Model save

README.md

@@ -1,103 +1,74 @@
 ---
-license: mit
-library_name: "trl"
+license: apache-2.0
+library_name: peft
 tags:
+- trl
+- kto
 - KTO
 - WeniGPT
+- generated_from_trainer
 base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
 model-index:
-- name: Weni/WeniGPT-Agents-Mixstral-Instruct-2.0.0-KTO
+- name: WeniGPT-Agents-Mixstral-Instruct-2.0.0-KTO
   results: []
-language: ['pt']
 ---
 
-# Weni/WeniGPT-Agents-Mixstral-Instruct-2.0.0-KTO
+<!-- 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. -->
 
-This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1] on the dataset Weni/wenigpt-agent-1.2.0 with the KTO trainer. It is part of the WeniGPT project for [Weni](https://weni.ai/).
-Description: KTO with Agents 1.2.0 dataset and Mixstral model
+# WeniGPT-Agents-Mixstral-Instruct-2.0.0-KTO
 
+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:
-{'eval_loss': nan, 'eval_runtime': 353.1676, 'eval_samples_per_second': 0.849, 'eval_steps_per_second': 0.212, 'eval_rewards/chosen': -5.434815883636475, 'eval_logps/chosen': -287.4195251464844, 'eval_rewards/rejected': -12.600561141967773, 'eval_logps/rejected': -352.2350769042969, 'eval_kl': nan, 'eval_rewards/margins': 7.475613594055176, 'epoch': 0.99}
+- Loss: 0.3856
+- Rewards/chosen: -2.7129
+- Logps/chosen: -263.7560
+- Rewards/rejected: -6.5728
+- Logps/rejected: -282.9854
+- Kl: 0.0
+- Rewards/margins: 3.9057
 
-## Intended uses & limitations
-
-This model has not been trained to avoid specific intructions. 
-
-## Training procedure
-
-Finetuning was done on the model mistralai/Mixtral-8x7B-Instruct-v0.1 with the following prompt:
-
-```
----------------------
-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}
-
-Na sua memória você tem esse contexto:
-{context}
+## Model description
 
-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}
+More information needed
 
+## Intended uses & limitations
 
----------------------
-Response:
-{answer}
+More information needed
 
+## Training and evaluation data
 
----------------------
+More information needed
 
-```
+## Training procedure
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- per_device_train_batch_size: 4
-- per_device_eval_batch_size: 4
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
 - gradient_accumulation_steps: 4
-- num_gpus: 1
 - total_train_batch_size: 16
-- optimizer: AdamW
-- lr_scheduler_type: cosine
-- num_steps: 145
-- 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",)
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.03
+- training_steps: 145
+- mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Logps/chosen | Rewards/rejected | Logps/rejected | Kl     | Rewards/margins |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:------------:|:----------------:|:--------------:|:------:|:---------------:|
+| 0.4403        | 0.34  | 50   | 0.4195          | -1.1683        | -248.3103    | -3.6153          | -253.4100      | 0.5120 | 2.6137          |
+| 0.3518        | 0.68  | 100  | 0.3856          | -2.7129        | -263.7560    | -6.5728          | -282.9854      | 0.0    | 3.9057          |
+
+
 ### Framework versions
 
-- 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/kawine/trl.git#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
+- PEFT 0.10.0
+- Transformers 4.39.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f62c273336a7b98480a304521101fe04fdd590ee43f6f0dea258f4d29dfeb79
-size 54560368
+oid sha256:4bb30d47ede0c352e498d1c9f7a6c920d002a796dcbd6af885c0357368d11c7b
+size 1103203256