metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- generated_from_trainer
model-index:
- name: miner_id_24
results: []
See axolotl config
axolotl version: 0.4.1
adapter: lora
auto_find_batch_size: true
base_model: Qwen/Qwen2.5-7B-Instruct
bf16: auto
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
- 0258260fff514215_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/0258260fff514215_train_data.json
type:
field_input: Context
field_instruction: Claim
field_output: Inconsistent Context-Span
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience:
early_stopping_threshold: 0.0001
eval_max_new_tokens: 128
eval_steps:
eval_strategy: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: false
group_by_length: false
hub_model_id:
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0004
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps:
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 1
micro_batch_size: 32
mlflow_experiment_name: /tmp/0258260fff514215_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 100
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: /workspace/hub_repo/last-checkpoint
s2_attention: null
sample_packing: false
save_steps:
saves_per_epoch: 0
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.0
wandb_entity: null
wandb_mode: disabled
wandb_name: 7ce57913-98f3-40da-a864-33f8df60155d
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 7ce57913-98f3-40da-a864-33f8df60155d
warmup_steps: 100
weight_decay: 0.0
xformers_attention: null
miner_id_24
This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1909
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: 0.0004
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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: 100
- training_steps: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0021 | 1 | 5.5854 |
| 2.5076 | 0.1101 | 52 | 0.4229 |
| 0.2709 | 0.2201 | 104 | 0.2650 |
| 0.2372 | 0.3302 | 156 | 0.2207 |
| 0.197 | 0.4402 | 208 | 0.2383 |
| 0.1677 | 0.5503 | 260 | 0.2076 |
| 0.1963 | 0.6603 | 312 | 0.2016 |
| 0.192 | 0.7704 | 364 | 0.1909 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1