Hugging Face's logo

tsunayoshi21
/
tinyLlamaChat-context-pubmed-qlora-2024

PEFT
Safetensors
llama
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
tinyLlamaChat-context-pubmed-qlora-2024 / README.md
tsunayoshi21's picture
tsunayoshi21
Subiendo mi modelo entrenado
2a72755 verified
preview code
|
raw
history blame contribute delete
3.73 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v0.1
model-index:
  - name: outputs/qlora-out
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: qlora
base_model: TinyLlama/TinyLlama-1.1B-Chat-v0.1
bf16: false
dataset_prepared_path: null
datasets:
- ds_tipe: json
  path: pubmed_continual_pretraning_dataset.jsonl
  type: completion
debug: null
deepspeed: null
early_stopping_patience: null
eval_sample_packing: false
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules: null
lr_scheduler: cosine
micro_batch_size: 8
model_type: LlamaForCausalLM
num_epochs: 4
optimizer: paged_adamw_32bit
output_dir: ./outputs/qlora-out
pad_to_sequence_len: false
resume_from_checkpoint: null
sample_packing: false
saves_per_epoch: 1
sequence_len: 4096
special_tokens: null
strict: false
tf32: false
tokenizer_type: LlamaTokenizer
train_on_inputs: false
val_set_size: 0.05
wandb_entity: null
wandb_log_model: null
wandb_name: null
wandb_project: null
wandb_watch: null
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

outputs/qlora-out

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v0.1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9667

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • 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
3.0408 0.0336 1 3.0278
2.6971 0.2689 8 2.5885
2.0158 0.5378 16 2.1604
1.9578 0.8067 24 2.0713
1.9457 1.0756 32 2.0373
1.9927 1.3445 40 2.0166
1.9848 1.6134 48 2.0021
1.9446 1.8824 56 1.9902
1.9023 2.1513 64 1.9825
1.834 2.4202 72 1.9764
1.9834 2.6891 80 1.9720
1.997 2.9580 88 1.9688
1.8704 3.2269 96 1.9672
1.9608 3.4958 104 1.9667
1.8624 3.7647 112 1.9667

Framework versions

  • PEFT 0.11.1
  • Transformers 4.41.1
  • Pytorch 2.1.2+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1