Update README.md

README.md

@@ -14,121 +14,7 @@ model-index:
 should probably proofread and complete it, then remove this comment. -->
 
 [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
-<details><summary>See axolotl config</summary>
 
-axolotl version: `0.4.1`
-```yaml
-adapter: lora
-base_model: unsloth/SmolLM-360M-Instruct
-bf16: true
-chat_template: llama3
-data_processes: 54
-dataset_prepared_path: null
-datasets:
-- data_files:
-  - e7d8f23205d40f8d_train_data.json
-  ds_type: json
-  format: custom
-  path: /workspace/input_data/e7d8f23205d40f8d_train_data.json
-  type:
-    field_instruction: source
-    field_output: target
-    format: '{instruction}'
-    no_input_format: '{instruction}'
-    system_format: '{system}'
-    system_prompt: ''
-debug: null
-deepspeed: null
-device_map: auto
-distributed_training:
-  backend: nccl
-  multi_gpu: true
-  num_gpus: 2
-do_eval: true
-early_stopping_patience: 4
-eval_batch_size: 16
-eval_max_new_tokens: 128
-eval_steps: 150
-eval_table_size: null
-evals_per_epoch: null
-flash_attention: true
-fp16: false
-fsdp:
-- full_shard
-fsdp_config:
-  backward_prefetch: BACKWARD_PRE
-  cpu_offload: false
-  forward_prefetch: false
-  mixed_precision: bf16
-  sharding_strategy: FULL_SHARD
-  use_orig_params: true
-gradient_accumulation_steps: 1
-gradient_checkpointing: true
-group_by_length: true
-hub_ignore_patterns:
-- README.md
-- config.json
-hub_model_id: cimol/fcef08cb-0f5e-44e1-ba45-9c886c47afab
-hub_repo: null
-hub_strategy: end
-hub_token: null
-learning_rate: 7.0e-05
-load_in_4bit: false
-load_in_8bit: false
-local_rank: null
-logging_steps: 10
-lora_alpha: 128
-lora_dropout: 0.1
-lora_fan_in_fan_out: null
-lora_model_dir: null
-lora_r: 64
-lora_target_linear: true
-lr_scheduler: polynomial
-lr_scheduler_warmup_steps: 150
-max_grad_norm: 0.5
-max_memory:
-  0: 75GB
-  1: 75GB
-max_steps: 1350
-micro_batch_size: 16
-mlflow_experiment_name: /tmp/e7d8f23205d40f8d_train_data.json
-model_type: AutoModelForCausalLM
-num_epochs: 3
-optim_args:
-  adam_beta1: 0.9
-  adam_beta2: 0.95
-  adam_epsilon: 1e-8
-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: 300
-saves_per_epoch: null
-seed: 17333
-sequence_len: 1024
-strict: false
-tf32: true
-tokenizer_type: AutoTokenizer
-total_train_batch_size: 32
-train_batch_size: 32
-train_on_inputs: false
-trust_remote_code: true
-val_set_size: 0.05
-wandb_entity: null
-wandb_mode: online
-wandb_name: be621283-b0f9-4449-8928-03752a4a386f
-wandb_project: Gradients-On-Demand
-wandb_run: your_name
-wandb_runid: be621283-b0f9-4449-8928-03752a4a386f
-warmup_steps: 150
-weight_decay: 0.01
-xformers_attention: null
-
-```
-
-</details><br>
 
 # fcef08cb-0f5e-44e1-ba45-9c886c47afab
 
@@ -153,18 +39,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 7e-05
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 17333
-- distributed_type: multi-GPU
-- num_devices: 2
-- total_train_batch_size: 32
-- total_eval_batch_size: 32
-- 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-8
-- lr_scheduler_type: polynomial
-- lr_scheduler_warmup_steps: 150
-- training_steps: 1350
+
 
 ### Training results