See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: JackFram/llama-160m
bf16: true
chat_template: llama3
datasets:
- data_files:
  - 2b85bbf48041fd87_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2b85bbf48041fd87_train_data.json
  type:
    field_input: poem_verses
    field_instruction: poem_title
    field_output: poem_theme
    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: lesso04/43add8cb-08d4-4521-abc0-1167226993fa
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: 77GiB
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/2b85bbf48041fd87_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
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: null
wandb_mode: online
wandb_name: 43add8cb-08d4-4521-abc0-1167226993fa
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 43add8cb-08d4-4521-abc0-1167226993fa
warmup_steps: 10
weight_decay: 0.01
xformers_attention: false

43add8cb-08d4-4521-abc0-1167226993fa

This model is a fine-tuned version of JackFram/llama-160m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2620

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
4.7383	0.0019	1	4.8211
4.0801	0.0175	9	3.9355
2.2625	0.0349	18	2.1969
1.1658	0.0524	27	1.3317
0.8439	0.0698	36	0.8822
0.5331	0.0873	45	0.6151
0.5796	0.1048	54	0.4402
0.4189	0.1222	63	0.3443
0.25	0.1397	72	0.3007
0.1978	0.1571	81	0.2723
0.3042	0.1746	90	0.2629
0.2709	0.1920	99	0.2620

Framework versions

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