tinyLlamaChat-context-pubmed-qlora-2024

<!-- 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. -->

<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

<details><summary>See axolotl config</summary>

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

</details><br>

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

Framework versions

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