Magpie's Friends
Collection
Collection of baselines!
•
9 items
•
Updated
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: flydust/tulu-v2-sft-mixture-sharegpt
type: sharegpt
conversation: llama3
dataset_prepared_path: last_run_prepared
val_set_size: 0.001
output_dir: ./out_Llama-8B-Tulu-330K
sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
wandb_project: SynDa
wandb_entity:
wandb_watch:
wandb_name: Llama-3-8B-Tulu-330K
wandb_log_model:
hub_model_id: SynDa/Llama-3-8B-Tulu-330K
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
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: 100
evals_per_epoch: 3
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
pad_token: <|end_of_text|>
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.9026 | 0.0008 | 1 | 1.6267 |
0.6553 | 0.3331 | 403 | 1.0752 |
0.6247 | 0.6662 | 806 | 1.0431 |
0.552 | 0.9993 | 1209 | 1.0544 |
0.4337 | 1.3207 | 1612 | 1.0577 |
0.5092 | 1.6538 | 2015 | 1.0530 |
0.4894 | 1.9869 | 2418 | 1.0525 |
Base model
meta-llama/Meta-Llama-3-8B