Sponsored by
APIMart
YoungPanda / swagllama
Model's Last Updated: March 14 2024
text-generation
Introduction of swagllama
Model Details of swagllama
See axolotl config
axolotl version:
0.4.0
base_model: Drewskidang/3LDANG
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
rl: dpo
datasets:
- path: Drewskidang/DPO_RAG
split: train
type: chatml.intel
- path: Drewskidang/dpotask
split: train
type: chatml.intel
- path: unalignment/toxic-dpo-v0.1
split: train
type: chatml.prompt_pairs
- path: argilla/ultrafeedback-binarized-preferences
split: train
type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./lora-out
eval_sample_packing: false
adapter: lora
lora_model_dir:
sequence_len: 4096
sample_packing: false
pad_to_sequence_len: false
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
- gate_proj
- down_proj
- up_proj
- q_proj
- v_proj
- k_proj
- o_proj
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: dpo_evreything
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 2
micro_batch_size: 3
num_epochs: 1
optimizer: adamw_8bit
lr_scheduler: linear
learning_rate: 0.0000002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3
warmup_steps: 10
eval_steps:
eval_table_size:
eval_table_max_new_tokens: 128
save_steps: 239
debug:
deepspeed:
weight_decay: 0.05
special_tokens:
eos_token: "<|im_end|>"
tokens:
- "<|im_start|>"
trust_remote_code: true
lora-out
This model is a fine-tuned version of Drewskidang/3LDANG 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: 2e-07
- train_batch_size: 3
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 48
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 2838
Training results
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.0
Runs of YoungPanda swagllama on huggingface.co
7
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About swagllama huggingface.co Model
Url of swagllama
swagllama huggingface.co Url
Provider of swagllama huggingface.co
Other API from YoungPanda
Total runs:
6
Run Growth:
0
Growth Rate:
0.00%
Total runs:
6
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%