See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: unsloth/Qwen2.5-1.5B
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 4be8682572110d5d_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/4be8682572110d5d_train_data.json
type:
field_input: character
field_instruction: persona
field_output: character_id
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
device_map:
? ''
: 0,1,2,3,4,5,6,7
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: true
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/db71447f-1e04-4261-aa50-cc63e8077ec5
hub_repo: null
hub_strategy: null
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: 128
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 2520
micro_batch_size: 4
mlflow_experiment_name: /tmp/4be8682572110d5d_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: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: e4955556-0159-49c5-83b2-24e0ea708e1c
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: e4955556-0159-49c5-83b2-24e0ea708e1c
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null
db71447f-1e04-4261-aa50-cc63e8077ec5
This model is a fine-tuned version of unsloth/Qwen2.5-1.5B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5792
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: 1140
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.2096 | 0.0018 | 1 | 3.1979 |
2.5828 | 0.1754 | 100 | 2.6026 |
2.5644 | 0.3509 | 200 | 2.5891 |
2.5733 | 0.5263 | 300 | 2.5828 |
2.6094 | 0.7018 | 400 | 2.5820 |
2.5868 | 0.8772 | 500 | 2.5814 |
2.6006 | 1.0526 | 600 | 2.5805 |
2.6019 | 1.2281 | 700 | 2.5801 |
2.5991 | 1.4035 | 800 | 2.5804 |
2.5511 | 1.5789 | 900 | 2.5800 |
2.5873 | 1.7544 | 1000 | 2.5794 |
2.6021 | 1.9298 | 1100 | 2.5792 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 8
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.