Downloads · 30 days
6
33% of all-time downloads
isafpr-tiny-llama-lora
Peaky8linders/isafpr-tiny-llama-lora
isafpr-tiny-llama-lora is a machine learning model from Peaky8linders. 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. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
18
Public
Repo size
505 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin101 MB · 50%
At a glance
- Library
- peft
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Jun 26, 2024
- Updated
- Jun 27, 2024
- SHA
- 22de27a5
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: 0.4.1
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
load_in_8bit: true
load_in_4bit: false
strict: false
data_seed: 2606
seed: 2606
datasets:
- path: data/templatefree_isaf_press_releases_ft_train.jsonl
type: input_output
dataset_prepared_path:
val_set_size: 0.1
output_dir: tiny-llama/lora-out
hub_model_id: Peaky8linders/isafpr-tiny-llama-lora
sequence_len: 4096
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
isafpr-tiny-llama-lora
This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0395
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: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 2606
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7938 | 0.0138 | 1 | 1.7961 |
| 0.2755 | 0.2483 | 18 | 0.2099 |
| 0.0937 | 0.4966 | 36 | 0.0798 |
| 0.0625 | 0.7448 | 54 | 0.0646 |
| 0.0507 | 0.9931 | 72 | 0.0581 |
| 0.0466 | 1.2138 | 90 | 0.0516 |
| 0.0391 | 1.4621 | 108 | 0.0485 |
| 0.0534 | 1.7103 | 126 | 0.0457 |
| 0.0611 | 1.9586 | 144 | 0.0439 |
| 0.0281 | 2.1793 | 162 | 0.0434 |
| 0.0382 | 2.4276 | 180 | 0.0416 |
| 0.031 | 2.6759 | 198 | 0.0407 |
| 0.0278 | 2.9241 | 216 | 0.0400 |
| 0.0377 | 3.1448 | 234 | 0.0397 |
| 0.0247 | 3.3931 | 252 | 0.0400 |
| 0.0419 | 3.6414 | 270 | 0.0395 |
| 0.0273 | 3.8897 | 288 | 0.0395 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.1.2+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1
- Library
- peft
- Type
- llama
- License
- apache-2.0
- Created
- Jun 26, 2024
- Updated
- Jun 27, 2024