See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Yarn-Solar-10b-64k
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 9ee19f1b2e41dcd9_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/9ee19f1b2e41dcd9_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: null
eval_max_new_tokens: 256
eval_steps: 5
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: gavrilstep/0807b43f-e534-4799-abea-42d37fcae847
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 3
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: 75GiB
max_steps: 40
micro_batch_size: 2
mlflow_experiment_name: /tmp/9ee19f1b2e41dcd9_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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: 10
sequence_len: 1024
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: fc72f85c-ef66-41a0-b29e-6c09a60e3524
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: fc72f85c-ef66-41a0-b29e-6c09a60e3524
warmup_steps: 10
weight_decay: 0.01
xformers_attention: true

0807b43f-e534-4799-abea-42d37fcae847

This model is a fine-tuned version of NousResearch/Yarn-Solar-10b-64k on the None dataset. It achieves the following results on the evaluation set:

• Loss: nan

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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: 40

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0019	1	nan
0.0	0.0095	5	nan
0.0	0.0190	10	nan
0.0	0.0285	15	nan
0.0	0.0380	20	nan
0.0	0.0475	25	nan
0.0	0.0570	30	nan
0.0	0.0664	35	nan
0.0	0.0759	40	nan

Framework versions

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