See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: samoline/c8d69a4b-91d7-4166-97ab-cb4a0ca0ce65
bf16: auto
chat_template: llama3
datasets:
- data_files:
  - train_c4393383-ef1d-4e9c-b95c-18b4f735570d.json
  ds_type: json
  format: custom
  path: /workspace/input_data/train_c4393383-ef1d-4e9c-b95c-18b4f735570d.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 1
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: true
gradient_checkpointing: true
group_by_length: false
hub_model_id: lesso10/12ec8955-4db3-4c6f-a667-bd7c4467ac09
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 3
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_steps: 25
micro_batch_size: 2
mlflow_experiment_name: /tmp/train_c4393383-ef1d-4e9c-b95c-18b4f735570d.json
model_type: AutoModelForCausalLM
num_epochs: 1
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: 10
sequence_len: 1024
special_tokens:
  pad_token: <|endoftext|>
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: f994e939-b231-4c6a-96ec-8e61e31045e2
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: f994e939-b231-4c6a-96ec-8e61e31045e2
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

12ec8955-4db3-4c6f-a667-bd7c4467ac09

This model is a fine-tuned version of samoline/c8d69a4b-91d7-4166-97ab-cb4a0ca0ce65 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7334

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: 2
• eval_batch_size: 2
• seed: 42
• 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: 25

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	2.1417
2.0147	0.0003	5	2.0777
1.679	0.0005	10	1.8831
1.7223	0.0008	15	1.7851
1.7238	0.0010	20	1.7434
1.6989	0.0013	25	1.7334

Framework versions

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