You can deploy this model and start earning money today!

romainnn/
b38fca3c-0e0a-4b01-8aae-24776fc5ce5c

Name: b38fca3c-0e0a-4b01-8aae-24776fc5ce5c
Availability: InStock

generated_from_trainer

trl-internal-testing/tiny-random-LlamaForCausalLM

adapter

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: trl-internal-testing/tiny-random-LlamaForCausalLM
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 64609937eb02e5a5_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/64609937eb02e5a5_train_data.json
  type:
    field_input: distractor2
    field_instruction: question
    field_output: distractor1
    field_system: support
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 2
early_stopping_threshold: 0.0001
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_card: false
hub_model_id: romainnn/b38fca3c-0e0a-4b01-8aae-24776fc5ce5c
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
lora_target_modules:
- q_proj
- k_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 1716
micro_batch_size: 4
mlflow_experiment_name: /tmp/64609937eb02e5a5_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
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 00a15d47-737e-4c96-8caf-3e8386c1bac6
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 00a15d47-737e-4c96-8caf-3e8386c1bac6
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

b38fca3c-0e0a-4b01-8aae-24776fc5ce5c

This model is a fine-tuned version of trl-internal-testing/tiny-random-LlamaForCausalLM on the None dataset. It achieves the following results on the evaluation set:

Loss: 10.2735

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: 804

Training results

Training Loss	Epoch	Step	Validation Loss
10.3803	0.0025	1	10.3775
10.2864	0.2490	100	10.2740
10.2614	0.4980	200	10.2739
10.2798	0.7470	300	10.2737
10.2868	0.9960	400	10.2737
10.608	1.2453	500	10.2736
10.2883	1.4942	600	10.2735
10.9907	1.7432	700	10.2735
9.6923	1.9922	800	10.2735

Framework versions

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