You can deploy this model and start earning money today!

Alphatao/
2c6413dc-d92f-4df2-8c35-d74ecae5a3d1

Name: 2c6413dc-d92f-4df2-8c35-d74ecae5a3d1
Rating: 2.5 (13 reviews)

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: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 0e8365ce28f10388_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/0e8365ce28f10388_train_data.json
  type:
    field_input: context
    field_instruction: question-X
    field_output: answer-Y
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 2
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: Alphatao/2c6413dc-d92f-4df2-8c35-d74ecae5a3d1
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: 6528
micro_batch_size: 4
mlflow_experiment_name: /tmp/0e8365ce28f10388_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: 0.04
wandb_entity: null
wandb_mode: online
wandb_name: 012ceced-ebc3-4133-9f3b-090d40160419
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 012ceced-ebc3-4133-9f3b-090d40160419
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

2c6413dc-d92f-4df2-8c35-d74ecae5a3d1

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: 1.8993

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: 2039

Training results

Training Loss	Epoch	Step	Validation Loss
5.7618	0.0010	1	5.8334
1.9971	0.0981	100	2.0450
2.0453	0.1962	200	2.0072
2.149	0.2944	300	1.9763
1.8109	0.3925	400	1.9683
1.7674	0.4906	500	1.9461
1.9503	0.5887	600	1.9336
1.9147	0.6869	700	1.9230
1.9247	0.7850	800	1.9150
1.76	0.8831	900	1.8989
1.87	0.9812	1000	1.8904
1.6386	1.0794	1100	1.9086
1.7189	1.1775	1200	1.8993

Framework versions

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