Downloads · 30 days
0
0% of all-time downloads
mamung/7e41a805-8c72-4f35-9888-bb37762d81c4
7e41a805-8c72-4f35-9888-bb37762d81c4 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. The card lists the license as llama2.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
0
0% of all-time downloads
All-time downloads
149
Public
Repo size
8.3 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: codellama/CodeLlama-7b-Instruct-hf
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 2e5ee99a4e2d6b71_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/2e5ee99a4e2d6b71_train_data.json
type:
field_input: constraint_type
field_instruction: constraint
field_output: ground_truth
format: '{instruction} {input}'
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/7e41a805-8c72-4f35-9888-bb37762d81c4
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/2e5ee99a4e2d6b71_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: f485a9e0-e5e4-4354-b944-a3289826cc68
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: f485a9e0-e5e4-4354-b944-a3289826cc68
warmup_steps: 20
weight_decay: 0.01
xformers_attention: false
</details><br>
This model is a fine-tuned version of codellama/CodeLlama-7b-Instruct-hf 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 | 0.0046 | 1 | nan |
| 0.0 | 0.0410 | 9 | nan |
| 0.0 | 0.0821 | 18 | nan |
| 0.0 | 0.1231 | 27 | nan |
| 0.0 | 0.1642 | 36 | nan |
| 0.0 | 0.2052 | 45 | nan |
| 0.0 | 0.2463 | 54 | nan |
| 0.0 | 0.2873 | 63 | nan |
| 0.0 | 0.3283 | 72 | nan |
| 0.0 | 0.3694 | 81 | nan |
| 0.0 | 0.4104 | 90 | nan |
| 0.0 | 0.4515 | 99 | nan |