diff --git "a/leoprint/log.txt" "b/leoprint/log.txt"
new file mode 100644--- /dev/null
+++ "b/leoprint/log.txt"
@@ -0,0 +1,263 @@
+Running 1 job
+/usr/local/lib/python3.10/dist-packages/albumentations/__init__.py:13: UserWarning: A new version of Albumentations is available: 2.0.8 (you have 1.4.15). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1.
+  check_for_updates()
+/usr/local/lib/python3.10/dist-packages/albumentations/__init__.py:13: UserWarning: A new version of Albumentations is available: 2.0.8 (you have 1.4.15). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1.
+  check_for_updates()
+{
+    "type": "ui_trainer",
+    "training_folder": "/app/ai-toolkit/output",
+    "sqlite_db_path": "/app/ai-toolkit/aitk_db.db",
+    "device": "cuda",
+    "trigger_word": "$leoprint",
+    "performance_log_every": 10,
+    "network": {
+        "type": "lora",
+        "linear": 32,
+        "linear_alpha": 32,
+        "conv": 16,
+        "conv_alpha": 16,
+        "lokr_full_rank": true,
+        "lokr_factor": -1,
+        "network_kwargs": {
+            "ignore_if_contains": []
+        }
+    },
+    "save": {
+        "dtype": "bf16",
+        "save_every": 200,
+        "max_step_saves_to_keep": 12,
+        "save_format": "diffusers",
+        "push_to_hub": false
+    },
+    "datasets": [
+        {
+            "folder_path": "/app/ai-toolkit/datasets/leoprint",
+            "control_path": null,
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "$leoprint",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0.05,
+            "cache_latents_to_disk": false,
+            "is_reg": false,
+            "network_weight": 1,
+            "resolution": [
+                1024
+            ],
+            "controls": []
+        }
+    ],
+    "train": {
+        "batch_size": 2,
+        "bypass_guidance_embedding": false,
+        "steps": 2400,
+        "gradient_accumulation": 1,
+        "train_unet": true,
+        "train_text_encoder": false,
+        "gradient_checkpointing": true,
+        "noise_scheduler": "flowmatch",
+        "optimizer": "adamw8bit",
+        "timestep_type": "sigmoid",
+        "content_or_style": "balanced",
+        "optimizer_params": {
+            "weight_decay": 0.0001
+        },
+        "unload_text_encoder": false,
+        "lr": 5e-05,
+        "ema_config": {
+            "use_ema": false,
+            "ema_decay": 0.99
+        },
+        "dtype": "bf16",
+        "diff_output_preservation": false,
+        "diff_output_preservation_multiplier": 1,
+        "diff_output_preservation_class": "character"
+    },
+    "model": {
+        "name_or_path": "multimodalart/FLUX.1-dev2pro-full",
+        "quantize": true,
+        "quantize_te": true,
+        "arch": "flux",
+        "low_vram": false,
+        "model_kwargs": {}
+    },
+    "sample": {
+        "sampler": "flowmatch",
+        "sample_every": 200,
+        "width": 1024,
+        "height": 1024,
+        "prompts": [
+            "$leoprint sitting cross-legged on a floating iceberg, calm and thoughtful, the face facing left; vast frozen ocean and aurora borealis lighting the sky.",
+            "$leoprint painting a massive mural on a crumbling city wall, focused and intense, the face turned right; golden hour sunlight casting long shadows.",
+            "$leoprint surfing a towering wave during a storm, determined and fierce, the face facing forward; dark clouds and crashing water spray all around.",
+            "$leoprint curled up inside a cozy library nook, peaceful and content, the face turned down; warm candlelight flickering over stacks of ancient books.",
+            "$leoprint leaping between rooftops in a futuristic cityscape, alert and daring, the face angled slightly up; neon signs and rain slick streets glowing below."
+        ],
+        "neg": "",
+        "seed": 42,
+        "walk_seed": true,
+        "guidance_scale": 4,
+        "sample_steps": 25,
+        "num_frames": 1,
+        "fps": 1
+    }
+}
+Using EMA
+Using SQLite database at /app/ai-toolkit/aitk_db.db
+Job ID: "95bb0d57-008d-45ed-9819-94feed57880d"
+
+#############################################
+# Running job: leoprint
+#############################################
+
+
+Running  1 process
+Loading Flux model
+Loading transformer
+
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards: 100%|##########| 3/3 [00:00<00:00, 62.89it/s]
Loading checkpoint shards: 100%|##########| 3/3 [00:00<00:00, 62.89it/s]
+
+Quantizing transformer
+Loading VAE
+Loading T5
+You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
+You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
+
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 100%|##########| 2/2 [00:00<00:00, 100.20it/s]
Loading checkpoint shards: 100%|##########| 2/2 [00:00<00:00, 100.20it/s]
+
+Quantizing T5
+Loading CLIP
+Making pipe
+Preparing Model
+create LoRA network. base dim (rank): 32, alpha: 32
+neuron dropout: p=None, rank dropout: p=None, module dropout: p=None
+apply LoRA to Conv2d with kernel size (3,3). dim (rank): 16, alpha: 16
+create LoRA for Text Encoder: 0 modules.
+create LoRA for U-Net: 494 modules.
+enable LoRA for U-Net
+#### IMPORTANT RESUMING FROM /app/ai-toolkit/output/leoprint/leoprint.safetensors ####
+Loading from /app/ai-toolkit/output/leoprint/leoprint.safetensors
+Missing keys: []
+Found step 1000 in metadata, starting from there
+Loading optimizer state from /app/ai-toolkit/output/leoprint/optimizer.pt
+Updating optimizer LR from params
+Dataset: /app/ai-toolkit/datasets/leoprint
+  -  Preprocessing image dimensions
+
  0%|          | 0/22 [00:00<?, ?it/s]
  0%|          | 0/22 [00:00<?, ?it/s]
100%|##########| 22/22 [00:00<00:00, 49743.77it/s]
100%|##########| 22/22 [00:00<00:00, 49743.77it/s]
+
+  -  Found 22 images
+Bucket sizes for /app/ai-toolkit/datasets/leoprint:
+1216x832: 16 files
+1024x1024: 6 files
+2 buckets made
+
leoprint:  42%|####1     | 1000/2400 [00:00<?, ?it/s]
leoprint:  42%|####1     | 1000/2400 [00:00<?, ?it/s]
leoprint:  42%|####1     | 1000/2400 [00:03<?, ?it/s, lr: 5.0e-05 loss: 2.558e-01]
leoprint:  42%|####1     | 1000/2400 [00:03<?, ?it/s, lr: 5.0e-05 loss: 2.558e-01]
leoprint:  42%|####1     | 1000/2400 [00:03<?, ?it/s, lr: 5.0e-05 loss: 2.558e-01]
leoprint:  42%|####1     | 1000/2400 [00:03<?, ?it/s, lr: 5.0e-05 loss: 2.558e-01]
leoprint:  42%|####1     | 1000/2400 [00:07<?, ?it/s, lr: 5.0e-05 loss: 4.765e-01]
leoprint:  42%|####1     | 1000/2400 [00:07<?, ?it/s, lr: 5.0e-05 loss: 4.765e-01]
leoprint:  42%|####1     | 1001/2400 [00:07<1:17:41,  3.33s/it, lr: 5.0e-05 loss: 4.765e-01]
leoprint:  42%|####1     | 1001/2400 [00:07<1:17:41,  3.33s/it, lr: 5.0e-05 loss: 4.765e-01]
leoprint:  42%|####1     | 1001/2400 [00:10<1:17:41,  3.33s/it, lr: 5.0e-05 loss: 3.145e-01]
leoprint:  42%|####1     | 1001/2400 [00:10<1:17:41,  3.33s/it, lr: 5.0e-05 loss: 3.145e-01]
leoprint:  42%|####1     | 1002/2400 [00:10<1:19:06,  3.40s/it, lr: 5.0e-05 loss: 3.145e-01]
leoprint:  42%|####1     | 1002/2400 [00:10<1:19:06,  3.40s/it, lr: 5.0e-05 loss: 3.145e-01]
leoprint:  42%|####1     | 1002/2400 [00:13<1:19:06,  3.40s/it, lr: 5.0e-05 loss: 3.787e-01]
leoprint:  42%|####1     | 1002/2400 [00:13<1:19:06,  3.40s/it, lr: 5.0e-05 loss: 3.787e-01]
leoprint:  42%|####1     | 1003/2400 [00:13<1:18:22,  3.37s/it, lr: 5.0e-05 loss: 3.787e-01]
leoprint:  42%|####1     | 1003/2400 [00:13<1:18:22,  3.37s/it, lr: 5.0e-05 loss: 3.787e-01]
leoprint:  42%|####1     | 1003/2400 [00:17<1:18:22,  3.37s/it, lr: 5.0e-05 loss: 3.774e-01]
leoprint:  42%|####1     | 1003/2400 [00:17<1:18:22,  3.37s/it, lr: 5.0e-05 loss: 3.774e-01]
leoprint:  42%|####1     | 1004/2400 [00:17<1:18:09,  3.36s/it, lr: 5.0e-05 loss: 3.774e-01]
leoprint:  42%|####1     | 1004/2400 [00:17<1:18:09,  3.36s/it, lr: 5.0e-05 loss: 3.774e-01]
leoprint:  42%|####1     | 1004/2400 [00:20<1:18:09,  3.36s/it, lr: 5.0e-05 loss: 3.116e-01]
leoprint:  42%|####1     | 1004/2400 [00:20<1:18:09,  3.36s/it, lr: 5.0e-05 loss: 3.116e-01]
leoprint:  42%|####1     | 1005/2400 [00:20<1:18:02,  3.36s/it, lr: 5.0e-05 loss: 3.116e-01]
leoprint:  42%|####1     | 1005/2400 [00:20<1:18:02,  3.36s/it, lr: 5.0e-05 loss: 3.116e-01]
leoprint:  42%|####1     | 1005/2400 [00:24<1:18:02,  3.36s/it, lr: 5.0e-05 loss: 3.039e-01]
leoprint:  42%|####1     | 1005/2400 [00:24<1:18:02,  3.36s/it, lr: 5.0e-05 loss: 3.039e-01]
leoprint:  42%|####1     | 1006/2400 [00:24<1:18:35,  3.38s/it, lr: 5.0e-05 loss: 3.039e-01]
leoprint:  42%|####1     | 1006/2400 [00:24<1:18:35,  3.38s/it, lr: 5.0e-05 loss: 3.039e-01]
leoprint:  42%|####1     | 1006/2400 [00:27<1:18:35,  3.38s/it, lr: 5.0e-05 loss: 2.369e-01]
leoprint:  42%|####1     | 1006/2400 [00:27<1:18:35,  3.38s/it, lr: 5.0e-05 loss: 2.369e-01]
leoprint:  42%|####1     | 1007/2400 [00:27<1:18:26,  3.38s/it, lr: 5.0e-05 loss: 2.369e-01]
leoprint:  42%|####1     | 1007/2400 [00:27<1:18:26,  3.38s/it, lr: 5.0e-05 loss: 2.369e-01]
leoprint:  42%|####1     | 1007/2400 [00:30<1:18:26,  3.38s/it, lr: 5.0e-05 loss: 2.548e-01]
leoprint:  42%|####1     | 1007/2400 [00:30<1:18:26,  3.38s/it, lr: 5.0e-05 loss: 2.548e-01]
leoprint:  42%|####2     | 1008/2400 [00:30<1:19:04,  3.41s/it, lr: 5.0e-05 loss: 2.548e-01]
leoprint:  42%|####2     | 1008/2400 [00:30<1:19:04,  3.41s/it, lr: 5.0e-05 loss: 2.548e-01]
leoprint:  42%|####2     | 1008/2400 [00:34<1:19:04,  3.41s/it, lr: 5.0e-05 loss: 2.018e-01]
leoprint:  42%|####2     | 1008/2400 [00:34<1:19:04,  3.41s/it, lr: 5.0e-05 loss: 2.018e-01]
leoprint:  42%|####2     | 1009/2400 [00:34<1:19:34,  3.43s/it, lr: 5.0e-05 loss: 2.018e-01]
leoprint:  42%|####2     | 1009/2400 [00:34<1:19:34,  3.43s/it, lr: 5.0e-05 loss: 2.018e-01]
leoprint:  42%|####2     | 1009/2400 [00:37<1:19:34,  3.43s/it, lr: 5.0e-05 loss: 3.074e-01]
leoprint:  42%|####2     | 1009/2400 [00:37<1:19:34,  3.43s/it, lr: 5.0e-05 loss: 3.074e-01]
leoprint:  42%|####2     | 1010/2400 [00:41<1:19:30,  3.43s/it, lr: 5.0e-05 loss: 2.937e-01]
leoprint:  42%|####2     | 1010/2400 [00:41<1:19:30,  3.43s/it, lr: 5.0e-05 loss: 2.937e-01]
leoprint:  42%|####2     | 1011/2400 [00:41<1:00:28,  2.61s/it, lr: 5.0e-05 loss: 2.937e-01]
leoprint:  42%|####2     | 1011/2400 [00:41<1:00:28,  2.61s/it, lr: 5.0e-05 loss: 2.937e-01]
leoprint:  42%|####2     | 1011/2400 [00:44<1:00:28,  2.61s/it, lr: 5.0e-05 loss: 2.988e-01]
leoprint:  42%|####2     | 1011/2400 [00:44<1:00:28,  2.61s/it, lr: 5.0e-05 loss: 2.988e-01]
leoprint:  42%|####2     | 1012/2400 [00:44<1:06:59,  2.90s/it, lr: 5.0e-05 loss: 2.988e-01]
leoprint:  42%|####2     | 1012/2400 [00:44<1:06:59,  2.90s/it, lr: 5.0e-05 loss: 2.988e-01]
leoprint:  42%|####2     | 1012/2400 [00:48<1:06:59,  2.90s/it, lr: 5.0e-05 loss: 2.165e-01]
leoprint:  42%|####2     | 1012/2400 [00:48<1:06:59,  2.90s/it, lr: 5.0e-05 loss: 2.165e-01]
leoprint:  42%|####2     | 1013/2400 [00:48<1:10:02,  3.03s/it, lr: 5.0e-05 loss: 2.165e-01]
leoprint:  42%|####2     | 1013/2400 [00:48<1:10:02,  3.03s/it, lr: 5.0e-05 loss: 2.165e-01]
leoprint:  42%|####2     | 1013/2400 [00:51<1:10:02,  3.03s/it, lr: 5.0e-05 loss: 3.305e-01]
leoprint:  42%|####2     | 1013/2400 [00:51<1:10:02,  3.03s/it, lr: 5.0e-05 loss: 3.305e-01]
leoprint:  42%|####2     | 1014/2400 [00:51<1:12:21,  3.13s/it, lr: 5.0e-05 loss: 3.305e-01]
leoprint:  42%|####2     | 1014/2400 [00:51<1:12:21,  3.13s/it, lr: 5.0e-05 loss: 3.305e-01]
leoprint:  42%|####2     | 1014/2400 [00:55<1:12:21,  3.13s/it, lr: 5.0e-05 loss: 2.868e-01]
leoprint:  42%|####2     | 1014/2400 [00:55<1:12:21,  3.13s/it, lr: 5.0e-05 loss: 2.868e-01]
leoprint:  42%|####2     | 1015/2400 [00:55<1:14:06,  3.21s/it, lr: 5.0e-05 loss: 2.868e-01]
leoprint:  42%|####2     | 1015/2400 [00:55<1:14:06,  3.21s/it, lr: 5.0e-05 loss: 2.868e-01]
leoprint:  42%|####2     | 1015/2400 [00:58<1:14:06,  3.21s/it, lr: 5.0e-05 loss: 2.196e-01]
leoprint:  42%|####2     | 1015/2400 [00:58<1:14:06,  3.21s/it, lr: 5.0e-05 loss: 2.196e-01]
leoprint:  42%|####2     | 1016/2400 [00:58<1:16:16,  3.31s/it, lr: 5.0e-05 loss: 2.196e-01]
leoprint:  42%|####2     | 1016/2400 [00:58<1:16:16,  3.31s/it, lr: 5.0e-05 loss: 2.196e-01]
leoprint:  42%|####2     | 1016/2400 [01:02<1:16:16,  3.31s/it, lr: 5.0e-05 loss: 3.895e-01]
leoprint:  42%|####2     | 1016/2400 [01:02<1:16:16,  3.31s/it, lr: 5.0e-05 loss: 3.895e-01]
leoprint:  42%|####2     | 1017/2400 [01:02<1:18:04,  3.39s/it, lr: 5.0e-05 loss: 3.895e-01]
leoprint:  42%|####2     | 1017/2400 [01:02<1:18:04,  3.39s/it, lr: 5.0e-05 loss: 3.895e-01]
leoprint:  42%|####2     | 1017/2400 [01:05<1:18:04,  3.39s/it, lr: 5.0e-05 loss: 2.492e-01]
leoprint:  42%|####2     | 1017/2400 [01:05<1:18:04,  3.39s/it, lr: 5.0e-05 loss: 2.492e-01]
leoprint:  42%|####2     | 1018/2400 [01:05<1:19:02,  3.43s/it, lr: 5.0e-05 loss: 2.492e-01]
leoprint:  42%|####2     | 1018/2400 [01:05<1:19:02,  3.43s/it, lr: 5.0e-05 loss: 2.492e-01]
leoprint:  42%|####2     | 1018/2400 [01:09<1:19:02,  3.43s/it, lr: 5.0e-05 loss: 2.769e-01]
leoprint:  42%|####2     | 1018/2400 [01:09<1:19:02,  3.43s/it, lr: 5.0e-05 loss: 2.769e-01]
leoprint:  42%|####2     | 1019/2400 [01:09<1:19:00,  3.43s/it, lr: 5.0e-05 loss: 2.769e-01]
leoprint:  42%|####2     | 1019/2400 [01:09<1:19:00,  3.43s/it, lr: 5.0e-05 loss: 2.769e-01]
leoprint:  42%|####2     | 1019/2400 [01:12<1:19:00,  3.43s/it, lr: 5.0e-05 loss: 3.923e-01]
leoprint:  42%|####2     | 1019/2400 [01:12<1:19:00,  3.43s/it, lr: 5.0e-05 loss: 3.923e-01]
leoprint:  42%|####2     | 1020/2400 [01:16<1:18:56,  3.43s/it, lr: 5.0e-05 loss: 3.371e-01]
leoprint:  42%|####2     | 1020/2400 [01:16<1:18:56,  3.43s/it, lr: 5.0e-05 loss: 3.371e-01]
leoprint:  43%|####2     | 1021/2400 [01:16<1:00:52,  2.65s/it, lr: 5.0e-05 loss: 3.371e-01]
leoprint:  43%|####2     | 1021/2400 [01:16<1:00:52,  2.65s/it, lr: 5.0e-05 loss: 3.371e-01]
leoprint:  43%|####2     | 1021/2400 [01:19<1:00:52,  2.65s/it, lr: 5.0e-05 loss: 3.885e-01]
leoprint:  43%|####2     | 1021/2400 [01:19<1:00:52,  2.65s/it, lr: 5.0e-05 loss: 3.885e-01]
leoprint:  43%|####2     | 1022/2400 [01:19<1:05:21,  2.85s/it, lr: 5.0e-05 loss: 3.885e-01]
leoprint:  43%|####2     | 1022/2400 [01:19<1:05:21,  2.85s/it, lr: 5.0e-05 loss: 3.885e-01]
leoprint:  43%|####2     | 1022/2400 [01:23<1:05:21,  2.85s/it, lr: 5.0e-05 loss: 2.464e-01]
leoprint:  43%|####2     | 1022/2400 [01:23<1:05:21,  2.85s/it, lr: 5.0e-05 loss: 2.464e-01]
leoprint:  43%|####2     | 1023/2400 [01:23<1:10:21,  3.07s/it, lr: 5.0e-05 loss: 2.464e-01]
leoprint:  43%|####2     | 1023/2400 [01:23<1:10:21,  3.07s/it, lr: 5.0e-05 loss: 2.464e-01]
leoprint:  43%|####2     | 1023/2400 [01:26<1:10:21,  3.07s/it, lr: 5.0e-05 loss: 2.000e-01]
leoprint:  43%|####2     | 1023/2400 [01:26<1:10:21,  3.07s/it, lr: 5.0e-05 loss: 2.000e-01]
leoprint:  43%|####2     | 1024/2400 [01:26<1:13:28,  3.20s/it, lr: 5.0e-05 loss: 2.000e-01]
leoprint:  43%|####2     | 1024/2400 [01:26<1:13:28,  3.20s/it, lr: 5.0e-05 loss: 2.000e-01]
leoprint:  43%|####2     | 1024/2400 [01:30<1:13:28,  3.20s/it, lr: 5.0e-05 loss: 3.467e-01]
leoprint:  43%|####2     | 1024/2400 [01:30<1:13:28,  3.20s/it, lr: 5.0e-05 loss: 3.467e-01]
leoprint:  43%|####2     | 1025/2400 [01:30<1:15:08,  3.28s/it, lr: 5.0e-05 loss: 3.467e-01]
leoprint:  43%|####2     | 1025/2400 [01:30<1:15:08,  3.28s/it, lr: 5.0e-05 loss: 3.467e-01]
leoprint:  43%|####2     | 1025/2400 [01:33<1:15:08,  3.28s/it, lr: 5.0e-05 loss: 2.483e-01]
leoprint:  43%|####2     | 1025/2400 [01:33<1:15:08,  3.28s/it, lr: 5.0e-05 loss: 2.483e-01]
leoprint:  43%|####2     | 1026/2400 [01:33<1:16:23,  3.34s/it, lr: 5.0e-05 loss: 2.483e-01]
leoprint:  43%|####2     | 1026/2400 [01:33<1:16:23,  3.34s/it, lr: 5.0e-05 loss: 2.483e-01]
leoprint:  43%|####2     | 1026/2400 [01:37<1:16:23,  3.34s/it, lr: 5.0e-05 loss: 2.981e-01]
leoprint:  43%|####2     | 1026/2400 [01:37<1:16:23,  3.34s/it, lr: 5.0e-05 loss: 2.981e-01]
leoprint:  43%|####2     | 1027/2400 [01:37<1:17:18,  3.38s/it, lr: 5.0e-05 loss: 2.981e-01]
leoprint:  43%|####2     | 1027/2400 [01:37<1:17:18,  3.38s/it, lr: 5.0e-05 loss: 2.981e-01]
leoprint:  43%|####2     | 1027/2400 [01:40<1:17:18,  3.38s/it, lr: 5.0e-05 loss: 3.397e-01]
leoprint:  43%|####2     | 1027/2400 [01:40<1:17:18,  3.38s/it, lr: 5.0e-05 loss: 3.397e-01]
leoprint:  43%|####2     | 1028/2400 [01:40<1:18:37,  3.44s/it, lr: 5.0e-05 loss: 3.397e-01]
leoprint:  43%|####2     | 1028/2400 [01:40<1:18:37,  3.44s/it, lr: 5.0e-05 loss: 3.397e-01]
leoprint:  43%|####2     | 1028/2400 [01:44<1:18:37,  3.44s/it, lr: 5.0e-05 loss: 1.851e-01]
leoprint:  43%|####2     | 1028/2400 [01:44<1:18:37,  3.44s/it, lr: 5.0e-05 loss: 1.851e-01]
leoprint:  43%|####2     | 1029/2400 [01:44<1:19:40,  3.49s/it, lr: 5.0e-05 loss: 1.851e-01]
leoprint:  43%|####2     | 1029/2400 [01:44<1:19:40,  3.49s/it, lr: 5.0e-05 loss: 1.851e-01]
leoprint:  43%|####2     | 1029/2400 [01:48<1:19:40,  3.49s/it, lr: 5.0e-05 loss: 3.441e-01]
leoprint:  43%|####2     | 1029/2400 [01:48<1:19:40,  3.49s/it, lr: 5.0e-05 loss: 3.441e-01]
leoprint:  43%|####2     | 1030/2400 [01:51<1:19:37,  3.49s/it, lr: 5.0e-05 loss: 2.432e-01]
leoprint:  43%|####2     | 1030/2400 [01:51<1:19:37,  3.49s/it, lr: 5.0e-05 loss: 2.432e-01]
leoprint:  43%|####2     | 1031/2400 [01:51<1:01:20,  2.69s/it, lr: 5.0e-05 loss: 2.432e-01]
leoprint:  43%|####2     | 1031/2400 [01:51<1:01:20,  2.69s/it, lr: 5.0e-05 loss: 2.432e-01]
leoprint:  43%|####2     | 1031/2400 [01:55<1:01:20,  2.69s/it, lr: 5.0e-05 loss: 2.418e-01]
leoprint:  43%|####2     | 1031/2400 [01:55<1:01:20,  2.69s/it, lr: 5.0e-05 loss: 2.418e-01]
leoprint:  43%|####3     | 1032/2400 [01:55<1:06:25,  2.91s/it, lr: 5.0e-05 loss: 2.418e-01]
leoprint:  43%|####3     | 1032/2400 [01:55<1:06:25,  2.91s/it, lr: 5.0e-05 loss: 2.418e-01]
leoprint:  43%|####3     | 1032/2400 [01:58<1:06:25,  2.91s/it, lr: 5.0e-05 loss: 3.014e-01]
leoprint:  43%|####3     | 1032/2400 [01:58<1:06:25,  2.91s/it, lr: 5.0e-05 loss: 3.014e-01]
leoprint:  43%|####3     | 1033/2400 [01:58<1:09:48,  3.06s/it, lr: 5.0e-05 loss: 3.014e-01]
leoprint:  43%|####3     | 1033/2400 [01:58<1:09:48,  3.06s/it, lr: 5.0e-05 loss: 3.014e-01]
leoprint:  43%|####3     | 1033/2400 [02:02<1:09:48,  3.06s/it, lr: 5.0e-05 loss: 2.563e-01]
leoprint:  43%|####3     | 1033/2400 [02:02<1:09:48,  3.06s/it, lr: 5.0e-05 loss: 2.563e-01]
leoprint:  43%|####3     | 1034/2400 [02:02<1:14:06,  3.26s/it, lr: 5.0e-05 loss: 2.563e-01]
leoprint:  43%|####3     | 1034/2400 [02:02<1:14:06,  3.26s/it, lr: 5.0e-05 loss: 2.563e-01]
leoprint:  43%|####3     | 1034/2400 [02:06<1:14:06,  3.26s/it, lr: 5.0e-05 loss: 2.863e-01]
leoprint:  43%|####3     | 1034/2400 [02:06<1:14:06,  3.26s/it, lr: 5.0e-05 loss: 2.863e-01]
leoprint:  43%|####3     | 1035/2400 [02:06<1:16:16,  3.35s/it, lr: 5.0e-05 loss: 2.863e-01]
leoprint:  43%|####3     | 1035/2400 [02:06<1:16:16,  3.35s/it, lr: 5.0e-05 loss: 2.863e-01]
leoprint:  43%|####3     | 1035/2400 [02:09<1:16:16,  3.35s/it, lr: 5.0e-05 loss: 2.852e-01]
leoprint:  43%|####3     | 1035/2400 [02:09<1:16:16,  3.35s/it, lr: 5.0e-05 loss: 2.852e-01]
leoprint:  43%|####3     | 1036/2400 [02:09<1:17:06,  3.39s/it, lr: 5.0e-05 loss: 2.852e-01]
leoprint:  43%|####3     | 1036/2400 [02:09<1:17:06,  3.39s/it, lr: 5.0e-05 loss: 2.852e-01]
leoprint:  43%|####3     | 1036/2400 [02:13<1:17:06,  3.39s/it, lr: 5.0e-05 loss: 2.991e-01]
leoprint:  43%|####3     | 1036/2400 [02:13<1:17:06,  3.39s/it, lr: 5.0e-05 loss: 2.991e-01]
leoprint:  43%|####3     | 1037/2400 [02:13<1:17:41,  3.42s/it, lr: 5.0e-05 loss: 2.991e-01]
leoprint:  43%|####3     | 1037/2400 [02:13<1:17:41,  3.42s/it, lr: 5.0e-05 loss: 2.991e-01]
leoprint:  43%|####3     | 1037/2400 [02:16<1:17:41,  3.42s/it, lr: 5.0e-05 loss: 3.473e-01]
leoprint:  43%|####3     | 1037/2400 [02:16<1:17:41,  3.42s/it, lr: 5.0e-05 loss: 3.473e-01]
leoprint:  43%|####3     | 1038/2400 [02:16<1:18:07,  3.44s/it, lr: 5.0e-05 loss: 3.473e-01]
leoprint:  43%|####3     | 1038/2400 [02:16<1:18:07,  3.44s/it, lr: 5.0e-05 loss: 3.473e-01]
leoprint:  43%|####3     | 1038/2400 [02:20<1:18:07,  3.44s/it, lr: 5.0e-05 loss: 3.745e-01]
leoprint:  43%|####3     | 1038/2400 [02:20<1:18:07,  3.44s/it, lr: 5.0e-05 loss: 3.745e-01]
leoprint:  43%|####3     | 1039/2400 [02:20<1:18:23,  3.46s/it, lr: 5.0e-05 loss: 3.745e-01]
leoprint:  43%|####3     | 1039/2400 [02:20<1:18:23,  3.46s/it, lr: 5.0e-05 loss: 3.745e-01]
leoprint:  43%|####3     | 1039/2400 [02:23<1:18:23,  3.46s/it, lr: 5.0e-05 loss: 2.777e-01]
leoprint:  43%|####3     | 1039/2400 [02:23<1:18:23,  3.46s/it, lr: 5.0e-05 loss: 2.777e-01]
leoprint:  43%|####3     | 1040/2400 [02:27<1:18:19,  3.46s/it, lr: 5.0e-05 loss: 3.510e-01]
leoprint:  43%|####3     | 1040/2400 [02:27<1:18:19,  3.46s/it, lr: 5.0e-05 loss: 3.510e-01]
leoprint:  43%|####3     | 1041/2400 [02:27<1:00:35,  2.67s/it, lr: 5.0e-05 loss: 3.510e-01]
leoprint:  43%|####3     | 1041/2400 [02:27<1:00:35,  2.67s/it, lr: 5.0e-05 loss: 3.510e-01]
leoprint:  43%|####3     | 1041/2400 [02:30<1:00:35,  2.67s/it, lr: 5.0e-05 loss: 1.991e-01]
leoprint:  43%|####3     | 1041/2400 [02:30<1:00:35,  2.67s/it, lr: 5.0e-05 loss: 1.991e-01]
leoprint:  43%|####3     | 1042/2400 [02:30<1:05:42,  2.90s/it, lr: 5.0e-05 loss: 1.991e-01]
leoprint:  43%|####3     | 1042/2400 [02:30<1:05:42,  2.90s/it, lr: 5.0e-05 loss: 1.991e-01]
leoprint:  43%|####3     | 1042/2400 [02:34<1:05:42,  2.90s/it, lr: 5.0e-05 loss: 2.594e-01]
leoprint:  43%|####3     | 1042/2400 [02:34<1:05:42,  2.90s/it, lr: 5.0e-05 loss: 2.594e-01]
leoprint:  43%|####3     | 1043/2400 [02:34<1:09:08,  3.06s/it, lr: 5.0e-05 loss: 2.594e-01]
leoprint:  43%|####3     | 1043/2400 [02:34<1:09:08,  3.06s/it, lr: 5.0e-05 loss: 2.594e-01]
leoprint:  43%|####3     | 1043/2400 [02:37<1:09:08,  3.06s/it, lr: 5.0e-05 loss: 2.687e-01]
leoprint:  43%|####3     | 1043/2400 [02:37<1:09:08,  3.06s/it, lr: 5.0e-05 loss: 2.687e-01]
leoprint:  44%|####3     | 1044/2400 [02:37<1:11:48,  3.18s/it, lr: 5.0e-05 loss: 2.687e-01]
leoprint:  44%|####3     | 1044/2400 [02:37<1:11:48,  3.18s/it, lr: 5.0e-05 loss: 2.687e-01]
leoprint:  44%|####3     | 1044/2400 [02:41<1:11:48,  3.18s/it, lr: 5.0e-05 loss: 2.340e-01]
leoprint:  44%|####3     | 1044/2400 [02:41<1:11:48,  3.18s/it, lr: 5.0e-05 loss: 2.340e-01]
leoprint:  44%|####3     | 1045/2400 [02:41<1:13:46,  3.27s/it, lr: 5.0e-05 loss: 2.340e-01]
leoprint:  44%|####3     | 1045/2400 [02:41<1:13:46,  3.27s/it, lr: 5.0e-05 loss: 2.340e-01]
leoprint:  44%|####3     | 1045/2400 [02:44<1:13:46,  3.27s/it, lr: 5.0e-05 loss: 3.241e-01]
leoprint:  44%|####3     | 1045/2400 [02:44<1:13:46,  3.27s/it, lr: 5.0e-05 loss: 3.241e-01]
leoprint:  44%|####3     | 1046/2400 [02:44<1:16:40,  3.40s/it, lr: 5.0e-05 loss: 3.241e-01]
leoprint:  44%|####3     | 1046/2400 [02:44<1:16:40,  3.40s/it, lr: 5.0e-05 loss: 3.241e-01]
leoprint:  44%|####3     | 1046/2400 [02:48<1:16:40,  3.40s/it, lr: 5.0e-05 loss: 2.604e-01]
leoprint:  44%|####3     | 1046/2400 [02:48<1:16:40,  3.40s/it, lr: 5.0e-05 loss: 2.604e-01]
leoprint:  44%|####3     | 1047/2400 [02:48<1:18:01,  3.46s/it, lr: 5.0e-05 loss: 2.604e-01]
leoprint:  44%|####3     | 1047/2400 [02:48<1:18:01,  3.46s/it, lr: 5.0e-05 loss: 2.604e-01]
leoprint:  44%|####3     | 1047/2400 [02:52<1:18:01,  3.46s/it, lr: 5.0e-05 loss: 3.558e-01]
leoprint:  44%|####3     | 1047/2400 [02:52<1:18:01,  3.46s/it, lr: 5.0e-05 loss: 3.558e-01]
leoprint:  44%|####3     | 1048/2400 [02:52<1:18:14,  3.47s/it, lr: 5.0e-05 loss: 3.558e-01]
leoprint:  44%|####3     | 1048/2400 [02:52<1:18:14,  3.47s/it, lr: 5.0e-05 loss: 3.558e-01]
leoprint:  44%|####3     | 1048/2400 [02:55<1:18:14,  3.47s/it, lr: 5.0e-05 loss: 2.874e-01]
leoprint:  44%|####3     | 1048/2400 [02:55<1:18:14,  3.47s/it, lr: 5.0e-05 loss: 2.874e-01]
leoprint:  44%|####3     | 1049/2400 [02:55<1:18:22,  3.48s/it, lr: 5.0e-05 loss: 2.874e-01]
leoprint:  44%|####3     | 1049/2400 [02:55<1:18:22,  3.48s/it, lr: 5.0e-05 loss: 2.874e-01]
leoprint:  44%|####3     | 1049/2400 [02:59<1:18:22,  3.48s/it, lr: 5.0e-05 loss: 2.632e-01]
leoprint:  44%|####3     | 1049/2400 [02:59<1:18:22,  3.48s/it, lr: 5.0e-05 loss: 2.632e-01]
leoprint:  44%|####3     | 1050/2400 [03:02<1:18:18,  3.48s/it, lr: 5.0e-05 loss: 2.608e-01]
leoprint:  44%|####3     | 1050/2400 [03:02<1:18:18,  3.48s/it, lr: 5.0e-05 loss: 2.608e-01]
leoprint:  44%|####3     | 1051/2400 [03:02<1:01:25,  2.73s/it, lr: 5.0e-05 loss: 2.608e-01]
leoprint:  44%|####3     | 1051/2400 [03:02<1:01:25,  2.73s/it, lr: 5.0e-05 loss: 2.608e-01]
leoprint:  44%|####3     | 1051/2400 [03:06<1:01:25,  2.73s/it, lr: 5.0e-05 loss: 3.683e-01]
leoprint:  44%|####3     | 1051/2400 [03:06<1:01:25,  2.73s/it, lr: 5.0e-05 loss: 3.683e-01]
leoprint:  44%|####3     | 1052/2400 [03:06<1:05:37,  2.92s/it, lr: 5.0e-05 loss: 3.683e-01]
leoprint:  44%|####3     | 1052/2400 [03:06<1:05:37,  2.92s/it, lr: 5.0e-05 loss: 3.683e-01]
leoprint:  44%|####3     | 1052/2400 [03:09<1:05:37,  2.92s/it, lr: 5.0e-05 loss: 2.741e-01]
leoprint:  44%|####3     | 1052/2400 [03:09<1:05:37,  2.92s/it, lr: 5.0e-05 loss: 2.741e-01]
leoprint:  44%|####3     | 1053/2400 [03:09<1:09:37,  3.10s/it, lr: 5.0e-05 loss: 2.741e-01]
leoprint:  44%|####3     | 1053/2400 [03:09<1:09:37,  3.10s/it, lr: 5.0e-05 loss: 2.741e-01]
leoprint:  44%|####3     | 1053/2400 [03:13<1:09:37,  3.10s/it, lr: 5.0e-05 loss: 3.372e-01]
leoprint:  44%|####3     | 1053/2400 [03:13<1:09:37,  3.10s/it, lr: 5.0e-05 loss: 3.372e-01]
leoprint:  44%|####3     | 1054/2400 [03:13<1:12:01,  3.21s/it, lr: 5.0e-05 loss: 3.372e-01]
leoprint:  44%|####3     | 1054/2400 [03:13<1:12:01,  3.21s/it, lr: 5.0e-05 loss: 3.372e-01]
leoprint:  44%|####3     | 1054/2400 [03:16<1:12:01,  3.21s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  44%|####3     | 1054/2400 [03:16<1:12:01,  3.21s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  44%|####3     | 1055/2400 [03:16<1:13:46,  3.29s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  44%|####3     | 1055/2400 [03:16<1:13:46,  3.29s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  44%|####3     | 1055/2400 [03:20<1:13:46,  3.29s/it, lr: 5.0e-05 loss: 3.221e-01]
leoprint:  44%|####3     | 1055/2400 [03:20<1:13:46,  3.29s/it, lr: 5.0e-05 loss: 3.221e-01]
leoprint:  44%|####4     | 1056/2400 [03:20<1:15:05,  3.35s/it, lr: 5.0e-05 loss: 3.221e-01]
leoprint:  44%|####4     | 1056/2400 [03:20<1:15:05,  3.35s/it, lr: 5.0e-05 loss: 3.221e-01]
leoprint:  44%|####4     | 1056/2400 [03:24<1:15:05,  3.35s/it, lr: 5.0e-05 loss: 3.237e-01]
leoprint:  44%|####4     | 1056/2400 [03:24<1:15:05,  3.35s/it, lr: 5.0e-05 loss: 3.237e-01]
leoprint:  44%|####4     | 1057/2400 [03:24<1:17:29,  3.46s/it, lr: 5.0e-05 loss: 3.237e-01]
leoprint:  44%|####4     | 1057/2400 [03:24<1:17:29,  3.46s/it, lr: 5.0e-05 loss: 3.237e-01]
leoprint:  44%|####4     | 1057/2400 [03:27<1:17:29,  3.46s/it, lr: 5.0e-05 loss: 3.054e-01]
leoprint:  44%|####4     | 1057/2400 [03:27<1:17:29,  3.46s/it, lr: 5.0e-05 loss: 3.054e-01]
leoprint:  44%|####4     | 1058/2400 [03:27<1:17:44,  3.48s/it, lr: 5.0e-05 loss: 3.054e-01]
leoprint:  44%|####4     | 1058/2400 [03:27<1:17:44,  3.48s/it, lr: 5.0e-05 loss: 3.054e-01]
leoprint:  44%|####4     | 1058/2400 [03:31<1:17:44,  3.48s/it, lr: 5.0e-05 loss: 2.122e-01]
leoprint:  44%|####4     | 1058/2400 [03:31<1:17:44,  3.48s/it, lr: 5.0e-05 loss: 2.122e-01]
leoprint:  44%|####4     | 1059/2400 [03:31<1:18:36,  3.52s/it, lr: 5.0e-05 loss: 2.122e-01]
leoprint:  44%|####4     | 1059/2400 [03:31<1:18:36,  3.52s/it, lr: 5.0e-05 loss: 2.122e-01]
leoprint:  44%|####4     | 1059/2400 [03:34<1:18:36,  3.52s/it, lr: 5.0e-05 loss: 3.448e-01]
leoprint:  44%|####4     | 1059/2400 [03:34<1:18:36,  3.52s/it, lr: 5.0e-05 loss: 3.448e-01]
leoprint:  44%|####4     | 1060/2400 [03:38<1:18:33,  3.52s/it, lr: 5.0e-05 loss: 2.762e-01]
leoprint:  44%|####4     | 1060/2400 [03:38<1:18:33,  3.52s/it, lr: 5.0e-05 loss: 2.762e-01]
leoprint:  44%|####4     | 1061/2400 [03:38<1:01:01,  2.73s/it, lr: 5.0e-05 loss: 2.762e-01]
leoprint:  44%|####4     | 1061/2400 [03:38<1:01:01,  2.73s/it, lr: 5.0e-05 loss: 2.762e-01]
leoprint:  44%|####4     | 1061/2400 [03:42<1:01:01,  2.73s/it, lr: 5.0e-05 loss: 2.559e-01]
leoprint:  44%|####4     | 1061/2400 [03:42<1:01:01,  2.73s/it, lr: 5.0e-05 loss: 2.559e-01]
leoprint:  44%|####4     | 1062/2400 [03:42<1:06:10,  2.97s/it, lr: 5.0e-05 loss: 2.559e-01]
leoprint:  44%|####4     | 1062/2400 [03:42<1:06:10,  2.97s/it, lr: 5.0e-05 loss: 2.559e-01]
leoprint:  44%|####4     | 1062/2400 [03:45<1:06:10,  2.97s/it, lr: 5.0e-05 loss: 2.976e-01]
leoprint:  44%|####4     | 1062/2400 [03:45<1:06:10,  2.97s/it, lr: 5.0e-05 loss: 2.976e-01]
leoprint:  44%|####4     | 1063/2400 [03:45<1:09:11,  3.11s/it, lr: 5.0e-05 loss: 2.976e-01]
leoprint:  44%|####4     | 1063/2400 [03:45<1:09:11,  3.11s/it, lr: 5.0e-05 loss: 2.976e-01]
leoprint:  44%|####4     | 1063/2400 [03:49<1:09:11,  3.11s/it, lr: 5.0e-05 loss: 2.346e-01]
leoprint:  44%|####4     | 1063/2400 [03:49<1:09:11,  3.11s/it, lr: 5.0e-05 loss: 2.346e-01]
leoprint:  44%|####4     | 1064/2400 [03:49<1:11:29,  3.21s/it, lr: 5.0e-05 loss: 2.346e-01]
leoprint:  44%|####4     | 1064/2400 [03:49<1:11:29,  3.21s/it, lr: 5.0e-05 loss: 2.346e-01]
leoprint:  44%|####4     | 1064/2400 [03:52<1:11:29,  3.21s/it, lr: 5.0e-05 loss: 4.100e-01]
leoprint:  44%|####4     | 1064/2400 [03:52<1:11:29,  3.21s/it, lr: 5.0e-05 loss: 4.100e-01]
leoprint:  44%|####4     | 1065/2400 [03:52<1:13:14,  3.29s/it, lr: 5.0e-05 loss: 4.100e-01]
leoprint:  44%|####4     | 1065/2400 [03:52<1:13:14,  3.29s/it, lr: 5.0e-05 loss: 4.100e-01]
leoprint:  44%|####4     | 1065/2400 [03:56<1:13:14,  3.29s/it, lr: 5.0e-05 loss: 2.178e-01]
leoprint:  44%|####4     | 1065/2400 [03:56<1:13:14,  3.29s/it, lr: 5.0e-05 loss: 2.178e-01]
leoprint:  44%|####4     | 1066/2400 [03:56<1:14:26,  3.35s/it, lr: 5.0e-05 loss: 2.178e-01]
leoprint:  44%|####4     | 1066/2400 [03:56<1:14:26,  3.35s/it, lr: 5.0e-05 loss: 2.178e-01]
leoprint:  44%|####4     | 1066/2400 [03:59<1:14:26,  3.35s/it, lr: 5.0e-05 loss: 2.712e-01]
leoprint:  44%|####4     | 1066/2400 [03:59<1:14:26,  3.35s/it, lr: 5.0e-05 loss: 2.712e-01]
leoprint:  44%|####4     | 1067/2400 [03:59<1:15:20,  3.39s/it, lr: 5.0e-05 loss: 2.712e-01]
leoprint:  44%|####4     | 1067/2400 [03:59<1:15:20,  3.39s/it, lr: 5.0e-05 loss: 2.712e-01]
leoprint:  44%|####4     | 1067/2400 [04:03<1:15:20,  3.39s/it, lr: 5.0e-05 loss: 2.583e-01]
leoprint:  44%|####4     | 1067/2400 [04:03<1:15:20,  3.39s/it, lr: 5.0e-05 loss: 2.583e-01]
leoprint:  44%|####4     | 1068/2400 [04:03<1:17:47,  3.50s/it, lr: 5.0e-05 loss: 2.583e-01]
leoprint:  44%|####4     | 1068/2400 [04:03<1:17:47,  3.50s/it, lr: 5.0e-05 loss: 2.583e-01]
leoprint:  44%|####4     | 1068/2400 [04:07<1:17:47,  3.50s/it, lr: 5.0e-05 loss: 2.373e-01]
leoprint:  44%|####4     | 1068/2400 [04:07<1:17:47,  3.50s/it, lr: 5.0e-05 loss: 2.373e-01]
leoprint:  45%|####4     | 1069/2400 [04:07<1:18:24,  3.53s/it, lr: 5.0e-05 loss: 2.373e-01]
leoprint:  45%|####4     | 1069/2400 [04:07<1:18:24,  3.53s/it, lr: 5.0e-05 loss: 2.373e-01]
leoprint:  45%|####4     | 1069/2400 [04:10<1:18:24,  3.53s/it, lr: 5.0e-05 loss: 2.159e-01]
leoprint:  45%|####4     | 1069/2400 [04:10<1:18:24,  3.53s/it, lr: 5.0e-05 loss: 2.159e-01]
leoprint:  45%|####4     | 1070/2400 [04:14<1:18:20,  3.53s/it, lr: 5.0e-05 loss: 3.741e-01]
leoprint:  45%|####4     | 1070/2400 [04:14<1:18:20,  3.53s/it, lr: 5.0e-05 loss: 3.741e-01]
leoprint:  45%|####4     | 1071/2400 [04:14<1:00:12,  2.72s/it, lr: 5.0e-05 loss: 3.741e-01]
leoprint:  45%|####4     | 1071/2400 [04:14<1:00:12,  2.72s/it, lr: 5.0e-05 loss: 3.741e-01]
leoprint:  45%|####4     | 1071/2400 [04:17<1:00:12,  2.72s/it, lr: 5.0e-05 loss: 2.757e-01]
leoprint:  45%|####4     | 1071/2400 [04:17<1:00:12,  2.72s/it, lr: 5.0e-05 loss: 2.757e-01]
leoprint:  45%|####4     | 1072/2400 [04:17<1:04:24,  2.91s/it, lr: 5.0e-05 loss: 2.757e-01]
leoprint:  45%|####4     | 1072/2400 [04:17<1:04:24,  2.91s/it, lr: 5.0e-05 loss: 2.757e-01]
leoprint:  45%|####4     | 1072/2400 [04:21<1:04:24,  2.91s/it, lr: 5.0e-05 loss: 3.177e-01]
leoprint:  45%|####4     | 1072/2400 [04:21<1:04:24,  2.91s/it, lr: 5.0e-05 loss: 3.177e-01]
leoprint:  45%|####4     | 1073/2400 [04:21<1:07:45,  3.06s/it, lr: 5.0e-05 loss: 3.177e-01]
leoprint:  45%|####4     | 1073/2400 [04:21<1:07:45,  3.06s/it, lr: 5.0e-05 loss: 3.177e-01]
leoprint:  45%|####4     | 1073/2400 [04:24<1:07:45,  3.06s/it, lr: 5.0e-05 loss: 2.981e-01]
leoprint:  45%|####4     | 1073/2400 [04:24<1:07:45,  3.06s/it, lr: 5.0e-05 loss: 2.981e-01]
leoprint:  45%|####4     | 1074/2400 [04:24<1:11:31,  3.24s/it, lr: 5.0e-05 loss: 2.981e-01]
leoprint:  45%|####4     | 1074/2400 [04:24<1:11:31,  3.24s/it, lr: 5.0e-05 loss: 2.981e-01]
leoprint:  45%|####4     | 1074/2400 [04:28<1:11:31,  3.24s/it, lr: 5.0e-05 loss: 3.456e-01]
leoprint:  45%|####4     | 1074/2400 [04:28<1:11:31,  3.24s/it, lr: 5.0e-05 loss: 3.456e-01]
leoprint:  45%|####4     | 1075/2400 [04:28<1:13:02,  3.31s/it, lr: 5.0e-05 loss: 3.456e-01]
leoprint:  45%|####4     | 1075/2400 [04:28<1:13:02,  3.31s/it, lr: 5.0e-05 loss: 3.456e-01]
leoprint:  45%|####4     | 1075/2400 [04:31<1:13:02,  3.31s/it, lr: 5.0e-05 loss: 2.436e-01]
leoprint:  45%|####4     | 1075/2400 [04:31<1:13:02,  3.31s/it, lr: 5.0e-05 loss: 2.436e-01]
leoprint:  45%|####4     | 1076/2400 [04:31<1:14:08,  3.36s/it, lr: 5.0e-05 loss: 2.436e-01]
leoprint:  45%|####4     | 1076/2400 [04:31<1:14:08,  3.36s/it, lr: 5.0e-05 loss: 2.436e-01]
leoprint:  45%|####4     | 1076/2400 [04:35<1:14:08,  3.36s/it, lr: 5.0e-05 loss: 2.635e-01]
leoprint:  45%|####4     | 1076/2400 [04:35<1:14:08,  3.36s/it, lr: 5.0e-05 loss: 2.635e-01]
leoprint:  45%|####4     | 1077/2400 [04:35<1:15:00,  3.40s/it, lr: 5.0e-05 loss: 2.635e-01]
leoprint:  45%|####4     | 1077/2400 [04:35<1:15:00,  3.40s/it, lr: 5.0e-05 loss: 2.635e-01]
leoprint:  45%|####4     | 1077/2400 [04:38<1:15:00,  3.40s/it, lr: 5.0e-05 loss: 3.059e-01]
leoprint:  45%|####4     | 1077/2400 [04:38<1:15:00,  3.40s/it, lr: 5.0e-05 loss: 3.059e-01]
leoprint:  45%|####4     | 1078/2400 [04:38<1:15:35,  3.43s/it, lr: 5.0e-05 loss: 3.059e-01]
leoprint:  45%|####4     | 1078/2400 [04:38<1:15:35,  3.43s/it, lr: 5.0e-05 loss: 3.059e-01]
leoprint:  45%|####4     | 1078/2400 [04:42<1:15:35,  3.43s/it, lr: 5.0e-05 loss: 2.462e-01]
leoprint:  45%|####4     | 1078/2400 [04:42<1:15:35,  3.43s/it, lr: 5.0e-05 loss: 2.462e-01]
leoprint:  45%|####4     | 1079/2400 [04:42<1:16:40,  3.48s/it, lr: 5.0e-05 loss: 2.462e-01]
leoprint:  45%|####4     | 1079/2400 [04:42<1:16:40,  3.48s/it, lr: 5.0e-05 loss: 2.462e-01]
leoprint:  45%|####4     | 1079/2400 [04:46<1:16:40,  3.48s/it, lr: 5.0e-05 loss: 3.458e-01]
leoprint:  45%|####4     | 1079/2400 [04:46<1:16:40,  3.48s/it, lr: 5.0e-05 loss: 3.458e-01]
leoprint:  45%|####5     | 1080/2400 [04:49<1:16:37,  3.48s/it, lr: 5.0e-05 loss: 3.378e-01]
leoprint:  45%|####5     | 1080/2400 [04:49<1:16:37,  3.48s/it, lr: 5.0e-05 loss: 3.378e-01]
leoprint:  45%|####5     | 1081/2400 [04:49<59:07,  2.69s/it, lr: 5.0e-05 loss: 3.378e-01]  
leoprint:  45%|####5     | 1081/2400 [04:49<59:07,  2.69s/it, lr: 5.0e-05 loss: 3.378e-01]  
leoprint:  45%|####5     | 1081/2400 [04:53<59:07,  2.69s/it, lr: 5.0e-05 loss: 4.121e-01]
leoprint:  45%|####5     | 1081/2400 [04:53<59:07,  2.69s/it, lr: 5.0e-05 loss: 4.121e-01]
leoprint:  45%|####5     | 1082/2400 [04:53<1:03:23,  2.89s/it, lr: 5.0e-05 loss: 4.121e-01]
leoprint:  45%|####5     | 1082/2400 [04:53<1:03:23,  2.89s/it, lr: 5.0e-05 loss: 4.121e-01]
leoprint:  45%|####5     | 1082/2400 [04:56<1:03:23,  2.89s/it, lr: 5.0e-05 loss: 2.798e-01]
leoprint:  45%|####5     | 1082/2400 [04:56<1:03:23,  2.89s/it, lr: 5.0e-05 loss: 2.798e-01]
leoprint:  45%|####5     | 1083/2400 [04:56<1:07:31,  3.08s/it, lr: 5.0e-05 loss: 2.798e-01]
leoprint:  45%|####5     | 1083/2400 [04:56<1:07:31,  3.08s/it, lr: 5.0e-05 loss: 2.798e-01]
leoprint:  45%|####5     | 1083/2400 [05:00<1:07:31,  3.08s/it, lr: 5.0e-05 loss: 2.038e-01]
leoprint:  45%|####5     | 1083/2400 [05:00<1:07:31,  3.08s/it, lr: 5.0e-05 loss: 2.038e-01]
leoprint:  45%|####5     | 1084/2400 [05:00<1:09:58,  3.19s/it, lr: 5.0e-05 loss: 2.038e-01]
leoprint:  45%|####5     | 1084/2400 [05:00<1:09:58,  3.19s/it, lr: 5.0e-05 loss: 2.038e-01]
leoprint:  45%|####5     | 1084/2400 [05:03<1:09:58,  3.19s/it, lr: 5.0e-05 loss: 2.764e-01]
leoprint:  45%|####5     | 1084/2400 [05:03<1:09:58,  3.19s/it, lr: 5.0e-05 loss: 2.764e-01]
leoprint:  45%|####5     | 1085/2400 [05:03<1:12:14,  3.30s/it, lr: 5.0e-05 loss: 2.764e-01]
leoprint:  45%|####5     | 1085/2400 [05:03<1:12:14,  3.30s/it, lr: 5.0e-05 loss: 2.764e-01]
leoprint:  45%|####5     | 1085/2400 [05:07<1:12:14,  3.30s/it, lr: 5.0e-05 loss: 2.476e-01]
leoprint:  45%|####5     | 1085/2400 [05:07<1:12:14,  3.30s/it, lr: 5.0e-05 loss: 2.476e-01]
leoprint:  45%|####5     | 1086/2400 [05:07<1:13:25,  3.35s/it, lr: 5.0e-05 loss: 2.476e-01]
leoprint:  45%|####5     | 1086/2400 [05:07<1:13:25,  3.35s/it, lr: 5.0e-05 loss: 2.476e-01]
leoprint:  45%|####5     | 1086/2400 [05:10<1:13:25,  3.35s/it, lr: 5.0e-05 loss: 2.338e-01]
leoprint:  45%|####5     | 1086/2400 [05:10<1:13:25,  3.35s/it, lr: 5.0e-05 loss: 2.338e-01]
leoprint:  45%|####5     | 1087/2400 [05:10<1:15:04,  3.43s/it, lr: 5.0e-05 loss: 2.338e-01]
leoprint:  45%|####5     | 1087/2400 [05:10<1:15:04,  3.43s/it, lr: 5.0e-05 loss: 2.338e-01]
leoprint:  45%|####5     | 1087/2400 [05:14<1:15:04,  3.43s/it, lr: 5.0e-05 loss: 3.418e-01]
leoprint:  45%|####5     | 1087/2400 [05:14<1:15:04,  3.43s/it, lr: 5.0e-05 loss: 3.418e-01]
leoprint:  45%|####5     | 1088/2400 [05:14<1:15:28,  3.45s/it, lr: 5.0e-05 loss: 3.418e-01]
leoprint:  45%|####5     | 1088/2400 [05:14<1:15:28,  3.45s/it, lr: 5.0e-05 loss: 3.418e-01]
leoprint:  45%|####5     | 1088/2400 [05:17<1:15:28,  3.45s/it, lr: 5.0e-05 loss: 3.849e-01]
leoprint:  45%|####5     | 1088/2400 [05:17<1:15:28,  3.45s/it, lr: 5.0e-05 loss: 3.849e-01]
leoprint:  45%|####5     | 1089/2400 [05:17<1:15:43,  3.47s/it, lr: 5.0e-05 loss: 3.849e-01]
leoprint:  45%|####5     | 1089/2400 [05:17<1:15:43,  3.47s/it, lr: 5.0e-05 loss: 3.849e-01]
leoprint:  45%|####5     | 1089/2400 [05:21<1:15:43,  3.47s/it, lr: 5.0e-05 loss: 2.922e-01]
leoprint:  45%|####5     | 1089/2400 [05:21<1:15:43,  3.47s/it, lr: 5.0e-05 loss: 2.922e-01]
leoprint:  45%|####5     | 1090/2400 [05:25<1:15:40,  3.47s/it, lr: 5.0e-05 loss: 2.692e-01]
leoprint:  45%|####5     | 1090/2400 [05:25<1:15:40,  3.47s/it, lr: 5.0e-05 loss: 2.692e-01]
leoprint:  45%|####5     | 1091/2400 [05:25<1:00:15,  2.76s/it, lr: 5.0e-05 loss: 2.692e-01]
leoprint:  45%|####5     | 1091/2400 [05:25<1:00:15,  2.76s/it, lr: 5.0e-05 loss: 2.692e-01]
leoprint:  45%|####5     | 1091/2400 [05:28<1:00:15,  2.76s/it, lr: 5.0e-05 loss: 1.936e-01]
