See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: unsloth/gemma-7b-it
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- a271550a67384169_train_data.json
ds_type: json
field: texte
path: /workspace/input_data/a271550a67384169_train_data.json
type: completion
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 1
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 1
gradient_checkpointing: true
group_by_length: false
hub_model_id: nbninh/498b62f0-6bf1-431e-b65c-8a37347f9c24
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 0.0001
load_in_4bit: true
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_steps: 50
micro_batch_size: 1
mlflow_experiment_name: /tmp/a271550a67384169_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 1
sequence_len: 2048
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: 498b62f0-6bf1-431e-b65c-8a37347f9c24
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 498b62f0-6bf1-431e-b65c-8a37347f9c24
warmup_steps: 10
weight_decay: 0.0
xformers_attention: true
498b62f0-6bf1-431e-b65c-8a37347f9c24
This model is a fine-tuned version of unsloth/gemma-7b-it on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2044
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_BNB 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: 50
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.9831 | 0.0280 | 50 | 2.2044 |
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
- 1
Model tree for nbninh/498b62f0-6bf1-431e-b65c-8a37347f9c24
Base model
unsloth/gemma-7b-it