See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: TinyLlama/TinyLlama_v1.1
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- bf4f7f7a6ea08749_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/bf4f7f7a6ea08749_train_data.json
type:
field_input: prompt_id
field_instruction: text
field_output: completion_a
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 3
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: dimasik2987/38a6c13c-3b6a-4554-b3c9-ca2ccb0d95ca
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
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
lr_scheduler: linear
max_memory:
0: 70GiB
max_steps: 25
micro_batch_size: 4
mlflow_experiment_name: /tmp/bf4f7f7a6ea08749_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
save_steps: 25
save_strategy: steps
sequence_len: 4056
special_tokens:
pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 38a6c13c-3b6a-4554-b3c9-ca2ccb0d95ca
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 38a6c13c-3b6a-4554-b3c9-ca2ccb0d95ca
warmup_ratio: 0.05
weight_decay: 0.01
xformers_attention: null
38a6c13c-3b6a-4554-b3c9-ca2ccb0d95ca
This model is a fine-tuned version of TinyLlama/TinyLlama_v1.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3108
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- 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: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 25
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.6563 | 0.0033 | 1 | 1.7122 |
1.4171 | 0.0098 | 3 | 1.6011 |
1.2534 | 0.0197 | 6 | 1.4521 |
1.21 | 0.0295 | 9 | 1.3822 |
1.7432 | 0.0394 | 12 | 1.3498 |
0.9953 | 0.0492 | 15 | 1.3323 |
1.1401 | 0.0591 | 18 | 1.3210 |
1.2508 | 0.0689 | 21 | 1.3149 |
1.236 | 0.0788 | 24 | 1.3108 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 0
Model tree for dimasik2987/38a6c13c-3b6a-4554-b3c9-ca2ccb0d95ca
Base model
TinyLlama/TinyLlama_v1.1