See axolotl config

axolotl version: 0.4.1

base_model: NousResearch/Meta-Llama-3-8B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: true
load_in_4bit: false
strict: false

# chat_template: llama3
datasets:
  - path: /home/ftcourse/sample_data/crossner_ai_train.jsonl
    type: alpaca
# datasets:
#   - path: fozziethebeat/alpaca_messages_2k_test
#     type: chat_template
#     field_messages: messages
#     message_field_role: role
#     message_field_content: content
#     roles:
#       user:
#         - user
#       assistant:
#         - assistant

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/lora-out
hub_model_id: femT-data/llama-3.1-8B-instruct-GNER

sequence_len: 4096
sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|end_of_text|>

llama-3.1-8B-instruct-GNER

This model is a fine-tuned version of NousResearch/Meta-Llama-3-8B-Instruct on the Crossner_ai dataset. It achieves the following results on the evaluation set:

• Loss: 0.0363

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.5951	0.0187	1	0.6405
0.1134	0.2617	14	0.0841
0.0224	0.5234	28	0.0434
0.0423	0.7850	42	0.0363

Framework versions

• PEFT 0.13.2
• Transformers 4.45.2
• Pytorch 2.3.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1