See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Meta-Llama-3-8B-Alternate-Tokenizer
bf16: true
chat_template: llama3
datasets:
- data_files:
  - 10fb9efa968d1d74_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/10fb9efa968d1d74_train_data.json
  type:
    field_instruction: input_persona
    field_output: prompt
    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: 4
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
hub_model_id: lesso04/05e9bfa8-5cf5-4e5e-a02a-025edcf13ba6
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
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
lr_scheduler: cosine
max_memory:
  0: 77GiB
max_steps: 50
micro_batch_size: 8
mlflow_experiment_name: /tmp/10fb9efa968d1d74_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: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 05e9bfa8-5cf5-4e5e-a02a-025edcf13ba6
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 05e9bfa8-5cf5-4e5e-a02a-025edcf13ba6
warmup_steps: 10
weight_decay: 0.01
xformers_attention: false

05e9bfa8-5cf5-4e5e-a02a-025edcf13ba6

This model is a fine-tuned version of NousResearch/Meta-Llama-3-8B-Alternate-Tokenizer on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9902

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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
1.5136	0.0001	1	1.4840
1.4067	0.0006	5	1.4601
1.284	0.0011	10	1.2559
1.1843	0.0017	15	1.1296
1.1302	0.0022	20	1.0698
1.0512	0.0028	25	1.0360
1.0801	0.0034	30	1.0141
1.0124	0.0039	35	1.0017
0.9176	0.0045	40	0.9943
1.002	0.0051	45	0.9909
0.9266	0.0056	50	0.9902

Framework versions

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