See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: NousResearch/Meta-Llama-3-8B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 32b7ba7519ab12ef_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/32b7ba7519ab12ef_train_data.json
type:
field_input: chosen
field_instruction: prompt
field_output: response
format: '{instruction} {input}'
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: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: dimasik87/ac551efb-eadd-43a3-b370-a3eed27d3cbe
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
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: cosine
max_memory:
0: 70GiB
max_steps: 50
micro_batch_size: 2
mlflow_experiment_name: /tmp/32b7ba7519ab12ef_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
save_steps: 25
save_strategy: steps
sequence_len: 2028
special_tokens:
pad_token: <|end_of_text|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_dtype: bfloat16
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: ac551efb-eadd-43a3-b370-a3eed27d3cbe
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: ac551efb-eadd-43a3-b370-a3eed27d3cbe
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null
ac551efb-eadd-43a3-b370-a3eed27d3cbe
This model is a fine-tuned version of NousResearch/Meta-Llama-3-8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0091
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- 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: 50
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.1314 | 0.0001 | 1 | 0.2797 |
0.2264 | 0.0003 | 5 | 0.2366 |
0.0519 | 0.0007 | 10 | 0.0734 |
0.0148 | 0.0010 | 15 | 0.0237 |
0.0061 | 0.0014 | 20 | 0.0122 |
0.0008 | 0.0017 | 25 | 0.0119 |
0.0103 | 0.0020 | 30 | 0.0148 |
0.0008 | 0.0024 | 35 | 0.0094 |
0.0125 | 0.0027 | 40 | 0.0103 |
0.0052 | 0.0030 | 45 | 0.0093 |
0.0054 | 0.0034 | 50 | 0.0091 |
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
- 7
Model tree for dimasik87/ac551efb-eadd-43a3-b370-a3eed27d3cbe
Base model
NousResearch/Meta-Llama-3-8B