YoungPanda/EU_LLAMA_USA_3

See axolotl config

axolotl version: 0.4.0

base_model: winglian/Llama-3-8b-64k-PoSE
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: eu_regulatory_ir
    name: eu2uk
    type: completion
  - path: billsum
    field: text
    type: completion
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false
wandb_project: eullama
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 6
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: out/checkpoint-424
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
evals_per_epoch: 2
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|end_of_text|>

out

This model is a fine-tuned version of winglian/Llama-3-8b-64k-PoSE on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7217

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: 6
• eval_batch_size: 6
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 48
• total_eval_batch_size: 48
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.059	0.0047	1	1.0060
0.9352	0.5	106	0.8914
0.8815	1.0	212	0.8217
0.6349	1.4764	318	0.7732
0.5906	1.9764	424	0.7217

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1