sn56a4/fb7a8ba2-0856-444d-b8ee-43c3b2474869

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/llama-2-7b-chat
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 6988c1d6cb479e79_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/6988c1d6cb479e79_train_data.json
  type:
    field_instruction: rephrased_questions
    field_output: email
    format: '{instruction}'
    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: sn56a4/fb7a8ba2-0856-444d-b8ee-43c3b2474869
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/6988c1d6cb479e79_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: sn56a4/fb7a8ba2
wandb_project: god
wandb_run: ginh
wandb_runid: sn56a4/fb7a8ba2
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

ba279694-1f74-4f18-852c-6193d6e455cf

This model is a fine-tuned version of unsloth/llama-2-7b-chat on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4648

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	0.0030	1	2.0068
1.8441	0.0274	9	1.9291
1.7904	0.0547	18	1.7400
1.6283	0.0821	27	1.6186
1.53	0.1094	36	1.5603
1.5453	0.1368	45	1.5282
1.441	0.1641	54	1.5023
1.4485	0.1915	63	1.4847
1.4485	0.2188	72	1.4739
1.4554	0.2462	81	1.4679
1.4489	0.2736	90	1.4652
1.4364	0.3009	99	1.4648

Framework versions

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