See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: trl-internal-testing/tiny-random-LlamaForCausalLM
bf16: true
chat_template: llama3
datasets:
- data_files:
  - 23977e381963069e_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/23977e381963069e_train_data.json
  type:
    field_input: context
    field_instruction: instruction
    field_output: response
    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: 2
gradient_checkpointing: true
group_by_length: false
hub_model_id: lesso01/9d8df440-408f-4c41-9534-ea64668b1dc3
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 80GiB
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/23977e381963069e_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: 25
save_strategy: steps
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: 9d8df440-408f-4c41-9534-ea64668b1dc3
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 9d8df440-408f-4c41-9534-ea64668b1dc3
warmup_steps: 10
weight_decay: 0.01
xformers_attention: false

9d8df440-408f-4c41-9534-ea64668b1dc3

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: 10.3667

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 100

Training results

Training Loss	Epoch	Step	Validation Loss
10.3752	0.0093	1	10.3765
10.3749	0.0841	9	10.3760
10.3761	0.1682	18	10.3749
10.3712	0.2523	27	10.3736
10.3724	0.3364	36	10.3722
10.3682	0.4206	45	10.3708
10.3709	0.5047	54	10.3694
10.3672	0.5888	63	10.3682
10.3705	0.6729	72	10.3674
10.3654	0.7570	81	10.3669
10.3666	0.8411	90	10.3667
10.3666	0.9252	99	10.3667

Framework versions

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