Downloads · 30 days
1
5% of all-time downloads
mrferr3t/2cc192b8-6458-4152-8616-37483980fba0
2cc192b8-6458-4152-8616-37483980fba0 is a machine learning model from mrferr3t. 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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
1
5% of all-time downloads
All-time downloads
19
Public
Repo size
664 MB
Likes
0
Public
Click a slice to open those files.
.safetensors35.3 MB · 37%
From the Hugging Face model README
axolotl version: 0.4.1
adapter: lora
auto_find_batch_size: false
base_model: Qwen/Qwen2-0.5B
bf16: auto
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
- d71bb2bc00591fdd_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/d71bb2bc00591fdd_train_data.json
type:
field_input: input
field_instruction: instruction
field_output: output
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 2
early_stopping_threshold: 1.0e-05
eval_max_new_tokens: 128
eval_steps: 35
eval_strategy: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: false
group_by_length: false
hub_model_id: mrferr3t/2cc192b8-6458-4152-8616-37483980fba0
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0004
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 35
lora_alpha: 16
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: null
micro_batch_size: 16
mlflow_experiment_name: /tmp/d71bb2bc00591fdd_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 100
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: 35
saves_per_epoch: 0
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: .05000000
wandb_entity: null
wandb_mode: disabled
wandb_name: 4f0a23b8-d970-42d9-a81d-d3c5bc5c2995
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 4f0a23b8-d970-42d9-a81d-d3c5bc5c2995
warmup_steps: 100
weight_decay: 0.0
xformers_attention: null
</details><br>
This model is a fine-tuned version of Qwen/Qwen2-0.5B 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 | 0.0054 | 1 | 0.7766 |
| 0.4151 | 0.1901 | 35 | 0.1866 |
| 0.1592 | 0.3802 | 70 | 0.1440 |
| 0.1387 | 0.5703 | 105 | 0.1358 |
| 0.1477 | 0.7604 | 140 | 0.1307 |
| 0.1322 | 0.9504 | 175 | 0.1270 |
| 0.1074 | 1.1405 | 210 | 0.1273 |
| 0.1135 | 1.3306 | 245 | 0.1238 |
| 0.118 | 1.5207 | 280 | 0.1229 |
| 0.1035 | 1.7108 | 315 | 0.1184 |
| 0.1134 | 1.9009 | 350 | 0.1179 |
| 0.0987 | 2.0910 | 385 | 0.1239 |
| 0.0833 | 2.2811 | 420 | 0.1216 |