See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Orenguteng/Llama-3-8B-Lexi-Uncensored
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 66aa7d57cbb187af_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/66aa7d57cbb187af_train_data.json
  type:
    field_input: transcription
    field_instruction: glosses
    field_output: translation
    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: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: false
group_by_length: false
hub_model_id: leixa/e15bb719-ea8f-46ea-8290-e5573063df0e
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: true
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_steps: 500
micro_batch_size: 4
mlflow_experiment_name: /tmp/66aa7d57cbb187af_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: false
sample_packing: false
saves_per_epoch: 4
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: leixa-personal
wandb_mode: online
wandb_name: e15bb719-ea8f-46ea-8290-e5573063df0e
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: e15bb719-ea8f-46ea-8290-e5573063df0e
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

e15bb719-ea8f-46ea-8290-e5573063df0e

This model is a fine-tuned version of Orenguteng/Llama-3-8B-Lexi-Uncensored on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3047

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: 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: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0033	1	6.0460
1.7595	0.1368	42	1.7991
1.5434	0.2736	84	1.6323
1.376	0.4104	126	1.5375
1.4669	0.5472	168	1.4719
1.2662	0.6840	210	1.3924
1.3146	0.8208	252	1.3527
1.0922	0.9577	294	1.2961
0.7865	1.0945	336	1.3442
0.705	1.2313	378	1.3148
0.8594	1.3681	420	1.3078
0.7819	1.5049	462	1.3047

Framework versions

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