See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: NousResearch/Yarn-Mistral-7b-128k
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 879afce2cb3c6794_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/879afce2cb3c6794_train_data.json
type:
field_input: source
field_instruction: prompt
field_output: prompt_id
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: false
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/45822166-6d97-4b65-bb48-c9b6067f220d
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: 588
micro_batch_size: 4
mlflow_experiment_name: /tmp/879afce2cb3c6794_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: 0.026936607388172676
wandb_entity: null
wandb_mode: online
wandb_name: 862afa12-c2da-43f7-9538-cde2ecde765f
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 862afa12-c2da-43f7-9538-cde2ecde765f
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null
45822166-6d97-4b65-bb48-c9b6067f220d
This model is a fine-tuned version of NousResearch/Yarn-Mistral-7b-128k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0063
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: 588
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
27.7694 | 0.0002 | 1 | 3.4768 |
24.437 | 0.0177 | 100 | 3.0262 |
24.2672 | 0.0354 | 200 | 3.0341 |
24.0393 | 0.0531 | 300 | 3.0146 |
24.0656 | 0.0709 | 400 | 3.0096 |
24.3404 | 0.0886 | 500 | 3.0063 |
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
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for Alphatao/45822166-6d97-4b65-bb48-c9b6067f220d
Base model
NousResearch/Yarn-Mistral-7b-128k