You can deploy this model and start earning money today!

Alphatao/
39990f15-9053-43d1-9daa-946e431eb154

Name: 39990f15-9053-43d1-9daa-946e431eb154
Availability: InStock

generated_from_trainer

HuggingFaceH4/tiny-random-LlamaForCausalLM

adapter

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: HuggingFaceH4/tiny-random-LlamaForCausalLM
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 94bc225e90b38509_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/94bc225e90b38509_train_data.json
  type:
    field_input: description
    field_instruction: reference
    field_output: article
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
device_map:
  ? ''
  : 0,1,2,3,4,5,6,7
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: true
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/39990f15-9053-43d1-9daa-946e431eb154
hub_repo: null
hub_strategy: null
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: 0.1
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
- o_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 36582
micro_batch_size: 4
mlflow_experiment_name: /tmp/94bc225e90b38509_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
special_tokens:
  pad_token: </s>
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: b5890fb6-bacc-436a-9f1f-7bcb9df35f08
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: b5890fb6-bacc-436a-9f1f-7bcb9df35f08
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

39990f15-9053-43d1-9daa-946e431eb154

This model is a fine-tuned version of HuggingFaceH4/tiny-random-LlamaForCausalLM on the None dataset. It achieves the following results on the evaluation set:

Loss: 10.3094

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: 1297

Training results

Training Loss	Epoch	Step	Validation Loss
10.374	0.0015	1	10.3741
10.3357	0.1543	100	10.3351
10.3238	0.3085	200	10.3237
10.318	0.4628	300	10.3187
10.3189	0.6170	400	10.3154
10.3169	0.7713	500	10.3135
10.3176	0.9256	600	10.3120
8.698	1.0798	700	10.3111
9.8584	1.2341	800	10.3103
11.633	1.3884	900	10.3099
10.6623	1.5426	1000	10.3096
9.7513	1.6969	1100	10.3095
10.7342	1.8511	1200	10.3094

Framework versions

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