metadata
library_name: peft
license: llama3.2
base_model: unsloth/Llama-3.2-3B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 1a43e5c4-855d-416a-b8ec-a2a916cb7907
results: []
See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: unsloth/Llama-3.2-3B
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 68ef826ced66c8c7_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/68ef826ced66c8c7_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
device_map:
? ''
: 0,1,2,3,4,5,6,7
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 400
eval_table_size: null
flash_attention: true
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/1a43e5c4-855d-416a-b8ec-a2a916cb7907
hub_repo: null
hub_strategy: null
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
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
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 7351
micro_batch_size: 2
mlflow_experiment_name: /tmp/68ef826ced66c8c7_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
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: 400
sequence_len: 2048
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.033916240452578315
wandb_entity: null
wandb_mode: online
wandb_name: f214522a-6979-41cd-a80c-d566c41b01d8
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: f214522a-6979-41cd-a80c-d566c41b01d8
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null
1a43e5c4-855d-416a-b8ec-a2a916cb7907
This model is a fine-tuned version of unsloth/Llama-3.2-3B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7412
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: 42
- gradient_accumulation_steps: 4
- total_train_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: 7351
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7224 | 0.0001 | 1 | 2.1008 |
| 0.8266 | 0.0225 | 400 | 0.8611 |
| 0.95 | 0.0449 | 800 | 0.8325 |
| 0.916 | 0.0674 | 1200 | 0.8323 |
| 0.9649 | 0.0899 | 1600 | 0.8187 |
| 1.0447 | 0.1123 | 2000 | 0.8094 |
| 0.9421 | 0.1348 | 2400 | 0.8086 |
| 0.759 | 0.1573 | 2800 | 0.8016 |
| 0.8835 | 0.1797 | 3200 | 0.7898 |
| 1.0793 | 0.2022 | 3600 | 0.7785 |
| 0.8628 | 0.2247 | 4000 | 0.7755 |
| 0.8557 | 0.2472 | 4400 | 0.7677 |
| 0.6361 | 0.2696 | 4800 | 0.7604 |
| 0.5638 | 0.2921 | 5200 | 0.7556 |
| 1.1077 | 0.3146 | 5600 | 0.7485 |
| 0.8949 | 0.3370 | 6000 | 0.7458 |
| 0.885 | 0.3595 | 6400 | 0.7437 |
| 1.1648 | 0.3820 | 6800 | 0.7415 |
| 1.0295 | 0.4044 | 7200 | 0.7412 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1