See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: microsoft/Phi-3-mini-128k-instruct
bf16: auto
chat_template: llama3
cosine_min_lr_ratio: 0.1
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - 356918e9e6f154d9_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/356918e9e6f154d9_train_data.json
  type:
    field_instruction: title
    field_output: summary
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: '{'''':torch.cuda.current_device()}'
do_eval: true
early_stopping_patience: 1
eval_batch_size: 1
eval_sample_packing: false
eval_steps: 25
evaluation_strategy: steps
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 64
gradient_checkpointing: true
group_by_length: true
hub_model_id: sn56c2/63d6e5e1-4c1e-4c62-9155-bf548946c7e7
hub_repo: stevemonite
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
lora_target_modules:
- q_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 70GiB
max_steps: 457
micro_batch_size: 1
mlflow_experiment_name: /tmp/356918e9e6f154d9_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
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: 50
save_strategy: steps
sequence_len: 2048
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: false
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: 63d6e5e1-4c1e-4c62-9155-bf548946c7e7
wandb_project: god
wandb_run: y030
wandb_runid: 63d6e5e1-4c1e-4c62-9155-bf548946c7e7
warmup_raio: 0.03
warmup_ratio: 0.04
weight_decay: 0.01
xformers_attention: null

63d6e5e1-4c1e-4c62-9155-bf548946c7e7

This model is a fine-tuned version of microsoft/Phi-3-mini-128k-instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3548

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
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 64
• total_train_batch_size: 256
• total_eval_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: cosine
• lr_scheduler_warmup_steps: 18
• training_steps: 457

Training results

Training Loss	Epoch	Step	Validation Loss
100.1855	0.0065	1	1.6956
91.224	0.1619	25	1.4068
94.1133	0.3238	50	1.3826
93.0197	0.4857	75	1.3749
91.5051	0.6476	100	1.3694
90.4118	0.8096	125	1.3663
91.253	0.9715	150	1.3635
84.4847	1.1334	175	1.3622
83.43	1.2953	200	1.3604
86.4043	1.4572	225	1.3591
85.2274	1.6191	250	1.3582
83.7095	1.7810	275	1.3561
83.9212	1.9429	300	1.3534
86.077	2.1048	325	1.3548

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1