leoprint:  45%|####5     | 1091/2400 [05:28<1:00:15,  2.76s/it, lr: 5.0e-05 loss: 1.936e-01]
leoprint:  46%|####5     | 1092/2400 [05:28<1:04:47,  2.97s/it, lr: 5.0e-05 loss: 1.936e-01]
leoprint:  46%|####5     | 1092/2400 [05:28<1:04:47,  2.97s/it, lr: 5.0e-05 loss: 1.936e-01]
leoprint:  46%|####5     | 1092/2400 [05:32<1:04:47,  2.97s/it, lr: 5.0e-05 loss: 2.572e-01]
leoprint:  46%|####5     | 1092/2400 [05:32<1:04:47,  2.97s/it, lr: 5.0e-05 loss: 2.572e-01]
leoprint:  46%|####5     | 1093/2400 [05:32<1:08:25,  3.14s/it, lr: 5.0e-05 loss: 2.572e-01]
leoprint:  46%|####5     | 1093/2400 [05:32<1:08:25,  3.14s/it, lr: 5.0e-05 loss: 2.572e-01]
leoprint:  46%|####5     | 1093/2400 [05:36<1:08:25,  3.14s/it, lr: 5.0e-05 loss: 3.117e-01]
leoprint:  46%|####5     | 1093/2400 [05:36<1:08:25,  3.14s/it, lr: 5.0e-05 loss: 3.117e-01]
leoprint:  46%|####5     | 1094/2400 [05:36<1:10:27,  3.24s/it, lr: 5.0e-05 loss: 3.117e-01]
leoprint:  46%|####5     | 1094/2400 [05:36<1:10:27,  3.24s/it, lr: 5.0e-05 loss: 3.117e-01]
leoprint:  46%|####5     | 1094/2400 [05:39<1:10:27,  3.24s/it, lr: 5.0e-05 loss: 3.399e-01]
leoprint:  46%|####5     | 1094/2400 [05:39<1:10:27,  3.24s/it, lr: 5.0e-05 loss: 3.399e-01]
leoprint:  46%|####5     | 1095/2400 [05:39<1:11:59,  3.31s/it, lr: 5.0e-05 loss: 3.399e-01]
leoprint:  46%|####5     | 1095/2400 [05:39<1:11:59,  3.31s/it, lr: 5.0e-05 loss: 3.399e-01]
leoprint:  46%|####5     | 1095/2400 [05:43<1:11:59,  3.31s/it, lr: 5.0e-05 loss: 3.437e-01]
leoprint:  46%|####5     | 1095/2400 [05:43<1:11:59,  3.31s/it, lr: 5.0e-05 loss: 3.437e-01]
leoprint:  46%|####5     | 1096/2400 [05:43<1:13:36,  3.39s/it, lr: 5.0e-05 loss: 3.437e-01]
leoprint:  46%|####5     | 1096/2400 [05:43<1:13:36,  3.39s/it, lr: 5.0e-05 loss: 3.437e-01]
leoprint:  46%|####5     | 1096/2400 [05:46<1:13:36,  3.39s/it, lr: 5.0e-05 loss: 2.694e-01]
leoprint:  46%|####5     | 1096/2400 [05:46<1:13:36,  3.39s/it, lr: 5.0e-05 loss: 2.694e-01]
leoprint:  46%|####5     | 1097/2400 [05:46<1:14:14,  3.42s/it, lr: 5.0e-05 loss: 2.694e-01]
leoprint:  46%|####5     | 1097/2400 [05:46<1:14:14,  3.42s/it, lr: 5.0e-05 loss: 2.694e-01]
leoprint:  46%|####5     | 1097/2400 [05:50<1:14:14,  3.42s/it, lr: 5.0e-05 loss: 3.023e-01]
leoprint:  46%|####5     | 1097/2400 [05:50<1:14:14,  3.42s/it, lr: 5.0e-05 loss: 3.023e-01]
leoprint:  46%|####5     | 1098/2400 [05:50<1:14:42,  3.44s/it, lr: 5.0e-05 loss: 3.023e-01]
leoprint:  46%|####5     | 1098/2400 [05:50<1:14:42,  3.44s/it, lr: 5.0e-05 loss: 3.023e-01]
leoprint:  46%|####5     | 1098/2400 [05:53<1:14:42,  3.44s/it, lr: 5.0e-05 loss: 2.443e-01]
leoprint:  46%|####5     | 1098/2400 [05:53<1:14:42,  3.44s/it, lr: 5.0e-05 loss: 2.443e-01]
leoprint:  46%|####5     | 1099/2400 [05:53<1:15:02,  3.46s/it, lr: 5.0e-05 loss: 2.443e-01]
leoprint:  46%|####5     | 1099/2400 [05:53<1:15:02,  3.46s/it, lr: 5.0e-05 loss: 2.443e-01]
leoprint:  46%|####5     | 1099/2400 [05:57<1:15:02,  3.46s/it, lr: 5.0e-05 loss: 2.761e-01]
leoprint:  46%|####5     | 1099/2400 [05:57<1:15:02,  3.46s/it, lr: 5.0e-05 loss: 2.761e-01]
leoprint:  46%|####5     | 1100/2400 [06:00<1:14:59,  3.46s/it, lr: 5.0e-05 loss: 3.556e-01]
leoprint:  46%|####5     | 1100/2400 [06:00<1:14:59,  3.46s/it, lr: 5.0e-05 loss: 3.556e-01]
leoprint:  46%|####5     | 1101/2400 [06:00<57:58,  2.68s/it, lr: 5.0e-05 loss: 3.556e-01]  
leoprint:  46%|####5     | 1101/2400 [06:00<57:58,  2.68s/it, lr: 5.0e-05 loss: 3.556e-01]  
leoprint:  46%|####5     | 1101/2400 [06:04<57:58,  2.68s/it, lr: 5.0e-05 loss: 2.624e-01]
leoprint:  46%|####5     | 1101/2400 [06:04<57:58,  2.68s/it, lr: 5.0e-05 loss: 2.624e-01]
leoprint:  46%|####5     | 1102/2400 [06:04<1:03:09,  2.92s/it, lr: 5.0e-05 loss: 2.624e-01]
leoprint:  46%|####5     | 1102/2400 [06:04<1:03:09,  2.92s/it, lr: 5.0e-05 loss: 2.624e-01]
leoprint:  46%|####5     | 1102/2400 [06:08<1:03:09,  2.92s/it, lr: 5.0e-05 loss: 2.853e-01]
leoprint:  46%|####5     | 1102/2400 [06:08<1:03:09,  2.92s/it, lr: 5.0e-05 loss: 2.853e-01]
leoprint:  46%|####5     | 1103/2400 [06:08<1:06:57,  3.10s/it, lr: 5.0e-05 loss: 2.853e-01]
leoprint:  46%|####5     | 1103/2400 [06:08<1:06:57,  3.10s/it, lr: 5.0e-05 loss: 2.853e-01]
leoprint:  46%|####5     | 1103/2400 [06:11<1:06:57,  3.10s/it, lr: 5.0e-05 loss: 2.633e-01]
leoprint:  46%|####5     | 1103/2400 [06:11<1:06:57,  3.10s/it, lr: 5.0e-05 loss: 2.633e-01]
leoprint:  46%|####6     | 1104/2400 [06:11<1:09:56,  3.24s/it, lr: 5.0e-05 loss: 2.633e-01]
leoprint:  46%|####6     | 1104/2400 [06:11<1:09:56,  3.24s/it, lr: 5.0e-05 loss: 2.633e-01]
leoprint:  46%|####6     | 1104/2400 [06:15<1:09:56,  3.24s/it, lr: 5.0e-05 loss: 2.552e-01]
leoprint:  46%|####6     | 1104/2400 [06:15<1:09:56,  3.24s/it, lr: 5.0e-05 loss: 2.552e-01]
leoprint:  46%|####6     | 1105/2400 [06:15<1:11:26,  3.31s/it, lr: 5.0e-05 loss: 2.552e-01]
leoprint:  46%|####6     | 1105/2400 [06:15<1:11:26,  3.31s/it, lr: 5.0e-05 loss: 2.552e-01]
leoprint:  46%|####6     | 1105/2400 [06:18<1:11:26,  3.31s/it, lr: 5.0e-05 loss: 2.865e-01]
leoprint:  46%|####6     | 1105/2400 [06:18<1:11:26,  3.31s/it, lr: 5.0e-05 loss: 2.865e-01]
leoprint:  46%|####6     | 1106/2400 [06:18<1:12:31,  3.36s/it, lr: 5.0e-05 loss: 2.865e-01]
leoprint:  46%|####6     | 1106/2400 [06:18<1:12:31,  3.36s/it, lr: 5.0e-05 loss: 2.865e-01]
leoprint:  46%|####6     | 1106/2400 [06:22<1:12:31,  3.36s/it, lr: 5.0e-05 loss: 2.094e-01]
leoprint:  46%|####6     | 1106/2400 [06:22<1:12:31,  3.36s/it, lr: 5.0e-05 loss: 2.094e-01]
leoprint:  46%|####6     | 1107/2400 [06:22<1:14:00,  3.43s/it, lr: 5.0e-05 loss: 2.094e-01]
leoprint:  46%|####6     | 1107/2400 [06:22<1:14:00,  3.43s/it, lr: 5.0e-05 loss: 2.094e-01]
leoprint:  46%|####6     | 1107/2400 [06:25<1:14:00,  3.43s/it, lr: 5.0e-05 loss: 2.856e-01]
leoprint:  46%|####6     | 1107/2400 [06:25<1:14:00,  3.43s/it, lr: 5.0e-05 loss: 2.856e-01]
leoprint:  46%|####6     | 1108/2400 [06:25<1:15:02,  3.48s/it, lr: 5.0e-05 loss: 2.856e-01]
leoprint:  46%|####6     | 1108/2400 [06:25<1:15:02,  3.48s/it, lr: 5.0e-05 loss: 2.856e-01]
leoprint:  46%|####6     | 1108/2400 [06:29<1:15:02,  3.48s/it, lr: 5.0e-05 loss: 4.009e-01]
leoprint:  46%|####6     | 1108/2400 [06:29<1:15:02,  3.48s/it, lr: 5.0e-05 loss: 4.009e-01]
leoprint:  46%|####6     | 1109/2400 [06:29<1:15:07,  3.49s/it, lr: 5.0e-05 loss: 4.009e-01]
leoprint:  46%|####6     | 1109/2400 [06:29<1:15:07,  3.49s/it, lr: 5.0e-05 loss: 4.009e-01]
leoprint:  46%|####6     | 1109/2400 [06:32<1:15:07,  3.49s/it, lr: 5.0e-05 loss: 2.541e-01]
leoprint:  46%|####6     | 1109/2400 [06:32<1:15:07,  3.49s/it, lr: 5.0e-05 loss: 2.541e-01]
leoprint:  46%|####6     | 1110/2400 [06:36<1:15:03,  3.49s/it, lr: 5.0e-05 loss: 2.195e-01]
leoprint:  46%|####6     | 1110/2400 [06:36<1:15:03,  3.49s/it, lr: 5.0e-05 loss: 2.195e-01]
leoprint:  46%|####6     | 1111/2400 [06:36<58:26,  2.72s/it, lr: 5.0e-05 loss: 2.195e-01]  
leoprint:  46%|####6     | 1111/2400 [06:36<58:26,  2.72s/it, lr: 5.0e-05 loss: 2.195e-01]  
leoprint:  46%|####6     | 1111/2400 [06:40<58:26,  2.72s/it, lr: 5.0e-05 loss: 3.818e-01]
leoprint:  46%|####6     | 1111/2400 [06:40<58:26,  2.72s/it, lr: 5.0e-05 loss: 3.818e-01]
leoprint:  46%|####6     | 1112/2400 [06:40<1:02:33,  2.91s/it, lr: 5.0e-05 loss: 3.818e-01]
leoprint:  46%|####6     | 1112/2400 [06:40<1:02:33,  2.91s/it, lr: 5.0e-05 loss: 3.818e-01]
leoprint:  46%|####6     | 1112/2400 [06:43<1:02:33,  2.91s/it, lr: 5.0e-05 loss: 2.444e-01]
leoprint:  46%|####6     | 1112/2400 [06:43<1:02:33,  2.91s/it, lr: 5.0e-05 loss: 2.444e-01]
leoprint:  46%|####6     | 1113/2400 [06:43<1:05:47,  3.07s/it, lr: 5.0e-05 loss: 2.444e-01]
leoprint:  46%|####6     | 1113/2400 [06:43<1:05:47,  3.07s/it, lr: 5.0e-05 loss: 2.444e-01]
leoprint:  46%|####6     | 1113/2400 [06:47<1:05:47,  3.07s/it, lr: 5.0e-05 loss: 3.602e-01]
leoprint:  46%|####6     | 1113/2400 [06:47<1:05:47,  3.07s/it, lr: 5.0e-05 loss: 3.602e-01]
leoprint:  46%|####6     | 1114/2400 [06:47<1:09:34,  3.25s/it, lr: 5.0e-05 loss: 3.602e-01]
leoprint:  46%|####6     | 1114/2400 [06:47<1:09:34,  3.25s/it, lr: 5.0e-05 loss: 3.602e-01]
leoprint:  46%|####6     | 1114/2400 [06:50<1:09:34,  3.25s/it, lr: 5.0e-05 loss: 2.172e-01]
leoprint:  46%|####6     | 1114/2400 [06:50<1:09:34,  3.25s/it, lr: 5.0e-05 loss: 2.172e-01]
leoprint:  46%|####6     | 1115/2400 [06:50<1:11:39,  3.35s/it, lr: 5.0e-05 loss: 2.172e-01]
leoprint:  46%|####6     | 1115/2400 [06:50<1:11:39,  3.35s/it, lr: 5.0e-05 loss: 2.172e-01]
leoprint:  46%|####6     | 1115/2400 [06:54<1:11:39,  3.35s/it, lr: 5.0e-05 loss: 2.541e-01]
leoprint:  46%|####6     | 1115/2400 [06:54<1:11:39,  3.35s/it, lr: 5.0e-05 loss: 2.541e-01]
leoprint:  46%|####6     | 1116/2400 [06:54<1:12:30,  3.39s/it, lr: 5.0e-05 loss: 2.541e-01]
leoprint:  46%|####6     | 1116/2400 [06:54<1:12:30,  3.39s/it, lr: 5.0e-05 loss: 2.541e-01]
leoprint:  46%|####6     | 1116/2400 [06:57<1:12:30,  3.39s/it, lr: 5.0e-05 loss: 2.995e-01]
leoprint:  46%|####6     | 1116/2400 [06:57<1:12:30,  3.39s/it, lr: 5.0e-05 loss: 2.995e-01]
leoprint:  47%|####6     | 1117/2400 [06:57<1:13:08,  3.42s/it, lr: 5.0e-05 loss: 2.995e-01]
leoprint:  47%|####6     | 1117/2400 [06:57<1:13:08,  3.42s/it, lr: 5.0e-05 loss: 2.995e-01]
leoprint:  47%|####6     | 1117/2400 [07:01<1:13:08,  3.42s/it, lr: 5.0e-05 loss: 3.204e-01]
leoprint:  47%|####6     | 1117/2400 [07:01<1:13:08,  3.42s/it, lr: 5.0e-05 loss: 3.204e-01]
leoprint:  47%|####6     | 1118/2400 [07:01<1:13:33,  3.44s/it, lr: 5.0e-05 loss: 3.204e-01]
leoprint:  47%|####6     | 1118/2400 [07:01<1:13:33,  3.44s/it, lr: 5.0e-05 loss: 3.204e-01]
leoprint:  47%|####6     | 1118/2400 [07:04<1:13:33,  3.44s/it, lr: 5.0e-05 loss: 2.553e-01]
leoprint:  47%|####6     | 1118/2400 [07:04<1:13:33,  3.44s/it, lr: 5.0e-05 loss: 2.553e-01]
leoprint:  47%|####6     | 1119/2400 [07:04<1:14:17,  3.48s/it, lr: 5.0e-05 loss: 2.553e-01]
leoprint:  47%|####6     | 1119/2400 [07:04<1:14:17,  3.48s/it, lr: 5.0e-05 loss: 2.553e-01]
leoprint:  47%|####6     | 1119/2400 [07:08<1:14:17,  3.48s/it, lr: 5.0e-05 loss: 3.197e-01]
leoprint:  47%|####6     | 1119/2400 [07:08<1:14:17,  3.48s/it, lr: 5.0e-05 loss: 3.197e-01]
leoprint:  47%|####6     | 1120/2400 [07:12<1:14:14,  3.48s/it, lr: 5.0e-05 loss: 2.941e-01]
leoprint:  47%|####6     | 1120/2400 [07:12<1:14:14,  3.48s/it, lr: 5.0e-05 loss: 2.941e-01]
leoprint:  47%|####6     | 1121/2400 [07:12<57:18,  2.69s/it, lr: 5.0e-05 loss: 2.941e-01]  
leoprint:  47%|####6     | 1121/2400 [07:12<57:18,  2.69s/it, lr: 5.0e-05 loss: 2.941e-01]  
leoprint:  47%|####6     | 1121/2400 [07:15<57:18,  2.69s/it, lr: 5.0e-05 loss: 2.794e-01]
leoprint:  47%|####6     | 1121/2400 [07:15<57:18,  2.69s/it, lr: 5.0e-05 loss: 2.794e-01]
leoprint:  47%|####6     | 1122/2400 [07:15<1:01:31,  2.89s/it, lr: 5.0e-05 loss: 2.794e-01]
leoprint:  47%|####6     | 1122/2400 [07:15<1:01:31,  2.89s/it, lr: 5.0e-05 loss: 2.794e-01]
leoprint:  47%|####6     | 1122/2400 [07:19<1:01:31,  2.89s/it, lr: 5.0e-05 loss: 2.595e-01]
leoprint:  47%|####6     | 1122/2400 [07:19<1:01:31,  2.89s/it, lr: 5.0e-05 loss: 2.595e-01]
leoprint:  47%|####6     | 1123/2400 [07:19<1:05:28,  3.08s/it, lr: 5.0e-05 loss: 2.595e-01]
leoprint:  47%|####6     | 1123/2400 [07:19<1:05:28,  3.08s/it, lr: 5.0e-05 loss: 2.595e-01]
leoprint:  47%|####6     | 1123/2400 [07:22<1:05:28,  3.08s/it, lr: 5.0e-05 loss: 3.234e-01]
leoprint:  47%|####6     | 1123/2400 [07:22<1:05:28,  3.08s/it, lr: 5.0e-05 loss: 3.234e-01]
leoprint:  47%|####6     | 1124/2400 [07:22<1:07:49,  3.19s/it, lr: 5.0e-05 loss: 3.234e-01]
leoprint:  47%|####6     | 1124/2400 [07:22<1:07:49,  3.19s/it, lr: 5.0e-05 loss: 3.234e-01]
leoprint:  47%|####6     | 1124/2400 [07:26<1:07:49,  3.19s/it, lr: 5.0e-05 loss: 2.573e-01]
leoprint:  47%|####6     | 1124/2400 [07:26<1:07:49,  3.19s/it, lr: 5.0e-05 loss: 2.573e-01]
leoprint:  47%|####6     | 1125/2400 [07:26<1:11:33,  3.37s/it, lr: 5.0e-05 loss: 2.573e-01]
leoprint:  47%|####6     | 1125/2400 [07:26<1:11:33,  3.37s/it, lr: 5.0e-05 loss: 2.573e-01]
leoprint:  47%|####6     | 1125/2400 [07:30<1:11:33,  3.37s/it, lr: 5.0e-05 loss: 2.547e-01]
leoprint:  47%|####6     | 1125/2400 [07:30<1:11:33,  3.37s/it, lr: 5.0e-05 loss: 2.547e-01]
leoprint:  47%|####6     | 1126/2400 [07:30<1:12:15,  3.40s/it, lr: 5.0e-05 loss: 2.547e-01]
leoprint:  47%|####6     | 1126/2400 [07:30<1:12:15,  3.40s/it, lr: 5.0e-05 loss: 2.547e-01]
leoprint:  47%|####6     | 1126/2400 [07:33<1:12:15,  3.40s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  47%|####6     | 1126/2400 [07:33<1:12:15,  3.40s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  47%|####6     | 1127/2400 [07:33<1:12:48,  3.43s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  47%|####6     | 1127/2400 [07:33<1:12:48,  3.43s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  47%|####6     | 1127/2400 [07:37<1:12:48,  3.43s/it, lr: 5.0e-05 loss: 2.958e-01]
leoprint:  47%|####6     | 1127/2400 [07:37<1:12:48,  3.43s/it, lr: 5.0e-05 loss: 2.958e-01]
leoprint:  47%|####6     | 1128/2400 [07:37<1:13:10,  3.45s/it, lr: 5.0e-05 loss: 2.958e-01]
leoprint:  47%|####6     | 1128/2400 [07:37<1:13:10,  3.45s/it, lr: 5.0e-05 loss: 2.958e-01]
leoprint:  47%|####6     | 1128/2400 [07:40<1:13:10,  3.45s/it, lr: 5.0e-05 loss: 3.211e-01]
leoprint:  47%|####6     | 1128/2400 [07:40<1:13:10,  3.45s/it, lr: 5.0e-05 loss: 3.211e-01]
leoprint:  47%|####7     | 1129/2400 [07:40<1:14:05,  3.50s/it, lr: 5.0e-05 loss: 3.211e-01]
leoprint:  47%|####7     | 1129/2400 [07:40<1:14:05,  3.50s/it, lr: 5.0e-05 loss: 3.211e-01]
leoprint:  47%|####7     | 1129/2400 [07:44<1:14:05,  3.50s/it, lr: 5.0e-05 loss: 3.425e-01]
leoprint:  47%|####7     | 1129/2400 [07:44<1:14:05,  3.50s/it, lr: 5.0e-05 loss: 3.425e-01]
leoprint:  47%|####7     | 1130/2400 [07:47<1:14:01,  3.50s/it, lr: 5.0e-05 loss: 2.720e-01]
leoprint:  47%|####7     | 1130/2400 [07:47<1:14:01,  3.50s/it, lr: 5.0e-05 loss: 2.720e-01]
leoprint:  47%|####7     | 1131/2400 [07:47<57:01,  2.70s/it, lr: 5.0e-05 loss: 2.720e-01]  
leoprint:  47%|####7     | 1131/2400 [07:47<57:01,  2.70s/it, lr: 5.0e-05 loss: 2.720e-01]  
leoprint:  47%|####7     | 1131/2400 [07:51<57:01,  2.70s/it, lr: 5.0e-05 loss: 2.661e-01]
leoprint:  47%|####7     | 1131/2400 [07:51<57:01,  2.70s/it, lr: 5.0e-05 loss: 2.661e-01]
leoprint:  47%|####7     | 1132/2400 [07:51<1:01:41,  2.92s/it, lr: 5.0e-05 loss: 2.661e-01]
leoprint:  47%|####7     | 1132/2400 [07:51<1:01:41,  2.92s/it, lr: 5.0e-05 loss: 2.661e-01]
leoprint:  47%|####7     | 1132/2400 [07:54<1:01:41,  2.92s/it, lr: 5.0e-05 loss: 2.252e-01]
leoprint:  47%|####7     | 1132/2400 [07:54<1:01:41,  2.92s/it, lr: 5.0e-05 loss: 2.252e-01]
leoprint:  47%|####7     | 1133/2400 [07:54<1:04:50,  3.07s/it, lr: 5.0e-05 loss: 2.252e-01]
leoprint:  47%|####7     | 1133/2400 [07:54<1:04:50,  3.07s/it, lr: 5.0e-05 loss: 2.252e-01]
leoprint:  47%|####7     | 1133/2400 [07:58<1:04:50,  3.07s/it, lr: 5.0e-05 loss: 2.896e-01]
leoprint:  47%|####7     | 1133/2400 [07:58<1:04:50,  3.07s/it, lr: 5.0e-05 loss: 2.896e-01]
leoprint:  47%|####7     | 1134/2400 [07:58<1:07:16,  3.19s/it, lr: 5.0e-05 loss: 2.896e-01]
leoprint:  47%|####7     | 1134/2400 [07:58<1:07:16,  3.19s/it, lr: 5.0e-05 loss: 2.896e-01]
leoprint:  47%|####7     | 1134/2400 [08:01<1:07:16,  3.19s/it, lr: 5.0e-05 loss: 3.465e-01]
leoprint:  47%|####7     | 1134/2400 [08:01<1:07:16,  3.19s/it, lr: 5.0e-05 loss: 3.465e-01]
leoprint:  47%|####7     | 1135/2400 [08:01<1:09:03,  3.28s/it, lr: 5.0e-05 loss: 3.465e-01]
leoprint:  47%|####7     | 1135/2400 [08:01<1:09:03,  3.28s/it, lr: 5.0e-05 loss: 3.465e-01]
leoprint:  47%|####7     | 1135/2400 [08:05<1:09:03,  3.28s/it, lr: 5.0e-05 loss: 2.308e-01]
leoprint:  47%|####7     | 1135/2400 [08:05<1:09:03,  3.28s/it, lr: 5.0e-05 loss: 2.308e-01]
leoprint:  47%|####7     | 1136/2400 [08:05<1:11:20,  3.39s/it, lr: 5.0e-05 loss: 2.308e-01]
leoprint:  47%|####7     | 1136/2400 [08:05<1:11:20,  3.39s/it, lr: 5.0e-05 loss: 2.308e-01]
leoprint:  47%|####7     | 1136/2400 [08:09<1:11:20,  3.39s/it, lr: 5.0e-05 loss: 2.366e-01]
leoprint:  47%|####7     | 1136/2400 [08:09<1:11:20,  3.39s/it, lr: 5.0e-05 loss: 2.366e-01]
leoprint:  47%|####7     | 1137/2400 [08:09<1:11:57,  3.42s/it, lr: 5.0e-05 loss: 2.366e-01]
leoprint:  47%|####7     | 1137/2400 [08:09<1:11:57,  3.42s/it, lr: 5.0e-05 loss: 2.366e-01]
leoprint:  47%|####7     | 1137/2400 [08:12<1:11:57,  3.42s/it, lr: 5.0e-05 loss: 2.288e-01]
leoprint:  47%|####7     | 1137/2400 [08:12<1:11:57,  3.42s/it, lr: 5.0e-05 loss: 2.288e-01]
leoprint:  47%|####7     | 1138/2400 [08:12<1:12:24,  3.44s/it, lr: 5.0e-05 loss: 2.288e-01]
leoprint:  47%|####7     | 1138/2400 [08:12<1:12:24,  3.44s/it, lr: 5.0e-05 loss: 2.288e-01]
leoprint:  47%|####7     | 1138/2400 [08:16<1:12:24,  3.44s/it, lr: 5.0e-05 loss: 2.445e-01]
leoprint:  47%|####7     | 1138/2400 [08:16<1:12:24,  3.44s/it, lr: 5.0e-05 loss: 2.445e-01]
leoprint:  47%|####7     | 1139/2400 [08:16<1:13:29,  3.50s/it, lr: 5.0e-05 loss: 2.445e-01]
leoprint:  47%|####7     | 1139/2400 [08:16<1:13:29,  3.50s/it, lr: 5.0e-05 loss: 2.445e-01]
leoprint:  47%|####7     | 1139/2400 [08:19<1:13:29,  3.50s/it, lr: 5.0e-05 loss: 3.194e-01]
leoprint:  47%|####7     | 1139/2400 [08:19<1:13:29,  3.50s/it, lr: 5.0e-05 loss: 3.194e-01]
leoprint:  48%|####7     | 1140/2400 [08:23<1:13:26,  3.50s/it, lr: 5.0e-05 loss: 2.376e-01]
leoprint:  48%|####7     | 1140/2400 [08:23<1:13:26,  3.50s/it, lr: 5.0e-05 loss: 2.376e-01]
leoprint:  48%|####7     | 1141/2400 [08:23<56:33,  2.70s/it, lr: 5.0e-05 loss: 2.376e-01]  
leoprint:  48%|####7     | 1141/2400 [08:23<56:33,  2.70s/it, lr: 5.0e-05 loss: 2.376e-01]  
leoprint:  48%|####7     | 1141/2400 [08:26<56:33,  2.70s/it, lr: 5.0e-05 loss: 2.601e-01]
leoprint:  48%|####7     | 1141/2400 [08:26<56:33,  2.70s/it, lr: 5.0e-05 loss: 2.601e-01]
leoprint:  48%|####7     | 1142/2400 [08:26<1:01:42,  2.94s/it, lr: 5.0e-05 loss: 2.601e-01]
leoprint:  48%|####7     | 1142/2400 [08:26<1:01:42,  2.94s/it, lr: 5.0e-05 loss: 2.601e-01]
leoprint:  48%|####7     | 1142/2400 [08:30<1:01:42,  2.94s/it, lr: 5.0e-05 loss: 3.545e-01]
leoprint:  48%|####7     | 1142/2400 [08:30<1:01:42,  2.94s/it, lr: 5.0e-05 loss: 3.545e-01]
leoprint:  48%|####7     | 1143/2400 [08:30<1:04:41,  3.09s/it, lr: 5.0e-05 loss: 3.545e-01]
leoprint:  48%|####7     | 1143/2400 [08:30<1:04:41,  3.09s/it, lr: 5.0e-05 loss: 3.545e-01]
leoprint:  48%|####7     | 1143/2400 [08:33<1:04:41,  3.09s/it, lr: 5.0e-05 loss: 3.302e-01]
leoprint:  48%|####7     | 1143/2400 [08:33<1:04:41,  3.09s/it, lr: 5.0e-05 loss: 3.302e-01]
leoprint:  48%|####7     | 1144/2400 [08:33<1:07:00,  3.20s/it, lr: 5.0e-05 loss: 3.302e-01]
leoprint:  48%|####7     | 1144/2400 [08:33<1:07:00,  3.20s/it, lr: 5.0e-05 loss: 3.302e-01]
leoprint:  48%|####7     | 1144/2400 [08:37<1:07:00,  3.20s/it, lr: 5.0e-05 loss: 2.824e-01]
leoprint:  48%|####7     | 1144/2400 [08:37<1:07:00,  3.20s/it, lr: 5.0e-05 loss: 2.824e-01]
leoprint:  48%|####7     | 1145/2400 [08:37<1:08:43,  3.29s/it, lr: 5.0e-05 loss: 2.824e-01]
leoprint:  48%|####7     | 1145/2400 [08:37<1:08:43,  3.29s/it, lr: 5.0e-05 loss: 2.824e-01]
leoprint:  48%|####7     | 1145/2400 [08:40<1:08:43,  3.29s/it, lr: 5.0e-05 loss: 3.028e-01]
leoprint:  48%|####7     | 1145/2400 [08:40<1:08:43,  3.29s/it, lr: 5.0e-05 loss: 3.028e-01]
leoprint:  48%|####7     | 1146/2400 [08:40<1:09:57,  3.35s/it, lr: 5.0e-05 loss: 3.028e-01]
leoprint:  48%|####7     | 1146/2400 [08:40<1:09:57,  3.35s/it, lr: 5.0e-05 loss: 3.028e-01]
leoprint:  48%|####7     | 1146/2400 [08:44<1:09:57,  3.35s/it, lr: 5.0e-05 loss: 1.954e-01]
leoprint:  48%|####7     | 1146/2400 [08:44<1:09:57,  3.35s/it, lr: 5.0e-05 loss: 1.954e-01]
leoprint:  48%|####7     | 1147/2400 [08:44<1:11:28,  3.42s/it, lr: 5.0e-05 loss: 1.954e-01]
leoprint:  48%|####7     | 1147/2400 [08:44<1:11:28,  3.42s/it, lr: 5.0e-05 loss: 1.954e-01]
leoprint:  48%|####7     | 1147/2400 [08:48<1:11:28,  3.42s/it, lr: 5.0e-05 loss: 2.142e-01]
leoprint:  48%|####7     | 1147/2400 [08:48<1:11:28,  3.42s/it, lr: 5.0e-05 loss: 2.142e-01]
leoprint:  48%|####7     | 1148/2400 [08:48<1:13:58,  3.54s/it, lr: 5.0e-05 loss: 2.142e-01]
leoprint:  48%|####7     | 1148/2400 [08:48<1:13:58,  3.54s/it, lr: 5.0e-05 loss: 2.142e-01]
leoprint:  48%|####7     | 1148/2400 [08:51<1:13:58,  3.54s/it, lr: 5.0e-05 loss: 2.519e-01]
leoprint:  48%|####7     | 1148/2400 [08:51<1:13:58,  3.54s/it, lr: 5.0e-05 loss: 2.519e-01]
leoprint:  48%|####7     | 1149/2400 [08:51<1:14:21,  3.57s/it, lr: 5.0e-05 loss: 2.519e-01]
leoprint:  48%|####7     | 1149/2400 [08:51<1:14:21,  3.57s/it, lr: 5.0e-05 loss: 2.519e-01]
leoprint:  48%|####7     | 1149/2400 [08:55<1:14:21,  3.57s/it, lr: 5.0e-05 loss: 3.066e-01]
leoprint:  48%|####7     | 1149/2400 [08:55<1:14:21,  3.57s/it, lr: 5.0e-05 loss: 3.066e-01]
leoprint:  48%|####7     | 1150/2400 [08:58<1:14:18,  3.57s/it, lr: 5.0e-05 loss: 2.702e-01]
leoprint:  48%|####7     | 1150/2400 [08:58<1:14:18,  3.57s/it, lr: 5.0e-05 loss: 2.702e-01]
leoprint:  48%|####7     | 1151/2400 [08:58<56:54,  2.73s/it, lr: 5.0e-05 loss: 2.702e-01]  
leoprint:  48%|####7     | 1151/2400 [08:58<56:54,  2.73s/it, lr: 5.0e-05 loss: 2.702e-01]  
leoprint:  48%|####7     | 1151/2400 [09:02<56:54,  2.73s/it, lr: 5.0e-05 loss: 2.170e-01]
leoprint:  48%|####7     | 1151/2400 [09:02<56:54,  2.73s/it, lr: 5.0e-05 loss: 2.170e-01]
leoprint:  48%|####8     | 1152/2400 [09:02<1:00:46,  2.92s/it, lr: 5.0e-05 loss: 2.170e-01]
leoprint:  48%|####8     | 1152/2400 [09:02<1:00:46,  2.92s/it, lr: 5.0e-05 loss: 2.170e-01]
leoprint:  48%|####8     | 1152/2400 [09:06<1:00:46,  2.92s/it, lr: 5.0e-05 loss: 2.371e-01]
leoprint:  48%|####8     | 1152/2400 [09:06<1:00:46,  2.92s/it, lr: 5.0e-05 loss: 2.371e-01]
leoprint:  48%|####8     | 1153/2400 [09:06<1:04:13,  3.09s/it, lr: 5.0e-05 loss: 2.371e-01]
leoprint:  48%|####8     | 1153/2400 [09:06<1:04:13,  3.09s/it, lr: 5.0e-05 loss: 2.371e-01]
leoprint:  48%|####8     | 1153/2400 [09:09<1:04:13,  3.09s/it, lr: 5.0e-05 loss: 2.146e-01]
leoprint:  48%|####8     | 1153/2400 [09:09<1:04:13,  3.09s/it, lr: 5.0e-05 loss: 2.146e-01]
leoprint:  48%|####8     | 1154/2400 [09:09<1:06:29,  3.20s/it, lr: 5.0e-05 loss: 2.146e-01]
leoprint:  48%|####8     | 1154/2400 [09:09<1:06:29,  3.20s/it, lr: 5.0e-05 loss: 2.146e-01]
leoprint:  48%|####8     | 1154/2400 [09:13<1:06:29,  3.20s/it, lr: 5.0e-05 loss: 3.373e-01]
leoprint:  48%|####8     | 1154/2400 [09:13<1:06:29,  3.20s/it, lr: 5.0e-05 loss: 3.373e-01]
leoprint:  48%|####8     | 1155/2400 [09:13<1:08:09,  3.28s/it, lr: 5.0e-05 loss: 3.373e-01]
leoprint:  48%|####8     | 1155/2400 [09:13<1:08:09,  3.28s/it, lr: 5.0e-05 loss: 3.373e-01]
leoprint:  48%|####8     | 1155/2400 [09:16<1:08:09,  3.28s/it, lr: 5.0e-05 loss: 3.000e-01]
leoprint:  48%|####8     | 1155/2400 [09:16<1:08:09,  3.28s/it, lr: 5.0e-05 loss: 3.000e-01]
leoprint:  48%|####8     | 1156/2400 [09:16<1:10:00,  3.38s/it, lr: 5.0e-05 loss: 3.000e-01]
leoprint:  48%|####8     | 1156/2400 [09:16<1:10:00,  3.38s/it, lr: 5.0e-05 loss: 3.000e-01]
leoprint:  48%|####8     | 1156/2400 [09:20<1:10:00,  3.38s/it, lr: 5.0e-05 loss: 2.530e-01]
leoprint:  48%|####8     | 1156/2400 [09:20<1:10:00,  3.38s/it, lr: 5.0e-05 loss: 2.530e-01]
leoprint:  48%|####8     | 1157/2400 [09:20<1:10:41,  3.41s/it, lr: 5.0e-05 loss: 2.530e-01]
leoprint:  48%|####8     | 1157/2400 [09:20<1:10:41,  3.41s/it, lr: 5.0e-05 loss: 2.530e-01]
leoprint:  48%|####8     | 1157/2400 [09:23<1:10:41,  3.41s/it, lr: 5.0e-05 loss: 2.363e-01]
leoprint:  48%|####8     | 1157/2400 [09:23<1:10:41,  3.41s/it, lr: 5.0e-05 loss: 2.363e-01]
leoprint:  48%|####8     | 1158/2400 [09:23<1:11:08,  3.44s/it, lr: 5.0e-05 loss: 2.363e-01]
leoprint:  48%|####8     | 1158/2400 [09:23<1:11:08,  3.44s/it, lr: 5.0e-05 loss: 2.363e-01]
leoprint:  48%|####8     | 1158/2400 [09:27<1:11:08,  3.44s/it, lr: 5.0e-05 loss: 2.482e-01]
leoprint:  48%|####8     | 1158/2400 [09:27<1:11:08,  3.44s/it, lr: 5.0e-05 loss: 2.482e-01]
leoprint:  48%|####8     | 1159/2400 [09:27<1:13:33,  3.56s/it, lr: 5.0e-05 loss: 2.482e-01]
leoprint:  48%|####8     | 1159/2400 [09:27<1:13:33,  3.56s/it, lr: 5.0e-05 loss: 2.482e-01]
leoprint:  48%|####8     | 1159/2400 [09:31<1:13:33,  3.56s/it, lr: 5.0e-05 loss: 2.972e-01]
leoprint:  48%|####8     | 1159/2400 [09:31<1:13:33,  3.56s/it, lr: 5.0e-05 loss: 2.972e-01]
leoprint:  48%|####8     | 1160/2400 [09:34<1:13:29,  3.56s/it, lr: 5.0e-05 loss: 3.547e-01]
leoprint:  48%|####8     | 1160/2400 [09:34<1:13:29,  3.56s/it, lr: 5.0e-05 loss: 3.547e-01]
leoprint:  48%|####8     | 1161/2400 [09:34<56:22,  2.73s/it, lr: 5.0e-05 loss: 3.547e-01]  
leoprint:  48%|####8     | 1161/2400 [09:34<56:22,  2.73s/it, lr: 5.0e-05 loss: 3.547e-01]  
leoprint:  48%|####8     | 1161/2400 [09:38<56:22,  2.73s/it, lr: 5.0e-05 loss: 3.689e-01]
leoprint:  48%|####8     | 1161/2400 [09:38<56:22,  2.73s/it, lr: 5.0e-05 loss: 3.689e-01]
leoprint:  48%|####8     | 1162/2400 [09:38<1:00:12,  2.92s/it, lr: 5.0e-05 loss: 3.689e-01]
leoprint:  48%|####8     | 1162/2400 [09:38<1:00:12,  2.92s/it, lr: 5.0e-05 loss: 3.689e-01]
leoprint:  48%|####8     | 1162/2400 [09:41<1:00:12,  2.92s/it, lr: 5.0e-05 loss: 3.928e-01]
leoprint:  48%|####8     | 1162/2400 [09:41<1:00:12,  2.92s/it, lr: 5.0e-05 loss: 3.928e-01]
leoprint:  48%|####8     | 1163/2400 [09:41<1:03:15,  3.07s/it, lr: 5.0e-05 loss: 3.928e-01]
leoprint:  48%|####8     | 1163/2400 [09:41<1:03:15,  3.07s/it, lr: 5.0e-05 loss: 3.928e-01]
leoprint:  48%|####8     | 1163/2400 [09:45<1:03:15,  3.07s/it, lr: 5.0e-05 loss: 2.596e-01]
leoprint:  48%|####8     | 1163/2400 [09:45<1:03:15,  3.07s/it, lr: 5.0e-05 loss: 2.596e-01]
leoprint:  48%|####8     | 1164/2400 [09:45<1:06:39,  3.24s/it, lr: 5.0e-05 loss: 2.596e-01]
leoprint:  48%|####8     | 1164/2400 [09:45<1:06:39,  3.24s/it, lr: 5.0e-05 loss: 2.596e-01]
leoprint:  48%|####8     | 1164/2400 [09:48<1:06:39,  3.24s/it, lr: 5.0e-05 loss: 3.862e-01]
leoprint:  48%|####8     | 1164/2400 [09:48<1:06:39,  3.24s/it, lr: 5.0e-05 loss: 3.862e-01]
leoprint:  49%|####8     | 1165/2400 [09:48<1:08:08,  3.31s/it, lr: 5.0e-05 loss: 3.862e-01]
leoprint:  49%|####8     | 1165/2400 [09:48<1:08:08,  3.31s/it, lr: 5.0e-05 loss: 3.862e-01]
leoprint:  49%|####8     | 1165/2400 [09:52<1:08:08,  3.31s/it, lr: 5.0e-05 loss: 2.584e-01]
leoprint:  49%|####8     | 1165/2400 [09:52<1:08:08,  3.31s/it, lr: 5.0e-05 loss: 2.584e-01]
leoprint:  49%|####8     | 1166/2400 [09:52<1:09:09,  3.36s/it, lr: 5.0e-05 loss: 2.584e-01]
leoprint:  49%|####8     | 1166/2400 [09:52<1:09:09,  3.36s/it, lr: 5.0e-05 loss: 2.584e-01]
leoprint:  49%|####8     | 1166/2400 [09:55<1:09:09,  3.36s/it, lr: 5.0e-05 loss: 3.612e-01]
leoprint:  49%|####8     | 1166/2400 [09:55<1:09:09,  3.36s/it, lr: 5.0e-05 loss: 3.612e-01]
leoprint:  49%|####8     | 1167/2400 [09:55<1:09:56,  3.40s/it, lr: 5.0e-05 loss: 3.612e-01]
leoprint:  49%|####8     | 1167/2400 [09:55<1:09:56,  3.40s/it, lr: 5.0e-05 loss: 3.612e-01]
leoprint:  49%|####8     | 1167/2400 [09:59<1:09:56,  3.40s/it, lr: 5.0e-05 loss: 3.710e-01]
leoprint:  49%|####8     | 1167/2400 [09:59<1:09:56,  3.40s/it, lr: 5.0e-05 loss: 3.710e-01]
leoprint:  49%|####8     | 1168/2400 [09:59<1:10:26,  3.43s/it, lr: 5.0e-05 loss: 3.710e-01]
leoprint:  49%|####8     | 1168/2400 [09:59<1:10:26,  3.43s/it, lr: 5.0e-05 loss: 3.710e-01]
leoprint:  49%|####8     | 1168/2400 [10:02<1:10:26,  3.43s/it, lr: 5.0e-05 loss: 2.503e-01]
leoprint:  49%|####8     | 1168/2400 [10:02<1:10:26,  3.43s/it, lr: 5.0e-05 loss: 2.503e-01]
leoprint:  49%|####8     | 1169/2400 [10:02<1:11:34,  3.49s/it, lr: 5.0e-05 loss: 2.503e-01]
leoprint:  49%|####8     | 1169/2400 [10:02<1:11:34,  3.49s/it, lr: 5.0e-05 loss: 2.503e-01]
leoprint:  49%|####8     | 1169/2400 [10:06<1:11:34,  3.49s/it, lr: 5.0e-05 loss: 3.771e-01]
leoprint:  49%|####8     | 1169/2400 [10:06<1:11:34,  3.49s/it, lr: 5.0e-05 loss: 3.771e-01]
leoprint:  49%|####8     | 1170/2400 [10:10<1:11:30,  3.49s/it, lr: 5.0e-05 loss: 2.014e-01]
leoprint:  49%|####8     | 1170/2400 [10:10<1:11:30,  3.49s/it, lr: 5.0e-05 loss: 2.014e-01]
leoprint:  49%|####8     | 1171/2400 [10:10<55:43,  2.72s/it, lr: 5.0e-05 loss: 2.014e-01]  
leoprint:  49%|####8     | 1171/2400 [10:10<55:43,  2.72s/it, lr: 5.0e-05 loss: 2.014e-01]  
leoprint:  49%|####8     | 1171/2400 [10:13<55:43,  2.72s/it, lr: 5.0e-05 loss: 2.919e-01]
leoprint:  49%|####8     | 1171/2400 [10:13<55:43,  2.72s/it, lr: 5.0e-05 loss: 2.919e-01]
leoprint:  49%|####8     | 1172/2400 [10:13<59:34,  2.91s/it, lr: 5.0e-05 loss: 2.919e-01]
leoprint:  49%|####8     | 1172/2400 [10:13<59:34,  2.91s/it, lr: 5.0e-05 loss: 2.919e-01]
leoprint:  49%|####8     | 1172/2400 [10:17<59:34,  2.91s/it, lr: 5.0e-05 loss: 3.122e-01]
leoprint:  49%|####8     | 1172/2400 [10:17<59:34,  2.91s/it, lr: 5.0e-05 loss: 3.122e-01]
leoprint:  49%|####8     | 1173/2400 [10:17<1:02:38,  3.06s/it, lr: 5.0e-05 loss: 3.122e-01]
leoprint:  49%|####8     | 1173/2400 [10:17<1:02:38,  3.06s/it, lr: 5.0e-05 loss: 3.122e-01]
leoprint:  49%|####8     | 1173/2400 [10:20<1:02:38,  3.06s/it, lr: 5.0e-05 loss: 2.836e-01]
leoprint:  49%|####8     | 1173/2400 [10:20<1:02:38,  3.06s/it, lr: 5.0e-05 loss: 2.836e-01]
leoprint:  49%|####8     | 1174/2400 [10:20<1:05:00,  3.18s/it, lr: 5.0e-05 loss: 2.836e-01]
leoprint:  49%|####8     | 1174/2400 [10:20<1:05:00,  3.18s/it, lr: 5.0e-05 loss: 2.836e-01]
leoprint:  49%|####8     | 1174/2400 [10:24<1:05:00,  3.18s/it, lr: 5.0e-05 loss: 2.544e-01]
leoprint:  49%|####8     | 1174/2400 [10:24<1:05:00,  3.18s/it, lr: 5.0e-05 loss: 2.544e-01]
leoprint:  49%|####8     | 1175/2400 [10:24<1:07:23,  3.30s/it, lr: 5.0e-05 loss: 2.544e-01]
leoprint:  49%|####8     | 1175/2400 [10:24<1:07:23,  3.30s/it, lr: 5.0e-05 loss: 2.544e-01]
leoprint:  49%|####8     | 1175/2400 [10:28<1:07:23,  3.30s/it, lr: 5.0e-05 loss: 3.157e-01]
leoprint:  49%|####8     | 1175/2400 [10:28<1:07:23,  3.30s/it, lr: 5.0e-05 loss: 3.157e-01]
leoprint:  49%|####9     | 1176/2400 [10:28<1:09:47,  3.42s/it, lr: 5.0e-05 loss: 3.157e-01]
leoprint:  49%|####9     | 1176/2400 [10:28<1:09:47,  3.42s/it, lr: 5.0e-05 loss: 3.157e-01]
leoprint:  49%|####9     | 1176/2400 [10:31<1:09:47,  3.42s/it, lr: 5.0e-05 loss: 2.707e-01]
leoprint:  49%|####9     | 1176/2400 [10:31<1:09:47,  3.42s/it, lr: 5.0e-05 loss: 2.707e-01]
leoprint:  49%|####9     | 1177/2400 [10:31<1:10:12,  3.44s/it, lr: 5.0e-05 loss: 2.707e-01]
leoprint:  49%|####9     | 1177/2400 [10:31<1:10:12,  3.44s/it, lr: 5.0e-05 loss: 2.707e-01]
leoprint:  49%|####9     | 1177/2400 [10:35<1:10:12,  3.44s/it, lr: 5.0e-05 loss: 3.167e-01]
leoprint:  49%|####9     | 1177/2400 [10:35<1:10:12,  3.44s/it, lr: 5.0e-05 loss: 3.167e-01]
leoprint:  49%|####9     | 1178/2400 [10:35<1:11:09,  3.49s/it, lr: 5.0e-05 loss: 3.167e-01]
leoprint:  49%|####9     | 1178/2400 [10:35<1:11:09,  3.49s/it, lr: 5.0e-05 loss: 3.167e-01]
leoprint:  49%|####9     | 1178/2400 [10:38<1:11:09,  3.49s/it, lr: 5.0e-05 loss: 3.243e-01]
leoprint:  49%|####9     | 1178/2400 [10:38<1:11:09,  3.49s/it, lr: 5.0e-05 loss: 3.243e-01]
leoprint:  49%|####9     | 1179/2400 [10:38<1:11:07,  3.50s/it, lr: 5.0e-05 loss: 3.243e-01]
leoprint:  49%|####9     | 1179/2400 [10:38<1:11:07,  3.50s/it, lr: 5.0e-05 loss: 3.243e-01]
leoprint:  49%|####9     | 1179/2400 [10:42<1:11:07,  3.50s/it, lr: 5.0e-05 loss: 3.131e-01]
leoprint:  49%|####9     | 1179/2400 [10:42<1:11:07,  3.50s/it, lr: 5.0e-05 loss: 3.131e-01]
leoprint:  49%|####9     | 1180/2400 [10:45<1:11:04,  3.50s/it, lr: 5.0e-05 loss: 3.060e-01]
leoprint:  49%|####9     | 1180/2400 [10:45<1:11:04,  3.50s/it, lr: 5.0e-05 loss: 3.060e-01]
leoprint:  49%|####9     | 1181/2400 [10:45<55:09,  2.71s/it, lr: 5.0e-05 loss: 3.060e-01]  
leoprint:  49%|####9     | 1181/2400 [10:45<55:09,  2.71s/it, lr: 5.0e-05 loss: 3.060e-01]  
leoprint:  49%|####9     | 1181/2400 [10:49<55:09,  2.71s/it, lr: 5.0e-05 loss: 3.476e-01]
leoprint:  49%|####9     | 1181/2400 [10:49<55:09,  2.71s/it, lr: 5.0e-05 loss: 3.476e-01]
leoprint:  49%|####9     | 1182/2400 [10:49<59:02,  2.91s/it, lr: 5.0e-05 loss: 3.476e-01]
leoprint:  49%|####9     | 1182/2400 [10:49<59:02,  2.91s/it, lr: 5.0e-05 loss: 3.476e-01]
leoprint:  49%|####9     | 1182/2400 [10:52<59:02,  2.91s/it, lr: 5.0e-05 loss: 3.002e-01]
leoprint:  49%|####9     | 1182/2400 [10:52<59:02,  2.91s/it, lr: 5.0e-05 loss: 3.002e-01]
leoprint:  49%|####9     | 1183/2400 [10:52<1:02:06,  3.06s/it, lr: 5.0e-05 loss: 3.002e-01]
leoprint:  49%|####9     | 1183/2400 [10:52<1:02:06,  3.06s/it, lr: 5.0e-05 loss: 3.002e-01]
leoprint:  49%|####9     | 1183/2400 [10:56<1:02:06,  3.06s/it, lr: 5.0e-05 loss: 3.601e-01]
leoprint:  49%|####9     | 1183/2400 [10:56<1:02:06,  3.06s/it, lr: 5.0e-05 loss: 3.601e-01]
leoprint:  49%|####9     | 1184/2400 [10:56<1:04:28,  3.18s/it, lr: 5.0e-05 loss: 3.601e-01]
leoprint:  49%|####9     | 1184/2400 [10:56<1:04:28,  3.18s/it, lr: 5.0e-05 loss: 3.601e-01]
leoprint:  49%|####9     | 1184/2400 [10:59<1:04:28,  3.18s/it, lr: 5.0e-05 loss: 2.051e-01]
leoprint:  49%|####9     | 1184/2400 [10:59<1:04:28,  3.18s/it, lr: 5.0e-05 loss: 2.051e-01]
leoprint:  49%|####9     | 1185/2400 [10:59<1:06:12,  3.27s/it, lr: 5.0e-05 loss: 2.051e-01]
leoprint:  49%|####9     | 1185/2400 [10:59<1:06:12,  3.27s/it, lr: 5.0e-05 loss: 2.051e-01]
leoprint:  49%|####9     | 1185/2400 [11:03<1:06:12,  3.27s/it, lr: 5.0e-05 loss: 2.642e-01]
leoprint:  49%|####9     | 1185/2400 [11:03<1:06:12,  3.27s/it, lr: 5.0e-05 loss: 2.642e-01]
leoprint:  49%|####9     | 1186/2400 [11:03<1:08:12,  3.37s/it, lr: 5.0e-05 loss: 2.642e-01]
leoprint:  49%|####9     | 1186/2400 [11:03<1:08:12,  3.37s/it, lr: 5.0e-05 loss: 2.642e-01]
leoprint:  49%|####9     | 1186/2400 [11:07<1:08:12,  3.37s/it, lr: 5.0e-05 loss: 4.178e-01]
leoprint:  49%|####9     | 1186/2400 [11:07<1:08:12,  3.37s/it, lr: 5.0e-05 loss: 4.178e-01]
leoprint:  49%|####9     | 1187/2400 [11:07<1:09:52,  3.46s/it, lr: 5.0e-05 loss: 4.178e-01]
leoprint:  49%|####9     | 1187/2400 [11:07<1:09:52,  3.46s/it, lr: 5.0e-05 loss: 4.178e-01]
leoprint:  49%|####9     | 1187/2400 [11:10<1:09:52,  3.46s/it, lr: 5.0e-05 loss: 2.618e-01]
leoprint:  49%|####9     | 1187/2400 [11:10<1:09:52,  3.46s/it, lr: 5.0e-05 loss: 2.618e-01]
leoprint:  50%|####9     | 1188/2400 [11:10<1:10:48,  3.51s/it, lr: 5.0e-05 loss: 2.618e-01]
leoprint:  50%|####9     | 1188/2400 [11:10<1:10:48,  3.51s/it, lr: 5.0e-05 loss: 2.618e-01]
leoprint:  50%|####9     | 1188/2400 [11:14<1:10:48,  3.51s/it, lr: 5.0e-05 loss: 2.291e-01]
leoprint:  50%|####9     | 1188/2400 [11:14<1:10:48,  3.51s/it, lr: 5.0e-05 loss: 2.291e-01]
leoprint:  50%|####9     | 1189/2400 [11:14<1:11:25,  3.54s/it, lr: 5.0e-05 loss: 2.291e-01]
leoprint:  50%|####9     | 1189/2400 [11:14<1:11:25,  3.54s/it, lr: 5.0e-05 loss: 2.291e-01]
leoprint:  50%|####9     | 1189/2400 [11:17<1:11:25,  3.54s/it, lr: 5.0e-05 loss: 2.902e-01]
leoprint:  50%|####9     | 1189/2400 [11:17<1:11:25,  3.54s/it, lr: 5.0e-05 loss: 2.902e-01]
leoprint:  50%|####9     | 1190/2400 [11:21<1:11:22,  3.54s/it, lr: 5.0e-05 loss: 3.081e-01]
leoprint:  50%|####9     | 1190/2400 [11:21<1:11:22,  3.54s/it, lr: 5.0e-05 loss: 3.081e-01]
leoprint:  50%|####9     | 1191/2400 [11:21<54:50,  2.72s/it, lr: 5.0e-05 loss: 3.081e-01]  
leoprint:  50%|####9     | 1191/2400 [11:21<54:50,  2.72s/it, lr: 5.0e-05 loss: 3.081e-01]  
leoprint:  50%|####9     | 1191/2400 [11:25<54:50,  2.72s/it, lr: 5.0e-05 loss: 1.940e-01]
leoprint:  50%|####9     | 1191/2400 [11:25<54:50,  2.72s/it, lr: 5.0e-05 loss: 1.940e-01]
leoprint:  50%|####9     | 1192/2400 [11:25<59:16,  2.94s/it, lr: 5.0e-05 loss: 1.940e-01]
leoprint:  50%|####9     | 1192/2400 [11:25<59:16,  2.94s/it, lr: 5.0e-05 loss: 1.940e-01]
leoprint:  50%|####9     | 1192/2400 [11:28<59:16,  2.94s/it, lr: 5.0e-05 loss: 2.243e-01]
leoprint:  50%|####9     | 1192/2400 [11:28<59:16,  2.94s/it, lr: 5.0e-05 loss: 2.243e-01]
leoprint:  50%|####9     | 1193/2400 [11:28<1:02:36,  3.11s/it, lr: 5.0e-05 loss: 2.243e-01]
leoprint:  50%|####9     | 1193/2400 [11:28<1:02:36,  3.11s/it, lr: 5.0e-05 loss: 2.243e-01]
leoprint:  50%|####9     | 1193/2400 [11:32<1:02:36,  3.11s/it, lr: 5.0e-05 loss: 2.589e-01]
leoprint:  50%|####9     | 1193/2400 [11:32<1:02:36,  3.11s/it, lr: 5.0e-05 loss: 2.589e-01]
leoprint:  50%|####9     | 1194/2400 [11:32<1:04:42,  3.22s/it, lr: 5.0e-05 loss: 2.589e-01]
leoprint:  50%|####9     | 1194/2400 [11:32<1:04:42,  3.22s/it, lr: 5.0e-05 loss: 2.589e-01]
leoprint:  50%|####9     | 1194/2400 [11:35<1:04:42,  3.22s/it, lr: 5.0e-05 loss: 2.955e-01]
leoprint:  50%|####9     | 1194/2400 [11:35<1:04:42,  3.22s/it, lr: 5.0e-05 loss: 2.955e-01]
leoprint:  50%|####9     | 1195/2400 [11:35<1:06:12,  3.30s/it, lr: 5.0e-05 loss: 2.955e-01]
leoprint:  50%|####9     | 1195/2400 [11:35<1:06:12,  3.30s/it, lr: 5.0e-05 loss: 2.955e-01]
leoprint:  50%|####9     | 1195/2400 [11:39<1:06:12,  3.30s/it, lr: 5.0e-05 loss: 2.974e-01]
leoprint:  50%|####9     | 1195/2400 [11:39<1:06:12,  3.30s/it, lr: 5.0e-05 loss: 2.974e-01]
leoprint:  50%|####9     | 1196/2400 [11:39<1:07:19,  3.35s/it, lr: 5.0e-05 loss: 2.974e-01]
leoprint:  50%|####9     | 1196/2400 [11:39<1:07:19,  3.35s/it, lr: 5.0e-05 loss: 2.974e-01]
leoprint:  50%|####9     | 1196/2400 [11:42<1:07:19,  3.35s/it, lr: 5.0e-05 loss: 2.900e-01]
leoprint:  50%|####9     | 1196/2400 [11:42<1:07:19,  3.35s/it, lr: 5.0e-05 loss: 2.900e-01]
leoprint:  50%|####9     | 1197/2400 [11:42<1:08:06,  3.40s/it, lr: 5.0e-05 loss: 2.900e-01]
leoprint:  50%|####9     | 1197/2400 [11:42<1:08:06,  3.40s/it, lr: 5.0e-05 loss: 2.900e-01]
leoprint:  50%|####9     | 1197/2400 [11:46<1:08:06,  3.40s/it, lr: 5.0e-05 loss: 3.938e-01]
leoprint:  50%|####9     | 1197/2400 [11:46<1:08:06,  3.40s/it, lr: 5.0e-05 loss: 3.938e-01]
leoprint:  50%|####9     | 1198/2400 [11:46<1:08:38,  3.43s/it, lr: 5.0e-05 loss: 3.938e-01]
leoprint:  50%|####9     | 1198/2400 [11:46<1:08:38,  3.43s/it, lr: 5.0e-05 loss: 3.938e-01]
leoprint:  50%|####9     | 1198/2400 [11:50<1:08:38,  3.43s/it, lr: 5.0e-05 loss: 2.467e-01]
leoprint:  50%|####9     | 1198/2400 [11:50<1:08:38,  3.43s/it, lr: 5.0e-05 loss: 2.467e-01]
leoprint:  50%|####9     | 1199/2400 [11:50<1:11:02,  3.55s/it, lr: 5.0e-05 loss: 2.467e-01]
leoprint:  50%|####9     | 1199/2400 [11:50<1:11:02,  3.55s/it, lr: 5.0e-05 loss: 2.467e-01]
leoprint:  50%|####9     | 1199/2400 [11:53<1:11:02,  3.55s/it, lr: 5.0e-05 loss: 3.160e-01]
leoprint:  50%|####9     | 1199/2400 [11:53<1:11:02,  3.55s/it, lr: 5.0e-05 loss: 3.160e-01]
+
+
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
+
+
Generating Images:  20%|##        | 1/5 [00:14<00:57, 14.41s/it]
Generating Images:  20%|##        | 1/5 [00:14<00:57, 14.41s/it]
+
+
Generating Images:  40%|####      | 2/5 [00:28<00:43, 14.39s/it]
