Mel-Iza0 commited on
Commit
ce6fbd1
1 Parent(s): 979257c

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +72 -43
README.md CHANGED
@@ -1,74 +1,103 @@
1
  ---
2
- license: apache-2.0
3
- library_name: peft
4
  tags:
5
- - trl
6
- - kto
7
  - KTO
8
  - WeniGPT
9
- - generated_from_trainer
10
  base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
11
  model-index:
12
- - name: WeniGPT-Agents-Mixstral-Instruct-2.0.0-KTO
13
  results: []
 
14
  ---
15
 
16
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
- should probably proofread and complete it, then remove this comment. -->
18
 
19
- # WeniGPT-Agents-Mixstral-Instruct-2.0.0-KTO
 
20
 
21
- 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.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.3856
24
- - Rewards/chosen: -2.7129
25
- - Logps/chosen: -263.7560
26
- - Rewards/rejected: -6.5728
27
- - Logps/rejected: -282.9854
28
- - Kl: 0.0
29
- - Rewards/margins: 3.9057
30
 
31
- ## Model description
32
 
33
- More information needed
34
 
35
- ## Intended uses & limitations
36
 
37
- More information needed
38
 
39
- ## Training and evaluation data
 
 
 
 
40
 
41
- More information needed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
 
43
- ## Training procedure
 
 
 
 
 
 
 
 
44
 
45
  ### Training hyperparameters
46
 
47
  The following hyperparameters were used during training:
48
  - learning_rate: 0.0002
49
- - train_batch_size: 4
50
- - eval_batch_size: 4
51
- - seed: 42
52
  - gradient_accumulation_steps: 4
 
53
  - total_train_batch_size: 16
54
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
- - lr_scheduler_type: linear
56
- - lr_scheduler_warmup_ratio: 0.03
57
- - training_steps: 145
58
- - mixed_precision_training: Native AMP
59
 
60
  ### Training results
61
 
62
- | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Logps/chosen | Rewards/rejected | Logps/rejected | Kl | Rewards/margins |
63
- |:-------------:|:-----:|:----:|:---------------:|:--------------:|:------------:|:----------------:|:--------------:|:------:|:---------------:|
64
- | 0.4403 | 0.34 | 50 | 0.4195 | -1.1683 | -248.3103 | -3.6153 | -253.4100 | 0.5120 | 2.6137 |
65
- | 0.3518 | 0.68 | 100 | 0.3856 | -2.7129 | -263.7560 | -6.5728 | -282.9854 | 0.0 | 3.9057 |
66
-
67
-
68
  ### Framework versions
69
 
70
- - PEFT 0.10.0
71
- - Transformers 4.39.1
72
- - Pytorch 2.1.0+cu118
73
- - Datasets 2.18.0
74
- - Tokenizers 0.15.2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: mit
3
+ library_name: "trl"
4
  tags:
 
 
5
  - KTO
6
  - WeniGPT
 
7
  base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
8
  model-index:
9
+ - name: Weni/WeniGPT-Agents-Mixstral-Instruct-2.0.0-KTO
10
  results: []
11
+ language: ['pt']
12
  ---
13
 
14
+ # Weni/WeniGPT-Agents-Mixstral-Instruct-2.0.0-KTO
 
15
 
16
+ 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/).
17
+ Description: KTO with Agents 1.2.0 dataset and Mixstral model
18
 
 
19
  It achieves the following results on the evaluation set:
20
+ {'eval_loss': 0.38556817173957825, 'eval_runtime': 357.3941, 'eval_samples_per_second': 0.839, 'eval_steps_per_second': 0.21, 'eval_rewards/chosen': -2.7128894329071045, 'eval_logps/chosen': -263.7559509277344, 'eval_rewards/rejected': -6.572808265686035, 'eval_logps/rejected': -282.9854431152344, 'eval_kl': 0.0, 'eval_rewards/margins': 3.9057483673095703, 'epoch': 0.99}
 
 
 
 
 
 
21
 
22
+ ## Intended uses & limitations
23
 
24
+ This model has not been trained to avoid specific intructions.
25
 
26
+ ## Training procedure
27
 
28
+ Finetuning was done on the model mistralai/Mixtral-8x7B-Instruct-v0.1 with the following prompt:
29
 
30
+ ```
31
+ ---------------------
32
+ System_prompt:
33
+ 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:
34
+ {instructions_formatted}
35
 
36
+ Na sua memória você tem esse contexto:
37
+ {context}
38
+
39
+ Lista de requisitos:
40
+ - Responda de forma natural, mas nunca fale sobre um assunto fora do contexto.
41
+ - Nunca traga informações do seu próprio conhecimento.
42
+ - Repito é crucial que você responda usando apenas informações do contexto.
43
+ - Nunca mencione o contexto fornecido.
44
+ - Nunca mencione a pergunta fornecida.
45
+ - Gere a resposta mais útil possível para a pergunta usando informações do conexto acima.
46
+ - Nunca elabore sobre o porque e como você fez a tarefa, apenas responda.
47
+
48
+
49
+ ---------------------
50
+ Question:
51
+ {question}
52
 
53
+
54
+ ---------------------
55
+ Response:
56
+ {answer}
57
+
58
+
59
+ ---------------------
60
+
61
+ ```
62
 
63
  ### Training hyperparameters
64
 
65
  The following hyperparameters were used during training:
66
  - learning_rate: 0.0002
67
+ - per_device_train_batch_size: 4
68
+ - per_device_eval_batch_size: 4
 
69
  - gradient_accumulation_steps: 4
70
+ - num_gpus: 1
71
  - total_train_batch_size: 16
72
+ - optimizer: AdamW
73
+ - lr_scheduler_type: cosine
74
+ - num_steps: 145
75
+ - quantization_type: bitsandbytes
76
+ - 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",)
77
 
78
  ### Training results
79
 
 
 
 
 
 
 
80
  ### Framework versions
81
 
82
+ - transformers==4.39.1
83
+ - datasets==2.18.0
84
+ - peft==0.10.0
85
+ - safetensors==0.4.2
86
+ - evaluate==0.4.1
87
+ - bitsandbytes==0.43
88
+ - huggingface_hub==0.20.3
89
+ - seqeval==1.2.2
90
+ - optimum==1.17.1
91
+ - auto-gptq==0.7.1
92
+ - gpustat==1.1.1
93
+ - deepspeed==0.14.0
94
+ - wandb==0.16.3
95
+ - # trl==0.8.1
96
+ - git+https://github.com/kawine/trl.git#egg=trl
97
+ - accelerate==0.28.0
98
+ - coloredlogs==15.0.1
99
+ - traitlets==5.14.1
100
+ - autoawq@https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.0/autoawq-0.2.0+cu118-cp310-cp310-linux_x86_64.whl
101
+
102
+ ### Hardware
103
+ - Cloud provided: runpod.io