See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/CodeLlama-7b-hf
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 40971d92d753c8f8_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/40971d92d753c8f8_train_data.json
  type:
    field_input: ''
    field_instruction: text
    field_output: phonemes
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 256
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: false
hub_model_id: eddysang/d106f1a5-7380-4770-b079-376f00f00d6a
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 3
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
lr_scheduler: cosine
max_grad_norm: 2
max_steps: 100
micro_batch_size: 2
mlflow_experiment_name: /tmp/40971d92d753c8f8_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
optimizer: adamw_torch
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: 2048
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: yaudayah0
wandb_mode: online
wandb_name: 1aa80b92-52ba-44a0-a76e-1996e838379f
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 1aa80b92-52ba-44a0-a76e-1996e838379f
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

d106f1a5-7380-4770-b079-376f00f00d6a

This model is a fine-tuned version of NousResearch/CodeLlama-7b-hf on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1418

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: 32
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	3.1602
80.7471	0.0009	9	2.1278
31.1364	0.0017	18	0.8450
15.5343	0.0026	27	0.4686
10.3941	0.0035	36	0.3381
8.5669	0.0043	45	0.2520
6.9151	0.0052	54	0.2129
5.5389	0.0061	63	0.1780
5.6267	0.0069	72	0.1619
5.1425	0.0078	81	0.1495
4.3707	0.0087	90	0.1439
4.3476	0.0095	99	0.1418

Framework versions

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