Downloads · 30 days
1
6% of all-time downloads
mamung/83ad4934-589d-4423-9d38-8e5a7753b866
83ad4934-589d-4423-9d38-8e5a7753b866 is a machine learning model from mamung. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
1
6% of all-time downloads
All-time downloads
18
Public
Repo size
11.8 GB
Likes
0
Public
Click a slice to open those files.
.pt640 MB · 40%
From the Hugging Face model README
axolotl version: 0.4.1
adapter: lora
base_model: NousResearch/CodeLlama-7b-hf-flash
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- a60a6a7ae850ffd6_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/a60a6a7ae850ffd6_train_data.json
type:
field_instruction: problem
field_output: generated_solution
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 256
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: false
hub_model_id: mamung/83ad4934-589d-4423-9d38-8e5a7753b866
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.00015
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 3
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
lr_scheduler: cosine
max_grad_norm: 2
max_steps: 100
micro_batch_size: 2
mlflow_experiment_name: /tmp/a60a6a7ae850ffd6_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 1.0e-05
optimizer: adamw_torch
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: 2048
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: eddysang
wandb_mode: online
wandb_name: eed72ffd-90a9-4f73-aae0-4351e1d99767
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: eed72ffd-90a9-4f73-aae0-4351e1d99767
warmup_steps: 20
weight_decay: 0.01
xformers_attention: false
</details><br>
This model is a fine-tuned version of NousResearch/CodeLlama-7b-hf-flash on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0008 | 1 | 0.6913 |
| 21.3435 | 0.0076 | 9 | 0.6442 |
| 17.5095 | 0.0152 | 18 | 0.5461 |
| 15.9583 | 0.0228 | 27 | 0.5060 |
| 15.7108 | 0.0304 | 36 | 0.4876 |
| 15.0592 | 0.0380 | 45 | 0.4748 |
| 15.1665 | 0.0456 | 54 | 0.4669 |
| 15.3952 | 0.0532 | 63 | 0.4617 |
| 15.2658 | 0.0608 | 72 | 0.4578 |
| 14.7619 | 0.0684 | 81 | 0.4556 |
| 14.1155 | 0.0760 | 90 | 0.4545 |
| 13.4427 | 0.0836 | 99 | 0.4543 |