See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: NousResearch/Hermes-2-Theta-Llama-3-8B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 40f7ad11b6eb9818_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/40f7ad11b6eb9818_train_data.json
type:
field_instruction: question
field_output: task
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: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: kokovova/2a42f8b7-2545-4438-a6f2-98abdf5b3b05
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: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 10
micro_batch_size: 2
mlflow_experiment_name: /tmp/40f7ad11b6eb9818_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: 1
sequence_len: 1024
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: 2a42f8b7-2545-4438-a6f2-98abdf5b3b05
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 2a42f8b7-2545-4438-a6f2-98abdf5b3b05
warmup_ratio: 0.05
weight_decay: 0.1
xformers_attention: true
2a42f8b7-2545-4438-a6f2-98abdf5b3b05
This model is a fine-tuned version of NousResearch/Hermes-2-Theta-Llama-3-8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9355
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: 4
- total_train_batch_size: 8
- 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
- training_steps: 10
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
11.2657 | 0.0001 | 1 | 10.2644 |
10.3745 | 0.0002 | 2 | 7.9682 |
7.559 | 0.0003 | 3 | 5.6689 |
5.5702 | 0.0003 | 4 | 4.1104 |
4.0312 | 0.0004 | 5 | 3.1122 |
2.5694 | 0.0005 | 6 | 2.4706 |
1.9479 | 0.0006 | 7 | 2.2116 |
1.5535 | 0.0007 | 8 | 2.0301 |
3.1075 | 0.0008 | 9 | 1.9554 |
2.4637 | 0.0008 | 10 | 1.9355 |
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
- 6
Model tree for kokovova/2a42f8b7-2545-4438-a6f2-98abdf5b3b05
Base model
NousResearch/Meta-Llama-3-8B
Finetuned
NousResearch/Hermes-2-Pro-Llama-3-8B
Finetuned
NousResearch/Hermes-2-Theta-Llama-3-8B