You can deploy this model and start earning money today!

JoshMe1/
3c2f6813-9dbf-48ac-a042-62a07d010439

Name: 3c2f6813-9dbf-48ac-a042-62a07d010439
Availability: InStock

generated_from_trainer

Qwen/Qwen2.5-0.5B

adapter

apache-2.0

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: Qwen/Qwen2.5-0.5B
bf16: false
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - deaa3c221395db45_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/deaa3c221395db45_train_data.json
  type:
    field_input: question_en
    field_instruction: question
    field_output: answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
ema_decay: 0.9992
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: true
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: JoshMe1/3c2f6813-9dbf-48ac-a042-62a07d010439
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: 1
lora_alpha: 32
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 0.3
max_steps: 500
micro_batch_size: 8
mlflow_experiment_name: /tmp/deaa3c221395db45_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_hf
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
trust_remote_code: true
use_ema: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 692b97c6-2969-485c-8f62-79a58340c54f
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 692b97c6-2969-485c-8f62-79a58340c54f
warmup_ratio: 0.03
weight_decay: 0.01
xformers_attention: true

3c2f6813-9dbf-48ac-a042-62a07d010439

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.7969

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_HF 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: 15
training_steps: 500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.0599	0.0004	1	1.0133
0.8315	0.0440	125	0.8653
0.7874	0.0880	250	0.8137
0.8329	0.1320	375	0.7990
0.8801	0.1760	500	0.7969

Framework versions

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