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:
  - c77c3f7427cc6755_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/c77c3f7427cc6755_train_data.json
  type:
    field_instruction: instruction
    field_output: response
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 100
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: true
hub_model_id: lesso08/6327705c-49b9-4714-8e58-fd2f1ca23058
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000208
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 128
lora_dropout: 0.15
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 800
micro_batch_size: 4
mlflow_experiment_name: /tmp/c77c3f7427cc6755_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 100
saves_per_epoch: null
seed: 80
sequence_len: 1024
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: null
wandb_mode: online
wandb_name: f5b4b805-5bc2-42ac-a909-e914a1d05432
wandb_project: 08a
wandb_run: your_name
wandb_runid: f5b4b805-5bc2-42ac-a909-e914a1d05432
warmup_steps: 100
weight_decay: 0.0
xformers_attention: null

6327705c-49b9-4714-8e58-fd2f1ca23058

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: 0.3018

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: 0.000208
• train_batch_size: 4
• eval_batch_size: 4
• seed: 80
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100
• training_steps: 800

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	0.6721
3.1287	0.0135	100	0.4423
3.0146	0.0271	200	0.4380
2.9837	0.0406	300	0.4099
2.8623	0.0542	400	0.3800
2.7309	0.0677	500	0.3479
2.5525	0.0813	600	0.3238
2.4616	0.0948	700	0.3050
2.4122	0.1083	800	0.3018

Framework versions

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