See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: teknium/OpenHermes-2.5-Mistral-7B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 79c090c63fd9ea29_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/79c090c63fd9ea29_train_data.json
  type:
    field_input: url
    field_instruction: title
    field_output: text
    format: '{instruction} {input}'
    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: 4
flash_attention: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 6
gradient_checkpointing: true
group_by_length: false
hub_model_id: dimasik2987/e212c598-c045-4788-97a1-b4691c0d6b4b
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: 1
lora_alpha: 32
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 70GiB
max_steps: 50
micro_batch_size: 4
mlflow_experiment_name: /tmp/79c090c63fd9ea29_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 25
save_strategy: steps
sequence_len: 2028
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: e212c598-c045-4788-97a1-b4691c0d6b4b
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: e212c598-c045-4788-97a1-b4691c0d6b4b
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

e212c598-c045-4788-97a1-b4691c0d6b4b

This model is a fine-tuned version of teknium/OpenHermes-2.5-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: 6
• total_train_batch_size: 24
• 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
0.0	0.0001	1	nan
0.0	0.0005	5	nan
0.0	0.0011	10	nan
0.0	0.0016	15	nan
0.0	0.0021	20	nan
0.0	0.0027	25	nan
0.0	0.0032	30	nan
0.0	0.0037	35	nan
0.0	0.0042	40	nan
0.0	0.0048	45	nan
0.0	0.0053	50	nan

Framework versions

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