Upload folder using huggingface_hub

README.md

@@ -1,75 +1,89 @@
 ---
-license: apache-2.0
-library_name: peft
+license: mit
+library_name: "trl"
 tags:
-- trl
-- kto
-- generated_from_trainer
+- KTO
+- WeniGPT
 base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
 model-index:
-- name: WeniGPT-QA-Zephyr-7B-5.0.1-KTO
+- name: Weni/WeniGPT-QA-Zephyr-7B-5.0.1-KTO
   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-QA-Zephyr-7B-5.0.1-KTO
 
-# WeniGPT-QA-Zephyr-7B-5.0.1-KTO
+This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1] on the dataset Weni/WeniGPT-QA-Binarized-1.2.0 with the KTO trainer. It is part of the WeniGPT project for [Weni](https://weni.ai/).
+Description: WeniGPT Experiment using KTO trainer with no collator, Mixstral model and no system prompt.
 
-This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0146
-- Eval/rewards/chosen: 6.5462
-- Eval/rewards/rejected: -30.7776
-- Eval/kl: 0.2505
-- Eval/logps/chosen: -129.4441
-- Eval/logps/rejected: -508.0271
-- Eval/rewards/margins: 37.3238
+{'eval_loss': 0.014605735428631306, 'eval_runtime': 1025.937, 'eval_samples_per_second': 0.476, 'eval_steps_per_second': 0.119, 'eval/rewards/chosen': 6.546164512634277, 'eval/rewards/rejected': -30.777591705322266, 'eval/kl': 0.25049710273742676, 'eval/logps/chosen': -129.4441375732422, 'eval/logps/rejected': -508.0271301269531, 'eval/rewards/margins': 37.32375621795654, 'epoch': 1.99}
 
-## 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 mistralai/Mixtral-8x7B-Instruct-v0.1 with the following prompt:
 
-## Training and evaluation data
+```
+---------------------
+Question:
+<|user|>
+Contexto: {context}
 
-More information needed
+Questão: {question}</s>
 
-## Training procedure
+
+---------------------
+Response:
+<|assistant|>
+{response}</s>
+
+
+---------------------
+
+```
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
-- eval_batch_size: 4
-- seed: 42
+- per_device_train_batch_size: 4
+- per_device_eval_batch_size: 4
 - gradient_accumulation_steps: 8
+- num_gpus: 1
 - total_train_batch_size: 32
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.03
-- training_steps: 262
-- mixed_precision_training: Native AMP
+- optimizer: AdamW
+- lr_scheduler_type: cosine
+- num_steps: 262
+- quantization_type: bitsandbytes
+- LoRA: ("\n  - bits: 4\n  - use_exllama: True\n  - device_map: auto\n  - use_cache: False\n  - lora_r: 16\n  - lora_alpha: 32\n  - lora_dropout: 0.05\n  - bias: none\n  - target_modules: ['q_proj', 'k_proj', 'v_proj', 'o_proj']\n  - task_type: CAUSAL_LM",)
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |         |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.1177        | 0.38  | 50   | 0.0468          | 24.8637 |
-| 0.0257        | 0.76  | 100  | 0.0236          | 30.5016 |
-| 0.0141        | 1.14  | 150  | 0.0219          | 33.9185 |
-| 0.0103        | 1.52  | 200  | 0.0146          | 37.3238 |
-| 0.0084        | 1.9   | 250  | 0.0129          | 39.0837 |
-
-
 ### Framework versions
 
-- PEFT 0.10.0
-- Transformers 4.39.1
-- Pytorch 2.1.0+cu118
-- Datasets 2.18.0
-- Tokenizers 0.15.1
+- transformers==4.39.1
+- datasets==2.18.0
+- peft==0.10.0
+- safetensors==0.4.2
+- evaluate==0.4.1
+- bitsandbytes==0.43
+- huggingface_hub==0.20.3
+- seqeval==1.2.2
+- optimum==1.17.1
+- auto-gptq==0.7.1
+- gpustat==1.1.1
+- deepspeed==0.14.0
+- wandb==0.16.3
+- # trl==0.8.1
+- git+https://github.com/claralp/trl.git@fix_nans#egg=trl
+- accelerate==0.28.0
+- coloredlogs==15.0.1
+- traitlets==5.14.1
+- autoawq@https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.0/autoawq-0.2.0+cu118-cp310-cp310-linux_x86_64.whl
+
+### Hardware
+- Cloud provided: runpod.io