See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: katuni4ka/tiny-random-qwen1.5-moe
bf16: true
chat_template: llama3
datasets:
- data_files:
  - b4d2ba1803d2784f_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/b4d2ba1803d2784f_train_data.json
  type:
    field_instruction: prompt
    field_output: chosen
    format: '{instruction}'
    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: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
hub_model_id: lesso11/eedf5c68-46f9-4642-8562-3d87f73846ad
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
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: 77GiB
max_steps: 50
micro_batch_size: 8
mlflow_experiment_name: /tmp/b4d2ba1803d2784f_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 25
save_strategy: steps
sequence_len: 1024
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: 1c169d6e-e69f-4e42-bc7b-e7be25bc6d95
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 1c169d6e-e69f-4e42-bc7b-e7be25bc6d95
warmup_steps: 10
weight_decay: 0.01
xformers_attention: false

eedf5c68-46f9-4642-8562-3d87f73846ad

This model is a fine-tuned version of katuni4ka/tiny-random-qwen1.5-moe on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.9164

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
11.9302	0.0003	1	11.9307
11.9335	0.0016	5	11.9303
11.9266	0.0032	10	11.9286
11.9255	0.0049	15	11.9261
11.9239	0.0065	20	11.9236
11.9197	0.0081	25	11.9213
11.9239	0.0097	30	11.9193
11.923	0.0113	35	11.9178
11.9169	0.0129	40	11.9169
11.9183	0.0146	45	11.9165
11.9227	0.0162	50	11.9164

Framework versions

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