Sponsored by
APIMart
qnguyen3 / quan-1.8b-base-v2
Model's Last Updated: January 31 2024
text-generation
Introduction of quan-1.8b-base-v2
Model Details of quan-1.8b-base-v2
See axolotl config
axolotl version:
0.3.0
base_model: qnguyen3/quan-1.8b-1e
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: false
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: vilm/pretrained_baomoi_2023
type: completion
- path: vilm/pretrained_baomoi_2022_1
type: completion
dataset_prepared_path: ./qwen_prepared
val_set_size: 0.00
output_dir: ./qwen-1.8b-vi
sequence_len: 4096 # supports up to 8192
sample_packing: true
pad_to_sequence_len:
wandb_project: qwen-vi-pt
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00003
train_on_input: true
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 100
evals_per_epoch: 0
eval_table_size:
eval_table_max_new_tokens:
saves_per_epoch: 4
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
special_tokens:
eos_token: "<|im_end|>"
pad_token: "<|im_end|>"
qwen-1.8b-vi
This model is a fine-tuned version of qnguyen3/quan-1.8b-1e on the None dataset.
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: 3e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- 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
Framework versions
- Transformers 4.37.0
- Pytorch 2.0.1+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0
Runs of qnguyen3 quan-1.8b-base-v2 on huggingface.co
1
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
1
30-day runs
More Information About quan-1.8b-base-v2 huggingface.co Model
Url of quan-1.8b-base-v2
quan-1.8b-base-v2 huggingface.co Url
Provider of quan-1.8b-base-v2 huggingface.co
Other API from qnguyen3
Total runs:
2.3K
Run Growth:
2.2K
Growth Rate:
95.18%
Total runs:
157
Run Growth:
0
Growth Rate:
0.00%
Total runs:
59
Run Growth:
29
Growth Rate:
49.15%
Total runs:
49
Run Growth:
17
Growth Rate:
34.69%
Total runs:
39
Run Growth:
0
Growth Rate:
0.00%
Total runs:
31
Run Growth:
16
Growth Rate:
51.61%
Total runs:
25
Run Growth:
10
Growth Rate:
41.67%
Total runs:
12
Run Growth:
11
Growth Rate:
91.67%
Total runs:
1
Run Growth:
1
Growth Rate:
100.00%
Total runs:
0
Run Growth:
-1
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%