Downloads · 30 days
1
6% of all-time downloads
rayonlabs/Qwen2_5-14B-Instruct-medical-o1-reasoning-SFT-8f32aa88-d0f0-43f3-a420-094a314f7826
Qwen2_5-14B-Instruct-medical-o1-reasoning-SFT-8f32aa88-d0f0-43f3-a420-094a314f7826 is a machine learning model from rayonlabs. 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
6% of all-time downloads
All-time downloads
16
Public
Repo size
2.8 GB
Likes
0
Public
Click a slice to open those files.
.bin276 MB · 49%
From the Hugging Face model README
axolotl version: 0.4.1
adapter: lora
base_model: Qwen/Qwen2.5-14B-Instruct
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 1aedbc4e31c87a64_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/1aedbc4e31c87a64_train_data.json
type:
field_input: Complex_CoT
field_instruction: Question
field_output: Response
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
device_map:
? ''
: 0,1,2,3,4,5,6,7
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: true
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/8e63feb9-79a3-4dc9-b791-5cfa7da0528f
hub_repo: null
hub_strategy: null
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
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: 16
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 1163
micro_batch_size: 4
mlflow_experiment_name: /tmp/1aedbc4e31c87a64_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
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
sequence_len: 1024
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: 8f32aa88-d0f0-43f3-a420-094a314f7826
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 8f32aa88-d0f0-43f3-a420-094a314f7826
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null
</details><br>
This model is a fine-tuned version of Qwen/Qwen2.5-14B-Instruct 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 |
|---|---|---|---|
| 0.8995 | 0.0014 | 1 | 1.0569 |
| 0.7583 | 0.1371 | 100 | 0.6463 |
| 0.5219 | 0.2742 | 200 | 0.6406 |
| 0.5865 | 0.4112 | 300 | 0.6360 |
| 0.6548 | 0.5483 | 400 | 0.6338 |
| 0.6471 | 0.6854 | 500 | 0.6303 |
| 0.6713 | 0.8225 | 600 | 0.6274 |
| 0.6815 | 0.9596 | 700 | 0.6260 |
| 0.4133 | 1.0966 | 800 | 0.6311 |
| 0.6866 | 1.2337 | 900 | 0.6311 |