See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Hermes-2-Pro-Mistral-7B
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 0b7cbbc7db8082ce_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/0b7cbbc7db8082ce_train_data.json
  type:
    field_input: original_version
    field_instruction: title
    field_output: french_version
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
device_map:
  ? ''
  : 0,1,2,3,4,5,6,7
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: false
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/0958c411-90d3-40a5-a490-6afc6d4097e6
hub_repo: null
hub_strategy: null
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:
- q_proj
- k_proj
- v_proj
- o_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 714
micro_batch_size: 4
mlflow_experiment_name: /tmp/0b7cbbc7db8082ce_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: 2048
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 4da8ea22-b433-4a3d-9ad5-9e5e01e4d981
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 4da8ea22-b433-4a3d-9ad5-9e5e01e4d981
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

0958c411-90d3-40a5-a490-6afc6d4097e6

This model is a fine-tuned version of NousResearch/Hermes-2-Pro-Mistral-7B on the None dataset. It achieves the following results on the evaluation set:

• Loss: nan

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
0.0	0.0003	1	nan
0.0	0.0343	100	nan
0.0	0.0686	200	nan
0.0	0.1029	300	nan

Framework versions

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