Downloads · 30 days
0
0% of all-time downloads
nttx/f088498f-4019-4442-b40f-4f3269245154
f088498f-4019-4442-b40f-4f3269245154 is a machine learning model from nttx. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
0
0% of all-time downloads
All-time downloads
9
Public
Repo size
19.9 GB
Likes
0
Public
Click a slice to open those files.
.safetensors1.3 GB · 57%
From the Hugging Face model README
axolotl version: 0.4.1
adapter: lora
base_model: The-matt/llama2_ko-7b_distinctive-snowflake-182_1060
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 711957066c915e08_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/711957066c915e08_train_data.json
type:
field_input: lang
field_instruction: sentence1
field_output: sentence2
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 2
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: nttx/f088498f-4019-4442-b40f-4f3269245154
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: 50
lora_alpha: 128
lora_dropout: 0.3
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
0: 75GB
max_steps: 3000
micro_batch_size: 4
mlflow_experiment_name: /tmp/711957066c915e08_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 1e-5
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: 384f64d9-6b7f-489b-adae-1e305ea68461
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 384f64d9-6b7f-489b-adae-1e305ea68461
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null
</details><br>
This model is a fine-tuned version of The-matt/llama2_ko-7b_distinctive-snowflake-182_1060 on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0002 | 1 | 3.2424 |
| 1.2631 | 0.0285 | 150 | 1.3433 |
| 1.2315 | 0.0569 | 300 | 1.3181 |
| 1.2071 | 0.0854 | 450 | 1.2266 |
| 1.1785 | 0.1138 | 600 | 1.1900 |
| 1.1557 | 0.1423 | 750 | 1.1578 |
| 1.1348 | 0.1707 | 900 | 1.1419 |
| 1.1172 | 0.1992 | 1050 | 1.0849 |
| 1.0538 | 0.2276 | 1200 | 1.0841 |
| 1.0807 | 0.2561 | 1350 | 1.0309 |
| 1.0398 | 0.2846 | 1500 | 1.0133 |
| 0.9615 | 0.3130 | 1650 | 0.9912 |
| 0.9626 | 0.3415 | 1800 | 0.9637 |
| 0.9436 | 0.3699 | 1950 | 0.9440 |
| 0.9883 | 0.3984 | 2100 | 0.9253 |
| 0.9292 | 0.4268 | 2250 | 0.9096 |
| 0.9373 | 0.4553 | 2400 | 0.8986 |
| 0.9225 | 0.4838 | 2550 | 0.8870 |
| 0.9328 | 0.5122 | 2700 | 0.8821 |
| 0.871 | 0.5407 | 2850 | 0.8804 |
| 0.8514 | 0.5691 | 3000 | 0.8802 |