See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: trl-internal-testing/tiny-random-LlamaForCausalLM
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 74f2973513629fe9_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/74f2973513629fe9_train_data.json
  type:
    field_input: taxa
    field_instruction: gene_type
    field_output: msa
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config:
  max_steps: 50
  weight_decay: 0.01
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: nadejdatarabukina/66e382fe-f019-4a3a-8964-27bc12c38fb3
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_memory:
  0: 70GiB
max_steps: 50
micro_batch_size: 2
mlflow_experiment_name: /tmp/74f2973513629fe9_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 70
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 66e382fe-f019-4a3a-8964-27bc12c38fb3
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 66e382fe-f019-4a3a-8964-27bc12c38fb3
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

66e382fe-f019-4a3a-8964-27bc12c38fb3

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

• Loss: 10.3443

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_TORCH 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
10.3604	0.0006	1	10.3623
10.3614	0.0030	5	10.3617
10.3592	0.0059	10	10.3596
10.3556	0.0089	15	10.3565
10.353	0.0118	20	10.3534
10.3498	0.0148	25	10.3505
10.3487	0.0177	30	10.3479
10.3453	0.0207	35	10.3461
10.3454	0.0236	40	10.3450
10.3431	0.0266	45	10.3444
10.3428	0.0296	50	10.3443

Framework versions

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