See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 557e1609420e0088_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/557e1609420e0088_train_data.json
type:
field_instruction: full_prompt
field_output: example
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: true
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: dimasik87/edb41855-7266-4205-a88c-20f868ce28d0
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_memory:
0: 70GiB
max_steps: 25
micro_batch_size: 1
mlflow_experiment_name: /tmp/557e1609420e0088_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 3
sequence_len: 2028
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: edb41855-7266-4205-a88c-20f868ce28d0
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: edb41855-7266-4205-a88c-20f868ce28d0
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null
edb41855-7266-4205-a88c-20f868ce28d0
This model is a fine-tuned version of aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0041
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: 4
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- training_steps: 25
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.4934 | 0.0833 | 1 | 1.4952 |
1.5472 | 0.25 | 3 | 1.4159 |
0.9888 | 0.5 | 6 | 0.6722 |
0.1057 | 0.75 | 9 | 0.0325 |
0.0412 | 1.0 | 12 | 0.0113 |
0.0136 | 1.25 | 15 | 0.0058 |
0.0054 | 1.5 | 18 | 0.0048 |
0.0053 | 1.75 | 21 | 0.0040 |
0.0087 | 2.0 | 24 | 0.0041 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 28
Model tree for dimasik87/edb41855-7266-4205-a88c-20f868ce28d0
Base model
meta-llama/Meta-Llama-3-8B-Instruct