Downloads · 30 days
4
19% of all-time downloads
marialvsantiago/af0a7349-808c-4ca0-905d-36be1503bc70
af0a7349-808c-4ca0-905d-36be1503bc70 is a machine learning model from marialvsantiago. 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. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
4
19% of all-time downloads
All-time downloads
21
Public
Repo size
567 MB
Likes
0
Public
Click a slice to open those files.
.pt113 MB · 39%
From the Hugging Face model README
axolotl version: 0.4.1
adapter: lora
base_model: facebook/opt-1.3b
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 65572158eadcb17c_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/65572158eadcb17c_train_data.json
type:
field_input: premise
field_instruction: question
field_output: choice1
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: 1
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: marialvsantiago/af0a7349-808c-4ca0-905d-36be1503bc70
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: 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_memory:
0: 79GiB
max_steps: 30
micro_batch_size: 4
mlflow_experiment_name: /tmp/65572158eadcb17c_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optim_args:
adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 1e-5
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 10
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 66a88d5c-56b8-450e-9ecb-64515b862823
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 66a88d5c-56b8-450e-9ecb-64515b862823
warmup_steps: 5
weight_decay: 0.001
xformers_attention: true
</details><br>
This model is a fine-tuned version of facebook/opt-1.3b 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 | 0.0187 | 1 | 7.0894 |
| 26.6897 | 0.0935 | 5 | 6.1494 |
| 22.0865 | 0.1869 | 10 | 4.7596 |
| 18.0035 | 0.2804 | 15 | 4.1775 |
| 17.1857 | 0.3738 | 20 | 3.9177 |
| 15.3555 | 0.4673 | 25 | 3.7748 |
| 15.2545 | 0.5607 | 30 | 3.7500 |