You can deploy this model and start earning money today!

CheapsetZero/
6551461e-5004-46af-b09f-f540f984c5cd

Name: 6551461e-5004-46af-b09f-f540f984c5cd
Availability: InStock

generated_from_trainer

unsloth/SmolLM-1.7B-Instruct

adapter

apache-2.0

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: unsloth/SmolLM-1.7B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - cd01db5ca4dbbd8a_train_data.json
  ds_type: json
  field: prompt
  path: /workspace/input_data/
  split: train
  type: completion
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: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: false
group_by_length: false
hub_model_id: CheapsetZero/6551461e-5004-46af-b09f-f540f984c5cd
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0005
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 50
micro_batch_size: 8
mlflow_experiment_name: /tmp/cd01db5ca4dbbd8a_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trl:
  beta: 0.1
  max_completion_length: 512
  num_generations: 8
  reward_funcs:
  - rewards_88d11139-97ae-46bf-9b1b-83c5ff6b73b3.reward_long_sentences
  - rewards_88d11139-97ae-46bf-9b1b-83c5ff6b73b3.reward_low_unique_words_percentage
  - rewards_88d11139-97ae-46bf-9b1b-83c5ff6b73b3.reward_short_words
  - rewards_88d11139-97ae-46bf-9b1b-83c5ff6b73b3.reward_high_difficult_words_percentage
  - rewards_88d11139-97ae-46bf-9b1b-83c5ff6b73b3.reward_low_syllables_per_word
  reward_weights:
  - 7.308181527219642
  - 0.7767976113257047
  - 1.827829375127008
  - 7.132576348927261
  - 4.530017204000101
  use_vllm: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 88d11139-97ae-46bf-9b1b-83c5ff6b73b3
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 88d11139-97ae-46bf-9b1b-83c5ff6b73b3
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

6551461e-5004-46af-b09f-f540f984c5cd

This model is a fine-tuned version of unsloth/SmolLM-1.7B-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: 0.0005
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
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: 10
training_steps: 50

Training results

Epoch	Step	Validation Loss
0.0001	1	nan
0.0008	7	nan
0.0016	14	nan
0.0025	21	nan
0.0033	28	nan
0.0041	35	nan
0.0049	42	nan
0.0057	49	nan

Framework versions

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