Upload folder using huggingface_hub

README.md

@@ -1,82 +1,90 @@
 ---
-library_name: peft
+license: mit
+library_name: "trl"
 tags:
-- trl
-- dpo
 - DPO
 - WeniGPT
-- generated_from_trainer
 base_model: Weni/WeniGPT-Agents-Mistral-1.0.0-SFT-merged
 model-index:
-- name: WeniGPT-Agents-Mistral-1.0.0-SFT-1.0.21-DPO
+- name: Weni/WeniGPT-Agents-Mistral-1.0.0-SFT-1.0.21-DPO
   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-Mistral-1.0.0-SFT-1.0.21-DPO
 
-# WeniGPT-Agents-Mistral-1.0.0-SFT-1.0.21-DPO
+This model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.0-SFT-merged] on the dataset Weni/wenigpt-agent-dpo-1.0.0 with the DPO trainer. It is part of the WeniGPT project for [Weni](https://weni.ai/).
+Description: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT
 
-This model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.0-SFT-merged](https://huggingface.co/Weni/WeniGPT-Agents-Mistral-1.0.0-SFT-merged) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0520
-- Rewards/chosen: 2.3217
-- Rewards/rejected: -1.5051
-- Rewards/accuracies: 1.0
-- Rewards/margins: 3.8268
-- Logps/rejected: -167.9981
-- Logps/chosen: -107.6077
-- Logits/rejected: -1.7717
-- Logits/chosen: -1.7573
+{'eval_loss': 0.052017249166965485, 'eval_runtime': 9.7177, 'eval_samples_per_second': 2.881, 'eval_steps_per_second': 0.72, 'eval_rewards/chosen': 2.3217406272888184, 'eval_rewards/rejected': -1.5050735473632812, 'eval_rewards/accuracies': 1.0, 'eval_rewards/margins': 3.8268144130706787, 'eval_logps/rejected': -167.99813842773438, 'eval_logps/chosen': -107.60765075683594, 'eval_logits/rejected': -1.7717255353927612, 'eval_logits/chosen': -1.7573397159576416, 'epoch': 5.806451612903226}
 
-## 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 Weni/WeniGPT-Agents-Mistral-1.0.0-SFT-merged 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.
 
-## Training procedure
+
+---------------------
+
+```
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-06
-- train_batch_size: 1
-- eval_batch_size: 1
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 4
+- per_device_train_batch_size: 1
+- per_device_eval_batch_size: 1
 - gradient_accumulation_steps: 2
+- num_gpus: 4
 - total_train_batch_size: 8
-- total_eval_batch_size: 4
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.03
-- training_steps: 180
-- mixed_precision_training: Native AMP
+- optimizer: AdamW
+- lr_scheduler_type: cosine
+- num_steps: 180
+- quantization_type: bitsandbytes
+- LoRA: ("\n  - bits: 4\n  - use_exllama: True\n  - device_map: auto\n  - use_cache: False\n  - lora_r: 32\n  - lora_alpha: 16\n  - lora_dropout: 0.05\n  - bias: none\n  - target_modules: ['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj']\n  - task_type: CAUSAL_LM",)
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
-|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 0.3976        | 0.9677 | 30   | 0.3186          | 0.8373         | -0.0381          | 1.0                | 0.8754          | -160.6632      | -115.0300    | -1.7561         | -1.7413       |
-| 0.1934        | 1.9355 | 60   | 0.1752          | 1.6472         | -0.5496          | 1.0                | 2.1968          | -163.2207      | -110.9804    | -1.7603         | -1.7456       |
-| 0.1058        | 2.9032 | 90   | 0.1096          | 1.9881         | -0.7856          | 1.0                | 2.7737          | -164.4007      | -109.2759    | -1.7637         | -1.7491       |
-| 0.0527        | 3.8710 | 120  | 0.0787          | 2.1758         | -1.0246          | 1.0                | 3.2004          | -165.5957      | -108.3371    | -1.7676         | -1.7532       |
-| 0.0526        | 4.8387 | 150  | 0.0577          | 2.2762         | -1.3610          | 1.0                | 3.6373          | -167.2778      | -107.8351    | -1.7693         | -1.7549       |
-| 0.0529        | 5.8065 | 180  | 0.0520          | 2.3217         | -1.5051          | 1.0                | 3.8268          | -167.9981      | -107.6077    | -1.7717         | -1.7573       |
-
-
 ### 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