See axolotl config
axolotl version: 0.4.0
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-pp
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: 4
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: 20
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: 20
- num_epochs: 4
Training results
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.0
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for awilliamson/exactapp
Base model
meta-llama/Meta-Llama-3-8B
Finetuned
this model