Generating Images:  40%|####      | 2/5 [00:28<00:43, 14.39s/it]
+
+
Generating Images:  60%|######    | 3/5 [00:43<00:28, 14.39s/it]
Generating Images:  60%|######    | 3/5 [00:43<00:28, 14.39s/it]
+
+
Generating Images:  80%|########  | 4/5 [00:57<00:14, 14.38s/it]
Generating Images:  80%|########  | 4/5 [00:57<00:14, 14.38s/it]
+
+
Generating Images: 100%|##########| 5/5 [01:11<00:00, 14.38s/it]
Generating Images: 100%|##########| 5/5 [01:11<00:00, 14.38s/it]
+
+
                                                                
                                                                
+Saving at step 1200
+Saved checkpoint to /app/ai-toolkit/output/leoprint/leoprint_000001200.safetensors
+Saved optimizer to /app/ai-toolkit/output/leoprint/optimizer.pt
+
leoprint:  50%|#####     | 1200/2400 [11:57<1:10:58,  3.55s/it, lr: 5.0e-05 loss: 2.698e-01]
leoprint:  50%|#####     | 1200/2400 [11:57<1:10:58,  3.55s/it, lr: 5.0e-05 loss: 2.698e-01]
leoprint:  50%|#####     | 1201/2400 [11:57<55:45,  2.79s/it, lr: 5.0e-05 loss: 2.698e-01]  
leoprint:  50%|#####     | 1201/2400 [11:57<55:45,  2.79s/it, lr: 5.0e-05 loss: 2.698e-01]  
leoprint:  50%|#####     | 1201/2400 [12:00<55:45,  2.79s/it, lr: 5.0e-05 loss: 4.107e-01]
leoprint:  50%|#####     | 1201/2400 [12:00<55:45,  2.79s/it, lr: 5.0e-05 loss: 4.107e-01]
leoprint:  50%|#####     | 1202/2400 [12:00<59:05,  2.96s/it, lr: 5.0e-05 loss: 4.107e-01]
leoprint:  50%|#####     | 1202/2400 [12:00<59:05,  2.96s/it, lr: 5.0e-05 loss: 4.107e-01]
leoprint:  50%|#####     | 1202/2400 [12:04<59:05,  2.96s/it, lr: 5.0e-05 loss: 2.732e-01]
leoprint:  50%|#####     | 1202/2400 [12:04<59:05,  2.96s/it, lr: 5.0e-05 loss: 2.732e-01]
leoprint:  50%|#####     | 1203/2400 [12:04<1:01:46,  3.10s/it, lr: 5.0e-05 loss: 2.732e-01]
leoprint:  50%|#####     | 1203/2400 [12:04<1:01:46,  3.10s/it, lr: 5.0e-05 loss: 2.732e-01]
leoprint:  50%|#####     | 1203/2400 [12:07<1:01:46,  3.10s/it, lr: 5.0e-05 loss: 3.482e-01]
leoprint:  50%|#####     | 1203/2400 [12:07<1:01:46,  3.10s/it, lr: 5.0e-05 loss: 3.482e-01]
leoprint:  50%|#####     | 1204/2400 [12:07<1:03:51,  3.20s/it, lr: 5.0e-05 loss: 3.482e-01]
leoprint:  50%|#####     | 1204/2400 [12:07<1:03:51,  3.20s/it, lr: 5.0e-05 loss: 3.482e-01]
leoprint:  50%|#####     | 1204/2400 [12:11<1:03:51,  3.20s/it, lr: 5.0e-05 loss: 3.020e-01]
leoprint:  50%|#####     | 1204/2400 [12:11<1:03:51,  3.20s/it, lr: 5.0e-05 loss: 3.020e-01]
leoprint:  50%|#####     | 1205/2400 [12:11<1:05:25,  3.28s/it, lr: 5.0e-05 loss: 3.020e-01]
leoprint:  50%|#####     | 1205/2400 [12:11<1:05:25,  3.28s/it, lr: 5.0e-05 loss: 3.020e-01]
leoprint:  50%|#####     | 1205/2400 [12:14<1:05:25,  3.28s/it, lr: 5.0e-05 loss: 3.974e-01]
leoprint:  50%|#####     | 1205/2400 [12:14<1:05:25,  3.28s/it, lr: 5.0e-05 loss: 3.974e-01]
leoprint:  50%|#####     | 1206/2400 [12:14<1:06:59,  3.37s/it, lr: 5.0e-05 loss: 3.974e-01]
leoprint:  50%|#####     | 1206/2400 [12:14<1:06:59,  3.37s/it, lr: 5.0e-05 loss: 3.974e-01]
leoprint:  50%|#####     | 1206/2400 [12:18<1:06:59,  3.37s/it, lr: 5.0e-05 loss: 3.242e-01]
leoprint:  50%|#####     | 1206/2400 [12:18<1:06:59,  3.37s/it, lr: 5.0e-05 loss: 3.242e-01]
leoprint:  50%|#####     | 1207/2400 [12:18<1:07:42,  3.40s/it, lr: 5.0e-05 loss: 3.242e-01]
leoprint:  50%|#####     | 1207/2400 [12:18<1:07:42,  3.40s/it, lr: 5.0e-05 loss: 3.242e-01]
leoprint:  50%|#####     | 1207/2400 [12:21<1:07:42,  3.40s/it, lr: 5.0e-05 loss: 1.936e-01]
leoprint:  50%|#####     | 1207/2400 [12:21<1:07:42,  3.40s/it, lr: 5.0e-05 loss: 1.936e-01]
leoprint:  50%|#####     | 1208/2400 [12:22<1:08:50,  3.46s/it, lr: 5.0e-05 loss: 1.936e-01]
leoprint:  50%|#####     | 1208/2400 [12:22<1:08:50,  3.46s/it, lr: 5.0e-05 loss: 1.936e-01]
leoprint:  50%|#####     | 1208/2400 [12:25<1:08:50,  3.46s/it, lr: 5.0e-05 loss: 3.824e-01]
leoprint:  50%|#####     | 1208/2400 [12:25<1:08:50,  3.46s/it, lr: 5.0e-05 loss: 3.824e-01]
leoprint:  50%|#####     | 1209/2400 [12:25<1:09:00,  3.48s/it, lr: 5.0e-05 loss: 3.824e-01]
leoprint:  50%|#####     | 1209/2400 [12:25<1:09:00,  3.48s/it, lr: 5.0e-05 loss: 3.824e-01]
leoprint:  50%|#####     | 1209/2400 [12:29<1:09:00,  3.48s/it, lr: 5.0e-05 loss: 3.230e-01]
leoprint:  50%|#####     | 1209/2400 [12:29<1:09:00,  3.48s/it, lr: 5.0e-05 loss: 3.230e-01]
leoprint:  50%|#####     | 1210/2400 [12:32<1:08:57,  3.48s/it, lr: 5.0e-05 loss: 3.259e-01]
leoprint:  50%|#####     | 1210/2400 [12:32<1:08:57,  3.48s/it, lr: 5.0e-05 loss: 3.259e-01]
leoprint:  50%|#####     | 1211/2400 [12:32<53:16,  2.69s/it, lr: 5.0e-05 loss: 3.259e-01]  
leoprint:  50%|#####     | 1211/2400 [12:32<53:16,  2.69s/it, lr: 5.0e-05 loss: 3.259e-01]  
leoprint:  50%|#####     | 1211/2400 [12:36<53:16,  2.69s/it, lr: 5.0e-05 loss: 2.165e-01]
leoprint:  50%|#####     | 1211/2400 [12:36<53:16,  2.69s/it, lr: 5.0e-05 loss: 2.165e-01]
leoprint:  50%|#####     | 1212/2400 [12:36<58:52,  2.97s/it, lr: 5.0e-05 loss: 2.165e-01]
leoprint:  50%|#####     | 1212/2400 [12:36<58:52,  2.97s/it, lr: 5.0e-05 loss: 2.165e-01]
leoprint:  50%|#####     | 1212/2400 [12:39<58:52,  2.97s/it, lr: 5.0e-05 loss: 3.043e-01]
leoprint:  50%|#####     | 1212/2400 [12:39<58:52,  2.97s/it, lr: 5.0e-05 loss: 3.043e-01]
leoprint:  51%|#####     | 1213/2400 [12:39<1:01:30,  3.11s/it, lr: 5.0e-05 loss: 3.043e-01]
leoprint:  51%|#####     | 1213/2400 [12:39<1:01:30,  3.11s/it, lr: 5.0e-05 loss: 3.043e-01]
leoprint:  51%|#####     | 1213/2400 [12:43<1:01:30,  3.11s/it, lr: 5.0e-05 loss: 2.880e-01]
leoprint:  51%|#####     | 1213/2400 [12:43<1:01:30,  3.11s/it, lr: 5.0e-05 loss: 2.880e-01]
leoprint:  51%|#####     | 1214/2400 [12:43<1:04:11,  3.25s/it, lr: 5.0e-05 loss: 2.880e-01]
leoprint:  51%|#####     | 1214/2400 [12:43<1:04:11,  3.25s/it, lr: 5.0e-05 loss: 2.880e-01]
leoprint:  51%|#####     | 1214/2400 [12:47<1:04:11,  3.25s/it, lr: 5.0e-05 loss: 2.004e-01]
leoprint:  51%|#####     | 1214/2400 [12:47<1:04:11,  3.25s/it, lr: 5.0e-05 loss: 2.004e-01]
leoprint:  51%|#####     | 1215/2400 [12:47<1:06:07,  3.35s/it, lr: 5.0e-05 loss: 2.004e-01]
leoprint:  51%|#####     | 1215/2400 [12:47<1:06:07,  3.35s/it, lr: 5.0e-05 loss: 2.004e-01]
leoprint:  51%|#####     | 1215/2400 [12:50<1:06:07,  3.35s/it, lr: 5.0e-05 loss: 2.066e-01]
leoprint:  51%|#####     | 1215/2400 [12:50<1:06:07,  3.35s/it, lr: 5.0e-05 loss: 2.066e-01]
leoprint:  51%|#####     | 1216/2400 [12:50<1:06:57,  3.39s/it, lr: 5.0e-05 loss: 2.066e-01]
leoprint:  51%|#####     | 1216/2400 [12:50<1:06:57,  3.39s/it, lr: 5.0e-05 loss: 2.066e-01]
leoprint:  51%|#####     | 1216/2400 [12:54<1:06:57,  3.39s/it, lr: 5.0e-05 loss: 3.199e-01]
leoprint:  51%|#####     | 1216/2400 [12:54<1:06:57,  3.39s/it, lr: 5.0e-05 loss: 3.199e-01]
leoprint:  51%|#####     | 1217/2400 [12:54<1:08:17,  3.46s/it, lr: 5.0e-05 loss: 3.199e-01]
leoprint:  51%|#####     | 1217/2400 [12:54<1:08:17,  3.46s/it, lr: 5.0e-05 loss: 3.199e-01]
leoprint:  51%|#####     | 1217/2400 [12:57<1:08:17,  3.46s/it, lr: 5.0e-05 loss: 3.808e-01]
leoprint:  51%|#####     | 1217/2400 [12:57<1:08:17,  3.46s/it, lr: 5.0e-05 loss: 3.808e-01]
leoprint:  51%|#####     | 1218/2400 [12:57<1:09:09,  3.51s/it, lr: 5.0e-05 loss: 3.808e-01]
leoprint:  51%|#####     | 1218/2400 [12:57<1:09:09,  3.51s/it, lr: 5.0e-05 loss: 3.808e-01]
leoprint:  51%|#####     | 1218/2400 [13:01<1:09:09,  3.51s/it, lr: 5.0e-05 loss: 3.028e-01]
leoprint:  51%|#####     | 1218/2400 [13:01<1:09:09,  3.51s/it, lr: 5.0e-05 loss: 3.028e-01]
leoprint:  51%|#####     | 1219/2400 [13:01<1:09:02,  3.51s/it, lr: 5.0e-05 loss: 3.028e-01]
leoprint:  51%|#####     | 1219/2400 [13:01<1:09:02,  3.51s/it, lr: 5.0e-05 loss: 3.028e-01]
leoprint:  51%|#####     | 1219/2400 [13:05<1:09:02,  3.51s/it, lr: 5.0e-05 loss: 3.781e-01]
leoprint:  51%|#####     | 1219/2400 [13:05<1:09:02,  3.51s/it, lr: 5.0e-05 loss: 3.781e-01]
leoprint:  51%|#####     | 1220/2400 [13:08<1:08:59,  3.51s/it, lr: 5.0e-05 loss: 2.371e-01]
leoprint:  51%|#####     | 1220/2400 [13:08<1:08:59,  3.51s/it, lr: 5.0e-05 loss: 2.371e-01]
leoprint:  51%|#####     | 1221/2400 [13:08<53:40,  2.73s/it, lr: 5.0e-05 loss: 2.371e-01]  
leoprint:  51%|#####     | 1221/2400 [13:08<53:40,  2.73s/it, lr: 5.0e-05 loss: 2.371e-01]  
leoprint:  51%|#####     | 1221/2400 [13:12<53:40,  2.73s/it, lr: 5.0e-05 loss: 2.857e-01]
leoprint:  51%|#####     | 1221/2400 [13:12<53:40,  2.73s/it, lr: 5.0e-05 loss: 2.857e-01]
leoprint:  51%|#####     | 1222/2400 [13:12<57:55,  2.95s/it, lr: 5.0e-05 loss: 2.857e-01]
leoprint:  51%|#####     | 1222/2400 [13:12<57:55,  2.95s/it, lr: 5.0e-05 loss: 2.857e-01]
leoprint:  51%|#####     | 1222/2400 [13:15<57:55,  2.95s/it, lr: 5.0e-05 loss: 2.665e-01]
leoprint:  51%|#####     | 1222/2400 [13:15<57:55,  2.95s/it, lr: 5.0e-05 loss: 2.665e-01]
leoprint:  51%|#####     | 1223/2400 [13:15<1:01:27,  3.13s/it, lr: 5.0e-05 loss: 2.665e-01]
leoprint:  51%|#####     | 1223/2400 [13:15<1:01:27,  3.13s/it, lr: 5.0e-05 loss: 2.665e-01]
leoprint:  51%|#####     | 1223/2400 [13:19<1:01:27,  3.13s/it, lr: 5.0e-05 loss: 4.032e-01]
leoprint:  51%|#####     | 1223/2400 [13:19<1:01:27,  3.13s/it, lr: 5.0e-05 loss: 4.032e-01]
leoprint:  51%|#####1    | 1224/2400 [13:19<1:03:20,  3.23s/it, lr: 5.0e-05 loss: 4.032e-01]
leoprint:  51%|#####1    | 1224/2400 [13:19<1:03:20,  3.23s/it, lr: 5.0e-05 loss: 4.032e-01]
leoprint:  51%|#####1    | 1224/2400 [13:22<1:03:20,  3.23s/it, lr: 5.0e-05 loss: 2.976e-01]
leoprint:  51%|#####1    | 1224/2400 [13:22<1:03:20,  3.23s/it, lr: 5.0e-05 loss: 2.976e-01]
leoprint:  51%|#####1    | 1225/2400 [13:22<1:04:46,  3.31s/it, lr: 5.0e-05 loss: 2.976e-01]
leoprint:  51%|#####1    | 1225/2400 [13:22<1:04:46,  3.31s/it, lr: 5.0e-05 loss: 2.976e-01]
leoprint:  51%|#####1    | 1225/2400 [13:26<1:04:46,  3.31s/it, lr: 5.0e-05 loss: 3.084e-01]
leoprint:  51%|#####1    | 1225/2400 [13:26<1:04:46,  3.31s/it, lr: 5.0e-05 loss: 3.084e-01]
leoprint:  51%|#####1    | 1226/2400 [13:26<1:06:28,  3.40s/it, lr: 5.0e-05 loss: 3.084e-01]
leoprint:  51%|#####1    | 1226/2400 [13:26<1:06:28,  3.40s/it, lr: 5.0e-05 loss: 3.084e-01]
leoprint:  51%|#####1    | 1226/2400 [13:30<1:06:28,  3.40s/it, lr: 5.0e-05 loss: 2.488e-01]
leoprint:  51%|#####1    | 1226/2400 [13:30<1:06:28,  3.40s/it, lr: 5.0e-05 loss: 2.488e-01]
leoprint:  51%|#####1    | 1227/2400 [13:30<1:07:00,  3.43s/it, lr: 5.0e-05 loss: 2.488e-01]
leoprint:  51%|#####1    | 1227/2400 [13:30<1:07:00,  3.43s/it, lr: 5.0e-05 loss: 2.488e-01]
leoprint:  51%|#####1    | 1227/2400 [13:33<1:07:00,  3.43s/it, lr: 5.0e-05 loss: 3.445e-01]
leoprint:  51%|#####1    | 1227/2400 [13:33<1:07:00,  3.43s/it, lr: 5.0e-05 loss: 3.445e-01]
leoprint:  51%|#####1    | 1228/2400 [13:33<1:07:18,  3.45s/it, lr: 5.0e-05 loss: 3.445e-01]
leoprint:  51%|#####1    | 1228/2400 [13:33<1:07:18,  3.45s/it, lr: 5.0e-05 loss: 3.445e-01]
leoprint:  51%|#####1    | 1228/2400 [13:37<1:07:18,  3.45s/it, lr: 5.0e-05 loss: 3.594e-01]
leoprint:  51%|#####1    | 1228/2400 [13:37<1:07:18,  3.45s/it, lr: 5.0e-05 loss: 3.594e-01]
leoprint:  51%|#####1    | 1229/2400 [13:37<1:07:59,  3.48s/it, lr: 5.0e-05 loss: 3.594e-01]
leoprint:  51%|#####1    | 1229/2400 [13:37<1:07:59,  3.48s/it, lr: 5.0e-05 loss: 3.594e-01]
leoprint:  51%|#####1    | 1229/2400 [13:40<1:07:59,  3.48s/it, lr: 5.0e-05 loss: 3.045e-01]
leoprint:  51%|#####1    | 1229/2400 [13:40<1:07:59,  3.48s/it, lr: 5.0e-05 loss: 3.045e-01]
leoprint:  51%|#####1    | 1230/2400 [13:44<1:07:55,  3.48s/it, lr: 5.0e-05 loss: 3.058e-01]
leoprint:  51%|#####1    | 1230/2400 [13:44<1:07:55,  3.48s/it, lr: 5.0e-05 loss: 3.058e-01]
leoprint:  51%|#####1    | 1231/2400 [13:44<52:26,  2.69s/it, lr: 5.0e-05 loss: 3.058e-01]  
leoprint:  51%|#####1    | 1231/2400 [13:44<52:26,  2.69s/it, lr: 5.0e-05 loss: 3.058e-01]  
leoprint:  51%|#####1    | 1231/2400 [13:47<52:26,  2.69s/it, lr: 5.0e-05 loss: 3.467e-01]
leoprint:  51%|#####1    | 1231/2400 [13:47<52:26,  2.69s/it, lr: 5.0e-05 loss: 3.467e-01]
leoprint:  51%|#####1    | 1232/2400 [13:47<56:16,  2.89s/it, lr: 5.0e-05 loss: 3.467e-01]
leoprint:  51%|#####1    | 1232/2400 [13:47<56:16,  2.89s/it, lr: 5.0e-05 loss: 3.467e-01]
leoprint:  51%|#####1    | 1232/2400 [13:51<56:16,  2.89s/it, lr: 5.0e-05 loss: 3.812e-01]
leoprint:  51%|#####1    | 1232/2400 [13:51<56:16,  2.89s/it, lr: 5.0e-05 loss: 3.812e-01]
leoprint:  51%|#####1    | 1233/2400 [13:51<59:18,  3.05s/it, lr: 5.0e-05 loss: 3.812e-01]
leoprint:  51%|#####1    | 1233/2400 [13:51<59:18,  3.05s/it, lr: 5.0e-05 loss: 3.812e-01]
leoprint:  51%|#####1    | 1233/2400 [13:54<59:18,  3.05s/it, lr: 5.0e-05 loss: 2.477e-01]
leoprint:  51%|#####1    | 1233/2400 [13:54<59:18,  3.05s/it, lr: 5.0e-05 loss: 2.477e-01]
leoprint:  51%|#####1    | 1234/2400 [13:54<1:02:17,  3.21s/it, lr: 5.0e-05 loss: 2.477e-01]
leoprint:  51%|#####1    | 1234/2400 [13:54<1:02:17,  3.21s/it, lr: 5.0e-05 loss: 2.477e-01]
leoprint:  51%|#####1    | 1234/2400 [13:58<1:02:17,  3.21s/it, lr: 5.0e-05 loss: 2.867e-01]
leoprint:  51%|#####1    | 1234/2400 [13:58<1:02:17,  3.21s/it, lr: 5.0e-05 loss: 2.867e-01]
leoprint:  51%|#####1    | 1235/2400 [13:58<1:05:03,  3.35s/it, lr: 5.0e-05 loss: 2.867e-01]
leoprint:  51%|#####1    | 1235/2400 [13:58<1:05:03,  3.35s/it, lr: 5.0e-05 loss: 2.867e-01]
leoprint:  51%|#####1    | 1235/2400 [14:02<1:05:03,  3.35s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  51%|#####1    | 1235/2400 [14:02<1:05:03,  3.35s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  52%|#####1    | 1236/2400 [14:02<1:06:28,  3.43s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  52%|#####1    | 1236/2400 [14:02<1:06:28,  3.43s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  52%|#####1    | 1236/2400 [14:05<1:06:28,  3.43s/it, lr: 5.0e-05 loss: 3.876e-01]
leoprint:  52%|#####1    | 1236/2400 [14:05<1:06:28,  3.43s/it, lr: 5.0e-05 loss: 3.876e-01]
leoprint:  52%|#####1    | 1237/2400 [14:05<1:06:50,  3.45s/it, lr: 5.0e-05 loss: 3.876e-01]
leoprint:  52%|#####1    | 1237/2400 [14:05<1:06:50,  3.45s/it, lr: 5.0e-05 loss: 3.876e-01]
leoprint:  52%|#####1    | 1237/2400 [14:09<1:06:50,  3.45s/it, lr: 5.0e-05 loss: 2.831e-01]
leoprint:  52%|#####1    | 1237/2400 [14:09<1:06:50,  3.45s/it, lr: 5.0e-05 loss: 2.831e-01]
leoprint:  52%|#####1    | 1238/2400 [14:09<1:07:02,  3.46s/it, lr: 5.0e-05 loss: 2.831e-01]
leoprint:  52%|#####1    | 1238/2400 [14:09<1:07:02,  3.46s/it, lr: 5.0e-05 loss: 2.831e-01]
leoprint:  52%|#####1    | 1238/2400 [14:12<1:07:02,  3.46s/it, lr: 5.0e-05 loss: 2.692e-01]
leoprint:  52%|#####1    | 1238/2400 [14:12<1:07:02,  3.46s/it, lr: 5.0e-05 loss: 2.692e-01]
leoprint:  52%|#####1    | 1239/2400 [14:12<1:07:11,  3.47s/it, lr: 5.0e-05 loss: 2.692e-01]
leoprint:  52%|#####1    | 1239/2400 [14:12<1:07:11,  3.47s/it, lr: 5.0e-05 loss: 2.692e-01]
leoprint:  52%|#####1    | 1239/2400 [14:16<1:07:11,  3.47s/it, lr: 5.0e-05 loss: 2.973e-01]
leoprint:  52%|#####1    | 1239/2400 [14:16<1:07:11,  3.47s/it, lr: 5.0e-05 loss: 2.973e-01]
leoprint:  52%|#####1    | 1240/2400 [14:19<1:07:07,  3.47s/it, lr: 5.0e-05 loss: 2.260e-01]
leoprint:  52%|#####1    | 1240/2400 [14:19<1:07:07,  3.47s/it, lr: 5.0e-05 loss: 2.260e-01]
leoprint:  52%|#####1    | 1241/2400 [14:19<52:58,  2.74s/it, lr: 5.0e-05 loss: 2.260e-01]  
leoprint:  52%|#####1    | 1241/2400 [14:19<52:58,  2.74s/it, lr: 5.0e-05 loss: 2.260e-01]  
leoprint:  52%|#####1    | 1241/2400 [14:23<52:58,  2.74s/it, lr: 5.0e-05 loss: 2.344e-01]
leoprint:  52%|#####1    | 1241/2400 [14:23<52:58,  2.74s/it, lr: 5.0e-05 loss: 2.344e-01]
leoprint:  52%|#####1    | 1242/2400 [14:23<57:06,  2.96s/it, lr: 5.0e-05 loss: 2.344e-01]
leoprint:  52%|#####1    | 1242/2400 [14:23<57:06,  2.96s/it, lr: 5.0e-05 loss: 2.344e-01]
leoprint:  52%|#####1    | 1242/2400 [14:27<57:06,  2.96s/it, lr: 5.0e-05 loss: 3.238e-01]
leoprint:  52%|#####1    | 1242/2400 [14:27<57:06,  2.96s/it, lr: 5.0e-05 loss: 3.238e-01]
leoprint:  52%|#####1    | 1243/2400 [14:27<59:44,  3.10s/it, lr: 5.0e-05 loss: 3.238e-01]
leoprint:  52%|#####1    | 1243/2400 [14:27<59:44,  3.10s/it, lr: 5.0e-05 loss: 3.238e-01]
leoprint:  52%|#####1    | 1243/2400 [14:30<59:44,  3.10s/it, lr: 5.0e-05 loss: 1.995e-01]
leoprint:  52%|#####1    | 1243/2400 [14:30<59:44,  3.10s/it, lr: 5.0e-05 loss: 1.995e-01]
leoprint:  52%|#####1    | 1244/2400 [14:30<1:02:21,  3.24s/it, lr: 5.0e-05 loss: 1.995e-01]
leoprint:  52%|#####1    | 1244/2400 [14:30<1:02:21,  3.24s/it, lr: 5.0e-05 loss: 1.995e-01]
leoprint:  52%|#####1    | 1244/2400 [14:34<1:02:21,  3.24s/it, lr: 5.0e-05 loss: 3.618e-01]
leoprint:  52%|#####1    | 1244/2400 [14:34<1:02:21,  3.24s/it, lr: 5.0e-05 loss: 3.618e-01]
leoprint:  52%|#####1    | 1245/2400 [14:34<1:03:43,  3.31s/it, lr: 5.0e-05 loss: 3.618e-01]
leoprint:  52%|#####1    | 1245/2400 [14:34<1:03:43,  3.31s/it, lr: 5.0e-05 loss: 3.618e-01]
leoprint:  52%|#####1    | 1245/2400 [14:37<1:03:43,  3.31s/it, lr: 5.0e-05 loss: 2.721e-01]
leoprint:  52%|#####1    | 1245/2400 [14:37<1:03:43,  3.31s/it, lr: 5.0e-05 loss: 2.721e-01]
leoprint:  52%|#####1    | 1246/2400 [14:37<1:05:36,  3.41s/it, lr: 5.0e-05 loss: 2.721e-01]
leoprint:  52%|#####1    | 1246/2400 [14:37<1:05:36,  3.41s/it, lr: 5.0e-05 loss: 2.721e-01]
leoprint:  52%|#####1    | 1246/2400 [14:41<1:05:36,  3.41s/it, lr: 5.0e-05 loss: 2.741e-01]
leoprint:  52%|#####1    | 1246/2400 [14:41<1:05:36,  3.41s/it, lr: 5.0e-05 loss: 2.741e-01]
leoprint:  52%|#####1    | 1247/2400 [14:41<1:06:03,  3.44s/it, lr: 5.0e-05 loss: 2.741e-01]
leoprint:  52%|#####1    | 1247/2400 [14:41<1:06:03,  3.44s/it, lr: 5.0e-05 loss: 2.741e-01]
leoprint:  52%|#####1    | 1247/2400 [14:44<1:06:03,  3.44s/it, lr: 5.0e-05 loss: 2.653e-01]
leoprint:  52%|#####1    | 1247/2400 [14:44<1:06:03,  3.44s/it, lr: 5.0e-05 loss: 2.653e-01]
leoprint:  52%|#####2    | 1248/2400 [14:44<1:06:21,  3.46s/it, lr: 5.0e-05 loss: 2.653e-01]
leoprint:  52%|#####2    | 1248/2400 [14:44<1:06:21,  3.46s/it, lr: 5.0e-05 loss: 2.653e-01]
leoprint:  52%|#####2    | 1248/2400 [14:48<1:06:21,  3.46s/it, lr: 5.0e-05 loss: 3.820e-01]
leoprint:  52%|#####2    | 1248/2400 [14:48<1:06:21,  3.46s/it, lr: 5.0e-05 loss: 3.820e-01]
leoprint:  52%|#####2    | 1249/2400 [14:48<1:06:33,  3.47s/it, lr: 5.0e-05 loss: 3.820e-01]
leoprint:  52%|#####2    | 1249/2400 [14:48<1:06:33,  3.47s/it, lr: 5.0e-05 loss: 3.820e-01]
leoprint:  52%|#####2    | 1249/2400 [14:51<1:06:33,  3.47s/it, lr: 5.0e-05 loss: 2.468e-01]
leoprint:  52%|#####2    | 1249/2400 [14:51<1:06:33,  3.47s/it, lr: 5.0e-05 loss: 2.468e-01]
leoprint:  52%|#####2    | 1250/2400 [14:55<1:06:30,  3.47s/it, lr: 5.0e-05 loss: 2.255e-01]
leoprint:  52%|#####2    | 1250/2400 [14:55<1:06:30,  3.47s/it, lr: 5.0e-05 loss: 2.255e-01]
leoprint:  52%|#####2    | 1251/2400 [14:55<51:22,  2.68s/it, lr: 5.0e-05 loss: 2.255e-01]  
leoprint:  52%|#####2    | 1251/2400 [14:55<51:22,  2.68s/it, lr: 5.0e-05 loss: 2.255e-01]  
leoprint:  52%|#####2    | 1251/2400 [14:59<51:22,  2.68s/it, lr: 5.0e-05 loss: 2.145e-01]
leoprint:  52%|#####2    | 1251/2400 [14:59<51:22,  2.68s/it, lr: 5.0e-05 loss: 2.145e-01]
leoprint:  52%|#####2    | 1252/2400 [14:59<55:32,  2.90s/it, lr: 5.0e-05 loss: 2.145e-01]
leoprint:  52%|#####2    | 1252/2400 [14:59<55:32,  2.90s/it, lr: 5.0e-05 loss: 2.145e-01]
leoprint:  52%|#####2    | 1252/2400 [15:02<55:32,  2.90s/it, lr: 5.0e-05 loss: 2.186e-01]
leoprint:  52%|#####2    | 1252/2400 [15:02<55:32,  2.90s/it, lr: 5.0e-05 loss: 2.186e-01]
leoprint:  52%|#####2    | 1253/2400 [15:02<58:27,  3.06s/it, lr: 5.0e-05 loss: 2.186e-01]
leoprint:  52%|#####2    | 1253/2400 [15:02<58:27,  3.06s/it, lr: 5.0e-05 loss: 2.186e-01]
leoprint:  52%|#####2    | 1253/2400 [15:06<58:27,  3.06s/it, lr: 5.0e-05 loss: 3.428e-01]
leoprint:  52%|#####2    | 1253/2400 [15:06<58:27,  3.06s/it, lr: 5.0e-05 loss: 3.428e-01]
leoprint:  52%|#####2    | 1254/2400 [15:06<1:00:41,  3.18s/it, lr: 5.0e-05 loss: 3.428e-01]
leoprint:  52%|#####2    | 1254/2400 [15:06<1:00:41,  3.18s/it, lr: 5.0e-05 loss: 3.428e-01]
leoprint:  52%|#####2    | 1254/2400 [15:09<1:00:41,  3.18s/it, lr: 5.0e-05 loss: 3.560e-01]
leoprint:  52%|#####2    | 1254/2400 [15:09<1:00:41,  3.18s/it, lr: 5.0e-05 loss: 3.560e-01]
leoprint:  52%|#####2    | 1255/2400 [15:09<1:02:20,  3.27s/it, lr: 5.0e-05 loss: 3.560e-01]
leoprint:  52%|#####2    | 1255/2400 [15:09<1:02:20,  3.27s/it, lr: 5.0e-05 loss: 3.560e-01]
leoprint:  52%|#####2    | 1255/2400 [15:13<1:02:20,  3.27s/it, lr: 5.0e-05 loss: 3.369e-01]
leoprint:  52%|#####2    | 1255/2400 [15:13<1:02:20,  3.27s/it, lr: 5.0e-05 loss: 3.369e-01]
leoprint:  52%|#####2    | 1256/2400 [15:13<1:03:32,  3.33s/it, lr: 5.0e-05 loss: 3.369e-01]
leoprint:  52%|#####2    | 1256/2400 [15:13<1:03:32,  3.33s/it, lr: 5.0e-05 loss: 3.369e-01]
leoprint:  52%|#####2    | 1256/2400 [15:16<1:03:32,  3.33s/it, lr: 5.0e-05 loss: 2.407e-01]
leoprint:  52%|#####2    | 1256/2400 [15:16<1:03:32,  3.33s/it, lr: 5.0e-05 loss: 2.407e-01]
leoprint:  52%|#####2    | 1257/2400 [15:16<1:04:59,  3.41s/it, lr: 5.0e-05 loss: 2.407e-01]
leoprint:  52%|#####2    | 1257/2400 [15:16<1:04:59,  3.41s/it, lr: 5.0e-05 loss: 2.407e-01]
leoprint:  52%|#####2    | 1257/2400 [15:20<1:04:59,  3.41s/it, lr: 5.0e-05 loss: 2.945e-01]
leoprint:  52%|#####2    | 1257/2400 [15:20<1:04:59,  3.41s/it, lr: 5.0e-05 loss: 2.945e-01]
leoprint:  52%|#####2    | 1258/2400 [15:20<1:06:41,  3.50s/it, lr: 5.0e-05 loss: 2.945e-01]
leoprint:  52%|#####2    | 1258/2400 [15:20<1:06:41,  3.50s/it, lr: 5.0e-05 loss: 2.945e-01]
leoprint:  52%|#####2    | 1258/2400 [15:23<1:06:41,  3.50s/it, lr: 5.0e-05 loss: 3.410e-01]
leoprint:  52%|#####2    | 1258/2400 [15:23<1:06:41,  3.50s/it, lr: 5.0e-05 loss: 3.410e-01]
leoprint:  52%|#####2    | 1259/2400 [15:23<1:06:33,  3.50s/it, lr: 5.0e-05 loss: 3.410e-01]
leoprint:  52%|#####2    | 1259/2400 [15:23<1:06:33,  3.50s/it, lr: 5.0e-05 loss: 3.410e-01]
leoprint:  52%|#####2    | 1259/2400 [15:27<1:06:33,  3.50s/it, lr: 5.0e-05 loss: 3.208e-01]
leoprint:  52%|#####2    | 1259/2400 [15:27<1:06:33,  3.50s/it, lr: 5.0e-05 loss: 3.208e-01]
leoprint:  52%|#####2    | 1260/2400 [15:31<1:06:30,  3.50s/it, lr: 5.0e-05 loss: 3.636e-01]
leoprint:  52%|#####2    | 1260/2400 [15:31<1:06:30,  3.50s/it, lr: 5.0e-05 loss: 3.636e-01]
leoprint:  53%|#####2    | 1261/2400 [15:31<51:12,  2.70s/it, lr: 5.0e-05 loss: 3.636e-01]  
leoprint:  53%|#####2    | 1261/2400 [15:31<51:12,  2.70s/it, lr: 5.0e-05 loss: 3.636e-01]  
leoprint:  53%|#####2    | 1261/2400 [15:34<51:12,  2.70s/it, lr: 5.0e-05 loss: 2.696e-01]
leoprint:  53%|#####2    | 1261/2400 [15:34<51:12,  2.70s/it, lr: 5.0e-05 loss: 2.696e-01]
leoprint:  53%|#####2    | 1262/2400 [15:34<55:26,  2.92s/it, lr: 5.0e-05 loss: 2.696e-01]
leoprint:  53%|#####2    | 1262/2400 [15:34<55:26,  2.92s/it, lr: 5.0e-05 loss: 2.696e-01]
leoprint:  53%|#####2    | 1262/2400 [15:38<55:26,  2.92s/it, lr: 5.0e-05 loss: 2.870e-01]
leoprint:  53%|#####2    | 1262/2400 [15:38<55:26,  2.92s/it, lr: 5.0e-05 loss: 2.870e-01]
leoprint:  53%|#####2    | 1263/2400 [15:38<58:12,  3.07s/it, lr: 5.0e-05 loss: 2.870e-01]
leoprint:  53%|#####2    | 1263/2400 [15:38<58:12,  3.07s/it, lr: 5.0e-05 loss: 2.870e-01]
leoprint:  53%|#####2    | 1263/2400 [15:41<58:12,  3.07s/it, lr: 5.0e-05 loss: 3.293e-01]
leoprint:  53%|#####2    | 1263/2400 [15:41<58:12,  3.07s/it, lr: 5.0e-05 loss: 3.293e-01]
leoprint:  53%|#####2    | 1264/2400 [15:41<1:01:27,  3.25s/it, lr: 5.0e-05 loss: 3.293e-01]
leoprint:  53%|#####2    | 1264/2400 [15:41<1:01:27,  3.25s/it, lr: 5.0e-05 loss: 3.293e-01]
leoprint:  53%|#####2    | 1264/2400 [15:45<1:01:27,  3.25s/it, lr: 5.0e-05 loss: 2.915e-01]
leoprint:  53%|#####2    | 1264/2400 [15:45<1:01:27,  3.25s/it, lr: 5.0e-05 loss: 2.915e-01]
leoprint:  53%|#####2    | 1265/2400 [15:45<1:02:43,  3.32s/it, lr: 5.0e-05 loss: 2.915e-01]
leoprint:  53%|#####2    | 1265/2400 [15:45<1:02:43,  3.32s/it, lr: 5.0e-05 loss: 2.915e-01]
leoprint:  53%|#####2    | 1265/2400 [15:48<1:02:43,  3.32s/it, lr: 5.0e-05 loss: 3.837e-01]
leoprint:  53%|#####2    | 1265/2400 [15:48<1:02:43,  3.32s/it, lr: 5.0e-05 loss: 3.837e-01]
leoprint:  53%|#####2    | 1266/2400 [15:48<1:03:39,  3.37s/it, lr: 5.0e-05 loss: 3.837e-01]
leoprint:  53%|#####2    | 1266/2400 [15:48<1:03:39,  3.37s/it, lr: 5.0e-05 loss: 3.837e-01]
leoprint:  53%|#####2    | 1266/2400 [15:52<1:03:39,  3.37s/it, lr: 5.0e-05 loss: 2.756e-01]
leoprint:  53%|#####2    | 1266/2400 [15:52<1:03:39,  3.37s/it, lr: 5.0e-05 loss: 2.756e-01]
leoprint:  53%|#####2    | 1267/2400 [15:52<1:04:19,  3.41s/it, lr: 5.0e-05 loss: 2.756e-01]
leoprint:  53%|#####2    | 1267/2400 [15:52<1:04:19,  3.41s/it, lr: 5.0e-05 loss: 2.756e-01]
leoprint:  53%|#####2    | 1267/2400 [15:56<1:04:19,  3.41s/it, lr: 5.0e-05 loss: 2.940e-01]
leoprint:  53%|#####2    | 1267/2400 [15:56<1:04:19,  3.41s/it, lr: 5.0e-05 loss: 2.940e-01]
leoprint:  53%|#####2    | 1268/2400 [15:56<1:05:24,  3.47s/it, lr: 5.0e-05 loss: 2.940e-01]
leoprint:  53%|#####2    | 1268/2400 [15:56<1:05:24,  3.47s/it, lr: 5.0e-05 loss: 2.940e-01]
leoprint:  53%|#####2    | 1268/2400 [15:59<1:05:24,  3.47s/it, lr: 5.0e-05 loss: 2.846e-01]
leoprint:  53%|#####2    | 1268/2400 [15:59<1:05:24,  3.47s/it, lr: 5.0e-05 loss: 2.846e-01]
leoprint:  53%|#####2    | 1269/2400 [15:59<1:05:55,  3.50s/it, lr: 5.0e-05 loss: 2.846e-01]
leoprint:  53%|#####2    | 1269/2400 [15:59<1:05:55,  3.50s/it, lr: 5.0e-05 loss: 2.846e-01]
leoprint:  53%|#####2    | 1269/2400 [16:03<1:05:55,  3.50s/it, lr: 5.0e-05 loss: 3.704e-01]
leoprint:  53%|#####2    | 1269/2400 [16:03<1:05:55,  3.50s/it, lr: 5.0e-05 loss: 3.704e-01]
leoprint:  53%|#####2    | 1270/2400 [16:06<1:05:52,  3.50s/it, lr: 5.0e-05 loss: 2.796e-01]
leoprint:  53%|#####2    | 1270/2400 [16:06<1:05:52,  3.50s/it, lr: 5.0e-05 loss: 2.796e-01]
leoprint:  53%|#####2    | 1271/2400 [16:06<51:15,  2.72s/it, lr: 5.0e-05 loss: 2.796e-01]  
leoprint:  53%|#####2    | 1271/2400 [16:06<51:15,  2.72s/it, lr: 5.0e-05 loss: 2.796e-01]  
leoprint:  53%|#####2    | 1271/2400 [16:10<51:15,  2.72s/it, lr: 5.0e-05 loss: 2.292e-01]
leoprint:  53%|#####2    | 1271/2400 [16:10<51:15,  2.72s/it, lr: 5.0e-05 loss: 2.292e-01]
leoprint:  53%|#####3    | 1272/2400 [16:10<54:46,  2.91s/it, lr: 5.0e-05 loss: 2.292e-01]
leoprint:  53%|#####3    | 1272/2400 [16:10<54:46,  2.91s/it, lr: 5.0e-05 loss: 2.292e-01]
leoprint:  53%|#####3    | 1272/2400 [16:13<54:46,  2.91s/it, lr: 5.0e-05 loss: 3.139e-01]
leoprint:  53%|#####3    | 1272/2400 [16:13<54:46,  2.91s/it, lr: 5.0e-05 loss: 3.139e-01]
leoprint:  53%|#####3    | 1273/2400 [16:13<57:34,  3.07s/it, lr: 5.0e-05 loss: 3.139e-01]
leoprint:  53%|#####3    | 1273/2400 [16:13<57:34,  3.07s/it, lr: 5.0e-05 loss: 3.139e-01]
leoprint:  53%|#####3    | 1273/2400 [16:17<57:34,  3.07s/it, lr: 5.0e-05 loss: 2.602e-01]
leoprint:  53%|#####3    | 1273/2400 [16:17<57:34,  3.07s/it, lr: 5.0e-05 loss: 2.602e-01]
leoprint:  53%|#####3    | 1274/2400 [16:17<1:00:18,  3.21s/it, lr: 5.0e-05 loss: 2.602e-01]
leoprint:  53%|#####3    | 1274/2400 [16:17<1:00:18,  3.21s/it, lr: 5.0e-05 loss: 2.602e-01]
leoprint:  53%|#####3    | 1274/2400 [16:21<1:00:18,  3.21s/it, lr: 5.0e-05 loss: 3.142e-01]
leoprint:  53%|#####3    | 1274/2400 [16:21<1:00:18,  3.21s/it, lr: 5.0e-05 loss: 3.142e-01]
leoprint:  53%|#####3    | 1275/2400 [16:21<1:03:18,  3.38s/it, lr: 5.0e-05 loss: 3.142e-01]
leoprint:  53%|#####3    | 1275/2400 [16:21<1:03:18,  3.38s/it, lr: 5.0e-05 loss: 3.142e-01]
leoprint:  53%|#####3    | 1275/2400 [16:24<1:03:18,  3.38s/it, lr: 5.0e-05 loss: 4.098e-01]
leoprint:  53%|#####3    | 1275/2400 [16:24<1:03:18,  3.38s/it, lr: 5.0e-05 loss: 4.098e-01]
leoprint:  53%|#####3    | 1276/2400 [16:24<1:03:53,  3.41s/it, lr: 5.0e-05 loss: 4.098e-01]
leoprint:  53%|#####3    | 1276/2400 [16:24<1:03:53,  3.41s/it, lr: 5.0e-05 loss: 4.098e-01]
leoprint:  53%|#####3    | 1276/2400 [16:28<1:03:53,  3.41s/it, lr: 5.0e-05 loss: 3.107e-01]
leoprint:  53%|#####3    | 1276/2400 [16:28<1:03:53,  3.41s/it, lr: 5.0e-05 loss: 3.107e-01]
leoprint:  53%|#####3    | 1277/2400 [16:28<1:04:54,  3.47s/it, lr: 5.0e-05 loss: 3.107e-01]
leoprint:  53%|#####3    | 1277/2400 [16:28<1:04:54,  3.47s/it, lr: 5.0e-05 loss: 3.107e-01]
leoprint:  53%|#####3    | 1277/2400 [16:31<1:04:54,  3.47s/it, lr: 5.0e-05 loss: 3.291e-01]
leoprint:  53%|#####3    | 1277/2400 [16:31<1:04:54,  3.47s/it, lr: 5.0e-05 loss: 3.291e-01]
leoprint:  53%|#####3    | 1278/2400 [16:31<1:05:01,  3.48s/it, lr: 5.0e-05 loss: 3.291e-01]
leoprint:  53%|#####3    | 1278/2400 [16:31<1:05:01,  3.48s/it, lr: 5.0e-05 loss: 3.291e-01]
leoprint:  53%|#####3    | 1278/2400 [16:35<1:05:01,  3.48s/it, lr: 5.0e-05 loss: 3.665e-01]
leoprint:  53%|#####3    | 1278/2400 [16:35<1:05:01,  3.48s/it, lr: 5.0e-05 loss: 3.665e-01]
leoprint:  53%|#####3    | 1279/2400 [16:35<1:05:03,  3.48s/it, lr: 5.0e-05 loss: 3.665e-01]
leoprint:  53%|#####3    | 1279/2400 [16:35<1:05:03,  3.48s/it, lr: 5.0e-05 loss: 3.665e-01]
leoprint:  53%|#####3    | 1279/2400 [16:38<1:05:03,  3.48s/it, lr: 5.0e-05 loss: 3.980e-01]
leoprint:  53%|#####3    | 1279/2400 [16:38<1:05:03,  3.48s/it, lr: 5.0e-05 loss: 3.980e-01]
leoprint:  53%|#####3    | 1280/2400 [16:42<1:05:00,  3.48s/it, lr: 5.0e-05 loss: 2.881e-01]
leoprint:  53%|#####3    | 1280/2400 [16:42<1:05:00,  3.48s/it, lr: 5.0e-05 loss: 2.881e-01]
leoprint:  53%|#####3    | 1281/2400 [16:42<51:15,  2.75s/it, lr: 5.0e-05 loss: 2.881e-01]  
leoprint:  53%|#####3    | 1281/2400 [16:42<51:15,  2.75s/it, lr: 5.0e-05 loss: 2.881e-01]  
leoprint:  53%|#####3    | 1281/2400 [16:46<51:15,  2.75s/it, lr: 5.0e-05 loss: 3.284e-01]
leoprint:  53%|#####3    | 1281/2400 [16:46<51:15,  2.75s/it, lr: 5.0e-05 loss: 3.284e-01]
leoprint:  53%|#####3    | 1282/2400 [16:46<54:38,  2.93s/it, lr: 5.0e-05 loss: 3.284e-01]
leoprint:  53%|#####3    | 1282/2400 [16:46<54:38,  2.93s/it, lr: 5.0e-05 loss: 3.284e-01]
leoprint:  53%|#####3    | 1282/2400 [16:49<54:38,  2.93s/it, lr: 5.0e-05 loss: 3.420e-01]
leoprint:  53%|#####3    | 1282/2400 [16:49<54:38,  2.93s/it, lr: 5.0e-05 loss: 3.420e-01]
leoprint:  53%|#####3    | 1283/2400 [16:49<57:19,  3.08s/it, lr: 5.0e-05 loss: 3.420e-01]
leoprint:  53%|#####3    | 1283/2400 [16:49<57:19,  3.08s/it, lr: 5.0e-05 loss: 3.420e-01]
leoprint:  53%|#####3    | 1283/2400 [16:53<57:19,  3.08s/it, lr: 5.0e-05 loss: 2.512e-01]
leoprint:  53%|#####3    | 1283/2400 [16:53<57:19,  3.08s/it, lr: 5.0e-05 loss: 2.512e-01]
leoprint:  54%|#####3    | 1284/2400 [16:53<59:23,  3.19s/it, lr: 5.0e-05 loss: 2.512e-01]
leoprint:  54%|#####3    | 1284/2400 [16:53<59:23,  3.19s/it, lr: 5.0e-05 loss: 2.512e-01]
leoprint:  54%|#####3    | 1284/2400 [16:56<59:23,  3.19s/it, lr: 5.0e-05 loss: 2.517e-01]
leoprint:  54%|#####3    | 1284/2400 [16:56<59:23,  3.19s/it, lr: 5.0e-05 loss: 2.517e-01]
leoprint:  54%|#####3    | 1285/2400 [16:56<1:00:55,  3.28s/it, lr: 5.0e-05 loss: 2.517e-01]
leoprint:  54%|#####3    | 1285/2400 [16:56<1:00:55,  3.28s/it, lr: 5.0e-05 loss: 2.517e-01]
leoprint:  54%|#####3    | 1285/2400 [17:00<1:00:55,  3.28s/it, lr: 5.0e-05 loss: 3.162e-01]
leoprint:  54%|#####3    | 1285/2400 [17:00<1:00:55,  3.28s/it, lr: 5.0e-05 loss: 3.162e-01]
leoprint:  54%|#####3    | 1286/2400 [17:00<1:03:29,  3.42s/it, lr: 5.0e-05 loss: 3.162e-01]
leoprint:  54%|#####3    | 1286/2400 [17:00<1:03:29,  3.42s/it, lr: 5.0e-05 loss: 3.162e-01]
leoprint:  54%|#####3    | 1286/2400 [17:03<1:03:29,  3.42s/it, lr: 5.0e-05 loss: 3.051e-01]
leoprint:  54%|#####3    | 1286/2400 [17:03<1:03:29,  3.42s/it, lr: 5.0e-05 loss: 3.051e-01]
leoprint:  54%|#####3    | 1287/2400 [17:03<1:03:53,  3.44s/it, lr: 5.0e-05 loss: 3.051e-01]
leoprint:  54%|#####3    | 1287/2400 [17:03<1:03:53,  3.44s/it, lr: 5.0e-05 loss: 3.051e-01]
leoprint:  54%|#####3    | 1287/2400 [17:07<1:03:53,  3.44s/it, lr: 5.0e-05 loss: 3.955e-01]
leoprint:  54%|#####3    | 1287/2400 [17:07<1:03:53,  3.44s/it, lr: 5.0e-05 loss: 3.955e-01]
leoprint:  54%|#####3    | 1288/2400 [17:07<1:04:10,  3.46s/it, lr: 5.0e-05 loss: 3.955e-01]
leoprint:  54%|#####3    | 1288/2400 [17:07<1:04:10,  3.46s/it, lr: 5.0e-05 loss: 3.955e-01]
leoprint:  54%|#####3    | 1288/2400 [17:11<1:04:10,  3.46s/it, lr: 5.0e-05 loss: 2.988e-01]
leoprint:  54%|#####3    | 1288/2400 [17:11<1:04:10,  3.46s/it, lr: 5.0e-05 loss: 2.988e-01]
leoprint:  54%|#####3    | 1289/2400 [17:11<1:04:54,  3.51s/it, lr: 5.0e-05 loss: 2.988e-01]
leoprint:  54%|#####3    | 1289/2400 [17:11<1:04:54,  3.51s/it, lr: 5.0e-05 loss: 2.988e-01]
leoprint:  54%|#####3    | 1289/2400 [17:14<1:04:54,  3.51s/it, lr: 5.0e-05 loss: 4.059e-01]
leoprint:  54%|#####3    | 1289/2400 [17:14<1:04:54,  3.51s/it, lr: 5.0e-05 loss: 4.059e-01]
leoprint:  54%|#####3    | 1290/2400 [17:19<1:04:51,  3.51s/it, lr: 5.0e-05 loss: 3.274e-01]
leoprint:  54%|#####3    | 1290/2400 [17:19<1:04:51,  3.51s/it, lr: 5.0e-05 loss: 3.274e-01]
leoprint:  54%|#####3    | 1291/2400 [17:19<54:47,  2.96s/it, lr: 5.0e-05 loss: 3.274e-01]  
leoprint:  54%|#####3    | 1291/2400 [17:19<54:47,  2.96s/it, lr: 5.0e-05 loss: 3.274e-01]  
leoprint:  54%|#####3    | 1291/2400 [17:28<54:47,  2.96s/it, lr: 5.0e-05 loss: 3.112e-01]
leoprint:  54%|#####3    | 1291/2400 [17:28<54:47,  2.96s/it, lr: 5.0e-05 loss: 3.112e-01]
leoprint:  54%|#####3    | 1292/2400 [17:28<1:24:03,  4.55s/it, lr: 5.0e-05 loss: 3.112e-01]
leoprint:  54%|#####3    | 1292/2400 [17:28<1:24:03,  4.55s/it, lr: 5.0e-05 loss: 3.112e-01]
leoprint:  54%|#####3    | 1292/2400 [17:38<1:24:03,  4.55s/it, lr: 5.0e-05 loss: 3.623e-01]
leoprint:  54%|#####3    | 1292/2400 [17:38<1:24:03,  4.55s/it, lr: 5.0e-05 loss: 3.623e-01]
leoprint:  54%|#####3    | 1293/2400 [17:38<1:48:29,  5.88s/it, lr: 5.0e-05 loss: 3.623e-01]
leoprint:  54%|#####3    | 1293/2400 [17:38<1:48:29,  5.88s/it, lr: 5.0e-05 loss: 3.623e-01]
leoprint:  54%|#####3    | 1293/2400 [17:47<1:48:29,  5.88s/it, lr: 5.0e-05 loss: 2.446e-01]
leoprint:  54%|#####3    | 1293/2400 [17:47<1:48:29,  5.88s/it, lr: 5.0e-05 loss: 2.446e-01]
leoprint:  54%|#####3    | 1294/2400 [17:47<2:07:15,  6.90s/it, lr: 5.0e-05 loss: 2.446e-01]
leoprint:  54%|#####3    | 1294/2400 [17:47<2:07:15,  6.90s/it, lr: 5.0e-05 loss: 2.446e-01]
leoprint:  54%|#####3    | 1294/2400 [17:51<2:07:15,  6.90s/it, lr: 5.0e-05 loss: 2.502e-01]
leoprint:  54%|#####3    | 1294/2400 [17:51<2:07:15,  6.90s/it, lr: 5.0e-05 loss: 2.502e-01]
leoprint:  54%|#####3    | 1295/2400 [17:51<1:50:09,  5.98s/it, lr: 5.0e-05 loss: 2.502e-01]
leoprint:  54%|#####3    | 1295/2400 [17:51<1:50:09,  5.98s/it, lr: 5.0e-05 loss: 2.502e-01]
leoprint:  54%|#####3    | 1295/2400 [17:55<1:50:09,  5.98s/it, lr: 5.0e-05 loss: 3.222e-01]
leoprint:  54%|#####3    | 1295/2400 [17:55<1:50:09,  5.98s/it, lr: 5.0e-05 loss: 3.222e-01]
leoprint:  54%|#####4    | 1296/2400 [17:55<1:37:07,  5.28s/it, lr: 5.0e-05 loss: 3.222e-01]
leoprint:  54%|#####4    | 1296/2400 [17:55<1:37:07,  5.28s/it, lr: 5.0e-05 loss: 3.222e-01]
leoprint:  54%|#####4    | 1296/2400 [17:58<1:37:07,  5.28s/it, lr: 5.0e-05 loss: 2.286e-01]
leoprint:  54%|#####4    | 1296/2400 [17:58<1:37:07,  5.28s/it, lr: 5.0e-05 loss: 2.286e-01]
leoprint:  54%|#####4    | 1297/2400 [17:58<1:27:37,  4.77s/it, lr: 5.0e-05 loss: 2.286e-01]
leoprint:  54%|#####4    | 1297/2400 [17:58<1:27:37,  4.77s/it, lr: 5.0e-05 loss: 2.286e-01]
leoprint:  54%|#####4    | 1297/2400 [18:02<1:27:37,  4.77s/it, lr: 5.0e-05 loss: 2.427e-01]
leoprint:  54%|#####4    | 1297/2400 [18:02<1:27:37,  4.77s/it, lr: 5.0e-05 loss: 2.427e-01]
leoprint:  54%|#####4    | 1298/2400 [18:02<1:21:59,  4.46s/it, lr: 5.0e-05 loss: 2.427e-01]
leoprint:  54%|#####4    | 1298/2400 [18:02<1:21:59,  4.46s/it, lr: 5.0e-05 loss: 2.427e-01]
leoprint:  54%|#####4    | 1298/2400 [18:05<1:21:59,  4.46s/it, lr: 5.0e-05 loss: 3.962e-01]
leoprint:  54%|#####4    | 1298/2400 [18:05<1:21:59,  4.46s/it, lr: 5.0e-05 loss: 3.962e-01]
leoprint:  54%|#####4    | 1299/2400 [18:05<1:16:44,  4.18s/it, lr: 5.0e-05 loss: 3.962e-01]
leoprint:  54%|#####4    | 1299/2400 [18:05<1:16:44,  4.18s/it, lr: 5.0e-05 loss: 3.962e-01]
leoprint:  54%|#####4    | 1299/2400 [18:09<1:16:44,  4.18s/it, lr: 5.0e-05 loss: 3.129e-01]
leoprint:  54%|#####4    | 1299/2400 [18:09<1:16:44,  4.18s/it, lr: 5.0e-05 loss: 3.129e-01]
leoprint:  54%|#####4    | 1300/2400 [18:12<1:16:40,  4.18s/it, lr: 5.0e-05 loss: 2.173e-01]
leoprint:  54%|#####4    | 1300/2400 [18:12<1:16:40,  4.18s/it, lr: 5.0e-05 loss: 2.173e-01]
leoprint:  54%|#####4    | 1301/2400 [18:12<56:12,  3.07s/it, lr: 5.0e-05 loss: 2.173e-01]  
leoprint:  54%|#####4    | 1301/2400 [18:12<56:12,  3.07s/it, lr: 5.0e-05 loss: 2.173e-01]  
leoprint:  54%|#####4    | 1301/2400 [18:16<56:12,  3.07s/it, lr: 5.0e-05 loss: 2.120e-01]
leoprint:  54%|#####4    | 1301/2400 [18:16<56:12,  3.07s/it, lr: 5.0e-05 loss: 2.120e-01]
leoprint:  54%|#####4    | 1302/2400 [18:16<58:35,  3.20s/it, lr: 5.0e-05 loss: 2.120e-01]
leoprint:  54%|#####4    | 1302/2400 [18:16<58:35,  3.20s/it, lr: 5.0e-05 loss: 2.120e-01]
leoprint:  54%|#####4    | 1302/2400 [18:20<58:35,  3.20s/it, lr: 5.0e-05 loss: 2.815e-01]
leoprint:  54%|#####4    | 1302/2400 [18:20<58:35,  3.20s/it, lr: 5.0e-05 loss: 2.815e-01]
leoprint:  54%|#####4    | 1303/2400 [18:20<1:00:19,  3.30s/it, lr: 5.0e-05 loss: 2.815e-01]
leoprint:  54%|#####4    | 1303/2400 [18:20<1:00:19,  3.30s/it, lr: 5.0e-05 loss: 2.815e-01]
leoprint:  54%|#####4    | 1303/2400 [18:23<1:00:19,  3.30s/it, lr: 5.0e-05 loss: 2.154e-01]
leoprint:  54%|#####4    | 1303/2400 [18:23<1:00:19,  3.30s/it, lr: 5.0e-05 loss: 2.154e-01]
leoprint:  54%|#####4    | 1304/2400 [18:23<1:01:14,  3.35s/it, lr: 5.0e-05 loss: 2.154e-01]
leoprint:  54%|#####4    | 1304/2400 [18:23<1:01:14,  3.35s/it, lr: 5.0e-05 loss: 2.154e-01]
leoprint:  54%|#####4    | 1304/2400 [18:27<1:01:14,  3.35s/it, lr: 5.0e-05 loss: 3.666e-01]
leoprint:  54%|#####4    | 1304/2400 [18:27<1:01:14,  3.35s/it, lr: 5.0e-05 loss: 3.666e-01]
leoprint:  54%|#####4    | 1305/2400 [18:27<1:01:54,  3.39s/it, lr: 5.0e-05 loss: 3.666e-01]
leoprint:  54%|#####4    | 1305/2400 [18:27<1:01:54,  3.39s/it, lr: 5.0e-05 loss: 3.666e-01]
leoprint:  54%|#####4    | 1305/2400 [18:30<1:01:54,  3.39s/it, lr: 5.0e-05 loss: 2.503e-01]
leoprint:  54%|#####4    | 1305/2400 [18:30<1:01:54,  3.39s/it, lr: 5.0e-05 loss: 2.503e-01]
leoprint:  54%|#####4    | 1306/2400 [18:30<1:03:00,  3.46s/it, lr: 5.0e-05 loss: 2.503e-01]
leoprint:  54%|#####4    | 1306/2400 [18:30<1:03:00,  3.46s/it, lr: 5.0e-05 loss: 2.503e-01]
leoprint:  54%|#####4    | 1306/2400 [18:39<1:03:00,  3.46s/it, lr: 5.0e-05 loss: 3.668e-01]
leoprint:  54%|#####4    | 1306/2400 [18:39<1:03:00,  3.46s/it, lr: 5.0e-05 loss: 3.668e-01]
leoprint:  54%|#####4    | 1307/2400 [18:39<1:30:36,  4.97s/it, lr: 5.0e-05 loss: 3.668e-01]
leoprint:  54%|#####4    | 1307/2400 [18:39<1:30:36,  4.97s/it, lr: 5.0e-05 loss: 3.668e-01]
leoprint:  54%|#####4    | 1307/2400 [18:49<1:30:36,  4.97s/it, lr: 5.0e-05 loss: 2.639e-01]
