axolotl version: 0.4.1
base_model: FourOhFour/Crispy_Crab_4B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
hub_model_id: jeiku/personal4B
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
datasets:
- path: jeiku/Hypno_ChatML
type: sharegpt
conversation: chatml
- path: jeiku/Soul_ChatML
type: sharegpt
conversation: chatml
- path: jeiku/Theory_Chat
type: sharegpt
conversation: chatml
- path: jeiku/Writing
type: completion
field: text
chat_template: chatml
shuffle_merged_datasets: true
val_set_size: 0.0025
output_dir: ./outputs/out
adapter:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true
wandb_project: EXP4B
wandb_entity:
wandb_watch:
wandb_name: EXP4B
wandb_log_model:
gradient_accumulation_steps: 12
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00001
weight_decay: 0.05
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_ratio: 0.1
evals_per_epoch: 2
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>
personal4B
This model is a fine-tuned version of FourOhFour/Crispy_Crab_4B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9273
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 12
- total_train_batch_size: 48
- total_eval_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1634 | 0.8571 | 1 | 2.0454 |
| 2.0907 | 1.7143 | 2 | 1.9455 |
| 1.9539 | 2.5714 | 3 | 1.9296 |
| 1.9493 | 3.4286 | 4 | 1.9273 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1