metadata

license: mit
base_model: microsoft/phi-2
tags:
  - axolotl
  - generated_from_trainer
  - phi
  - phi-2
  - logical
  - reasoning
  - transformers
  - text-generation-inference
model-index:
  - name: phi-2-logical-sft
    results: []
datasets:
  - garage-bAInd/Open-Platypus

See axolotl config

axolotl version: 0.4.0

base_model: microsoft/phi-2
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

hub_model_id: MaziyarPanahi/phi-2-logical-sft
hf_use_auth_token: true


load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: garage-bAInd/Open-Platypus
    type: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./phi-2-logical-sft-out

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: adamw_torch
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0
lr_scheduler: cosine
learning_rate: 0.000003

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: True
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
resize_token_embeddings_to_32x: true
special_tokens:
  pad_token: "<|endoftext|>"

phi-2-logical-sft

This model is a fine-tuned version of microsoft/phi-2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.0075

Prompt Template

### Instruction:

<prompt> (without the <>)

### Response:

Examples

You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.
### Instruction:

Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.

### Response:

Goku woke up one day in his hometown of Earth and went out for his daily training routine. He was feeling confident and happy as usual, until he received news that his dear friend Kirby had teamed up with Majin Buu to destroy the world.

Shocked and saddened by this news, Goku immediately knew he had to act fast to save his friends and loved ones. With his superhuman strength and incredible speed, he set off on a mission to stop the evil duo from carrying out their destructive plan.

Along the way, Goku encountered many challenges and obstacles, but he never gave up. He fought fiercely against Kirby and Majin Buu, using all of his powers and skills to try and defeat them.

Finally, after a long and grueling battle, Goku emerged victorious. He managed to convince Kirby to turn against Majin Buu and join forces with him to defeat the evil being once and for all. Together, they were able to defeat Majin Buu and save the world from destruction.

Goku felt a sense of relief and happiness wash over him as he realized that his friends were safe and the world was no longer in danger. He knew that he had done everything he could to protect those he cared about, and he was grateful for the opportunity to use his powers for good.
<|endoftext|>

You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.
### Instruction:

describe about pros and cons of docker system.

### Response:

Docker is a containerization platform that allows developers to package applications as lightweight containers, which can be easily deployed on any Linux-based operating system. Docker offers several advantages over traditional methods of application deployment such as virtual machines or physical servers. Here are some of the pros and cons of using Docker:

Pros:
1. Portability: Docker containers run in an isolated environment, making it easier for developers to deploy their applications across different environments without worrying about compatibility issues. This makes it easier to test applications in multiple environments and ensures that they work seamlessly across different platforms.

2. Scalability: Docker containers can be scaled up or down based on demand, allowing developers to quickly adjust the size of their infrastructure as needed. This makes it easier to handle spikes in traffic or other sudden changes in workload.

3. Simplicity: Docker provides a simple, intuitive interface for managing containers, making it easy for developers to create and manage their applications. This reduces the time and effort required to set up and maintain a complex infrastructure.

Cons:
1. Cost: While Docker is generally free to use, there may be additional costs associated with deploying and scaling your applications, especially if you require a large number of containers. Additionally, you may need to purchase additional tools or services to manage your containers effectively.

2. Security: Containerized applications are more vulnerable to security threats than traditional applications, as they are running in an isolated environment. This means that developers must take extra precautions to ensure that their applications are secure and protected from attacks.

3. Performance: Containerized applications can experience performance issues when running on certain types of hardware or in high-traffic environments. Developers must carefully consider the performance requirements of their applications before deciding whether to use Docker.
<|endoftext|>

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 3e-06
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 8
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.8319	0.0	1	1.0229
0.8799	0.25	71	1.0208
0.8349	0.5	142	1.0119
0.7798	0.76	213	1.0093
0.8317	1.01	284	1.0083
0.777	1.24	355	1.0080
0.7544	1.49	426	1.0075
0.7037	1.74	497	1.0075

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.2.0+cu121
Datasets 2.17.0
Tokenizers 0.15.0