ironrock commited on
Commit
9516c25
1 Parent(s): 493ac0b

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +71 -38
README.md CHANGED
@@ -1,68 +1,101 @@
1
  ---
2
  license: mit
3
- library_name: peft
4
  tags:
5
- - trl
6
- - kto
7
- - generated_from_trainer
8
  base_model: HuggingFaceH4/zephyr-7b-beta
9
  model-index:
10
- - name: WeniGPT-Agents-Zephyr-1.0.30-KTO
11
  results: []
 
12
  ---
13
 
14
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
- should probably proofread and complete it, then remove this comment. -->
16
 
17
- # WeniGPT-Agents-Zephyr-1.0.30-KTO
 
18
 
19
- This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.4411
22
- - Rewards/chosen: -0.1290
23
- - Rewards/rejected: -1.7667
24
- - Rewards/margins: 1.6377
25
- - Kl: 4.6044
26
- - Logps/chosen: -303.0165
27
- - Logps/rejected: -255.1877
28
 
29
- ## Model description
30
 
31
- More information needed
32
 
33
- ## Intended uses & limitations
34
 
35
- More information needed
36
 
37
- ## Training and evaluation data
 
 
 
 
38
 
39
- More information needed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
 
41
- ## Training procedure
 
 
 
 
 
 
 
 
42
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 0.0002
47
- - train_batch_size: 4
48
- - eval_batch_size: 4
49
- - seed: 42
50
  - gradient_accumulation_steps: 4
 
51
  - total_train_batch_size: 16
52
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
- - lr_scheduler_type: linear
54
- - lr_scheduler_warmup_ratio: 0.03
55
- - training_steps: 47
56
- - mixed_precision_training: Native AMP
57
 
58
  ### Training results
59
 
60
-
61
-
62
  ### Framework versions
63
 
64
- - PEFT 0.10.0
65
- - Transformers 4.38.2
66
- - Pytorch 2.1.0+cu118
67
- - Datasets 2.18.0
68
- - Tokenizers 0.15.2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
+ library_name: "trl"
4
  tags:
5
+ - KTO
6
+ - WeniGPT
 
7
  base_model: HuggingFaceH4/zephyr-7b-beta
8
  model-index:
9
+ - name: Weni/WeniGPT-Agents-Zephyr-1.0.30-KTO
10
  results: []
11
+ language: ['pt']
12
  ---
13
 
14
+ # Weni/WeniGPT-Agents-Zephyr-1.0.30-KTO
 
15
 
16
+ This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta] on the dataset Weni/wenigpt-agent-1.4.0 with the KTO trainer. It is part of the WeniGPT project for [Weni](https://weni.ai/).
17
+ Description: Experiment with new tokenizer configuration for chat template of zephyr
18
 
 
19
  It achieves the following results on the evaluation set:
20
+ {'eval_loss': 0.44106873869895935, 'eval_runtime': 100.5121, 'eval_samples_per_second': 2.169, 'eval_steps_per_second': 0.547, 'eval_rewards/chosen': -0.12895259261131287, 'eval_rewards/rejected': -1.7666949033737183, 'eval_rewards/margins': 1.637742280960083, 'eval_kl': 4.604356288909912, 'eval_logps/chosen': -303.01654052734375, 'eval_logps/rejected': -255.187744140625, 'epoch': 0.9}
 
 
 
 
 
 
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 HuggingFaceH4/zephyr-7b-beta 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
+ {context_statement}
37
+
38
+ Lista de requisitos:
39
+ - Responda de forma natural, mas nunca fale sobre um assunto fora do contexto.
40
+ - Nunca traga informações do seu próprio conhecimento.
41
+ - Repito é crucial que você responda usando apenas informações do contexto.
42
+ - Nunca mencione o contexto fornecido.
43
+ - Nunca mencione a pergunta fornecida.
44
+ - Gere a resposta mais útil possível para a pergunta usando informações do conexto acima.
45
+ - Nunca elabore sobre o porque e como você fez a tarefa, apenas responda.
46
+
47
+
48
+ ---------------------
49
+ Question:
50
+ {question}
51
 
52
+
53
+ ---------------------
54
+ Response:
55
+ {answer}
56
+
57
+
58
+ ---------------------
59
+
60
+ ```
61
 
62
  ### Training hyperparameters
63
 
64
  The following hyperparameters were used during training:
65
  - learning_rate: 0.0002
66
+ - per_device_train_batch_size: 4
67
+ - per_device_eval_batch_size: 4
 
68
  - gradient_accumulation_steps: 4
69
+ - num_gpus: 1
70
  - total_train_batch_size: 16
71
+ - optimizer: AdamW
72
+ - lr_scheduler_type: cosine
73
+ - num_steps: 47
74
+ - quantization_type: bitsandbytes
75
+ - 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",)
76
 
77
  ### Training results
78
 
 
 
79
  ### Framework versions
80
 
81
+ - transformers==4.38.2
82
+ - datasets==2.18.0
83
+ - peft==0.10.0
84
+ - safetensors==0.4.2
85
+ - evaluate==0.4.1
86
+ - bitsandbytes==0.43
87
+ - huggingface_hub==0.22.2
88
+ - seqeval==1.2.2
89
+ - optimum==1.18.1
90
+ - auto-gptq==0.7.1
91
+ - gpustat==1.1.1
92
+ - deepspeed==0.14.0
93
+ - wandb==0.16.6
94
+ - trl==0.8.1
95
+ - accelerate==0.29.2
96
+ - coloredlogs==15.0.1
97
+ - traitlets==5.14.2
98
+ - autoawq@https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.4/autoawq-0.2.4+cu118-cp310-cp310-linux_x86_64.whl
99
+
100
+ ### Hardware
101
+ - Cloud provided: runpod.io