Upload folder using huggingface_hub
Browse files
README.md
CHANGED
@@ -1,88 +1,90 @@
|
|
1 |
---
|
2 |
-
|
|
|
3 |
tags:
|
4 |
-
- trl
|
5 |
-
- dpo
|
6 |
- DPO
|
7 |
- WeniGPT
|
8 |
-
- generated_from_trainer
|
9 |
base_model: Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged
|
10 |
model-index:
|
11 |
-
- name: WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.11-DPO
|
12 |
results: []
|
|
|
13 |
---
|
14 |
|
15 |
-
|
16 |
-
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
-
|
|
|
19 |
|
20 |
-
This model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged](https://huggingface.co/Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged) on an unknown dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
-
-
|
23 |
-
- Rewards/chosen: 1.1764
|
24 |
-
- Rewards/rejected: -0.8691
|
25 |
-
- Rewards/accuracies: 0.7857
|
26 |
-
- Rewards/margins: 2.0455
|
27 |
-
- Logps/rejected: -193.9308
|
28 |
-
- Logps/chosen: -125.0071
|
29 |
-
- Logits/rejected: -1.8155
|
30 |
-
- Logits/chosen: -1.7656
|
31 |
|
32 |
-
##
|
33 |
|
34 |
-
|
35 |
|
36 |
-
##
|
37 |
|
38 |
-
|
39 |
|
40 |
-
|
|
|
|
|
|
|
|
|
41 |
|
42 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
|
44 |
-
|
|
|
|
|
|
|
45 |
|
46 |
### Training hyperparameters
|
47 |
|
48 |
The following hyperparameters were used during training:
|
49 |
- learning_rate: 5e-06
|
50 |
-
-
|
51 |
-
-
|
52 |
-
- seed: 42
|
53 |
-
- distributed_type: multi-GPU
|
54 |
-
- num_devices: 2
|
55 |
- gradient_accumulation_steps: 2
|
|
|
56 |
- total_train_batch_size: 4
|
57 |
-
-
|
58 |
-
-
|
59 |
-
-
|
60 |
-
-
|
61 |
-
-
|
62 |
-
- mixed_precision_training: Native AMP
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
-
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
67 |
-
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
68 |
-
| 0.6531 | 0.4878 | 30 | 0.6394 | 0.1271 | -0.0075 | 0.7857 | 0.1346 | -185.3151 | -135.4998 | -1.7717 | -1.7290 |
|
69 |
-
| 0.5732 | 0.9756 | 60 | 0.5476 | 0.3645 | -0.0302 | 0.7857 | 0.3947 | -185.5418 | -133.1256 | -1.7778 | -1.7342 |
|
70 |
-
| 0.5252 | 1.4634 | 90 | 0.4644 | 0.6021 | -0.0850 | 0.7857 | 0.6871 | -186.0897 | -130.7499 | -1.7853 | -1.7405 |
|
71 |
-
| 0.4402 | 1.9512 | 120 | 0.4089 | 0.7788 | -0.1757 | 0.7857 | 0.9545 | -186.9970 | -128.9828 | -1.7949 | -1.7492 |
|
72 |
-
| 0.4138 | 2.4390 | 150 | 0.3652 | 0.9271 | -0.3082 | 0.7857 | 1.2353 | -188.3218 | -127.4999 | -1.8014 | -1.7541 |
|
73 |
-
| 0.3863 | 2.9268 | 180 | 0.3403 | 1.0288 | -0.4194 | 0.7857 | 1.4482 | -189.4338 | -126.4830 | -1.8065 | -1.7584 |
|
74 |
-
| 0.2999 | 3.4146 | 210 | 0.3210 | 1.0940 | -0.5570 | 0.7857 | 1.6510 | -190.8097 | -125.8309 | -1.8114 | -1.7629 |
|
75 |
-
| 0.2311 | 3.9024 | 240 | 0.3085 | 1.1291 | -0.6550 | 0.7857 | 1.7841 | -191.7899 | -125.4799 | -1.8136 | -1.7646 |
|
76 |
-
| 0.2992 | 4.3902 | 270 | 0.3012 | 1.1494 | -0.7427 | 0.7857 | 1.8921 | -192.6667 | -125.2770 | -1.8147 | -1.7654 |
|
77 |
-
| 0.2532 | 4.8780 | 300 | 0.2943 | 1.1602 | -0.8051 | 0.7857 | 1.9653 | -193.2910 | -125.1693 | -1.8146 | -1.7650 |
