Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 sample_data/mnist_test.csv filter=lfs diff=lfs merge=lfs -text
 sample_data/mnist_train_small.csv filter=lfs diff=lfs merge=lfs -text
+wandb/run-20260622_130442-dha4p9go/run-dha4p9go.wandb filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -5,4 +5,6 @@ __pycache__/
 *.pyc
 *.pyo
 *.pyd
-.pth
+*.pth
+artifacts/model.pth
+.env

inference.py

@@ -1,5 +1,6 @@
 import argparse
 import logging
+import os
 import torch
 from huggingface_hub import hf_hub_download
 
@@ -28,8 +29,13 @@ if __name__ == "__main__":
     cfg = GPT124M_CONFIG
     tokenizer = TikTokenizer("gpt2")
 
-    logging.info(f"Downloading weights from {args.repo_id} ...")
-    weights_path = hf_hub_download(repo_id=args.repo_id, filename=args.filename)
+    local_path = os.path.join("artifacts", "model.pth")
+    if os.path.exists(local_path):
+        weights_path = local_path
+        logging.info(f"Loading local model from {weights_path}")
+    else:
+        logging.info(f"Downloading weights from {args.repo_id} ...")
+        weights_path = hf_hub_download(repo_id=args.repo_id, filename=args.filename)
 
     model = GPTModel(cfg).to(device)
     state_dict = torch.load(weights_path, map_location=device)

requirements.txt

@@ -6,4 +6,5 @@ pandas
 matplotlib
 seaborn
 pytest
-datasets
+datasets
+wandb

src/engine/train.py

@@ -1,62 +1,136 @@
 import torch
 import torch.nn.functional as F
 import logging
+import time
+from dataclasses import asdict
+
 import numpy as np
+import wandb
 from torch.cuda.amp import autocast, GradScaler
+from tqdm import tqdm
+
 from src.engine.generate import generate_greedy
 
-# Enable TF32 for faster matmul
 torch.backends.cuda.matmul.allow_tf32 = True
 torch.backends.cudnn.allow_tf32 = True
-scaler = GradScaler()
 
 
-def calc_loss(logits, targets):
-    """Cross-entropy loss over a batch."""
+def calc_cross_entropy_loss(logits, targets):
     B, T, V = logits.shape
     return F.cross_entropy(logits.view(B * T, V), targets.view(B * T))
 
+
+def calc_perplexity(loss: float) -> float:
+    return float(np.exp(loss))
+
+
 def train(
     model, optimizer, train_loader, val_loader, device, cfg, sample_prompt, tokenizer
 ):
-    scaler = GradScaler()  
+    run = wandb.init(
+        entity="pjawale-student",
+        project="gpt2-pytorch",
+        config=asdict(cfg),
+    )
+
+    scaler = GradScaler()
     history = []
-    
-    for epoch in range(1, cfg.num_epochs + 1):
-        model.train()
-        train_loss = 0.0
-        
-        for batch_idx, (inputs, targets) in enumerate(train_loader, 1):
-            inputs, targets = inputs.to(device), targets.to(device)
-            optimizer.zero_grad()
-            
-            # MIXED PRECISION FORWARD
-            with autocast(dtype=torch.bfloat16):
-                loss = calc_loss(model(inputs), targets)
-            
-            # MIXED PRECISION BACKWARD
-            scaler.scale(loss).backward()
-            scaler.step(optimizer)
-            scaler.update()
-            
-            train_loss += loss.item()
-
-            if batch_idx % 50 == 0:
-                logging.info(f"  Epoch {epoch}/{cfg.num_epochs} | batch {batch_idx}/{len(train_loader)} | loss={loss.item():.4f}")
-
-        # Validation
-        model.eval()
-        val_loss = 0.0
-        with torch.no_grad():
-            for inputs, targets in val_loader:
+    tokens_per_batch = cfg.batch_size * cfg.context_window_size
+    global_step = 0
+
+    try:
+        for epoch in range(1, cfg.num_epochs + 1):
+            model.train()
+            train_loss = 0.0
+            epoch_start = time.perf_counter()
+            window_start = epoch_start
+            window_batches = 0
+
+            pbar = tqdm(
+                train_loader,
+                desc=f"Epoch {epoch}/{cfg.num_epochs}",
+                unit="batch",
+                leave=True,
+            )
+
+            for batch_idx, (inputs, targets) in enumerate(pbar, 1):
                 inputs, targets = inputs.to(device), targets.to(device)
-                with autocast(dtype=torch.bfloat16):  # ADD FOR CONSISTENCY
-                    val_loss += calc_loss(model(inputs), targets).item()
-
-        avg_train = train_loss / len(train_loader)
-        avg_val = val_loss / len(val_loader)
-        logging.info(f"Epoch {epoch:2d}/{cfg.num_epochs} | train={avg_train:.4f} | val={avg_val:.4f}")
-        history.append((avg_train, avg_val))
-        logging.info(f"  Sample: {generate_greedy(model, tokenizer, device, sample_prompt)}\n")
+                optimizer.zero_grad()
+
+                with autocast(dtype=torch.bfloat16):
+                    loss = calc_cross_entropy_loss(model(inputs), targets)
+
+                scaler.scale(loss).backward()
+                scaler.step(optimizer)
+                scaler.update()
+
+                train_loss += loss.item()
+                window_batches += 1
+                global_step += 1
+
+                if batch_idx % 10 == 0 or batch_idx == len(train_loader):
+                    now = time.perf_counter()
+                    elapsed = now - window_start
+                    tok_s = (window_batches * tokens_per_batch) / elapsed if elapsed > 0 else 0.0
+                    window_start = now
+                    window_batches = 0
+
+                    pbar.set_postfix(
+                        loss=f"{loss.item():.4f}",
+                        tok_s=f"{tok_s:,.0f}",
+                    )
+
+                    wandb.log(
+                        {
+                            "train/batch_loss": loss.item(),
+                            "train/batch_perplexity": calc_perplexity(loss.item()),
+                            "train/tok_s": tok_s,
+                            "epoch": epoch,
+                        },
+                        step=global_step,
+                    )
+
+            epoch_elapsed = time.perf_counter() - epoch_start
+            epoch_tokens = len(train_loader) * tokens_per_batch
+            epoch_tok_s = epoch_tokens / epoch_elapsed if epoch_elapsed > 0 else 0.0
+
+            model.eval()
+            val_loss = 0.0
+            with torch.no_grad():
+                for inputs, targets in tqdm(val_loader, desc="Validating", leave=False):
+                    inputs, targets = inputs.to(device), targets.to(device)
+                    with autocast(dtype=torch.bfloat16):
+                        val_loss += calc_cross_entropy_loss(model(inputs), targets).item()
+
+            avg_train = train_loss / len(train_loader)
+            avg_val = val_loss / len(val_loader)
+            avg_train_perplexity = calc_perplexity(avg_train)
+            avg_val_perplexity = calc_perplexity(avg_val)
+            sample = generate_greedy(model, tokenizer, device, sample_prompt)
+
+            logging.info(
+                f"Epoch {epoch:2d}/{cfg.num_epochs} | train={avg_train:.4f} | val={avg_val:.4f} | "
+                f"train_perplexity={avg_train_perplexity:.4f} | val_perplexity={avg_val_perplexity:.4f} | "
+                f"{epoch_tok_s:,.0f} tok/s (epoch avg)"
+            )
+
+            wandb.log(
+                {
+                    "train/loss": avg_train,
+                    "val/loss": avg_val,
+                    "train/perplexity": avg_train_perplexity,
+                    "val/perplexity": avg_val_perplexity,
+                    "train/tok_s_epoch": epoch_tok_s,
+                    "sample": sample,
+                    "epoch": epoch,
+                },
+                step=global_step,
+            )
+
+            history.append((avg_train, avg_val))
+            logging.info(f"  Sample: {sample}\n")
+
+    finally:
+        wandb.finish()
 
     return np.array(history)

src/model/config.py

@@ -35,7 +35,7 @@ GPT124M_CONFIG = GPTConfig(
     num_heads=12,
     drop_rate=0.0,
     n_layer=12,
-    num_epochs=5,
+    num_epochs=1,
     num_workers=4, 
     lr=3e-4,
     temperature=1.0,

train_model.py

@@ -16,6 +16,7 @@ from src.data.dataset import create_gpt_dataloader
 from src.model.gpt import GPTModel
 from src.data.tokenizer import TikTokenizer
 from src.engine.train import train
+from huggingface_hub import hf_hub_download
 
 logging.basicConfig(level=logging.INFO, format="%(levelname)s: %(message)s")
 
@@ -26,6 +27,8 @@ def parse_args():
     parser.add_argument("--data-url", type=str, default=DEFAULT_DATA_URL)
     parser.add_argument("--dataset-path", type=str, default=DEFAULT_DATASET_PATH)
     parser.add_argument("--output-dir", type=str, default=DEFAULT_OUTPUT_DIR)
+    parser.add_argument("--repo-id", type=str, default="triton329/gpt2")
+    parser.add_argument("--filename", type=str, default="GPT-2/artifacts/model.pth")
     return parser.parse_args()
 
