See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: unsloth/gemma-2-2b-it
bf16: false
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 87abe4d80b97880d_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/87abe4d80b97880d_train_data.json
type:
field_input: input
field_instruction: instruction
field_output: output
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
devices:
- 0
- 1
- 2
- 3
- 4
- 5
- 6
- 7
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: false
group_by_length: false
hub_model_id: jssky/cd45bd18-ae14-49e0-a27b-76db2c9ff747
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: 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: 10
micro_batch_size: 1
mlflow_experiment_name: /tmp/87abe4d80b97880d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
num_gpus: 8
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: 4
sequence_len: 4056
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_batch_size: 32
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: cd45bd18-ae14-49e0-a27b-76db2c9ff747
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: cd45bd18-ae14-49e0-a27b-76db2c9ff747
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null
cd45bd18-ae14-49e0-a27b-76db2c9ff747
This model is a fine-tuned version of unsloth/gemma-2-2b-it on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0102
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
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- 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: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.5602 | 0.0052 | 1 | 2.8289 |
2.7503 | 0.0155 | 3 | 2.6559 |
2.1317 | 0.0311 | 6 | 2.1993 |
2.1536 | 0.0466 | 9 | 2.0102 |
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
- 12
Model tree for jssky/cd45bd18-ae14-49e0-a27b-76db2c9ff747
Base model
unsloth/gemma-2-2b-it