sn56b2/276151e4-a5d1-40a7-8233-3d97bd318f31

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Phi-3.5-mini-instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 5c2afcd0d3df129b_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/5c2afcd0d3df129b_train_data.json
  type:
    field_input: article
    field_instruction: template
    field_output: rendered_output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
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
gradient_clipping: 1.0
group_by_length: false
hub_model_id: sn56b2/276151e4-a5d1-40a7-8233-3d97bd318f31
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 5.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/5c2afcd0d3df129b_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: sn56b2/276151e4
wandb_project: god
wandb_run: 15lm
wandb_runid: sn56b2/276151e4
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

2b301748-7bee-46e7-b614-581cf1d3f5f6

This model is a fine-tuned version of unsloth/Phi-3.5-mini-instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 12.1339

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0093	1	12.1339
11.7524	0.0839	9	12.1339
12.2523	0.1678	18	12.1339
11.8441	0.2517	27	12.1339
12.6077	0.3357	36	12.1339
12.6694	0.4196	45	12.1339
12.0588	0.5035	54	12.1339
12.1476	0.5874	63	12.1339
12.5738	0.6713	72	12.1339
12.2524	0.7552	81	12.1339
12.3795	0.8392	90	12.1339
12.7524	0.9231	99	12.1339

Framework versions

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