leoprint:  54%|#####4    | 1307/2400 [18:49<1:30:36,  4.97s/it, lr: 5.0e-05 loss: 2.639e-01]
leoprint:  55%|#####4    | 1308/2400 [18:49<1:55:28,  6.34s/it, lr: 5.0e-05 loss: 2.639e-01]
leoprint:  55%|#####4    | 1308/2400 [18:49<1:55:28,  6.34s/it, lr: 5.0e-05 loss: 2.639e-01]
leoprint:  55%|#####4    | 1308/2400 [18:58<1:55:28,  6.34s/it, lr: 5.0e-05 loss: 2.752e-01]
leoprint:  55%|#####4    | 1308/2400 [18:58<1:55:28,  6.34s/it, lr: 5.0e-05 loss: 2.752e-01]
leoprint:  55%|#####4    | 1309/2400 [18:58<2:13:06,  7.32s/it, lr: 5.0e-05 loss: 2.752e-01]
leoprint:  55%|#####4    | 1309/2400 [18:58<2:13:06,  7.32s/it, lr: 5.0e-05 loss: 2.752e-01]
leoprint:  55%|#####4    | 1309/2400 [19:02<2:13:06,  7.32s/it, lr: 5.0e-05 loss: 3.889e-01]
leoprint:  55%|#####4    | 1309/2400 [19:02<2:13:06,  7.32s/it, lr: 5.0e-05 loss: 3.889e-01]
leoprint:  55%|#####4    | 1310/2400 [19:05<2:12:59,  7.32s/it, lr: 5.0e-05 loss: 2.955e-01]
leoprint:  55%|#####4    | 1310/2400 [19:05<2:12:59,  7.32s/it, lr: 5.0e-05 loss: 2.955e-01]
leoprint:  55%|#####4    | 1311/2400 [19:05<1:26:37,  4.77s/it, lr: 5.0e-05 loss: 2.955e-01]
leoprint:  55%|#####4    | 1311/2400 [19:05<1:26:37,  4.77s/it, lr: 5.0e-05 loss: 2.955e-01]
leoprint:  55%|#####4    | 1311/2400 [19:09<1:26:37,  4.77s/it, lr: 5.0e-05 loss: 2.334e-01]
leoprint:  55%|#####4    | 1311/2400 [19:09<1:26:37,  4.77s/it, lr: 5.0e-05 loss: 2.334e-01]
leoprint:  55%|#####4    | 1312/2400 [19:09<1:21:21,  4.49s/it, lr: 5.0e-05 loss: 2.334e-01]
leoprint:  55%|#####4    | 1312/2400 [19:09<1:21:21,  4.49s/it, lr: 5.0e-05 loss: 2.334e-01]
leoprint:  55%|#####4    | 1312/2400 [19:13<1:21:21,  4.49s/it, lr: 5.0e-05 loss: 2.403e-01]
leoprint:  55%|#####4    | 1312/2400 [19:13<1:21:21,  4.49s/it, lr: 5.0e-05 loss: 2.403e-01]
leoprint:  55%|#####4    | 1313/2400 [19:13<1:17:11,  4.26s/it, lr: 5.0e-05 loss: 2.403e-01]
leoprint:  55%|#####4    | 1313/2400 [19:13<1:17:11,  4.26s/it, lr: 5.0e-05 loss: 2.403e-01]
leoprint:  55%|#####4    | 1313/2400 [19:16<1:17:11,  4.26s/it, lr: 5.0e-05 loss: 3.120e-01]
leoprint:  55%|#####4    | 1313/2400 [19:16<1:17:11,  4.26s/it, lr: 5.0e-05 loss: 3.120e-01]
leoprint:  55%|#####4    | 1314/2400 [19:16<1:13:26,  4.06s/it, lr: 5.0e-05 loss: 3.120e-01]
leoprint:  55%|#####4    | 1314/2400 [19:16<1:13:26,  4.06s/it, lr: 5.0e-05 loss: 3.120e-01]
leoprint:  55%|#####4    | 1314/2400 [19:20<1:13:26,  4.06s/it, lr: 5.0e-05 loss: 3.542e-01]
leoprint:  55%|#####4    | 1314/2400 [19:20<1:13:26,  4.06s/it, lr: 5.0e-05 loss: 3.542e-01]
leoprint:  55%|#####4    | 1315/2400 [19:20<1:11:13,  3.94s/it, lr: 5.0e-05 loss: 3.542e-01]
leoprint:  55%|#####4    | 1315/2400 [19:20<1:11:13,  3.94s/it, lr: 5.0e-05 loss: 3.542e-01]
leoprint:  55%|#####4    | 1315/2400 [19:23<1:11:13,  3.94s/it, lr: 5.0e-05 loss: 3.184e-01]
leoprint:  55%|#####4    | 1315/2400 [19:23<1:11:13,  3.94s/it, lr: 5.0e-05 loss: 3.184e-01]
leoprint:  55%|#####4    | 1316/2400 [19:23<1:08:56,  3.82s/it, lr: 5.0e-05 loss: 3.184e-01]
leoprint:  55%|#####4    | 1316/2400 [19:23<1:08:56,  3.82s/it, lr: 5.0e-05 loss: 3.184e-01]
leoprint:  55%|#####4    | 1316/2400 [19:27<1:08:56,  3.82s/it, lr: 5.0e-05 loss: 3.159e-01]
leoprint:  55%|#####4    | 1316/2400 [19:27<1:08:56,  3.82s/it, lr: 5.0e-05 loss: 3.159e-01]
leoprint:  55%|#####4    | 1317/2400 [19:27<1:07:13,  3.72s/it, lr: 5.0e-05 loss: 3.159e-01]
leoprint:  55%|#####4    | 1317/2400 [19:27<1:07:13,  3.72s/it, lr: 5.0e-05 loss: 3.159e-01]
leoprint:  55%|#####4    | 1317/2400 [19:30<1:07:13,  3.72s/it, lr: 5.0e-05 loss: 2.622e-01]
leoprint:  55%|#####4    | 1317/2400 [19:30<1:07:13,  3.72s/it, lr: 5.0e-05 loss: 2.622e-01]
leoprint:  55%|#####4    | 1318/2400 [19:30<1:06:34,  3.69s/it, lr: 5.0e-05 loss: 2.622e-01]
leoprint:  55%|#####4    | 1318/2400 [19:30<1:06:34,  3.69s/it, lr: 5.0e-05 loss: 2.622e-01]
leoprint:  55%|#####4    | 1318/2400 [19:34<1:06:34,  3.69s/it, lr: 5.0e-05 loss: 2.826e-01]
leoprint:  55%|#####4    | 1318/2400 [19:34<1:06:34,  3.69s/it, lr: 5.0e-05 loss: 2.826e-01]
leoprint:  55%|#####4    | 1319/2400 [19:34<1:05:32,  3.64s/it, lr: 5.0e-05 loss: 2.826e-01]
leoprint:  55%|#####4    | 1319/2400 [19:34<1:05:32,  3.64s/it, lr: 5.0e-05 loss: 2.826e-01]
leoprint:  55%|#####4    | 1319/2400 [19:38<1:05:32,  3.64s/it, lr: 5.0e-05 loss: 2.055e-01]
leoprint:  55%|#####4    | 1319/2400 [19:38<1:05:32,  3.64s/it, lr: 5.0e-05 loss: 2.055e-01]
leoprint:  55%|#####5    | 1320/2400 [19:41<1:05:28,  3.64s/it, lr: 5.0e-05 loss: 2.972e-01]
leoprint:  55%|#####5    | 1320/2400 [19:41<1:05:28,  3.64s/it, lr: 5.0e-05 loss: 2.972e-01]
leoprint:  55%|#####5    | 1321/2400 [19:41<50:01,  2.78s/it, lr: 5.0e-05 loss: 2.972e-01]  
leoprint:  55%|#####5    | 1321/2400 [19:41<50:01,  2.78s/it, lr: 5.0e-05 loss: 2.972e-01]  
leoprint:  55%|#####5    | 1321/2400 [19:45<50:01,  2.78s/it, lr: 5.0e-05 loss: 3.878e-01]
leoprint:  55%|#####5    | 1321/2400 [19:45<50:01,  2.78s/it, lr: 5.0e-05 loss: 3.878e-01]
leoprint:  55%|#####5    | 1322/2400 [19:45<53:09,  2.96s/it, lr: 5.0e-05 loss: 3.878e-01]
leoprint:  55%|#####5    | 1322/2400 [19:45<53:09,  2.96s/it, lr: 5.0e-05 loss: 3.878e-01]
leoprint:  55%|#####5    | 1322/2400 [19:48<53:09,  2.96s/it, lr: 5.0e-05 loss: 2.986e-01]
leoprint:  55%|#####5    | 1322/2400 [19:48<53:09,  2.96s/it, lr: 5.0e-05 loss: 2.986e-01]
leoprint:  55%|#####5    | 1323/2400 [19:48<56:13,  3.13s/it, lr: 5.0e-05 loss: 2.986e-01]
leoprint:  55%|#####5    | 1323/2400 [19:48<56:13,  3.13s/it, lr: 5.0e-05 loss: 2.986e-01]
leoprint:  55%|#####5    | 1323/2400 [19:52<56:13,  3.13s/it, lr: 5.0e-05 loss: 2.852e-01]
leoprint:  55%|#####5    | 1323/2400 [19:52<56:13,  3.13s/it, lr: 5.0e-05 loss: 2.852e-01]
leoprint:  55%|#####5    | 1324/2400 [19:52<57:58,  3.23s/it, lr: 5.0e-05 loss: 2.852e-01]
leoprint:  55%|#####5    | 1324/2400 [19:52<57:58,  3.23s/it, lr: 5.0e-05 loss: 2.852e-01]
leoprint:  55%|#####5    | 1324/2400 [19:59<57:58,  3.23s/it, lr: 5.0e-05 loss: 3.043e-01]
leoprint:  55%|#####5    | 1324/2400 [19:59<57:58,  3.23s/it, lr: 5.0e-05 loss: 3.043e-01]
leoprint:  55%|#####5    | 1325/2400 [19:59<1:16:26,  4.27s/it, lr: 5.0e-05 loss: 3.043e-01]
leoprint:  55%|#####5    | 1325/2400 [19:59<1:16:26,  4.27s/it, lr: 5.0e-05 loss: 3.043e-01]
leoprint:  55%|#####5    | 1325/2400 [20:09<1:16:26,  4.27s/it, lr: 5.0e-05 loss: 2.235e-01]
leoprint:  55%|#####5    | 1325/2400 [20:09<1:16:26,  4.27s/it, lr: 5.0e-05 loss: 2.235e-01]
leoprint:  55%|#####5    | 1326/2400 [20:09<1:45:01,  5.87s/it, lr: 5.0e-05 loss: 2.235e-01]
leoprint:  55%|#####5    | 1326/2400 [20:09<1:45:01,  5.87s/it, lr: 5.0e-05 loss: 2.235e-01]
leoprint:  55%|#####5    | 1326/2400 [20:18<1:45:01,  5.87s/it, lr: 5.0e-05 loss: 4.034e-01]
leoprint:  55%|#####5    | 1326/2400 [20:18<1:45:01,  5.87s/it, lr: 5.0e-05 loss: 4.034e-01]
leoprint:  55%|#####5    | 1327/2400 [20:18<2:04:25,  6.96s/it, lr: 5.0e-05 loss: 4.034e-01]
leoprint:  55%|#####5    | 1327/2400 [20:18<2:04:25,  6.96s/it, lr: 5.0e-05 loss: 4.034e-01]
leoprint:  55%|#####5    | 1327/2400 [20:24<2:04:25,  6.96s/it, lr: 5.0e-05 loss: 2.635e-01]
leoprint:  55%|#####5    | 1327/2400 [20:24<2:04:25,  6.96s/it, lr: 5.0e-05 loss: 2.635e-01]
leoprint:  55%|#####5    | 1328/2400 [20:24<1:57:45,  6.59s/it, lr: 5.0e-05 loss: 2.635e-01]
leoprint:  55%|#####5    | 1328/2400 [20:24<1:57:45,  6.59s/it, lr: 5.0e-05 loss: 2.635e-01]
leoprint:  55%|#####5    | 1328/2400 [20:33<1:57:45,  6.59s/it, lr: 5.0e-05 loss: 2.366e-01]
leoprint:  55%|#####5    | 1328/2400 [20:33<1:57:45,  6.59s/it, lr: 5.0e-05 loss: 2.366e-01]
leoprint:  55%|#####5    | 1329/2400 [20:33<2:08:48,  7.22s/it, lr: 5.0e-05 loss: 2.366e-01]
leoprint:  55%|#####5    | 1329/2400 [20:33<2:08:48,  7.22s/it, lr: 5.0e-05 loss: 2.366e-01]
leoprint:  55%|#####5    | 1329/2400 [20:42<2:08:48,  7.22s/it, lr: 5.0e-05 loss: 3.888e-01]
leoprint:  55%|#####5    | 1329/2400 [20:42<2:08:48,  7.22s/it, lr: 5.0e-05 loss: 3.888e-01]
leoprint:  55%|#####5    | 1330/2400 [20:52<2:08:41,  7.22s/it, lr: 5.0e-05 loss: 2.889e-01]
leoprint:  55%|#####5    | 1330/2400 [20:52<2:08:41,  7.22s/it, lr: 5.0e-05 loss: 2.889e-01]
leoprint:  55%|#####5    | 1331/2400 [20:52<1:49:47,  6.16s/it, lr: 5.0e-05 loss: 2.889e-01]
leoprint:  55%|#####5    | 1331/2400 [20:52<1:49:47,  6.16s/it, lr: 5.0e-05 loss: 2.889e-01]
leoprint:  55%|#####5    | 1331/2400 [20:56<1:49:47,  6.16s/it, lr: 5.0e-05 loss: 2.971e-01]
leoprint:  55%|#####5    | 1331/2400 [20:56<1:49:47,  6.16s/it, lr: 5.0e-05 loss: 2.971e-01]
leoprint:  56%|#####5    | 1332/2400 [20:56<1:39:29,  5.59s/it, lr: 5.0e-05 loss: 2.971e-01]
leoprint:  56%|#####5    | 1332/2400 [20:56<1:39:29,  5.59s/it, lr: 5.0e-05 loss: 2.971e-01]
leoprint:  56%|#####5    | 1332/2400 [21:00<1:39:29,  5.59s/it, lr: 5.0e-05 loss: 2.893e-01]
leoprint:  56%|#####5    | 1332/2400 [21:00<1:39:29,  5.59s/it, lr: 5.0e-05 loss: 2.893e-01]
leoprint:  56%|#####5    | 1333/2400 [21:00<1:29:46,  5.05s/it, lr: 5.0e-05 loss: 2.893e-01]
leoprint:  56%|#####5    | 1333/2400 [21:00<1:29:46,  5.05s/it, lr: 5.0e-05 loss: 2.893e-01]
leoprint:  56%|#####5    | 1333/2400 [21:03<1:29:46,  5.05s/it, lr: 5.0e-05 loss: 3.633e-01]
leoprint:  56%|#####5    | 1333/2400 [21:03<1:29:46,  5.05s/it, lr: 5.0e-05 loss: 3.633e-01]
leoprint:  56%|#####5    | 1334/2400 [21:03<1:22:15,  4.63s/it, lr: 5.0e-05 loss: 3.633e-01]
leoprint:  56%|#####5    | 1334/2400 [21:03<1:22:15,  4.63s/it, lr: 5.0e-05 loss: 3.633e-01]
leoprint:  56%|#####5    | 1334/2400 [21:07<1:22:15,  4.63s/it, lr: 5.0e-05 loss: 2.339e-01]
leoprint:  56%|#####5    | 1334/2400 [21:07<1:22:15,  4.63s/it, lr: 5.0e-05 loss: 2.339e-01]
leoprint:  56%|#####5    | 1335/2400 [21:07<1:16:37,  4.32s/it, lr: 5.0e-05 loss: 2.339e-01]
leoprint:  56%|#####5    | 1335/2400 [21:07<1:16:37,  4.32s/it, lr: 5.0e-05 loss: 2.339e-01]
leoprint:  56%|#####5    | 1335/2400 [21:10<1:16:37,  4.32s/it, lr: 5.0e-05 loss: 2.623e-01]
leoprint:  56%|#####5    | 1335/2400 [21:10<1:16:37,  4.32s/it, lr: 5.0e-05 loss: 2.623e-01]
leoprint:  56%|#####5    | 1336/2400 [21:10<1:12:28,  4.09s/it, lr: 5.0e-05 loss: 2.623e-01]
leoprint:  56%|#####5    | 1336/2400 [21:10<1:12:28,  4.09s/it, lr: 5.0e-05 loss: 2.623e-01]
leoprint:  56%|#####5    | 1336/2400 [21:14<1:12:28,  4.09s/it, lr: 5.0e-05 loss: 2.300e-01]
leoprint:  56%|#####5    | 1336/2400 [21:14<1:12:28,  4.09s/it, lr: 5.0e-05 loss: 2.300e-01]
leoprint:  56%|#####5    | 1337/2400 [21:14<1:10:19,  3.97s/it, lr: 5.0e-05 loss: 2.300e-01]
leoprint:  56%|#####5    | 1337/2400 [21:14<1:10:19,  3.97s/it, lr: 5.0e-05 loss: 2.300e-01]
leoprint:  56%|#####5    | 1337/2400 [21:17<1:10:19,  3.97s/it, lr: 5.0e-05 loss: 2.786e-01]
leoprint:  56%|#####5    | 1337/2400 [21:17<1:10:19,  3.97s/it, lr: 5.0e-05 loss: 2.786e-01]
leoprint:  56%|#####5    | 1338/2400 [21:17<1:07:50,  3.83s/it, lr: 5.0e-05 loss: 2.786e-01]
leoprint:  56%|#####5    | 1338/2400 [21:17<1:07:50,  3.83s/it, lr: 5.0e-05 loss: 2.786e-01]
leoprint:  56%|#####5    | 1338/2400 [21:21<1:07:50,  3.83s/it, lr: 5.0e-05 loss: 3.377e-01]
leoprint:  56%|#####5    | 1338/2400 [21:21<1:07:50,  3.83s/it, lr: 5.0e-05 loss: 3.377e-01]
leoprint:  56%|#####5    | 1339/2400 [21:21<1:06:07,  3.74s/it, lr: 5.0e-05 loss: 3.377e-01]
leoprint:  56%|#####5    | 1339/2400 [21:21<1:06:07,  3.74s/it, lr: 5.0e-05 loss: 3.377e-01]
leoprint:  56%|#####5    | 1339/2400 [21:24<1:06:07,  3.74s/it, lr: 5.0e-05 loss: 2.311e-01]
leoprint:  56%|#####5    | 1339/2400 [21:24<1:06:07,  3.74s/it, lr: 5.0e-05 loss: 2.311e-01]
leoprint:  56%|#####5    | 1340/2400 [21:28<1:06:03,  3.74s/it, lr: 5.0e-05 loss: 2.630e-01]
leoprint:  56%|#####5    | 1340/2400 [21:28<1:06:03,  3.74s/it, lr: 5.0e-05 loss: 2.630e-01]
leoprint:  56%|#####5    | 1341/2400 [21:28<50:00,  2.83s/it, lr: 5.0e-05 loss: 2.630e-01]  
leoprint:  56%|#####5    | 1341/2400 [21:28<50:00,  2.83s/it, lr: 5.0e-05 loss: 2.630e-01]  
leoprint:  56%|#####5    | 1341/2400 [21:35<50:00,  2.83s/it, lr: 5.0e-05 loss: 1.855e-01]
leoprint:  56%|#####5    | 1341/2400 [21:35<50:00,  2.83s/it, lr: 5.0e-05 loss: 1.855e-01]
leoprint:  56%|#####5    | 1342/2400 [21:35<1:09:29,  3.94s/it, lr: 5.0e-05 loss: 1.855e-01]
leoprint:  56%|#####5    | 1342/2400 [21:35<1:09:29,  3.94s/it, lr: 5.0e-05 loss: 1.855e-01]
leoprint:  56%|#####5    | 1342/2400 [21:45<1:09:29,  3.94s/it, lr: 5.0e-05 loss: 3.382e-01]
leoprint:  56%|#####5    | 1342/2400 [21:45<1:09:29,  3.94s/it, lr: 5.0e-05 loss: 3.382e-01]
leoprint:  56%|#####5    | 1343/2400 [21:45<1:35:51,  5.44s/it, lr: 5.0e-05 loss: 3.382e-01]
leoprint:  56%|#####5    | 1343/2400 [21:45<1:35:51,  5.44s/it, lr: 5.0e-05 loss: 3.382e-01]
leoprint:  56%|#####5    | 1343/2400 [21:55<1:35:51,  5.44s/it, lr: 5.0e-05 loss: 2.475e-01]
leoprint:  56%|#####5    | 1343/2400 [21:55<1:35:51,  5.44s/it, lr: 5.0e-05 loss: 2.475e-01]
leoprint:  56%|#####6    | 1344/2400 [21:55<1:55:53,  6.58s/it, lr: 5.0e-05 loss: 2.475e-01]
leoprint:  56%|#####6    | 1344/2400 [21:55<1:55:53,  6.58s/it, lr: 5.0e-05 loss: 2.475e-01]
leoprint:  56%|#####6    | 1344/2400 [22:00<1:55:53,  6.58s/it, lr: 5.0e-05 loss: 2.299e-01]
leoprint:  56%|#####6    | 1344/2400 [22:00<1:55:53,  6.58s/it, lr: 5.0e-05 loss: 2.299e-01]
leoprint:  56%|#####6    | 1345/2400 [22:00<1:51:05,  6.32s/it, lr: 5.0e-05 loss: 2.299e-01]
leoprint:  56%|#####6    | 1345/2400 [22:00<1:51:05,  6.32s/it, lr: 5.0e-05 loss: 2.299e-01]
leoprint:  56%|#####6    | 1345/2400 [22:04<1:51:05,  6.32s/it, lr: 5.0e-05 loss: 2.555e-01]
leoprint:  56%|#####6    | 1345/2400 [22:04<1:51:05,  6.32s/it, lr: 5.0e-05 loss: 2.555e-01]
leoprint:  56%|#####6    | 1346/2400 [22:04<1:36:56,  5.52s/it, lr: 5.0e-05 loss: 2.555e-01]
leoprint:  56%|#####6    | 1346/2400 [22:04<1:36:56,  5.52s/it, lr: 5.0e-05 loss: 2.555e-01]
leoprint:  56%|#####6    | 1346/2400 [22:07<1:36:56,  5.52s/it, lr: 5.0e-05 loss: 3.953e-01]
leoprint:  56%|#####6    | 1346/2400 [22:07<1:36:56,  5.52s/it, lr: 5.0e-05 loss: 3.953e-01]
leoprint:  56%|#####6    | 1347/2400 [22:07<1:26:48,  4.95s/it, lr: 5.0e-05 loss: 3.953e-01]
leoprint:  56%|#####6    | 1347/2400 [22:07<1:26:48,  4.95s/it, lr: 5.0e-05 loss: 3.953e-01]
leoprint:  56%|#####6    | 1347/2400 [22:11<1:26:48,  4.95s/it, lr: 5.0e-05 loss: 2.989e-01]
leoprint:  56%|#####6    | 1347/2400 [22:11<1:26:48,  4.95s/it, lr: 5.0e-05 loss: 2.989e-01]
leoprint:  56%|#####6    | 1348/2400 [22:11<1:19:20,  4.53s/it, lr: 5.0e-05 loss: 2.989e-01]
leoprint:  56%|#####6    | 1348/2400 [22:11<1:19:20,  4.53s/it, lr: 5.0e-05 loss: 2.989e-01]
leoprint:  56%|#####6    | 1348/2400 [22:15<1:19:20,  4.53s/it, lr: 5.0e-05 loss: 2.323e-01]
leoprint:  56%|#####6    | 1348/2400 [22:15<1:19:20,  4.53s/it, lr: 5.0e-05 loss: 2.323e-01]
leoprint:  56%|#####6    | 1349/2400 [22:15<1:14:41,  4.26s/it, lr: 5.0e-05 loss: 2.323e-01]
leoprint:  56%|#####6    | 1349/2400 [22:15<1:14:41,  4.26s/it, lr: 5.0e-05 loss: 2.323e-01]
leoprint:  56%|#####6    | 1349/2400 [22:18<1:14:41,  4.26s/it, lr: 5.0e-05 loss: 3.983e-01]
leoprint:  56%|#####6    | 1349/2400 [22:18<1:14:41,  4.26s/it, lr: 5.0e-05 loss: 3.983e-01]
leoprint:  56%|#####6    | 1350/2400 [22:22<1:14:37,  4.26s/it, lr: 5.0e-05 loss: 2.693e-01]
leoprint:  56%|#####6    | 1350/2400 [22:22<1:14:37,  4.26s/it, lr: 5.0e-05 loss: 2.693e-01]
leoprint:  56%|#####6    | 1351/2400 [22:22<54:55,  3.14s/it, lr: 5.0e-05 loss: 2.693e-01]  
leoprint:  56%|#####6    | 1351/2400 [22:22<54:55,  3.14s/it, lr: 5.0e-05 loss: 2.693e-01]  
leoprint:  56%|#####6    | 1351/2400 [22:25<54:55,  3.14s/it, lr: 5.0e-05 loss: 2.719e-01]
leoprint:  56%|#####6    | 1351/2400 [22:25<54:55,  3.14s/it, lr: 5.0e-05 loss: 2.719e-01]
leoprint:  56%|#####6    | 1352/2400 [22:25<56:28,  3.23s/it, lr: 5.0e-05 loss: 2.719e-01]
leoprint:  56%|#####6    | 1352/2400 [22:25<56:28,  3.23s/it, lr: 5.0e-05 loss: 2.719e-01]
leoprint:  56%|#####6    | 1352/2400 [22:29<56:28,  3.23s/it, lr: 5.0e-05 loss: 2.786e-01]
leoprint:  56%|#####6    | 1352/2400 [22:29<56:28,  3.23s/it, lr: 5.0e-05 loss: 2.786e-01]
leoprint:  56%|#####6    | 1353/2400 [22:29<57:39,  3.30s/it, lr: 5.0e-05 loss: 2.786e-01]
leoprint:  56%|#####6    | 1353/2400 [22:29<57:39,  3.30s/it, lr: 5.0e-05 loss: 2.786e-01]
leoprint:  56%|#####6    | 1353/2400 [22:35<57:39,  3.30s/it, lr: 5.0e-05 loss: 3.402e-01]
leoprint:  56%|#####6    | 1353/2400 [22:35<57:39,  3.30s/it, lr: 5.0e-05 loss: 3.402e-01]
leoprint:  56%|#####6    | 1354/2400 [22:35<1:13:05,  4.19s/it, lr: 5.0e-05 loss: 3.402e-01]
leoprint:  56%|#####6    | 1354/2400 [22:35<1:13:05,  4.19s/it, lr: 5.0e-05 loss: 3.402e-01]
leoprint:  56%|#####6    | 1354/2400 [22:45<1:13:05,  4.19s/it, lr: 5.0e-05 loss: 2.509e-01]
leoprint:  56%|#####6    | 1354/2400 [22:45<1:13:05,  4.19s/it, lr: 5.0e-05 loss: 2.509e-01]
leoprint:  56%|#####6    | 1355/2400 [22:45<1:40:40,  5.78s/it, lr: 5.0e-05 loss: 2.509e-01]
leoprint:  56%|#####6    | 1355/2400 [22:45<1:40:40,  5.78s/it, lr: 5.0e-05 loss: 2.509e-01]
leoprint:  56%|#####6    | 1355/2400 [22:55<1:40:40,  5.78s/it, lr: 5.0e-05 loss: 3.783e-01]
leoprint:  56%|#####6    | 1355/2400 [22:55<1:40:40,  5.78s/it, lr: 5.0e-05 loss: 3.783e-01]
leoprint:  56%|#####6    | 1356/2400 [22:55<1:59:52,  6.89s/it, lr: 5.0e-05 loss: 3.783e-01]
leoprint:  56%|#####6    | 1356/2400 [22:55<1:59:52,  6.89s/it, lr: 5.0e-05 loss: 3.783e-01]
leoprint:  56%|#####6    | 1356/2400 [23:01<1:59:52,  6.89s/it, lr: 5.0e-05 loss: 2.979e-01]
leoprint:  56%|#####6    | 1356/2400 [23:01<1:59:52,  6.89s/it, lr: 5.0e-05 loss: 2.979e-01]
leoprint:  57%|#####6    | 1357/2400 [23:01<1:56:57,  6.73s/it, lr: 5.0e-05 loss: 2.979e-01]
leoprint:  57%|#####6    | 1357/2400 [23:01<1:56:57,  6.73s/it, lr: 5.0e-05 loss: 2.979e-01]
leoprint:  57%|#####6    | 1357/2400 [23:05<1:56:57,  6.73s/it, lr: 5.0e-05 loss: 2.984e-01]
leoprint:  57%|#####6    | 1357/2400 [23:05<1:56:57,  6.73s/it, lr: 5.0e-05 loss: 2.984e-01]
leoprint:  57%|#####6    | 1358/2400 [23:05<1:40:30,  5.79s/it, lr: 5.0e-05 loss: 2.984e-01]
leoprint:  57%|#####6    | 1358/2400 [23:05<1:40:30,  5.79s/it, lr: 5.0e-05 loss: 2.984e-01]
leoprint:  57%|#####6    | 1358/2400 [23:08<1:40:30,  5.79s/it, lr: 5.0e-05 loss: 2.656e-01]
leoprint:  57%|#####6    | 1358/2400 [23:08<1:40:30,  5.79s/it, lr: 5.0e-05 loss: 2.656e-01]
leoprint:  57%|#####6    | 1359/2400 [23:08<1:29:21,  5.15s/it, lr: 5.0e-05 loss: 2.656e-01]
leoprint:  57%|#####6    | 1359/2400 [23:08<1:29:21,  5.15s/it, lr: 5.0e-05 loss: 2.656e-01]
leoprint:  57%|#####6    | 1359/2400 [23:12<1:29:21,  5.15s/it, lr: 5.0e-05 loss: 2.801e-01]
leoprint:  57%|#####6    | 1359/2400 [23:12<1:29:21,  5.15s/it, lr: 5.0e-05 loss: 2.801e-01]
leoprint:  57%|#####6    | 1360/2400 [23:15<1:29:16,  5.15s/it, lr: 5.0e-05 loss: 2.079e-01]
leoprint:  57%|#####6    | 1360/2400 [23:15<1:29:16,  5.15s/it, lr: 5.0e-05 loss: 2.079e-01]
leoprint:  57%|#####6    | 1361/2400 [23:15<1:02:17,  3.60s/it, lr: 5.0e-05 loss: 2.079e-01]
leoprint:  57%|#####6    | 1361/2400 [23:15<1:02:17,  3.60s/it, lr: 5.0e-05 loss: 2.079e-01]
leoprint:  57%|#####6    | 1361/2400 [23:19<1:02:17,  3.60s/it, lr: 5.0e-05 loss: 3.565e-01]
leoprint:  57%|#####6    | 1361/2400 [23:19<1:02:17,  3.60s/it, lr: 5.0e-05 loss: 3.565e-01]
leoprint:  57%|#####6    | 1362/2400 [23:19<1:01:49,  3.57s/it, lr: 5.0e-05 loss: 3.565e-01]
leoprint:  57%|#####6    | 1362/2400 [23:19<1:01:49,  3.57s/it, lr: 5.0e-05 loss: 3.565e-01]
leoprint:  57%|#####6    | 1362/2400 [23:23<1:01:49,  3.57s/it, lr: 5.0e-05 loss: 2.036e-01]
leoprint:  57%|#####6    | 1362/2400 [23:23<1:01:49,  3.57s/it, lr: 5.0e-05 loss: 2.036e-01]
leoprint:  57%|#####6    | 1363/2400 [23:23<1:01:59,  3.59s/it, lr: 5.0e-05 loss: 2.036e-01]
leoprint:  57%|#####6    | 1363/2400 [23:23<1:01:59,  3.59s/it, lr: 5.0e-05 loss: 2.036e-01]
leoprint:  57%|#####6    | 1363/2400 [23:26<1:01:59,  3.59s/it, lr: 5.0e-05 loss: 3.240e-01]
leoprint:  57%|#####6    | 1363/2400 [23:26<1:01:59,  3.59s/it, lr: 5.0e-05 loss: 3.240e-01]
leoprint:  57%|#####6    | 1364/2400 [23:26<1:01:34,  3.57s/it, lr: 5.0e-05 loss: 3.240e-01]
leoprint:  57%|#####6    | 1364/2400 [23:26<1:01:34,  3.57s/it, lr: 5.0e-05 loss: 3.240e-01]
leoprint:  57%|#####6    | 1364/2400 [23:30<1:01:34,  3.57s/it, lr: 5.0e-05 loss: 3.444e-01]
leoprint:  57%|#####6    | 1364/2400 [23:30<1:01:34,  3.57s/it, lr: 5.0e-05 loss: 3.444e-01]
leoprint:  57%|#####6    | 1365/2400 [23:30<1:01:14,  3.55s/it, lr: 5.0e-05 loss: 3.444e-01]
leoprint:  57%|#####6    | 1365/2400 [23:30<1:01:14,  3.55s/it, lr: 5.0e-05 loss: 3.444e-01]
leoprint:  57%|#####6    | 1365/2400 [23:33<1:01:14,  3.55s/it, lr: 5.0e-05 loss: 2.485e-01]
leoprint:  57%|#####6    | 1365/2400 [23:33<1:01:14,  3.55s/it, lr: 5.0e-05 loss: 2.485e-01]
leoprint:  57%|#####6    | 1366/2400 [23:33<1:02:03,  3.60s/it, lr: 5.0e-05 loss: 2.485e-01]
leoprint:  57%|#####6    | 1366/2400 [23:33<1:02:03,  3.60s/it, lr: 5.0e-05 loss: 2.485e-01]
leoprint:  57%|#####6    | 1366/2400 [23:37<1:02:03,  3.60s/it, lr: 5.0e-05 loss: 3.701e-01]
leoprint:  57%|#####6    | 1366/2400 [23:37<1:02:03,  3.60s/it, lr: 5.0e-05 loss: 3.701e-01]
leoprint:  57%|#####6    | 1367/2400 [23:37<1:01:29,  3.57s/it, lr: 5.0e-05 loss: 3.701e-01]
leoprint:  57%|#####6    | 1367/2400 [23:37<1:01:29,  3.57s/it, lr: 5.0e-05 loss: 3.701e-01]
leoprint:  57%|#####6    | 1367/2400 [23:40<1:01:29,  3.57s/it, lr: 5.0e-05 loss: 3.324e-01]
leoprint:  57%|#####6    | 1367/2400 [23:40<1:01:29,  3.57s/it, lr: 5.0e-05 loss: 3.324e-01]
leoprint:  57%|#####6    | 1368/2400 [23:40<1:01:05,  3.55s/it, lr: 5.0e-05 loss: 3.324e-01]
leoprint:  57%|#####6    | 1368/2400 [23:40<1:01:05,  3.55s/it, lr: 5.0e-05 loss: 3.324e-01]
leoprint:  57%|#####6    | 1368/2400 [23:44<1:01:05,  3.55s/it, lr: 5.0e-05 loss: 1.798e-01]
leoprint:  57%|#####6    | 1368/2400 [23:44<1:01:05,  3.55s/it, lr: 5.0e-05 loss: 1.798e-01]
leoprint:  57%|#####7    | 1369/2400 [23:44<1:01:24,  3.57s/it, lr: 5.0e-05 loss: 1.798e-01]
leoprint:  57%|#####7    | 1369/2400 [23:44<1:01:24,  3.57s/it, lr: 5.0e-05 loss: 1.798e-01]
leoprint:  57%|#####7    | 1369/2400 [23:48<1:01:24,  3.57s/it, lr: 5.0e-05 loss: 2.644e-01]
leoprint:  57%|#####7    | 1369/2400 [23:48<1:01:24,  3.57s/it, lr: 5.0e-05 loss: 2.644e-01]
leoprint:  57%|#####7    | 1370/2400 [23:51<1:01:20,  3.57s/it, lr: 5.0e-05 loss: 2.877e-01]
leoprint:  57%|#####7    | 1370/2400 [23:51<1:01:20,  3.57s/it, lr: 5.0e-05 loss: 2.877e-01]
leoprint:  57%|#####7    | 1371/2400 [23:51<47:14,  2.76s/it, lr: 5.0e-05 loss: 2.877e-01]  
leoprint:  57%|#####7    | 1371/2400 [23:51<47:14,  2.76s/it, lr: 5.0e-05 loss: 2.877e-01]  
leoprint:  57%|#####7    | 1371/2400 [23:55<47:14,  2.76s/it, lr: 5.0e-05 loss: 3.350e-01]
leoprint:  57%|#####7    | 1371/2400 [23:55<47:14,  2.76s/it, lr: 5.0e-05 loss: 3.350e-01]
leoprint:  57%|#####7    | 1372/2400 [23:55<50:20,  2.94s/it, lr: 5.0e-05 loss: 3.350e-01]
leoprint:  57%|#####7    | 1372/2400 [23:55<50:20,  2.94s/it, lr: 5.0e-05 loss: 3.350e-01]
leoprint:  57%|#####7    | 1372/2400 [23:58<50:20,  2.94s/it, lr: 5.0e-05 loss: 3.088e-01]
leoprint:  57%|#####7    | 1372/2400 [23:58<50:20,  2.94s/it, lr: 5.0e-05 loss: 3.088e-01]
leoprint:  57%|#####7    | 1373/2400 [23:58<52:47,  3.08s/it, lr: 5.0e-05 loss: 3.088e-01]
leoprint:  57%|#####7    | 1373/2400 [23:58<52:47,  3.08s/it, lr: 5.0e-05 loss: 3.088e-01]
leoprint:  57%|#####7    | 1373/2400 [24:02<52:47,  3.08s/it, lr: 5.0e-05 loss: 3.536e-01]
leoprint:  57%|#####7    | 1373/2400 [24:02<52:47,  3.08s/it, lr: 5.0e-05 loss: 3.536e-01]
leoprint:  57%|#####7    | 1374/2400 [24:02<54:41,  3.20s/it, lr: 5.0e-05 loss: 3.536e-01]
leoprint:  57%|#####7    | 1374/2400 [24:02<54:41,  3.20s/it, lr: 5.0e-05 loss: 3.536e-01]
leoprint:  57%|#####7    | 1374/2400 [24:05<54:41,  3.20s/it, lr: 5.0e-05 loss: 2.463e-01]
leoprint:  57%|#####7    | 1374/2400 [24:05<54:41,  3.20s/it, lr: 5.0e-05 loss: 2.463e-01]
leoprint:  57%|#####7    | 1375/2400 [24:05<56:40,  3.32s/it, lr: 5.0e-05 loss: 2.463e-01]
leoprint:  57%|#####7    | 1375/2400 [24:05<56:40,  3.32s/it, lr: 5.0e-05 loss: 2.463e-01]
leoprint:  57%|#####7    | 1375/2400 [24:09<56:40,  3.32s/it, lr: 5.0e-05 loss: 2.742e-01]
leoprint:  57%|#####7    | 1375/2400 [24:09<56:40,  3.32s/it, lr: 5.0e-05 loss: 2.742e-01]
leoprint:  57%|#####7    | 1376/2400 [24:09<58:06,  3.41s/it, lr: 5.0e-05 loss: 2.742e-01]
leoprint:  57%|#####7    | 1376/2400 [24:09<58:06,  3.41s/it, lr: 5.0e-05 loss: 2.742e-01]
leoprint:  57%|#####7    | 1376/2400 [24:13<58:06,  3.41s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  57%|#####7    | 1376/2400 [24:13<58:06,  3.41s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  57%|#####7    | 1377/2400 [24:13<59:27,  3.49s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  57%|#####7    | 1377/2400 [24:13<59:27,  3.49s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  57%|#####7    | 1377/2400 [24:16<59:27,  3.49s/it, lr: 5.0e-05 loss: 3.379e-01]
leoprint:  57%|#####7    | 1377/2400 [24:16<59:27,  3.49s/it, lr: 5.0e-05 loss: 3.379e-01]
leoprint:  57%|#####7    | 1378/2400 [24:16<59:29,  3.49s/it, lr: 5.0e-05 loss: 3.379e-01]
leoprint:  57%|#####7    | 1378/2400 [24:16<59:29,  3.49s/it, lr: 5.0e-05 loss: 3.379e-01]
leoprint:  57%|#####7    | 1378/2400 [24:20<59:29,  3.49s/it, lr: 5.0e-05 loss: 2.629e-01]
leoprint:  57%|#####7    | 1378/2400 [24:20<59:29,  3.49s/it, lr: 5.0e-05 loss: 2.629e-01]
leoprint:  57%|#####7    | 1379/2400 [24:20<59:28,  3.50s/it, lr: 5.0e-05 loss: 2.629e-01]
leoprint:  57%|#####7    | 1379/2400 [24:20<59:28,  3.50s/it, lr: 5.0e-05 loss: 2.629e-01]
leoprint:  57%|#####7    | 1379/2400 [24:23<59:28,  3.50s/it, lr: 5.0e-05 loss: 2.656e-01]
leoprint:  57%|#####7    | 1379/2400 [24:23<59:28,  3.50s/it, lr: 5.0e-05 loss: 2.656e-01]
leoprint:  57%|#####7    | 1380/2400 [24:27<59:25,  3.50s/it, lr: 5.0e-05 loss: 2.345e-01]
leoprint:  57%|#####7    | 1380/2400 [24:27<59:25,  3.50s/it, lr: 5.0e-05 loss: 2.345e-01]
leoprint:  58%|#####7    | 1381/2400 [24:27<45:48,  2.70s/it, lr: 5.0e-05 loss: 2.345e-01]
leoprint:  58%|#####7    | 1381/2400 [24:27<45:48,  2.70s/it, lr: 5.0e-05 loss: 2.345e-01]
leoprint:  58%|#####7    | 1381/2400 [24:30<45:48,  2.70s/it, lr: 5.0e-05 loss: 2.194e-01]
leoprint:  58%|#####7    | 1381/2400 [24:30<45:48,  2.70s/it, lr: 5.0e-05 loss: 2.194e-01]
leoprint:  58%|#####7    | 1382/2400 [24:30<49:07,  2.89s/it, lr: 5.0e-05 loss: 2.194e-01]
leoprint:  58%|#####7    | 1382/2400 [24:30<49:07,  2.89s/it, lr: 5.0e-05 loss: 2.194e-01]
leoprint:  58%|#####7    | 1382/2400 [24:34<49:07,  2.89s/it, lr: 5.0e-05 loss: 3.088e-01]
leoprint:  58%|#####7    | 1382/2400 [24:34<49:07,  2.89s/it, lr: 5.0e-05 loss: 3.088e-01]
leoprint:  58%|#####7    | 1383/2400 [24:34<52:20,  3.09s/it, lr: 5.0e-05 loss: 3.088e-01]
leoprint:  58%|#####7    | 1383/2400 [24:34<52:20,  3.09s/it, lr: 5.0e-05 loss: 3.088e-01]
leoprint:  58%|#####7    | 1383/2400 [24:38<52:20,  3.09s/it, lr: 5.0e-05 loss: 2.290e-01]
leoprint:  58%|#####7    | 1383/2400 [24:38<52:20,  3.09s/it, lr: 5.0e-05 loss: 2.290e-01]
leoprint:  58%|#####7    | 1384/2400 [24:38<54:41,  3.23s/it, lr: 5.0e-05 loss: 2.290e-01]
leoprint:  58%|#####7    | 1384/2400 [24:38<54:41,  3.23s/it, lr: 5.0e-05 loss: 2.290e-01]
leoprint:  58%|#####7    | 1384/2400 [24:41<54:41,  3.23s/it, lr: 5.0e-05 loss: 2.833e-01]
leoprint:  58%|#####7    | 1384/2400 [24:41<54:41,  3.23s/it, lr: 5.0e-05 loss: 2.833e-01]
leoprint:  58%|#####7    | 1385/2400 [24:41<55:54,  3.30s/it, lr: 5.0e-05 loss: 2.833e-01]
leoprint:  58%|#####7    | 1385/2400 [24:41<55:54,  3.30s/it, lr: 5.0e-05 loss: 2.833e-01]
leoprint:  58%|#####7    | 1385/2400 [24:45<55:54,  3.30s/it, lr: 5.0e-05 loss: 3.164e-01]
leoprint:  58%|#####7    | 1385/2400 [24:45<55:54,  3.30s/it, lr: 5.0e-05 loss: 3.164e-01]
leoprint:  58%|#####7    | 1386/2400 [24:45<56:46,  3.36s/it, lr: 5.0e-05 loss: 3.164e-01]
leoprint:  58%|#####7    | 1386/2400 [24:45<56:46,  3.36s/it, lr: 5.0e-05 loss: 3.164e-01]
leoprint:  58%|#####7    | 1386/2400 [24:48<56:46,  3.36s/it, lr: 5.0e-05 loss: 3.133e-01]
leoprint:  58%|#####7    | 1386/2400 [24:48<56:46,  3.36s/it, lr: 5.0e-05 loss: 3.133e-01]
leoprint:  58%|#####7    | 1387/2400 [24:48<57:56,  3.43s/it, lr: 5.0e-05 loss: 3.133e-01]
leoprint:  58%|#####7    | 1387/2400 [24:48<57:56,  3.43s/it, lr: 5.0e-05 loss: 3.133e-01]
leoprint:  58%|#####7    | 1387/2400 [24:52<57:56,  3.43s/it, lr: 5.0e-05 loss: 2.464e-01]
leoprint:  58%|#####7    | 1387/2400 [24:52<57:56,  3.43s/it, lr: 5.0e-05 loss: 2.464e-01]
leoprint:  58%|#####7    | 1388/2400 [24:52<59:03,  3.50s/it, lr: 5.0e-05 loss: 2.464e-01]
leoprint:  58%|#####7    | 1388/2400 [24:52<59:03,  3.50s/it, lr: 5.0e-05 loss: 2.464e-01]
leoprint:  58%|#####7    | 1388/2400 [24:55<59:03,  3.50s/it, lr: 5.0e-05 loss: 2.481e-01]
leoprint:  58%|#####7    | 1388/2400 [24:55<59:03,  3.50s/it, lr: 5.0e-05 loss: 2.481e-01]
leoprint:  58%|#####7    | 1389/2400 [24:55<59:32,  3.53s/it, lr: 5.0e-05 loss: 2.481e-01]
leoprint:  58%|#####7    | 1389/2400 [24:55<59:32,  3.53s/it, lr: 5.0e-05 loss: 2.481e-01]
leoprint:  58%|#####7    | 1389/2400 [24:59<59:32,  3.53s/it, lr: 5.0e-05 loss: 2.661e-01]
leoprint:  58%|#####7    | 1389/2400 [24:59<59:32,  3.53s/it, lr: 5.0e-05 loss: 2.661e-01]
leoprint:  58%|#####7    | 1390/2400 [25:03<59:28,  3.53s/it, lr: 5.0e-05 loss: 2.681e-01]
leoprint:  58%|#####7    | 1390/2400 [25:03<59:28,  3.53s/it, lr: 5.0e-05 loss: 2.681e-01]
leoprint:  58%|#####7    | 1391/2400 [25:03<46:08,  2.74s/it, lr: 5.0e-05 loss: 2.681e-01]
leoprint:  58%|#####7    | 1391/2400 [25:03<46:08,  2.74s/it, lr: 5.0e-05 loss: 2.681e-01]
leoprint:  58%|#####7    | 1391/2400 [25:06<46:08,  2.74s/it, lr: 5.0e-05 loss: 3.323e-01]
leoprint:  58%|#####7    | 1391/2400 [25:06<46:08,  2.74s/it, lr: 5.0e-05 loss: 3.323e-01]
leoprint:  58%|#####8    | 1392/2400 [25:06<49:14,  2.93s/it, lr: 5.0e-05 loss: 3.323e-01]
leoprint:  58%|#####8    | 1392/2400 [25:06<49:14,  2.93s/it, lr: 5.0e-05 loss: 3.323e-01]
leoprint:  58%|#####8    | 1392/2400 [25:10<49:14,  2.93s/it, lr: 5.0e-05 loss: 3.332e-01]
leoprint:  58%|#####8    | 1392/2400 [25:10<49:14,  2.93s/it, lr: 5.0e-05 loss: 3.332e-01]
leoprint:  58%|#####8    | 1393/2400 [25:10<51:38,  3.08s/it, lr: 5.0e-05 loss: 3.332e-01]
leoprint:  58%|#####8    | 1393/2400 [25:10<51:38,  3.08s/it, lr: 5.0e-05 loss: 3.332e-01]
leoprint:  58%|#####8    | 1393/2400 [25:13<51:38,  3.08s/it, lr: 5.0e-05 loss: 2.838e-01]
leoprint:  58%|#####8    | 1393/2400 [25:13<51:38,  3.08s/it, lr: 5.0e-05 loss: 2.838e-01]
leoprint:  58%|#####8    | 1394/2400 [25:13<53:55,  3.22s/it, lr: 5.0e-05 loss: 2.838e-01]
leoprint:  58%|#####8    | 1394/2400 [25:13<53:55,  3.22s/it, lr: 5.0e-05 loss: 2.838e-01]
leoprint:  58%|#####8    | 1394/2400 [25:17<53:55,  3.22s/it, lr: 5.0e-05 loss: 2.656e-01]
leoprint:  58%|#####8    | 1394/2400 [25:17<53:55,  3.22s/it, lr: 5.0e-05 loss: 2.656e-01]
leoprint:  58%|#####8    | 1395/2400 [25:17<55:11,  3.29s/it, lr: 5.0e-05 loss: 2.656e-01]
leoprint:  58%|#####8    | 1395/2400 [25:17<55:11,  3.29s/it, lr: 5.0e-05 loss: 2.656e-01]
leoprint:  58%|#####8    | 1395/2400 [25:20<55:11,  3.29s/it, lr: 5.0e-05 loss: 3.858e-01]
leoprint:  58%|#####8    | 1395/2400 [25:20<55:11,  3.29s/it, lr: 5.0e-05 loss: 3.858e-01]
leoprint:  58%|#####8    | 1396/2400 [25:20<56:07,  3.35s/it, lr: 5.0e-05 loss: 3.858e-01]
leoprint:  58%|#####8    | 1396/2400 [25:20<56:07,  3.35s/it, lr: 5.0e-05 loss: 3.858e-01]
leoprint:  58%|#####8    | 1396/2400 [25:24<56:07,  3.35s/it, lr: 5.0e-05 loss: 3.169e-01]
leoprint:  58%|#####8    | 1396/2400 [25:24<56:07,  3.35s/it, lr: 5.0e-05 loss: 3.169e-01]
leoprint:  58%|#####8    | 1397/2400 [25:24<56:45,  3.40s/it, lr: 5.0e-05 loss: 3.169e-01]
leoprint:  58%|#####8    | 1397/2400 [25:24<56:45,  3.40s/it, lr: 5.0e-05 loss: 3.169e-01]
leoprint:  58%|#####8    | 1397/2400 [25:27<56:45,  3.40s/it, lr: 5.0e-05 loss: 2.627e-01]
leoprint:  58%|#####8    | 1397/2400 [25:27<56:45,  3.40s/it, lr: 5.0e-05 loss: 2.627e-01]
leoprint:  58%|#####8    | 1398/2400 [25:27<57:12,  3.43s/it, lr: 5.0e-05 loss: 2.627e-01]
leoprint:  58%|#####8    | 1398/2400 [25:27<57:12,  3.43s/it, lr: 5.0e-05 loss: 2.627e-01]
leoprint:  58%|#####8    | 1398/2400 [25:31<57:12,  3.43s/it, lr: 5.0e-05 loss: 2.430e-01]
leoprint:  58%|#####8    | 1398/2400 [25:31<57:12,  3.43s/it, lr: 5.0e-05 loss: 2.430e-01]
leoprint:  58%|#####8    | 1399/2400 [25:31<58:03,  3.48s/it, lr: 5.0e-05 loss: 2.430e-01]
leoprint:  58%|#####8    | 1399/2400 [25:31<58:03,  3.48s/it, lr: 5.0e-05 loss: 2.430e-01]
leoprint:  58%|#####8    | 1399/2400 [25:35<58:03,  3.48s/it, lr: 5.0e-05 loss: 2.813e-01]
leoprint:  58%|#####8    | 1399/2400 [25:35<58:03,  3.48s/it, lr: 5.0e-05 loss: 2.813e-01]
+
+
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
+
+
Generating Images:  20%|##        | 1/5 [00:14<00:57, 14.37s/it]
Generating Images:  20%|##        | 1/5 [00:14<00:57, 14.37s/it]
+
+
Generating Images:  40%|####      | 2/5 [00:28<00:43, 14.38s/it]
Generating Images:  40%|####      | 2/5 [00:28<00:43, 14.38s/it]
+
+
Generating Images:  60%|######    | 3/5 [00:43<00:28, 14.38s/it]
Generating Images:  60%|######    | 3/5 [00:43<00:28, 14.38s/it]
+
+
Generating Images:  80%|########  | 4/5 [00:57<00:14, 14.39s/it]
Generating Images:  80%|########  | 4/5 [00:57<00:14, 14.39s/it]
+
+
Generating Images: 100%|##########| 5/5 [01:11<00:00, 14.39s/it]
Generating Images: 100%|##########| 5/5 [01:11<00:00, 14.39s/it]
+
+
                                                                
                                                                
+Saving at step 1400
+Saved checkpoint to /app/ai-toolkit/output/leoprint/leoprint_000001400.safetensors
+Saved optimizer to /app/ai-toolkit/output/leoprint/optimizer.pt
+
leoprint:  58%|#####8    | 1400/2400 [25:38<58:00,  3.48s/it, lr: 5.0e-05 loss: 2.945e-01]
leoprint:  58%|#####8    | 1400/2400 [25:38<58:00,  3.48s/it, lr: 5.0e-05 loss: 2.945e-01]
leoprint:  58%|#####8    | 1401/2400 [25:38<45:54,  2.76s/it, lr: 5.0e-05 loss: 2.945e-01]
leoprint:  58%|#####8    | 1401/2400 [25:38<45:54,  2.76s/it, lr: 5.0e-05 loss: 2.945e-01]
leoprint:  58%|#####8    | 1401/2400 [25:42<45:54,  2.76s/it, lr: 5.0e-05 loss: 1.976e-01]
leoprint:  58%|#####8    | 1401/2400 [25:42<45:54,  2.76s/it, lr: 5.0e-05 loss: 1.976e-01]
leoprint:  58%|#####8    | 1402/2400 [25:42<49:18,  2.96s/it, lr: 5.0e-05 loss: 1.976e-01]
leoprint:  58%|#####8    | 1402/2400 [25:42<49:18,  2.96s/it, lr: 5.0e-05 loss: 1.976e-01]
leoprint:  58%|#####8    | 1402/2400 [25:45<49:18,  2.96s/it, lr: 5.0e-05 loss: 2.844e-01]
leoprint:  58%|#####8    | 1402/2400 [25:45<49:18,  2.96s/it, lr: 5.0e-05 loss: 2.844e-01]
leoprint:  58%|#####8    | 1403/2400 [25:45<51:31,  3.10s/it, lr: 5.0e-05 loss: 2.844e-01]
leoprint:  58%|#####8    | 1403/2400 [25:45<51:31,  3.10s/it, lr: 5.0e-05 loss: 2.844e-01]
leoprint:  58%|#####8    | 1403/2400 [25:49<51:31,  3.10s/it, lr: 5.0e-05 loss: 3.303e-01]
leoprint:  58%|#####8    | 1403/2400 [25:49<51:31,  3.10s/it, lr: 5.0e-05 loss: 3.303e-01]
leoprint:  58%|#####8    | 1404/2400 [25:49<53:12,  3.21s/it, lr: 5.0e-05 loss: 3.303e-01]
leoprint:  58%|#####8    | 1404/2400 [25:49<53:12,  3.21s/it, lr: 5.0e-05 loss: 3.303e-01]
leoprint:  58%|#####8    | 1404/2400 [25:52<53:12,  3.21s/it, lr: 5.0e-05 loss: 2.364e-01]
leoprint:  58%|#####8    | 1404/2400 [25:52<53:12,  3.21s/it, lr: 5.0e-05 loss: 2.364e-01]
leoprint:  59%|#####8    | 1405/2400 [25:52<54:31,  3.29s/it, lr: 5.0e-05 loss: 2.364e-01]
leoprint:  59%|#####8    | 1405/2400 [25:52<54:31,  3.29s/it, lr: 5.0e-05 loss: 2.364e-01]
leoprint:  59%|#####8    | 1405/2400 [25:56<54:31,  3.29s/it, lr: 5.0e-05 loss: 2.881e-01]
leoprint:  59%|#####8    | 1405/2400 [25:56<54:31,  3.29s/it, lr: 5.0e-05 loss: 2.881e-01]
leoprint:  59%|#####8    | 1406/2400 [25:56<55:46,  3.37s/it, lr: 5.0e-05 loss: 2.881e-01]
leoprint:  59%|#####8    | 1406/2400 [25:56<55:46,  3.37s/it, lr: 5.0e-05 loss: 2.881e-01]
leoprint:  59%|#####8    | 1406/2400 [26:00<55:46,  3.37s/it, lr: 5.0e-05 loss: 2.983e-01]
leoprint:  59%|#####8    | 1406/2400 [26:00<55:46,  3.37s/it, lr: 5.0e-05 loss: 2.983e-01]
leoprint:  59%|#####8    | 1407/2400 [26:00<56:23,  3.41s/it, lr: 5.0e-05 loss: 2.983e-01]
leoprint:  59%|#####8    | 1407/2400 [26:00<56:23,  3.41s/it, lr: 5.0e-05 loss: 2.983e-01]
leoprint:  59%|#####8    | 1407/2400 [26:03<56:23,  3.41s/it, lr: 5.0e-05 loss: 3.287e-01]
leoprint:  59%|#####8    | 1407/2400 [26:03<56:23,  3.41s/it, lr: 5.0e-05 loss: 3.287e-01]
leoprint:  59%|#####8    | 1408/2400 [26:03<56:46,  3.43s/it, lr: 5.0e-05 loss: 3.287e-01]
leoprint:  59%|#####8    | 1408/2400 [26:03<56:46,  3.43s/it, lr: 5.0e-05 loss: 3.287e-01]
leoprint:  59%|#####8    | 1408/2400 [26:07<56:46,  3.43s/it, lr: 5.0e-05 loss: 2.149e-01]
leoprint:  59%|#####8    | 1408/2400 [26:07<56:46,  3.43s/it, lr: 5.0e-05 loss: 2.149e-01]
leoprint:  59%|#####8    | 1409/2400 [26:07<57:39,  3.49s/it, lr: 5.0e-05 loss: 2.149e-01]
leoprint:  59%|#####8    | 1409/2400 [26:07<57:39,  3.49s/it, lr: 5.0e-05 loss: 2.149e-01]
leoprint:  59%|#####8    | 1409/2400 [26:11<57:39,  3.49s/it, lr: 5.0e-05 loss: 2.676e-01]
leoprint:  59%|#####8    | 1409/2400 [26:11<57:39,  3.49s/it, lr: 5.0e-05 loss: 2.676e-01]
leoprint:  59%|#####8    | 1410/2400 [26:14<57:35,  3.49s/it, lr: 5.0e-05 loss: 2.819e-01]
leoprint:  59%|#####8    | 1410/2400 [26:14<57:35,  3.49s/it, lr: 5.0e-05 loss: 2.819e-01]
leoprint:  59%|#####8    | 1411/2400 [26:14<44:26,  2.70s/it, lr: 5.0e-05 loss: 2.819e-01]
leoprint:  59%|#####8    | 1411/2400 [26:14<44:26,  2.70s/it, lr: 5.0e-05 loss: 2.819e-01]
leoprint:  59%|#####8    | 1411/2400 [26:18<44:26,  2.70s/it, lr: 5.0e-05 loss: 3.660e-01]
leoprint:  59%|#####8    | 1411/2400 [26:18<44:26,  2.70s/it, lr: 5.0e-05 loss: 3.660e-01]
leoprint:  59%|#####8    | 1412/2400 [26:18<48:34,  2.95s/it, lr: 5.0e-05 loss: 3.660e-01]
leoprint:  59%|#####8    | 1412/2400 [26:18<48:34,  2.95s/it, lr: 5.0e-05 loss: 3.660e-01]
leoprint:  59%|#####8    | 1412/2400 [26:22<48:34,  2.95s/it, lr: 5.0e-05 loss: 1.940e-01]
leoprint:  59%|#####8    | 1412/2400 [26:22<48:34,  2.95s/it, lr: 5.0e-05 loss: 1.940e-01]
leoprint:  59%|#####8    | 1413/2400 [26:22<51:27,  3.13s/it, lr: 5.0e-05 loss: 1.940e-01]
leoprint:  59%|#####8    | 1413/2400 [26:22<51:27,  3.13s/it, lr: 5.0e-05 loss: 1.940e-01]
leoprint:  59%|#####8    | 1413/2400 [26:25<51:27,  3.13s/it, lr: 5.0e-05 loss: 3.128e-01]
leoprint:  59%|#####8    | 1413/2400 [26:25<51:27,  3.13s/it, lr: 5.0e-05 loss: 3.128e-01]
leoprint:  59%|#####8    | 1414/2400 [26:25<53:03,  3.23s/it, lr: 5.0e-05 loss: 3.128e-01]
leoprint:  59%|#####8    | 1414/2400 [26:25<53:03,  3.23s/it, lr: 5.0e-05 loss: 3.128e-01]
leoprint:  59%|#####8    | 1414/2400 [26:29<53:03,  3.23s/it, lr: 5.0e-05 loss: 2.603e-01]
leoprint:  59%|#####8    | 1414/2400 [26:29<53:03,  3.23s/it, lr: 5.0e-05 loss: 2.603e-01]
leoprint:  59%|#####8    | 1415/2400 [26:29<54:47,  3.34s/it, lr: 5.0e-05 loss: 2.603e-01]