 
@@ -51,6 +54,7 @@ if __name__ == "__main__":
         stride=cfg.stride,
         batch_size=cfg.batch_size,
         num_workers=cfg.num_workers,
+        pin_memory=True,
     )
     val_loader = create_gpt_dataloader(
         val_text,
@@ -59,6 +63,7 @@ if __name__ == "__main__":
         stride=cfg.stride,
         batch_size=cfg.batch_size,
         num_workers=cfg.num_workers,
+        pin_memory=True,
     )
     logging.info(
         f"  Train batches: {len(train_loader)} | Val batches: {len(val_loader)}"
@@ -69,6 +74,17 @@ if __name__ == "__main__":
         raise RuntimeError("No CUDA device found. CPU training is not supported.")
 
     model = GPTModel(cfg).to(device)
+    local_path = os.path.join(args.output_dir, "model.pth")
+    if os.path.exists(local_path):
+        weights_path = local_path
+        logging.info(f"Loading local weights from {weights_path}")
+    else:
+        logging.info(f"Downloading weights from {args.repo_id} ...")
+        weights_path = hf_hub_download(repo_id=args.repo_id, filename=args.filename)
+    state_dict = torch.load(weights_path, map_location=device)
+    model.load_state_dict(state_dict, strict=False)
+    
+    logging.info("Loaded pretrained weights")
     optimizer = torch.optim.AdamW(model.parameters(), lr=cfg.lr)
     logging.info(
         f"  Model: {sum(p.numel() for p in model.parameters()):,} params | device: {device}"

wandb/debug-internal.log

@@ -0,0 +1,197 @@
+{"time":"2026-06-22T13:04:42.660730794Z","level":"INFO","msg":"wandb-core"}
+{"time":"2026-06-22T13:04:42.66127115Z","level":"INFO","msg":"stream: starting","core version":"0.27.2"}
+{"time":"2026-06-22T13:04:42.986008785Z","level":"INFO","msg":"stream: created new stream","id":"dha4p9go"}
+{"time":"2026-06-22T13:04:42.986071884Z","level":"INFO","msg":"handler: started"}
+{"time":"2026-06-22T13:04:42.986240005Z","level":"INFO","msg":"stream: started"}
+{"time":"2026-06-22T13:04:42.986272882Z","level":"INFO","msg":"writer: started","stream_id":"dha4p9go"}
+{"time":"2026-06-22T13:04:42.986292513Z","level":"INFO","msg":"sender: started"}
+{"time":"2026-06-22T13:04:44.06588626Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":2}
+{"time":"2026-06-22T13:04:44.370960804Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:04:59.066168693Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":2,"events_offset":0,"events_lines":2,"console_offset":2,"console_lines":3,"uploaded_len":2}
+{"time":"2026-06-22T13:04:59.414924178Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:05:14.066021294Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":4,"events_offset":2,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:05:14.349079599Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:05:29.066004741Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":6,"history_lines":4,"events_offset":4,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:05:29.376279603Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:05:44.066669927Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":10,"history_lines":3,"events_offset":6,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:05:44.431216173Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:05:59.066063064Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":13,"history_lines":4,"events_offset":8,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:05:59.38386744Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:06:14.065869131Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":17,"history_lines":4,"events_offset":10,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:06:14.373706429Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:06:29.066188147Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":21,"history_lines":4,"events_offset":12,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:06:29.410331688Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:06:44.066729941Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":25,"history_lines":4,"events_offset":14,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:06:44.35917359Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:06:59.065972138Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":29,"history_lines":4,"events_offset":16,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:06:59.51603569Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:07:14.066473598Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":33,"history_lines":3,"events_offset":18,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:07:14.436919783Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:07:29.066622963Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":36,"history_lines":4,"events_offset":20,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:07:29.720448036Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:07:44.066405507Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":40,"history_lines":4,"events_offset":22,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:07:44.372530748Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:07:59.066090139Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":44,"history_lines":4,"events_offset":24,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:07:59.423465657Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:08:14.066430779Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":48,"history_lines":4,"events_offset":26,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:08:14.40413525Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:08:29.066452342Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":52,"history_lines":4,"events_offset":28,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:08:29.433530978Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:08:44.066651476Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":56,"history_lines":3,"events_offset":30,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:08:44.374315892Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:08:59.066690415Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":59,"history_lines":4,"events_offset":32,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:08:59.558020456Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:09:14.066217579Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":63,"history_lines":4,"events_offset":34,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:09:14.538803988Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:09:29.066503326Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":67,"history_lines":4,"events_offset":36,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:09:29.677704844Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:09:44.066230925Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":71,"history_lines":4,"events_offset":38,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:09:45.010785128Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:09:59.066813063Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":75,"history_lines":4,"events_offset":40,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:09:59.35974622Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:10:14.066206432Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":79,"history_lines":3,"events_offset":42,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:10:14.365718891Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:10:29.066636693Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":82,"history_lines":4,"events_offset":44,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:10:30.051534367Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:10:44.066497981Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":86,"history_lines":4,"events_offset":46,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:10:44.374571807Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:10:59.066665341Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":90,"history_lines":4,"events_offset":48,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:10:59.416594153Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:11:14.066694827Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":94,"history_lines":4,"events_offset":50,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:11:14.383182275Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:11:29.066540345Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":98,"history_lines":4,"events_offset":52,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:11:29.403610089Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:11:44.066779446Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":102,"history_lines":3,"events_offset":54,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:11:44.44479461Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:11:59.066725681Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":105,"history_lines":4,"events_offset":56,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:11:59.378761821Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:12:14.066645205Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":109,"history_lines":4,"events_offset":58,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:12:14.342045401Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:12:29.066163754Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":113,"history_lines":4,"events_offset":60,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:12:29.38031115Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:12:44.066696431Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":117,"history_lines":4,"events_offset":62,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:12:44.323231638Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:12:59.066021219Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":121,"history_lines":4,"events_offset":64,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:12:59.494159006Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:13:14.066551059Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":125,"history_lines":3,"events_offset":66,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:13:14.363646369Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:13:29.066941827Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":128,"history_lines":4,"events_offset":68,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:13:29.352443517Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:13:44.066386745Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":132,"history_lines":4,"events_offset":70,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:13:44.363611571Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:13:59.066065064Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":136,"history_lines":4,"events_offset":72,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:13:59.36379284Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:14:14.065990016Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":140,"history_lines":4,"events_offset":74,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:14:14.329761208Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:14:29.06594223Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":144,"history_lines":3,"events_offset":76,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:14:29.328338369Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:14:44.066543388Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":147,"history_lines":4,"events_offset":78,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:14:44.509708496Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:14:59.066167852Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":151,"history_lines":4,"events_offset":80,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:14:59.490483182Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:15:14.065920483Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":155,"history_lines":4,"events_offset":82,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:15:14.671523075Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:15:29.066640749Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":159,"history_lines":4,"events_offset":84,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:15:29.50016493Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:15:44.066051946Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":163,"history_lines":4,"events_offset":86,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:15:44.362149815Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:15:59.065970304Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":167,"history_lines":3,"events_offset":88,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:15:59.357212283Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:16:14.066678028Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":170,"history_lines":4,"events_offset":90,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:16:14.416915065Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:16:29.066188961Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":174,"history_lines":4,"events_offset":92,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:16:29.349371947Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:16:44.066851069Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":178,"history_lines":4,"events_offset":94,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:16:44.432035722Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:16:59.066457421Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":182,"history_lines":4,"events_offset":96,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:16:59.358441192Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:17:14.066456205Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":186,"history_lines":4,"events_offset":98,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:17:14.360386855Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:17:29.06671787Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":190,"history_lines":3,"events_offset":100,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:17:29.412817251Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:17:44.066397617Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":193,"history_lines":4,"events_offset":102,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:17:44.395304947Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:17:59.066566068Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":197,"history_lines":4,"events_offset":104,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:17:59.357734362Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:18:14.066372292Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":201,"history_lines":4,"events_offset":106,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:18:14.410064678Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:18:29.06660889Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":205,"history_lines":4,"events_offset":108,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:18:29.434748551Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:18:44.066364689Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":209,"history_lines":4,"events_offset":110,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:18:44.381444935Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:18:59.06624177Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":213,"history_lines":3,"events_offset":112,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:18:59.360679465Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:19:14.06591638Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":216,"history_lines":4,"events_offset":114,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:19:14.331790272Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:19:29.066121323Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":220,"history_lines":4,"events_offset":116,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:19:29.329933056Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:19:44.066149215Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":224,"history_lines":4,"events_offset":118,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:19:44.393707681Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:19:59.066785837Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":228,"history_lines":4,"events_offset":120,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:19:59.389776853Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:20:14.0667644Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":232,"history_lines":4,"events_offset":122,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:20:14.370443666Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:20:29.066303036Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":236,"history_lines":3,"events_offset":124,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:20:29.417998571Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:20:44.066364364Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":239,"history_lines":4,"events_offset":126,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:20:44.363554403Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:20:59.066262984Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":243,"history_lines":4,"events_offset":128,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:20:59.388786528Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:21:14.065899293Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":247,"history_lines":4,"events_offset":130,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:21:14.456796539Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:21:29.066394994Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":251,"history_lines":4,"events_offset":132,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:21:29.421446747Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:21:44.066478602Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":255,"history_lines":3,"events_offset":134,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:21:44.481977933Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:21:59.06627728Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":258,"history_lines":4,"events_offset":136,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:21:59.375008336Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:22:14.066162169Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":262,"history_lines":4,"events_offset":138,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:22:14.400334142Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:22:29.065924263Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":266,"history_lines":4,"events_offset":140,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:22:29.394311577Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:22:44.065937158Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":270,"history_lines":4,"events_offset":142,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:22:44.363782085Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:22:59.066066545Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":274,"history_lines":4,"events_offset":144,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:22:59.433887386Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:23:14.066219514Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":278,"history_lines":4,"events_offset":146,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:23:14.346283951Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:23:29.065949464Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":282,"history_lines":3,"events_offset":148,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:23:29.375798806Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:23:44.066199628Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":285,"history_lines":4,"events_offset":150,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:23:44.417693746Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:23:59.066352646Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":289,"history_lines":4,"events_offset":152,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:23:59.390451335Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:24:14.066821679Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":293,"history_lines":4,"events_offset":154,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:24:14.392388863Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:24:29.066279855Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":297,"history_lines":4,"events_offset":156,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:24:29.493963667Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:24:44.066681845Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":301,"history_lines":3,"events_offset":158,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:24:44.354808849Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:24:59.065883568Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":304,"history_lines":4,"events_offset":160,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:24:59.417800621Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:25:14.066325408Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":308,"history_lines":4,"events_offset":162,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:25:14.669757211Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:25:29.066231116Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":312,"history_lines":4,"events_offset":164,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:25:29.483273888Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:25:44.066075196Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":316,"history_lines":4,"events_offset":166,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:25:44.519602158Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:25:59.066809238Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":320,"history_lines":4,"events_offset":168,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:25:59.519469663Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:26:14.066475239Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":324,"history_lines":4,"events_offset":170,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:26:14.458071548Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:26:29.066068585Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":328,"history_lines":3,"events_offset":172,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:26:29.447744844Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:26:44.0668045Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":331,"history_lines":4,"events_offset":174,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:26:44.739668572Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:26:59.066827175Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":335,"history_lines":4,"events_offset":176,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:26:59.654331022Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:27:14.066819023Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":339,"history_lines":4,"events_offset":178,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:27:14.727796148Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:27:25.265030197Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-06-22T13:27:25.265219608Z","level":"INFO","msg":"filestream: sending request","total_files":3,"history_offset":343,"history_lines":3,"console_offset":4,"console_lines":5,"uploaded_len":3,"complete":true,"exit_code":0}
+{"time":"2026-06-22T13:27:26.155160645Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:27:26.156721896Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2026-06-22T13:27:26.160304355Z","level":"INFO","msg":"stream: finishing up"}
+{"time":"2026-06-22T13:27:26.160325847Z","level":"INFO","msg":"handler: closed"}
+{"time":"2026-06-22T13:27:26.160381752Z","level":"INFO","msg":"sender: closed"}
+{"time":"2026-06-22T13:27:26.160388481Z","level":"INFO","msg":"stream: all finished"}

