karthyick commited on
Commit
cfcc16d
Β·
verified Β·
1 Parent(s): 5efea4f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -62,7 +62,7 @@ A small language model (24.5M parameters) trained on the TinyStories dataset tha
62
  | **Grammar Score** | 8+/10 | **8.8-10/10** (with post-processing) | βœ… Exceeded |
63
  | **Perplexity** | <20 | **15.7** | βœ… Excellent |
64
  | **Articles per Story** | ~10 | **9 average** | βœ… Optimal |
65
- | **Training Time** | <48h | **~35 hours** (RTX 5090) | βœ… Met |
66
 
67
  **Overall Grade:** A (95/100) - Production Ready
68
 
@@ -84,7 +84,7 @@ python train_custom_tokenizer.py \
84
  --max_samples 100000
85
  ```
86
 
87
- ### 2. Train Model (30-40 hours on RTX 5090)
88
  ```bash
89
  # Clean old cache
90
  rm -rf ./data/cache/*
 
62
  | **Grammar Score** | 8+/10 | **8.8-10/10** (with post-processing) | βœ… Exceeded |
63
  | **Perplexity** | <20 | **15.7** | βœ… Excellent |
64
  | **Articles per Story** | ~10 | **9 average** | βœ… Optimal |
65
+ | **Training Time** | <48h | **~6 hours** (RTX 5090) | βœ… Met |
66
 
67
  **Overall Grade:** A (95/100) - Production Ready
68
 
 
84
  --max_samples 100000
85
  ```
86
 
87
+ ### 2. Train Model (6 hours on RTX 5090)
88
  ```bash
89
  # Clean old cache
90
  rm -rf ./data/cache/*