See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: tiiuae/falcon-rw-1b
batch_size: 2
bf16: auto
dataset_prepared_path: null
datasets:
- data_files:
  - f7c215d0b2b248b0_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/f7c215d0b2b248b0_train_data.json
  type:
    field_input: French
    field_instruction: English
    field_output: MSA
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
evals_per_epoch: 2
flash_attention: null
fp16: null
fsdp: null
fsdp_config: null
gptq: false
gptq_groupsize: null
gptq_model_v1: null
gradient_checkpointing: true
group_by_length: false
hub_model_id: sn56b2/1de8e8c6-1406-493a-875b-3caa24ecb874
learning_rate: 3.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lora_target_modules: null
lr_scheduler: cosine
max_packed_sequence_len: null
micro_batch_size: 1
mlflow_experiment_name: /tmp/f7c215d0b2b248b0_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: ./outputs/falcon-7b/taopanda-1_b7683979-658e-429a-ab3b-266769f33e1a
push_dataset_to_hub: null
resume_from_checkpoint: null
saves_per_epoch: 1
seed: 2648976514
sequence_len: 2048
shuffle: true
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: true
tokenizer_type: AutoTokenizer
torch_compile: true
torchdistx_path: null
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: sn56-miner
wandb_log_model: null
wandb_mode: disabled
wandb_name: null
wandb_project: god
wandb_run: 83s9
wandb_runid: null
wandb_watch: null
warmup_steps: 40
weight_decay: 0.0
xformers_attention: true

1de8e8c6-1406-493a-875b-3caa24ecb874

This model is a fine-tuned version of tiiuae/falcon-rw-1b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4365

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: 3e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 2648976514
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 2
• total_eval_batch_size: 2
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 40
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
2.7109	0.0002	1	3.0288
1.7031	0.5001	2352	1.4365

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1