Hugging Face's logo

Nexspear
/
2bb74f15-8c16-4d0d-b1dd-71797c26b916

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
2bb74f15-8c16-4d0d-b1dd-71797c26b916 / README.md
Nexspear's picture
Nexspear
End of training
1369ee7 verified
preview code
|
raw
history blame contribute delete
4.29 kB
metadata
library_name: peft
license: apache-2.0
base_model: dltjdgh0928/test_instruction
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 2bb74f15-8c16-4d0d-b1dd-71797c26b916
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: dltjdgh0928/test_instruction
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 6696aa05f176a686_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/6696aa05f176a686_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    format: '{instruction} {input}'
    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: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: Nexspear/2bb74f15-8c16-4d0d-b1dd-71797c26b916
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 5.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/6696aa05f176a686_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: null
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: techspear-hub
wandb_mode: online
wandb_name: c775b91c-bde5-4fbe-8e68-743d12422d29
wandb_project: Gradients-On-Four
wandb_run: your_name
wandb_runid: c775b91c-bde5-4fbe-8e68-743d12422d29
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

2bb74f15-8c16-4d0d-b1dd-71797c26b916

This model is a fine-tuned version of dltjdgh0928/test_instruction on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1104

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • 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: 100

Training results

Training Loss Epoch Step Validation Loss
No log 0.0001 1 1.4265
5.2099 0.0008 9 1.2637
4.7295 0.0015 18 1.1791
4.6329 0.0023 27 1.1524
4.5452 0.0031 36 1.1379
4.4224 0.0038 45 1.1294
4.5655 0.0046 54 1.1215
4.4129 0.0054 63 1.1172
4.3209 0.0061 72 1.1139
4.3767 0.0069 81 1.1115
4.3995 0.0077 90 1.1106
4.4013 0.0084 99 1.1104

Framework versions

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