You can deploy this model and start earning money today!

CheapsetZero/
5a20d01f-9b30-4e8c-9438-06fc7d83f3e4

Name: 5a20d01f-9b30-4e8c-9438-06fc7d83f3e4
Rating: 2.5 (5 reviews)

generated_from_trainer

unsloth/Qwen2.5-0.5B-Instruct

adapter

apache-2.0

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: unsloth/Qwen2.5-0.5B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - f135eab6c916657f_train_data.json
  ds_type: json
  field: prompt
  path: /workspace/input_data/
  split: train
  type: completion
ddp_find_unused_parameters: false
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 256
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 1
gradient_checkpointing: true
gradient_clipping: 0.5
greater_is_better: false
group_by_length: false
hub_model_id: CheapsetZero/5a20d01f-9b30-4e8c-9438-06fc7d83f3e4
learning_rate: 0.0002
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_nan_inf_filter: true
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_steps: 4896
metric_for_best_model: eval_loss
micro_batch_size: 16
min_lr: 1.5000000000000002e-05
mlflow_experiment_name: /tmp/f135eab6c916657f_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
reward_model_sampling_temperature: 0.7
s2_attention: null
sample_packing: false
save_total_limit: 3
saves_per_epoch: 4
sequence_len: 768
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trl:
  beta: 0.08
  max_completion_length: 1024
  num_generations: 16
  reward_funcs:
  - rewards_0f567adf-46fb-4da6-8fb5-2c3e48200314.reward_high_syllables_per_word
  reward_weights:
  - 7.304164465854353
  use_vllm: false
trust_remote_code: true
use_ema: false
use_peft: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: offline
wandb_name: 0f567adf-46fb-4da6-8fb5-2c3e48200314
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 0f567adf-46fb-4da6-8fb5-2c3e48200314
warmup_steps: 244
weight_decay: 0.01
xformers_attention: null

5a20d01f-9b30-4e8c-9438-06fc7d83f3e4

This model is a fine-tuned version of unsloth/Qwen2.5-0.5B-Instruct 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: 16
eval_batch_size: 16
seed: 42
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: 244
training_steps: 2819

Training results

Training Loss	Epoch	Step	Validation Loss
0.0	0.0011	1	nan
0.0	0.25	235	nan
0.0	0.5	470	nan
0.0	0.75	705	nan
1.8103	1.0	940	nan
0.0	1.25	1175	nan
1.7843	1.5	1410	nan
0.0	1.75	1645	nan
0.0	2.0	1880	nan
0.0	2.25	2115	nan
0.0	2.5	2350	nan
0.0	2.75	2585	nan

Framework versions

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