wandb/debug.log

@@ -0,0 +1,25 @@
+2026-06-22 13:04:42,658 INFO    MainThread:1019 [wandb_setup.py:_flush():81] Current SDK version is 0.27.2
+2026-06-22 13:04:42,658 INFO    MainThread:1019 [wandb_setup.py:_flush():81] Configure stats pid to 1019
+2026-06-22 13:04:42,658 INFO    MainThread:1019 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-06-22 13:04:42,658 INFO    MainThread:1019 [wandb_init.py:setup_run_log_directory():723] Logging user logs to /content/GPT-2/wandb/run-20260622_130442-dha4p9go/logs/debug.log
+2026-06-22 13:04:42,659 INFO    MainThread:1019 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to /content/GPT-2/wandb/run-20260622_130442-dha4p9go/logs/debug-internal.log
+2026-06-22 13:04:42,659 INFO    MainThread:1019 [wandb_init.py:init():766] calling init triggers
+2026-06-22 13:04:42,659 INFO    MainThread:1019 [wandb_init.py:init():771] wandb.init called with sweep_config: {}
+config: {'vocab_size': 50257, 'context_window_size': 256, 'context_length': 1024, 'batch_size': 64, 'stride': 256, 'embed_dim': 768, 'head_dim': 64, 'num_heads': 12, 'drop_rate': 0.0, 'n_layer': 12, 'num_epochs': 1, 'num_workers': 4, 'lr': 0.0003, 'temperature': 1.0, '_wandb': {}}
+2026-06-22 13:04:42,659 INFO    MainThread:1019 [wandb_init.py:init():814] starting backend
+2026-06-22 13:04:42,659 INFO    MainThread:1019 [wandb_init.py:init():820] Connected to an existing wandb-core service via WANDB_SERVICE
+2026-06-22 13:04:42,659 INFO    MainThread:1019 [wandb_init.py:init():829] sending inform_init request
+2026-06-22 13:04:42,986 INFO    MainThread:1019 [wandb_init.py:init():834] backend started and connected
+2026-06-22 13:04:42,990 INFO    MainThread:1019 [wandb_init.py:init():904] updated telemetry
+2026-06-22 13:04:42,995 INFO    MainThread:1019 [wandb_init.py:init():927] communicating run to backend with 90.0 second timeout
+2026-06-22 13:04:43,541 INFO    MainThread:1019 [wandb_init.py:init():972] starting run threads in backend
+2026-06-22 13:04:44,056 INFO    MainThread:1019 [wandb_run.py:_console_start():2523] atexit reg
+2026-06-22 13:04:44,056 INFO    MainThread:1019 [wandb_run.py:_redirect():2373] redirect: wrap_raw
+2026-06-22 13:04:44,056 INFO    MainThread:1019 [wandb_run.py:_redirect():2442] Wrapping output streams.
+2026-06-22 13:04:44,056 INFO    MainThread:1019 [wandb_run.py:_redirect():2465] Redirects installed.
+2026-06-22 13:04:44,062 INFO    MainThread:1019 [wandb_init.py:init():1010] run started, returning control to user process
+2026-06-22 13:27:23,166 INFO    MainThread:1019 [wandb_run.py:_finish():2285] finishing run pjawale-student/gpt2-pytorch/dha4p9go
+2026-06-22 13:27:23,167 INFO    MainThread:1019 [wandb_run.py:_atexit_cleanup():2490] got exitcode: 0
+2026-06-22 13:27:23,167 INFO    MainThread:1019 [wandb_run.py:_restore():2472] restore
+2026-06-22 13:27:23,167 INFO    MainThread:1019 [wandb_run.py:_restore():2478] restore done
+2026-06-22 13:27:26,159 INFO    MainThread:1019 [wandb_run.py:_footer_sync_info():3891] logging synced files

wandb/run-20260622_130442-dha4p9go/files/config.yaml

@@ -0,0 +1,83 @@
+_wandb:
+    value:
+        cli_version: 0.27.2
+        e:
+            zze5q4wfftrhphcr57ma7c3se33zut8w:
+                codePath: train_model.py
+                codePathLocal: train_model.py
+                cpu_count: 6
+                cpu_count_logical: 12
+                cudaVersion: "13.0"
+                disk:
+                    /:
+                        total: "253055008768"
+                        used: "51951943680"
+                email: pjawale@wisc.edu
+                executable: /usr/bin/python3
+                git:
+                    commit: e46ee167dc2f1d60e959b25e0e67bab662677acf
+                    remote: https://github.com/Tydos/GPT-2
+                gpu: NVIDIA A100-SXM4-40GB
+                gpu_count: 1
+                gpu_nvidia:
+                    - architecture: Ampere
+                      cudaCores: 6912
+                      memoryTotal: "42949672960"
+                      name: NVIDIA A100-SXM4-40GB
+                      uuid: GPU-314c604d-9d75-ef32-01fe-33fd37c595c5
+                host: 18db444010a9
+                memory:
+                    total: "89629196288"
+                os: Linux-6.6.122+-x86_64-with-glibc2.35
+                program: /content/GPT-2/train_model.py
+                python: CPython 3.12.13
+                root: /content/GPT-2
+                startedAt: "2026-06-22T13:04:42.657339Z"
+                writerId: zze5q4wfftrhphcr57ma7c3se33zut8w
+        m: []
+        python_version: 3.12.13
+        t:
+            "1":
+                - 1
+                - 49
+                - 51
+            "2":
+                - 1
+                - 49
+                - 51
+            "3":
+                - 2
+                - 16
+                - 61
+            "4": 3.12.13
+            "5": 0.27.2
+            "12": 0.27.2
+            "13": linux-x86_64
+batch_size:
+    value: 64
+context_length:
+    value: 1024
+context_window_size:
+    value: 256
+drop_rate:
+    value: 0
+embed_dim:
+    value: 768
+head_dim:
+    value: 64
+lr:
+    value: 0.0003
+n_layer:
+    value: 12
+num_epochs:
+    value: 1
+num_heads:
+    value: 12
+num_workers:
+    value: 4
+stride:
+    value: 256
+temperature:
+    value: 1
+vocab_size:
+    value: 50257

