See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: NousResearch/Yarn-Mistral-7b-128k
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 478a728aef80630a_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/478a728aef80630a_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: false
group_by_length: true
hub_model_id: tuantmdev/685940b0-6137-4dea-873e-f54936302b99
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 1e-4
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 40
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_grad_norm: 1.0
max_steps: 400
micro_batch_size: 2
mlflow_experiment_name: /tmp/478a728aef80630a_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 50
save_strategy: steps
sequence_len: 512
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: 7ce94ff2-a64e-4b40-b40f-e2103588a456
wandb_project: Gradients-On-Demand
wandb_run: unknown
wandb_runid: 7ce94ff2-a64e-4b40-b40f-e2103588a456
warmup_steps: 80
weight_decay: 0.0
xformers_attention: null

685940b0-6137-4dea-873e-f54936302b99

This model is a fine-tuned version of NousResearch/Yarn-Mistral-7b-128k on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3853

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• 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: 80
• training_steps: 400

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0010	1	0.7596
3.9989	0.0478	50	0.4616
3.6408	0.0956	100	0.4839
3.5644	0.1434	150	0.4791
3.1311	0.1913	200	0.4448
3.3588	0.2391	250	0.4165
3.4291	0.2869	300	0.3969
3.399	0.3347	350	0.3856
3.1352	0.3825	400	0.3853

Framework versions

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