You can deploy this model and start earning money today!

romainnn/
4dd8b072-b54a-4048-841c-1d18f16ddf8f

Name: 4dd8b072-b54a-4048-841c-1d18f16ddf8f
Availability: InStock

generated_from_trainer

Qwen/Qwen2.5-Math-7B-Instruct

adapter

apache-2.0

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: Qwen/Qwen2.5-Math-7B-Instruct
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 2f13b1554c22829e_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2f13b1554c22829e_train_data.json
  type:
    field_input: principle
    field_instruction: domain
    field_output: goal
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 2
early_stopping_threshold: 0.0001
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: romainnn/4dd8b072-b54a-4048-841c-1d18f16ddf8f
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.3
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 744
micro_batch_size: 4
mlflow_experiment_name: /tmp/2f13b1554c22829e_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
save_steps: 100
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.015525587721123182
wandb_entity: null
wandb_mode: online
wandb_name: 27b32cdb-ac8e-43c3-a972-d532845d8b51
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 27b32cdb-ac8e-43c3-a972-d532845d8b51
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

4dd8b072-b54a-4048-841c-1d18f16ddf8f

This model is a fine-tuned version of Qwen/Qwen2.5-Math-7B-Instruct on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3151

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
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: 744

Training results

Training Loss	Epoch	Step	Validation Loss
8.1236	0.0001	1	8.3928
0.3505	0.0101	100	0.3478
0.3372	0.0202	200	0.3421
0.361	0.0303	300	0.3321
0.3182	0.0404	400	0.3270
0.2996	0.0505	500	0.3198
0.3184	0.0606	600	0.3171
0.3009	0.0707	700	0.3151

Framework versions

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