wandb/run-20260622_130442-dha4p9go/files/output.log

@@ -0,0 +1,9 @@
+/content/GPT-2/src/engine/train.py:36: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
+  scaler = GradScaler()
+Epoch 1/1:   0% 0/3458 [00:00<?, ?batch/s]/content/GPT-2/src/engine/train.py:60: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead.
+  with autocast(dtype=torch.bfloat16):
+Epoch 1/1: 100% 3458/3458 [22:35<00:00,  2.55batch/s, loss=4.4687, tok_s=42,951]
+Validating:   0% 0/15 [00:00<?, ?it/s]/content/GPT-2/src/engine/train.py:102: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead.
+  with autocast(dtype=torch.bfloat16):
+INFO: Epoch  1/1 | train=4.6269 | val=4.6042 | train_perplexity=102.2017 | val_perplexity=99.9030 | 41,794 tok/s (epoch avg)
+INFO:   Sample: Gisburn had a evil smile, and was a " good one " . He was also a member of the Australian team , and was a

wandb/run-20260622_130442-dha4p9go/files/requirements.txt

@@ -0,0 +1,745 @@
+types-setuptools==82.0.0.20260518
+pip==24.1.2
+requirements-parser==0.9.0
+setuptools==75.2.0
+google-colab==1.0.0
+tf_keras==2.20.0
+google-cloud-datastore==2.25.0
+google-pasta==0.2.0
+plotnine==0.14.5
+opentelemetry-exporter-otlp-proto-http==1.38.0
+en_core_web_sm==3.8.0
+urllib3==2.5.0
+google-genai==1.68.0
+semantic-version==2.10.0
+docutils==0.21.2
+httpx==0.28.1
+cucim-cu12==26.2.0
+editdistance==0.8.1
+stanio==0.5.1
+nvidia-nvjitlink-cu12==12.8.93
+sklearn-compat==0.1.6
+grpc-google-iam-v1==0.14.4
+frozenlist==1.8.0
+tabulate==0.9.0
+cuvs-cu12==26.2.0
+shellingham==1.5.4
+nvidia-cuda-cccl-cu12==12.9.27
+joserfc==1.7.1
+antlr4-python3-runtime==4.9.3
+clarabel==0.11.1
+segregation==2.5.4
+scipy==1.16.3
+nvidia-nvtx-cu12==12.8.90
+weasel==1.0.0
+betterproto==2.0.0b6
+tomlkit==0.13.3
+tbb==2022.3.1
+librmm-cu12==26.2.0
+tokenizers==0.22.2
+argon2-cffi-bindings==25.1.0
+atpublic==5.1
+traitlets==5.7.1
+numba-cuda==0.22.2
+MarkupSafe==3.0.3
+gin-config==0.5.0
+multitasking==0.0.13
+bleach==6.4.0
+tenacity==9.1.4
+Pygments==2.20.0
+tensorflow==2.20.0
+holidays==0.98
+diffusers==0.38.0
+websockets==15.0.1
+prettytable==3.17.0
+Bottleneck==1.4.2
+pandocfilters==1.5.1
+h5py==3.16.0
+arrow==1.4.0
+kiwisolver==1.5.0
+zict==3.0.0
+jiter==0.15.0
+kagglesdk==0.1.23
+safetensors==0.8.0
+nltk==3.9.1
+google-auth-oauthlib==1.4.0
+fastlite==0.2.4
+ipython-genutils==0.2.0
+vega-datasets==0.9.0
+pyasn1==0.6.3
+openpyxl==3.1.5
+traittypes==0.2.3
+httpimport==1.4.1
+google-resumable-media==2.10.0
+chardet==5.2.0
+jsonpointer==3.1.1
+rmm-cu12==26.2.0
+osqp==1.1.2
+inflect==7.5.0
+nbclient==0.10.4
+parso==0.8.7
+logical-unification==0.4.7
+inequality==1.1.2
+PuLP==3.3.2
+google-cloud-dataplex==2.20.0
+aiosqlite==0.22.1
+rpy2==3.5.17
+six==1.17.0
+catalogue==2.0.10
+multipledispatch==1.0.0
+stringzilla==4.6.2
+distro==1.9.0
+keras-nlp==0.26.0
+rapids-dask-dependency==26.2.0
+pointpats==2.5.5
+progressbar2==4.5.0
+uvicorn==0.49.0
+nx-cugraph-cu12==26.2.0
+fsspec==2025.3.0
+PyGObject==3.48.2
+PyDrive2==1.21.1
+google-api-core==2.30.3
+ormsgpack==1.12.2
+nvidia-cusparselt-cu12==0.7.1
+cyipopt==1.5.0
+typeguard==4.5.2
+fastprogress==1.1.6
+highspy==1.14.0
+gitdb==4.0.12
+torchaudio==2.11.0+cu128
+anyio==4.13.0
+importlib_metadata==8.7.1
+graphviz==0.21
+typer==0.25.1
+rfc3987-syntax==1.1.0
+google-cloud-bigquery==3.41.0
+eerepr==0.1.2
+zstandard==0.25.0
+httpx-sse==0.4.3
+langchain==1.3.6
+param==2.4.1
+natsort==8.4.0
+jupyterlab_pygments==0.3.0
+jsonpickle==4.1.2
+google-cloud-bigquery-storage==2.39.0
+spacy-legacy==3.0.12
+ipyfilechooser==0.6.0
+fastai==2.8.7
+python-snappy==0.7.3
+hdbscan==0.8.44
+langsmith==0.8.12
+annotated-doc==0.0.4
+holoviews==1.22.1
+cuda-bindings==12.9.7
+xarray-einstats==0.10.0
+promise==2.3
+cramjam==2.11.0
+jsonschema-specifications==2025.9.1
+imageio-ffmpeg==0.6.0
+annotated-types==0.7.0
+tensorflow-probability==0.25.0
+uuid_utils==0.16.0
+imutils==0.5.4
+opencv-contrib-python==4.13.0.92
+Markdown==3.10.2
+nvidia-curand-cu12==10.3.9.90
+pandas-stubs==2.2.2.240909
+aiosignal==1.4.0
+widgetsnbextension==3.6.10
+opentelemetry-sdk==1.38.0
+rpds-py==2026.5.1
+filelock==3.29.2
+flax==0.11.2
+sqlalchemy-spanner==1.19.0
+pytensor==2.38.3
+treescope==0.1.10
+colorlover==0.3.0
+datasets==4.0.0
+nvidia-cufile-cu12==1.13.1.3
+jupyter_server==2.18.2
+treelite==4.7.0
+deprecation==2.1.0
+portpicker==1.5.2
+google-ai-generativelanguage==0.6.15
+psutil==5.9.5
+jupyter_server_terminals==0.5.4
+torchao==0.10.0
+google-cloud-dataproc==5.28.0
+nibabel==5.4.2
+tinycss2==1.5.1
+pylibcugraph-cu12==26.2.0
+grpcio-status==1.71.2
+tensorflow-metadata==1.21.0
+jupyter-events==0.12.1
+cons==0.4.7
+panel==1.9.3
+aiohappyeyeballs==2.6.2
+jaraco.context==6.1.2
+python-json-logger==4.1.0
+alembic==1.18.4
+cachetools==6.2.6
+curl_cffi==0.15.0
+tables==3.10.2
+toolz==0.12.1
+orbax-checkpoint==0.12.0
+zipp==4.1.0
+onemkl-license==2025.3.1
+sphinxcontrib-qthelp==2.0.0
+brotli==1.2.0
+tifffile==2026.4.11
+PyJWT==2.13.0
+cufflinks==0.17.3
+itsdangerous==2.2.0
+giddy==2.3.6
+gspread==6.2.1
+requests==2.32.4
+cycler==0.12.1
+bqplot==0.12.47
+gymnasium==1.3.0
+optree==0.19.1
+types-pytz==2026.2.0.20260518
+Authlib==1.7.2
+easydict==1.13
+sympy==1.14.0
+pickleshare==0.7.5
+nvidia-nvimgcodec-cu12==0.7.0.11
+pillow==11.3.0
+groovy==0.1.2
+albucore==0.0.24
+grpc-interceptor==0.15.4
+murmurhash==1.0.15
+python-louvain==0.16
+soundfile==0.14.0
+jieba==0.42.1
+cloudpathlib==0.24.0
+gradio==5.50.0
+termcolor==3.3.0
+accelerate==1.13.0
+rasterstats==0.21.0
+apsw==3.53.2.0
+pytest==8.4.2
+colorcet==3.2.1
+Send2Trash==2.1.0
+google-api-python-client==2.197.0
+flatbuffers==25.12.19
+tensorboard==2.20.0
+python-box==7.4.1
+jupyter_kernel_gateway==2.5.2
+simple-parsing==0.1.8
+watchfiles==1.2.0
+cuda-core==0.3.2
+jax-cuda12-pjrt==0.7.2
+pyspark==4.0.2
+regex==2025.11.3
+umap-learn==0.5.12
+pydantic_core==2.41.4
+jupyterlab_widgets==3.0.16
+geopandas==1.1.3
+propcache==0.5.2
+libucxx-cu12==0.48.0
+webcolors==25.10.0
+PyOpenGL==3.1.10
+access==1.1.10.post3
+charset-normalizer==3.4.7
+contourpy==1.3.3
+h11==0.16.0
+py4j==0.10.9.9
+google-cloud-language==2.20.0
+ImageIO==2.37.3
+networkx==3.6.1
+langgraph-checkpoint==4.1.1
+nvidia-cudnn-cu12==9.19.0.56
+prometheus_client==0.25.0
+cuml-cu12==26.2.0
+pycryptodomex==3.23.0
+nvidia-libnvcomp-cu12==5.1.0.21
+srsly==2.5.3
+scikit-learn==1.6.1
+immutabledict==4.3.1
+opt_einsum==3.4.0
+nvidia-cublas-cu12==12.8.4.1
+timm==1.0.27
+SecretStorage==3.5.0
+google-crc32c==1.8.0
+google-cloud-bigtable==2.38.0
+nh3==0.3.5
+python-utils==3.9.1
+pycparser==3.0
+jax-cuda12-plugin==0.7.2
+python-fasthtml==0.12.50
+platformdirs==4.10.0
+sphinxcontrib-serializinghtml==2.0.0
+requests-oauthlib==2.0.0
+click==8.4.1
+anywidget==0.9.21
+thinc==8.3.13
+mlxtend==0.23.4
+folium==0.20.0
+cupy-cuda12x==14.0.1
+psycopg2==2.9.12
+libucx-cu12==1.19.0
+mgwr==2.2.1
+sphinxcontrib-devhelp==2.0.0
+moviepy==1.0.3
+cmake==3.31.10
+nvidia-cuda-runtime-cu12==12.8.90
+rtree==1.4.1
+ipykernel==6.17.1
+ipywidgets==7.7.1
+music21==9.9.2
+mmh3==5.2.1
+gym==0.25.2
+safehttpx==0.1.7
+cvxopt==1.3.2
+xlrd==2.0.2
+libkvikio-cu12==26.2.0
+ffmpy==1.0.0
+msgpack==1.1.2
+astropy-iers-data==0.2026.6.8.17.49.5
+bigquery-magics==0.14.0
+shap==0.52.0
+imbalanced-learn==0.14.2
+langchain-core==1.4.3
+absl-py==1.4.0
+opentelemetry-resourcedetector-gcp==1.12.0a0
+stumpy==1.13.0
+websocket-client==1.9.0
+python-dotenv==1.2.2
+tcmlib==1.5.0
+pymc==5.28.5
+linkify-it-py==2.1.0
+matplotlib-venn==1.1.2
+polars==1.35.2
+opentelemetry-exporter-otlp-proto-common==1.38.0
+etils==1.14.0
+h2==4.3.0
+ipyparallel==8.8.0
+pyarrow==18.1.0
+lark==1.3.1
+decorator==4.4.2
+google-cloud-discoveryengine==0.13.12
+sphinxcontrib-jsmath==1.0.1
+google-cloud-core==2.6.0
+mistune==3.2.1
+jupyter-console==6.6.3
+narwhals==2.22.1
+nvidia-cuda-cupti-cu12==12.8.90
+nvidia-ml-py==13.610.43
+beartype==0.22.9
+ipyleaflet==0.20.0
+grain==0.2.17
+peewee==4.0.6
+ml_dtypes==0.5.4
+pysal==25.7
+numba==0.60.0
+tf-slim==1.1.0
+protobuf==5.29.6
+et_xmlfile==2.0.0
+dask==2026.1.1
+wandb==0.27.2
+jupyter_client==7.4.9
+jupyter-leaflet==0.20.0
+fastapi==0.136.3
+python-multipart==0.0.32
