cimol/ba35dac9-bacf-455b-b358-ad2832af61ee
07
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/> <details><summary>See axolotl config</summary>
axolotl version: 0.4.1
adapter: lora
base_model: TitanML/tiny-mixtral
bf16: false
chat_template: llama3
data_processes: 10
dataset_prepared_path: null
datasets:
- data_files:
- f54c9d4f1c67d609_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/f54c9d4f1c67d609_train_data.json
type:
field_instruction: query
field_output: output
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
device_map: auto
distributed_training:
multi_gpu: true
num_gpus: 2
do_eval: true
early_stopping_patience: 4
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: true
hub_model_id: cimol/ba35dac9-bacf-455b-b358-ad2832af61ee
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 7.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 5
lora_alpha: 128
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
lr_scheduler_warmup_steps: 50
max_grad_norm: 1.0
max_steps: 100
micro_batch_size: 2
mlflow_experiment_name: /tmp/f54c9d4f1c67d609_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 1e-8
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: 50
saves_per_epoch: null
seed: 17333
sequence_len: 1024
special_tokens:
pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
total_train_batch_size: 4
train_batch_size: 8
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: fc98de17-d5df-414d-af46-7dc25952c804
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: fc98de17-d5df-414d-af46-7dc25952c804
warmup_steps: 10
weight_decay: 0.01
xformers_attention: true
</details><br>
ba35dac9-bacf-455b-b358-ad2832af61ee
This model is a fine-tuned version of TitanML/tiny-mixtral on the None dataset. It achieves the following results on the evaluation set:
- Loss: 8.9425
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: 7e-05
- trainbatchsize: 2
- evalbatchsize: 4
- seed: 17333
- distributed_type: multi-GPU
- num_devices: 2
- gradientaccumulationsteps: 2
- totaltrainbatch_size: 8
- totalevalbatch_size: 8
- optimizer: Use OptimizerNames.ADAMWBNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=adambeta1=0.9,adambeta2=0.95,adam_epsilon=1e-8
- lrschedulertype: cosine
- lrschedulerwarmup_steps: 10
- training_steps: 100
- mixedprecisiontraining: Native AMP
Training results
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1