Downloads · 30 days
0
0% of all-time downloads
apriasmoro/732f1749-0827-46e2-8f42-3bba240763eb
732f1749-0827-46e2-8f42-3bba240763eb is a machine learning model from apriasmoro. 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
17
Public
Repo size
198 MB
Likes
0
Public
Click a slice to open those files.
.safetensors22.6 MB · 57%
From the Hugging Face model README
axolotl version: 0.10.0.dev0
adapter: lora
base_model: samoline/a1f70de9-9a4a-4ead-84f4-71761ee932ca
bf16: true
chat_template: llama3
datasets:
- data_files:
- 48d38ee9ca83f6bf_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/
type:
field_input: input
field_instruction: instruct
field_output: output
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
eval_max_new_tokens: 256
evals_per_epoch: 2
flash_attention: false
fp16: false
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: true
hub_model_id: apriasmoro/732f1749-0827-46e2-8f42-3bba240763eb
learning_rate: 0.0002
logging_steps: 10
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: false
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 304
micro_batch_size: 8
mlflow_experiment_name: /tmp/48d38ee9ca83f6bf_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
sample_packing: false
save_steps: 38
sequence_len: 2048
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: 1e8a58e3-a4c1-41a5-8a72-bc820ee1d9d6
wandb_project: Gradients-On-Demand
wandb_run: apriasmoro
wandb_runid: 1e8a58e3-a4c1-41a5-8a72-bc820ee1d9d6
warmup_steps: 100
weight_decay: 0.01
</details><br>
This model is a fine-tuned version of samoline/a1f70de9-9a4a-4ead-84f4-71761ee932ca on an unknown 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 | 0.0018 | 1 | 1.2509 |
| 2.0158 | 0.0934 | 51 | 1.1848 |
| 1.738 | 0.1868 | 102 | 1.1831 |
| 1.7298 | 0.2802 | 153 | 1.1562 |
| 1.7872 | 0.3736 | 204 | 1.1230 |
| 1.7758 | 0.4670 | 255 | 1.1069 |