See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: tiiuae/falcon-7b
bf16: auto
datasets:
- path: data.jsonl
  type: alpaca
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_sample_packing: false
eval_table_size: null
evals_per_epoch: 4
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: FatCat87/test-task-2025-01-06-19-02-10
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
micro_batch_size: 2
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: adamw_bnb_8bit
output_dir: ./outputs/out
pad_to_sequence_len: true
resume_from_checkpoint: null
sample_packing: true
saves_per_epoch: 1
sequence_len: 4096
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
val_set_size: 0.1
wandb_entity: fatcat87-taopanda
wandb_log_model: null
wandb_mode: online
wandb_name: test-task-2025-01-06-19-02-10
wandb_project: subnet56
wandb_runid: test-task-2025-01-06-19-02-10
wandb_watch: null
warmup_ratio: 0.1
weight_decay: 0.0
xformers_attention: null

test-task-2025-01-06-19-02-10

This model is a fine-tuned version of tiiuae/falcon-7b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1264

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
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• total_eval_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 27
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.2697	0.0072	1	1.6099
1.0992	0.2518	35	1.3500
1.0617	0.5036	70	1.2067
1.0583	0.7554	105	1.1780
1.0331	1.0072	140	1.1443
1.3871	1.2392	175	1.1334
1.3272	1.4910	210	1.1283
1.027	1.7428	245	1.1264

Framework versions

• PEFT 0.11.1
• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1