leoprint:  59%|#####8    | 1415/2400 [26:29<54:47,  3.34s/it, lr: 5.0e-05 loss: 2.603e-01]
leoprint:  59%|#####8    | 1415/2400 [26:32<54:47,  3.34s/it, lr: 5.0e-05 loss: 2.868e-01]
leoprint:  59%|#####8    | 1415/2400 [26:32<54:47,  3.34s/it, lr: 5.0e-05 loss: 2.868e-01]
leoprint:  59%|#####8    | 1416/2400 [26:32<55:28,  3.38s/it, lr: 5.0e-05 loss: 2.868e-01]
leoprint:  59%|#####8    | 1416/2400 [26:32<55:28,  3.38s/it, lr: 5.0e-05 loss: 2.868e-01]
leoprint:  59%|#####8    | 1416/2400 [26:36<55:28,  3.38s/it, lr: 5.0e-05 loss: 2.876e-01]
leoprint:  59%|#####8    | 1416/2400 [26:36<55:28,  3.38s/it, lr: 5.0e-05 loss: 2.876e-01]
leoprint:  59%|#####9    | 1417/2400 [26:36<55:58,  3.42s/it, lr: 5.0e-05 loss: 2.876e-01]
leoprint:  59%|#####9    | 1417/2400 [26:36<55:58,  3.42s/it, lr: 5.0e-05 loss: 2.876e-01]
leoprint:  59%|#####9    | 1417/2400 [26:40<55:58,  3.42s/it, lr: 5.0e-05 loss: 4.036e-01]
leoprint:  59%|#####9    | 1417/2400 [26:40<55:58,  3.42s/it, lr: 5.0e-05 loss: 4.036e-01]
leoprint:  59%|#####9    | 1418/2400 [26:40<57:31,  3.51s/it, lr: 5.0e-05 loss: 4.036e-01]
leoprint:  59%|#####9    | 1418/2400 [26:40<57:31,  3.51s/it, lr: 5.0e-05 loss: 4.036e-01]
leoprint:  59%|#####9    | 1418/2400 [26:43<57:31,  3.51s/it, lr: 5.0e-05 loss: 3.153e-01]
leoprint:  59%|#####9    | 1418/2400 [26:43<57:31,  3.51s/it, lr: 5.0e-05 loss: 3.153e-01]
leoprint:  59%|#####9    | 1419/2400 [26:43<57:26,  3.51s/it, lr: 5.0e-05 loss: 3.153e-01]
leoprint:  59%|#####9    | 1419/2400 [26:43<57:26,  3.51s/it, lr: 5.0e-05 loss: 3.153e-01]
leoprint:  59%|#####9    | 1419/2400 [26:47<57:26,  3.51s/it, lr: 5.0e-05 loss: 2.175e-01]
leoprint:  59%|#####9    | 1419/2400 [26:47<57:26,  3.51s/it, lr: 5.0e-05 loss: 2.175e-01]
leoprint:  59%|#####9    | 1420/2400 [26:50<57:23,  3.51s/it, lr: 5.0e-05 loss: 2.137e-01]
leoprint:  59%|#####9    | 1420/2400 [26:50<57:23,  3.51s/it, lr: 5.0e-05 loss: 2.137e-01]
leoprint:  59%|#####9    | 1421/2400 [26:50<44:11,  2.71s/it, lr: 5.0e-05 loss: 2.137e-01]
leoprint:  59%|#####9    | 1421/2400 [26:50<44:11,  2.71s/it, lr: 5.0e-05 loss: 2.137e-01]
leoprint:  59%|#####9    | 1421/2400 [26:54<44:11,  2.71s/it, lr: 5.0e-05 loss: 3.098e-01]
leoprint:  59%|#####9    | 1421/2400 [26:54<44:11,  2.71s/it, lr: 5.0e-05 loss: 3.098e-01]
leoprint:  59%|#####9    | 1422/2400 [26:54<47:19,  2.90s/it, lr: 5.0e-05 loss: 3.098e-01]
leoprint:  59%|#####9    | 1422/2400 [26:54<47:19,  2.90s/it, lr: 5.0e-05 loss: 3.098e-01]
leoprint:  59%|#####9    | 1422/2400 [26:57<47:19,  2.90s/it, lr: 5.0e-05 loss: 3.142e-01]
leoprint:  59%|#####9    | 1422/2400 [26:57<47:19,  2.90s/it, lr: 5.0e-05 loss: 3.142e-01]
leoprint:  59%|#####9    | 1423/2400 [26:57<50:35,  3.11s/it, lr: 5.0e-05 loss: 3.142e-01]
leoprint:  59%|#####9    | 1423/2400 [26:57<50:35,  3.11s/it, lr: 5.0e-05 loss: 3.142e-01]
leoprint:  59%|#####9    | 1423/2400 [27:01<50:35,  3.11s/it, lr: 5.0e-05 loss: 2.387e-01]
leoprint:  59%|#####9    | 1423/2400 [27:01<50:35,  3.11s/it, lr: 5.0e-05 loss: 2.387e-01]
leoprint:  59%|#####9    | 1424/2400 [27:01<52:48,  3.25s/it, lr: 5.0e-05 loss: 2.387e-01]
leoprint:  59%|#####9    | 1424/2400 [27:01<52:48,  3.25s/it, lr: 5.0e-05 loss: 2.387e-01]
leoprint:  59%|#####9    | 1424/2400 [27:05<52:48,  3.25s/it, lr: 5.0e-05 loss: 3.400e-01]
leoprint:  59%|#####9    | 1424/2400 [27:05<52:48,  3.25s/it, lr: 5.0e-05 loss: 3.400e-01]
leoprint:  59%|#####9    | 1425/2400 [27:05<53:54,  3.32s/it, lr: 5.0e-05 loss: 3.400e-01]
leoprint:  59%|#####9    | 1425/2400 [27:05<53:54,  3.32s/it, lr: 5.0e-05 loss: 3.400e-01]
leoprint:  59%|#####9    | 1425/2400 [27:08<53:54,  3.32s/it, lr: 5.0e-05 loss: 2.183e-01]
leoprint:  59%|#####9    | 1425/2400 [27:08<53:54,  3.32s/it, lr: 5.0e-05 loss: 2.183e-01]
leoprint:  59%|#####9    | 1426/2400 [27:08<55:14,  3.40s/it, lr: 5.0e-05 loss: 2.183e-01]
leoprint:  59%|#####9    | 1426/2400 [27:08<55:14,  3.40s/it, lr: 5.0e-05 loss: 2.183e-01]
leoprint:  59%|#####9    | 1426/2400 [27:12<55:14,  3.40s/it, lr: 5.0e-05 loss: 2.925e-01]
leoprint:  59%|#####9    | 1426/2400 [27:12<55:14,  3.40s/it, lr: 5.0e-05 loss: 2.925e-01]
leoprint:  59%|#####9    | 1427/2400 [27:12<55:37,  3.43s/it, lr: 5.0e-05 loss: 2.925e-01]
leoprint:  59%|#####9    | 1427/2400 [27:12<55:37,  3.43s/it, lr: 5.0e-05 loss: 2.925e-01]
leoprint:  59%|#####9    | 1427/2400 [27:15<55:37,  3.43s/it, lr: 5.0e-05 loss: 2.321e-01]
leoprint:  59%|#####9    | 1427/2400 [27:15<55:37,  3.43s/it, lr: 5.0e-05 loss: 2.321e-01]
leoprint:  60%|#####9    | 1428/2400 [27:15<55:52,  3.45s/it, lr: 5.0e-05 loss: 2.321e-01]
leoprint:  60%|#####9    | 1428/2400 [27:15<55:52,  3.45s/it, lr: 5.0e-05 loss: 2.321e-01]
leoprint:  60%|#####9    | 1428/2400 [27:19<55:52,  3.45s/it, lr: 5.0e-05 loss: 2.846e-01]
leoprint:  60%|#####9    | 1428/2400 [27:19<55:52,  3.45s/it, lr: 5.0e-05 loss: 2.846e-01]
leoprint:  60%|#####9    | 1429/2400 [27:19<56:56,  3.52s/it, lr: 5.0e-05 loss: 2.846e-01]
leoprint:  60%|#####9    | 1429/2400 [27:19<56:56,  3.52s/it, lr: 5.0e-05 loss: 2.846e-01]
leoprint:  60%|#####9    | 1429/2400 [27:22<56:56,  3.52s/it, lr: 5.0e-05 loss: 2.281e-01]
leoprint:  60%|#####9    | 1429/2400 [27:22<56:56,  3.52s/it, lr: 5.0e-05 loss: 2.281e-01]
leoprint:  60%|#####9    | 1430/2400 [27:26<56:52,  3.52s/it, lr: 5.0e-05 loss: 3.414e-01]
leoprint:  60%|#####9    | 1430/2400 [27:26<56:52,  3.52s/it, lr: 5.0e-05 loss: 3.414e-01]
leoprint:  60%|#####9    | 1431/2400 [27:26<43:45,  2.71s/it, lr: 5.0e-05 loss: 3.414e-01]
leoprint:  60%|#####9    | 1431/2400 [27:26<43:45,  2.71s/it, lr: 5.0e-05 loss: 3.414e-01]
leoprint:  60%|#####9    | 1431/2400 [27:29<43:45,  2.71s/it, lr: 5.0e-05 loss: 3.137e-01]
leoprint:  60%|#####9    | 1431/2400 [27:29<43:45,  2.71s/it, lr: 5.0e-05 loss: 3.137e-01]
leoprint:  60%|#####9    | 1432/2400 [27:29<46:50,  2.90s/it, lr: 5.0e-05 loss: 3.137e-01]
leoprint:  60%|#####9    | 1432/2400 [27:29<46:50,  2.90s/it, lr: 5.0e-05 loss: 3.137e-01]
leoprint:  60%|#####9    | 1432/2400 [27:33<46:50,  2.90s/it, lr: 5.0e-05 loss: 2.959e-01]
leoprint:  60%|#####9    | 1432/2400 [27:33<46:50,  2.90s/it, lr: 5.0e-05 loss: 2.959e-01]
leoprint:  60%|#####9    | 1433/2400 [27:33<49:18,  3.06s/it, lr: 5.0e-05 loss: 2.959e-01]
leoprint:  60%|#####9    | 1433/2400 [27:33<49:18,  3.06s/it, lr: 5.0e-05 loss: 2.959e-01]
leoprint:  60%|#####9    | 1433/2400 [27:37<49:18,  3.06s/it, lr: 5.0e-05 loss: 2.725e-01]
leoprint:  60%|#####9    | 1433/2400 [27:37<49:18,  3.06s/it, lr: 5.0e-05 loss: 2.725e-01]
leoprint:  60%|#####9    | 1434/2400 [27:37<51:42,  3.21s/it, lr: 5.0e-05 loss: 2.725e-01]
leoprint:  60%|#####9    | 1434/2400 [27:37<51:42,  3.21s/it, lr: 5.0e-05 loss: 2.725e-01]
leoprint:  60%|#####9    | 1434/2400 [27:40<51:42,  3.21s/it, lr: 5.0e-05 loss: 1.908e-01]
leoprint:  60%|#####9    | 1434/2400 [27:40<51:42,  3.21s/it, lr: 5.0e-05 loss: 1.908e-01]
leoprint:  60%|#####9    | 1435/2400 [27:40<54:07,  3.37s/it, lr: 5.0e-05 loss: 1.908e-01]
leoprint:  60%|#####9    | 1435/2400 [27:40<54:07,  3.37s/it, lr: 5.0e-05 loss: 1.908e-01]
leoprint:  60%|#####9    | 1435/2400 [27:44<54:07,  3.37s/it, lr: 5.0e-05 loss: 3.401e-01]
leoprint:  60%|#####9    | 1435/2400 [27:44<54:07,  3.37s/it, lr: 5.0e-05 loss: 3.401e-01]
leoprint:  60%|#####9    | 1436/2400 [27:44<54:39,  3.40s/it, lr: 5.0e-05 loss: 3.401e-01]
leoprint:  60%|#####9    | 1436/2400 [27:44<54:39,  3.40s/it, lr: 5.0e-05 loss: 3.401e-01]
leoprint:  60%|#####9    | 1436/2400 [27:47<54:39,  3.40s/it, lr: 5.0e-05 loss: 3.275e-01]
leoprint:  60%|#####9    | 1436/2400 [27:47<54:39,  3.40s/it, lr: 5.0e-05 loss: 3.275e-01]
leoprint:  60%|#####9    | 1437/2400 [27:47<55:03,  3.43s/it, lr: 5.0e-05 loss: 3.275e-01]
leoprint:  60%|#####9    | 1437/2400 [27:47<55:03,  3.43s/it, lr: 5.0e-05 loss: 3.275e-01]
leoprint:  60%|#####9    | 1437/2400 [27:51<55:03,  3.43s/it, lr: 5.0e-05 loss: 2.222e-01]
leoprint:  60%|#####9    | 1437/2400 [27:51<55:03,  3.43s/it, lr: 5.0e-05 loss: 2.222e-01]
leoprint:  60%|#####9    | 1438/2400 [27:51<55:20,  3.45s/it, lr: 5.0e-05 loss: 2.222e-01]
leoprint:  60%|#####9    | 1438/2400 [27:51<55:20,  3.45s/it, lr: 5.0e-05 loss: 2.222e-01]
leoprint:  60%|#####9    | 1438/2400 [27:54<55:20,  3.45s/it, lr: 5.0e-05 loss: 3.337e-01]
leoprint:  60%|#####9    | 1438/2400 [27:54<55:20,  3.45s/it, lr: 5.0e-05 loss: 3.337e-01]
leoprint:  60%|#####9    | 1439/2400 [27:54<55:30,  3.47s/it, lr: 5.0e-05 loss: 3.337e-01]
leoprint:  60%|#####9    | 1439/2400 [27:54<55:30,  3.47s/it, lr: 5.0e-05 loss: 3.337e-01]
leoprint:  60%|#####9    | 1439/2400 [27:58<55:30,  3.47s/it, lr: 5.0e-05 loss: 2.895e-01]
leoprint:  60%|#####9    | 1439/2400 [27:58<55:30,  3.47s/it, lr: 5.0e-05 loss: 2.895e-01]
leoprint:  60%|######    | 1440/2400 [28:02<55:26,  3.47s/it, lr: 5.0e-05 loss: 3.279e-01]
leoprint:  60%|######    | 1440/2400 [28:02<55:26,  3.47s/it, lr: 5.0e-05 loss: 3.279e-01]
leoprint:  60%|######    | 1441/2400 [28:02<43:41,  2.73s/it, lr: 5.0e-05 loss: 3.279e-01]
leoprint:  60%|######    | 1441/2400 [28:02<43:41,  2.73s/it, lr: 5.0e-05 loss: 3.279e-01]
leoprint:  60%|######    | 1441/2400 [28:05<43:41,  2.73s/it, lr: 5.0e-05 loss: 3.701e-01]
leoprint:  60%|######    | 1441/2400 [28:05<43:41,  2.73s/it, lr: 5.0e-05 loss: 3.701e-01]
leoprint:  60%|######    | 1442/2400 [28:05<46:40,  2.92s/it, lr: 5.0e-05 loss: 3.701e-01]
leoprint:  60%|######    | 1442/2400 [28:05<46:40,  2.92s/it, lr: 5.0e-05 loss: 3.701e-01]
leoprint:  60%|######    | 1442/2400 [28:09<46:40,  2.92s/it, lr: 5.0e-05 loss: 2.756e-01]
leoprint:  60%|######    | 1442/2400 [28:09<46:40,  2.92s/it, lr: 5.0e-05 loss: 2.756e-01]
leoprint:  60%|######    | 1443/2400 [28:09<48:59,  3.07s/it, lr: 5.0e-05 loss: 2.756e-01]
leoprint:  60%|######    | 1443/2400 [28:09<48:59,  3.07s/it, lr: 5.0e-05 loss: 2.756e-01]
leoprint:  60%|######    | 1443/2400 [28:12<48:59,  3.07s/it, lr: 5.0e-05 loss: 2.900e-01]
leoprint:  60%|######    | 1443/2400 [28:12<48:59,  3.07s/it, lr: 5.0e-05 loss: 2.900e-01]
leoprint:  60%|######    | 1444/2400 [28:12<50:47,  3.19s/it, lr: 5.0e-05 loss: 2.900e-01]
leoprint:  60%|######    | 1444/2400 [28:12<50:47,  3.19s/it, lr: 5.0e-05 loss: 2.900e-01]
leoprint:  60%|######    | 1444/2400 [28:16<50:47,  3.19s/it, lr: 5.0e-05 loss: 3.036e-01]
leoprint:  60%|######    | 1444/2400 [28:16<50:47,  3.19s/it, lr: 5.0e-05 loss: 3.036e-01]
leoprint:  60%|######    | 1445/2400 [28:16<52:06,  3.27s/it, lr: 5.0e-05 loss: 3.036e-01]
leoprint:  60%|######    | 1445/2400 [28:16<52:06,  3.27s/it, lr: 5.0e-05 loss: 3.036e-01]
leoprint:  60%|######    | 1445/2400 [28:19<52:06,  3.27s/it, lr: 5.0e-05 loss: 2.596e-01]
leoprint:  60%|######    | 1445/2400 [28:19<52:06,  3.27s/it, lr: 5.0e-05 loss: 2.596e-01]
leoprint:  60%|######    | 1446/2400 [28:19<53:55,  3.39s/it, lr: 5.0e-05 loss: 2.596e-01]
leoprint:  60%|######    | 1446/2400 [28:19<53:55,  3.39s/it, lr: 5.0e-05 loss: 2.596e-01]
leoprint:  60%|######    | 1446/2400 [28:23<53:55,  3.39s/it, lr: 5.0e-05 loss: 3.434e-01]
leoprint:  60%|######    | 1446/2400 [28:23<53:55,  3.39s/it, lr: 5.0e-05 loss: 3.434e-01]
leoprint:  60%|######    | 1447/2400 [28:23<54:22,  3.42s/it, lr: 5.0e-05 loss: 3.434e-01]
leoprint:  60%|######    | 1447/2400 [28:23<54:22,  3.42s/it, lr: 5.0e-05 loss: 3.434e-01]
leoprint:  60%|######    | 1447/2400 [28:26<54:22,  3.42s/it, lr: 5.0e-05 loss: 2.262e-01]
leoprint:  60%|######    | 1447/2400 [28:26<54:22,  3.42s/it, lr: 5.0e-05 loss: 2.262e-01]
leoprint:  60%|######    | 1448/2400 [28:26<55:13,  3.48s/it, lr: 5.0e-05 loss: 2.262e-01]
leoprint:  60%|######    | 1448/2400 [28:26<55:13,  3.48s/it, lr: 5.0e-05 loss: 2.262e-01]
leoprint:  60%|######    | 1448/2400 [28:30<55:13,  3.48s/it, lr: 5.0e-05 loss: 2.985e-01]
leoprint:  60%|######    | 1448/2400 [28:30<55:13,  3.48s/it, lr: 5.0e-05 loss: 2.985e-01]
leoprint:  60%|######    | 1449/2400 [28:30<55:14,  3.48s/it, lr: 5.0e-05 loss: 2.985e-01]
leoprint:  60%|######    | 1449/2400 [28:30<55:14,  3.48s/it, lr: 5.0e-05 loss: 2.985e-01]
leoprint:  60%|######    | 1449/2400 [28:34<55:14,  3.48s/it, lr: 5.0e-05 loss: 1.915e-01]
leoprint:  60%|######    | 1449/2400 [28:34<55:14,  3.48s/it, lr: 5.0e-05 loss: 1.915e-01]
leoprint:  60%|######    | 1450/2400 [28:37<55:10,  3.48s/it, lr: 5.0e-05 loss: 3.710e-01]
leoprint:  60%|######    | 1450/2400 [28:37<55:10,  3.48s/it, lr: 5.0e-05 loss: 3.710e-01]
leoprint:  60%|######    | 1451/2400 [28:37<42:36,  2.69s/it, lr: 5.0e-05 loss: 3.710e-01]
leoprint:  60%|######    | 1451/2400 [28:37<42:36,  2.69s/it, lr: 5.0e-05 loss: 3.710e-01]
leoprint:  60%|######    | 1451/2400 [28:41<42:36,  2.69s/it, lr: 5.0e-05 loss: 2.035e-01]
leoprint:  60%|######    | 1451/2400 [28:41<42:36,  2.69s/it, lr: 5.0e-05 loss: 2.035e-01]
leoprint:  60%|######    | 1452/2400 [28:41<46:48,  2.96s/it, lr: 5.0e-05 loss: 2.035e-01]
leoprint:  60%|######    | 1452/2400 [28:41<46:48,  2.96s/it, lr: 5.0e-05 loss: 2.035e-01]
leoprint:  60%|######    | 1452/2400 [28:44<46:48,  2.96s/it, lr: 5.0e-05 loss: 2.370e-01]
leoprint:  60%|######    | 1452/2400 [28:44<46:48,  2.96s/it, lr: 5.0e-05 loss: 2.370e-01]
leoprint:  61%|######    | 1453/2400 [28:44<48:59,  3.10s/it, lr: 5.0e-05 loss: 2.370e-01]
leoprint:  61%|######    | 1453/2400 [28:44<48:59,  3.10s/it, lr: 5.0e-05 loss: 2.370e-01]
leoprint:  61%|######    | 1453/2400 [28:48<48:59,  3.10s/it, lr: 5.0e-05 loss: 2.368e-01]
leoprint:  61%|######    | 1453/2400 [28:48<48:59,  3.10s/it, lr: 5.0e-05 loss: 2.368e-01]
leoprint:  61%|######    | 1454/2400 [28:48<51:08,  3.24s/it, lr: 5.0e-05 loss: 2.368e-01]
leoprint:  61%|######    | 1454/2400 [28:48<51:08,  3.24s/it, lr: 5.0e-05 loss: 2.368e-01]
leoprint:  61%|######    | 1454/2400 [28:52<51:08,  3.24s/it, lr: 5.0e-05 loss: 2.611e-01]
leoprint:  61%|######    | 1454/2400 [28:52<51:08,  3.24s/it, lr: 5.0e-05 loss: 2.611e-01]
leoprint:  61%|######    | 1455/2400 [28:52<52:44,  3.35s/it, lr: 5.0e-05 loss: 2.611e-01]
leoprint:  61%|######    | 1455/2400 [28:52<52:44,  3.35s/it, lr: 5.0e-05 loss: 2.611e-01]
leoprint:  61%|######    | 1455/2400 [28:55<52:44,  3.35s/it, lr: 5.0e-05 loss: 4.091e-01]
leoprint:  61%|######    | 1455/2400 [28:55<52:44,  3.35s/it, lr: 5.0e-05 loss: 4.091e-01]
leoprint:  61%|######    | 1456/2400 [28:55<53:22,  3.39s/it, lr: 5.0e-05 loss: 4.091e-01]
leoprint:  61%|######    | 1456/2400 [28:55<53:22,  3.39s/it, lr: 5.0e-05 loss: 4.091e-01]
leoprint:  61%|######    | 1456/2400 [28:59<53:22,  3.39s/it, lr: 5.0e-05 loss: 3.249e-01]
leoprint:  61%|######    | 1456/2400 [28:59<53:22,  3.39s/it, lr: 5.0e-05 loss: 3.249e-01]
leoprint:  61%|######    | 1457/2400 [28:59<53:50,  3.43s/it, lr: 5.0e-05 loss: 3.249e-01]
leoprint:  61%|######    | 1457/2400 [28:59<53:50,  3.43s/it, lr: 5.0e-05 loss: 3.249e-01]
leoprint:  61%|######    | 1457/2400 [29:02<53:50,  3.43s/it, lr: 5.0e-05 loss: 3.127e-01]
leoprint:  61%|######    | 1457/2400 [29:02<53:50,  3.43s/it, lr: 5.0e-05 loss: 3.127e-01]
leoprint:  61%|######    | 1458/2400 [29:02<54:47,  3.49s/it, lr: 5.0e-05 loss: 3.127e-01]
leoprint:  61%|######    | 1458/2400 [29:02<54:47,  3.49s/it, lr: 5.0e-05 loss: 3.127e-01]
leoprint:  61%|######    | 1458/2400 [29:06<54:47,  3.49s/it, lr: 5.0e-05 loss: 2.187e-01]
leoprint:  61%|######    | 1458/2400 [29:06<54:47,  3.49s/it, lr: 5.0e-05 loss: 2.187e-01]
leoprint:  61%|######    | 1459/2400 [29:06<54:45,  3.49s/it, lr: 5.0e-05 loss: 2.187e-01]
leoprint:  61%|######    | 1459/2400 [29:06<54:45,  3.49s/it, lr: 5.0e-05 loss: 2.187e-01]
leoprint:  61%|######    | 1459/2400 [29:09<54:45,  3.49s/it, lr: 5.0e-05 loss: 2.861e-01]
leoprint:  61%|######    | 1459/2400 [29:09<54:45,  3.49s/it, lr: 5.0e-05 loss: 2.861e-01]
leoprint:  61%|######    | 1460/2400 [29:13<54:42,  3.49s/it, lr: 5.0e-05 loss: 3.222e-01]
leoprint:  61%|######    | 1460/2400 [29:13<54:42,  3.49s/it, lr: 5.0e-05 loss: 3.222e-01]
leoprint:  61%|######    | 1461/2400 [29:13<42:10,  2.69s/it, lr: 5.0e-05 loss: 3.222e-01]
leoprint:  61%|######    | 1461/2400 [29:13<42:10,  2.69s/it, lr: 5.0e-05 loss: 3.222e-01]
leoprint:  61%|######    | 1461/2400 [29:16<42:10,  2.69s/it, lr: 5.0e-05 loss: 3.067e-01]
leoprint:  61%|######    | 1461/2400 [29:16<42:10,  2.69s/it, lr: 5.0e-05 loss: 3.067e-01]
leoprint:  61%|######    | 1462/2400 [29:16<45:13,  2.89s/it, lr: 5.0e-05 loss: 3.067e-01]
leoprint:  61%|######    | 1462/2400 [29:16<45:13,  2.89s/it, lr: 5.0e-05 loss: 3.067e-01]
leoprint:  61%|######    | 1462/2400 [29:20<45:13,  2.89s/it, lr: 5.0e-05 loss: 3.198e-01]
leoprint:  61%|######    | 1462/2400 [29:20<45:13,  2.89s/it, lr: 5.0e-05 loss: 3.198e-01]
leoprint:  61%|######    | 1463/2400 [29:20<48:08,  3.08s/it, lr: 5.0e-05 loss: 3.198e-01]
leoprint:  61%|######    | 1463/2400 [29:20<48:08,  3.08s/it, lr: 5.0e-05 loss: 3.198e-01]
leoprint:  61%|######    | 1463/2400 [29:24<48:08,  3.08s/it, lr: 5.0e-05 loss: 2.208e-01]
leoprint:  61%|######    | 1463/2400 [29:24<48:08,  3.08s/it, lr: 5.0e-05 loss: 2.208e-01]
leoprint:  61%|######1   | 1464/2400 [29:24<50:51,  3.26s/it, lr: 5.0e-05 loss: 2.208e-01]
leoprint:  61%|######1   | 1464/2400 [29:24<50:51,  3.26s/it, lr: 5.0e-05 loss: 2.208e-01]
leoprint:  61%|######1   | 1464/2400 [29:27<50:51,  3.26s/it, lr: 5.0e-05 loss: 2.316e-01]
leoprint:  61%|######1   | 1464/2400 [29:27<50:51,  3.26s/it, lr: 5.0e-05 loss: 2.316e-01]
leoprint:  61%|######1   | 1465/2400 [29:27<51:49,  3.33s/it, lr: 5.0e-05 loss: 2.316e-01]
leoprint:  61%|######1   | 1465/2400 [29:27<51:49,  3.33s/it, lr: 5.0e-05 loss: 2.316e-01]
leoprint:  61%|######1   | 1465/2400 [29:31<51:49,  3.33s/it, lr: 5.0e-05 loss: 2.740e-01]
leoprint:  61%|######1   | 1465/2400 [29:31<51:49,  3.33s/it, lr: 5.0e-05 loss: 2.740e-01]
leoprint:  61%|######1   | 1466/2400 [29:31<53:01,  3.41s/it, lr: 5.0e-05 loss: 2.740e-01]
leoprint:  61%|######1   | 1466/2400 [29:31<53:01,  3.41s/it, lr: 5.0e-05 loss: 2.740e-01]
leoprint:  61%|######1   | 1466/2400 [29:34<53:01,  3.41s/it, lr: 5.0e-05 loss: 2.527e-01]
leoprint:  61%|######1   | 1466/2400 [29:34<53:01,  3.41s/it, lr: 5.0e-05 loss: 2.527e-01]
leoprint:  61%|######1   | 1467/2400 [29:34<53:26,  3.44s/it, lr: 5.0e-05 loss: 2.527e-01]
leoprint:  61%|######1   | 1467/2400 [29:34<53:26,  3.44s/it, lr: 5.0e-05 loss: 2.527e-01]
leoprint:  61%|######1   | 1467/2400 [29:38<53:26,  3.44s/it, lr: 5.0e-05 loss: 2.664e-01]
leoprint:  61%|######1   | 1467/2400 [29:38<53:26,  3.44s/it, lr: 5.0e-05 loss: 2.664e-01]
leoprint:  61%|######1   | 1468/2400 [29:38<53:40,  3.46s/it, lr: 5.0e-05 loss: 2.664e-01]
leoprint:  61%|######1   | 1468/2400 [29:38<53:40,  3.46s/it, lr: 5.0e-05 loss: 2.664e-01]
leoprint:  61%|######1   | 1468/2400 [29:42<53:40,  3.46s/it, lr: 5.0e-05 loss: 2.631e-01]
leoprint:  61%|######1   | 1468/2400 [29:42<53:40,  3.46s/it, lr: 5.0e-05 loss: 2.631e-01]
leoprint:  61%|######1   | 1469/2400 [29:42<54:40,  3.52s/it, lr: 5.0e-05 loss: 2.631e-01]
leoprint:  61%|######1   | 1469/2400 [29:42<54:40,  3.52s/it, lr: 5.0e-05 loss: 2.631e-01]
leoprint:  61%|######1   | 1469/2400 [29:45<54:40,  3.52s/it, lr: 5.0e-05 loss: 2.469e-01]
leoprint:  61%|######1   | 1469/2400 [29:45<54:40,  3.52s/it, lr: 5.0e-05 loss: 2.469e-01]
leoprint:  61%|######1   | 1470/2400 [29:49<54:36,  3.52s/it, lr: 5.0e-05 loss: 2.467e-01]
leoprint:  61%|######1   | 1470/2400 [29:49<54:36,  3.52s/it, lr: 5.0e-05 loss: 2.467e-01]
leoprint:  61%|######1   | 1471/2400 [29:49<41:58,  2.71s/it, lr: 5.0e-05 loss: 2.467e-01]
leoprint:  61%|######1   | 1471/2400 [29:49<41:58,  2.71s/it, lr: 5.0e-05 loss: 2.467e-01]
leoprint:  61%|######1   | 1471/2400 [29:52<41:58,  2.71s/it, lr: 5.0e-05 loss: 2.181e-01]
leoprint:  61%|######1   | 1471/2400 [29:52<41:58,  2.71s/it, lr: 5.0e-05 loss: 2.181e-01]
leoprint:  61%|######1   | 1472/2400 [29:52<44:55,  2.90s/it, lr: 5.0e-05 loss: 2.181e-01]
leoprint:  61%|######1   | 1472/2400 [29:52<44:55,  2.90s/it, lr: 5.0e-05 loss: 2.181e-01]
leoprint:  61%|######1   | 1472/2400 [29:56<44:55,  2.90s/it, lr: 5.0e-05 loss: 3.499e-01]
leoprint:  61%|######1   | 1472/2400 [29:56<44:55,  2.90s/it, lr: 5.0e-05 loss: 3.499e-01]
leoprint:  61%|######1   | 1473/2400 [29:56<47:18,  3.06s/it, lr: 5.0e-05 loss: 3.499e-01]
leoprint:  61%|######1   | 1473/2400 [29:56<47:18,  3.06s/it, lr: 5.0e-05 loss: 3.499e-01]
leoprint:  61%|######1   | 1473/2400 [29:59<47:18,  3.06s/it, lr: 5.0e-05 loss: 2.656e-01]
leoprint:  61%|######1   | 1473/2400 [29:59<47:18,  3.06s/it, lr: 5.0e-05 loss: 2.656e-01]
leoprint:  61%|######1   | 1474/2400 [29:59<49:34,  3.21s/it, lr: 5.0e-05 loss: 2.656e-01]
leoprint:  61%|######1   | 1474/2400 [29:59<49:34,  3.21s/it, lr: 5.0e-05 loss: 2.656e-01]
leoprint:  61%|######1   | 1474/2400 [30:03<49:34,  3.21s/it, lr: 5.0e-05 loss: 2.151e-01]
leoprint:  61%|######1   | 1474/2400 [30:03<49:34,  3.21s/it, lr: 5.0e-05 loss: 2.151e-01]
leoprint:  61%|######1   | 1475/2400 [30:03<51:38,  3.35s/it, lr: 5.0e-05 loss: 2.151e-01]
leoprint:  61%|######1   | 1475/2400 [30:03<51:38,  3.35s/it, lr: 5.0e-05 loss: 2.151e-01]
leoprint:  61%|######1   | 1475/2400 [30:06<51:38,  3.35s/it, lr: 5.0e-05 loss: 3.304e-01]
leoprint:  61%|######1   | 1475/2400 [30:06<51:38,  3.35s/it, lr: 5.0e-05 loss: 3.304e-01]
leoprint:  62%|######1   | 1476/2400 [30:06<52:16,  3.39s/it, lr: 5.0e-05 loss: 3.304e-01]
leoprint:  62%|######1   | 1476/2400 [30:06<52:16,  3.39s/it, lr: 5.0e-05 loss: 3.304e-01]
leoprint:  62%|######1   | 1476/2400 [30:10<52:16,  3.39s/it, lr: 5.0e-05 loss: 1.992e-01]
leoprint:  62%|######1   | 1476/2400 [30:10<52:16,  3.39s/it, lr: 5.0e-05 loss: 1.992e-01]
leoprint:  62%|######1   | 1477/2400 [30:10<53:14,  3.46s/it, lr: 5.0e-05 loss: 1.992e-01]
leoprint:  62%|######1   | 1477/2400 [30:10<53:14,  3.46s/it, lr: 5.0e-05 loss: 1.992e-01]
leoprint:  62%|######1   | 1477/2400 [30:14<53:14,  3.46s/it, lr: 5.0e-05 loss: 2.630e-01]
leoprint:  62%|######1   | 1477/2400 [30:14<53:14,  3.46s/it, lr: 5.0e-05 loss: 2.630e-01]
leoprint:  62%|######1   | 1478/2400 [30:14<53:21,  3.47s/it, lr: 5.0e-05 loss: 2.630e-01]
leoprint:  62%|######1   | 1478/2400 [30:14<53:21,  3.47s/it, lr: 5.0e-05 loss: 2.630e-01]
leoprint:  62%|######1   | 1478/2400 [30:17<53:21,  3.47s/it, lr: 5.0e-05 loss: 3.737e-01]
leoprint:  62%|######1   | 1478/2400 [30:17<53:21,  3.47s/it, lr: 5.0e-05 loss: 3.737e-01]
leoprint:  62%|######1   | 1479/2400 [30:17<53:24,  3.48s/it, lr: 5.0e-05 loss: 3.737e-01]
leoprint:  62%|######1   | 1479/2400 [30:17<53:24,  3.48s/it, lr: 5.0e-05 loss: 3.737e-01]
leoprint:  62%|######1   | 1479/2400 [30:21<53:24,  3.48s/it, lr: 5.0e-05 loss: 3.757e-01]
leoprint:  62%|######1   | 1479/2400 [30:21<53:24,  3.48s/it, lr: 5.0e-05 loss: 3.757e-01]
leoprint:  62%|######1   | 1480/2400 [30:24<53:21,  3.48s/it, lr: 5.0e-05 loss: 3.494e-01]
leoprint:  62%|######1   | 1480/2400 [30:24<53:21,  3.48s/it, lr: 5.0e-05 loss: 3.494e-01]
leoprint:  62%|######1   | 1481/2400 [30:24<41:39,  2.72s/it, lr: 5.0e-05 loss: 3.494e-01]
leoprint:  62%|######1   | 1481/2400 [30:24<41:39,  2.72s/it, lr: 5.0e-05 loss: 3.494e-01]
leoprint:  62%|######1   | 1481/2400 [30:28<41:39,  2.72s/it, lr: 5.0e-05 loss: 3.901e-01]
leoprint:  62%|######1   | 1481/2400 [30:28<41:39,  2.72s/it, lr: 5.0e-05 loss: 3.901e-01]
leoprint:  62%|######1   | 1482/2400 [30:28<44:34,  2.91s/it, lr: 5.0e-05 loss: 3.901e-01]
leoprint:  62%|######1   | 1482/2400 [30:28<44:34,  2.91s/it, lr: 5.0e-05 loss: 3.901e-01]
leoprint:  62%|######1   | 1482/2400 [30:31<44:34,  2.91s/it, lr: 5.0e-05 loss: 2.426e-01]
leoprint:  62%|######1   | 1482/2400 [30:31<44:34,  2.91s/it, lr: 5.0e-05 loss: 2.426e-01]
leoprint:  62%|######1   | 1483/2400 [30:31<47:17,  3.09s/it, lr: 5.0e-05 loss: 2.426e-01]
leoprint:  62%|######1   | 1483/2400 [30:31<47:17,  3.09s/it, lr: 5.0e-05 loss: 2.426e-01]
leoprint:  62%|######1   | 1483/2400 [30:35<47:17,  3.09s/it, lr: 5.0e-05 loss: 1.969e-01]
leoprint:  62%|######1   | 1483/2400 [30:35<47:17,  3.09s/it, lr: 5.0e-05 loss: 1.969e-01]
leoprint:  62%|######1   | 1484/2400 [30:35<49:25,  3.24s/it, lr: 5.0e-05 loss: 1.969e-01]
leoprint:  62%|######1   | 1484/2400 [30:35<49:25,  3.24s/it, lr: 5.0e-05 loss: 1.969e-01]
leoprint:  62%|######1   | 1484/2400 [30:39<49:25,  3.24s/it, lr: 5.0e-05 loss: 3.712e-01]
leoprint:  62%|######1   | 1484/2400 [30:39<49:25,  3.24s/it, lr: 5.0e-05 loss: 3.712e-01]
leoprint:  62%|######1   | 1485/2400 [30:39<50:30,  3.31s/it, lr: 5.0e-05 loss: 3.712e-01]
leoprint:  62%|######1   | 1485/2400 [30:39<50:30,  3.31s/it, lr: 5.0e-05 loss: 3.712e-01]
leoprint:  62%|######1   | 1485/2400 [30:42<50:30,  3.31s/it, lr: 5.0e-05 loss: 2.722e-01]
leoprint:  62%|######1   | 1485/2400 [30:42<50:30,  3.31s/it, lr: 5.0e-05 loss: 2.722e-01]
leoprint:  62%|######1   | 1486/2400 [30:42<51:17,  3.37s/it, lr: 5.0e-05 loss: 2.722e-01]
leoprint:  62%|######1   | 1486/2400 [30:42<51:17,  3.37s/it, lr: 5.0e-05 loss: 2.722e-01]
leoprint:  62%|######1   | 1486/2400 [30:46<51:17,  3.37s/it, lr: 5.0e-05 loss: 2.460e-01]
leoprint:  62%|######1   | 1486/2400 [30:46<51:17,  3.37s/it, lr: 5.0e-05 loss: 2.460e-01]
leoprint:  62%|######1   | 1487/2400 [30:46<53:27,  3.51s/it, lr: 5.0e-05 loss: 2.460e-01]
leoprint:  62%|######1   | 1487/2400 [30:46<53:27,  3.51s/it, lr: 5.0e-05 loss: 2.460e-01]
leoprint:  62%|######1   | 1487/2400 [30:49<53:27,  3.51s/it, lr: 5.0e-05 loss: 3.130e-01]
leoprint:  62%|######1   | 1487/2400 [30:49<53:27,  3.51s/it, lr: 5.0e-05 loss: 3.130e-01]
leoprint:  62%|######2   | 1488/2400 [30:49<53:21,  3.51s/it, lr: 5.0e-05 loss: 3.130e-01]
leoprint:  62%|######2   | 1488/2400 [30:49<53:21,  3.51s/it, lr: 5.0e-05 loss: 3.130e-01]
leoprint:  62%|######2   | 1488/2400 [30:53<53:21,  3.51s/it, lr: 5.0e-05 loss: 3.573e-01]
leoprint:  62%|######2   | 1488/2400 [30:53<53:21,  3.51s/it, lr: 5.0e-05 loss: 3.573e-01]
leoprint:  62%|######2   | 1489/2400 [30:53<53:16,  3.51s/it, lr: 5.0e-05 loss: 3.573e-01]
leoprint:  62%|######2   | 1489/2400 [30:53<53:16,  3.51s/it, lr: 5.0e-05 loss: 3.573e-01]
leoprint:  62%|######2   | 1489/2400 [30:56<53:16,  3.51s/it, lr: 5.0e-05 loss: 2.241e-01]
leoprint:  62%|######2   | 1489/2400 [30:56<53:16,  3.51s/it, lr: 5.0e-05 loss: 2.241e-01]
leoprint:  62%|######2   | 1490/2400 [31:00<53:13,  3.51s/it, lr: 5.0e-05 loss: 2.865e-01]
leoprint:  62%|######2   | 1490/2400 [31:00<53:13,  3.51s/it, lr: 5.0e-05 loss: 2.865e-01]
leoprint:  62%|######2   | 1491/2400 [31:00<40:57,  2.70s/it, lr: 5.0e-05 loss: 2.865e-01]
leoprint:  62%|######2   | 1491/2400 [31:00<40:57,  2.70s/it, lr: 5.0e-05 loss: 2.865e-01]
leoprint:  62%|######2   | 1491/2400 [31:04<40:57,  2.70s/it, lr: 5.0e-05 loss: 2.230e-01]
leoprint:  62%|######2   | 1491/2400 [31:04<40:57,  2.70s/it, lr: 5.0e-05 loss: 2.230e-01]
leoprint:  62%|######2   | 1492/2400 [31:04<44:10,  2.92s/it, lr: 5.0e-05 loss: 2.230e-01]
leoprint:  62%|######2   | 1492/2400 [31:04<44:10,  2.92s/it, lr: 5.0e-05 loss: 2.230e-01]
leoprint:  62%|######2   | 1492/2400 [31:07<44:10,  2.92s/it, lr: 5.0e-05 loss: 3.975e-01]
leoprint:  62%|######2   | 1492/2400 [31:07<44:10,  2.92s/it, lr: 5.0e-05 loss: 3.975e-01]
leoprint:  62%|######2   | 1493/2400 [31:07<46:24,  3.07s/it, lr: 5.0e-05 loss: 3.975e-01]
leoprint:  62%|######2   | 1493/2400 [31:07<46:24,  3.07s/it, lr: 5.0e-05 loss: 3.975e-01]
leoprint:  62%|######2   | 1493/2400 [31:11<46:24,  3.07s/it, lr: 5.0e-05 loss: 2.714e-01]
leoprint:  62%|######2   | 1493/2400 [31:11<46:24,  3.07s/it, lr: 5.0e-05 loss: 2.714e-01]
leoprint:  62%|######2   | 1494/2400 [31:11<48:36,  3.22s/it, lr: 5.0e-05 loss: 2.714e-01]
leoprint:  62%|######2   | 1494/2400 [31:11<48:36,  3.22s/it, lr: 5.0e-05 loss: 2.714e-01]
leoprint:  62%|######2   | 1494/2400 [31:14<48:36,  3.22s/it, lr: 5.0e-05 loss: 2.735e-01]
leoprint:  62%|######2   | 1494/2400 [31:14<48:36,  3.22s/it, lr: 5.0e-05 loss: 2.735e-01]
leoprint:  62%|######2   | 1495/2400 [31:14<50:16,  3.33s/it, lr: 5.0e-05 loss: 2.735e-01]
leoprint:  62%|######2   | 1495/2400 [31:14<50:16,  3.33s/it, lr: 5.0e-05 loss: 2.735e-01]
leoprint:  62%|######2   | 1495/2400 [31:18<50:16,  3.33s/it, lr: 5.0e-05 loss: 3.353e-01]
leoprint:  62%|######2   | 1495/2400 [31:18<50:16,  3.33s/it, lr: 5.0e-05 loss: 3.353e-01]
leoprint:  62%|######2   | 1496/2400 [31:18<50:56,  3.38s/it, lr: 5.0e-05 loss: 3.353e-01]
leoprint:  62%|######2   | 1496/2400 [31:18<50:56,  3.38s/it, lr: 5.0e-05 loss: 3.353e-01]
leoprint:  62%|######2   | 1496/2400 [31:21<50:56,  3.38s/it, lr: 5.0e-05 loss: 3.148e-01]
leoprint:  62%|######2   | 1496/2400 [31:21<50:56,  3.38s/it, lr: 5.0e-05 loss: 3.148e-01]
leoprint:  62%|######2   | 1497/2400 [31:21<51:56,  3.45s/it, lr: 5.0e-05 loss: 3.148e-01]
leoprint:  62%|######2   | 1497/2400 [31:21<51:56,  3.45s/it, lr: 5.0e-05 loss: 3.148e-01]
leoprint:  62%|######2   | 1497/2400 [31:25<51:56,  3.45s/it, lr: 5.0e-05 loss: 2.813e-01]
leoprint:  62%|######2   | 1497/2400 [31:25<51:56,  3.45s/it, lr: 5.0e-05 loss: 2.813e-01]
leoprint:  62%|######2   | 1498/2400 [31:25<52:49,  3.51s/it, lr: 5.0e-05 loss: 2.813e-01]
leoprint:  62%|######2   | 1498/2400 [31:25<52:49,  3.51s/it, lr: 5.0e-05 loss: 2.813e-01]
leoprint:  62%|######2   | 1498/2400 [31:29<52:49,  3.51s/it, lr: 5.0e-05 loss: 2.934e-01]
leoprint:  62%|######2   | 1498/2400 [31:29<52:49,  3.51s/it, lr: 5.0e-05 loss: 2.934e-01]
leoprint:  62%|######2   | 1499/2400 [31:29<52:43,  3.51s/it, lr: 5.0e-05 loss: 2.934e-01]
leoprint:  62%|######2   | 1499/2400 [31:29<52:43,  3.51s/it, lr: 5.0e-05 loss: 2.934e-01]
leoprint:  62%|######2   | 1499/2400 [31:32<52:43,  3.51s/it, lr: 5.0e-05 loss: 3.131e-01]
leoprint:  62%|######2   | 1499/2400 [31:32<52:43,  3.51s/it, lr: 5.0e-05 loss: 3.131e-01]
leoprint:  62%|######2   | 1500/2400 [31:36<52:39,  3.51s/it, lr: 5.0e-05 loss: 2.177e-01]
leoprint:  62%|######2   | 1500/2400 [31:36<52:39,  3.51s/it, lr: 5.0e-05 loss: 2.177e-01]
leoprint:  63%|######2   | 1501/2400 [31:36<40:55,  2.73s/it, lr: 5.0e-05 loss: 2.177e-01]
leoprint:  63%|######2   | 1501/2400 [31:36<40:55,  2.73s/it, lr: 5.0e-05 loss: 2.177e-01]
leoprint:  63%|######2   | 1501/2400 [31:39<40:55,  2.73s/it, lr: 5.0e-05 loss: 3.126e-01]
leoprint:  63%|######2   | 1501/2400 [31:39<40:55,  2.73s/it, lr: 5.0e-05 loss: 3.126e-01]
leoprint:  63%|######2   | 1502/2400 [31:39<43:45,  2.92s/it, lr: 5.0e-05 loss: 3.126e-01]
leoprint:  63%|######2   | 1502/2400 [31:39<43:45,  2.92s/it, lr: 5.0e-05 loss: 3.126e-01]
leoprint:  63%|######2   | 1502/2400 [31:43<43:45,  2.92s/it, lr: 5.0e-05 loss: 3.725e-01]
leoprint:  63%|######2   | 1502/2400 [31:43<43:45,  2.92s/it, lr: 5.0e-05 loss: 3.725e-01]
leoprint:  63%|######2   | 1503/2400 [31:43<45:57,  3.07s/it, lr: 5.0e-05 loss: 3.725e-01]
leoprint:  63%|######2   | 1503/2400 [31:43<45:57,  3.07s/it, lr: 5.0e-05 loss: 3.725e-01]
leoprint:  63%|######2   | 1503/2400 [31:46<45:57,  3.07s/it, lr: 5.0e-05 loss: 3.137e-01]
leoprint:  63%|######2   | 1503/2400 [31:46<45:57,  3.07s/it, lr: 5.0e-05 loss: 3.137e-01]
leoprint:  63%|######2   | 1504/2400 [31:46<48:14,  3.23s/it, lr: 5.0e-05 loss: 3.137e-01]
leoprint:  63%|######2   | 1504/2400 [31:46<48:14,  3.23s/it, lr: 5.0e-05 loss: 3.137e-01]
leoprint:  63%|######2   | 1504/2400 [31:50<48:14,  3.23s/it, lr: 5.0e-05 loss: 2.845e-01]
leoprint:  63%|######2   | 1504/2400 [31:50<48:14,  3.23s/it, lr: 5.0e-05 loss: 2.845e-01]
leoprint:  63%|######2   | 1505/2400 [31:50<49:21,  3.31s/it, lr: 5.0e-05 loss: 2.845e-01]
leoprint:  63%|######2   | 1505/2400 [31:50<49:21,  3.31s/it, lr: 5.0e-05 loss: 2.845e-01]
leoprint:  63%|######2   | 1505/2400 [31:53<49:21,  3.31s/it, lr: 5.0e-05 loss: 3.262e-01]
leoprint:  63%|######2   | 1505/2400 [31:53<49:21,  3.31s/it, lr: 5.0e-05 loss: 3.262e-01]
leoprint:  63%|######2   | 1506/2400 [31:54<50:08,  3.36s/it, lr: 5.0e-05 loss: 3.262e-01]
leoprint:  63%|######2   | 1506/2400 [31:54<50:08,  3.36s/it, lr: 5.0e-05 loss: 3.262e-01]
leoprint:  63%|######2   | 1506/2400 [31:57<50:08,  3.36s/it, lr: 5.0e-05 loss: 3.703e-01]
leoprint:  63%|######2   | 1506/2400 [31:57<50:08,  3.36s/it, lr: 5.0e-05 loss: 3.703e-01]
leoprint:  63%|######2   | 1507/2400 [31:57<50:41,  3.41s/it, lr: 5.0e-05 loss: 3.703e-01]
leoprint:  63%|######2   | 1507/2400 [31:57<50:41,  3.41s/it, lr: 5.0e-05 loss: 3.703e-01]
leoprint:  63%|######2   | 1507/2400 [32:01<50:41,  3.41s/it, lr: 5.0e-05 loss: 3.298e-01]
leoprint:  63%|######2   | 1507/2400 [32:01<50:41,  3.41s/it, lr: 5.0e-05 loss: 3.298e-01]
leoprint:  63%|######2   | 1508/2400 [32:01<51:04,  3.44s/it, lr: 5.0e-05 loss: 3.298e-01]
leoprint:  63%|######2   | 1508/2400 [32:01<51:04,  3.44s/it, lr: 5.0e-05 loss: 3.298e-01]
leoprint:  63%|######2   | 1508/2400 [32:04<51:04,  3.44s/it, lr: 5.0e-05 loss: 2.581e-01]
leoprint:  63%|######2   | 1508/2400 [32:04<51:04,  3.44s/it, lr: 5.0e-05 loss: 2.581e-01]
leoprint:  63%|######2   | 1509/2400 [32:04<51:50,  3.49s/it, lr: 5.0e-05 loss: 2.581e-01]
leoprint:  63%|######2   | 1509/2400 [32:04<51:50,  3.49s/it, lr: 5.0e-05 loss: 2.581e-01]
leoprint:  63%|######2   | 1509/2400 [32:08<51:50,  3.49s/it, lr: 5.0e-05 loss: 3.260e-01]
leoprint:  63%|######2   | 1509/2400 [32:08<51:50,  3.49s/it, lr: 5.0e-05 loss: 3.260e-01]
leoprint:  63%|######2   | 1510/2400 [32:11<51:46,  3.49s/it, lr: 5.0e-05 loss: 2.071e-01]
leoprint:  63%|######2   | 1510/2400 [32:11<51:46,  3.49s/it, lr: 5.0e-05 loss: 2.071e-01]
leoprint:  63%|######2   | 1511/2400 [32:11<40:17,  2.72s/it, lr: 5.0e-05 loss: 2.071e-01]
leoprint:  63%|######2   | 1511/2400 [32:11<40:17,  2.72s/it, lr: 5.0e-05 loss: 2.071e-01]
leoprint:  63%|######2   | 1511/2400 [32:15<40:17,  2.72s/it, lr: 5.0e-05 loss: 2.448e-01]
leoprint:  63%|######2   | 1511/2400 [32:15<40:17,  2.72s/it, lr: 5.0e-05 loss: 2.448e-01]
leoprint:  63%|######3   | 1512/2400 [32:15<43:31,  2.94s/it, lr: 5.0e-05 loss: 2.448e-01]
leoprint:  63%|######3   | 1512/2400 [32:15<43:31,  2.94s/it, lr: 5.0e-05 loss: 2.448e-01]
leoprint:  63%|######3   | 1512/2400 [32:19<43:31,  2.94s/it, lr: 5.0e-05 loss: 3.742e-01]
leoprint:  63%|######3   | 1512/2400 [32:19<43:31,  2.94s/it, lr: 5.0e-05 loss: 3.742e-01]
leoprint:  63%|######3   | 1513/2400 [32:19<45:36,  3.09s/it, lr: 5.0e-05 loss: 3.742e-01]
leoprint:  63%|######3   | 1513/2400 [32:19<45:36,  3.09s/it, lr: 5.0e-05 loss: 3.742e-01]
leoprint:  63%|######3   | 1513/2400 [32:22<45:36,  3.09s/it, lr: 5.0e-05 loss: 2.538e-01]
leoprint:  63%|######3   | 1513/2400 [32:22<45:36,  3.09s/it, lr: 5.0e-05 loss: 2.538e-01]
leoprint:  63%|######3   | 1514/2400 [32:22<47:12,  3.20s/it, lr: 5.0e-05 loss: 2.538e-01]
leoprint:  63%|######3   | 1514/2400 [32:22<47:12,  3.20s/it, lr: 5.0e-05 loss: 2.538e-01]
leoprint:  63%|######3   | 1514/2400 [32:26<47:12,  3.20s/it, lr: 5.0e-05 loss: 2.330e-01]
leoprint:  63%|######3   | 1514/2400 [32:26<47:12,  3.20s/it, lr: 5.0e-05 loss: 2.330e-01]
leoprint:  63%|######3   | 1515/2400 [32:26<48:42,  3.30s/it, lr: 5.0e-05 loss: 2.330e-01]
leoprint:  63%|######3   | 1515/2400 [32:26<48:42,  3.30s/it, lr: 5.0e-05 loss: 2.330e-01]
leoprint:  63%|######3   | 1515/2400 [32:29<48:42,  3.30s/it, lr: 5.0e-05 loss: 2.791e-01]
leoprint:  63%|######3   | 1515/2400 [32:29<48:42,  3.30s/it, lr: 5.0e-05 loss: 2.791e-01]
leoprint:  63%|######3   | 1516/2400 [32:29<49:30,  3.36s/it, lr: 5.0e-05 loss: 2.791e-01]
leoprint:  63%|######3   | 1516/2400 [32:29<49:30,  3.36s/it, lr: 5.0e-05 loss: 2.791e-01]
leoprint:  63%|######3   | 1516/2400 [32:33<49:30,  3.36s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  63%|######3   | 1516/2400 [32:33<49:30,  3.36s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  63%|######3   | 1517/2400 [32:33<50:06,  3.40s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  63%|######3   | 1517/2400 [32:33<50:06,  3.40s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  63%|######3   | 1517/2400 [32:36<50:06,  3.40s/it, lr: 5.0e-05 loss: 2.204e-01]
leoprint:  63%|######3   | 1517/2400 [32:36<50:06,  3.40s/it, lr: 5.0e-05 loss: 2.204e-01]
leoprint:  63%|######3   | 1518/2400 [32:36<50:27,  3.43s/it, lr: 5.0e-05 loss: 2.204e-01]
leoprint:  63%|######3   | 1518/2400 [32:36<50:27,  3.43s/it, lr: 5.0e-05 loss: 2.204e-01]
leoprint:  63%|######3   | 1518/2400 [32:40<50:27,  3.43s/it, lr: 5.0e-05 loss: 2.742e-01]
leoprint:  63%|######3   | 1518/2400 [32:40<50:27,  3.43s/it, lr: 5.0e-05 loss: 2.742e-01]
leoprint:  63%|######3   | 1519/2400 [32:40<50:41,  3.45s/it, lr: 5.0e-05 loss: 2.742e-01]
leoprint:  63%|######3   | 1519/2400 [32:40<50:41,  3.45s/it, lr: 5.0e-05 loss: 2.742e-01]
leoprint:  63%|######3   | 1519/2400 [32:43<50:41,  3.45s/it, lr: 5.0e-05 loss: 2.997e-01]
leoprint:  63%|######3   | 1519/2400 [32:43<50:41,  3.45s/it, lr: 5.0e-05 loss: 2.997e-01]
leoprint:  63%|######3   | 1520/2400 [32:47<50:38,  3.45s/it, lr: 5.0e-05 loss: 2.948e-01]
leoprint:  63%|######3   | 1520/2400 [32:47<50:38,  3.45s/it, lr: 5.0e-05 loss: 2.948e-01]
leoprint:  63%|######3   | 1521/2400 [32:47<40:09,  2.74s/it, lr: 5.0e-05 loss: 2.948e-01]
leoprint:  63%|######3   | 1521/2400 [32:47<40:09,  2.74s/it, lr: 5.0e-05 loss: 2.948e-01]
leoprint:  63%|######3   | 1521/2400 [32:51<40:09,  2.74s/it, lr: 5.0e-05 loss: 2.520e-01]
leoprint:  63%|######3   | 1521/2400 [32:51<40:09,  2.74s/it, lr: 5.0e-05 loss: 2.520e-01]
leoprint:  63%|######3   | 1522/2400 [32:51<43:17,  2.96s/it, lr: 5.0e-05 loss: 2.520e-01]
leoprint:  63%|######3   | 1522/2400 [32:51<43:17,  2.96s/it, lr: 5.0e-05 loss: 2.520e-01]
leoprint:  63%|######3   | 1522/2400 [32:54<43:17,  2.96s/it, lr: 5.0e-05 loss: 2.371e-01]
leoprint:  63%|######3   | 1522/2400 [32:54<43:17,  2.96s/it, lr: 5.0e-05 loss: 2.371e-01]
leoprint:  63%|######3   | 1523/2400 [32:54<45:19,  3.10s/it, lr: 5.0e-05 loss: 2.371e-01]
leoprint:  63%|######3   | 1523/2400 [32:54<45:19,  3.10s/it, lr: 5.0e-05 loss: 2.371e-01]
leoprint:  63%|######3   | 1523/2400 [32:58<45:19,  3.10s/it, lr: 5.0e-05 loss: 4.003e-01]
leoprint:  63%|######3   | 1523/2400 [32:58<45:19,  3.10s/it, lr: 5.0e-05 loss: 4.003e-01]
leoprint:  64%|######3   | 1524/2400 [32:58<46:52,  3.21s/it, lr: 5.0e-05 loss: 4.003e-01]
leoprint:  64%|######3   | 1524/2400 [32:58<46:52,  3.21s/it, lr: 5.0e-05 loss: 4.003e-01]
leoprint:  64%|######3   | 1524/2400 [33:01<46:52,  3.21s/it, lr: 5.0e-05 loss: 3.871e-01]
leoprint:  64%|######3   | 1524/2400 [33:01<46:52,  3.21s/it, lr: 5.0e-05 loss: 3.871e-01]
leoprint:  64%|######3   | 1525/2400 [33:01<48:01,  3.29s/it, lr: 5.0e-05 loss: 3.871e-01]
leoprint:  64%|######3   | 1525/2400 [33:01<48:01,  3.29s/it, lr: 5.0e-05 loss: 3.871e-01]
leoprint:  64%|######3   | 1525/2400 [33:05<48:01,  3.29s/it, lr: 5.0e-05 loss: 2.748e-01]
leoprint:  64%|######3   | 1525/2400 [33:05<48:01,  3.29s/it, lr: 5.0e-05 loss: 2.748e-01]
leoprint:  64%|######3   | 1526/2400 [33:05<48:48,  3.35s/it, lr: 5.0e-05 loss: 2.748e-01]
leoprint:  64%|######3   | 1526/2400 [33:05<48:48,  3.35s/it, lr: 5.0e-05 loss: 2.748e-01]
leoprint:  64%|######3   | 1526/2400 [33:08<48:48,  3.35s/it, lr: 5.0e-05 loss: 3.057e-01]
