See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: bigscience/bloomz-560m
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - xstory_cloze_train_data.json
  ds_type: json
  path: /workspace/input_data/xstory_cloze_train_data.json
  type:
    field_input: input_sentence_1
    field_instruction: sentence_quiz1
    field_output: input_sentence_2
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 1
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hours_to_complete: 5
hub_model_id: besimray/miner1_dd63b72e-0c06-4c3a-af43-4e568d1e70f6_1731033536
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: true
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: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 500
micro_batch_size: 2
mlflow_experiment_name: /tmp/xstory_cloze_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 4
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 10
save_strategy: steps
sequence_len: 4096
started_at: '2024-11-08T02:38:56.234876'
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: besimray24-rayon
wandb_mode: online
wandb_project: Public_TuningSN
wandb_run: miner_id_24
wandb_runid: dd63b72e-0c06-4c3a-af43-4e568d1e70f6
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

miner1_dd63b72e-0c06-4c3a-af43-4e568d1e70f6_1731033536

This model is a fine-tuned version of bigscience/bloomz-560m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.3749

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: 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: 10
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
19.1426	0.0048	1	4.6159
14.9184	0.0238	5	4.1914
15.2543	0.0476	10	3.7814
16.7979	0.0713	15	3.5054
13.9489	0.0951	20	3.4185
14.2309	0.1189	25	3.3699
13.8212	0.1427	30	3.3540
14.279	0.1665	35	3.3749

Framework versions

• PEFT 0.13.2
• Transformers 4.46.1
• Pytorch 2.3.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.3