axolotl version: 0.5.2
base_model: huihui-ai/Llama-3.1-Tulu-3-8B-abliterated
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: FourOhFour/RP_Phase
type: chat_template
chat_template: llama3
roles_to_train: ["gpt"]
field_messages: conversations
message_field_role: from
message_field_content: value
train_on_eos: turn
shuffle_merged_datasets: true
default_system_message:
dataset_prepared_path:
val_set_size: 0.0125
output_dir: ./output/out
hub_model_id: jeiku/evil8b
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len:
wandb_project: evil
wandb_entity:
wandb_watch:
wandb_name: evil
wandb_log_model:
gradient_accumulation_steps: 16
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 1e-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:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
evals_per_epoch: 2
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>
eos_token: <|eot_id|>
evil8b
This model is a fine-tuned version of huihui-ai/Llama-3.1-Tulu-3-8B-abliterated on the FourOhFour/RP_Phase dataset. It achieves the following results on the evaluation set:
- Loss: 1.0089
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
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5229 | 0.5004 | 131 | 1.0768 |
| 2.103 | 1.0012 | 262 | 1.0223 |
| 1.3982 | 1.5016 | 393 | 1.0089 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.3.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3