Hugging Face's logo

nyu-dice-lab
/
Mistral-7B-Base-SFT-ShareGPT-Vicuna

Text Generation
Transformers
PyTorch
Safetensors
mistral
axolotl
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Mistral-7B-Base-SFT-ShareGPT-Vicuna / README.md
penfever's picture
penfever
End of training
5276511 verified
preview code
|
raw
history blame
2.93 kB
metadata
library_name: transformers
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.3
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: Mistral-7B-sharegpt-vicuna-v1.0
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: Aeala/ShareGPT_Vicuna_unfiltered
    type: sharegpt
    conversation: llama3

chat_template: llama3

dataset_prepared_path: ./datasets/m7b-sharegpt-vicuna
output_dir: ./outputs/m7b-sharegpt-vicuna-v1.0

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

wandb_project: lm-evals
wandb_entity:
wandb_watch:
wandb_name: Mistral-7B-sharegpt-vicuna-v1.0
wandb_log_model:
hub_model_id: penfever/Mistral-7B-sharegpt-vicuna-v1.0

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: <|begin_of_text|>
  eos_token: <|end_of_text|>
  pad_token: <|end_of_text|>
tokens:
  - "<|start_header_id|>"
  - "<|end_header_id|>"
  - "<|eot_id|>"

Mistral-7B-sharegpt-vicuna-v1.0

This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 on the None dataset.

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: 5e-06
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • total_eval_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 3

Training results

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.3.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1