See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: migtissera/Tess-v2.5-Phi-3-medium-128k-14B
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - bbc2b0d5025abdac_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/bbc2b0d5025abdac_train_data.json
  type:
    field_instruction: text
    field_output: title
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/d72533e5-daac-4649-b865-c3e1dd60ad01
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
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_grad_norm: 1.0
max_steps: 714
micro_batch_size: 4
mlflow_experiment_name: /tmp/bbc2b0d5025abdac_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
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: 100
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.014207451524175399
wandb_entity: null
wandb_mode: online
wandb_name: abc60950-fe78-486f-beb0-a4be81e4be68
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: abc60950-fe78-486f-beb0-a4be81e4be68
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

d72533e5-daac-4649-b865-c3e1dd60ad01

This model is a fine-tuned version of migtissera/Tess-v2.5-Phi-3-medium-128k-14B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9754

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• 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: 714

Training results

Training Loss	Epoch	Step	Validation Loss
24.1999	0.0001	1	2.9422
9.7766	0.0092	100	1.0913
8.8958	0.0184	200	1.0493
8.6695	0.0277	300	1.0187
7.3278	0.0369	400	1.0010
7.6945	0.0461	500	0.9853
7.1903	0.0553	600	0.9773
7.8715	0.0646	700	0.9754

Framework versions

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