See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: trl-internal-testing/tiny-random-LlamaForCausalLM
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 601b6aeac5662af3_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/601b6aeac5662af3_train_data.json
  type:
    field_instruction: prediction_agent
    field_output: text
    format: '{instruction}'
    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: 1
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: false
hub_model_id: error577/f80b9134-90c2-4c67-92c6-2aa821f6fe35
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 0.0000005
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
#lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
#max_steps: 1000
micro_batch_size: 2
mlflow_experiment_name: /tmp/601b6aeac5662af3_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
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: 1
sequence_len: 512
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: e8dc62d6-3055-4e48-a688-0e0030a94ed7
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: e8dc62d6-3055-4e48-a688-0e0030a94ed7
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

f80b9134-90c2-4c67-92c6-2aa821f6fe35

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: 10.3785

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: 5e-07
• 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=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
10.3781	0.0141	1	10.3788
10.3795	0.9894	70	10.3787
10.7924	1.9828	140	10.3787
10.3258	2.9761	210	10.3786
10.0967	3.9695	280	10.3786
10.5201	4.9629	350	10.3785
10.3242	5.9563	420	10.3785
10.5056	6.9496	490	10.3785
10.5823	7.9430	560	10.3785
10.5136	8.9364	630	10.3785
10.0944	9.9298	700	10.3785

Framework versions

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