Downloads · 30 days
9
38% of all-time downloads
29-0
tomaszki/29-0
29-0 is a machine learning model from tomaszki. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
should probably proofread and complete it, then remove this comment. --
All-time downloads
24
Public
Repo size
336 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin168 MB · 50%
At a glance
- Library
- peft
- Model type
- llama
- Access
- Public
- Created
- Feb 14, 2024
- Updated
- Feb 14, 2024
- SHA
- d79d6a19
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
<details><summary>See axolotl config</summary>
axolotl version: 0.4.0
base_model: tomaszki/nous-twenty-nine
model_type: LlamaForCausalLM
is_llama_derived_model: true
hub_model_id: 29-0
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: tomaszki/nous-finetune-axolotl-completion-0
val_set_size: 0.0
output_dir: ./out
sequence_len: 512
sample_packing: false
wandb_project: axolotl
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.00
lora_target_linear: true
lora_fan_in_fan_out:
gradient_accumulation_steps: 1
micro_batch_size: 12
num_epochs: 1
optimizer: adamw_hf
lr_scheduler: cosine
learning_rate: 0.00002
cosine_min_lr_ratio: 0.5
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 0
saves_per_epoch: 1
debug:
deepspeed: #deepspeed_configs/zero2.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
29-0
This model is a fine-tuned version of tomaszki/nous-twenty-nine on an unknown 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: 2e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1
Training results
Framework versions
- PEFT 0.8.2
- Transformers 4.38.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.17.0
- Tokenizers 0.15.0
- Library
- peft
- Type
- llama
- Created
- Feb 14, 2024
- Updated
- Feb 14, 2024