You can deploy this model and start earning money today!

dimasik87/
1bc7b11d-8ab3-44f1-bd3f-c2b84e0d0cb0

Name: 1bc7b11d-8ab3-44f1-bd3f-c2b84e0d0cb0
Availability: InStock

generated_from_trainer

Maykeye/TinyLLama-v0

adapter

apache-2.0

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: Maykeye/TinyLLama-v0
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - f140ad20081c78ce_train_data.json
  ds_type: json
  field: title
  path: /workspace/input_data/f140ad20081c78ce_train_data.json
  type: completion
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 3
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 6
gradient_checkpointing: true
group_by_length: false
hub_model_id: dimasik87/1bc7b11d-8ab3-44f1-bd3f-c2b84e0d0cb0
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 70GiB
max_steps: 25
micro_batch_size: 2
mlflow_experiment_name: /tmp/f140ad20081c78ce_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 3
sequence_len: 4056
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: 1bc7b11d-8ab3-44f1-bd3f-c2b84e0d0cb0
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 1bc7b11d-8ab3-44f1-bd3f-c2b84e0d0cb0
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

1bc7b11d-8ab3-44f1-bd3f-c2b84e0d0cb0

This model is a fine-tuned version of Maykeye/TinyLLama-v0 on the None dataset. It achieves the following results on the evaluation set:

Loss: 9.6964

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
gradient_accumulation_steps: 6
total_train_batch_size: 12
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
10.2977	0.0003	1	10.2500
10.2551	0.0010	3	10.2480
10.3599	0.0019	6	10.1868
10.2925	0.0029	9	10.0792
9.8382	0.0039	12	9.9451
9.9685	0.0049	15	9.8311
9.741	0.0058	18	9.7523
9.0752	0.0068	21	9.7099
10.1768	0.0078	24	9.6964

Framework versions

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