See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: heegyu/WizardVicuna-open-llama-3b-v2
bf16: auto
datasets:
- data_files:
- c80922e5615264fa_train_data.json
ds_type: json
format: custom
path: c80922e5615264fa_train_data.json
type:
field: null
field_input: input
field_instruction: instruction
field_output: output
field_system: null
format: null
no_input_format: null
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_sample_packing: false
eval_table_size: null
evals_per_epoch: 2
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: taopanda/f04e564d-fd64-4ad3-b850-847879330a35
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
micro_batch_size: 2
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: adamw_bnb_8bit
output_dir: ./outputs/out/taopanda-3_db77949d-e35c-457a-8370-2bfddc5702da
pad_to_sequence_len: true
resume_from_checkpoint: null
sample_packing: true
saves_per_epoch: 1
seed: 68605
sequence_len: 4096
special_tokens:
pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.1
wandb_entity: fatcat87-taopanda
wandb_log_model: null
wandb_mode: online
wandb_name: taopanda-3_db77949d-e35c-457a-8370-2bfddc5702da
wandb_project: subnet56
wandb_runid: taopanda-3_db77949d-e35c-457a-8370-2bfddc5702da
wandb_watch: null
warmup_ratio: 0.05
weight_decay: 0.0
xformers_attention: null
f04e564d-fd64-4ad3-b850-847879330a35
This model is a fine-tuned version of heegyu/WizardVicuna-open-llama-3b-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2477
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: 68605
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.4539 | 0.1212 | 1 | 1.4461 |
1.3463 | 0.4848 | 4 | 1.3584 |
1.258 | 0.9697 | 8 | 1.2859 |
1.2372 | 1.3939 | 12 | 1.2540 |
1.2207 | 1.8788 | 16 | 1.2477 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for taopanda/f04e564d-fd64-4ad3-b850-847879330a35
Base model
heegyu/WizardVicuna-open-llama-3b-v2