See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: Maykeye/TinyLLama-v0
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- d3285c09a4659e58_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/d3285c09a4659e58_train_data.json
type:
field_instruction: question
field_output: context
format: '{instruction}'
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: 4
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: oldiday/02980b06-009c-411f-bbb3-9aa4a86487dc
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: 0
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: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/d3285c09a4659e58_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 1024
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: techspear-hub
wandb_mode: online
wandb_name: 1ca754fe-e447-4b8d-b4c4-ed9dd79ab1f2
wandb_project: Gradients-On-Six
wandb_run: your_name
wandb_runid: 1ca754fe-e447-4b8d-b4c4-ed9dd79ab1f2
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null
02980b06-009c-411f-bbb3-9aa4a86487dc
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: 8.1179
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 100
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
No log | 0.0002 | 1 | 11.9766 |
11.2672 | 0.0021 | 9 | 10.9598 |
9.8807 | 0.0043 | 18 | 9.6660 |
9.1127 | 0.0064 | 27 | 8.9846 |
8.6422 | 0.0085 | 36 | 8.5606 |
8.3684 | 0.0107 | 45 | 8.3394 |
8.2492 | 0.0128 | 54 | 8.2338 |
8.1976 | 0.0149 | 63 | 8.1752 |
8.1625 | 0.0171 | 72 | 8.1429 |
8.1421 | 0.0192 | 81 | 8.1259 |
8.117 | 0.0213 | 90 | 8.1192 |
8.1194 | 0.0235 | 99 | 8.1179 |
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
- 2
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for oldiday/02980b06-009c-411f-bbb3-9aa4a86487dc
Base model
Maykeye/TinyLLama-v0