See axolotl config
axolotl version: 0.4.0
base_model: aurora-m/aurora-m-v0.1 # this can be swapped for mdel model when the model is released
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
is_llama_derived_model: false
load_in_8bit: false # when this is true inference quality is terrible
load_in_4bit: false
strict: false
datasets:
- path: tatsu-lab/alpaca # change this to where your dataset is
type: alpaca # change this to 'alpaca' if you are using alpaca formatting
lora_modules_to_save:
- embed_tokens
- lm_head
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./lora-out
sequence_len: 4096 # this can be tweaked for efficiency
sample_packing: true
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: aurora-instruct-alpaca # give this a name
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 2 # this can be tweaked for efficiency
micro_batch_size: 1 # this can be tweaked for efficiency
num_epochs: 1 # this can be experimented with
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: true
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: false # when this is true, inference quality is terrible
s2_attention:
warmup_steps: 10 # this can be tweaked for efficiency
evals_per_epoch: 10 # this can be tweaked for efficiency
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
pad_token: "<|endoftext|>"
eos_token: "<|endoftext|>"
lora-out
This model is a fine-tuned version of aurora-m/aurora-m-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9600
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.9777 | 0.0 | 1 | 3.8904 |
1.228 | 0.1 | 73 | 1.1761 |
1.2383 | 0.2 | 146 | 1.0635 |
0.9985 | 0.3 | 219 | 1.0268 |
1.0444 | 0.4 | 292 | 1.0058 |
0.9859 | 0.5 | 365 | 0.9904 |
0.9736 | 0.6 | 438 | 0.9759 |
1.0146 | 0.7 | 511 | 0.9655 |
1.0007 | 0.8 | 584 | 0.9610 |
0.9943 | 0.9 | 657 | 0.9600 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 2
Model tree for stillerman/instruct-aurora-alpaca
Base model
bigcode/starcoderplus
Finetuned
aurora-m/aurora-m-biden-harris-redteamed