leoprint:  64%|######3   | 1526/2400 [33:08<48:48,  3.35s/it, lr: 5.0e-05 loss: 3.057e-01]
leoprint:  64%|######3   | 1527/2400 [33:08<50:28,  3.47s/it, lr: 5.0e-05 loss: 3.057e-01]
leoprint:  64%|######3   | 1527/2400 [33:08<50:28,  3.47s/it, lr: 5.0e-05 loss: 3.057e-01]
leoprint:  64%|######3   | 1527/2400 [33:12<50:28,  3.47s/it, lr: 5.0e-05 loss: 2.774e-01]
leoprint:  64%|######3   | 1527/2400 [33:12<50:28,  3.47s/it, lr: 5.0e-05 loss: 2.774e-01]
leoprint:  64%|######3   | 1528/2400 [33:12<51:03,  3.51s/it, lr: 5.0e-05 loss: 2.774e-01]
leoprint:  64%|######3   | 1528/2400 [33:12<51:03,  3.51s/it, lr: 5.0e-05 loss: 2.774e-01]
leoprint:  64%|######3   | 1528/2400 [33:16<51:03,  3.51s/it, lr: 5.0e-05 loss: 3.126e-01]
leoprint:  64%|######3   | 1528/2400 [33:16<51:03,  3.51s/it, lr: 5.0e-05 loss: 3.126e-01]
leoprint:  64%|######3   | 1529/2400 [33:16<50:58,  3.51s/it, lr: 5.0e-05 loss: 3.126e-01]
leoprint:  64%|######3   | 1529/2400 [33:16<50:58,  3.51s/it, lr: 5.0e-05 loss: 3.126e-01]
leoprint:  64%|######3   | 1529/2400 [33:19<50:58,  3.51s/it, lr: 5.0e-05 loss: 2.910e-01]
leoprint:  64%|######3   | 1529/2400 [33:19<50:58,  3.51s/it, lr: 5.0e-05 loss: 2.910e-01]
leoprint:  64%|######3   | 1530/2400 [33:23<50:55,  3.51s/it, lr: 5.0e-05 loss: 3.391e-01]
leoprint:  64%|######3   | 1530/2400 [33:23<50:55,  3.51s/it, lr: 5.0e-05 loss: 3.391e-01]
leoprint:  64%|######3   | 1531/2400 [33:23<39:11,  2.71s/it, lr: 5.0e-05 loss: 3.391e-01]
leoprint:  64%|######3   | 1531/2400 [33:23<39:11,  2.71s/it, lr: 5.0e-05 loss: 3.391e-01]
leoprint:  64%|######3   | 1531/2400 [33:26<39:11,  2.71s/it, lr: 5.0e-05 loss: 2.121e-01]
leoprint:  64%|######3   | 1531/2400 [33:26<39:11,  2.71s/it, lr: 5.0e-05 loss: 2.121e-01]
leoprint:  64%|######3   | 1532/2400 [33:26<42:23,  2.93s/it, lr: 5.0e-05 loss: 2.121e-01]
leoprint:  64%|######3   | 1532/2400 [33:26<42:23,  2.93s/it, lr: 5.0e-05 loss: 2.121e-01]
leoprint:  64%|######3   | 1532/2400 [33:30<42:23,  2.93s/it, lr: 5.0e-05 loss: 3.027e-01]
leoprint:  64%|######3   | 1532/2400 [33:30<42:23,  2.93s/it, lr: 5.0e-05 loss: 3.027e-01]
leoprint:  64%|######3   | 1533/2400 [33:30<45:22,  3.14s/it, lr: 5.0e-05 loss: 3.027e-01]
leoprint:  64%|######3   | 1533/2400 [33:30<45:22,  3.14s/it, lr: 5.0e-05 loss: 3.027e-01]
leoprint:  64%|######3   | 1533/2400 [33:33<45:22,  3.14s/it, lr: 5.0e-05 loss: 2.272e-01]
leoprint:  64%|######3   | 1533/2400 [33:33<45:22,  3.14s/it, lr: 5.0e-05 loss: 2.272e-01]
leoprint:  64%|######3   | 1534/2400 [33:33<46:43,  3.24s/it, lr: 5.0e-05 loss: 2.272e-01]
leoprint:  64%|######3   | 1534/2400 [33:33<46:43,  3.24s/it, lr: 5.0e-05 loss: 2.272e-01]
leoprint:  64%|######3   | 1534/2400 [33:37<46:43,  3.24s/it, lr: 5.0e-05 loss: 3.247e-01]
leoprint:  64%|######3   | 1534/2400 [33:37<46:43,  3.24s/it, lr: 5.0e-05 loss: 3.247e-01]
leoprint:  64%|######3   | 1535/2400 [33:37<47:43,  3.31s/it, lr: 5.0e-05 loss: 3.247e-01]
leoprint:  64%|######3   | 1535/2400 [33:37<47:43,  3.31s/it, lr: 5.0e-05 loss: 3.247e-01]
leoprint:  64%|######3   | 1535/2400 [33:40<47:43,  3.31s/it, lr: 5.0e-05 loss: 3.433e-01]
leoprint:  64%|######3   | 1535/2400 [33:40<47:43,  3.31s/it, lr: 5.0e-05 loss: 3.433e-01]
leoprint:  64%|######4   | 1536/2400 [33:40<48:27,  3.36s/it, lr: 5.0e-05 loss: 3.433e-01]
leoprint:  64%|######4   | 1536/2400 [33:40<48:27,  3.36s/it, lr: 5.0e-05 loss: 3.433e-01]
leoprint:  64%|######4   | 1536/2400 [33:44<48:27,  3.36s/it, lr: 5.0e-05 loss: 3.007e-01]
leoprint:  64%|######4   | 1536/2400 [33:44<48:27,  3.36s/it, lr: 5.0e-05 loss: 3.007e-01]
leoprint:  64%|######4   | 1537/2400 [33:44<48:57,  3.40s/it, lr: 5.0e-05 loss: 3.007e-01]
leoprint:  64%|######4   | 1537/2400 [33:44<48:57,  3.40s/it, lr: 5.0e-05 loss: 3.007e-01]
leoprint:  64%|######4   | 1537/2400 [33:48<48:57,  3.40s/it, lr: 5.0e-05 loss: 2.514e-01]
leoprint:  64%|######4   | 1537/2400 [33:48<48:57,  3.40s/it, lr: 5.0e-05 loss: 2.514e-01]
leoprint:  64%|######4   | 1538/2400 [33:48<50:05,  3.49s/it, lr: 5.0e-05 loss: 2.514e-01]
leoprint:  64%|######4   | 1538/2400 [33:48<50:05,  3.49s/it, lr: 5.0e-05 loss: 2.514e-01]
leoprint:  64%|######4   | 1538/2400 [33:51<50:05,  3.49s/it, lr: 5.0e-05 loss: 3.742e-01]
leoprint:  64%|######4   | 1538/2400 [33:51<50:05,  3.49s/it, lr: 5.0e-05 loss: 3.742e-01]
leoprint:  64%|######4   | 1539/2400 [33:51<50:05,  3.49s/it, lr: 5.0e-05 loss: 3.742e-01]
leoprint:  64%|######4   | 1539/2400 [33:51<50:05,  3.49s/it, lr: 5.0e-05 loss: 3.742e-01]
leoprint:  64%|######4   | 1539/2400 [33:55<50:05,  3.49s/it, lr: 5.0e-05 loss: 3.295e-01]
leoprint:  64%|######4   | 1539/2400 [33:55<50:05,  3.49s/it, lr: 5.0e-05 loss: 3.295e-01]
leoprint:  64%|######4   | 1540/2400 [33:58<50:01,  3.49s/it, lr: 5.0e-05 loss: 2.247e-01]
leoprint:  64%|######4   | 1540/2400 [33:58<50:01,  3.49s/it, lr: 5.0e-05 loss: 2.247e-01]
leoprint:  64%|######4   | 1541/2400 [33:58<38:57,  2.72s/it, lr: 5.0e-05 loss: 2.247e-01]
leoprint:  64%|######4   | 1541/2400 [33:58<38:57,  2.72s/it, lr: 5.0e-05 loss: 2.247e-01]
leoprint:  64%|######4   | 1541/2400 [34:02<38:57,  2.72s/it, lr: 5.0e-05 loss: 3.464e-01]
leoprint:  64%|######4   | 1541/2400 [34:02<38:57,  2.72s/it, lr: 5.0e-05 loss: 3.464e-01]
leoprint:  64%|######4   | 1542/2400 [34:02<41:38,  2.91s/it, lr: 5.0e-05 loss: 3.464e-01]
leoprint:  64%|######4   | 1542/2400 [34:02<41:38,  2.91s/it, lr: 5.0e-05 loss: 3.464e-01]
leoprint:  64%|######4   | 1542/2400 [34:05<41:38,  2.91s/it, lr: 5.0e-05 loss: 2.611e-01]
leoprint:  64%|######4   | 1542/2400 [34:05<41:38,  2.91s/it, lr: 5.0e-05 loss: 2.611e-01]
leoprint:  64%|######4   | 1543/2400 [34:05<43:46,  3.06s/it, lr: 5.0e-05 loss: 2.611e-01]
leoprint:  64%|######4   | 1543/2400 [34:05<43:46,  3.06s/it, lr: 5.0e-05 loss: 2.611e-01]
leoprint:  64%|######4   | 1543/2400 [34:09<43:46,  3.06s/it, lr: 5.0e-05 loss: 1.939e-01]
leoprint:  64%|######4   | 1543/2400 [34:09<43:46,  3.06s/it, lr: 5.0e-05 loss: 1.939e-01]
leoprint:  64%|######4   | 1544/2400 [34:09<46:30,  3.26s/it, lr: 5.0e-05 loss: 1.939e-01]
leoprint:  64%|######4   | 1544/2400 [34:09<46:30,  3.26s/it, lr: 5.0e-05 loss: 1.939e-01]
leoprint:  64%|######4   | 1544/2400 [34:13<46:30,  3.26s/it, lr: 5.0e-05 loss: 1.888e-01]
leoprint:  64%|######4   | 1544/2400 [34:13<46:30,  3.26s/it, lr: 5.0e-05 loss: 1.888e-01]
leoprint:  64%|######4   | 1545/2400 [34:13<47:53,  3.36s/it, lr: 5.0e-05 loss: 1.888e-01]
leoprint:  64%|######4   | 1545/2400 [34:13<47:53,  3.36s/it, lr: 5.0e-05 loss: 1.888e-01]
leoprint:  64%|######4   | 1545/2400 [34:16<47:53,  3.36s/it, lr: 5.0e-05 loss: 3.582e-01]
leoprint:  64%|######4   | 1545/2400 [34:16<47:53,  3.36s/it, lr: 5.0e-05 loss: 3.582e-01]
leoprint:  64%|######4   | 1546/2400 [34:16<48:23,  3.40s/it, lr: 5.0e-05 loss: 3.582e-01]
leoprint:  64%|######4   | 1546/2400 [34:16<48:23,  3.40s/it, lr: 5.0e-05 loss: 3.582e-01]
leoprint:  64%|######4   | 1546/2400 [34:20<48:23,  3.40s/it, lr: 5.0e-05 loss: 2.984e-01]
leoprint:  64%|######4   | 1546/2400 [34:20<48:23,  3.40s/it, lr: 5.0e-05 loss: 2.984e-01]
leoprint:  64%|######4   | 1547/2400 [34:20<48:44,  3.43s/it, lr: 5.0e-05 loss: 2.984e-01]
leoprint:  64%|######4   | 1547/2400 [34:20<48:44,  3.43s/it, lr: 5.0e-05 loss: 2.984e-01]
leoprint:  64%|######4   | 1547/2400 [34:23<48:44,  3.43s/it, lr: 5.0e-05 loss: 2.131e-01]
leoprint:  64%|######4   | 1547/2400 [34:23<48:44,  3.43s/it, lr: 5.0e-05 loss: 2.131e-01]
leoprint:  64%|######4   | 1548/2400 [34:23<48:58,  3.45s/it, lr: 5.0e-05 loss: 2.131e-01]
leoprint:  64%|######4   | 1548/2400 [34:23<48:58,  3.45s/it, lr: 5.0e-05 loss: 2.131e-01]
leoprint:  64%|######4   | 1548/2400 [34:27<48:58,  3.45s/it, lr: 5.0e-05 loss: 3.239e-01]
leoprint:  64%|######4   | 1548/2400 [34:27<48:58,  3.45s/it, lr: 5.0e-05 loss: 3.239e-01]
leoprint:  65%|######4   | 1549/2400 [34:27<49:08,  3.46s/it, lr: 5.0e-05 loss: 3.239e-01]
leoprint:  65%|######4   | 1549/2400 [34:27<49:08,  3.46s/it, lr: 5.0e-05 loss: 3.239e-01]
leoprint:  65%|######4   | 1549/2400 [34:31<49:08,  3.46s/it, lr: 5.0e-05 loss: 3.875e-01]
leoprint:  65%|######4   | 1549/2400 [34:31<49:08,  3.46s/it, lr: 5.0e-05 loss: 3.875e-01]
leoprint:  65%|######4   | 1550/2400 [34:34<49:04,  3.46s/it, lr: 5.0e-05 loss: 3.644e-01]
leoprint:  65%|######4   | 1550/2400 [34:34<49:04,  3.46s/it, lr: 5.0e-05 loss: 3.644e-01]
leoprint:  65%|######4   | 1551/2400 [34:34<37:54,  2.68s/it, lr: 5.0e-05 loss: 3.644e-01]
leoprint:  65%|######4   | 1551/2400 [34:34<37:54,  2.68s/it, lr: 5.0e-05 loss: 3.644e-01]
leoprint:  65%|######4   | 1551/2400 [34:38<37:54,  2.68s/it, lr: 5.0e-05 loss: 2.318e-01]
leoprint:  65%|######4   | 1551/2400 [34:38<37:54,  2.68s/it, lr: 5.0e-05 loss: 2.318e-01]
leoprint:  65%|######4   | 1552/2400 [34:38<40:43,  2.88s/it, lr: 5.0e-05 loss: 2.318e-01]
leoprint:  65%|######4   | 1552/2400 [34:38<40:43,  2.88s/it, lr: 5.0e-05 loss: 2.318e-01]
leoprint:  65%|######4   | 1552/2400 [34:41<40:43,  2.88s/it, lr: 5.0e-05 loss: 2.722e-01]
leoprint:  65%|######4   | 1552/2400 [34:41<40:43,  2.88s/it, lr: 5.0e-05 loss: 2.722e-01]
leoprint:  65%|######4   | 1553/2400 [34:41<42:56,  3.04s/it, lr: 5.0e-05 loss: 2.722e-01]
leoprint:  65%|######4   | 1553/2400 [34:41<42:56,  3.04s/it, lr: 5.0e-05 loss: 2.722e-01]
leoprint:  65%|######4   | 1553/2400 [34:45<42:56,  3.04s/it, lr: 5.0e-05 loss: 2.326e-01]
leoprint:  65%|######4   | 1553/2400 [34:45<42:56,  3.04s/it, lr: 5.0e-05 loss: 2.326e-01]
leoprint:  65%|######4   | 1554/2400 [34:45<45:03,  3.20s/it, lr: 5.0e-05 loss: 2.326e-01]
leoprint:  65%|######4   | 1554/2400 [34:45<45:03,  3.20s/it, lr: 5.0e-05 loss: 2.326e-01]
leoprint:  65%|######4   | 1554/2400 [34:48<45:03,  3.20s/it, lr: 5.0e-05 loss: 2.642e-01]
leoprint:  65%|######4   | 1554/2400 [34:48<45:03,  3.20s/it, lr: 5.0e-05 loss: 2.642e-01]
leoprint:  65%|######4   | 1555/2400 [34:48<46:39,  3.31s/it, lr: 5.0e-05 loss: 2.642e-01]
leoprint:  65%|######4   | 1555/2400 [34:48<46:39,  3.31s/it, lr: 5.0e-05 loss: 2.642e-01]
leoprint:  65%|######4   | 1555/2400 [34:52<46:39,  3.31s/it, lr: 5.0e-05 loss: 3.148e-01]
leoprint:  65%|######4   | 1555/2400 [34:52<46:39,  3.31s/it, lr: 5.0e-05 loss: 3.148e-01]
leoprint:  65%|######4   | 1556/2400 [34:52<47:52,  3.40s/it, lr: 5.0e-05 loss: 3.148e-01]
leoprint:  65%|######4   | 1556/2400 [34:52<47:52,  3.40s/it, lr: 5.0e-05 loss: 3.148e-01]
leoprint:  65%|######4   | 1556/2400 [34:55<47:52,  3.40s/it, lr: 5.0e-05 loss: 2.818e-01]
leoprint:  65%|######4   | 1556/2400 [34:55<47:52,  3.40s/it, lr: 5.0e-05 loss: 2.818e-01]
leoprint:  65%|######4   | 1557/2400 [34:55<48:12,  3.43s/it, lr: 5.0e-05 loss: 2.818e-01]
leoprint:  65%|######4   | 1557/2400 [34:55<48:12,  3.43s/it, lr: 5.0e-05 loss: 2.818e-01]
leoprint:  65%|######4   | 1557/2400 [34:59<48:12,  3.43s/it, lr: 5.0e-05 loss: 2.489e-01]
leoprint:  65%|######4   | 1557/2400 [34:59<48:12,  3.43s/it, lr: 5.0e-05 loss: 2.489e-01]
leoprint:  65%|######4   | 1558/2400 [34:59<48:53,  3.48s/it, lr: 5.0e-05 loss: 2.489e-01]
leoprint:  65%|######4   | 1558/2400 [34:59<48:53,  3.48s/it, lr: 5.0e-05 loss: 2.489e-01]
leoprint:  65%|######4   | 1558/2400 [35:03<48:53,  3.48s/it, lr: 5.0e-05 loss: 3.012e-01]
leoprint:  65%|######4   | 1558/2400 [35:03<48:53,  3.48s/it, lr: 5.0e-05 loss: 3.012e-01]
leoprint:  65%|######4   | 1559/2400 [35:03<48:52,  3.49s/it, lr: 5.0e-05 loss: 3.012e-01]
leoprint:  65%|######4   | 1559/2400 [35:03<48:52,  3.49s/it, lr: 5.0e-05 loss: 3.012e-01]
leoprint:  65%|######4   | 1559/2400 [35:06<48:52,  3.49s/it, lr: 5.0e-05 loss: 3.315e-01]
leoprint:  65%|######4   | 1559/2400 [35:06<48:52,  3.49s/it, lr: 5.0e-05 loss: 3.315e-01]
leoprint:  65%|######5   | 1560/2400 [35:10<48:48,  3.49s/it, lr: 5.0e-05 loss: 3.524e-01]
leoprint:  65%|######5   | 1560/2400 [35:10<48:48,  3.49s/it, lr: 5.0e-05 loss: 3.524e-01]
leoprint:  65%|######5   | 1561/2400 [35:10<38:13,  2.73s/it, lr: 5.0e-05 loss: 3.524e-01]
leoprint:  65%|######5   | 1561/2400 [35:10<38:13,  2.73s/it, lr: 5.0e-05 loss: 3.524e-01]
leoprint:  65%|######5   | 1561/2400 [35:13<38:13,  2.73s/it, lr: 5.0e-05 loss: 4.037e-01]
leoprint:  65%|######5   | 1561/2400 [35:13<38:13,  2.73s/it, lr: 5.0e-05 loss: 4.037e-01]
leoprint:  65%|######5   | 1562/2400 [35:13<40:48,  2.92s/it, lr: 5.0e-05 loss: 4.037e-01]
leoprint:  65%|######5   | 1562/2400 [35:13<40:48,  2.92s/it, lr: 5.0e-05 loss: 4.037e-01]
leoprint:  65%|######5   | 1562/2400 [35:17<40:48,  2.92s/it, lr: 5.0e-05 loss: 3.086e-01]
leoprint:  65%|######5   | 1562/2400 [35:17<40:48,  2.92s/it, lr: 5.0e-05 loss: 3.086e-01]
leoprint:  65%|######5   | 1563/2400 [35:17<42:51,  3.07s/it, lr: 5.0e-05 loss: 3.086e-01]
leoprint:  65%|######5   | 1563/2400 [35:17<42:51,  3.07s/it, lr: 5.0e-05 loss: 3.086e-01]
leoprint:  65%|######5   | 1563/2400 [35:20<42:51,  3.07s/it, lr: 5.0e-05 loss: 2.458e-01]
leoprint:  65%|######5   | 1563/2400 [35:20<42:51,  3.07s/it, lr: 5.0e-05 loss: 2.458e-01]
leoprint:  65%|######5   | 1564/2400 [35:20<44:50,  3.22s/it, lr: 5.0e-05 loss: 2.458e-01]
leoprint:  65%|######5   | 1564/2400 [35:20<44:50,  3.22s/it, lr: 5.0e-05 loss: 2.458e-01]
leoprint:  65%|######5   | 1564/2400 [35:24<44:50,  3.22s/it, lr: 5.0e-05 loss: 3.243e-01]
leoprint:  65%|######5   | 1564/2400 [35:24<44:50,  3.22s/it, lr: 5.0e-05 loss: 3.243e-01]
leoprint:  65%|######5   | 1565/2400 [35:24<45:52,  3.30s/it, lr: 5.0e-05 loss: 3.243e-01]
leoprint:  65%|######5   | 1565/2400 [35:24<45:52,  3.30s/it, lr: 5.0e-05 loss: 3.243e-01]
leoprint:  65%|######5   | 1565/2400 [35:27<45:52,  3.30s/it, lr: 5.0e-05 loss: 2.212e-01]
leoprint:  65%|######5   | 1565/2400 [35:27<45:52,  3.30s/it, lr: 5.0e-05 loss: 2.212e-01]
leoprint:  65%|######5   | 1566/2400 [35:28<47:05,  3.39s/it, lr: 5.0e-05 loss: 2.212e-01]
leoprint:  65%|######5   | 1566/2400 [35:28<47:05,  3.39s/it, lr: 5.0e-05 loss: 2.212e-01]
leoprint:  65%|######5   | 1566/2400 [35:31<47:05,  3.39s/it, lr: 5.0e-05 loss: 2.584e-01]
leoprint:  65%|######5   | 1566/2400 [35:31<47:05,  3.39s/it, lr: 5.0e-05 loss: 2.584e-01]
leoprint:  65%|######5   | 1567/2400 [35:31<47:45,  3.44s/it, lr: 5.0e-05 loss: 2.584e-01]
leoprint:  65%|######5   | 1567/2400 [35:31<47:45,  3.44s/it, lr: 5.0e-05 loss: 2.584e-01]
leoprint:  65%|######5   | 1567/2400 [35:35<47:45,  3.44s/it, lr: 5.0e-05 loss: 3.323e-01]
leoprint:  65%|######5   | 1567/2400 [35:35<47:45,  3.44s/it, lr: 5.0e-05 loss: 3.323e-01]
leoprint:  65%|######5   | 1568/2400 [35:35<47:57,  3.46s/it, lr: 5.0e-05 loss: 3.323e-01]
leoprint:  65%|######5   | 1568/2400 [35:35<47:57,  3.46s/it, lr: 5.0e-05 loss: 3.323e-01]
leoprint:  65%|######5   | 1568/2400 [35:38<47:57,  3.46s/it, lr: 5.0e-05 loss: 4.000e-01]
leoprint:  65%|######5   | 1568/2400 [35:38<47:57,  3.46s/it, lr: 5.0e-05 loss: 4.000e-01]
leoprint:  65%|######5   | 1569/2400 [35:38<48:05,  3.47s/it, lr: 5.0e-05 loss: 4.000e-01]
leoprint:  65%|######5   | 1569/2400 [35:38<48:05,  3.47s/it, lr: 5.0e-05 loss: 4.000e-01]
leoprint:  65%|######5   | 1569/2400 [35:42<48:05,  3.47s/it, lr: 5.0e-05 loss: 2.388e-01]
leoprint:  65%|######5   | 1569/2400 [35:42<48:05,  3.47s/it, lr: 5.0e-05 loss: 2.388e-01]
leoprint:  65%|######5   | 1570/2400 [35:45<48:01,  3.47s/it, lr: 5.0e-05 loss: 2.738e-01]
leoprint:  65%|######5   | 1570/2400 [35:45<48:01,  3.47s/it, lr: 5.0e-05 loss: 2.738e-01]
leoprint:  65%|######5   | 1571/2400 [35:45<37:05,  2.68s/it, lr: 5.0e-05 loss: 2.738e-01]
leoprint:  65%|######5   | 1571/2400 [35:45<37:05,  2.68s/it, lr: 5.0e-05 loss: 2.738e-01]
leoprint:  65%|######5   | 1571/2400 [35:49<37:05,  2.68s/it, lr: 5.0e-05 loss: 2.827e-01]
leoprint:  65%|######5   | 1571/2400 [35:49<37:05,  2.68s/it, lr: 5.0e-05 loss: 2.827e-01]
leoprint:  66%|######5   | 1572/2400 [35:49<39:50,  2.89s/it, lr: 5.0e-05 loss: 2.827e-01]
leoprint:  66%|######5   | 1572/2400 [35:49<39:50,  2.89s/it, lr: 5.0e-05 loss: 2.827e-01]
leoprint:  66%|######5   | 1572/2400 [35:53<39:50,  2.89s/it, lr: 5.0e-05 loss: 2.493e-01]
leoprint:  66%|######5   | 1572/2400 [35:53<39:50,  2.89s/it, lr: 5.0e-05 loss: 2.493e-01]
leoprint:  66%|######5   | 1573/2400 [35:53<42:50,  3.11s/it, lr: 5.0e-05 loss: 2.493e-01]
leoprint:  66%|######5   | 1573/2400 [35:53<42:50,  3.11s/it, lr: 5.0e-05 loss: 2.493e-01]
leoprint:  66%|######5   | 1573/2400 [35:56<42:50,  3.11s/it, lr: 5.0e-05 loss: 2.417e-01]
leoprint:  66%|######5   | 1573/2400 [35:56<42:50,  3.11s/it, lr: 5.0e-05 loss: 2.417e-01]
leoprint:  66%|######5   | 1574/2400 [35:56<44:16,  3.22s/it, lr: 5.0e-05 loss: 2.417e-01]
leoprint:  66%|######5   | 1574/2400 [35:56<44:16,  3.22s/it, lr: 5.0e-05 loss: 2.417e-01]
leoprint:  66%|######5   | 1574/2400 [36:00<44:16,  3.22s/it, lr: 5.0e-05 loss: 2.639e-01]
leoprint:  66%|######5   | 1574/2400 [36:00<44:16,  3.22s/it, lr: 5.0e-05 loss: 2.639e-01]
leoprint:  66%|######5   | 1575/2400 [36:00<45:44,  3.33s/it, lr: 5.0e-05 loss: 2.639e-01]
leoprint:  66%|######5   | 1575/2400 [36:00<45:44,  3.33s/it, lr: 5.0e-05 loss: 2.639e-01]
leoprint:  66%|######5   | 1575/2400 [36:03<45:44,  3.33s/it, lr: 5.0e-05 loss: 3.020e-01]
leoprint:  66%|######5   | 1575/2400 [36:03<45:44,  3.33s/it, lr: 5.0e-05 loss: 3.020e-01]
leoprint:  66%|######5   | 1576/2400 [36:03<46:50,  3.41s/it, lr: 5.0e-05 loss: 3.020e-01]
leoprint:  66%|######5   | 1576/2400 [36:03<46:50,  3.41s/it, lr: 5.0e-05 loss: 3.020e-01]
leoprint:  66%|######5   | 1576/2400 [36:07<46:50,  3.41s/it, lr: 5.0e-05 loss: 3.217e-01]
leoprint:  66%|######5   | 1576/2400 [36:07<46:50,  3.41s/it, lr: 5.0e-05 loss: 3.217e-01]
leoprint:  66%|######5   | 1577/2400 [36:07<47:37,  3.47s/it, lr: 5.0e-05 loss: 3.217e-01]
leoprint:  66%|######5   | 1577/2400 [36:07<47:37,  3.47s/it, lr: 5.0e-05 loss: 3.217e-01]
leoprint:  66%|######5   | 1577/2400 [36:10<47:37,  3.47s/it, lr: 5.0e-05 loss: 2.940e-01]
leoprint:  66%|######5   | 1577/2400 [36:10<47:37,  3.47s/it, lr: 5.0e-05 loss: 2.940e-01]
leoprint:  66%|######5   | 1578/2400 [36:10<47:40,  3.48s/it, lr: 5.0e-05 loss: 2.940e-01]
leoprint:  66%|######5   | 1578/2400 [36:10<47:40,  3.48s/it, lr: 5.0e-05 loss: 2.940e-01]
leoprint:  66%|######5   | 1578/2400 [36:14<47:40,  3.48s/it, lr: 5.0e-05 loss: 3.112e-01]
leoprint:  66%|######5   | 1578/2400 [36:14<47:40,  3.48s/it, lr: 5.0e-05 loss: 3.112e-01]
leoprint:  66%|######5   | 1579/2400 [36:14<48:15,  3.53s/it, lr: 5.0e-05 loss: 3.112e-01]
leoprint:  66%|######5   | 1579/2400 [36:14<48:15,  3.53s/it, lr: 5.0e-05 loss: 3.112e-01]
leoprint:  66%|######5   | 1579/2400 [36:18<48:15,  3.53s/it, lr: 5.0e-05 loss: 4.260e-01]
leoprint:  66%|######5   | 1579/2400 [36:18<48:15,  3.53s/it, lr: 5.0e-05 loss: 4.260e-01]
leoprint:  66%|######5   | 1580/2400 [36:21<48:11,  3.53s/it, lr: 5.0e-05 loss: 3.250e-01]
leoprint:  66%|######5   | 1580/2400 [36:21<48:11,  3.53s/it, lr: 5.0e-05 loss: 3.250e-01]
leoprint:  66%|######5   | 1581/2400 [36:21<37:03,  2.71s/it, lr: 5.0e-05 loss: 3.250e-01]
leoprint:  66%|######5   | 1581/2400 [36:21<37:03,  2.71s/it, lr: 5.0e-05 loss: 3.250e-01]
leoprint:  66%|######5   | 1581/2400 [36:25<37:03,  2.71s/it, lr: 5.0e-05 loss: 2.734e-01]
leoprint:  66%|######5   | 1581/2400 [36:25<37:03,  2.71s/it, lr: 5.0e-05 loss: 2.734e-01]
leoprint:  66%|######5   | 1582/2400 [36:25<39:39,  2.91s/it, lr: 5.0e-05 loss: 2.734e-01]
leoprint:  66%|######5   | 1582/2400 [36:25<39:39,  2.91s/it, lr: 5.0e-05 loss: 2.734e-01]
leoprint:  66%|######5   | 1582/2400 [36:28<39:39,  2.91s/it, lr: 5.0e-05 loss: 2.361e-01]
leoprint:  66%|######5   | 1582/2400 [36:28<39:39,  2.91s/it, lr: 5.0e-05 loss: 2.361e-01]
leoprint:  66%|######5   | 1583/2400 [36:28<41:44,  3.07s/it, lr: 5.0e-05 loss: 2.361e-01]
leoprint:  66%|######5   | 1583/2400 [36:28<41:44,  3.07s/it, lr: 5.0e-05 loss: 2.361e-01]
leoprint:  66%|######5   | 1583/2400 [36:32<41:44,  3.07s/it, lr: 5.0e-05 loss: 3.843e-01]
leoprint:  66%|######5   | 1583/2400 [36:32<41:44,  3.07s/it, lr: 5.0e-05 loss: 3.843e-01]
leoprint:  66%|######6   | 1584/2400 [36:32<43:55,  3.23s/it, lr: 5.0e-05 loss: 3.843e-01]
leoprint:  66%|######6   | 1584/2400 [36:32<43:55,  3.23s/it, lr: 5.0e-05 loss: 3.843e-01]
leoprint:  66%|######6   | 1584/2400 [36:35<43:55,  3.23s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  66%|######6   | 1584/2400 [36:35<43:55,  3.23s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  66%|######6   | 1585/2400 [36:35<45:19,  3.34s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  66%|######6   | 1585/2400 [36:35<45:19,  3.34s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  66%|######6   | 1585/2400 [36:39<45:19,  3.34s/it, lr: 5.0e-05 loss: 3.118e-01]
leoprint:  66%|######6   | 1585/2400 [36:39<45:19,  3.34s/it, lr: 5.0e-05 loss: 3.118e-01]
leoprint:  66%|######6   | 1586/2400 [36:39<45:54,  3.38s/it, lr: 5.0e-05 loss: 3.118e-01]
leoprint:  66%|######6   | 1586/2400 [36:39<45:54,  3.38s/it, lr: 5.0e-05 loss: 3.118e-01]
leoprint:  66%|######6   | 1586/2400 [36:42<45:54,  3.38s/it, lr: 5.0e-05 loss: 3.143e-01]
leoprint:  66%|######6   | 1586/2400 [36:42<45:54,  3.38s/it, lr: 5.0e-05 loss: 3.143e-01]
leoprint:  66%|######6   | 1587/2400 [36:42<46:19,  3.42s/it, lr: 5.0e-05 loss: 3.143e-01]
leoprint:  66%|######6   | 1587/2400 [36:42<46:19,  3.42s/it, lr: 5.0e-05 loss: 3.143e-01]
leoprint:  66%|######6   | 1587/2400 [36:46<46:19,  3.42s/it, lr: 5.0e-05 loss: 2.785e-01]
leoprint:  66%|######6   | 1587/2400 [36:46<46:19,  3.42s/it, lr: 5.0e-05 loss: 2.785e-01]
leoprint:  66%|######6   | 1588/2400 [36:46<46:36,  3.44s/it, lr: 5.0e-05 loss: 2.785e-01]
leoprint:  66%|######6   | 1588/2400 [36:46<46:36,  3.44s/it, lr: 5.0e-05 loss: 2.785e-01]
leoprint:  66%|######6   | 1588/2400 [36:49<46:36,  3.44s/it, lr: 5.0e-05 loss: 2.465e-01]
leoprint:  66%|######6   | 1588/2400 [36:49<46:36,  3.44s/it, lr: 5.0e-05 loss: 2.465e-01]
leoprint:  66%|######6   | 1589/2400 [36:49<46:46,  3.46s/it, lr: 5.0e-05 loss: 2.465e-01]
leoprint:  66%|######6   | 1589/2400 [36:49<46:46,  3.46s/it, lr: 5.0e-05 loss: 2.465e-01]
leoprint:  66%|######6   | 1589/2400 [36:53<46:46,  3.46s/it, lr: 5.0e-05 loss: 2.089e-01]
leoprint:  66%|######6   | 1589/2400 [36:53<46:46,  3.46s/it, lr: 5.0e-05 loss: 2.089e-01]
leoprint:  66%|######6   | 1590/2400 [36:56<46:43,  3.46s/it, lr: 5.0e-05 loss: 2.790e-01]
leoprint:  66%|######6   | 1590/2400 [36:56<46:43,  3.46s/it, lr: 5.0e-05 loss: 2.790e-01]
leoprint:  66%|######6   | 1591/2400 [36:56<36:06,  2.68s/it, lr: 5.0e-05 loss: 2.790e-01]
leoprint:  66%|######6   | 1591/2400 [36:56<36:06,  2.68s/it, lr: 5.0e-05 loss: 2.790e-01]
leoprint:  66%|######6   | 1591/2400 [37:00<36:06,  2.68s/it, lr: 5.0e-05 loss: 2.821e-01]
leoprint:  66%|######6   | 1591/2400 [37:00<36:06,  2.68s/it, lr: 5.0e-05 loss: 2.821e-01]
leoprint:  66%|######6   | 1592/2400 [37:00<39:10,  2.91s/it, lr: 5.0e-05 loss: 2.821e-01]
leoprint:  66%|######6   | 1592/2400 [37:00<39:10,  2.91s/it, lr: 5.0e-05 loss: 2.821e-01]
leoprint:  66%|######6   | 1592/2400 [37:04<39:10,  2.91s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  66%|######6   | 1592/2400 [37:04<39:10,  2.91s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  66%|######6   | 1593/2400 [37:04<41:36,  3.09s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  66%|######6   | 1593/2400 [37:04<41:36,  3.09s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  66%|######6   | 1593/2400 [37:07<41:36,  3.09s/it, lr: 5.0e-05 loss: 3.251e-01]
leoprint:  66%|######6   | 1593/2400 [37:07<41:36,  3.09s/it, lr: 5.0e-05 loss: 3.251e-01]
leoprint:  66%|######6   | 1594/2400 [37:07<43:03,  3.20s/it, lr: 5.0e-05 loss: 3.251e-01]
leoprint:  66%|######6   | 1594/2400 [37:07<43:03,  3.20s/it, lr: 5.0e-05 loss: 3.251e-01]
leoprint:  66%|######6   | 1594/2400 [37:11<43:03,  3.20s/it, lr: 5.0e-05 loss: 2.537e-01]
leoprint:  66%|######6   | 1594/2400 [37:11<43:03,  3.20s/it, lr: 5.0e-05 loss: 2.537e-01]
leoprint:  66%|######6   | 1595/2400 [37:11<44:07,  3.29s/it, lr: 5.0e-05 loss: 2.537e-01]
leoprint:  66%|######6   | 1595/2400 [37:11<44:07,  3.29s/it, lr: 5.0e-05 loss: 2.537e-01]
leoprint:  66%|######6   | 1595/2400 [37:15<44:07,  3.29s/it, lr: 5.0e-05 loss: 3.607e-01]
leoprint:  66%|######6   | 1595/2400 [37:15<44:07,  3.29s/it, lr: 5.0e-05 loss: 3.607e-01]
leoprint:  66%|######6   | 1596/2400 [37:15<45:48,  3.42s/it, lr: 5.0e-05 loss: 3.607e-01]
leoprint:  66%|######6   | 1596/2400 [37:15<45:48,  3.42s/it, lr: 5.0e-05 loss: 3.607e-01]
leoprint:  66%|######6   | 1596/2400 [37:18<45:48,  3.42s/it, lr: 5.0e-05 loss: 1.966e-01]
leoprint:  66%|######6   | 1596/2400 [37:18<45:48,  3.42s/it, lr: 5.0e-05 loss: 1.966e-01]
leoprint:  67%|######6   | 1597/2400 [37:18<46:30,  3.48s/it, lr: 5.0e-05 loss: 1.966e-01]
leoprint:  67%|######6   | 1597/2400 [37:18<46:30,  3.48s/it, lr: 5.0e-05 loss: 1.966e-01]
leoprint:  67%|######6   | 1597/2400 [37:22<46:30,  3.48s/it, lr: 5.0e-05 loss: 3.004e-01]
leoprint:  67%|######6   | 1597/2400 [37:22<46:30,  3.48s/it, lr: 5.0e-05 loss: 3.004e-01]
leoprint:  67%|######6   | 1598/2400 [37:22<46:32,  3.48s/it, lr: 5.0e-05 loss: 3.004e-01]
leoprint:  67%|######6   | 1598/2400 [37:22<46:32,  3.48s/it, lr: 5.0e-05 loss: 3.004e-01]
leoprint:  67%|######6   | 1598/2400 [37:25<46:32,  3.48s/it, lr: 5.0e-05 loss: 2.167e-01]
leoprint:  67%|######6   | 1598/2400 [37:25<46:32,  3.48s/it, lr: 5.0e-05 loss: 2.167e-01]
leoprint:  67%|######6   | 1599/2400 [37:25<47:02,  3.52s/it, lr: 5.0e-05 loss: 2.167e-01]
leoprint:  67%|######6   | 1599/2400 [37:25<47:02,  3.52s/it, lr: 5.0e-05 loss: 2.167e-01]
leoprint:  67%|######6   | 1599/2400 [37:29<47:02,  3.52s/it, lr: 5.0e-05 loss: 3.078e-01]
leoprint:  67%|######6   | 1599/2400 [37:29<47:02,  3.52s/it, lr: 5.0e-05 loss: 3.078e-01]
+
+
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
+
+
Generating Images:  20%|##        | 1/5 [00:14<00:57, 14.39s/it]
Generating Images:  20%|##        | 1/5 [00:14<00:57, 14.39s/it]
+
+
Generating Images:  40%|####      | 2/5 [00:28<00:43, 14.39s/it]
Generating Images:  40%|####      | 2/5 [00:28<00:43, 14.39s/it]
+
+
Generating Images:  60%|######    | 3/5 [00:43<00:28, 14.39s/it]
Generating Images:  60%|######    | 3/5 [00:43<00:28, 14.39s/it]
+
+
Generating Images:  80%|########  | 4/5 [00:57<00:14, 14.39s/it]
Generating Images:  80%|########  | 4/5 [00:57<00:14, 14.39s/it]
+
+
Generating Images: 100%|##########| 5/5 [01:11<00:00, 14.39s/it]
Generating Images: 100%|##########| 5/5 [01:11<00:00, 14.39s/it]
+
+
                                                                
                                                                
+Saving at step 1600
+Saved checkpoint to /app/ai-toolkit/output/leoprint/leoprint_000001600.safetensors
+Saved optimizer to /app/ai-toolkit/output/leoprint/optimizer.pt
+
leoprint:  67%|######6   | 1600/2400 [37:33<46:59,  3.52s/it, lr: 5.0e-05 loss: 3.926e-01]
leoprint:  67%|######6   | 1600/2400 [37:33<46:59,  3.52s/it, lr: 5.0e-05 loss: 3.926e-01]
leoprint:  67%|######6   | 1601/2400 [37:33<36:40,  2.75s/it, lr: 5.0e-05 loss: 3.926e-01]
leoprint:  67%|######6   | 1601/2400 [37:33<36:40,  2.75s/it, lr: 5.0e-05 loss: 3.926e-01]
leoprint:  67%|######6   | 1601/2400 [37:36<36:40,  2.75s/it, lr: 5.0e-05 loss: 3.265e-01]
leoprint:  67%|######6   | 1601/2400 [37:36<36:40,  2.75s/it, lr: 5.0e-05 loss: 3.265e-01]
leoprint:  67%|######6   | 1602/2400 [37:36<38:58,  2.93s/it, lr: 5.0e-05 loss: 3.265e-01]
leoprint:  67%|######6   | 1602/2400 [37:36<38:58,  2.93s/it, lr: 5.0e-05 loss: 3.265e-01]
leoprint:  67%|######6   | 1602/2400 [37:40<38:58,  2.93s/it, lr: 5.0e-05 loss: 3.007e-01]
leoprint:  67%|######6   | 1602/2400 [37:40<38:58,  2.93s/it, lr: 5.0e-05 loss: 3.007e-01]
leoprint:  67%|######6   | 1603/2400 [37:40<40:50,  3.07s/it, lr: 5.0e-05 loss: 3.007e-01]
leoprint:  67%|######6   | 1603/2400 [37:40<40:50,  3.07s/it, lr: 5.0e-05 loss: 3.007e-01]
leoprint:  67%|######6   | 1603/2400 [37:43<40:50,  3.07s/it, lr: 5.0e-05 loss: 2.099e-01]
leoprint:  67%|######6   | 1603/2400 [37:43<40:50,  3.07s/it, lr: 5.0e-05 loss: 2.099e-01]
leoprint:  67%|######6   | 1604/2400 [37:43<42:17,  3.19s/it, lr: 5.0e-05 loss: 2.099e-01]
leoprint:  67%|######6   | 1604/2400 [37:43<42:17,  3.19s/it, lr: 5.0e-05 loss: 2.099e-01]
leoprint:  67%|######6   | 1604/2400 [37:47<42:17,  3.19s/it, lr: 5.0e-05 loss: 3.258e-01]
leoprint:  67%|######6   | 1604/2400 [37:47<42:17,  3.19s/it, lr: 5.0e-05 loss: 3.258e-01]
leoprint:  67%|######6   | 1605/2400 [37:47<43:47,  3.31s/it, lr: 5.0e-05 loss: 3.258e-01]
leoprint:  67%|######6   | 1605/2400 [37:47<43:47,  3.31s/it, lr: 5.0e-05 loss: 3.258e-01]
leoprint:  67%|######6   | 1605/2400 [37:50<43:47,  3.31s/it, lr: 5.0e-05 loss: 3.553e-01]
leoprint:  67%|######6   | 1605/2400 [37:50<43:47,  3.31s/it, lr: 5.0e-05 loss: 3.553e-01]
leoprint:  67%|######6   | 1606/2400 [37:50<45:09,  3.41s/it, lr: 5.0e-05 loss: 3.553e-01]
leoprint:  67%|######6   | 1606/2400 [37:50<45:09,  3.41s/it, lr: 5.0e-05 loss: 3.553e-01]
leoprint:  67%|######6   | 1606/2400 [37:54<45:09,  3.41s/it, lr: 5.0e-05 loss: 3.117e-01]
leoprint:  67%|######6   | 1606/2400 [37:54<45:09,  3.41s/it, lr: 5.0e-05 loss: 3.117e-01]
leoprint:  67%|######6   | 1607/2400 [37:54<45:24,  3.44s/it, lr: 5.0e-05 loss: 3.117e-01]
leoprint:  67%|######6   | 1607/2400 [37:54<45:24,  3.44s/it, lr: 5.0e-05 loss: 3.117e-01]
leoprint:  67%|######6   | 1607/2400 [37:57<45:24,  3.44s/it, lr: 5.0e-05 loss: 2.609e-01]
leoprint:  67%|######6   | 1607/2400 [37:57<45:24,  3.44s/it, lr: 5.0e-05 loss: 2.609e-01]
leoprint:  67%|######7   | 1608/2400 [37:57<45:35,  3.45s/it, lr: 5.0e-05 loss: 2.609e-01]
leoprint:  67%|######7   | 1608/2400 [37:57<45:35,  3.45s/it, lr: 5.0e-05 loss: 2.609e-01]
leoprint:  67%|######7   | 1608/2400 [38:01<45:35,  3.45s/it, lr: 5.0e-05 loss: 3.585e-01]
leoprint:  67%|######7   | 1608/2400 [38:01<45:35,  3.45s/it, lr: 5.0e-05 loss: 3.585e-01]
leoprint:  67%|######7   | 1609/2400 [38:01<45:43,  3.47s/it, lr: 5.0e-05 loss: 3.585e-01]
leoprint:  67%|######7   | 1609/2400 [38:01<45:43,  3.47s/it, lr: 5.0e-05 loss: 3.585e-01]
leoprint:  67%|######7   | 1609/2400 [38:05<45:43,  3.47s/it, lr: 5.0e-05 loss: 2.716e-01]
leoprint:  67%|######7   | 1609/2400 [38:05<45:43,  3.47s/it, lr: 5.0e-05 loss: 2.716e-01]
leoprint:  67%|######7   | 1610/2400 [38:09<45:39,  3.47s/it, lr: 5.0e-05 loss: 3.088e-01]
leoprint:  67%|######7   | 1610/2400 [38:09<45:39,  3.47s/it, lr: 5.0e-05 loss: 3.088e-01]
leoprint:  67%|######7   | 1611/2400 [38:09<35:16,  2.68s/it, lr: 5.0e-05 loss: 3.088e-01]
leoprint:  67%|######7   | 1611/2400 [38:09<35:16,  2.68s/it, lr: 5.0e-05 loss: 3.088e-01]
leoprint:  67%|######7   | 1611/2400 [38:13<35:16,  2.68s/it, lr: 5.0e-05 loss: 2.840e-01]
leoprint:  67%|######7   | 1611/2400 [38:13<35:16,  2.68s/it, lr: 5.0e-05 loss: 2.840e-01]
leoprint:  67%|######7   | 1612/2400 [38:13<38:44,  2.95s/it, lr: 5.0e-05 loss: 2.840e-01]
leoprint:  67%|######7   | 1612/2400 [38:13<38:44,  2.95s/it, lr: 5.0e-05 loss: 2.840e-01]
leoprint:  67%|######7   | 1612/2400 [38:16<38:44,  2.95s/it, lr: 5.0e-05 loss: 3.352e-01]
leoprint:  67%|######7   | 1612/2400 [38:16<38:44,  2.95s/it, lr: 5.0e-05 loss: 3.352e-01]
leoprint:  67%|######7   | 1613/2400 [38:16<40:33,  3.09s/it, lr: 5.0e-05 loss: 3.352e-01]
leoprint:  67%|######7   | 1613/2400 [38:16<40:33,  3.09s/it, lr: 5.0e-05 loss: 3.352e-01]
leoprint:  67%|######7   | 1613/2400 [38:20<40:33,  3.09s/it, lr: 5.0e-05 loss: 2.315e-01]
leoprint:  67%|######7   | 1613/2400 [38:20<40:33,  3.09s/it, lr: 5.0e-05 loss: 2.315e-01]
leoprint:  67%|######7   | 1614/2400 [38:20<41:56,  3.20s/it, lr: 5.0e-05 loss: 2.315e-01]
leoprint:  67%|######7   | 1614/2400 [38:20<41:56,  3.20s/it, lr: 5.0e-05 loss: 2.315e-01]
leoprint:  67%|######7   | 1614/2400 [38:23<41:56,  3.20s/it, lr: 5.0e-05 loss: 2.697e-01]
leoprint:  67%|######7   | 1614/2400 [38:23<41:56,  3.20s/it, lr: 5.0e-05 loss: 2.697e-01]
leoprint:  67%|######7   | 1615/2400 [38:23<43:22,  3.32s/it, lr: 5.0e-05 loss: 2.697e-01]
leoprint:  67%|######7   | 1615/2400 [38:23<43:22,  3.32s/it, lr: 5.0e-05 loss: 2.697e-01]
leoprint:  67%|######7   | 1615/2400 [38:27<43:22,  3.32s/it, lr: 5.0e-05 loss: 3.739e-01]
leoprint:  67%|######7   | 1615/2400 [38:27<43:22,  3.32s/it, lr: 5.0e-05 loss: 3.739e-01]
leoprint:  67%|######7   | 1616/2400 [38:27<44:01,  3.37s/it, lr: 5.0e-05 loss: 3.739e-01]
leoprint:  67%|######7   | 1616/2400 [38:27<44:01,  3.37s/it, lr: 5.0e-05 loss: 3.739e-01]
leoprint:  67%|######7   | 1616/2400 [38:30<44:01,  3.37s/it, lr: 5.0e-05 loss: 3.086e-01]
leoprint:  67%|######7   | 1616/2400 [38:30<44:01,  3.37s/it, lr: 5.0e-05 loss: 3.086e-01]
leoprint:  67%|######7   | 1617/2400 [38:30<44:54,  3.44s/it, lr: 5.0e-05 loss: 3.086e-01]
leoprint:  67%|######7   | 1617/2400 [38:30<44:54,  3.44s/it, lr: 5.0e-05 loss: 3.086e-01]
leoprint:  67%|######7   | 1617/2400 [38:34<44:54,  3.44s/it, lr: 5.0e-05 loss: 3.863e-01]
leoprint:  67%|######7   | 1617/2400 [38:34<44:54,  3.44s/it, lr: 5.0e-05 loss: 3.863e-01]
leoprint:  67%|######7   | 1618/2400 [38:34<45:59,  3.53s/it, lr: 5.0e-05 loss: 3.863e-01]
leoprint:  67%|######7   | 1618/2400 [38:34<45:59,  3.53s/it, lr: 5.0e-05 loss: 3.863e-01]
leoprint:  67%|######7   | 1618/2400 [38:38<45:59,  3.53s/it, lr: 5.0e-05 loss: 3.526e-01]
leoprint:  67%|######7   | 1618/2400 [38:38<45:59,  3.53s/it, lr: 5.0e-05 loss: 3.526e-01]
leoprint:  67%|######7   | 1619/2400 [38:38<45:50,  3.52s/it, lr: 5.0e-05 loss: 3.526e-01]
leoprint:  67%|######7   | 1619/2400 [38:38<45:50,  3.52s/it, lr: 5.0e-05 loss: 3.526e-01]
leoprint:  67%|######7   | 1619/2400 [38:41<45:50,  3.52s/it, lr: 5.0e-05 loss: 2.866e-01]
leoprint:  67%|######7   | 1619/2400 [38:41<45:50,  3.52s/it, lr: 5.0e-05 loss: 2.866e-01]
leoprint:  68%|######7   | 1620/2400 [38:45<45:47,  3.52s/it, lr: 5.0e-05 loss: 2.254e-01]
leoprint:  68%|######7   | 1620/2400 [38:45<45:47,  3.52s/it, lr: 5.0e-05 loss: 2.254e-01]
leoprint:  68%|######7   | 1621/2400 [38:45<35:13,  2.71s/it, lr: 5.0e-05 loss: 2.254e-01]
leoprint:  68%|######7   | 1621/2400 [38:45<35:13,  2.71s/it, lr: 5.0e-05 loss: 2.254e-01]
leoprint:  68%|######7   | 1621/2400 [38:48<35:13,  2.71s/it, lr: 5.0e-05 loss: 1.948e-01]
leoprint:  68%|######7   | 1621/2400 [38:48<35:13,  2.71s/it, lr: 5.0e-05 loss: 1.948e-01]
leoprint:  68%|######7   | 1622/2400 [38:48<38:05,  2.94s/it, lr: 5.0e-05 loss: 1.948e-01]
leoprint:  68%|######7   | 1622/2400 [38:48<38:05,  2.94s/it, lr: 5.0e-05 loss: 1.948e-01]
leoprint:  68%|######7   | 1622/2400 [38:52<38:05,  2.94s/it, lr: 5.0e-05 loss: 2.207e-01]
leoprint:  68%|######7   | 1622/2400 [38:52<38:05,  2.94s/it, lr: 5.0e-05 loss: 2.207e-01]
leoprint:  68%|######7   | 1623/2400 [38:52<40:10,  3.10s/it, lr: 5.0e-05 loss: 2.207e-01]
leoprint:  68%|######7   | 1623/2400 [38:52<40:10,  3.10s/it, lr: 5.0e-05 loss: 2.207e-01]
leoprint:  68%|######7   | 1623/2400 [38:55<40:10,  3.10s/it, lr: 5.0e-05 loss: 3.287e-01]
leoprint:  68%|######7   | 1623/2400 [38:55<40:10,  3.10s/it, lr: 5.0e-05 loss: 3.287e-01]
leoprint:  68%|######7   | 1624/2400 [38:55<41:32,  3.21s/it, lr: 5.0e-05 loss: 3.287e-01]
leoprint:  68%|######7   | 1624/2400 [38:55<41:32,  3.21s/it, lr: 5.0e-05 loss: 3.287e-01]
leoprint:  68%|######7   | 1624/2400 [38:59<41:32,  3.21s/it, lr: 5.0e-05 loss: 3.984e-01]
leoprint:  68%|######7   | 1624/2400 [38:59<41:32,  3.21s/it, lr: 5.0e-05 loss: 3.984e-01]
leoprint:  68%|######7   | 1625/2400 [38:59<42:31,  3.29s/it, lr: 5.0e-05 loss: 3.984e-01]
leoprint:  68%|######7   | 1625/2400 [38:59<42:31,  3.29s/it, lr: 5.0e-05 loss: 3.984e-01]
leoprint:  68%|######7   | 1625/2400 [39:02<42:31,  3.29s/it, lr: 5.0e-05 loss: 2.871e-01]
leoprint:  68%|######7   | 1625/2400 [39:02<42:31,  3.29s/it, lr: 5.0e-05 loss: 2.871e-01]
leoprint:  68%|######7   | 1626/2400 [39:02<43:39,  3.38s/it, lr: 5.0e-05 loss: 2.871e-01]
leoprint:  68%|######7   | 1626/2400 [39:02<43:39,  3.38s/it, lr: 5.0e-05 loss: 2.871e-01]
leoprint:  68%|######7   | 1626/2400 [39:06<43:39,  3.38s/it, lr: 5.0e-05 loss: 3.561e-01]
leoprint:  68%|######7   | 1626/2400 [39:06<43:39,  3.38s/it, lr: 5.0e-05 loss: 3.561e-01]
leoprint:  68%|######7   | 1627/2400 [39:06<44:03,  3.42s/it, lr: 5.0e-05 loss: 3.561e-01]
leoprint:  68%|######7   | 1627/2400 [39:06<44:03,  3.42s/it, lr: 5.0e-05 loss: 3.561e-01]
leoprint:  68%|######7   | 1627/2400 [39:10<44:03,  3.42s/it, lr: 5.0e-05 loss: 2.088e-01]
leoprint:  68%|######7   | 1627/2400 [39:10<44:03,  3.42s/it, lr: 5.0e-05 loss: 2.088e-01]
leoprint:  68%|######7   | 1628/2400 [39:10<44:21,  3.45s/it, lr: 5.0e-05 loss: 2.088e-01]
leoprint:  68%|######7   | 1628/2400 [39:10<44:21,  3.45s/it, lr: 5.0e-05 loss: 2.088e-01]
leoprint:  68%|######7   | 1628/2400 [39:13<44:21,  3.45s/it, lr: 5.0e-05 loss: 3.058e-01]
leoprint:  68%|######7   | 1628/2400 [39:13<44:21,  3.45s/it, lr: 5.0e-05 loss: 3.058e-01]
leoprint:  68%|######7   | 1629/2400 [39:13<45:10,  3.52s/it, lr: 5.0e-05 loss: 3.058e-01]
leoprint:  68%|######7   | 1629/2400 [39:13<45:10,  3.52s/it, lr: 5.0e-05 loss: 3.058e-01]
leoprint:  68%|######7   | 1629/2400 [39:17<45:10,  3.52s/it, lr: 5.0e-05 loss: 2.702e-01]
leoprint:  68%|######7   | 1629/2400 [39:17<45:10,  3.52s/it, lr: 5.0e-05 loss: 2.702e-01]
leoprint:  68%|######7   | 1630/2400 [39:20<45:06,  3.52s/it, lr: 5.0e-05 loss: 2.964e-01]
leoprint:  68%|######7   | 1630/2400 [39:20<45:06,  3.52s/it, lr: 5.0e-05 loss: 2.964e-01]
leoprint:  68%|######7   | 1631/2400 [39:20<34:42,  2.71s/it, lr: 5.0e-05 loss: 2.964e-01]
leoprint:  68%|######7   | 1631/2400 [39:20<34:42,  2.71s/it, lr: 5.0e-05 loss: 2.964e-01]
leoprint:  68%|######7   | 1631/2400 [39:24<34:42,  2.71s/it, lr: 5.0e-05 loss: 2.768e-01]
leoprint:  68%|######7   | 1631/2400 [39:24<34:42,  2.71s/it, lr: 5.0e-05 loss: 2.768e-01]
leoprint:  68%|######8   | 1632/2400 [39:24<37:09,  2.90s/it, lr: 5.0e-05 loss: 2.768e-01]
leoprint:  68%|######8   | 1632/2400 [39:24<37:09,  2.90s/it, lr: 5.0e-05 loss: 2.768e-01]
leoprint:  68%|######8   | 1632/2400 [39:28<37:09,  2.90s/it, lr: 5.0e-05 loss: 2.739e-01]
leoprint:  68%|######8   | 1632/2400 [39:28<37:09,  2.90s/it, lr: 5.0e-05 loss: 2.739e-01]
leoprint:  68%|######8   | 1633/2400 [39:28<39:30,  3.09s/it, lr: 5.0e-05 loss: 2.739e-01]
leoprint:  68%|######8   | 1633/2400 [39:28<39:30,  3.09s/it, lr: 5.0e-05 loss: 2.739e-01]
leoprint:  68%|######8   | 1633/2400 [39:31<39:30,  3.09s/it, lr: 5.0e-05 loss: 2.704e-01]
leoprint:  68%|######8   | 1633/2400 [39:31<39:30,  3.09s/it, lr: 5.0e-05 loss: 2.704e-01]
leoprint:  68%|######8   | 1634/2400 [39:31<40:54,  3.20s/it, lr: 5.0e-05 loss: 2.704e-01]
leoprint:  68%|######8   | 1634/2400 [39:31<40:54,  3.20s/it, lr: 5.0e-05 loss: 2.704e-01]
leoprint:  68%|######8   | 1634/2400 [39:35<40:54,  3.20s/it, lr: 5.0e-05 loss: 3.076e-01]
leoprint:  68%|######8   | 1634/2400 [39:35<40:54,  3.20s/it, lr: 5.0e-05 loss: 3.076e-01]
leoprint:  68%|######8   | 1635/2400 [39:35<42:27,  3.33s/it, lr: 5.0e-05 loss: 3.076e-01]
