You can deploy this model and start earning money today!

fats-fme/
2d9a2740-732d-47d2-ba90-804bcad79664

Name: 2d9a2740-732d-47d2-ba90-804bcad79664
Availability: InStock

generated_from_trainer

Qwen/Qwen2-0.5B

adapter

apache-2.0

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: Qwen/Qwen2-0.5B
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 0ff843dae97d4af7_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/
  type:
    field_input: input
    field_instruction: system_prompt
    field_output: reference_answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
early_stopping_patience: 4
environment:
  CUDA_LAUNCH_BLOCKING: '1'
eval_max_new_tokens: 128
eval_sample_packing: false
eval_steps: 100
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: true
hub_model_id: fats-fme/2d9a2740-732d-47d2-ba90-804bcad79664
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 5.0e-06
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
lr_scheduler: constant_with_warmup
max_memory:
  0: 130GB
max_steps: 300
micro_batch_size: 4
mlflow_experiment_name: /tmp/0ff843dae97d4af7_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 5
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: true
save_steps: 100
saves_per_epoch: null
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
use_scaled_dot_product_attention: false
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: b9f13347-e7e7-4d6c-9285-a9b0b48c2d69
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: b9f13347-e7e7-4d6c-9285-a9b0b48c2d69
warmup_steps: 200
weight_decay: 0.03
xformers_attention: null

2d9a2740-732d-47d2-ba90-804bcad79664

This model is a fine-tuned version of Qwen/Qwen2-0.5B on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.7895

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: 5e-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 200
training_steps: 300

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0010	1	1.9487
2.5238	0.0992	100	1.9275
2.0778	0.1984	200	1.8562
1.7961	0.2977	300	1.7895

Framework versions

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