metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 5807bbc0-18e4-48a5-aa6e-ba928564ad68
results: []
See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 2fd0d0574a856db9_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/2fd0d0574a856db9_train_data.json
type:
field_instruction: caption
field_output: states_of_matter
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: ardaspear/5807bbc0-18e4-48a5-aa6e-ba928564ad68
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: true
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_memory:
0: 72GB
max_steps: 100
micro_batch_size: 4
mlflow_experiment_name: /tmp/2fd0d0574a856db9_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: false
sample_packing: false
saves_per_epoch: 4
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: leixa-personal
wandb_mode: online
wandb_name: 5807bbc0-18e4-48a5-aa6e-ba928564ad68
wandb_project: Gradients-On-Two
wandb_run: your_name
wandb_runid: 5807bbc0-18e4-48a5-aa6e-ba928564ad68
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null
5807bbc0-18e4-48a5-aa6e-ba928564ad68
This model is a fine-tuned version of Qwen/Qwen2.5-Coder-7B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0012
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0038 | 1 | 10.3854 |
| 5.2104 | 0.0338 | 9 | 1.9947 |
| 0.3104 | 0.0675 | 18 | 0.1860 |
| 0.1533 | 0.1013 | 27 | 0.1180 |
| 0.0679 | 0.1351 | 36 | 0.0529 |
| 0.0276 | 0.1689 | 45 | 0.0394 |
| 0.0028 | 0.2026 | 54 | 0.0202 |
| 0.021 | 0.2364 | 63 | 0.0058 |
| 0.0012 | 0.2702 | 72 | 0.0040 |
| 0.0024 | 0.3039 | 81 | 0.0015 |
| 0.0006 | 0.3377 | 90 | 0.0012 |
| 0.0003 | 0.3715 | 99 | 0.0012 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1