See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Meta-Llama-3-8B-Alternate-Tokenizer
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 67a64d4e8799f348_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/67a64d4e8799f348_train_data.json
  type:
    field_instruction: instruction
    field_output: output
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Romain-XV/77a10a3f-d7db-4889-93b8-fbd39927ffb3
hub_repo: null
hub_strategy: checkpoint
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: 128
lora_dropout: 0.3
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 1092
micro_batch_size: 4
mlflow_experiment_name: /tmp/67a64d4e8799f348_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
use_rslora: true
val_set_size: 0.008941104941748702
wandb_entity: null
wandb_mode: online
wandb_name: b63b2f41-5360-44a3-bf07-b59ccbe2f2f3
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: b63b2f41-5360-44a3-bf07-b59ccbe2f2f3
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

77a10a3f-d7db-4889-93b8-fbd39927ffb3

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: 1.0060

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: 1092

Training results

Training Loss	Epoch	Step	Validation Loss
0.9592	0.0001	1	1.5503
0.712	0.0058	100	1.0710
0.7325	0.0115	200	1.0618
1.0703	0.0173	300	1.0535
0.8864	0.0231	400	1.0454
0.786	0.0289	500	1.0358
0.8329	0.0346	600	1.0282
1.0388	0.0404	700	1.0201
0.8176	0.0462	800	1.0131
1.0233	0.0520	900	1.0080
0.8965	0.0577	1000	1.0060

Framework versions

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