leoprint:  68%|######8   | 1635/2400 [39:35<42:27,  3.33s/it, lr: 5.0e-05 loss: 3.076e-01]
leoprint:  68%|######8   | 1635/2400 [39:38<42:27,  3.33s/it, lr: 5.0e-05 loss: 3.295e-01]
leoprint:  68%|######8   | 1635/2400 [39:38<42:27,  3.33s/it, lr: 5.0e-05 loss: 3.295e-01]
leoprint:  68%|######8   | 1636/2400 [39:38<43:00,  3.38s/it, lr: 5.0e-05 loss: 3.295e-01]
leoprint:  68%|######8   | 1636/2400 [39:38<43:00,  3.38s/it, lr: 5.0e-05 loss: 3.295e-01]
leoprint:  68%|######8   | 1636/2400 [39:42<43:00,  3.38s/it, lr: 5.0e-05 loss: 2.928e-01]
leoprint:  68%|######8   | 1636/2400 [39:42<43:00,  3.38s/it, lr: 5.0e-05 loss: 2.928e-01]
leoprint:  68%|######8   | 1637/2400 [39:42<43:51,  3.45s/it, lr: 5.0e-05 loss: 2.928e-01]
leoprint:  68%|######8   | 1637/2400 [39:42<43:51,  3.45s/it, lr: 5.0e-05 loss: 2.928e-01]
leoprint:  68%|######8   | 1637/2400 [39:45<43:51,  3.45s/it, lr: 5.0e-05 loss: 2.885e-01]
leoprint:  68%|######8   | 1637/2400 [39:45<43:51,  3.45s/it, lr: 5.0e-05 loss: 2.885e-01]
leoprint:  68%|######8   | 1638/2400 [39:45<44:01,  3.47s/it, lr: 5.0e-05 loss: 2.885e-01]
leoprint:  68%|######8   | 1638/2400 [39:45<44:01,  3.47s/it, lr: 5.0e-05 loss: 2.885e-01]
leoprint:  68%|######8   | 1638/2400 [39:49<44:01,  3.47s/it, lr: 5.0e-05 loss: 2.726e-01]
leoprint:  68%|######8   | 1638/2400 [39:49<44:01,  3.47s/it, lr: 5.0e-05 loss: 2.726e-01]
leoprint:  68%|######8   | 1639/2400 [39:49<44:06,  3.48s/it, lr: 5.0e-05 loss: 2.726e-01]
leoprint:  68%|######8   | 1639/2400 [39:49<44:06,  3.48s/it, lr: 5.0e-05 loss: 2.726e-01]
leoprint:  68%|######8   | 1639/2400 [39:52<44:06,  3.48s/it, lr: 5.0e-05 loss: 2.540e-01]
leoprint:  68%|######8   | 1639/2400 [39:52<44:06,  3.48s/it, lr: 5.0e-05 loss: 2.540e-01]
leoprint:  68%|######8   | 1640/2400 [39:56<44:02,  3.48s/it, lr: 5.0e-05 loss: 3.195e-01]
leoprint:  68%|######8   | 1640/2400 [39:56<44:02,  3.48s/it, lr: 5.0e-05 loss: 3.195e-01]
leoprint:  68%|######8   | 1641/2400 [39:56<34:43,  2.75s/it, lr: 5.0e-05 loss: 3.195e-01]
leoprint:  68%|######8   | 1641/2400 [39:56<34:43,  2.75s/it, lr: 5.0e-05 loss: 3.195e-01]
leoprint:  68%|######8   | 1641/2400 [40:00<34:43,  2.75s/it, lr: 5.0e-05 loss: 2.942e-01]
leoprint:  68%|######8   | 1641/2400 [40:00<34:43,  2.75s/it, lr: 5.0e-05 loss: 2.942e-01]
leoprint:  68%|######8   | 1642/2400 [40:00<37:04,  2.93s/it, lr: 5.0e-05 loss: 2.942e-01]
leoprint:  68%|######8   | 1642/2400 [40:00<37:04,  2.93s/it, lr: 5.0e-05 loss: 2.942e-01]
leoprint:  68%|######8   | 1642/2400 [40:03<37:04,  2.93s/it, lr: 5.0e-05 loss: 2.569e-01]
leoprint:  68%|######8   | 1642/2400 [40:03<37:04,  2.93s/it, lr: 5.0e-05 loss: 2.569e-01]
leoprint:  68%|######8   | 1643/2400 [40:03<38:52,  3.08s/it, lr: 5.0e-05 loss: 2.569e-01]
leoprint:  68%|######8   | 1643/2400 [40:03<38:52,  3.08s/it, lr: 5.0e-05 loss: 2.569e-01]
leoprint:  68%|######8   | 1643/2400 [40:07<38:52,  3.08s/it, lr: 5.0e-05 loss: 2.192e-01]
leoprint:  68%|######8   | 1643/2400 [40:07<38:52,  3.08s/it, lr: 5.0e-05 loss: 2.192e-01]
leoprint:  68%|######8   | 1644/2400 [40:07<40:15,  3.20s/it, lr: 5.0e-05 loss: 2.192e-01]
leoprint:  68%|######8   | 1644/2400 [40:07<40:15,  3.20s/it, lr: 5.0e-05 loss: 2.192e-01]
leoprint:  68%|######8   | 1644/2400 [40:10<40:15,  3.20s/it, lr: 5.0e-05 loss: 2.035e-01]
leoprint:  68%|######8   | 1644/2400 [40:10<40:15,  3.20s/it, lr: 5.0e-05 loss: 2.035e-01]
leoprint:  69%|######8   | 1645/2400 [40:10<41:42,  3.31s/it, lr: 5.0e-05 loss: 2.035e-01]
leoprint:  69%|######8   | 1645/2400 [40:10<41:42,  3.31s/it, lr: 5.0e-05 loss: 2.035e-01]
leoprint:  69%|######8   | 1645/2400 [40:14<41:42,  3.31s/it, lr: 5.0e-05 loss: 2.514e-01]
leoprint:  69%|######8   | 1645/2400 [40:14<41:42,  3.31s/it, lr: 5.0e-05 loss: 2.514e-01]
leoprint:  69%|######8   | 1646/2400 [40:14<42:34,  3.39s/it, lr: 5.0e-05 loss: 2.514e-01]
leoprint:  69%|######8   | 1646/2400 [40:14<42:34,  3.39s/it, lr: 5.0e-05 loss: 2.514e-01]
leoprint:  69%|######8   | 1646/2400 [40:17<42:34,  3.39s/it, lr: 5.0e-05 loss: 1.913e-01]
leoprint:  69%|######8   | 1646/2400 [40:17<42:34,  3.39s/it, lr: 5.0e-05 loss: 1.913e-01]
leoprint:  69%|######8   | 1647/2400 [40:17<43:20,  3.45s/it, lr: 5.0e-05 loss: 1.913e-01]
leoprint:  69%|######8   | 1647/2400 [40:17<43:20,  3.45s/it, lr: 5.0e-05 loss: 1.913e-01]
leoprint:  69%|######8   | 1647/2400 [40:21<43:20,  3.45s/it, lr: 5.0e-05 loss: 1.861e-01]
leoprint:  69%|######8   | 1647/2400 [40:21<43:20,  3.45s/it, lr: 5.0e-05 loss: 1.861e-01]
leoprint:  69%|######8   | 1648/2400 [40:21<43:53,  3.50s/it, lr: 5.0e-05 loss: 1.861e-01]
leoprint:  69%|######8   | 1648/2400 [40:21<43:53,  3.50s/it, lr: 5.0e-05 loss: 1.861e-01]
leoprint:  69%|######8   | 1648/2400 [40:25<43:53,  3.50s/it, lr: 5.0e-05 loss: 3.325e-01]
leoprint:  69%|######8   | 1648/2400 [40:25<43:53,  3.50s/it, lr: 5.0e-05 loss: 3.325e-01]
leoprint:  69%|######8   | 1649/2400 [40:25<43:51,  3.50s/it, lr: 5.0e-05 loss: 3.325e-01]
leoprint:  69%|######8   | 1649/2400 [40:25<43:51,  3.50s/it, lr: 5.0e-05 loss: 3.325e-01]
leoprint:  69%|######8   | 1649/2400 [40:28<43:51,  3.50s/it, lr: 5.0e-05 loss: 3.356e-01]
leoprint:  69%|######8   | 1649/2400 [40:28<43:51,  3.50s/it, lr: 5.0e-05 loss: 3.356e-01]
leoprint:  69%|######8   | 1650/2400 [40:32<43:47,  3.50s/it, lr: 5.0e-05 loss: 2.831e-01]
leoprint:  69%|######8   | 1650/2400 [40:32<43:47,  3.50s/it, lr: 5.0e-05 loss: 2.831e-01]
leoprint:  69%|######8   | 1651/2400 [40:32<33:44,  2.70s/it, lr: 5.0e-05 loss: 2.831e-01]
leoprint:  69%|######8   | 1651/2400 [40:32<33:44,  2.70s/it, lr: 5.0e-05 loss: 2.831e-01]
leoprint:  69%|######8   | 1651/2400 [40:35<33:44,  2.70s/it, lr: 5.0e-05 loss: 2.300e-01]
leoprint:  69%|######8   | 1651/2400 [40:35<33:44,  2.70s/it, lr: 5.0e-05 loss: 2.300e-01]
leoprint:  69%|######8   | 1652/2400 [40:35<36:40,  2.94s/it, lr: 5.0e-05 loss: 2.300e-01]
leoprint:  69%|######8   | 1652/2400 [40:35<36:40,  2.94s/it, lr: 5.0e-05 loss: 2.300e-01]
leoprint:  69%|######8   | 1652/2400 [40:39<36:40,  2.94s/it, lr: 5.0e-05 loss: 3.024e-01]
leoprint:  69%|######8   | 1652/2400 [40:39<36:40,  2.94s/it, lr: 5.0e-05 loss: 3.024e-01]
leoprint:  69%|######8   | 1653/2400 [40:39<38:50,  3.12s/it, lr: 5.0e-05 loss: 3.024e-01]
leoprint:  69%|######8   | 1653/2400 [40:39<38:50,  3.12s/it, lr: 5.0e-05 loss: 3.024e-01]
leoprint:  69%|######8   | 1653/2400 [40:42<38:50,  3.12s/it, lr: 5.0e-05 loss: 2.546e-01]
leoprint:  69%|######8   | 1653/2400 [40:42<38:50,  3.12s/it, lr: 5.0e-05 loss: 2.546e-01]
leoprint:  69%|######8   | 1654/2400 [40:42<40:06,  3.23s/it, lr: 5.0e-05 loss: 2.546e-01]
leoprint:  69%|######8   | 1654/2400 [40:42<40:06,  3.23s/it, lr: 5.0e-05 loss: 2.546e-01]
leoprint:  69%|######8   | 1654/2400 [40:46<40:06,  3.23s/it, lr: 5.0e-05 loss: 2.060e-01]
leoprint:  69%|######8   | 1654/2400 [40:46<40:06,  3.23s/it, lr: 5.0e-05 loss: 2.060e-01]
leoprint:  69%|######8   | 1655/2400 [40:46<41:24,  3.33s/it, lr: 5.0e-05 loss: 2.060e-01]
leoprint:  69%|######8   | 1655/2400 [40:46<41:24,  3.33s/it, lr: 5.0e-05 loss: 2.060e-01]
leoprint:  69%|######8   | 1655/2400 [40:50<41:24,  3.33s/it, lr: 5.0e-05 loss: 2.686e-01]
leoprint:  69%|######8   | 1655/2400 [40:50<41:24,  3.33s/it, lr: 5.0e-05 loss: 2.686e-01]
leoprint:  69%|######9   | 1656/2400 [40:50<42:20,  3.41s/it, lr: 5.0e-05 loss: 2.686e-01]
leoprint:  69%|######9   | 1656/2400 [40:50<42:20,  3.41s/it, lr: 5.0e-05 loss: 2.686e-01]
leoprint:  69%|######9   | 1656/2400 [40:53<42:20,  3.41s/it, lr: 5.0e-05 loss: 3.212e-01]
leoprint:  69%|######9   | 1656/2400 [40:53<42:20,  3.41s/it, lr: 5.0e-05 loss: 3.212e-01]
leoprint:  69%|######9   | 1657/2400 [40:53<42:34,  3.44s/it, lr: 5.0e-05 loss: 3.212e-01]
leoprint:  69%|######9   | 1657/2400 [40:53<42:34,  3.44s/it, lr: 5.0e-05 loss: 3.212e-01]
leoprint:  69%|######9   | 1657/2400 [40:57<42:34,  3.44s/it, lr: 5.0e-05 loss: 2.284e-01]
leoprint:  69%|######9   | 1657/2400 [40:57<42:34,  3.44s/it, lr: 5.0e-05 loss: 2.284e-01]
leoprint:  69%|######9   | 1658/2400 [40:57<43:12,  3.49s/it, lr: 5.0e-05 loss: 2.284e-01]
leoprint:  69%|######9   | 1658/2400 [40:57<43:12,  3.49s/it, lr: 5.0e-05 loss: 2.284e-01]
leoprint:  69%|######9   | 1658/2400 [41:00<43:12,  3.49s/it, lr: 5.0e-05 loss: 2.125e-01]
leoprint:  69%|######9   | 1658/2400 [41:00<43:12,  3.49s/it, lr: 5.0e-05 loss: 2.125e-01]
leoprint:  69%|######9   | 1659/2400 [41:00<43:11,  3.50s/it, lr: 5.0e-05 loss: 2.125e-01]
leoprint:  69%|######9   | 1659/2400 [41:00<43:11,  3.50s/it, lr: 5.0e-05 loss: 2.125e-01]
leoprint:  69%|######9   | 1659/2400 [41:04<43:11,  3.50s/it, lr: 5.0e-05 loss: 3.303e-01]
leoprint:  69%|######9   | 1659/2400 [41:04<43:11,  3.50s/it, lr: 5.0e-05 loss: 3.303e-01]
leoprint:  69%|######9   | 1660/2400 [41:07<43:08,  3.50s/it, lr: 5.0e-05 loss: 2.925e-01]
leoprint:  69%|######9   | 1660/2400 [41:07<43:08,  3.50s/it, lr: 5.0e-05 loss: 2.925e-01]
leoprint:  69%|######9   | 1661/2400 [41:07<33:14,  2.70s/it, lr: 5.0e-05 loss: 2.925e-01]
leoprint:  69%|######9   | 1661/2400 [41:07<33:14,  2.70s/it, lr: 5.0e-05 loss: 2.925e-01]
leoprint:  69%|######9   | 1661/2400 [41:11<33:14,  2.70s/it, lr: 5.0e-05 loss: 3.429e-01]
leoprint:  69%|######9   | 1661/2400 [41:11<33:14,  2.70s/it, lr: 5.0e-05 loss: 3.429e-01]
leoprint:  69%|######9   | 1662/2400 [41:11<35:37,  2.90s/it, lr: 5.0e-05 loss: 3.429e-01]
leoprint:  69%|######9   | 1662/2400 [41:11<35:37,  2.90s/it, lr: 5.0e-05 loss: 3.429e-01]
leoprint:  69%|######9   | 1662/2400 [41:14<35:37,  2.90s/it, lr: 5.0e-05 loss: 3.869e-01]
leoprint:  69%|######9   | 1662/2400 [41:14<35:37,  2.90s/it, lr: 5.0e-05 loss: 3.869e-01]
leoprint:  69%|######9   | 1663/2400 [41:14<37:29,  3.05s/it, lr: 5.0e-05 loss: 3.869e-01]
leoprint:  69%|######9   | 1663/2400 [41:14<37:29,  3.05s/it, lr: 5.0e-05 loss: 3.869e-01]
leoprint:  69%|######9   | 1663/2400 [41:18<37:29,  3.05s/it, lr: 5.0e-05 loss: 2.436e-01]
leoprint:  69%|######9   | 1663/2400 [41:18<37:29,  3.05s/it, lr: 5.0e-05 loss: 2.436e-01]
leoprint:  69%|######9   | 1664/2400 [41:18<39:42,  3.24s/it, lr: 5.0e-05 loss: 2.436e-01]
leoprint:  69%|######9   | 1664/2400 [41:18<39:42,  3.24s/it, lr: 5.0e-05 loss: 2.436e-01]
leoprint:  69%|######9   | 1664/2400 [41:22<39:42,  3.24s/it, lr: 5.0e-05 loss: 3.190e-01]
leoprint:  69%|######9   | 1664/2400 [41:22<39:42,  3.24s/it, lr: 5.0e-05 loss: 3.190e-01]
leoprint:  69%|######9   | 1665/2400 [41:22<40:33,  3.31s/it, lr: 5.0e-05 loss: 3.190e-01]
leoprint:  69%|######9   | 1665/2400 [41:22<40:33,  3.31s/it, lr: 5.0e-05 loss: 3.190e-01]
leoprint:  69%|######9   | 1665/2400 [41:25<40:33,  3.31s/it, lr: 5.0e-05 loss: 3.746e-01]
leoprint:  69%|######9   | 1665/2400 [41:25<40:33,  3.31s/it, lr: 5.0e-05 loss: 3.746e-01]
leoprint:  69%|######9   | 1666/2400 [41:25<41:34,  3.40s/it, lr: 5.0e-05 loss: 3.746e-01]
leoprint:  69%|######9   | 1666/2400 [41:25<41:34,  3.40s/it, lr: 5.0e-05 loss: 3.746e-01]
leoprint:  69%|######9   | 1666/2400 [41:29<41:34,  3.40s/it, lr: 5.0e-05 loss: 3.169e-01]
leoprint:  69%|######9   | 1666/2400 [41:29<41:34,  3.40s/it, lr: 5.0e-05 loss: 3.169e-01]
leoprint:  69%|######9   | 1667/2400 [41:29<42:17,  3.46s/it, lr: 5.0e-05 loss: 3.169e-01]
leoprint:  69%|######9   | 1667/2400 [41:29<42:17,  3.46s/it, lr: 5.0e-05 loss: 3.169e-01]
leoprint:  69%|######9   | 1667/2400 [41:33<42:17,  3.46s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  69%|######9   | 1667/2400 [41:33<42:17,  3.46s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  70%|######9   | 1668/2400 [41:33<42:47,  3.51s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  70%|######9   | 1668/2400 [41:33<42:47,  3.51s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  70%|######9   | 1668/2400 [41:36<42:47,  3.51s/it, lr: 5.0e-05 loss: 2.616e-01]
leoprint:  70%|######9   | 1668/2400 [41:36<42:47,  3.51s/it, lr: 5.0e-05 loss: 2.616e-01]
leoprint:  70%|######9   | 1669/2400 [41:36<43:01,  3.53s/it, lr: 5.0e-05 loss: 2.616e-01]
leoprint:  70%|######9   | 1669/2400 [41:36<43:01,  3.53s/it, lr: 5.0e-05 loss: 2.616e-01]
leoprint:  70%|######9   | 1669/2400 [41:40<43:01,  3.53s/it, lr: 5.0e-05 loss: 2.723e-01]
leoprint:  70%|######9   | 1669/2400 [41:40<43:01,  3.53s/it, lr: 5.0e-05 loss: 2.723e-01]
leoprint:  70%|######9   | 1670/2400 [41:43<42:57,  3.53s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  70%|######9   | 1670/2400 [41:43<42:57,  3.53s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  70%|######9   | 1671/2400 [41:43<33:01,  2.72s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  70%|######9   | 1671/2400 [41:43<33:01,  2.72s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  70%|######9   | 1671/2400 [41:47<33:01,  2.72s/it, lr: 5.0e-05 loss: 2.950e-01]
leoprint:  70%|######9   | 1671/2400 [41:47<33:01,  2.72s/it, lr: 5.0e-05 loss: 2.950e-01]
leoprint:  70%|######9   | 1672/2400 [41:47<35:20,  2.91s/it, lr: 5.0e-05 loss: 2.950e-01]
leoprint:  70%|######9   | 1672/2400 [41:47<35:20,  2.91s/it, lr: 5.0e-05 loss: 2.950e-01]
leoprint:  70%|######9   | 1672/2400 [41:50<35:20,  2.91s/it, lr: 5.0e-05 loss: 2.916e-01]
leoprint:  70%|######9   | 1672/2400 [41:50<35:20,  2.91s/it, lr: 5.0e-05 loss: 2.916e-01]
leoprint:  70%|######9   | 1673/2400 [41:50<37:09,  3.07s/it, lr: 5.0e-05 loss: 2.916e-01]
leoprint:  70%|######9   | 1673/2400 [41:50<37:09,  3.07s/it, lr: 5.0e-05 loss: 2.916e-01]
leoprint:  70%|######9   | 1673/2400 [41:54<37:09,  3.07s/it, lr: 5.0e-05 loss: 2.573e-01]
leoprint:  70%|######9   | 1673/2400 [41:54<37:09,  3.07s/it, lr: 5.0e-05 loss: 2.573e-01]
leoprint:  70%|######9   | 1674/2400 [41:54<38:55,  3.22s/it, lr: 5.0e-05 loss: 2.573e-01]
leoprint:  70%|######9   | 1674/2400 [41:54<38:55,  3.22s/it, lr: 5.0e-05 loss: 2.573e-01]
leoprint:  70%|######9   | 1674/2400 [41:57<38:55,  3.22s/it, lr: 5.0e-05 loss: 2.390e-01]
leoprint:  70%|######9   | 1674/2400 [41:57<38:55,  3.22s/it, lr: 5.0e-05 loss: 2.390e-01]
leoprint:  70%|######9   | 1675/2400 [41:58<40:24,  3.34s/it, lr: 5.0e-05 loss: 2.390e-01]
leoprint:  70%|######9   | 1675/2400 [41:58<40:24,  3.34s/it, lr: 5.0e-05 loss: 2.390e-01]
leoprint:  70%|######9   | 1675/2400 [42:01<40:24,  3.34s/it, lr: 5.0e-05 loss: 2.174e-01]
leoprint:  70%|######9   | 1675/2400 [42:01<40:24,  3.34s/it, lr: 5.0e-05 loss: 2.174e-01]
leoprint:  70%|######9   | 1676/2400 [42:01<40:54,  3.39s/it, lr: 5.0e-05 loss: 2.174e-01]
leoprint:  70%|######9   | 1676/2400 [42:01<40:54,  3.39s/it, lr: 5.0e-05 loss: 2.174e-01]
leoprint:  70%|######9   | 1676/2400 [42:05<40:54,  3.39s/it, lr: 5.0e-05 loss: 2.776e-01]
leoprint:  70%|######9   | 1676/2400 [42:05<40:54,  3.39s/it, lr: 5.0e-05 loss: 2.776e-01]
leoprint:  70%|######9   | 1677/2400 [42:05<41:14,  3.42s/it, lr: 5.0e-05 loss: 2.776e-01]
leoprint:  70%|######9   | 1677/2400 [42:05<41:14,  3.42s/it, lr: 5.0e-05 loss: 2.776e-01]
leoprint:  70%|######9   | 1677/2400 [42:08<41:14,  3.42s/it, lr: 5.0e-05 loss: 2.286e-01]
leoprint:  70%|######9   | 1677/2400 [42:08<41:14,  3.42s/it, lr: 5.0e-05 loss: 2.286e-01]
leoprint:  70%|######9   | 1678/2400 [42:08<41:54,  3.48s/it, lr: 5.0e-05 loss: 2.286e-01]
leoprint:  70%|######9   | 1678/2400 [42:08<41:54,  3.48s/it, lr: 5.0e-05 loss: 2.286e-01]
leoprint:  70%|######9   | 1678/2400 [42:12<41:54,  3.48s/it, lr: 5.0e-05 loss: 2.881e-01]
leoprint:  70%|######9   | 1678/2400 [42:12<41:54,  3.48s/it, lr: 5.0e-05 loss: 2.881e-01]
leoprint:  70%|######9   | 1679/2400 [42:12<42:20,  3.52s/it, lr: 5.0e-05 loss: 2.881e-01]
leoprint:  70%|######9   | 1679/2400 [42:12<42:20,  3.52s/it, lr: 5.0e-05 loss: 2.881e-01]
leoprint:  70%|######9   | 1679/2400 [42:15<42:20,  3.52s/it, lr: 5.0e-05 loss: 2.096e-01]
leoprint:  70%|######9   | 1679/2400 [42:15<42:20,  3.52s/it, lr: 5.0e-05 loss: 2.096e-01]
leoprint:  70%|#######   | 1680/2400 [42:19<42:17,  3.52s/it, lr: 5.0e-05 loss: 3.594e-01]
leoprint:  70%|#######   | 1680/2400 [42:19<42:17,  3.52s/it, lr: 5.0e-05 loss: 3.594e-01]
leoprint:  70%|#######   | 1681/2400 [42:19<32:54,  2.75s/it, lr: 5.0e-05 loss: 3.594e-01]
leoprint:  70%|#######   | 1681/2400 [42:19<32:54,  2.75s/it, lr: 5.0e-05 loss: 3.594e-01]
leoprint:  70%|#######   | 1681/2400 [42:22<32:54,  2.75s/it, lr: 5.0e-05 loss: 3.858e-01]
leoprint:  70%|#######   | 1681/2400 [42:22<32:54,  2.75s/it, lr: 5.0e-05 loss: 3.858e-01]
leoprint:  70%|#######   | 1682/2400 [42:22<35:05,  2.93s/it, lr: 5.0e-05 loss: 3.858e-01]
leoprint:  70%|#######   | 1682/2400 [42:22<35:05,  2.93s/it, lr: 5.0e-05 loss: 3.858e-01]
leoprint:  70%|#######   | 1682/2400 [42:26<35:05,  2.93s/it, lr: 5.0e-05 loss: 2.556e-01]
leoprint:  70%|#######   | 1682/2400 [42:26<35:05,  2.93s/it, lr: 5.0e-05 loss: 2.556e-01]
leoprint:  70%|#######   | 1683/2400 [42:26<36:51,  3.08s/it, lr: 5.0e-05 loss: 2.556e-01]
leoprint:  70%|#######   | 1683/2400 [42:26<36:51,  3.08s/it, lr: 5.0e-05 loss: 2.556e-01]
leoprint:  70%|#######   | 1683/2400 [42:30<36:51,  3.08s/it, lr: 5.0e-05 loss: 3.199e-01]
leoprint:  70%|#######   | 1683/2400 [42:30<36:51,  3.08s/it, lr: 5.0e-05 loss: 3.199e-01]
leoprint:  70%|#######   | 1684/2400 [42:30<38:09,  3.20s/it, lr: 5.0e-05 loss: 3.199e-01]
leoprint:  70%|#######   | 1684/2400 [42:30<38:09,  3.20s/it, lr: 5.0e-05 loss: 3.199e-01]
leoprint:  70%|#######   | 1684/2400 [42:33<38:09,  3.20s/it, lr: 5.0e-05 loss: 2.119e-01]
leoprint:  70%|#######   | 1684/2400 [42:33<38:09,  3.20s/it, lr: 5.0e-05 loss: 2.119e-01]
leoprint:  70%|#######   | 1685/2400 [42:33<39:07,  3.28s/it, lr: 5.0e-05 loss: 2.119e-01]
leoprint:  70%|#######   | 1685/2400 [42:33<39:07,  3.28s/it, lr: 5.0e-05 loss: 2.119e-01]
leoprint:  70%|#######   | 1685/2400 [42:37<39:07,  3.28s/it, lr: 5.0e-05 loss: 1.875e-01]
leoprint:  70%|#######   | 1685/2400 [42:37<39:07,  3.28s/it, lr: 5.0e-05 loss: 1.875e-01]
leoprint:  70%|#######   | 1686/2400 [42:37<39:47,  3.34s/it, lr: 5.0e-05 loss: 1.875e-01]
leoprint:  70%|#######   | 1686/2400 [42:37<39:47,  3.34s/it, lr: 5.0e-05 loss: 1.875e-01]
leoprint:  70%|#######   | 1686/2400 [42:40<39:47,  3.34s/it, lr: 5.0e-05 loss: 2.441e-01]
leoprint:  70%|#######   | 1686/2400 [42:40<39:47,  3.34s/it, lr: 5.0e-05 loss: 2.441e-01]
leoprint:  70%|#######   | 1687/2400 [42:40<41:27,  3.49s/it, lr: 5.0e-05 loss: 2.441e-01]
leoprint:  70%|#######   | 1687/2400 [42:40<41:27,  3.49s/it, lr: 5.0e-05 loss: 2.441e-01]
leoprint:  70%|#######   | 1687/2400 [42:44<41:27,  3.49s/it, lr: 5.0e-05 loss: 3.269e-01]
leoprint:  70%|#######   | 1687/2400 [42:44<41:27,  3.49s/it, lr: 5.0e-05 loss: 3.269e-01]
leoprint:  70%|#######   | 1688/2400 [42:44<41:26,  3.49s/it, lr: 5.0e-05 loss: 3.269e-01]
leoprint:  70%|#######   | 1688/2400 [42:44<41:26,  3.49s/it, lr: 5.0e-05 loss: 3.269e-01]
leoprint:  70%|#######   | 1688/2400 [42:47<41:26,  3.49s/it, lr: 5.0e-05 loss: 3.209e-01]
leoprint:  70%|#######   | 1688/2400 [42:47<41:26,  3.49s/it, lr: 5.0e-05 loss: 3.209e-01]
leoprint:  70%|#######   | 1689/2400 [42:47<41:23,  3.49s/it, lr: 5.0e-05 loss: 3.209e-01]
leoprint:  70%|#######   | 1689/2400 [42:47<41:23,  3.49s/it, lr: 5.0e-05 loss: 3.209e-01]
leoprint:  70%|#######   | 1689/2400 [42:51<41:23,  3.49s/it, lr: 5.0e-05 loss: 2.457e-01]
leoprint:  70%|#######   | 1689/2400 [42:51<41:23,  3.49s/it, lr: 5.0e-05 loss: 2.457e-01]
leoprint:  70%|#######   | 1690/2400 [42:54<41:20,  3.49s/it, lr: 5.0e-05 loss: 2.364e-01]
leoprint:  70%|#######   | 1690/2400 [42:54<41:20,  3.49s/it, lr: 5.0e-05 loss: 2.364e-01]
leoprint:  70%|#######   | 1691/2400 [42:54<31:51,  2.70s/it, lr: 5.0e-05 loss: 2.364e-01]
leoprint:  70%|#######   | 1691/2400 [42:54<31:51,  2.70s/it, lr: 5.0e-05 loss: 2.364e-01]
leoprint:  70%|#######   | 1691/2400 [42:58<31:51,  2.70s/it, lr: 5.0e-05 loss: 2.576e-01]
leoprint:  70%|#######   | 1691/2400 [42:58<31:51,  2.70s/it, lr: 5.0e-05 loss: 2.576e-01]
leoprint:  70%|#######   | 1692/2400 [42:58<34:41,  2.94s/it, lr: 5.0e-05 loss: 2.576e-01]
leoprint:  70%|#######   | 1692/2400 [42:58<34:41,  2.94s/it, lr: 5.0e-05 loss: 2.576e-01]
leoprint:  70%|#######   | 1692/2400 [43:02<34:41,  2.94s/it, lr: 5.0e-05 loss: 2.826e-01]
leoprint:  70%|#######   | 1692/2400 [43:02<34:41,  2.94s/it, lr: 5.0e-05 loss: 2.826e-01]
leoprint:  71%|#######   | 1693/2400 [43:02<36:23,  3.09s/it, lr: 5.0e-05 loss: 2.826e-01]
leoprint:  71%|#######   | 1693/2400 [43:02<36:23,  3.09s/it, lr: 5.0e-05 loss: 2.826e-01]
leoprint:  71%|#######   | 1693/2400 [43:05<36:23,  3.09s/it, lr: 5.0e-05 loss: 3.324e-01]
leoprint:  71%|#######   | 1693/2400 [43:05<36:23,  3.09s/it, lr: 5.0e-05 loss: 3.324e-01]
leoprint:  71%|#######   | 1694/2400 [43:05<37:39,  3.20s/it, lr: 5.0e-05 loss: 3.324e-01]
leoprint:  71%|#######   | 1694/2400 [43:05<37:39,  3.20s/it, lr: 5.0e-05 loss: 3.324e-01]
leoprint:  71%|#######   | 1694/2400 [43:09<37:39,  3.20s/it, lr: 5.0e-05 loss: 2.722e-01]
leoprint:  71%|#######   | 1694/2400 [43:09<37:39,  3.20s/it, lr: 5.0e-05 loss: 2.722e-01]
leoprint:  71%|#######   | 1695/2400 [43:09<38:34,  3.28s/it, lr: 5.0e-05 loss: 2.722e-01]
leoprint:  71%|#######   | 1695/2400 [43:09<38:34,  3.28s/it, lr: 5.0e-05 loss: 2.722e-01]
leoprint:  71%|#######   | 1695/2400 [43:12<38:34,  3.28s/it, lr: 5.0e-05 loss: 2.751e-01]
leoprint:  71%|#######   | 1695/2400 [43:12<38:34,  3.28s/it, lr: 5.0e-05 loss: 2.751e-01]
leoprint:  71%|#######   | 1696/2400 [43:12<39:15,  3.35s/it, lr: 5.0e-05 loss: 2.751e-01]
leoprint:  71%|#######   | 1696/2400 [43:12<39:15,  3.35s/it, lr: 5.0e-05 loss: 2.751e-01]
leoprint:  71%|#######   | 1696/2400 [43:16<39:15,  3.35s/it, lr: 5.0e-05 loss: 2.858e-01]
leoprint:  71%|#######   | 1696/2400 [43:16<39:15,  3.35s/it, lr: 5.0e-05 loss: 2.858e-01]
leoprint:  71%|#######   | 1697/2400 [43:16<39:43,  3.39s/it, lr: 5.0e-05 loss: 2.858e-01]
leoprint:  71%|#######   | 1697/2400 [43:16<39:43,  3.39s/it, lr: 5.0e-05 loss: 2.858e-01]
leoprint:  71%|#######   | 1697/2400 [43:20<39:43,  3.39s/it, lr: 5.0e-05 loss: 3.155e-01]
leoprint:  71%|#######   | 1697/2400 [43:20<39:43,  3.39s/it, lr: 5.0e-05 loss: 3.155e-01]
leoprint:  71%|#######   | 1698/2400 [43:20<41:03,  3.51s/it, lr: 5.0e-05 loss: 3.155e-01]
leoprint:  71%|#######   | 1698/2400 [43:20<41:03,  3.51s/it, lr: 5.0e-05 loss: 3.155e-01]
leoprint:  71%|#######   | 1698/2400 [43:23<41:03,  3.51s/it, lr: 5.0e-05 loss: 3.338e-01]
leoprint:  71%|#######   | 1698/2400 [43:23<41:03,  3.51s/it, lr: 5.0e-05 loss: 3.338e-01]
leoprint:  71%|#######   | 1699/2400 [43:23<40:58,  3.51s/it, lr: 5.0e-05 loss: 3.338e-01]
leoprint:  71%|#######   | 1699/2400 [43:23<40:58,  3.51s/it, lr: 5.0e-05 loss: 3.338e-01]
leoprint:  71%|#######   | 1699/2400 [43:27<40:58,  3.51s/it, lr: 5.0e-05 loss: 1.876e-01]
leoprint:  71%|#######   | 1699/2400 [43:27<40:58,  3.51s/it, lr: 5.0e-05 loss: 1.876e-01]
leoprint:  71%|#######   | 1700/2400 [43:30<40:54,  3.51s/it, lr: 5.0e-05 loss: 3.368e-01]
leoprint:  71%|#######   | 1700/2400 [43:30<40:54,  3.51s/it, lr: 5.0e-05 loss: 3.368e-01]
leoprint:  71%|#######   | 1701/2400 [43:30<31:29,  2.70s/it, lr: 5.0e-05 loss: 3.368e-01]
leoprint:  71%|#######   | 1701/2400 [43:30<31:29,  2.70s/it, lr: 5.0e-05 loss: 3.368e-01]
leoprint:  71%|#######   | 1701/2400 [43:34<31:29,  2.70s/it, lr: 5.0e-05 loss: 2.223e-01]
leoprint:  71%|#######   | 1701/2400 [43:34<31:29,  2.70s/it, lr: 5.0e-05 loss: 2.223e-01]
leoprint:  71%|#######   | 1702/2400 [43:34<33:43,  2.90s/it, lr: 5.0e-05 loss: 2.223e-01]
leoprint:  71%|#######   | 1702/2400 [43:34<33:43,  2.90s/it, lr: 5.0e-05 loss: 2.223e-01]
leoprint:  71%|#######   | 1702/2400 [43:37<33:43,  2.90s/it, lr: 5.0e-05 loss: 2.192e-01]
leoprint:  71%|#######   | 1702/2400 [43:37<33:43,  2.90s/it, lr: 5.0e-05 loss: 2.192e-01]
leoprint:  71%|#######   | 1703/2400 [43:37<35:51,  3.09s/it, lr: 5.0e-05 loss: 2.192e-01]
leoprint:  71%|#######   | 1703/2400 [43:37<35:51,  3.09s/it, lr: 5.0e-05 loss: 2.192e-01]
leoprint:  71%|#######   | 1703/2400 [43:41<35:51,  3.09s/it, lr: 5.0e-05 loss: 2.268e-01]
leoprint:  71%|#######   | 1703/2400 [43:41<35:51,  3.09s/it, lr: 5.0e-05 loss: 2.268e-01]
leoprint:  71%|#######1  | 1704/2400 [43:41<38:15,  3.30s/it, lr: 5.0e-05 loss: 2.268e-01]
leoprint:  71%|#######1  | 1704/2400 [43:41<38:15,  3.30s/it, lr: 5.0e-05 loss: 2.268e-01]
leoprint:  71%|#######1  | 1704/2400 [43:45<38:15,  3.30s/it, lr: 5.0e-05 loss: 4.590e-01]
leoprint:  71%|#######1  | 1704/2400 [43:45<38:15,  3.30s/it, lr: 5.0e-05 loss: 4.590e-01]
leoprint:  71%|#######1  | 1705/2400 [43:45<38:52,  3.36s/it, lr: 5.0e-05 loss: 4.590e-01]
leoprint:  71%|#######1  | 1705/2400 [43:45<38:52,  3.36s/it, lr: 5.0e-05 loss: 4.590e-01]
leoprint:  71%|#######1  | 1705/2400 [43:48<38:52,  3.36s/it, lr: 5.0e-05 loss: 3.498e-01]
leoprint:  71%|#######1  | 1705/2400 [43:48<38:52,  3.36s/it, lr: 5.0e-05 loss: 3.498e-01]
leoprint:  71%|#######1  | 1706/2400 [43:48<39:18,  3.40s/it, lr: 5.0e-05 loss: 3.498e-01]
leoprint:  71%|#######1  | 1706/2400 [43:48<39:18,  3.40s/it, lr: 5.0e-05 loss: 3.498e-01]
leoprint:  71%|#######1  | 1706/2400 [43:52<39:18,  3.40s/it, lr: 5.0e-05 loss: 2.540e-01]
leoprint:  71%|#######1  | 1706/2400 [43:52<39:18,  3.40s/it, lr: 5.0e-05 loss: 2.540e-01]
leoprint:  71%|#######1  | 1707/2400 [43:52<39:57,  3.46s/it, lr: 5.0e-05 loss: 2.540e-01]
leoprint:  71%|#######1  | 1707/2400 [43:52<39:57,  3.46s/it, lr: 5.0e-05 loss: 2.540e-01]
leoprint:  71%|#######1  | 1707/2400 [43:55<39:57,  3.46s/it, lr: 5.0e-05 loss: 2.767e-01]
leoprint:  71%|#######1  | 1707/2400 [43:55<39:57,  3.46s/it, lr: 5.0e-05 loss: 2.767e-01]
leoprint:  71%|#######1  | 1708/2400 [43:55<40:04,  3.48s/it, lr: 5.0e-05 loss: 2.767e-01]
leoprint:  71%|#######1  | 1708/2400 [43:55<40:04,  3.48s/it, lr: 5.0e-05 loss: 2.767e-01]
leoprint:  71%|#######1  | 1708/2400 [43:59<40:04,  3.48s/it, lr: 5.0e-05 loss: 2.775e-01]
leoprint:  71%|#######1  | 1708/2400 [43:59<40:04,  3.48s/it, lr: 5.0e-05 loss: 2.775e-01]
leoprint:  71%|#######1  | 1709/2400 [43:59<40:06,  3.48s/it, lr: 5.0e-05 loss: 2.775e-01]
leoprint:  71%|#######1  | 1709/2400 [43:59<40:06,  3.48s/it, lr: 5.0e-05 loss: 2.775e-01]
leoprint:  71%|#######1  | 1709/2400 [44:02<40:06,  3.48s/it, lr: 5.0e-05 loss: 3.464e-01]
leoprint:  71%|#######1  | 1709/2400 [44:02<40:06,  3.48s/it, lr: 5.0e-05 loss: 3.464e-01]
leoprint:  71%|#######1  | 1710/2400 [44:06<40:03,  3.48s/it, lr: 5.0e-05 loss: 3.351e-01]
leoprint:  71%|#######1  | 1710/2400 [44:06<40:03,  3.48s/it, lr: 5.0e-05 loss: 3.351e-01]
leoprint:  71%|#######1  | 1711/2400 [44:06<30:53,  2.69s/it, lr: 5.0e-05 loss: 3.351e-01]
leoprint:  71%|#######1  | 1711/2400 [44:06<30:53,  2.69s/it, lr: 5.0e-05 loss: 3.351e-01]
leoprint:  71%|#######1  | 1711/2400 [44:09<30:53,  2.69s/it, lr: 5.0e-05 loss: 3.817e-01]
leoprint:  71%|#######1  | 1711/2400 [44:09<30:53,  2.69s/it, lr: 5.0e-05 loss: 3.817e-01]
leoprint:  71%|#######1  | 1712/2400 [44:09<33:07,  2.89s/it, lr: 5.0e-05 loss: 3.817e-01]
leoprint:  71%|#######1  | 1712/2400 [44:09<33:07,  2.89s/it, lr: 5.0e-05 loss: 3.817e-01]
leoprint:  71%|#######1  | 1712/2400 [44:13<33:07,  2.89s/it, lr: 5.0e-05 loss: 3.958e-01]
leoprint:  71%|#######1  | 1712/2400 [44:13<33:07,  2.89s/it, lr: 5.0e-05 loss: 3.958e-01]
leoprint:  71%|#######1  | 1713/2400 [44:13<34:53,  3.05s/it, lr: 5.0e-05 loss: 3.958e-01]
leoprint:  71%|#######1  | 1713/2400 [44:13<34:53,  3.05s/it, lr: 5.0e-05 loss: 3.958e-01]
leoprint:  71%|#######1  | 1713/2400 [44:17<34:53,  3.05s/it, lr: 5.0e-05 loss: 1.860e-01]
leoprint:  71%|#######1  | 1713/2400 [44:17<34:53,  3.05s/it, lr: 5.0e-05 loss: 1.860e-01]
leoprint:  71%|#######1  | 1714/2400 [44:17<36:37,  3.20s/it, lr: 5.0e-05 loss: 1.860e-01]
leoprint:  71%|#######1  | 1714/2400 [44:17<36:37,  3.20s/it, lr: 5.0e-05 loss: 1.860e-01]
leoprint:  71%|#######1  | 1714/2400 [44:20<36:37,  3.20s/it, lr: 5.0e-05 loss: 2.276e-01]
leoprint:  71%|#######1  | 1714/2400 [44:20<36:37,  3.20s/it, lr: 5.0e-05 loss: 2.276e-01]
leoprint:  71%|#######1  | 1715/2400 [44:20<38:25,  3.37s/it, lr: 5.0e-05 loss: 2.276e-01]
leoprint:  71%|#######1  | 1715/2400 [44:20<38:25,  3.37s/it, lr: 5.0e-05 loss: 2.276e-01]
leoprint:  71%|#######1  | 1715/2400 [44:24<38:25,  3.37s/it, lr: 5.0e-05 loss: 2.419e-01]
leoprint:  71%|#######1  | 1715/2400 [44:24<38:25,  3.37s/it, lr: 5.0e-05 loss: 2.419e-01]
leoprint:  72%|#######1  | 1716/2400 [44:24<38:50,  3.41s/it, lr: 5.0e-05 loss: 2.419e-01]
leoprint:  72%|#######1  | 1716/2400 [44:24<38:50,  3.41s/it, lr: 5.0e-05 loss: 2.419e-01]
leoprint:  72%|#######1  | 1716/2400 [44:27<38:50,  3.41s/it, lr: 5.0e-05 loss: 3.075e-01]
leoprint:  72%|#######1  | 1716/2400 [44:27<38:50,  3.41s/it, lr: 5.0e-05 loss: 3.075e-01]
leoprint:  72%|#######1  | 1717/2400 [44:27<39:06,  3.44s/it, lr: 5.0e-05 loss: 3.075e-01]
leoprint:  72%|#######1  | 1717/2400 [44:27<39:06,  3.44s/it, lr: 5.0e-05 loss: 3.075e-01]
leoprint:  72%|#######1  | 1717/2400 [44:31<39:06,  3.44s/it, lr: 5.0e-05 loss: 2.494e-01]
leoprint:  72%|#######1  | 1717/2400 [44:31<39:06,  3.44s/it, lr: 5.0e-05 loss: 2.494e-01]
leoprint:  72%|#######1  | 1718/2400 [44:31<39:41,  3.49s/it, lr: 5.0e-05 loss: 2.494e-01]
leoprint:  72%|#######1  | 1718/2400 [44:31<39:41,  3.49s/it, lr: 5.0e-05 loss: 2.494e-01]
leoprint:  72%|#######1  | 1718/2400 [44:35<39:41,  3.49s/it, lr: 5.0e-05 loss: 3.848e-01]
leoprint:  72%|#######1  | 1718/2400 [44:35<39:41,  3.49s/it, lr: 5.0e-05 loss: 3.848e-01]
leoprint:  72%|#######1  | 1719/2400 [44:35<39:41,  3.50s/it, lr: 5.0e-05 loss: 3.848e-01]
leoprint:  72%|#######1  | 1719/2400 [44:35<39:41,  3.50s/it, lr: 5.0e-05 loss: 3.848e-01]
leoprint:  72%|#######1  | 1719/2400 [44:38<39:41,  3.50s/it, lr: 5.0e-05 loss: 2.710e-01]
leoprint:  72%|#######1  | 1719/2400 [44:38<39:41,  3.50s/it, lr: 5.0e-05 loss: 2.710e-01]
leoprint:  72%|#######1  | 1720/2400 [44:42<39:38,  3.50s/it, lr: 5.0e-05 loss: 2.663e-01]
leoprint:  72%|#######1  | 1720/2400 [44:42<39:38,  3.50s/it, lr: 5.0e-05 loss: 2.663e-01]
leoprint:  72%|#######1  | 1721/2400 [44:42<30:45,  2.72s/it, lr: 5.0e-05 loss: 2.663e-01]
leoprint:  72%|#######1  | 1721/2400 [44:42<30:45,  2.72s/it, lr: 5.0e-05 loss: 2.663e-01]
leoprint:  72%|#######1  | 1721/2400 [44:45<30:45,  2.72s/it, lr: 5.0e-05 loss: 2.769e-01]
leoprint:  72%|#######1  | 1721/2400 [44:45<30:45,  2.72s/it, lr: 5.0e-05 loss: 2.769e-01]
leoprint:  72%|#######1  | 1722/2400 [44:45<33:11,  2.94s/it, lr: 5.0e-05 loss: 2.769e-01]
leoprint:  72%|#######1  | 1722/2400 [44:45<33:11,  2.94s/it, lr: 5.0e-05 loss: 2.769e-01]
leoprint:  72%|#######1  | 1722/2400 [44:49<33:11,  2.94s/it, lr: 5.0e-05 loss: 2.220e-01]
leoprint:  72%|#######1  | 1722/2400 [44:49<33:11,  2.94s/it, lr: 5.0e-05 loss: 2.220e-01]
leoprint:  72%|#######1  | 1723/2400 [44:49<34:49,  3.09s/it, lr: 5.0e-05 loss: 2.220e-01]
leoprint:  72%|#######1  | 1723/2400 [44:49<34:49,  3.09s/it, lr: 5.0e-05 loss: 2.220e-01]
leoprint:  72%|#######1  | 1723/2400 [44:52<34:49,  3.09s/it, lr: 5.0e-05 loss: 3.127e-01]
leoprint:  72%|#######1  | 1723/2400 [44:52<34:49,  3.09s/it, lr: 5.0e-05 loss: 3.127e-01]
leoprint:  72%|#######1  | 1724/2400 [44:52<36:02,  3.20s/it, lr: 5.0e-05 loss: 3.127e-01]
leoprint:  72%|#######1  | 1724/2400 [44:52<36:02,  3.20s/it, lr: 5.0e-05 loss: 3.127e-01]
leoprint:  72%|#######1  | 1724/2400 [44:56<36:02,  3.20s/it, lr: 5.0e-05 loss: 2.770e-01]
leoprint:  72%|#######1  | 1724/2400 [44:56<36:02,  3.20s/it, lr: 5.0e-05 loss: 2.770e-01]
leoprint:  72%|#######1  | 1725/2400 [44:56<36:57,  3.29s/it, lr: 5.0e-05 loss: 2.770e-01]
leoprint:  72%|#######1  | 1725/2400 [44:56<36:57,  3.29s/it, lr: 5.0e-05 loss: 2.770e-01]
leoprint:  72%|#######1  | 1725/2400 [45:00<36:57,  3.29s/it, lr: 5.0e-05 loss: 1.782e-01]
leoprint:  72%|#######1  | 1725/2400 [45:00<36:57,  3.29s/it, lr: 5.0e-05 loss: 1.782e-01]
leoprint:  72%|#######1  | 1726/2400 [45:00<38:01,  3.38s/it, lr: 5.0e-05 loss: 1.782e-01]
leoprint:  72%|#######1  | 1726/2400 [45:00<38:01,  3.38s/it, lr: 5.0e-05 loss: 1.782e-01]
leoprint:  72%|#######1  | 1726/2400 [45:03<38:01,  3.38s/it, lr: 5.0e-05 loss: 2.716e-01]
leoprint:  72%|#######1  | 1726/2400 [45:03<38:01,  3.38s/it, lr: 5.0e-05 loss: 2.716e-01]
leoprint:  72%|#######1  | 1727/2400 [45:03<39:08,  3.49s/it, lr: 5.0e-05 loss: 2.716e-01]
leoprint:  72%|#######1  | 1727/2400 [45:03<39:08,  3.49s/it, lr: 5.0e-05 loss: 2.716e-01]
leoprint:  72%|#######1  | 1727/2400 [45:07<39:08,  3.49s/it, lr: 5.0e-05 loss: 2.877e-01]
leoprint:  72%|#######1  | 1727/2400 [45:07<39:08,  3.49s/it, lr: 5.0e-05 loss: 2.877e-01]
leoprint:  72%|#######2  | 1728/2400 [45:07<39:07,  3.49s/it, lr: 5.0e-05 loss: 2.877e-01]
leoprint:  72%|#######2  | 1728/2400 [45:07<39:07,  3.49s/it, lr: 5.0e-05 loss: 2.877e-01]
leoprint:  72%|#######2  | 1728/2400 [45:10<39:07,  3.49s/it, lr: 5.0e-05 loss: 2.846e-01]
leoprint:  72%|#######2  | 1728/2400 [45:10<39:07,  3.49s/it, lr: 5.0e-05 loss: 2.846e-01]
leoprint:  72%|#######2  | 1729/2400 [45:10<39:30,  3.53s/it, lr: 5.0e-05 loss: 2.846e-01]
leoprint:  72%|#######2  | 1729/2400 [45:10<39:30,  3.53s/it, lr: 5.0e-05 loss: 2.846e-01]
leoprint:  72%|#######2  | 1729/2400 [45:14<39:30,  3.53s/it, lr: 5.0e-05 loss: 2.913e-01]
leoprint:  72%|#######2  | 1729/2400 [45:14<39:30,  3.53s/it, lr: 5.0e-05 loss: 2.913e-01]
leoprint:  72%|#######2  | 1730/2400 [45:17<39:27,  3.53s/it, lr: 5.0e-05 loss: 2.090e-01]
leoprint:  72%|#######2  | 1730/2400 [45:17<39:27,  3.53s/it, lr: 5.0e-05 loss: 2.090e-01]
leoprint:  72%|#######2  | 1731/2400 [45:17<30:18,  2.72s/it, lr: 5.0e-05 loss: 2.090e-01]
leoprint:  72%|#######2  | 1731/2400 [45:17<30:18,  2.72s/it, lr: 5.0e-05 loss: 2.090e-01]
leoprint:  72%|#######2  | 1731/2400 [45:21<30:18,  2.72s/it, lr: 5.0e-05 loss: 3.379e-01]
leoprint:  72%|#######2  | 1731/2400 [45:21<30:18,  2.72s/it, lr: 5.0e-05 loss: 3.379e-01]
leoprint:  72%|#######2  | 1732/2400 [45:21<32:24,  2.91s/it, lr: 5.0e-05 loss: 3.379e-01]
leoprint:  72%|#######2  | 1732/2400 [45:21<32:24,  2.91s/it, lr: 5.0e-05 loss: 3.379e-01]
leoprint:  72%|#######2  | 1732/2400 [45:25<32:24,  2.91s/it, lr: 5.0e-05 loss: 3.429e-01]
leoprint:  72%|#######2  | 1732/2400 [45:25<32:24,  2.91s/it, lr: 5.0e-05 loss: 3.429e-01]
leoprint:  72%|#######2  | 1733/2400 [45:25<34:29,  3.10s/it, lr: 5.0e-05 loss: 3.429e-01]
leoprint:  72%|#######2  | 1733/2400 [45:25<34:29,  3.10s/it, lr: 5.0e-05 loss: 3.429e-01]
leoprint:  72%|#######2  | 1733/2400 [45:28<34:29,  3.10s/it, lr: 5.0e-05 loss: 3.541e-01]
leoprint:  72%|#######2  | 1733/2400 [45:28<34:29,  3.10s/it, lr: 5.0e-05 loss: 3.541e-01]
leoprint:  72%|#######2  | 1734/2400 [45:28<35:40,  3.21s/it, lr: 5.0e-05 loss: 3.541e-01]
leoprint:  72%|#######2  | 1734/2400 [45:28<35:40,  3.21s/it, lr: 5.0e-05 loss: 3.541e-01]
leoprint:  72%|#######2  | 1734/2400 [45:32<35:40,  3.21s/it, lr: 5.0e-05 loss: 2.015e-01]
leoprint:  72%|#######2  | 1734/2400 [45:32<35:40,  3.21s/it, lr: 5.0e-05 loss: 2.015e-01]
leoprint:  72%|#######2  | 1735/2400 [45:32<36:30,  3.29s/it, lr: 5.0e-05 loss: 2.015e-01]
leoprint:  72%|#######2  | 1735/2400 [45:32<36:30,  3.29s/it, lr: 5.0e-05 loss: 2.015e-01]
leoprint:  72%|#######2  | 1735/2400 [45:35<36:30,  3.29s/it, lr: 5.0e-05 loss: 3.245e-01]
leoprint:  72%|#######2  | 1735/2400 [45:35<36:30,  3.29s/it, lr: 5.0e-05 loss: 3.245e-01]
leoprint:  72%|#######2  | 1736/2400 [45:35<37:30,  3.39s/it, lr: 5.0e-05 loss: 3.245e-01]
leoprint:  72%|#######2  | 1736/2400 [45:35<37:30,  3.39s/it, lr: 5.0e-05 loss: 3.245e-01]
leoprint:  72%|#######2  | 1736/2400 [45:39<37:30,  3.39s/it, lr: 5.0e-05 loss: 3.166e-01]
leoprint:  72%|#######2  | 1736/2400 [45:39<37:30,  3.39s/it, lr: 5.0e-05 loss: 3.166e-01]
leoprint:  72%|#######2  | 1737/2400 [45:39<37:50,  3.43s/it, lr: 5.0e-05 loss: 3.166e-01]
leoprint:  72%|#######2  | 1737/2400 [45:39<37:50,  3.43s/it, lr: 5.0e-05 loss: 3.166e-01]
leoprint:  72%|#######2  | 1737/2400 [45:42<37:50,  3.43s/it, lr: 5.0e-05 loss: 2.747e-01]
leoprint:  72%|#######2  | 1737/2400 [45:42<37:50,  3.43s/it, lr: 5.0e-05 loss: 2.747e-01]
leoprint:  72%|#######2  | 1738/2400 [45:42<38:37,  3.50s/it, lr: 5.0e-05 loss: 2.747e-01]
leoprint:  72%|#######2  | 1738/2400 [45:42<38:37,  3.50s/it, lr: 5.0e-05 loss: 2.747e-01]
leoprint:  72%|#######2  | 1738/2400 [45:46<38:37,  3.50s/it, lr: 5.0e-05 loss: 2.422e-01]
leoprint:  72%|#######2  | 1738/2400 [45:46<38:37,  3.50s/it, lr: 5.0e-05 loss: 2.422e-01]
leoprint:  72%|#######2  | 1739/2400 [45:46<38:58,  3.54s/it, lr: 5.0e-05 loss: 2.422e-01]
leoprint:  72%|#######2  | 1739/2400 [45:46<38:58,  3.54s/it, lr: 5.0e-05 loss: 2.422e-01]
leoprint:  72%|#######2  | 1739/2400 [45:50<38:58,  3.54s/it, lr: 5.0e-05 loss: 2.484e-01]
leoprint:  72%|#######2  | 1739/2400 [45:50<38:58,  3.54s/it, lr: 5.0e-05 loss: 2.484e-01]
leoprint:  72%|#######2  | 1740/2400 [45:53<38:54,  3.54s/it, lr: 5.0e-05 loss: 3.141e-01]
leoprint:  72%|#######2  | 1740/2400 [45:53<38:54,  3.54s/it, lr: 5.0e-05 loss: 3.141e-01]
leoprint:  73%|#######2  | 1741/2400 [45:53<29:53,  2.72s/it, lr: 5.0e-05 loss: 3.141e-01]
leoprint:  73%|#######2  | 1741/2400 [45:53<29:53,  2.72s/it, lr: 5.0e-05 loss: 3.141e-01]
leoprint:  73%|#######2  | 1741/2400 [45:57<29:53,  2.72s/it, lr: 5.0e-05 loss: 2.934e-01]
leoprint:  73%|#######2  | 1741/2400 [45:57<29:53,  2.72s/it, lr: 5.0e-05 loss: 2.934e-01]
leoprint:  73%|#######2  | 1742/2400 [45:57<31:57,  2.91s/it, lr: 5.0e-05 loss: 2.934e-01]
leoprint:  73%|#######2  | 1742/2400 [45:57<31:57,  2.91s/it, lr: 5.0e-05 loss: 2.934e-01]
leoprint:  73%|#######2  | 1742/2400 [46:00<31:57,  2.91s/it, lr: 5.0e-05 loss: 3.223e-01]
leoprint:  73%|#######2  | 1742/2400 [46:00<31:57,  2.91s/it, lr: 5.0e-05 loss: 3.223e-01]
leoprint:  73%|#######2  | 1743/2400 [46:00<33:35,  3.07s/it, lr: 5.0e-05 loss: 3.223e-01]
leoprint:  73%|#######2  | 1743/2400 [46:00<33:35,  3.07s/it, lr: 5.0e-05 loss: 3.223e-01]
leoprint:  73%|#######2  | 1743/2400 [46:04<33:35,  3.07s/it, lr: 5.0e-05 loss: 2.947e-01]
leoprint:  73%|#######2  | 1743/2400 [46:04<33:35,  3.07s/it, lr: 5.0e-05 loss: 2.947e-01]
leoprint:  73%|#######2  | 1744/2400 [46:04<35:02,  3.21s/it, lr: 5.0e-05 loss: 2.947e-01]
leoprint:  73%|#######2  | 1744/2400 [46:04<35:02,  3.21s/it, lr: 5.0e-05 loss: 2.947e-01]
leoprint:  73%|#######2  | 1744/2400 [46:07<35:02,  3.21s/it, lr: 5.0e-05 loss: 2.411e-01]
leoprint:  73%|#######2  | 1744/2400 [46:07<35:02,  3.21s/it, lr: 5.0e-05 loss: 2.411e-01]
leoprint:  73%|#######2  | 1745/2400 [46:07<35:53,  3.29s/it, lr: 5.0e-05 loss: 2.411e-01]
leoprint:  73%|#######2  | 1745/2400 [46:07<35:53,  3.29s/it, lr: 5.0e-05 loss: 2.411e-01]
leoprint:  73%|#######2  | 1745/2400 [46:11<35:53,  3.29s/it, lr: 5.0e-05 loss: 4.060e-01]
leoprint:  73%|#######2  | 1745/2400 [46:11<35:53,  3.29s/it, lr: 5.0e-05 loss: 4.060e-01]
leoprint:  73%|#######2  | 1746/2400 [46:11<36:30,  3.35s/it, lr: 5.0e-05 loss: 4.060e-01]
leoprint:  73%|#######2  | 1746/2400 [46:11<36:30,  3.35s/it, lr: 5.0e-05 loss: 4.060e-01]
leoprint:  73%|#######2  | 1746/2400 [46:14<36:30,  3.35s/it, lr: 5.0e-05 loss: 2.760e-01]
