absolute_data_files: false
adapter: lora
base_model: teknium/OpenHermes-2.5-Mistral-7B
bf16: true
chat_template: llama3
dataset_prepared_path: /workspace/axolotl
datasets:
- data_files:
  - 4ee598d3e4a39a4f_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/
  type:
    field_instruction: instruct
    field_output: output
    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: 1
flash_attention: true
flash_attn_cross_entropy: false
flash_attn_fuse_mlp: false
flash_attn_fuse_qkv: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 1
gradient_checkpointing: true
gradient_clipping: 0.55
group_by_length: false
hub_model_id: nellifurtado23/28cd287f-6023-43ab-a76e-1b3186732244
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 5e-6
load_in_4bit: true
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 48
lora_dropout: 0.01
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 24
lora_target_linear: true
lr_scheduler: cosine
max_steps: 125
micro_batch_size: 2
mixed_precision: bf16
mlflow_experiment_name: /tmp/4ee598d3e4a39a4f_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
saves_per_epoch: 1
sequence_len: 2048
special_tokens:
  pad_token: <|im_end|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 7c914f75-add3-42d8-88f3-0e8fc854e1fa
wandb_project: s56-7
wandb_run: your_name
wandb_runid: 7c914f75-add3-42d8-88f3-0e8fc854e1fa
warmup_steps: 5
weight_decay: 0.01
xformers_attention: false

28cd287f-6023-43ab-a76e-1b3186732244

This model is a fine-tuned version of teknium/OpenHermes-2.5-Mistral-7B on an unknown dataset.

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-06
train_batch_size: 2
eval_batch_size: 2
seed: 42
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: 5
training_steps: 125

Training results

Framework versions

PEFT 0.15.2
Transformers 4.52.4
Pytorch 2.5.1+cu124
Datasets 3.6.0
Tokenizers 0.21.1