+proglog==0.1.12
+torchsummary==1.5.1
+sphinxcontrib-htmlhelp==2.1.0
+attrs==26.1.0
+ibis-framework==9.5.0
+Werkzeug==3.1.8
+tornado==6.5.7
+Sphinx==8.2.3
+opencv-python-headless==4.13.0.92
+threadpoolctl==3.6.0
+Jinja2==3.1.6
+cymem==2.0.13
+nvtx==0.2.15
+cuda-toolkit==12.8.1
+audioread==3.1.0
+wasabi==1.1.3
+pyzmq==26.2.1
+alabaster==1.0.0
+libcuvs-cu12==26.2.0
+pytz==2025.2
+ydf_tf==2.20.0
+spint==1.0.7
+geemap==0.38.0
+torchvision==0.26.0+cu128
+libcuml-cu12==26.2.0
+numpy==2.0.2
+rich==13.9.4
+yfinance==0.2.66
+pyOpenSSL==26.2.0
+toml==0.10.2
+arviz==0.22.0
+cligj==0.7.2
+Mako==1.3.12
+pandas==2.2.2
+raft-dask-cu12==26.2.0
+typing-inspection==0.4.2
+mdurl==0.1.2
+aiohttp==3.14.1
+google-auth==2.47.0
+distributed==2026.1.1
+kaggle==2.0.2
+httplib2==0.31.2
+simplejson==4.1.1
+apswutils==0.1.2
+opentelemetry-api==1.38.0
+dm-tree==0.1.10
+imagesize==2.0.0
+iniconfig==2.3.0
+jax==0.7.2
+xyzservices==2026.3.0
+libcugraph-cu12==26.2.0
+glob2==0.7
+array_record==0.8.3
+matplotlib-inline==0.2.2
+google-cloud-storage==3.11.0
+geocoder==1.38.1
+isoduration==20.11.0
+scooby==0.11.2
+python-slugify==8.0.4
+triton==3.6.0
+humanize==4.15.0
+pyperclip==1.11.0
+tensorflow-text==2.20.1
+cmdstanpy==1.3.0
+blinker==1.9.0
+SQLAlchemy==2.0.50
+PyYAML==6.0.3
+ruff==0.15.16
+google-cloud-iam==2.23.0
+Farama-Notifications==0.0.6
+librosa==0.11.0
+yarl==1.24.2
+duckdb==1.3.2
+hpack==4.1.0
+tsfresh==0.21.2
+pooch==1.9.0
+pydantic-settings==2.14.1
+jaraco.functools==4.5.0
+kagglehub==1.0.2
+jeepney==0.9.0
+google-cloud-pubsub==2.39.0
+nbclassic==1.3.3
+huggingface_hub==1.18.0
+hyperframe==6.1.0
+babel==2.18.0
+google-cloud-aiplatform==1.157.0
+libraft-cu12==26.2.0
+pydot==4.0.1
+webencodings==0.5.1
+pylibraft-cu12==26.2.0
+nvidia-nccl-cu12==2.28.9
+seaborn==0.13.2
+torchdata==0.11.0
+jsonschema==4.26.0
+PySocks==1.7.1
+sqlparse==0.5.5
+smart_open==7.6.1
+tobler==0.14.0
+hyperopt==0.2.7
+mcp==1.27.2
+dataproc-spark-connect==1.1.0
+pydantic==2.12.3
+pyroaring==1.1.0
+torch==2.11.0+cu128
+gym-notices==0.1.0
+sentence-transformers==5.5.1
+mdit-py-plugins==0.6.1
+splot==1.1.7
+httpcore==1.0.9
+wheel==0.47.0
+ipython-sql==0.5.0
+referencing==0.37.0
+peft==0.19.1
+google-adk==1.29.0
+fastcore==1.13.3
+earthengine-api==1.7.30
+xxhash==3.7.0
+astunparse==1.6.3
+entrypoints==0.4
+tweepy==4.16.0
+proto-plus==1.28.0
+google-cloud-secret-manager==2.29.0
+opentelemetry-exporter-gcp-logging==1.11.0a0
+gcsfs==2025.3.0
+ucxx-cu12==0.48.0
+intel-cmplr-lib-ur==2025.3.3
+ratelim==0.1.6
+rsa==4.9.1
+tiktoken==0.13.0
+prompt_toolkit==3.0.52
+openai==2.41.0
+tensorstore==0.1.84
+sphinxcontrib-applehelp==2.0.0
+rfc3986-validator==0.1.1
+beautifulsoup4==4.13.5
+uritemplate==4.2.0
+geopy==2.4.1
+spglm==1.1.0
+bigframes==2.42.0
+googleapis-common-protos==1.75.0
+keyring==25.7.0
+scs==3.2.11
+ipython==7.34.0
+uri-template==1.3.0
+esda==2.9.0
+Cython==3.0.12
+google-cloud-bigquery-connection==1.22.0
+tqdm==4.67.3
+panel-material-ui==0.12.0
+ptyprocess==0.7.0
+google-auth-httplib2==0.4.0
+spopt==0.7.0
+cvxpy==1.6.7
+fastdownload==0.0.7
+idna==3.18
+aiofiles==24.1.0
+langgraph-sdk==0.4.2
+nbconvert==7.17.1
+certifi==2026.5.20
+google-cloud-translate==3.26.0
+ale-py==0.12.0
+joblib==1.5.3
+lxml==6.1.1
+jsonpatch==1.33
+ndindex==1.10.1
+snowballstemmer==3.1.1
+shapely==2.1.2
+roman-numerals-py==4.1.0
+google-generativeai==0.8.6
+torchcodec==0.11.0+cu128
+pycairo==1.29.0
+autograd==1.8.0
+CacheControl==0.14.4
+langgraph==1.2.4
+pyogrio==0.12.1
+importlib_resources==7.1.0
+branca==0.8.2
+spanner-graph-notebook==1.1.10
+altair==5.5.0
+distributed-ucxx-cu12==0.48.0
+locket==1.0.0
+polars-runtime-32==1.35.2
+hf-xet==1.5.1
+pyproj==3.7.2
+google-cloud-functions==1.23.0
+mpmath==1.3.0
+etuples==0.3.10
+jupytext==1.19.3
+preshed==3.0.13
+opentelemetry-exporter-gcp-monitoring==1.12.0a0
+tblib==3.2.2
+slicer==0.0.8
+libpysal==4.14.1
+future==1.0.0
+google-cloud-resource-manager==1.17.0
+google-cloud-logging==3.16.0
+google==3.0.0
+langchain-protocol==0.0.16
+sniffio==1.3.1
+google-cloud-spanner==3.67.0
+ydf==0.15.0
+nest-asyncio==1.6.0
+confection==1.3.3
+cuda-python==12.9.7
+markdown-it-py==4.2.0
+py-cpuinfo==9.0.0
+python-dateutil==2.9.0.post0
+cloudpickle==3.1.2
+fqdn==1.5.1
+notebook_shim==0.2.4
+GDAL==3.8.4
+fonttools==4.63.0
+spacy-loggers==1.0.5
+libclang==18.1.1
+pydotplus==2.0.2
+GitPython==3.1.50
+momepy==0.11.0
+llvmlite==0.43.0
+pynndescent==0.6.0
+rapids-logger==0.2.3
+googledrivedownloader==1.1.0
+spaghetti==1.7.6
+cudf-polars-cu12==26.2.1
+google-cloud-appengine-logging==1.10.0
+pyasn1_modules==0.4.2
+pyiceberg==0.11.1
+cryptography==48.0.1
+pyerfa==2.0.1.5
+lazy-loader==0.5
+text-unidecode==1.3
+Flask==3.1.3
+argon2-cffi==25.1.0
+packaging==26.2
+opentelemetry-semantic-conventions==0.59b0
+wcwidth==0.8.1
+h5netcdf==1.8.1
+PyWavelets==1.9.0
+nvidia-cufft-cu12==11.3.3.83
+optax==0.2.8
+astropy==7.2.0
+numexpr==2.14.1
+tensorflow-hub==0.16.1
+pydata-google-auth==1.9.1
+yellowbrick==1.5
+nbformat==5.10.4
+simsimd==6.5.16
+plotly==5.24.1
+textblob==0.19.0
+blosc2==4.4.2
+jaxlib==0.7.2
+albumentations==2.0.8
+google-cloud-trace==1.19.0
+oauth2client==4.1.3
+missingno==0.5.2
+pandas-datareader==0.10.0
+google-cloud-speech==2.40.0
+bokeh==3.8.2
+tzlocal==5.3.1
+pluggy==1.6.0
+gdown==5.2.2
+namex==0.1.0
+cudf-cu12==26.2.1
+watchdog==6.0.0
+strictyaml==1.7.3
+terminado==0.18.1
+umf==1.0.3
+uc-micro-py==2.0.0
+mizani==0.13.5
+einops==0.8.2
+lightgbm==4.6.0
+html5lib==1.1
+plum-dispatch==2.9.0
+orjson==3.11.9
+blobfile==3.2.0
+google-cloud-audit-log==0.6.0
+sklearn-pandas==2.2.0
+ipyevents==2.0.4
+nvidia-cusolver-cu12==11.7.3.90
+dopamine_rl==4.1.2
+pygame==2.6.1
+frozendict==2.4.7
+quantecon==0.11.2
+roman-numerals==4.1.0
+gradio_client==1.14.0
+wrapt==2.2.1
+prophet==1.3.0
+psygnal==0.15.1
+google-cloud-monitoring==2.31.0
+tensorboard-data-server==0.7.2
+rfc3339-validator==0.1.4
+scikit-image==0.25.2
+pyparsing==3.3.2
+multidict==6.7.1
+typing_extensions==4.15.0
+grpclib==0.4.9
+sentencepiece==0.2.1
+cuda-pathfinder==1.5.5
+statsmodels==0.14.6
+jaraco.classes==3.4.0
+docstring_parser==0.18.0
+oauthlib==3.3.1
+partd==1.4.2
+keras==3.13.2
+uvloop==0.22.1
+firebase-admin==6.9.0
+multiprocess==0.70.16
+fastjsonschema==2.21.2
+soupsieve==2.8.4
+cffi==2.0.0
+sentry-sdk==2.62.0
+patsy==1.0.2
+httptools==0.8.0
+pexpect==4.9.0
+sortedcontainers==2.4.0
+pycocotools==2.0.11
+google-cloud-firestore==2.27.0
+spacy==3.8.14
+mapclassify==2.10.0
+tzdata==2026.2
+opentelemetry-proto==1.38.0
+pylibcudf-cu12==26.2.1
+pyomo==6.10.1
+spreg==1.9.0
+dill==0.3.8
+sqlglot==25.20.2
+mkl==2025.3.1
+fasttransform==0.0.2
+pyshp==3.0.12
+requests-toolbelt==1.0.0
+intel-openmp==2025.3.3
+pydub==0.25.1
+xarray==2025.12.0
+db-dtypes==1.7.0
+tensorflow-datasets==4.9.10
+gast==0.7.0
+dlib==19.24.6
+notebook==6.5.7
+torchtune==0.6.1
+jupyter_core==5.9.1
+geographiclib==2.1
+langgraph-prebuilt==1.1.0
+pandas-gbq==0.30.0
+blis==1.3.3
+omegaconf==2.3.0
+pyviz_comms==3.0.6
+soxr==1.1.0
+dask-cuda==26.2.0
+grpcio==1.81.0
+parsy==2.2
+debugpy==1.8.15
+sse-starlette==3.4.4
+community==1.0.0b1
+rasterio==1.5.0
+wordcloud==1.9.6
+gspread-dataframe==4.0.0
+affine==2.4.0
+keyrings.google-artifactregistry-auth==1.1.2
+starlette==0.52.1
+keras-hub==0.26.0
+xgboost==3.2.0
+pygit2==1.19.2
+smmap==5.0.3
+miniKanren==1.0.5
+transformers==5.10.2
+defusedxml==0.7.1
+backcall==0.2.0
+greenlet==3.5.1
+nvidia-cusparse-cu12==12.5.8.93
+dask-cudf-cu12==26.2.1
+opentelemetry-exporter-gcp-trace==1.12.0
+more-itertools==10.8.0
+nvidia-nvshmem-cu12==3.4.5
+nvidia-cuda-nvcc-cu12==12.8.93
+opencv-python==4.13.0.92
+libcudf-cu12==26.2.1
+nvidia-cuda-nvrtc-cu12==12.8.93
+matplotlib==3.10.0
+python-apt==0.0.0
+importlib-metadata==4.6.4
+launchpadlib==1.10.16
+lazr.restfulclient==0.14.4
+six==1.16.0
+wadllib==1.3.6
+python-apt==2.4.0+ubuntu4.1
+PyJWT==2.3.0
+keyring==23.5.0
+dbus-python==1.2.18
+httplib2==0.20.2
+PyGObject==3.42.1
+oauthlib==3.2.0
+more-itertools==8.10.0
+pyparsing==2.4.7
+distro==1.7.0
+cryptography==3.4.8
+lazr.uri==1.0.6
+jeepney==0.7.1
+SecretStorage==3.3.1
+blinker==1.4
+zipp==1.0.0
+MarkupSafe==2.0.1
+Markdown==3.3.6
+Mako==1.1.3

