See axolotl config

axolotl version: 0.6.0

adapter: lora
base_model: echarlaix/tiny-random-PhiForCausalLM
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - b8d5a1b8325b7097_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/b8d5a1b8325b7097_train_data.json
  type:
    field_input: source
    field_instruction: prompt_type
    field_output: input
    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: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: false
group_by_length: true
hub_model_id: jssky/530f1140-b64f-4828-b7d0-807218b52ab6
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: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 1500
micro_batch_size: 2
mlflow_experiment_name: /tmp/b8d5a1b8325b7097_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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: 1024
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: fe22c41a-675f-47c6-8a0c-7298fb167991
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: fe22c41a-675f-47c6-8a0c-7298fb167991
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

530f1140-b64f-4828-b7d0-807218b52ab6

This model is a fine-tuned version of echarlaix/tiny-random-PhiForCausalLM on the None dataset. It achieves the following results on the evaluation set:

• Loss: 6.8349

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: 16
• total_train_batch_size: 32
• optimizer: Use adamw_bnb_8bit 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: 1500

Training results

Training Loss	Epoch	Step	Validation Loss
6.8557	0.0469	375	6.8476
6.7582	0.0938	750	6.8384
6.8436	0.1408	1125	6.8353
6.7472	0.1877	1500	6.8349

Framework versions

• PEFT 0.14.0
• Transformers 4.46.3
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3