metadata
library_name: peft
license: mit
base_model: fxmarty/tiny-random-GemmaForCausalLM
tags:
- axolotl
- generated_from_trainer
model-index:
- name: f51bfe77-a6eb-4b31-8db3-03587638137c
results: []
See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: fxmarty/tiny-random-GemmaForCausalLM
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 5357759852985b4d_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/5357759852985b4d_train_data.json
type:
field_input: Complex_CoT
field_instruction: Question
field_output: Response
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 200
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: baby-dev/f51bfe77-a6eb-4b31-8db3-03587638137c
hub_strategy: end
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: constant
max_grad_norm: 1.0
max_memory:
0: 75GB
max_steps: 23974
micro_batch_size: 4
mlflow_experiment_name: /tmp/5357759852985b4d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 1e-5
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 200
saves_per_epoch: null
sequence_len: 512
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 4825c224-af5c-46aa-8cf7-640b49b5a593
wandb_project: SN56-45
wandb_run: your_name
wandb_runid: 4825c224-af5c-46aa-8cf7-640b49b5a593
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null
f51bfe77-a6eb-4b31-8db3-03587638137c
This model is a fine-tuned version of fxmarty/tiny-random-GemmaForCausalLM on the None dataset. It achieves the following results on the evaluation set:
- Loss: 12.3695
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 50
- training_steps: 14470
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0007 | 1 | 12.4576 |
| 12.4008 | 0.1382 | 200 | 12.4003 |
| 12.395 | 0.2764 | 400 | 12.3943 |
| 12.3938 | 0.4147 | 600 | 12.3938 |
| 12.3923 | 0.5529 | 800 | 12.3918 |
| 12.3906 | 0.6911 | 1000 | 12.3871 |
| 12.3865 | 0.8293 | 1200 | 12.3827 |
| 12.383 | 0.9675 | 1400 | 12.3802 |
| 12.3819 | 1.1057 | 1600 | 12.3794 |
| 12.3811 | 1.2440 | 1800 | 12.3783 |
| 12.3801 | 1.3822 | 2000 | 12.3778 |
| 12.3811 | 1.5204 | 2200 | 12.3772 |
| 12.3805 | 1.6586 | 2400 | 12.3774 |
| 12.3807 | 1.7968 | 2600 | 12.3770 |
| 12.3804 | 1.9350 | 2800 | 12.3774 |
| 12.3793 | 2.0733 | 3000 | 12.3764 |
| 12.38 | 2.2115 | 3200 | 12.3761 |
| 12.3799 | 2.3497 | 3400 | 12.3763 |
| 12.3795 | 2.4879 | 3600 | 12.3758 |
| 12.3809 | 2.6261 | 3800 | 12.3757 |
| 12.3785 | 2.7643 | 4000 | 12.3757 |
| 12.3779 | 2.9026 | 4200 | 12.3755 |
| 12.379 | 3.0408 | 4400 | 12.3753 |
| 12.3781 | 3.1790 | 4600 | 12.3754 |
| 12.3778 | 3.3172 | 4800 | 12.3750 |
| 12.3765 | 3.4554 | 5000 | 12.3751 |
| 12.3777 | 3.5936 | 5200 | 12.3748 |
| 12.3765 | 3.7319 | 5400 | 12.3749 |
| 12.3778 | 3.8701 | 5600 | 12.3746 |
| 12.3788 | 4.0083 | 5800 | 12.3746 |
| 12.3768 | 4.1465 | 6000 | 12.3746 |
| 12.3774 | 4.2847 | 6200 | 12.3742 |
| 12.3774 | 4.4229 | 6400 | 12.3741 |
| 12.3766 | 4.5612 | 6600 | 12.3739 |
| 12.3775 | 4.6994 | 6800 | 12.3738 |
| 12.3769 | 4.8376 | 7000 | 12.3740 |
| 12.3769 | 4.9758 | 7200 | 12.3737 |
| 12.3774 | 5.1140 | 7400 | 12.3736 |
| 12.3754 | 5.2522 | 7600 | 12.3733 |
| 12.3759 | 5.3905 | 7800 | 12.3728 |
| 12.3742 | 5.5287 | 8000 | 12.3728 |
| 12.3764 | 5.6669 | 8200 | 12.3724 |
| 12.3766 | 5.8051 | 8400 | 12.3721 |
| 12.3761 | 5.9433 | 8600 | 12.3720 |
| 12.3746 | 6.0815 | 8800 | 12.3714 |
| 12.3749 | 6.2198 | 9000 | 12.3710 |
| 12.3739 | 6.3580 | 9200 | 12.3710 |
| 12.3743 | 6.4962 | 9400 | 12.3709 |
| 12.3748 | 6.6344 | 9600 | 12.3706 |
| 12.3723 | 6.7726 | 9800 | 12.3706 |
| 12.3738 | 6.9109 | 10000 | 12.3703 |
| 12.3724 | 7.0491 | 10200 | 12.3702 |
| 12.3723 | 7.1873 | 10400 | 12.3696 |
| 12.3728 | 7.3255 | 10600 | 12.3697 |
| 12.3736 | 7.4637 | 10800 | 12.3694 |
| 12.3728 | 7.6019 | 11000 | 12.3698 |
| 12.3735 | 7.7402 | 11200 | 12.3695 |
| 12.3732 | 7.8784 | 11400 | 12.3695 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1