See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: HuggingFaceM4/tiny-random-LlamaForCausalLM
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 7d2873533aebb0a7_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/7d2873533aebb0a7_train_data.json
  type:
    field_instruction: instruction
    field_output: response
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 200
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: true
hub_model_id: error577/44bd8f54-d146-4f18-ba64-4ae420dd044c
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: 1024
lora_dropout: 0.15
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 512
lora_target_linear: true
lr_scheduler: constant_with_warmup
micro_batch_size: 8
mlflow_experiment_name: /tmp/7d2873533aebb0a7_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
restore_best_weights: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 200
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.005
wandb_entity: null
wandb_mode: online
wandb_name: 7fc74494-54e7-45aa-842f-df51296de70d
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 7fc74494-54e7-45aa-842f-df51296de70d
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

44bd8f54-d146-4f18-ba64-4ae420dd044c

This model is a fine-tuned version of HuggingFaceM4/tiny-random-LlamaForCausalLM on the None dataset. It achieves the following results on the evaluation set:

• Loss: 10.3111

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
10.3795	0.0001	1	10.3780
10.3207	0.0162	200	10.3211
10.3203	0.0323	400	10.3169
10.3231	0.0485	600	10.3151
10.3248	0.0646	800	10.3140
10.3212	0.0808	1000	10.3136
10.3305	0.0970	1200	10.3131
10.3172	0.1131	1400	10.3128
10.3159	0.1293	1600	10.3130
10.3197	0.1454	1800	10.3124
10.3238	0.1616	2000	10.3122
10.3206	0.1778	2200	10.3121
10.3162	0.1939	2400	10.3113
10.3113	0.2101	2600	10.3116
10.3258	0.2263	2800	10.3113
10.3244	0.2424	3000	10.3114
10.3286	0.2586	3200	10.3112
10.3122	0.2747	3400	10.3110
10.3181	0.2909	3600	10.3111
10.3216	0.3071	3800	10.3111
10.314	0.3232	4000	10.3111

Framework versions

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