See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: katuni4ka/tiny-random-falcon-40b
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 1ed05c663c7d03c9_train_data.json
  ds_type: json
  field: text
  path: /workspace/input_data/1ed05c663c7d03c9_train_data.json
  type: completion
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 3
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 6
gradient_checkpointing: true
group_by_length: false
hub_model_id: dimasik87/215b0d7a-ffe6-4846-9c5e-b572c0e8e862
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: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 70GiB
max_steps: 50
micro_batch_size: 4
mlflow_experiment_name: /tmp/1ed05c663c7d03c9_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: 2048
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_dtype: bfloat16
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 215b0d7a-ffe6-4846-9c5e-b572c0e8e862
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 215b0d7a-ffe6-4846-9c5e-b572c0e8e862
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

215b0d7a-ffe6-4846-9c5e-b572c0e8e862

This model is a fine-tuned version of katuni4ka/tiny-random-falcon-40b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 10.9848

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 6
• total_train_batch_size: 24
• 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
66.6603	0.0003	1	11.1075
66.6068	0.0015	6	11.1015
66.4966	0.0030	12	11.0795
66.2697	0.0046	18	11.0519
66.2157	0.0061	24	11.0262
66.0429	0.0076	30	11.0060
65.9892	0.0091	36	10.9927
65.8852	0.0107	42	10.9864
65.9682	0.0122	48	10.9848

Framework versions

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