You can deploy this model and start earning money today!

abaddon182/
7c75b232-e15e-4929-b678-644953555426

Name: 7c75b232-e15e-4929-b678-644953555426
Availability: InStock

generated_from_trainer

unsloth/Meta-Llama-3.1-8B

adapter

llama3.1

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: unsloth/Meta-Llama-3.1-8B
bf16: auto
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
  - 6ce0953de243dd4c_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/6ce0953de243dd4c_train_data.json
  type:
    field_instruction: ext
    field_output: prompt
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 150
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: abaddon182/7c75b232-e15e-4929-b678-644953555426
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
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_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 1200
micro_batch_size: 4
mlflow_experiment_name: /tmp/6ce0953de243dd4c_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.999
  adam_epsilon: 1e-08
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: 150
saves_per_epoch: null
sequence_len: 512
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: bb6f66ac-93c6-4923-9d84-f73e0abe5248
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: bb6f66ac-93c6-4923-9d84-f73e0abe5248
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

7c75b232-e15e-4929-b678-644953555426

This model is a fine-tuned version of unsloth/Meta-Llama-3.1-8B on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.0319

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: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.999,adam_epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 50
training_steps: 1200

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0019	1	3.5601
2.4543	0.2806	150	2.3317
2.3669	0.5613	300	2.2224
2.3023	0.8419	450	2.0862
1.5739	1.1225	600	2.0609
1.5418	1.4032	750	2.0083
1.5311	1.6838	900	1.9947
1.4957	1.9645	1050	1.9922
1.2456	2.2451	1200	2.0319

Framework versions

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