See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Meta-Llama-3-8B
bf16: true
chat_template: llama3
dataloader_num_workers: 24
dataset_prepared_path: null
datasets:
- data_files:
  - b2e7c777e34e2e3a_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/b2e7c777e34e2e3a_train_data.json
  type:
    field_input: mesh_terms
    field_instruction: title
    field_output: abstract
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 2
eval_max_new_tokens: 128
eval_steps: 300
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: abaddon182/05380c2d-21e9-4c3c-9d62-bb7b21c4f11c
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: 3000
micro_batch_size: 2
mlflow_experiment_name: /tmp/b2e7c777e34e2e3a_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1000
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.999
  adam_epsilon: 1e-8
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 300
saves_per_epoch: null
sequence_len: 512
special_tokens:
  pad_token: <|end_of_text|>
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: ebc1d32b-fcce-4618-af23-91cae11e666e
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: ebc1d32b-fcce-4618-af23-91cae11e666e
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

05380c2d-21e9-4c3c-9d62-bb7b21c4f11c

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: 1.7026

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: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.999,adam_epsilon=1e-8
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 3000

Training results

Training Loss	Epoch	Step	Validation Loss
1.5364	0.0000	1	1.8703
1.9588	0.0073	300	1.7685
1.9918	0.0145	600	1.7515
2.1918	0.0218	900	1.7420
2.1336	0.0290	1200	1.7366
2.0281	0.0363	1500	1.7234
2.0135	0.0435	1800	1.7152
1.8346	0.0508	2100	1.7085
1.949	0.0580	2400	1.7053
2.2682	0.0653	2700	1.7031
1.7266	0.0725	3000	1.7026

Framework versions

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