Alphatao / 8506de0c-efe1-48ec-9251-be484f0af856

huggingface.co
Total runs: 25
24-hour runs: 0
7-day runs: -2
30-day runs: 19
Model's Last Updated: March 06 2025

Introduction of 8506de0c-efe1-48ec-9251-be484f0af856

Model Details of 8506de0c-efe1-48ec-9251-be484f0af856

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

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/8506de0c-efe1-48ec-9251-be484f0af856
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

8506de0c-efe1-48ec-9251-be484f0af856

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: 1.8955
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
1.9927 0.0981 100 2.0468
2.0532 0.1962 200 2.0067
2.1606 0.2944 300 1.9800
1.8224 0.3925 400 1.9714
1.7791 0.4906 500 1.9451
1.931 0.5887 600 1.9355
1.9044 0.6869 700 1.9215
1.9545 0.7850 800 1.9157
1.7429 0.8831 900 1.8967
1.8895 0.9812 1000 1.8883
1.6458 1.0794 1100 1.9046
1.7252 1.1775 1200 1.8955
Framework versions
  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1

Runs of Alphatao 8506de0c-efe1-48ec-9251-be484f0af856 on huggingface.co

25
Total runs
0
24-hour runs
0
3-day runs
-2
7-day runs
19
30-day runs

More Information About 8506de0c-efe1-48ec-9251-be484f0af856 huggingface.co Model

More 8506de0c-efe1-48ec-9251-be484f0af856 license Visit here:

https://choosealicense.com/licenses/apache-2.0

8506de0c-efe1-48ec-9251-be484f0af856 huggingface.co

8506de0c-efe1-48ec-9251-be484f0af856 huggingface.co is an AI model on huggingface.co that provides 8506de0c-efe1-48ec-9251-be484f0af856's model effect (), which can be used instantly with this Alphatao 8506de0c-efe1-48ec-9251-be484f0af856 model. huggingface.co supports a free trial of the 8506de0c-efe1-48ec-9251-be484f0af856 model, and also provides paid use of the 8506de0c-efe1-48ec-9251-be484f0af856. Support call 8506de0c-efe1-48ec-9251-be484f0af856 model through api, including Node.js, Python, http.

8506de0c-efe1-48ec-9251-be484f0af856 huggingface.co Url

https://huggingface.co/Alphatao/8506de0c-efe1-48ec-9251-be484f0af856

Alphatao 8506de0c-efe1-48ec-9251-be484f0af856 online free

8506de0c-efe1-48ec-9251-be484f0af856 huggingface.co is an online trial and call api platform, which integrates 8506de0c-efe1-48ec-9251-be484f0af856's modeling effects, including api services, and provides a free online trial of 8506de0c-efe1-48ec-9251-be484f0af856, you can try 8506de0c-efe1-48ec-9251-be484f0af856 online for free by clicking the link below.

Alphatao 8506de0c-efe1-48ec-9251-be484f0af856 online free url in huggingface.co:

https://huggingface.co/Alphatao/8506de0c-efe1-48ec-9251-be484f0af856

8506de0c-efe1-48ec-9251-be484f0af856 install

8506de0c-efe1-48ec-9251-be484f0af856 is an open source model from GitHub that offers a free installation service, and any user can find 8506de0c-efe1-48ec-9251-be484f0af856 on GitHub to install. At the same time, huggingface.co provides the effect of 8506de0c-efe1-48ec-9251-be484f0af856 install, users can directly use 8506de0c-efe1-48ec-9251-be484f0af856 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

8506de0c-efe1-48ec-9251-be484f0af856 install url in huggingface.co:

https://huggingface.co/Alphatao/8506de0c-efe1-48ec-9251-be484f0af856

Url of 8506de0c-efe1-48ec-9251-be484f0af856

8506de0c-efe1-48ec-9251-be484f0af856 huggingface.co Url

Provider of 8506de0c-efe1-48ec-9251-be484f0af856 huggingface.co

Alphatao
ORGANIZATIONS

Other API from Alphatao