Sponsored by
Vmake Labs Video Enhancer
razhan / Llama3-8b-ckb
Model's Last Updated: June 21 2024
text-generation
Introduction of Llama3-8b-ckb
Model Details of Llama3-8b-ckb
See axolotl config
axolotl version:
0.4.1
base_model: meta-llama/Meta-Llama-3-8B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: razhan/alpaca_ckb
type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./outputs/out
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 100
evals_per_epoch: 2
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
pad_token: <|end_of_text|>
outputs/out
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5749
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9714 | 0.0051 | 1 | 0.9833 |
| 0.6586 | 0.4978 | 98 | 0.6659 |
| 0.5686 | 0.9956 | 196 | 0.5749 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1
Runs of razhan Llama3-8b-ckb on huggingface.co
18
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About Llama3-8b-ckb huggingface.co Model
Url of Llama3-8b-ckb
Llama3-8b-ckb huggingface.co Url
Provider of Llama3-8b-ckb huggingface.co
Other API from razhan
Total runs:
44
Run Growth:
-196
Growth Rate:
-445.45%
Total runs:
23
Run Growth:
-60
Growth Rate:
-240.00%
Total runs:
22
Run Growth:
15
Growth Rate:
68.18%
Total runs:
13
Run Growth:
8
Growth Rate:
61.54%
Total runs:
12
Run Growth:
0
Growth Rate:
0.00%
Total runs:
8
Run Growth:
3
Growth Rate:
37.50%
Total runs:
5
Run Growth:
0
Growth Rate:
0.00%
Total runs:
4
Run Growth:
-1
Growth Rate:
-20.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%