|
78 |
-
| 0.2564 | 5.3659 | 330 | 0.2905 | 1.1717 | -0.8471 | 0.7857 | 2.0188 | -193.7112 | -125.0541 | -1.8151 | -1.7652 |
|
79 |
-
| 0.2457 | 5.8537 | 360 | 0.2882 | 1.1764 | -0.8691 | 0.7857 | 2.0455 | -193.9308 | -125.0071 | -1.8155 | -1.7656 |
|
80 |
-
|
81 |
-
|
82 |
### Framework versions
|
83 |
|
84 |
-
-
|
85 |
-
-
|
86 |
-
-
|
87 |
-
-
|
88 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: mit
|
3 |
+
library_name: "trl"
|
4 |
tags:
|
|
|
|
|
5 |
- DPO
|
6 |
- WeniGPT
|
|
|
7 |
base_model: Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged
|
8 |
model-index:
|
9 |
+
- name: Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.11-DPO
|
10 |
results: []
|
11 |
+
language: ['pt']
|
12 |
---
|
13 |
|
14 |
+
# Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.11-DPO
|
|
|
15 |
|
16 |
+
This model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-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/).
|
17 |
+
Description: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT
|
18 |
|
|
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
{'eval_loss': 0.2881975471973419, 'eval_runtime': 17.3794, 'eval_samples_per_second': 1.611, 'eval_steps_per_second': 0.806, 'eval_rewards/chosen': 1.1763746738433838, 'eval_rewards/rejected': -0.8690943121910095, 'eval_rewards/accuracies': 0.7857142686843872, 'eval_rewards/margins': 2.045469045639038, 'eval_logps/rejected': -193.93080139160156, 'eval_logps/chosen': -125.00711822509766, 'eval_logits/rejected': -1.8155311346054077, 'eval_logits/chosen': -1.7656012773513794, 'epoch': 5.951219512195122}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged 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 |
+
|
50 |
+
```
|
51 |
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 5e-06
|
56 |
+
- per_device_train_batch_size: 1
|
57 |
+
- per_device_eval_batch_size: 1
|
|
|
|
|
|
|
58 |
- gradient_accumulation_steps: 2
|
59 |
+
- num_gpus: 2
|
60 |
- total_train_batch_size: 4
|
61 |
+
- optimizer: AdamW
|
62 |
+
- lr_scheduler_type: cosine
|
63 |
+
- num_steps: 366
|
64 |
+
- quantization_type: bitsandbytes
|
65 |
+
- LoRA: ("\n - bits: 4\n - use_exllama: True\n - device_map: auto\n - use_cache: False\n - lora_r: 8\n - lora_alpha: 16\n - lora_dropout: 0.05\n - bias: none\n - target_modules: ['v_proj', 'q_proj']\n - task_type: CAUSAL_LM",)
|
|
|
66 |
|
67 |
### Training results
|
68 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
### Framework versions
|
70 |
|
71 |
+
- transformers==4.40.0
|
72 |
+
- datasets==2.18.0
|
73 |
+
- peft==0.10.0
|
74 |
+
- safetensors==0.4.2
|
75 |
+
- evaluate==0.4.1
|
76 |
+
- bitsandbytes==0.43
|
77 |
+
- huggingface_hub==0.22.2
|
78 |
+
- seqeval==1.2.2
|
79 |
+
- auto-gptq==0.7.1
|
80 |
+
- gpustat==1.1.1
|
81 |
+
- deepspeed==0.14.0
|
82 |
+
- wandb==0.16.6
|
83 |
+
- trl==0.8.1
|
84 |
+
- accelerate==0.29.3
|
85 |
+
- coloredlogs==15.0.1
|
86 |
+
- traitlets==5.14.2
|
87 |
+
- git+https://github.com/casper-hansen/AutoAWQ.git
|
88 |
+
|
89 |
+
### Hardware
|
90 |
+
- Cloud provided: runpod.io
|