metadata
library_name: peft
license: apache-2.0
base_model: teknium/OpenHermes-2.5-Mistral-7B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: befa1a68-b759-41cd-aa37-79f4aaa9a6a5
results: []
See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: teknium/OpenHermes-2.5-Mistral-7B
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 0117447d3950c946_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/0117447d3950c946_train_data.json
type:
field_instruction: first_message
field_output: first_answer
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
device_map: auto
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: false
hub_model_id: fats-fme/befa1a68-b759-41cd-aa37-79f4aaa9a6a5
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 5.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 16
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lora_target_modules:
- q_proj
- v_proj
lr_scheduler: cosine
max_memory:
0: 130GB
max_steps: 50
micro_batch_size: 1
mlflow_experiment_name: /tmp/0117447d3950c946_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
save_steps: 100
saves_per_epoch: null
sequence_len: 1024
special_tokens:
pad_token: <|im_end|>
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: dace43b8-8ffb-4c18-baa0-ebd02df71793
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: dace43b8-8ffb-4c18-baa0-ebd02df71793
warmup_steps: 200
weight_decay: 0.01
xformers_attention: null
befa1a68-b759-41cd-aa37-79f4aaa9a6a5
This model is a fine-tuned version of teknium/OpenHermes-2.5-Mistral-7B on the None dataset.
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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- 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: 200
- training_steps: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0008 | 1 | 1.6654 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1