You can deploy this model and start earning money today!

mrferr3t/
97a410f8-7c5b-4770-b967-ba92482790ca

Name: 97a410f8-7c5b-4770-b967-ba92482790ca
Availability: InStock

generated_from_trainer

aisingapore/Llama-SEA-LION-v2-8B-IT

adapter

llama3

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
auto_find_batch_size: false
base_model: aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct
bf16: auto
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
  - 08da8533d861e152_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/08da8533d861e152_train_data.json
  type:
    field_instruction: query
    field_output: answer
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 2
early_stopping_threshold: 1.0e-05
eval_max_new_tokens: 128
eval_steps: 115
eval_strategy: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 3
gradient_checkpointing: false
group_by_length: false
hub_model_id: mrferr3t/97a410f8-7c5b-4770-b967-ba92482790ca
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: 115
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: null
micro_batch_size: 6
mlflow_experiment_name: /tmp/08da8533d861e152_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: null
s2_attention: null
sample_packing: false
save_steps: 115
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: .05000000
wandb_entity: null
wandb_mode: disabled
wandb_name: 244e3a94-d823-4a6c-820e-b10442e313f6
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 244e3a94-d823-4a6c-820e-b10442e313f6
warmup_steps: 100
weight_decay: 0.0
xformers_attention: null

97a410f8-7c5b-4770-b967-ba92482790ca

This model is a fine-tuned version of aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1574

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: 6
eval_batch_size: 6
seed: 42
gradient_accumulation_steps: 3
total_train_batch_size: 18
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
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0019	1	0.8061
0.2988	0.2167	115	0.1717
0.1723	0.4334	230	0.1629
0.1675	0.6501	345	0.1631
0.1606	0.8668	460	0.1544
0.1498	1.0842	575	0.1584
0.1411	1.3009	690	0.1574

Framework versions

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