579,
|
||||
"step": 92
|
||||
},
|
||||
{
|
||||
"epoch": 23.5,
|
||||
"learning_rate": 2.821955178097488e-05,
|
||||
"loss": 0.5689,
|
||||
"step": 94
|
||||
},
|
||||
{
|
||||
"epoch": 24.0,
|
||||
"learning_rate": 2.8144600200657953e-05,
|
||||
"loss": 0.5278,
|
||||
"step": 96
|
||||
},
|
||||
{
|
||||
"epoch": 24.5,
|
||||
"learning_rate": 2.8068207166802843e-05,
|
||||
"loss": 0.55,
|
||||
"step": 98
|
||||
},
|
||||
{
|
||||
"epoch": 25.0,
|
||||
"learning_rate": 2.7990381056766583e-05,
|
||||
"loss": 0.516,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 25.5,
|
||||
"learning_rate": 2.7911130405059155e-05,
|
||||
"loss": 0.5342,
|
||||
"step": 102
|
||||
},
|
||||
{
|
||||
"epoch": 26.0,
|
||||
"learning_rate": 2.78304639024076e-05,
|
||||
"loss": 0.5021,
|
||||
"step": 104
|
||||
},
|
||||
{
|
||||
"epoch": 26.5,
|
||||
"learning_rate": 2.774839039480296e-05,
|
||||
"loss": 0.5042,
|
||||
"step": 106
|
||||
},
|
||||
{
|
||||
"epoch": 27.0,
|
||||
"learning_rate": 2.7664918882530227e-05,
|
||||
"loss": 0.4999,
|
||||
"step": 108
|
||||
},
|
||||
{
|
||||
"epoch": 27.5,
|
||||
"learning_rate": 2.7580058519181363e-05,
|
||||
"loss": 0.4847,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 28.0,
|
||||
"learning_rate": 2.7493818610651493e-05,
|
||||
"loss": 0.467,
|
||||
"step": 112
|
||||
},
|
||||
{
|
||||
"epoch": 28.5,
|
||||
"learning_rate": 2.7406208614118427e-05,
|
||||
"loss": 0.462,
|
||||
"step": 114
|
||||
},
|
||||
{
|
||||
"epoch": 29.0,
|
||||
"learning_rate": 2.731723813700556e-05,
|
||||
"loss": 0.4576,
|
||||
"step": 116
|
||||
},
|
||||
{
|
||||
"epoch": 29.5,
|
||||
"learning_rate": 2.7226916935928312e-05,
|
||||
"loss": 0.45,
|
||||
"step": 118
|
||||
},
|
||||
{
|
||||
"epoch": 30.0,
|
||||
"learning_rate": 2.7135254915624213e-05,
|
||||
"loss": 0.4045,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 30.5,
|
||||
"learning_rate": 2.7042262127866718e-05,
|
||||
"loss": 0.424,
|
||||
"step": 122
|
||||
},
|
||||
{
|
||||
"epoch": 31.0,
|
||||
"learning_rate": 2.6947948770362945e-05,
|
||||
"loss": 0.3926,
|
||||
"step": 124
|
||||
}
|
||||
],
|
||||
"logging_steps": 2,
|
||||
"max_steps": 600,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 150,
|
||||
"save_steps": 500,
|
||||
"total_flos": 5907688382791680.0,
|
||||
"train_batch_size": 52,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
Binary file not shown.
|
|
@ -0,0 +1,204 @@
|
|||
---
|
||||
library_name: peft
|
||||
base_model: /home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ
|
||||
---
|
||||
|
||||
# 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 0.8.2
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "/home/paulius/Data/sync/RND/ncn/Mistral-7B-Instruct-v0.2-GPTQ",
|
||||
"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": [
|
||||
"k_proj",
|
||||
"o_proj",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"v_proj",
|
||||
"up_proj",
|
||||
"down_proj"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"use_rslora": false
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue