moved output_graphs into main script and restructured

training log is seperate from normal output & is compressed
slightly adjusted lr
made final test stage test 4xTRAIN_BATCHSZ number of samples

output_graphs.py

@@ -1,37 +0,0 @@
-import re
-import pandas as pd
-import matplotlib.pyplot as plt
-
-text = r"""
-"""
-
-pattern = re.compile(r"step=\s*(\d+)\s+loss=([0-9.]+)\s+acc=([0-9.]+)")
-rows = [(int(s), float(l), float(a)) for s, l, a in pattern.findall(text)]
-df = pd.DataFrame(rows, columns=["step", "loss", "acc"]).sort_values("step").reset_index(drop=True)
-
-# Avoid log(0) issues for loss plot by clamping at a tiny positive value
-eps = 1e-10
-df["loss_clamped"] = df["loss"].clip(lower=eps)
-
-# Plot 1: Loss
-plt.figure(figsize=(9, 4.8))
-plt.plot(df["step"], df["loss_clamped"])
-plt.yscale("log")
-plt.xlabel("Step")
-plt.ylabel("Loss (log scale)")
-plt.title("Training Loss vs Step")
-plt.tight_layout()
-plt.savefig('./files/training_loss_v_step.png')
-plt.show()
-
-# Plot 2: Accuracy
-df["err"] = (1.0 - df["acc"]).clip(lower=eps)
-plt.figure(figsize=(9, 4.8))
-plt.plot(df["step"], df["err"])
-plt.yscale("log")
-plt.xlabel("Step")
-plt.ylabel("Error rate (1 - accuracy) (log scale)")
-plt.title("Training Error Rate vs Step")
-plt.tight_layout()
-plt.savefig('./files/training_error_v_step.png')
-plt.show()

pairwise_comp_nn.py

@@ -16,7 +16,7 @@ class NumberEmbedder(nn.Module):
 
 # 3) Comparator head: takes (ea, eb, e) -> logit for "a > b"
 class PairwiseComparator(nn.Module):
-    def __init__(self, d=4, hidden=16, k=1.0):
+    def __init__(self, d=4, hidden=16, k=0.5):
         super().__init__()
         self.log_k = nn.Parameter(torch.tensor([k]))
         self.embed = NumberEmbedder(d, hidden)

pairwise_compare.py

@@ -2,11 +2,16 @@
 # pairwise_compare.py
 import logging
 import random
+import lzma
 
 import torch
 from torch import nn
 from torch.nn import functional as F
 
+import re
+import pandas as pd
+import matplotlib.pyplot as plt
+
 import pairwise_comp_nn as comp_nn
 
 # early pytorch device setup
@@ -20,13 +25,60 @@ TRAIN_PROGRESS = 10
 BATCH_LOWER = -100.0
 BATCH_UPPER = 100.0
 DO_VERBOSE_EARLY_TRAIN = False
+
+# Files
 MODEL_PATH = "./files/pwcomp.model"
 LOGGING_PATH = "./files/output.log"
 EMBED_CHART_PATH = "./files/embedding_chart.png"
-EMBEDDINGS_DATA = "./files/embedding_data.csv"
+EMBEDDINGS_DATA_PATH = "./files/embedding_data.csv"
+TRAINING_LOG_PATH = "./files/training.log.xz"
 
-def plt_embeddings(model: comp_nn.PairwiseComparator):
+def parse_training_log(file_path: str) -> pd.DataFrame:
-    import matplotlib.pyplot as plt
+    text: str = ""
+    with lzma.open(file_path, mode='rt') as f:
+        text = f.read()
+        
+
+    pattern = re.compile(r"step=\s*(\d+)\s+loss=([0-9.]+)\s+acc=([0-9.]+)")
+    rows = [(int(s), float(l), float(a)) for s, l, a in pattern.findall(text)]
+    df = pd.DataFrame(rows, columns=["step", "loss", "acc"]).sort_values("step").reset_index(drop=True)
+
+    # Avoid log(0) issues for loss plot by clamping at a tiny positive value
+    eps = 1e-10
+    df["loss_clamped"] = df["loss"].clip(lower=eps)
+
+    return df
+
+def plt_loss_tstep(df: pd.DataFrame) -> None:
+    # Plot 1: Loss
+    plt.figure(figsize=(8, 4))
+    plt.plot(df["step"], df["loss_clamped"])
+    plt.yscale("log")
+    plt.xlabel("Step")
+    plt.ylabel("Loss (log scale)")
+    plt.title("Training Loss vs Step")
+    plt.tight_layout()
+    plt.savefig('./files/training_loss_v_step.png')
+    plt.close()
+
+    return None
+
+def plt_acc_tstep(df: pd.DataFrame, eps=1e-10) -> None:
+    # Plot 2: Accuracy
+    df["err"] = (1.0 - df["acc"]).clip(lower=eps)
+    plt.figure(figsize=(8, 4))
+    plt.plot(df["step"], df["err"])
+    plt.yscale("log")
+    plt.xlabel("Step")
+    plt.ylabel("Error rate (1 - accuracy) (log scale)")
+    plt.title("Training Error Rate vs Step")
+    plt.tight_layout()
+    plt.savefig('./files/training_error_v_step.png')
+    plt.close()
+
+    return None
+
+def plt_embeddings(model: comp_nn.PairwiseComparator) -> None:
     import csv
 
     log.info("Starting embeddings sweep...")
@@ -35,7 +87,7 @@ def plt_embeddings(model: comp_nn.PairwiseComparator):
         xs = torch.arange(
             BATCH_LOWER,
             BATCH_UPPER + 1.0,
-            1.0,
+            0.1,
         ).unsqueeze(1).to(DEVICE)   # shape: (N, 1)
 
         embeddings = model.embed(xs)  # shape: (N, d)
@@ -49,13 +101,17 @@ def plt_embeddings(model: comp_nn.PairwiseComparator):
         
     plt.legend()
     plt.savefig(EMBED_CHART_PATH)
-    #plt.show()
+    plt.close()
+
+    # save all our embeddings data to csv
     csv_data = list(zip(xs.squeeze().tolist(), embeddings.tolist()))
-    with open(file=EMBEDDINGS_DATA, mode="w", newline='') as f:
+    with open(file=EMBEDDINGS_DATA_PATH, mode="w", newline='') as f:
         csv_file = csv.writer(f)
         csv_file.writerows(csv_data)
 
-def get_torch_info():
+    return None
+    
+def get_torch_info() -> None:
     log.info("PyTorch Version: %s", torch.__version__)
     log.info("HIP Version: %s", torch.version.hip)
     log.info("CUDA support: %s", torch.cuda.is_available())
@@ -65,14 +121,14 @@ def get_torch_info():
 
     log.info("Using %s compute mode", DEVICE)
 
-def set_seed(seed: int):
+def set_seed(seed: int) -> None:
     random.seed(seed)
     torch.manual_seed(seed)
     if torch.cuda.is_available():
         torch.cuda.manual_seed_all(seed)
 
-# 1) Data: pairs (a, b) with label y = 1 if a > b else 0
+# Data: pairs (a, b) with label y = 1 if a > b else 0 -> (a,b,y)
-def sample_batch(batch_size: int, low=BATCH_LOWER, high=BATCH_UPPER):
+def sample_batch(batch_size: int, low=BATCH_LOWER, high=BATCH_UPPER, epsi=1e-4) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
     a = (high - low) * torch.rand(batch_size, 1) + low
     b = (high - low) * torch.rand(batch_size, 1) + low
 
@@ -88,9 +144,12 @@ def training_entry():
     set_seed(0)
 
     model = comp_nn.PairwiseComparator(d=DIMENSIONS).to(DEVICE)
-    opt = torch.optim.AdamW(model.parameters(), lr=9e-4, weight_decay=1e-3)
+    opt = torch.optim.AdamW(model.parameters(), lr=8e-4, weight_decay=1e-3)
 
-    # 4) Train
+    log.info(f"Using {TRAINING_LOG_PATH} as the logging destination for training...")
+    with lzma.open(TRAINING_LOG_PATH, mode='wt') as tlog:
+        # training loop
+        training_start_time = datetime.datetime.now()
         for step in range(TRAIN_STEPS):
             a, b, y = sample_batch(TRAIN_BATCHSZ)
             a, b, y = a.to(DEVICE), b.to(DEVICE), y.to(DEVICE)
@@ -102,20 +161,22 @@ def training_entry():
             loss_fn.backward()
             opt.step()
 
-        if step <= TRAIN_PROGRESS and DO_VERBOSE_EARLY_TRAIN is True:
+            if step % TRAIN_PROGRESS == 0:
                 with torch.no_grad():
                     pred = (torch.sigmoid(logits) > 0.5).float()
                     acc = (pred == y).float().mean().item()
-            log.info(f"step={step:5d} loss={loss_fn.item():.7f} acc={acc:.7f}")
+                tlog.write(f"step={step:5d} loss={loss_fn.item():.7f} acc={acc:.7f}\n")
-        elif step % TRAIN_PROGRESS == 0:
-            with torch.no_grad():
-                pred = (torch.sigmoid(logits) > 0.5).float()
-                acc = (pred == y).float().mean().item()
-            log.info(f"step={step:5d} loss={loss_fn.item():.7f} acc={acc:.7f}")
 
-    # 5) Quick test: evaluate final model accuracy on fresh pairs
+                # also print to normal text log occasionally to show some activity.
+                if step % 2500 == 0:
+                    log.info(f"still training... step={step} of {TRAIN_STEPS}")
+
+    training_end_time = datetime.datetime.now()
+    log.info(f"Training steps complete. Start time: {training_start_time} End time: {training_end_time}")
+
+    # evaluate final model accuracy on fresh pairs
     with torch.no_grad():
-        a, b, y = sample_batch(TRAIN_BATCHSZ)
+        a, b, y = sample_batch(TRAIN_BATCHSZ*4)
         a, b, y = a.to(DEVICE), b.to(DEVICE), y.to(DEVICE)
         logits = model(a, b)
         pred = (torch.sigmoid(logits) > 0.5).float()
@@ -174,12 +235,17 @@ if __name__ == '__main__':
         # alt call patern
         # python3 pairwise_compare.py train
         # python3 pairwise_compare.py infer
+        # python3 pairwise_compare.py graphs
         if len(sys.argv) > 1:
             mode = sys.argv[1].strip().lower()
             if mode == "train":
                 training_entry()
             elif mode == "infer":
                 infer_entry()
+            elif mode == "graphs":
+                data = parse_training_log(TRAINING_LOG_PATH)
+                plt_loss_tstep(data)
+                plt_acc_tstep(data)
             else:
                 log.error(f"Unknown operation: {mode}")
                 log.error("Invalid call syntax, call script as \"train.py\" or \"infer.py\" or as pairwise_compare.py <mode> where mode is \"train\" or \"infer\"")