See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: DeepMount00/Llama-3-8b-Ita
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - c9212afc7e280e39_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/c9212afc7e280e39_train_data.json
  type:
    field_input: context
    field_instruction: question
    field_output: context_en
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 256
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: false
hub_model_id: eddysang/75df37cd-a91e-4e34-8a06-4a599ca1b9ca
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.00015
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 3
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
lr_scheduler: cosine
max_grad_norm: 2
max_steps: 100
micro_batch_size: 2
mlflow_experiment_name: /tmp/c9212afc7e280e39_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 2048
special_tokens:
  pad_token: <|eot_id|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: yaudayah0
wandb_mode: online
wandb_name: f03bde3a-7ef8-48ba-bc20-17fcd70d2608
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: f03bde3a-7ef8-48ba-bc20-17fcd70d2608
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

75df37cd-a91e-4e34-8a06-4a599ca1b9ca

This model is a fine-tuned version of DeepMount00/Llama-3-8b-Ita on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2414

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: 0.00015
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 64
• 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-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0089	1	0.6202
0.3605	0.0797	9	0.4265
0.2762	0.1593	18	0.2961
0.2376	0.2390	27	0.2735
0.3293	0.3187	36	0.2635
0.3035	0.3983	45	0.2566
0.252	0.4780	54	0.2500
0.2203	0.5577	63	0.2471
0.2039	0.6373	72	0.2439
0.2102	0.7170	81	0.2422
0.1768	0.7967	90	0.2417
0.2284	0.8763	99	0.2414

Framework versions

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