See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/CodeLlama-7b-hf
bf16: true
chat_template: llama3
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
device: cuda
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: lesso16/98dd07bd-b9cb-4026-adb4-a49b4deaf696
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 2.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 25
micro_batch_size: 2
mlflow_experiment_name: /tmp/40971d92d753c8f8_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 10
sequence_len: 512
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
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: 10
weight_decay: 0.0
xformers_attention: true

98dd07bd-b9cb-4026-adb4-a49b4deaf696

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: 3.3203

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: 25

Training results

Training Loss	Epoch	Step	Validation Loss
11.9726	0.0000	1	3.3685
14.3786	0.0001	5	3.3679
14.7897	0.0001	10	3.3603
13.3129	0.0002	15	3.3403
11.7674	0.0002	20	3.3243
13.7271	0.0003	25	3.3203

Framework versions

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