Downloads · 30 days
2
10% of all-time downloads
cilorku/3d6605d9-3015-4747-adc1-50c3cbccb457
3d6605d9-3015-4747-adc1-50c3cbccb457 is a machine learning model from cilorku. 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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
2
10% of all-time downloads
All-time downloads
20
Public
Repo size
7.1 GB
Likes
0
Public
Click a slice to open those files.
.safetensors2 GB · 57%
From the Hugging Face model README
axolotl version: 0.4.1
adapter: lora
base_model: NousResearch/Yarn-Solar-10b-32k
bf16: true
chat_template: llama3
data_processes: 40
dataset_prepared_path: null
datasets:
- data_files:
- 944428010357d088_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/944428010357d088_train_data.json
type:
field_input: description
field_instruction: input persona
field_output: synthesized text
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: 4
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 250
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: cilorku/3d6605d9-3015-4747-adc1-50c3cbccb457
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 9.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.04
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
lr_scheduler_warmup_steps: 50
max_grad_norm: 1.0
max_memory:
0: 135GB
max_steps: 2000
micro_batch_size: 16
mlflow_experiment_name: /tmp/944428010357d088_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 1e-8
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: 500
saves_per_epoch: null
seed: 17333
sequence_len: 1024
special_tokens:
pad_token: </s>
strict: false
tf32: true
tokenizer_type: AutoTokenizer
total_train_batch_size: 64
train_batch_size: 8
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 2c1e703b-be68-4ed7-980c-0f149857291b
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 2c1e703b-be68-4ed7-980c-0f149857291b
warmup_steps: 300
weight_decay: 0.0
xformers_attention: null
</details><br>
This model is a fine-tuned version of NousResearch/Yarn-Solar-10b-32k 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 |
|---|---|---|---|
| 2.9674 | 0.0014 | 1 | 1.1262 |
| 3.4306 | 0.3382 | 250 | 0.7594 |
| 3.567 | 0.6764 | 500 | 0.7319 |
| 2.0008 | 1.0145 | 750 | 0.6969 |
| 1.8881 | 1.3527 | 1000 | 0.6876 |
| 1.8083 | 1.6909 | 1250 | 0.6635 |
| 1.136 | 2.0291 | 1500 | 0.7033 |
| 1.0433 | 2.3673 | 1750 | 0.7137 |
| 1.1869 | 2.7054 | 2000 | 0.7249 |