See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: microsoft/phi-1_5
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 6eed7441b5fcee02_train_data.json
  ds_type: json
  field: task
  path: /workspace/input_data/6eed7441b5fcee02_train_data.json
  type: completion
debug: null
deepspeed: null
device_map: auto
early_stopping_patience: 3
ema_decay: 0.9992
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
greater_is_better: false
group_by_length: false
hub_model_id: JoshMe1/4bac0e6f-4b1f-49c3-b109-fb13a8ece857
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 10
lora_alpha: 256
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: reduce_lr_on_plateau
lr_scheduler_factor: 0.5
lr_scheduler_patience: 2
max_memory:
  0: 130GB
max_steps: 500
metric_for_best_model: eval_loss
micro_batch_size: 4
mlflow_experiment_name: /tmp/6eed7441b5fcee02_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_hf
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 100
saves_per_epoch: null
sequence_len: 2048
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
use_ema: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 21d8ac24-7f66-4238-9a95-d2fd13d13d58
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 21d8ac24-7f66-4238-9a95-d2fd13d13d58
warmup_steps: 200
weight_decay: 0.01
xformers_attention: null

4bac0e6f-4b1f-49c3-b109-fb13a8ece857

This model is a fine-tuned version of microsoft/phi-1_5 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1127

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: reduce_lr_on_plateau
• lr_scheduler_warmup_steps: 200
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	5.3492
0.1362	0.0077	100	0.1291
0.1285	0.0154	200	0.1120
0.1204	0.0231	300	0.1192
0.126	0.0308	400	0.1200
0.1236	0.0385	500	0.1127

Framework versions

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