See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Yarn-Solar-10b-64k
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - f69997622e88b2e2_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/f69997622e88b2e2_train_data.json
  type:
    field_input: Query
    field_instruction: Prompt
    field_output: Response
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 5
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: oldiday/07842df3-503d-4d79-9f21-35a929ea2e5a
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
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_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 600
micro_batch_size: 8
mlflow_experiment_name: /tmp/f69997622e88b2e2_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
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
saves_per_epoch: null
sequence_len: 512
special_tokens:
  pad_token: </s>
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: techspear-hub
wandb_mode: online
wandb_name: 6ab3de9b-c6f7-4825-831d-3a8790bdd87a
wandb_project: Gradients-On-Six
wandb_run: your_name
wandb_runid: 6ab3de9b-c6f7-4825-831d-3a8790bdd87a
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

07842df3-503d-4d79-9f21-35a929ea2e5a

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: 1.8307

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: 8
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 600

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0002	1	2.4169
8.7825	0.0090	50	2.1226
8.3004	0.0181	100	2.0489
8.2362	0.0271	150	1.9942
8.1521	0.0361	200	1.9561
7.9439	0.0451	250	1.9264
7.9633	0.0542	300	1.9012
7.848	0.0632	350	1.8796
7.9365	0.0722	400	1.8597
7.8769	0.0813	450	1.8424
8.1112	0.0903	500	1.8346
7.7599	0.0993	550	1.8292
8.0428	0.1083	600	1.8307

Framework versions

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