wandb/run-20260622_130442-dha4p9go/files/wandb-metadata.json

@@ -0,0 +1,40 @@
+{
+  "os": "Linux-6.6.122+-x86_64-with-glibc2.35",
+  "python": "CPython 3.12.13",
+  "startedAt": "2026-06-22T13:04:42.657339Z",
+  "program": "/content/GPT-2/train_model.py",
+  "codePath": "train_model.py",
+  "codePathLocal": "train_model.py",
+  "git": {
+    "remote": "https://github.com/Tydos/GPT-2",
+    "commit": "e46ee167dc2f1d60e959b25e0e67bab662677acf"
+  },
+  "email": "pjawale@wisc.edu",
+  "root": "/content/GPT-2",
+  "host": "18db444010a9",
+  "executable": "/usr/bin/python3",
+  "cpu_count": 6,
+  "cpu_count_logical": 12,
+  "gpu": "NVIDIA A100-SXM4-40GB",
+  "gpu_count": 1,
+  "disk": {
+    "/": {
+      "total": "253055008768",
+      "used": "51951943680"
+    }
+  },
+  "memory": {
+    "total": "89629196288"
+  },
+  "gpu_nvidia": [
+    {
+      "name": "NVIDIA A100-SXM4-40GB",
+      "memoryTotal": "42949672960",
+      "cudaCores": 6912,
+      "architecture": "Ampere",
+      "uuid": "GPU-314c604d-9d75-ef32-01fe-33fd37c595c5"
+    }
+  ],
+  "cudaVersion": "13.0",
+  "writerId": "zze5q4wfftrhphcr57ma7c3se33zut8w"
+}

