See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: fxmarty/really-tiny-falcon-testing
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 62950d35147ac7fd_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/62950d35147ac7fd_train_data.json
  type:
    field_input: new-context
    field_instruction: new-instruction
    field_output: new-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: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: ardaspear/5f82e1f9-da65-46bd-8980-ad940e82e5da
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: true
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 72GB
max_steps: 100
micro_batch_size: 4
mlflow_experiment_name: /tmp/62950d35147ac7fd_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: false
sample_packing: false
saves_per_epoch: 4
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: leixa-personal
wandb_mode: online
wandb_name: 5f82e1f9-da65-46bd-8980-ad940e82e5da
wandb_project: Gradients-On-Two
wandb_run: your_name
wandb_runid: 5f82e1f9-da65-46bd-8980-ad940e82e5da
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

5f82e1f9-da65-46bd-8980-ad940e82e5da

This model is a fine-tuned version of fxmarty/really-tiny-falcon-testing on the None dataset. It achieves the following results on the evaluation set:

• Loss: 10.9336

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: 4
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_BNB 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
No log	0.0011	1	11.0954
44.3444	0.0102	9	11.0740
44.1568	0.0203	18	11.0313
44.0424	0.0305	27	10.9990
43.9742	0.0406	36	10.9763
43.8749	0.0508	45	10.9577
43.795	0.0610	54	10.9469
43.8452	0.0711	63	10.9395
43.827	0.0813	72	10.9363
43.7551	0.0914	81	10.9349
43.7536	0.1016	90	10.9338
43.7583	0.1118	99	10.9336

Framework versions

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