You can deploy this model and start earning money today!

tryingpro/
e529b0f9-3b27-4579-ae5f-915f723627ac

Name: e529b0f9-3b27-4579-ae5f-915f723627ac
Availability: InStock

generated_from_trainer

JackFram/llama-160m

adapter

apache-2.0

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: JackFram/llama-160m
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 56545c5943e24039_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/56545c5943e24039_train_data.json
  type:
    field_input: lang
    field_instruction: sentence
    field_output: modified
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 256
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: false
hub_model_id: tryingpro/e529b0f9-3b27-4579-ae5f-915f723627ac
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 3
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_grad_norm: 2
max_steps: 90
micro_batch_size: 2
mlflow_experiment_name: /tmp/56545c5943e24039_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
optimizer: adamw_torch
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: 2048
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: tryingpro-unicourt
wandb_mode: online
wandb_name: 208abd5d-0ed8-4d77-9397-1ec5ff508ff0
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 208abd5d-0ed8-4d77-9397-1ec5ff508ff0
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

e529b0f9-3b27-4579-ae5f-915f723627ac

This model is a fine-tuned version of JackFram/llama-160m on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.0171

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: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 32
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-05
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 20
training_steps: 90

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0003	1	3.9976
3.5493	0.0025	8	3.5823
2.6376	0.0049	16	2.4332
1.6306	0.0074	24	1.7077
1.4292	0.0099	32	1.4497
1.2395	0.0123	40	1.3151
1.2899	0.0148	48	1.1905
1.0184	0.0173	56	1.1038
0.9975	0.0197	64	1.0508
1.1134	0.0222	72	1.0286
0.9458	0.0247	80	1.0191
0.9936	0.0271	88	1.0171

Framework versions

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