wandb/run-20260622_130442-dha4p9go/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/perplexity":102.20170913152995,"train/batch_perplexity":87.24489118239137,"val/perplexity":99.90300438891872,"train/tok_s_epoch":41793.61607398984,"val/loss":4.6041997591654455,"train/loss":4.626948401030258,"train/batch_loss":4.468719005584717,"epoch":1,"_wandb":{"runtime":1359},"train/tok_s":42950.69505514834,"sample":"Gisburn had a evil smile, and was a \" good one \" . He was also a member of the Australian team , and was a","_runtime":1359.626624319,"_step":3458,"_timestamp":1.7821348431661158e+09}

wandb/run-20260622_130442-dha4p9go/logs/debug-core.log

@@ -0,0 +1,16 @@
+{"time":"2026-06-22T13:02:09.530814245Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpm5flexv5/port-621.txt","pid":621,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2026-06-22T13:02:09.532723183Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":621}
+{"time":"2026-06-22T13:02:09.532728443Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-621-946-2629321594/socket","Net":"unix"}}
+{"time":"2026-06-22T13:02:09.678653243Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2026-06-22T13:04:42.304710365Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"2(@)"}
+{"time":"2026-06-22T13:04:42.660605087Z","level":"INFO","msg":"handleInformInit: received","streamId":"dha4p9go","id":"2(@)"}
+{"time":"2026-06-22T13:04:42.986249683Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"dha4p9go","id":"2(@)"}
+{"time":"2026-06-22T13:04:49.058713829Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"kajiofpmic50"}
+{"time":"2026-06-22T13:27:23.168142083Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"kajiofpmic50"}
+{"time":"2026-06-22T13:27:26.158459198Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"kajiofpmic50"}
+{"time":"2026-06-22T13:27:26.160284757Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"dha4p9go","id":"2(@)"}
+{"time":"2026-06-22T13:27:26.163305749Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"dha4p9go","id":"2(@)"}
+{"time":"2026-06-22T13:27:30.364702099Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
+{"time":"2026-06-22T13:27:30.36469046Z","level":"INFO","msg":"connection: closing","id":"2(@)"}
+{"time":"2026-06-22T13:27:30.364783395Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
+{"time":"2026-06-22T13:27:30.364790478Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}

wandb/run-20260622_130442-dha4p9go/logs/debug-internal.log

@@ -0,0 +1,197 @@
+{"time":"2026-06-22T13:04:42.660730794Z","level":"INFO","msg":"wandb-core"}
+{"time":"2026-06-22T13:04:42.66127115Z","level":"INFO","msg":"stream: starting","core version":"0.27.2"}
+{"time":"2026-06-22T13:04:42.986008785Z","level":"INFO","msg":"stream: created new stream","id":"dha4p9go"}
+{"time":"2026-06-22T13:04:42.986071884Z","level":"INFO","msg":"handler: started"}
+{"time":"2026-06-22T13:04:42.986240005Z","level":"INFO","msg":"stream: started"}
+{"time":"2026-06-22T13:04:42.986272882Z","level":"INFO","msg":"writer: started","stream_id":"dha4p9go"}
+{"time":"2026-06-22T13:04:42.986292513Z","level":"INFO","msg":"sender: started"}
+{"time":"2026-06-22T13:04:44.06588626Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":2}
+{"time":"2026-06-22T13:04:44.370960804Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:04:59.066168693Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":2,"events_offset":0,"events_lines":2,"console_offset":2,"console_lines":3,"uploaded_len":2}
+{"time":"2026-06-22T13:04:59.414924178Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:05:14.066021294Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":4,"events_offset":2,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:05:14.349079599Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:05:29.066004741Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":6,"history_lines":4,"events_offset":4,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:05:29.376279603Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:05:44.066669927Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":10,"history_lines":3,"events_offset":6,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:05:44.431216173Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:05:59.066063064Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":13,"history_lines":4,"events_offset":8,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:05:59.38386744Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:06:14.065869131Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":17,"history_lines":4,"events_offset":10,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:06:14.373706429Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:06:29.066188147Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":21,"history_lines":4,"events_offset":12,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:06:29.410331688Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:06:44.066729941Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":25,"history_lines":4,"events_offset":14,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:06:44.35917359Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:06:59.065972138Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":29,"history_lines":4,"events_offset":16,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:06:59.51603569Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:07:14.066473598Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":33,"history_lines":3,"events_offset":18,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:07:14.436919783Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:07:29.066622963Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":36,"history_lines":4,"events_offset":20,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:07:29.720448036Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:07:44.066405507Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":40,"history_lines":4,"events_offset":22,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:07:44.372530748Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:07:59.066090139Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":44,"history_lines":4,"events_offset":24,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:07:59.423465657Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:08:14.066430779Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":48,"history_lines":4,"events_offset":26,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:08:14.40413525Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:08:29.066452342Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":52,"history_lines":4,"events_offset":28,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:08:29.433530978Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:08:44.066651476Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":56,"history_lines":3,"events_offset":30,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:08:44.374315892Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:08:59.066690415Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":59,"history_lines":4,"events_offset":32,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:08:59.558020456Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:09:14.066217579Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":63,"history_lines":4,"events_offset":34,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:09:14.538803988Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:09:29.066503326Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":67,"history_lines":4,"events_offset":36,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:09:29.677704844Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:09:44.066230925Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":71,"history_lines":4,"events_offset":38,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:09:45.010785128Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:09:59.066813063Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":75,"history_lines":4,"events_offset":40,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:09:59.35974622Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:10:14.066206432Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":79,"history_lines":3,"events_offset":42,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:10:14.365718891Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:10:29.066636693Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":82,"history_lines":4,"events_offset":44,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:10:30.051534367Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:10:44.066497981Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":86,"history_lines":4,"events_offset":46,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:10:44.374571807Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:10:59.066665341Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":90,"history_lines":4,"events_offset":48,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:10:59.416594153Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:11:14.066694827Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":94,"history_lines":4,"events_offset":50,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:11:14.383182275Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:11:29.066540345Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":98,"history_lines":4,"events_offset":52,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:11:29.403610089Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:11:44.066779446Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":102,"history_lines":3,"events_offset":54,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:11:44.44479461Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:11:59.066725681Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":105,"history_lines":4,"events_offset":56,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:11:59.378761821Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:12:14.066645205Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":109,"history_lines":4,"events_offset":58,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:12:14.342045401Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:12:29.066163754Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":113,"history_lines":4,"events_offset":60,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:12:29.38031115Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:12:44.066696431Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":117,"history_lines":4,"events_offset":62,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:12:44.323231638Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:12:59.066021219Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":121,"history_lines":4,"events_offset":64,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:12:59.494159006Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:13:14.066551059Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":125,"history_lines":3,"events_offset":66,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:13:14.363646369Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:13:29.066941827Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":128,"history_lines":4,"events_offset":68,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:13:29.352443517Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:13:44.066386745Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":132,"history_lines":4,"events_offset":70,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:13:44.363611571Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:13:59.066065064Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":136,"history_lines":4,"events_offset":72,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:13:59.36379284Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:14:14.065990016Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":140,"history_lines":4,"events_offset":74,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:14:14.329761208Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:14:29.06594223Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":144,"history_lines":3,"events_offset":76,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:14:29.328338369Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:14:44.066543388Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":147,"history_lines":4,"events_offset":78,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:14:44.509708496Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:14:59.066167852Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":151,"history_lines":4,"events_offset":80,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:14:59.490483182Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:15:14.065920483Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":155,"history_lines":4,"events_offset":82,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:15:14.671523075Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:15:29.066640749Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":159,"history_lines":4,"events_offset":84,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:15:29.50016493Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:15:44.066051946Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":163,"history_lines":4,"events_offset":86,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:15:44.362149815Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:15:59.065970304Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":167,"history_lines":3,"events_offset":88,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:15:59.357212283Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:16:14.066678028Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":170,"history_lines":4,"events_offset":90,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:16:14.416915065Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:16:29.066188961Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":174,"history_lines":4,"events_offset":92,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:16:29.349371947Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:16:44.066851069Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":178,"history_lines":4,"events_offset":94,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:16:44.432035722Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:16:59.066457421Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":182,"history_lines":4,"events_offset":96,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:16:59.358441192Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:17:14.066456205Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":186,"history_lines":4,"events_offset":98,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:17:14.360386855Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:17:29.06671787Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":190,"history_lines":3,"events_offset":100,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:17:29.412817251Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:17:44.066397617Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":193,"history_lines":4,"events_offset":102,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:17:44.395304947Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:17:59.066566068Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":197,"history_lines":4,"events_offset":104,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:17:59.357734362Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:18:14.066372292Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":201,"history_lines":4,"events_offset":106,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:18:14.410064678Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:18:29.06660889Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":205,"history_lines":4,"events_offset":108,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:18:29.434748551Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:18:44.066364689Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":209,"history_lines":4,"events_offset":110,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:18:44.381444935Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:18:59.06624177Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":213,"history_lines":3,"events_offset":112,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:18:59.360679465Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:19:14.06591638Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":216,"history_lines":4,"events_offset":114,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:19:14.331790272Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:19:29.066121323Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":220,"history_lines":4,"events_offset":116,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:19:29.329933056Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:19:44.066149215Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":224,"history_lines":4,"events_offset":118,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:19:44.393707681Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:19:59.066785837Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":228,"history_lines":4,"events_offset":120,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:19:59.389776853Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:20:14.0667644Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":232,"history_lines":4,"events_offset":122,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:20:14.370443666Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:20:29.066303036Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":236,"history_lines":3,"events_offset":124,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:20:29.417998571Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:20:44.066364364Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":239,"history_lines":4,"events_offset":126,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:20:44.363554403Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:20:59.066262984Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":243,"history_lines":4,"events_offset":128,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:20:59.388786528Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:21:14.065899293Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":247,"history_lines":4,"events_offset":130,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:21:14.456796539Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:21:29.066394994Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":251,"history_lines":4,"events_offset":132,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:21:29.421446747Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:21:44.066478602Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":255,"history_lines":3,"events_offset":134,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:21:44.481977933Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:21:59.06627728Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":258,"history_lines":4,"events_offset":136,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:21:59.375008336Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:22:14.066162169Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":262,"history_lines":4,"events_offset":138,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:22:14.400334142Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:22:29.065924263Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":266,"history_lines":4,"events_offset":140,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:22:29.394311577Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:22:44.065937158Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":270,"history_lines":4,"events_offset":142,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:22:44.363782085Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:22:59.066066545Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":274,"history_lines":4,"events_offset":144,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:22:59.433887386Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:23:14.066219514Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":278,"history_lines":4,"events_offset":146,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:23:14.346283951Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:23:29.065949464Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":282,"history_lines":3,"events_offset":148,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:23:29.375798806Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:23:44.066199628Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":285,"history_lines":4,"events_offset":150,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:23:44.417693746Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:23:59.066352646Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":289,"history_lines":4,"events_offset":152,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:23:59.390451335Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:24:14.066821679Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":293,"history_lines":4,"events_offset":154,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:24:14.392388863Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:24:29.066279855Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":297,"history_lines":4,"events_offset":156,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:24:29.493963667Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:24:44.066681845Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":301,"history_lines":3,"events_offset":158,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:24:44.354808849Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:24:59.065883568Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":304,"history_lines":4,"events_offset":160,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:24:59.417800621Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:25:14.066325408Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":308,"history_lines":4,"events_offset":162,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:25:14.669757211Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:25:29.066231116Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":312,"history_lines":4,"events_offset":164,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:25:29.483273888Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:25:44.066075196Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":316,"history_lines":4,"events_offset":166,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:25:44.519602158Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:25:59.066809238Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":320,"history_lines":4,"events_offset":168,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:25:59.519469663Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:26:14.066475239Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":324,"history_lines":4,"events_offset":170,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:26:14.458071548Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:26:29.066068585Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":328,"history_lines":3,"events_offset":172,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:26:29.447744844Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:26:44.0668045Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":331,"history_lines":4,"events_offset":174,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:26:44.739668572Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:26:59.066827175Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":335,"history_lines":4,"events_offset":176,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:26:59.654331022Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:27:14.066819023Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":339,"history_lines":4,"events_offset":178,"events_lines":2,"console_offset":4,"console_lines":1}
+{"time":"2026-06-22T13:27:14.727796148Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:27:25.265030197Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-06-22T13:27:25.265219608Z","level":"INFO","msg":"filestream: sending request","total_files":3,"history_offset":343,"history_lines":3,"console_offset":4,"console_lines":5,"uploaded_len":3,"complete":true,"exit_code":0}
+{"time":"2026-06-22T13:27:26.155160645Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-06-22T13:27:26.156721896Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2026-06-22T13:27:26.160304355Z","level":"INFO","msg":"stream: finishing up"}
+{"time":"2026-06-22T13:27:26.160325847Z","level":"INFO","msg":"handler: closed"}
+{"time":"2026-06-22T13:27:26.160381752Z","level":"INFO","msg":"sender: closed"}
+{"time":"2026-06-22T13:27:26.160388481Z","level":"INFO","msg":"stream: all finished"}

