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: awilliamson/horses-long
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./no-inputs

sequence_len: 8192
sample_packing: false
pad_to_sequence_len: true

wandb_project: derby
wandb_entity: willfulbytes
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 5
optimizer: adamw_torch
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: 25
evals_per_epoch:
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
  - full_shard
  - auto_wrap
fsdp_config:
  fsdp_offload_params: true
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
special_tokens:
  pad_token: <|end_of_text|>
tokens:
  - <|start_St|>
  - <|end_St|>
  - <|start_1/4|>
  - <|end_1/4|>
  - <|start_1/2|>
  - <|end_1/2|>
  - <|start_3/8|>
  - <|end_3/8|>
  - <|start_3/4|>
  - <|end_4/4|>
  - <|start_Str|>
  - <|end_Str|>
  - <|start_Fin|>
  - <|end_Fin|>
  - PP1
  - PP2
  - PP3
  - PP4
  - PP5
  - PP6
  - PP7
  - PP8
  - PP9
  - PP10
  - PP11
  - PP12
  - PP13
  - PP14
  - PP15
  - PP16
  - PP17
  - PP18
  - PP19
  - PP20

no-inputs

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B 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-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 2
total_train_batch_size: 2
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: 25
num_epochs: 5

Training results

Framework versions

Transformers 4.40.0.dev0
Pytorch 2.2.0
Datasets 2.15.0
Tokenizers 0.15.0

awilliamson/exacta-longer

no-inputs

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

awilliamson/
exacta-longer