Upload folder using huggingface_hub

README.md

@@ -1,88 +1,100 @@
 ---
-license: other
-library_name: peft
+license: mit
+library_name: "trl"
 tags:
-- trl
-- sft
-- generated_from_trainer
+- SFT
+- WeniGPT
 base_model: meta-llama/Meta-Llama-3-8B
-datasets:
-- generator
 model-index:
-- name: WeniGPT-Agents-Llama3-1.0.8-SFT
+- name: Weni/WeniGPT-Agents-Llama3-1.0.8-SFT
   results: []
+language: ['pt']
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# Weni/WeniGPT-Agents-Llama3-1.0.8-SFT
 
-# WeniGPT-Agents-Llama3-1.0.8-SFT
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B] on the dataset Weni/wenigpt-agent-1.4.0 with the SFT trainer. It is part of the WeniGPT project for [Weni](https://weni.ai/).
+Description: Experiment with SFT and Llama3 and updates in requirements
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3744
+{'eval_loss': 1.3743919134140015, 'eval_runtime': 10.9572, 'eval_samples_per_second': 4.198, 'eval_steps_per_second': 4.198, 'epoch': 2.9932885906040267}
 
-## Model description
+## Intended uses & limitations
 
-More information needed
+This model has not been trained to avoid specific intructions. 
 
-## Intended uses & limitations
+## Training procedure
 
-More information needed
+Finetuning was done on the model meta-llama/Meta-Llama-3-8B with the following prompt:
 
-## Training and evaluation data
+```
+---------------------
+System_prompt:
+Agora você se chama {name}, você é {occupation} e seu objetivo é {chatbot_goal}. O adjetivo que mais define a sua personalidade é {adjective} e você se comporta da seguinte forma:
+{instructions_formatted}
 
-More information needed
+{context_statement}
+
+Lista de requisitos:
+ - Responda de forma natural, mas nunca fale sobre um assunto fora do contexto.
+ - Nunca traga informações do seu próprio conhecimento.
+ - Repito é crucial que você responda usando apenas informações do contexto.
+ - Nunca mencione o contexto fornecido.
+ - Nunca mencione a pergunta fornecida.
+ - Gere a resposta mais útil possível para a pergunta usando informações do conexto acima.
+ - Nunca elabore sobre o porque e como você fez a tarefa, apenas responda.
+
+
+---------------------
+Question:
+{question}
 
-## Training procedure
+
+---------------------
+Response:
+{answer}
+
+
+---------------------
+
+```
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 1
-- eval_batch_size: 1
-- seed: 42
+- per_device_train_batch_size: 1
+- per_device_eval_batch_size: 1
 - gradient_accumulation_steps: 2
+- num_gpus: 1
 - total_train_batch_size: 2
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.03
-- training_steps: 669
-- mixed_precision_training: Native AMP
+- optimizer: AdamW
+- lr_scheduler_type: cosine
+- num_steps: 669
+- quantization_type: bitsandbytes
+- LoRA: ("\n  - bits: 4\n  - use_exllama: True\n  - device_map: auto\n  - use_cache: False\n  - lora_r: 8\n  - lora_alpha: 16\n  - lora_dropout: 0.05\n  - bias: none\n  - target_modules: ['v_proj', 'q_proj']\n  - task_type: CAUSAL_LM",)
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 1.7877        | 0.1342 | 30   | 1.7082          |
-| 1.3675        | 0.2685 | 60   | 1.4539          |
-| 1.3782        | 0.4027 | 90   | 1.4236          |
-| 1.3884        | 0.5369 | 120  | 1.3938          |
-| 1.3448        | 0.6711 | 150  | 1.3899          |
-| 1.3357        | 0.8054 | 180  | 1.3870          |
-| 1.2788        | 0.9396 | 210  | 1.3739          |
-| 1.2396        | 1.0738 | 240  | 1.3778          |
-| 1.2949        | 1.2081 | 270  | 1.3809          |
-| 1.337         | 1.3423 | 300  | 1.3792          |
-| 1.3266        | 1.4765 | 330  | 1.3775          |
-| 1.2735        | 1.6107 | 360  | 1.3744          |
-| 1.2809        | 1.7450 | 390  | 1.3752          |
-| 1.2383        | 1.8792 | 420  | 1.3775          |
-| 1.2116        | 2.0134 | 450  | 1.3859          |
-| 1.0153        | 2.1477 | 480  | 1.3926          |
-| 1.2039        | 2.2819 | 510  | 1.3884          |
-| 1.2451        | 2.4161 | 540  | 1.3886          |
-| 1.2311        | 2.5503 | 570  | 1.3921          |
-| 1.1299        | 2.6846 | 600  | 1.3941          |
-| 1.2163        | 2.8188 | 630  | 1.3913          |
-| 1.0719        | 2.9530 | 660  | 1.3907          |
-
-
 ### Framework versions
 
-- PEFT 0.10.0
-- Transformers 4.40.0
-- Pytorch 2.1.0+cu118
-- Datasets 2.18.0
-- Tokenizers 0.19.1
+- transformers==4.40.0
+- datasets==2.18.0
+- peft==0.10.0
+- safetensors==0.4.2
+- evaluate==0.4.1
+- bitsandbytes==0.43
+- huggingface_hub==0.22.2
+- seqeval==1.2.2
+- auto-gptq==0.7.1
+- gpustat==1.1.1
+- deepspeed==0.14.0
+- wandb==0.16.6
+- trl==0.8.1
+- accelerate==0.29.3
+- coloredlogs==15.0.1
+- traitlets==5.14.2
+- git+https://github.com/casper-hansen/AutoAWQ.git
+
+### Hardware
+- Cloud provided: runpod.io