See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: fxmarty/tiny-llama-fast-tokenizer
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - b3a9688ba2138862_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/b3a9688ba2138862_train_data.json
  type:
    field_instruction: instruction
    field_output: response
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 256
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: false
hub_model_id: tryingpro/3f82fb01-a38c-432f-9abd-937215e2c9d1
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: 3
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
- k_proj
- v_proj
- o_proj
- gate_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_grad_norm: 2
max_steps: 90
micro_batch_size: 2
mlflow_experiment_name: /tmp/b3a9688ba2138862_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
optimizer: adamw_torch
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: 2048
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: tryingpro-unicourt
wandb_mode: online
wandb_name: 54c47ee9-c166-45ef-90de-b726d8040c37
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 54c47ee9-c166-45ef-90de-b726d8040c37
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

3f82fb01-a38c-432f-9abd-937215e2c9d1

This model is a fine-tuned version of fxmarty/tiny-llama-fast-tokenizer on the None dataset. It achieves the following results on the evaluation set:

• Loss: 10.3578

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: 32
• total_train_batch_size: 64
• 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-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• training_steps: 90

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0006	1	10.3792
10.3804	0.0051	8	10.3789
10.3791	0.0102	16	10.3779
10.3774	0.0153	24	10.3756
10.3739	0.0204	32	10.3714
10.3678	0.0254	40	10.3653
10.3625	0.0305	48	10.3608
10.3604	0.0356	56	10.3589
10.3588	0.0407	64	10.3582
10.3586	0.0458	72	10.3579
10.3585	0.0509	80	10.3578
10.3575	0.0560	88	10.3578

Framework versions

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