Text Generation
PEFT
TensorBoard
Safetensors
English
medical
radiology
medical-coding
icd-10
cpt
llama-3
lora
healthcare
conversational
Instructions to use vineetdaniels/NYXMed-V18-Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use vineetdaniels/NYXMed-V18-Model with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("vineetdaniels/NYXMed-V17-Merged") model = PeftModel.from_pretrained(base_model, "vineetdaniels/NYXMed-V18-Model") - Notebooks
- Google Colab
- Kaggle
| [ | |
| { | |
| "step": 100, | |
| "epoch": 0.05407963225850064, | |
| "eval_loss": 0.09886857122182846, | |
| "eval_runtime": 99.676, | |
| "eval_samples_per_second": 5.016, | |
| "eval_steps_per_second": 1.254 | |
| }, | |
| { | |
| "step": 200, | |
| "epoch": 0.10815926451700128, | |
| "eval_loss": 0.08997273445129395, | |
| "eval_runtime": 99.9051, | |
| "eval_samples_per_second": 5.005, | |
| "eval_steps_per_second": 1.251 | |
| }, | |
| { | |
| "step": 300, | |
| "epoch": 0.16223889677550193, | |
| "eval_loss": 0.0827580988407135, | |
| "eval_runtime": 99.9942, | |
| "eval_samples_per_second": 5.0, | |
| "eval_steps_per_second": 1.25 | |
| }, | |
| { | |
| "step": 400, | |
| "epoch": 0.21631852903400256, | |
| "eval_loss": 0.08142668008804321, | |
| "eval_runtime": 100.2043, | |
| "eval_samples_per_second": 4.99, | |
| "eval_steps_per_second": 1.247 | |
| }, | |
| { | |
| "step": 500, | |
| "epoch": 0.2703981612925032, | |
| "eval_loss": 0.0792667418718338, | |
| "eval_runtime": 100.2297, | |
| "eval_samples_per_second": 4.989, | |
| "eval_steps_per_second": 1.247 | |
| }, | |
| { | |
| "step": 600, | |
| "epoch": 0.32447779355100387, | |
| "eval_loss": 0.07775916159152985, | |
| "eval_runtime": 100.4763, | |
| "eval_samples_per_second": 4.976, | |
| "eval_steps_per_second": 1.244 | |
| }, | |
| { | |
| "step": 700, | |
| "epoch": 0.3785574258095045, | |
| "eval_loss": 0.07459608465433121, | |
| "eval_runtime": 100.3142, | |
| "eval_samples_per_second": 4.984, | |
| "eval_steps_per_second": 1.246 | |
| }, | |
| { | |
| "step": 800, | |
| "epoch": 0.4326370580680051, | |
| "eval_loss": 0.07352492958307266, | |
| "eval_runtime": 100.4561, | |
| "eval_samples_per_second": 4.977, | |
| "eval_steps_per_second": 1.244 | |
| }, | |
| { | |
| "step": 900, | |
| "epoch": 0.4867166903265058, | |
| "eval_loss": 0.0734986960887909, | |
| "eval_runtime": 100.4508, | |
| "eval_samples_per_second": 4.978, | |
| "eval_steps_per_second": 1.244 | |
| }, | |
| { | |
| "step": 1000, | |
| "epoch": 0.5407963225850064, | |
| "eval_loss": 0.07477952539920807, | |
| "eval_runtime": 100.3276, | |
| "eval_samples_per_second": 4.984, | |
| "eval_steps_per_second": 1.246 | |
| }, | |
| { | |
| "step": 1100, | |
| "epoch": 0.5948759548435071, | |
| "eval_loss": 0.07260795682668686, | |
| "eval_runtime": 100.4446, | |
| "eval_samples_per_second": 4.978, | |
| "eval_steps_per_second": 1.244 | |
| }, | |
| { | |
| "step": 1200, | |
| "epoch": 0.6489555871020077, | |
| "eval_loss": 0.0755784884095192, | |
| "eval_runtime": 100.3831, | |
| "eval_samples_per_second": 4.981, | |
| "eval_steps_per_second": 1.245 | |
| }, | |
| { | |
| "step": 1300, | |
| "epoch": 0.7030352193605084, | |
| "eval_loss": 0.07137385755777359, | |
| "eval_runtime": 100.5705, | |
| "eval_samples_per_second": 4.972, | |
| "eval_steps_per_second": 1.243 | |
| }, | |
| { | |
| "step": 1400, | |
| "epoch": 0.757114851619009, | |
| "eval_loss": 0.07097452133893967, | |
| "eval_runtime": 101.0814, | |
| "eval_samples_per_second": 4.947, | |
| "eval_steps_per_second": 1.237 | |
| }, | |
| { | |
| "step": 1500, | |
| "epoch": 0.8111944838775096, | |
| "eval_loss": 0.0741763636469841, | |
| "eval_runtime": 100.7848, | |
| "eval_samples_per_second": 4.961, | |
| "eval_steps_per_second": 1.24 | |
| }, | |
| { | |
| "step": 1600, | |
| "epoch": 0.8652741161360102, | |
| "eval_loss": 0.07683192193508148, | |
| "eval_runtime": 100.6515, | |
| "eval_samples_per_second": 4.968, | |
| "eval_steps_per_second": 1.242 | |
| }, | |
| { | |
| "step": 1700, | |
| "epoch": 0.9193537483945109, | |
| "eval_loss": 0.0766952782869339, | |
| "eval_runtime": 100.6532, | |
| "eval_samples_per_second": 4.968, | |
| "eval_steps_per_second": 1.242 | |
| }, | |
| { | |
| "step": 1700, | |
| "epoch": 0.9193537483945109, | |
| "eval_loss": 0.07097452133893967, | |
| "eval_runtime": 100.1105, | |
| "eval_samples_per_second": 4.994, | |
| "eval_steps_per_second": 1.249 | |
| } | |
| ] |