wandb/run-20260622_130442-dha4p9go/logs/debug.log

@@ -0,0 +1,25 @@
+2026-06-22 13:04:42,658 INFO    MainThread:1019 [wandb_setup.py:_flush():81] Current SDK version is 0.27.2
+2026-06-22 13:04:42,658 INFO    MainThread:1019 [wandb_setup.py:_flush():81] Configure stats pid to 1019
+2026-06-22 13:04:42,658 INFO    MainThread:1019 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-06-22 13:04:42,658 INFO    MainThread:1019 [wandb_init.py:setup_run_log_directory():723] Logging user logs to /content/GPT-2/wandb/run-20260622_130442-dha4p9go/logs/debug.log
+2026-06-22 13:04:42,659 INFO    MainThread:1019 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to /content/GPT-2/wandb/run-20260622_130442-dha4p9go/logs/debug-internal.log
+2026-06-22 13:04:42,659 INFO    MainThread:1019 [wandb_init.py:init():766] calling init triggers
+2026-06-22 13:04:42,659 INFO    MainThread:1019 [wandb_init.py:init():771] wandb.init called with sweep_config: {}
+config: {'vocab_size': 50257, 'context_window_size': 256, 'context_length': 1024, 'batch_size': 64, 'stride': 256, 'embed_dim': 768, 'head_dim': 64, 'num_heads': 12, 'drop_rate': 0.0, 'n_layer': 12, 'num_epochs': 1, 'num_workers': 4, 'lr': 0.0003, 'temperature': 1.0, '_wandb': {}}
+2026-06-22 13:04:42,659 INFO    MainThread:1019 [wandb_init.py:init():814] starting backend
+2026-06-22 13:04:42,659 INFO    MainThread:1019 [wandb_init.py:init():820] Connected to an existing wandb-core service via WANDB_SERVICE
+2026-06-22 13:04:42,659 INFO    MainThread:1019 [wandb_init.py:init():829] sending inform_init request
+2026-06-22 13:04:42,986 INFO    MainThread:1019 [wandb_init.py:init():834] backend started and connected
+2026-06-22 13:04:42,990 INFO    MainThread:1019 [wandb_init.py:init():904] updated telemetry
+2026-06-22 13:04:42,995 INFO    MainThread:1019 [wandb_init.py:init():927] communicating run to backend with 90.0 second timeout
+2026-06-22 13:04:43,541 INFO    MainThread:1019 [wandb_init.py:init():972] starting run threads in backend
+2026-06-22 13:04:44,056 INFO    MainThread:1019 [wandb_run.py:_console_start():2523] atexit reg
+2026-06-22 13:04:44,056 INFO    MainThread:1019 [wandb_run.py:_redirect():2373] redirect: wrap_raw
+2026-06-22 13:04:44,056 INFO    MainThread:1019 [wandb_run.py:_redirect():2442] Wrapping output streams.
+2026-06-22 13:04:44,056 INFO    MainThread:1019 [wandb_run.py:_redirect():2465] Redirects installed.
+2026-06-22 13:04:44,062 INFO    MainThread:1019 [wandb_init.py:init():1010] run started, returning control to user process
+2026-06-22 13:27:23,166 INFO    MainThread:1019 [wandb_run.py:_finish():2285] finishing run pjawale-student/gpt2-pytorch/dha4p9go
+2026-06-22 13:27:23,167 INFO    MainThread:1019 [wandb_run.py:_atexit_cleanup():2490] got exitcode: 0
+2026-06-22 13:27:23,167 INFO    MainThread:1019 [wandb_run.py:_restore():2472] restore
+2026-06-22 13:27:23,167 INFO    MainThread:1019 [wandb_run.py:_restore():2478] restore done
+2026-06-22 13:27:26,159 INFO    MainThread:1019 [wandb_run.py:_footer_sync_info():3891] logging synced files

wandb/run-20260622_130442-dha4p9go/run-dha4p9go.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1944698fd6a9f07c27e1227983718cc57dc07674d9c4d6eff356883ea92696
+size 775212