You can deploy this model and start earning money today!

romainnn/
6a7751e5-d3c7-4a6c-a85b-da1dc69012e4

Name: 6a7751e5-d3c7-4a6c-a85b-da1dc69012e4
Availability: InStock

generated_from_trainer

Qwen/Qwen2-7B-Instruct

adapter

apache-2.0

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: Qwen/Qwen2-7B-Instruct
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - bd57acaff8182e57_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/bd57acaff8182e57_train_data.json
  type:
    field_input: testcase
    field_instruction: instruction
    field_output: output
    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/6a7751e5-d3c7-4a6c-a85b-da1dc69012e4
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: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 855
micro_batch_size: 4
mlflow_experiment_name: /tmp/bd57acaff8182e57_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: 0.04230905921575928
wandb_entity: null
wandb_mode: online
wandb_name: e572fc41-d502-496e-a750-44cde70ec9e4
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: e572fc41-d502-496e-a750-44cde70ec9e4
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

6a7751e5-d3c7-4a6c-a85b-da1dc69012e4

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

Loss: 0.1901

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: 855

Training results

Training Loss	Epoch	Step	Validation Loss
0.6361	0.0003	1	0.6258
0.206	0.0283	100	0.2034
0.2387	0.0565	200	0.2012
0.263	0.0848	300	0.1986
0.2191	0.1131	400	0.1958
0.1875	0.1414	500	0.1938
0.2336	0.1696	600	0.1919
0.199	0.1979	700	0.1906
0.2011	0.2262	800	0.1901

Framework versions

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