leoprint:  73%|#######2  | 1746/2400 [46:14<36:30,  3.35s/it, lr: 5.0e-05 loss: 2.760e-01]
leoprint:  73%|#######2  | 1747/2400 [46:14<37:18,  3.43s/it, lr: 5.0e-05 loss: 2.760e-01]
leoprint:  73%|#######2  | 1747/2400 [46:14<37:18,  3.43s/it, lr: 5.0e-05 loss: 2.760e-01]
leoprint:  73%|#######2  | 1747/2400 [46:18<37:18,  3.43s/it, lr: 5.0e-05 loss: 3.074e-01]
leoprint:  73%|#######2  | 1747/2400 [46:18<37:18,  3.43s/it, lr: 5.0e-05 loss: 3.074e-01]
leoprint:  73%|#######2  | 1748/2400 [46:18<37:30,  3.45s/it, lr: 5.0e-05 loss: 3.074e-01]
leoprint:  73%|#######2  | 1748/2400 [46:18<37:30,  3.45s/it, lr: 5.0e-05 loss: 3.074e-01]
leoprint:  73%|#######2  | 1748/2400 [46:22<37:30,  3.45s/it, lr: 5.0e-05 loss: 3.107e-01]
leoprint:  73%|#######2  | 1748/2400 [46:22<37:30,  3.45s/it, lr: 5.0e-05 loss: 3.107e-01]
leoprint:  73%|#######2  | 1749/2400 [46:22<37:59,  3.50s/it, lr: 5.0e-05 loss: 3.107e-01]
leoprint:  73%|#######2  | 1749/2400 [46:22<37:59,  3.50s/it, lr: 5.0e-05 loss: 3.107e-01]
leoprint:  73%|#######2  | 1749/2400 [46:25<37:59,  3.50s/it, lr: 5.0e-05 loss: 1.882e-01]
leoprint:  73%|#######2  | 1749/2400 [46:25<37:59,  3.50s/it, lr: 5.0e-05 loss: 1.882e-01]
leoprint:  73%|#######2  | 1750/2400 [46:29<37:55,  3.50s/it, lr: 5.0e-05 loss: 3.097e-01]
leoprint:  73%|#######2  | 1750/2400 [46:29<37:55,  3.50s/it, lr: 5.0e-05 loss: 3.097e-01]
leoprint:  73%|#######2  | 1751/2400 [46:29<29:12,  2.70s/it, lr: 5.0e-05 loss: 3.097e-01]
leoprint:  73%|#######2  | 1751/2400 [46:29<29:12,  2.70s/it, lr: 5.0e-05 loss: 3.097e-01]
leoprint:  73%|#######2  | 1751/2400 [46:32<29:12,  2.70s/it, lr: 5.0e-05 loss: 2.439e-01]
leoprint:  73%|#######2  | 1751/2400 [46:32<29:12,  2.70s/it, lr: 5.0e-05 loss: 2.439e-01]
leoprint:  73%|#######3  | 1752/2400 [46:32<31:16,  2.90s/it, lr: 5.0e-05 loss: 2.439e-01]
leoprint:  73%|#######3  | 1752/2400 [46:32<31:16,  2.90s/it, lr: 5.0e-05 loss: 2.439e-01]
leoprint:  73%|#######3  | 1752/2400 [46:36<31:16,  2.90s/it, lr: 5.0e-05 loss: 2.935e-01]
leoprint:  73%|#######3  | 1752/2400 [46:36<31:16,  2.90s/it, lr: 5.0e-05 loss: 2.935e-01]
leoprint:  73%|#######3  | 1753/2400 [46:36<32:55,  3.05s/it, lr: 5.0e-05 loss: 2.935e-01]
leoprint:  73%|#######3  | 1753/2400 [46:36<32:55,  3.05s/it, lr: 5.0e-05 loss: 2.935e-01]
leoprint:  73%|#######3  | 1753/2400 [46:40<32:55,  3.05s/it, lr: 5.0e-05 loss: 2.675e-01]
leoprint:  73%|#######3  | 1753/2400 [46:40<32:55,  3.05s/it, lr: 5.0e-05 loss: 2.675e-01]
leoprint:  73%|#######3  | 1754/2400 [46:40<34:30,  3.20s/it, lr: 5.0e-05 loss: 2.675e-01]
leoprint:  73%|#######3  | 1754/2400 [46:40<34:30,  3.20s/it, lr: 5.0e-05 loss: 2.675e-01]
leoprint:  73%|#######3  | 1754/2400 [46:43<34:30,  3.20s/it, lr: 5.0e-05 loss: 2.414e-01]
leoprint:  73%|#######3  | 1754/2400 [46:43<34:30,  3.20s/it, lr: 5.0e-05 loss: 2.414e-01]
leoprint:  73%|#######3  | 1755/2400 [46:43<35:20,  3.29s/it, lr: 5.0e-05 loss: 2.414e-01]
leoprint:  73%|#######3  | 1755/2400 [46:43<35:20,  3.29s/it, lr: 5.0e-05 loss: 2.414e-01]
leoprint:  73%|#######3  | 1755/2400 [46:47<35:20,  3.29s/it, lr: 5.0e-05 loss: 3.166e-01]
leoprint:  73%|#######3  | 1755/2400 [46:47<35:20,  3.29s/it, lr: 5.0e-05 loss: 3.166e-01]
leoprint:  73%|#######3  | 1756/2400 [46:47<36:22,  3.39s/it, lr: 5.0e-05 loss: 3.166e-01]
leoprint:  73%|#######3  | 1756/2400 [46:47<36:22,  3.39s/it, lr: 5.0e-05 loss: 3.166e-01]
leoprint:  73%|#######3  | 1756/2400 [46:50<36:22,  3.39s/it, lr: 5.0e-05 loss: 2.863e-01]
leoprint:  73%|#######3  | 1756/2400 [46:50<36:22,  3.39s/it, lr: 5.0e-05 loss: 2.863e-01]
leoprint:  73%|#######3  | 1757/2400 [46:50<36:40,  3.42s/it, lr: 5.0e-05 loss: 2.863e-01]
leoprint:  73%|#######3  | 1757/2400 [46:50<36:40,  3.42s/it, lr: 5.0e-05 loss: 2.863e-01]
leoprint:  73%|#######3  | 1757/2400 [46:54<36:40,  3.42s/it, lr: 5.0e-05 loss: 3.773e-01]
leoprint:  73%|#######3  | 1757/2400 [46:54<36:40,  3.42s/it, lr: 5.0e-05 loss: 3.773e-01]
leoprint:  73%|#######3  | 1758/2400 [46:54<36:51,  3.44s/it, lr: 5.0e-05 loss: 3.773e-01]
leoprint:  73%|#######3  | 1758/2400 [46:54<36:51,  3.44s/it, lr: 5.0e-05 loss: 3.773e-01]
leoprint:  73%|#######3  | 1758/2400 [46:57<36:51,  3.44s/it, lr: 5.0e-05 loss: 3.795e-01]
leoprint:  73%|#######3  | 1758/2400 [46:57<36:51,  3.44s/it, lr: 5.0e-05 loss: 3.795e-01]
leoprint:  73%|#######3  | 1759/2400 [46:57<36:59,  3.46s/it, lr: 5.0e-05 loss: 3.795e-01]
leoprint:  73%|#######3  | 1759/2400 [46:57<36:59,  3.46s/it, lr: 5.0e-05 loss: 3.795e-01]
leoprint:  73%|#######3  | 1759/2400 [47:01<36:59,  3.46s/it, lr: 5.0e-05 loss: 2.119e-01]
leoprint:  73%|#######3  | 1759/2400 [47:01<36:59,  3.46s/it, lr: 5.0e-05 loss: 2.119e-01]
leoprint:  73%|#######3  | 1760/2400 [47:05<36:56,  3.46s/it, lr: 5.0e-05 loss: 3.360e-01]
leoprint:  73%|#######3  | 1760/2400 [47:05<36:56,  3.46s/it, lr: 5.0e-05 loss: 3.360e-01]
leoprint:  73%|#######3  | 1761/2400 [47:05<28:57,  2.72s/it, lr: 5.0e-05 loss: 3.360e-01]
leoprint:  73%|#######3  | 1761/2400 [47:05<28:57,  2.72s/it, lr: 5.0e-05 loss: 3.360e-01]
leoprint:  73%|#######3  | 1761/2400 [47:08<28:57,  2.72s/it, lr: 5.0e-05 loss: 3.658e-01]
leoprint:  73%|#######3  | 1761/2400 [47:08<28:57,  2.72s/it, lr: 5.0e-05 loss: 3.658e-01]
leoprint:  73%|#######3  | 1762/2400 [47:08<30:57,  2.91s/it, lr: 5.0e-05 loss: 3.658e-01]
leoprint:  73%|#######3  | 1762/2400 [47:08<30:57,  2.91s/it, lr: 5.0e-05 loss: 3.658e-01]
leoprint:  73%|#######3  | 1762/2400 [47:12<30:57,  2.91s/it, lr: 5.0e-05 loss: 1.810e-01]
leoprint:  73%|#######3  | 1762/2400 [47:12<30:57,  2.91s/it, lr: 5.0e-05 loss: 1.810e-01]
leoprint:  73%|#######3  | 1763/2400 [47:12<32:50,  3.09s/it, lr: 5.0e-05 loss: 1.810e-01]
leoprint:  73%|#######3  | 1763/2400 [47:12<32:50,  3.09s/it, lr: 5.0e-05 loss: 1.810e-01]
leoprint:  73%|#######3  | 1763/2400 [47:15<32:50,  3.09s/it, lr: 5.0e-05 loss: 2.504e-01]
leoprint:  73%|#######3  | 1763/2400 [47:15<32:50,  3.09s/it, lr: 5.0e-05 loss: 2.504e-01]
leoprint:  74%|#######3  | 1764/2400 [47:15<33:58,  3.21s/it, lr: 5.0e-05 loss: 2.504e-01]
leoprint:  74%|#######3  | 1764/2400 [47:15<33:58,  3.21s/it, lr: 5.0e-05 loss: 2.504e-01]
leoprint:  74%|#######3  | 1764/2400 [47:19<33:58,  3.21s/it, lr: 5.0e-05 loss: 3.357e-01]
leoprint:  74%|#######3  | 1764/2400 [47:19<33:58,  3.21s/it, lr: 5.0e-05 loss: 3.357e-01]
leoprint:  74%|#######3  | 1765/2400 [47:19<34:48,  3.29s/it, lr: 5.0e-05 loss: 3.357e-01]
leoprint:  74%|#######3  | 1765/2400 [47:19<34:48,  3.29s/it, lr: 5.0e-05 loss: 3.357e-01]
leoprint:  74%|#######3  | 1765/2400 [47:22<34:48,  3.29s/it, lr: 5.0e-05 loss: 2.259e-01]
leoprint:  74%|#######3  | 1765/2400 [47:22<34:48,  3.29s/it, lr: 5.0e-05 loss: 2.259e-01]
leoprint:  74%|#######3  | 1766/2400 [47:22<35:46,  3.39s/it, lr: 5.0e-05 loss: 2.259e-01]
leoprint:  74%|#######3  | 1766/2400 [47:22<35:46,  3.39s/it, lr: 5.0e-05 loss: 2.259e-01]
leoprint:  74%|#######3  | 1766/2400 [47:26<35:46,  3.39s/it, lr: 5.0e-05 loss: 3.107e-01]
leoprint:  74%|#######3  | 1766/2400 [47:26<35:46,  3.39s/it, lr: 5.0e-05 loss: 3.107e-01]
leoprint:  74%|#######3  | 1767/2400 [47:26<36:17,  3.44s/it, lr: 5.0e-05 loss: 3.107e-01]
leoprint:  74%|#######3  | 1767/2400 [47:26<36:17,  3.44s/it, lr: 5.0e-05 loss: 3.107e-01]
leoprint:  74%|#######3  | 1767/2400 [47:29<36:17,  3.44s/it, lr: 5.0e-05 loss: 3.181e-01]
leoprint:  74%|#######3  | 1767/2400 [47:29<36:17,  3.44s/it, lr: 5.0e-05 loss: 3.181e-01]
leoprint:  74%|#######3  | 1768/2400 [47:29<36:25,  3.46s/it, lr: 5.0e-05 loss: 3.181e-01]
leoprint:  74%|#######3  | 1768/2400 [47:29<36:25,  3.46s/it, lr: 5.0e-05 loss: 3.181e-01]
leoprint:  74%|#######3  | 1768/2400 [47:33<36:25,  3.46s/it, lr: 5.0e-05 loss: 3.062e-01]
leoprint:  74%|#######3  | 1768/2400 [47:33<36:25,  3.46s/it, lr: 5.0e-05 loss: 3.062e-01]
leoprint:  74%|#######3  | 1769/2400 [47:33<36:30,  3.47s/it, lr: 5.0e-05 loss: 3.062e-01]
leoprint:  74%|#######3  | 1769/2400 [47:33<36:30,  3.47s/it, lr: 5.0e-05 loss: 3.062e-01]
leoprint:  74%|#######3  | 1769/2400 [47:37<36:30,  3.47s/it, lr: 5.0e-05 loss: 1.905e-01]
leoprint:  74%|#######3  | 1769/2400 [47:37<36:30,  3.47s/it, lr: 5.0e-05 loss: 1.905e-01]
leoprint:  74%|#######3  | 1770/2400 [47:40<36:27,  3.47s/it, lr: 5.0e-05 loss: 2.878e-01]
leoprint:  74%|#######3  | 1770/2400 [47:40<36:27,  3.47s/it, lr: 5.0e-05 loss: 2.878e-01]
leoprint:  74%|#######3  | 1771/2400 [47:40<28:09,  2.69s/it, lr: 5.0e-05 loss: 2.878e-01]
leoprint:  74%|#######3  | 1771/2400 [47:40<28:09,  2.69s/it, lr: 5.0e-05 loss: 2.878e-01]
leoprint:  74%|#######3  | 1771/2400 [47:44<28:09,  2.69s/it, lr: 5.0e-05 loss: 2.407e-01]
leoprint:  74%|#######3  | 1771/2400 [47:44<28:09,  2.69s/it, lr: 5.0e-05 loss: 2.407e-01]
leoprint:  74%|#######3  | 1772/2400 [47:44<30:13,  2.89s/it, lr: 5.0e-05 loss: 2.407e-01]
leoprint:  74%|#######3  | 1772/2400 [47:44<30:13,  2.89s/it, lr: 5.0e-05 loss: 2.407e-01]
leoprint:  74%|#######3  | 1772/2400 [47:47<30:13,  2.89s/it, lr: 5.0e-05 loss: 2.985e-01]
leoprint:  74%|#######3  | 1772/2400 [47:47<30:13,  2.89s/it, lr: 5.0e-05 loss: 2.985e-01]
leoprint:  74%|#######3  | 1773/2400 [47:47<32:28,  3.11s/it, lr: 5.0e-05 loss: 2.985e-01]
leoprint:  74%|#######3  | 1773/2400 [47:47<32:28,  3.11s/it, lr: 5.0e-05 loss: 2.985e-01]
leoprint:  74%|#######3  | 1773/2400 [47:51<32:28,  3.11s/it, lr: 5.0e-05 loss: 3.797e-01]
leoprint:  74%|#######3  | 1773/2400 [47:51<32:28,  3.11s/it, lr: 5.0e-05 loss: 3.797e-01]
leoprint:  74%|#######3  | 1774/2400 [47:51<33:33,  3.22s/it, lr: 5.0e-05 loss: 3.797e-01]
leoprint:  74%|#######3  | 1774/2400 [47:51<33:33,  3.22s/it, lr: 5.0e-05 loss: 3.797e-01]
leoprint:  74%|#######3  | 1774/2400 [47:54<33:33,  3.22s/it, lr: 5.0e-05 loss: 2.440e-01]
leoprint:  74%|#######3  | 1774/2400 [47:54<33:33,  3.22s/it, lr: 5.0e-05 loss: 2.440e-01]
leoprint:  74%|#######3  | 1775/2400 [47:54<34:19,  3.30s/it, lr: 5.0e-05 loss: 2.440e-01]
leoprint:  74%|#######3  | 1775/2400 [47:54<34:19,  3.30s/it, lr: 5.0e-05 loss: 2.440e-01]
leoprint:  74%|#######3  | 1775/2400 [47:58<34:19,  3.30s/it, lr: 5.0e-05 loss: 3.135e-01]
leoprint:  74%|#######3  | 1775/2400 [47:58<34:19,  3.30s/it, lr: 5.0e-05 loss: 3.135e-01]
leoprint:  74%|#######4  | 1776/2400 [47:58<34:53,  3.35s/it, lr: 5.0e-05 loss: 3.135e-01]
leoprint:  74%|#######4  | 1776/2400 [47:58<34:53,  3.35s/it, lr: 5.0e-05 loss: 3.135e-01]
leoprint:  74%|#######4  | 1776/2400 [48:02<34:53,  3.35s/it, lr: 5.0e-05 loss: 2.763e-01]
leoprint:  74%|#######4  | 1776/2400 [48:02<34:53,  3.35s/it, lr: 5.0e-05 loss: 2.763e-01]
leoprint:  74%|#######4  | 1777/2400 [48:02<35:38,  3.43s/it, lr: 5.0e-05 loss: 2.763e-01]
leoprint:  74%|#######4  | 1777/2400 [48:02<35:38,  3.43s/it, lr: 5.0e-05 loss: 2.763e-01]
leoprint:  74%|#######4  | 1777/2400 [48:05<35:38,  3.43s/it, lr: 5.0e-05 loss: 2.772e-01]
leoprint:  74%|#######4  | 1777/2400 [48:05<35:38,  3.43s/it, lr: 5.0e-05 loss: 2.772e-01]
leoprint:  74%|#######4  | 1778/2400 [48:05<35:49,  3.46s/it, lr: 5.0e-05 loss: 2.772e-01]
leoprint:  74%|#######4  | 1778/2400 [48:05<35:49,  3.46s/it, lr: 5.0e-05 loss: 2.772e-01]
leoprint:  74%|#######4  | 1778/2400 [48:09<35:49,  3.46s/it, lr: 5.0e-05 loss: 2.253e-01]
leoprint:  74%|#######4  | 1778/2400 [48:09<35:49,  3.46s/it, lr: 5.0e-05 loss: 2.253e-01]
leoprint:  74%|#######4  | 1779/2400 [48:09<36:43,  3.55s/it, lr: 5.0e-05 loss: 2.253e-01]
leoprint:  74%|#######4  | 1779/2400 [48:09<36:43,  3.55s/it, lr: 5.0e-05 loss: 2.253e-01]
leoprint:  74%|#######4  | 1779/2400 [48:12<36:43,  3.55s/it, lr: 5.0e-05 loss: 3.095e-01]
leoprint:  74%|#######4  | 1779/2400 [48:12<36:43,  3.55s/it, lr: 5.0e-05 loss: 3.095e-01]
leoprint:  74%|#######4  | 1780/2400 [48:16<36:39,  3.55s/it, lr: 5.0e-05 loss: 3.048e-01]
leoprint:  74%|#######4  | 1780/2400 [48:16<36:39,  3.55s/it, lr: 5.0e-05 loss: 3.048e-01]
leoprint:  74%|#######4  | 1781/2400 [48:16<28:08,  2.73s/it, lr: 5.0e-05 loss: 3.048e-01]
leoprint:  74%|#######4  | 1781/2400 [48:16<28:08,  2.73s/it, lr: 5.0e-05 loss: 3.048e-01]
leoprint:  74%|#######4  | 1781/2400 [48:19<28:08,  2.73s/it, lr: 5.0e-05 loss: 3.061e-01]
leoprint:  74%|#######4  | 1781/2400 [48:19<28:08,  2.73s/it, lr: 5.0e-05 loss: 3.061e-01]
leoprint:  74%|#######4  | 1782/2400 [48:19<30:05,  2.92s/it, lr: 5.0e-05 loss: 3.061e-01]
leoprint:  74%|#######4  | 1782/2400 [48:19<30:05,  2.92s/it, lr: 5.0e-05 loss: 3.061e-01]
leoprint:  74%|#######4  | 1782/2400 [48:23<30:05,  2.92s/it, lr: 5.0e-05 loss: 2.979e-01]
leoprint:  74%|#######4  | 1782/2400 [48:23<30:05,  2.92s/it, lr: 5.0e-05 loss: 2.979e-01]
leoprint:  74%|#######4  | 1783/2400 [48:23<31:36,  3.07s/it, lr: 5.0e-05 loss: 2.979e-01]
leoprint:  74%|#######4  | 1783/2400 [48:23<31:36,  3.07s/it, lr: 5.0e-05 loss: 2.979e-01]
leoprint:  74%|#######4  | 1783/2400 [48:27<31:36,  3.07s/it, lr: 5.0e-05 loss: 2.313e-01]
leoprint:  74%|#######4  | 1783/2400 [48:27<31:36,  3.07s/it, lr: 5.0e-05 loss: 2.313e-01]
leoprint:  74%|#######4  | 1784/2400 [48:27<33:31,  3.27s/it, lr: 5.0e-05 loss: 2.313e-01]
leoprint:  74%|#######4  | 1784/2400 [48:27<33:31,  3.27s/it, lr: 5.0e-05 loss: 2.313e-01]
leoprint:  74%|#######4  | 1784/2400 [48:30<33:31,  3.27s/it, lr: 5.0e-05 loss: 3.002e-01]
leoprint:  74%|#######4  | 1784/2400 [48:30<33:31,  3.27s/it, lr: 5.0e-05 loss: 3.002e-01]
leoprint:  74%|#######4  | 1785/2400 [48:30<34:31,  3.37s/it, lr: 5.0e-05 loss: 3.002e-01]
leoprint:  74%|#######4  | 1785/2400 [48:30<34:31,  3.37s/it, lr: 5.0e-05 loss: 3.002e-01]
leoprint:  74%|#######4  | 1785/2400 [48:34<34:31,  3.37s/it, lr: 5.0e-05 loss: 2.535e-01]
leoprint:  74%|#######4  | 1785/2400 [48:34<34:31,  3.37s/it, lr: 5.0e-05 loss: 2.535e-01]
leoprint:  74%|#######4  | 1786/2400 [48:34<34:51,  3.41s/it, lr: 5.0e-05 loss: 2.535e-01]
leoprint:  74%|#######4  | 1786/2400 [48:34<34:51,  3.41s/it, lr: 5.0e-05 loss: 2.535e-01]
leoprint:  74%|#######4  | 1786/2400 [48:37<34:51,  3.41s/it, lr: 5.0e-05 loss: 2.830e-01]
leoprint:  74%|#######4  | 1786/2400 [48:37<34:51,  3.41s/it, lr: 5.0e-05 loss: 2.830e-01]
leoprint:  74%|#######4  | 1787/2400 [48:37<35:05,  3.43s/it, lr: 5.0e-05 loss: 2.830e-01]
leoprint:  74%|#######4  | 1787/2400 [48:37<35:05,  3.43s/it, lr: 5.0e-05 loss: 2.830e-01]
leoprint:  74%|#######4  | 1787/2400 [48:41<35:05,  3.43s/it, lr: 5.0e-05 loss: 2.685e-01]
leoprint:  74%|#######4  | 1787/2400 [48:41<35:05,  3.43s/it, lr: 5.0e-05 loss: 2.685e-01]
leoprint:  74%|#######4  | 1788/2400 [48:41<35:36,  3.49s/it, lr: 5.0e-05 loss: 2.685e-01]
leoprint:  74%|#######4  | 1788/2400 [48:41<35:36,  3.49s/it, lr: 5.0e-05 loss: 2.685e-01]
leoprint:  74%|#######4  | 1788/2400 [48:44<35:36,  3.49s/it, lr: 5.0e-05 loss: 2.742e-01]
leoprint:  74%|#######4  | 1788/2400 [48:44<35:36,  3.49s/it, lr: 5.0e-05 loss: 2.742e-01]
leoprint:  75%|#######4  | 1789/2400 [48:44<35:36,  3.50s/it, lr: 5.0e-05 loss: 2.742e-01]
leoprint:  75%|#######4  | 1789/2400 [48:44<35:36,  3.50s/it, lr: 5.0e-05 loss: 2.742e-01]
leoprint:  75%|#######4  | 1789/2400 [48:48<35:36,  3.50s/it, lr: 5.0e-05 loss: 2.624e-01]
leoprint:  75%|#######4  | 1789/2400 [48:48<35:36,  3.50s/it, lr: 5.0e-05 loss: 2.624e-01]
leoprint:  75%|#######4  | 1790/2400 [48:52<35:32,  3.50s/it, lr: 5.0e-05 loss: 3.896e-01]
leoprint:  75%|#######4  | 1790/2400 [48:52<35:32,  3.50s/it, lr: 5.0e-05 loss: 3.896e-01]
leoprint:  75%|#######4  | 1791/2400 [48:52<27:24,  2.70s/it, lr: 5.0e-05 loss: 3.896e-01]
leoprint:  75%|#######4  | 1791/2400 [48:52<27:24,  2.70s/it, lr: 5.0e-05 loss: 3.896e-01]
leoprint:  75%|#######4  | 1791/2400 [48:55<27:24,  2.70s/it, lr: 5.0e-05 loss: 3.873e-01]
leoprint:  75%|#######4  | 1791/2400 [48:55<27:24,  2.70s/it, lr: 5.0e-05 loss: 3.873e-01]
leoprint:  75%|#######4  | 1792/2400 [48:55<29:22,  2.90s/it, lr: 5.0e-05 loss: 3.873e-01]
leoprint:  75%|#######4  | 1792/2400 [48:55<29:22,  2.90s/it, lr: 5.0e-05 loss: 3.873e-01]
leoprint:  75%|#######4  | 1792/2400 [48:59<29:22,  2.90s/it, lr: 5.0e-05 loss: 2.797e-01]
leoprint:  75%|#######4  | 1792/2400 [48:59<29:22,  2.90s/it, lr: 5.0e-05 loss: 2.797e-01]
leoprint:  75%|#######4  | 1793/2400 [48:59<30:56,  3.06s/it, lr: 5.0e-05 loss: 2.797e-01]
leoprint:  75%|#######4  | 1793/2400 [48:59<30:56,  3.06s/it, lr: 5.0e-05 loss: 2.797e-01]
leoprint:  75%|#######4  | 1793/2400 [49:02<30:56,  3.06s/it, lr: 5.0e-05 loss: 2.503e-01]
leoprint:  75%|#######4  | 1793/2400 [49:02<30:56,  3.06s/it, lr: 5.0e-05 loss: 2.503e-01]
leoprint:  75%|#######4  | 1794/2400 [49:02<32:26,  3.21s/it, lr: 5.0e-05 loss: 2.503e-01]
leoprint:  75%|#######4  | 1794/2400 [49:02<32:26,  3.21s/it, lr: 5.0e-05 loss: 2.503e-01]
leoprint:  75%|#######4  | 1794/2400 [49:06<32:26,  3.21s/it, lr: 5.0e-05 loss: 2.747e-01]
leoprint:  75%|#######4  | 1794/2400 [49:06<32:26,  3.21s/it, lr: 5.0e-05 loss: 2.747e-01]
leoprint:  75%|#######4  | 1795/2400 [49:06<33:14,  3.30s/it, lr: 5.0e-05 loss: 2.747e-01]
leoprint:  75%|#######4  | 1795/2400 [49:06<33:14,  3.30s/it, lr: 5.0e-05 loss: 2.747e-01]
leoprint:  75%|#######4  | 1795/2400 [49:10<33:14,  3.30s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  75%|#######4  | 1795/2400 [49:10<33:14,  3.30s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  75%|#######4  | 1796/2400 [49:10<34:49,  3.46s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  75%|#######4  | 1796/2400 [49:10<34:49,  3.46s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  75%|#######4  | 1796/2400 [49:13<34:49,  3.46s/it, lr: 5.0e-05 loss: 3.464e-01]
leoprint:  75%|#######4  | 1796/2400 [49:13<34:49,  3.46s/it, lr: 5.0e-05 loss: 3.464e-01]
leoprint:  75%|#######4  | 1797/2400 [49:13<34:55,  3.47s/it, lr: 5.0e-05 loss: 3.464e-01]
leoprint:  75%|#######4  | 1797/2400 [49:13<34:55,  3.47s/it, lr: 5.0e-05 loss: 3.464e-01]
leoprint:  75%|#######4  | 1797/2400 [49:17<34:55,  3.47s/it, lr: 5.0e-05 loss: 2.294e-01]
leoprint:  75%|#######4  | 1797/2400 [49:17<34:55,  3.47s/it, lr: 5.0e-05 loss: 2.294e-01]
leoprint:  75%|#######4  | 1798/2400 [49:17<34:58,  3.49s/it, lr: 5.0e-05 loss: 2.294e-01]
leoprint:  75%|#######4  | 1798/2400 [49:17<34:58,  3.49s/it, lr: 5.0e-05 loss: 2.294e-01]
leoprint:  75%|#######4  | 1798/2400 [49:20<34:58,  3.49s/it, lr: 5.0e-05 loss: 3.034e-01]
leoprint:  75%|#######4  | 1798/2400 [49:20<34:58,  3.49s/it, lr: 5.0e-05 loss: 3.034e-01]
leoprint:  75%|#######4  | 1799/2400 [49:20<34:59,  3.49s/it, lr: 5.0e-05 loss: 3.034e-01]
leoprint:  75%|#######4  | 1799/2400 [49:20<34:59,  3.49s/it, lr: 5.0e-05 loss: 3.034e-01]
leoprint:  75%|#######4  | 1799/2400 [49:24<34:59,  3.49s/it, lr: 5.0e-05 loss: 2.943e-01]
leoprint:  75%|#######4  | 1799/2400 [49:24<34:59,  3.49s/it, lr: 5.0e-05 loss: 2.943e-01]
+
+
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
+
+
Generating Images:  20%|##        | 1/5 [00:14<00:57, 14.39s/it]
Generating Images:  20%|##        | 1/5 [00:14<00:57, 14.39s/it]
+
+
Generating Images:  40%|####      | 2/5 [00:28<00:43, 14.40s/it]
Generating Images:  40%|####      | 2/5 [00:28<00:43, 14.40s/it]
+
+
Generating Images:  60%|######    | 3/5 [00:43<00:28, 14.40s/it]
Generating Images:  60%|######    | 3/5 [00:43<00:28, 14.40s/it]
+
+
Generating Images:  80%|########  | 4/5 [00:57<00:14, 14.40s/it]
Generating Images:  80%|########  | 4/5 [00:57<00:14, 14.40s/it]
+
+
Generating Images: 100%|##########| 5/5 [01:12<00:00, 14.41s/it]
Generating Images: 100%|##########| 5/5 [01:12<00:00, 14.41s/it]
+
+
                                                                
                                                                
+Saving at step 1800
+Saved checkpoint to /app/ai-toolkit/output/leoprint/leoprint_000001800.safetensors
+Saved optimizer to /app/ai-toolkit/output/leoprint/optimizer.pt
+
leoprint:  75%|#######5  | 1800/2400 [49:28<34:55,  3.49s/it, lr: 5.0e-05 loss: 3.225e-01]
leoprint:  75%|#######5  | 1800/2400 [49:28<34:55,  3.49s/it, lr: 5.0e-05 loss: 3.225e-01]
leoprint:  75%|#######5  | 1801/2400 [49:28<27:35,  2.76s/it, lr: 5.0e-05 loss: 3.225e-01]
leoprint:  75%|#######5  | 1801/2400 [49:28<27:35,  2.76s/it, lr: 5.0e-05 loss: 3.225e-01]
leoprint:  75%|#######5  | 1801/2400 [49:31<27:35,  2.76s/it, lr: 5.0e-05 loss: 2.546e-01]
leoprint:  75%|#######5  | 1801/2400 [49:31<27:35,  2.76s/it, lr: 5.0e-05 loss: 2.546e-01]
leoprint:  75%|#######5  | 1802/2400 [49:31<29:18,  2.94s/it, lr: 5.0e-05 loss: 2.546e-01]
leoprint:  75%|#######5  | 1802/2400 [49:31<29:18,  2.94s/it, lr: 5.0e-05 loss: 2.546e-01]
leoprint:  75%|#######5  | 1802/2400 [49:35<29:18,  2.94s/it, lr: 5.0e-05 loss: 3.551e-01]
leoprint:  75%|#######5  | 1802/2400 [49:35<29:18,  2.94s/it, lr: 5.0e-05 loss: 3.551e-01]
leoprint:  75%|#######5  | 1803/2400 [49:35<30:43,  3.09s/it, lr: 5.0e-05 loss: 3.551e-01]
leoprint:  75%|#######5  | 1803/2400 [49:35<30:43,  3.09s/it, lr: 5.0e-05 loss: 3.551e-01]
leoprint:  75%|#######5  | 1803/2400 [49:38<30:43,  3.09s/it, lr: 5.0e-05 loss: 3.020e-01]
leoprint:  75%|#######5  | 1803/2400 [49:38<30:43,  3.09s/it, lr: 5.0e-05 loss: 3.020e-01]
leoprint:  75%|#######5  | 1804/2400 [49:38<31:46,  3.20s/it, lr: 5.0e-05 loss: 3.020e-01]
leoprint:  75%|#######5  | 1804/2400 [49:38<31:46,  3.20s/it, lr: 5.0e-05 loss: 3.020e-01]
leoprint:  75%|#######5  | 1804/2400 [49:42<31:46,  3.20s/it, lr: 5.0e-05 loss: 3.409e-01]
leoprint:  75%|#######5  | 1804/2400 [49:42<31:46,  3.20s/it, lr: 5.0e-05 loss: 3.409e-01]
leoprint:  75%|#######5  | 1805/2400 [49:42<32:34,  3.29s/it, lr: 5.0e-05 loss: 3.409e-01]
leoprint:  75%|#######5  | 1805/2400 [49:42<32:34,  3.29s/it, lr: 5.0e-05 loss: 3.409e-01]
leoprint:  75%|#######5  | 1805/2400 [49:45<32:34,  3.29s/it, lr: 5.0e-05 loss: 2.120e-01]
leoprint:  75%|#######5  | 1805/2400 [49:45<32:34,  3.29s/it, lr: 5.0e-05 loss: 2.120e-01]
leoprint:  75%|#######5  | 1806/2400 [49:45<33:40,  3.40s/it, lr: 5.0e-05 loss: 2.120e-01]
leoprint:  75%|#######5  | 1806/2400 [49:45<33:40,  3.40s/it, lr: 5.0e-05 loss: 2.120e-01]
leoprint:  75%|#######5  | 1806/2400 [49:49<33:40,  3.40s/it, lr: 5.0e-05 loss: 3.454e-01]
leoprint:  75%|#######5  | 1806/2400 [49:49<33:40,  3.40s/it, lr: 5.0e-05 loss: 3.454e-01]
leoprint:  75%|#######5  | 1807/2400 [49:49<33:55,  3.43s/it, lr: 5.0e-05 loss: 3.454e-01]
leoprint:  75%|#######5  | 1807/2400 [49:49<33:55,  3.43s/it, lr: 5.0e-05 loss: 3.454e-01]
leoprint:  75%|#######5  | 1807/2400 [49:52<33:55,  3.43s/it, lr: 5.0e-05 loss: 2.385e-01]
leoprint:  75%|#######5  | 1807/2400 [49:52<33:55,  3.43s/it, lr: 5.0e-05 loss: 2.385e-01]
leoprint:  75%|#######5  | 1808/2400 [49:52<34:25,  3.49s/it, lr: 5.0e-05 loss: 2.385e-01]
leoprint:  75%|#######5  | 1808/2400 [49:52<34:25,  3.49s/it, lr: 5.0e-05 loss: 2.385e-01]
leoprint:  75%|#######5  | 1808/2400 [49:57<34:25,  3.49s/it, lr: 5.0e-05 loss: 2.658e-01]
leoprint:  75%|#######5  | 1808/2400 [49:57<34:25,  3.49s/it, lr: 5.0e-05 loss: 2.658e-01]
leoprint:  75%|#######5  | 1809/2400 [49:57<36:28,  3.70s/it, lr: 5.0e-05 loss: 2.658e-01]
leoprint:  75%|#######5  | 1809/2400 [49:57<36:28,  3.70s/it, lr: 5.0e-05 loss: 2.658e-01]
leoprint:  75%|#######5  | 1809/2400 [50:00<36:28,  3.70s/it, lr: 5.0e-05 loss: 4.605e-01]
leoprint:  75%|#######5  | 1809/2400 [50:00<36:28,  3.70s/it, lr: 5.0e-05 loss: 4.605e-01]
leoprint:  75%|#######5  | 1810/2400 [50:04<36:24,  3.70s/it, lr: 5.0e-05 loss: 2.827e-01]
leoprint:  75%|#######5  | 1810/2400 [50:04<36:24,  3.70s/it, lr: 5.0e-05 loss: 2.827e-01]
leoprint:  75%|#######5  | 1811/2400 [50:04<27:51,  2.84s/it, lr: 5.0e-05 loss: 2.827e-01]
leoprint:  75%|#######5  | 1811/2400 [50:04<27:51,  2.84s/it, lr: 5.0e-05 loss: 2.827e-01]
leoprint:  75%|#######5  | 1811/2400 [50:09<27:51,  2.84s/it, lr: 5.0e-05 loss: 3.047e-01]
leoprint:  75%|#######5  | 1811/2400 [50:09<27:51,  2.84s/it, lr: 5.0e-05 loss: 3.047e-01]
leoprint:  76%|#######5  | 1812/2400 [50:09<33:16,  3.40s/it, lr: 5.0e-05 loss: 3.047e-01]
leoprint:  76%|#######5  | 1812/2400 [50:09<33:16,  3.40s/it, lr: 5.0e-05 loss: 3.047e-01]
leoprint:  76%|#######5  | 1812/2400 [50:17<33:16,  3.40s/it, lr: 5.0e-05 loss: 3.490e-01]
leoprint:  76%|#######5  | 1812/2400 [50:17<33:16,  3.40s/it, lr: 5.0e-05 loss: 3.490e-01]
leoprint:  76%|#######5  | 1813/2400 [50:17<46:13,  4.73s/it, lr: 5.0e-05 loss: 3.490e-01]
leoprint:  76%|#######5  | 1813/2400 [50:17<46:13,  4.73s/it, lr: 5.0e-05 loss: 3.490e-01]
leoprint:  76%|#######5  | 1813/2400 [50:27<46:13,  4.73s/it, lr: 5.0e-05 loss: 3.435e-01]
leoprint:  76%|#######5  | 1813/2400 [50:27<46:13,  4.73s/it, lr: 5.0e-05 loss: 3.435e-01]
leoprint:  76%|#######5  | 1814/2400 [50:27<59:15,  6.07s/it, lr: 5.0e-05 loss: 3.435e-01]
leoprint:  76%|#######5  | 1814/2400 [50:27<59:15,  6.07s/it, lr: 5.0e-05 loss: 3.435e-01]
leoprint:  76%|#######5  | 1814/2400 [50:37<59:15,  6.07s/it, lr: 5.0e-05 loss: 2.006e-01]
leoprint:  76%|#######5  | 1814/2400 [50:37<59:15,  6.07s/it, lr: 5.0e-05 loss: 2.006e-01]
leoprint:  76%|#######5  | 1815/2400 [50:37<1:09:41,  7.15s/it, lr: 5.0e-05 loss: 2.006e-01]
leoprint:  76%|#######5  | 1815/2400 [50:37<1:09:41,  7.15s/it, lr: 5.0e-05 loss: 2.006e-01]
leoprint:  76%|#######5  | 1815/2400 [50:41<1:09:41,  7.15s/it, lr: 5.0e-05 loss: 3.057e-01]
leoprint:  76%|#######5  | 1815/2400 [50:41<1:09:41,  7.15s/it, lr: 5.0e-05 loss: 3.057e-01]
leoprint:  76%|#######5  | 1816/2400 [50:41<1:00:35,  6.22s/it, lr: 5.0e-05 loss: 3.057e-01]
leoprint:  76%|#######5  | 1816/2400 [50:41<1:00:35,  6.22s/it, lr: 5.0e-05 loss: 3.057e-01]
leoprint:  76%|#######5  | 1816/2400 [50:45<1:00:35,  6.22s/it, lr: 5.0e-05 loss: 2.534e-01]
leoprint:  76%|#######5  | 1816/2400 [50:45<1:00:35,  6.22s/it, lr: 5.0e-05 loss: 2.534e-01]
leoprint:  76%|#######5  | 1817/2400 [50:45<52:52,  5.44s/it, lr: 5.0e-05 loss: 2.534e-01]  
leoprint:  76%|#######5  | 1817/2400 [50:45<52:52,  5.44s/it, lr: 5.0e-05 loss: 2.534e-01]  
leoprint:  76%|#######5  | 1817/2400 [50:48<52:52,  5.44s/it, lr: 5.0e-05 loss: 3.588e-01]
leoprint:  76%|#######5  | 1817/2400 [50:48<52:52,  5.44s/it, lr: 5.0e-05 loss: 3.588e-01]
leoprint:  76%|#######5  | 1818/2400 [50:48<48:00,  4.95s/it, lr: 5.0e-05 loss: 3.588e-01]
leoprint:  76%|#######5  | 1818/2400 [50:48<48:00,  4.95s/it, lr: 5.0e-05 loss: 3.588e-01]
leoprint:  76%|#######5  | 1818/2400 [50:52<48:00,  4.95s/it, lr: 5.0e-05 loss: 2.520e-01]
leoprint:  76%|#######5  | 1818/2400 [50:52<48:00,  4.95s/it, lr: 5.0e-05 loss: 2.520e-01]
leoprint:  76%|#######5  | 1819/2400 [50:52<43:50,  4.53s/it, lr: 5.0e-05 loss: 2.520e-01]
leoprint:  76%|#######5  | 1819/2400 [50:52<43:50,  4.53s/it, lr: 5.0e-05 loss: 2.520e-01]
leoprint:  76%|#######5  | 1819/2400 [50:55<43:50,  4.53s/it, lr: 5.0e-05 loss: 3.689e-01]
leoprint:  76%|#######5  | 1819/2400 [50:55<43:50,  4.53s/it, lr: 5.0e-05 loss: 3.689e-01]
leoprint:  76%|#######5  | 1820/2400 [50:59<43:45,  4.53s/it, lr: 5.0e-05 loss: 3.869e-01]
leoprint:  76%|#######5  | 1820/2400 [50:59<43:45,  4.53s/it, lr: 5.0e-05 loss: 3.869e-01]
leoprint:  76%|#######5  | 1821/2400 [50:59<31:26,  3.26s/it, lr: 5.0e-05 loss: 3.869e-01]
leoprint:  76%|#######5  | 1821/2400 [50:59<31:26,  3.26s/it, lr: 5.0e-05 loss: 3.869e-01]
leoprint:  76%|#######5  | 1821/2400 [51:02<31:26,  3.26s/it, lr: 5.0e-05 loss: 2.649e-01]
leoprint:  76%|#######5  | 1821/2400 [51:02<31:26,  3.26s/it, lr: 5.0e-05 loss: 2.649e-01]
leoprint:  76%|#######5  | 1822/2400 [51:02<31:58,  3.32s/it, lr: 5.0e-05 loss: 2.649e-01]
leoprint:  76%|#######5  | 1822/2400 [51:02<31:58,  3.32s/it, lr: 5.0e-05 loss: 2.649e-01]
leoprint:  76%|#######5  | 1822/2400 [51:06<31:58,  3.32s/it, lr: 5.0e-05 loss: 3.524e-01]
leoprint:  76%|#######5  | 1822/2400 [51:06<31:58,  3.32s/it, lr: 5.0e-05 loss: 3.524e-01]
leoprint:  76%|#######5  | 1823/2400 [51:06<32:35,  3.39s/it, lr: 5.0e-05 loss: 3.524e-01]
leoprint:  76%|#######5  | 1823/2400 [51:06<32:35,  3.39s/it, lr: 5.0e-05 loss: 3.524e-01]
leoprint:  76%|#######5  | 1823/2400 [51:10<32:35,  3.39s/it, lr: 5.0e-05 loss: 2.098e-01]
leoprint:  76%|#######5  | 1823/2400 [51:10<32:35,  3.39s/it, lr: 5.0e-05 loss: 2.098e-01]
leoprint:  76%|#######6  | 1824/2400 [51:10<33:09,  3.45s/it, lr: 5.0e-05 loss: 2.098e-01]
leoprint:  76%|#######6  | 1824/2400 [51:10<33:09,  3.45s/it, lr: 5.0e-05 loss: 2.098e-01]
leoprint:  76%|#######6  | 1824/2400 [51:13<33:09,  3.45s/it, lr: 5.0e-05 loss: 2.046e-01]
leoprint:  76%|#######6  | 1824/2400 [51:13<33:09,  3.45s/it, lr: 5.0e-05 loss: 2.046e-01]
leoprint:  76%|#######6  | 1825/2400 [51:13<33:35,  3.51s/it, lr: 5.0e-05 loss: 2.046e-01]
leoprint:  76%|#######6  | 1825/2400 [51:13<33:35,  3.51s/it, lr: 5.0e-05 loss: 2.046e-01]
leoprint:  76%|#######6  | 1825/2400 [51:17<33:35,  3.51s/it, lr: 5.0e-05 loss: 3.015e-01]
leoprint:  76%|#######6  | 1825/2400 [51:17<33:35,  3.51s/it, lr: 5.0e-05 loss: 3.015e-01]
leoprint:  76%|#######6  | 1826/2400 [51:17<33:33,  3.51s/it, lr: 5.0e-05 loss: 3.015e-01]
leoprint:  76%|#######6  | 1826/2400 [51:17<33:33,  3.51s/it, lr: 5.0e-05 loss: 3.015e-01]
leoprint:  76%|#######6  | 1826/2400 [51:20<33:33,  3.51s/it, lr: 5.0e-05 loss: 2.423e-01]
leoprint:  76%|#######6  | 1826/2400 [51:20<33:33,  3.51s/it, lr: 5.0e-05 loss: 2.423e-01]
leoprint:  76%|#######6  | 1827/2400 [51:20<33:49,  3.54s/it, lr: 5.0e-05 loss: 2.423e-01]
leoprint:  76%|#######6  | 1827/2400 [51:20<33:49,  3.54s/it, lr: 5.0e-05 loss: 2.423e-01]
leoprint:  76%|#######6  | 1827/2400 [51:24<33:49,  3.54s/it, lr: 5.0e-05 loss: 2.568e-01]
leoprint:  76%|#######6  | 1827/2400 [51:24<33:49,  3.54s/it, lr: 5.0e-05 loss: 2.568e-01]
leoprint:  76%|#######6  | 1828/2400 [51:24<33:40,  3.53s/it, lr: 5.0e-05 loss: 2.568e-01]
leoprint:  76%|#######6  | 1828/2400 [51:24<33:40,  3.53s/it, lr: 5.0e-05 loss: 2.568e-01]
leoprint:  76%|#######6  | 1828/2400 [51:28<33:40,  3.53s/it, lr: 5.0e-05 loss: 2.983e-01]
leoprint:  76%|#######6  | 1828/2400 [51:28<33:40,  3.53s/it, lr: 5.0e-05 loss: 2.983e-01]
leoprint:  76%|#######6  | 1829/2400 [51:28<34:21,  3.61s/it, lr: 5.0e-05 loss: 2.983e-01]
leoprint:  76%|#######6  | 1829/2400 [51:28<34:21,  3.61s/it, lr: 5.0e-05 loss: 2.983e-01]
leoprint:  76%|#######6  | 1829/2400 [51:36<34:21,  3.61s/it, lr: 5.0e-05 loss: 4.039e-01]
leoprint:  76%|#######6  | 1829/2400 [51:36<34:21,  3.61s/it, lr: 5.0e-05 loss: 4.039e-01]
leoprint:  76%|#######6  | 1830/2400 [51:46<34:17,  3.61s/it, lr: 5.0e-05 loss: 2.448e-01]
leoprint:  76%|#######6  | 1830/2400 [51:46<34:17,  3.61s/it, lr: 5.0e-05 loss: 2.448e-01]
leoprint:  76%|#######6  | 1831/2400 [51:46<39:32,  4.17s/it, lr: 5.0e-05 loss: 2.448e-01]
leoprint:  76%|#######6  | 1831/2400 [51:46<39:32,  4.17s/it, lr: 5.0e-05 loss: 2.448e-01]
leoprint:  76%|#######6  | 1831/2400 [51:55<39:32,  4.17s/it, lr: 5.0e-05 loss: 3.424e-01]
leoprint:  76%|#######6  | 1831/2400 [51:55<39:32,  4.17s/it, lr: 5.0e-05 loss: 3.424e-01]
leoprint:  76%|#######6  | 1832/2400 [51:55<52:18,  5.53s/it, lr: 5.0e-05 loss: 3.424e-01]
leoprint:  76%|#######6  | 1832/2400 [51:55<52:18,  5.53s/it, lr: 5.0e-05 loss: 3.424e-01]
leoprint:  76%|#######6  | 1832/2400 [52:00<52:18,  5.53s/it, lr: 5.0e-05 loss: 3.076e-01]
leoprint:  76%|#######6  | 1832/2400 [52:00<52:18,  5.53s/it, lr: 5.0e-05 loss: 3.076e-01]
leoprint:  76%|#######6  | 1833/2400 [52:00<49:14,  5.21s/it, lr: 5.0e-05 loss: 3.076e-01]
leoprint:  76%|#######6  | 1833/2400 [52:00<49:14,  5.21s/it, lr: 5.0e-05 loss: 3.076e-01]
leoprint:  76%|#######6  | 1833/2400 [52:03<49:14,  5.21s/it, lr: 5.0e-05 loss: 2.407e-01]
leoprint:  76%|#######6  | 1833/2400 [52:03<49:14,  5.21s/it, lr: 5.0e-05 loss: 2.407e-01]
leoprint:  76%|#######6  | 1834/2400 [52:03<44:48,  4.75s/it, lr: 5.0e-05 loss: 2.407e-01]
leoprint:  76%|#######6  | 1834/2400 [52:03<44:48,  4.75s/it, lr: 5.0e-05 loss: 2.407e-01]
leoprint:  76%|#######6  | 1834/2400 [52:07<44:48,  4.75s/it, lr: 5.0e-05 loss: 3.924e-01]
leoprint:  76%|#######6  | 1834/2400 [52:07<44:48,  4.75s/it, lr: 5.0e-05 loss: 3.924e-01]
leoprint:  76%|#######6  | 1835/2400 [52:07<41:49,  4.44s/it, lr: 5.0e-05 loss: 3.924e-01]
leoprint:  76%|#######6  | 1835/2400 [52:07<41:49,  4.44s/it, lr: 5.0e-05 loss: 3.924e-01]
leoprint:  76%|#######6  | 1835/2400 [52:10<41:49,  4.44s/it, lr: 5.0e-05 loss: 2.093e-01]
leoprint:  76%|#######6  | 1835/2400 [52:10<41:49,  4.44s/it, lr: 5.0e-05 loss: 2.093e-01]
leoprint:  76%|#######6  | 1836/2400 [52:10<39:16,  4.18s/it, lr: 5.0e-05 loss: 2.093e-01]
leoprint:  76%|#######6  | 1836/2400 [52:10<39:16,  4.18s/it, lr: 5.0e-05 loss: 2.093e-01]
leoprint:  76%|#######6  | 1836/2400 [52:14<39:16,  4.18s/it, lr: 5.0e-05 loss: 3.946e-01]
leoprint:  76%|#######6  | 1836/2400 [52:14<39:16,  4.18s/it, lr: 5.0e-05 loss: 3.946e-01]
leoprint:  77%|#######6  | 1837/2400 [52:14<37:24,  3.99s/it, lr: 5.0e-05 loss: 3.946e-01]
leoprint:  77%|#######6  | 1837/2400 [52:14<37:24,  3.99s/it, lr: 5.0e-05 loss: 3.946e-01]
leoprint:  77%|#######6  | 1837/2400 [52:18<37:24,  3.99s/it, lr: 5.0e-05 loss: 2.955e-01]
leoprint:  77%|#######6  | 1837/2400 [52:18<37:24,  3.99s/it, lr: 5.0e-05 loss: 2.955e-01]
leoprint:  77%|#######6  | 1838/2400 [52:18<36:01,  3.85s/it, lr: 5.0e-05 loss: 2.955e-01]
leoprint:  77%|#######6  | 1838/2400 [52:18<36:01,  3.85s/it, lr: 5.0e-05 loss: 2.955e-01]
leoprint:  77%|#######6  | 1838/2400 [52:21<36:01,  3.85s/it, lr: 5.0e-05 loss: 2.957e-01]
leoprint:  77%|#######6  | 1838/2400 [52:21<36:01,  3.85s/it, lr: 5.0e-05 loss: 2.957e-01]
leoprint:  77%|#######6  | 1839/2400 [52:21<35:00,  3.74s/it, lr: 5.0e-05 loss: 2.957e-01]
leoprint:  77%|#######6  | 1839/2400 [52:21<35:00,  3.74s/it, lr: 5.0e-05 loss: 2.957e-01]
leoprint:  77%|#######6  | 1839/2400 [52:25<35:00,  3.74s/it, lr: 5.0e-05 loss: 2.309e-01]
leoprint:  77%|#######6  | 1839/2400 [52:25<35:00,  3.74s/it, lr: 5.0e-05 loss: 2.309e-01]
leoprint:  77%|#######6  | 1840/2400 [52:28<34:56,  3.74s/it, lr: 5.0e-05 loss: 2.659e-01]
leoprint:  77%|#######6  | 1840/2400 [52:28<34:56,  3.74s/it, lr: 5.0e-05 loss: 2.659e-01]
leoprint:  77%|#######6  | 1841/2400 [52:28<27:10,  2.92s/it, lr: 5.0e-05 loss: 2.659e-01]
leoprint:  77%|#######6  | 1841/2400 [52:28<27:10,  2.92s/it, lr: 5.0e-05 loss: 2.659e-01]
leoprint:  77%|#######6  | 1841/2400 [52:32<27:10,  2.92s/it, lr: 5.0e-05 loss: 2.273e-01]
leoprint:  77%|#######6  | 1841/2400 [52:32<27:10,  2.92s/it, lr: 5.0e-05 loss: 2.273e-01]
leoprint:  77%|#######6  | 1842/2400 [52:32<28:28,  3.06s/it, lr: 5.0e-05 loss: 2.273e-01]
leoprint:  77%|#######6  | 1842/2400 [52:32<28:28,  3.06s/it, lr: 5.0e-05 loss: 2.273e-01]
leoprint:  77%|#######6  | 1842/2400 [52:35<28:28,  3.06s/it, lr: 5.0e-05 loss: 3.673e-01]
leoprint:  77%|#######6  | 1842/2400 [52:35<28:28,  3.06s/it, lr: 5.0e-05 loss: 3.673e-01]
leoprint:  77%|#######6  | 1843/2400 [52:35<29:29,  3.18s/it, lr: 5.0e-05 loss: 3.673e-01]
leoprint:  77%|#######6  | 1843/2400 [52:35<29:29,  3.18s/it, lr: 5.0e-05 loss: 3.673e-01]
leoprint:  77%|#######6  | 1843/2400 [52:39<29:29,  3.18s/it, lr: 5.0e-05 loss: 2.096e-01]
leoprint:  77%|#######6  | 1843/2400 [52:39<29:29,  3.18s/it, lr: 5.0e-05 loss: 2.096e-01]
leoprint:  77%|#######6  | 1844/2400 [52:39<30:33,  3.30s/it, lr: 5.0e-05 loss: 2.096e-01]
leoprint:  77%|#######6  | 1844/2400 [52:39<30:33,  3.30s/it, lr: 5.0e-05 loss: 2.096e-01]
leoprint:  77%|#######6  | 1844/2400 [52:43<30:33,  3.30s/it, lr: 5.0e-05 loss: 2.718e-01]
leoprint:  77%|#######6  | 1844/2400 [52:43<30:33,  3.30s/it, lr: 5.0e-05 loss: 2.718e-01]
leoprint:  77%|#######6  | 1845/2400 [52:43<31:01,  3.35s/it, lr: 5.0e-05 loss: 2.718e-01]
leoprint:  77%|#######6  | 1845/2400 [52:43<31:01,  3.35s/it, lr: 5.0e-05 loss: 2.718e-01]
leoprint:  77%|#######6  | 1845/2400 [52:46<31:01,  3.35s/it, lr: 5.0e-05 loss: 2.650e-01]
leoprint:  77%|#######6  | 1845/2400 [52:46<31:01,  3.35s/it, lr: 5.0e-05 loss: 2.650e-01]
leoprint:  77%|#######6  | 1846/2400 [52:46<31:50,  3.45s/it, lr: 5.0e-05 loss: 2.650e-01]
leoprint:  77%|#######6  | 1846/2400 [52:46<31:50,  3.45s/it, lr: 5.0e-05 loss: 2.650e-01]
leoprint:  77%|#######6  | 1846/2400 [52:50<31:50,  3.45s/it, lr: 5.0e-05 loss: 3.867e-01]
leoprint:  77%|#######6  | 1846/2400 [52:50<31:50,  3.45s/it, lr: 5.0e-05 loss: 3.867e-01]
leoprint:  77%|#######6  | 1847/2400 [52:50<31:56,  3.47s/it, lr: 5.0e-05 loss: 3.867e-01]
leoprint:  77%|#######6  | 1847/2400 [52:50<31:56,  3.47s/it, lr: 5.0e-05 loss: 3.867e-01]
leoprint:  77%|#######6  | 1847/2400 [52:53<31:56,  3.47s/it, lr: 5.0e-05 loss: 3.500e-01]
leoprint:  77%|#######6  | 1847/2400 [52:53<31:56,  3.47s/it, lr: 5.0e-05 loss: 3.500e-01]
leoprint:  77%|#######7  | 1848/2400 [52:53<32:01,  3.48s/it, lr: 5.0e-05 loss: 3.500e-01]
leoprint:  77%|#######7  | 1848/2400 [52:53<32:01,  3.48s/it, lr: 5.0e-05 loss: 3.500e-01]
leoprint:  77%|#######7  | 1848/2400 [52:57<32:01,  3.48s/it, lr: 5.0e-05 loss: 4.152e-01]
leoprint:  77%|#######7  | 1848/2400 [52:57<32:01,  3.48s/it, lr: 5.0e-05 loss: 4.152e-01]
leoprint:  77%|#######7  | 1849/2400 [52:57<32:02,  3.49s/it, lr: 5.0e-05 loss: 4.152e-01]
leoprint:  77%|#######7  | 1849/2400 [52:57<32:02,  3.49s/it, lr: 5.0e-05 loss: 4.152e-01]
leoprint:  77%|#######7  | 1849/2400 [53:00<32:02,  3.49s/it, lr: 5.0e-05 loss: 2.832e-01]
leoprint:  77%|#######7  | 1849/2400 [53:00<32:02,  3.49s/it, lr: 5.0e-05 loss: 2.832e-01]
leoprint:  77%|#######7  | 1850/2400 [53:04<31:58,  3.49s/it, lr: 5.0e-05 loss: 2.789e-01]
leoprint:  77%|#######7  | 1850/2400 [53:04<31:58,  3.49s/it, lr: 5.0e-05 loss: 2.789e-01]
leoprint:  77%|#######7  | 1851/2400 [53:04<24:54,  2.72s/it, lr: 5.0e-05 loss: 2.789e-01]
leoprint:  77%|#######7  | 1851/2400 [53:04<24:54,  2.72s/it, lr: 5.0e-05 loss: 2.789e-01]
leoprint:  77%|#######7  | 1851/2400 [53:08<24:54,  2.72s/it, lr: 5.0e-05 loss: 2.807e-01]
leoprint:  77%|#######7  | 1851/2400 [53:08<24:54,  2.72s/it, lr: 5.0e-05 loss: 2.807e-01]
leoprint:  77%|#######7  | 1852/2400 [53:08<27:01,  2.96s/it, lr: 5.0e-05 loss: 2.807e-01]
leoprint:  77%|#######7  | 1852/2400 [53:08<27:01,  2.96s/it, lr: 5.0e-05 loss: 2.807e-01]
leoprint:  77%|#######7  | 1852/2400 [53:11<27:01,  2.96s/it, lr: 5.0e-05 loss: 3.722e-01]
leoprint:  77%|#######7  | 1852/2400 [53:11<27:01,  2.96s/it, lr: 5.0e-05 loss: 3.722e-01]
leoprint:  77%|#######7  | 1853/2400 [53:11<28:16,  3.10s/it, lr: 5.0e-05 loss: 3.722e-01]
leoprint:  77%|#######7  | 1853/2400 [53:11<28:16,  3.10s/it, lr: 5.0e-05 loss: 3.722e-01]
leoprint:  77%|#######7  | 1853/2400 [53:15<28:16,  3.10s/it, lr: 5.0e-05 loss: 3.355e-01]
leoprint:  77%|#######7  | 1853/2400 [53:15<28:16,  3.10s/it, lr: 5.0e-05 loss: 3.355e-01]
leoprint:  77%|#######7  | 1854/2400 [53:15<29:12,  3.21s/it, lr: 5.0e-05 loss: 3.355e-01]
leoprint:  77%|#######7  | 1854/2400 [53:15<29:12,  3.21s/it, lr: 5.0e-05 loss: 3.355e-01]
leoprint:  77%|#######7  | 1854/2400 [53:18<29:12,  3.21s/it, lr: 5.0e-05 loss: 3.270e-01]
leoprint:  77%|#######7  | 1854/2400 [53:18<29:12,  3.21s/it, lr: 5.0e-05 loss: 3.270e-01]
leoprint:  77%|#######7  | 1855/2400 [53:18<29:53,  3.29s/it, lr: 5.0e-05 loss: 3.270e-01]
leoprint:  77%|#######7  | 1855/2400 [53:18<29:53,  3.29s/it, lr: 5.0e-05 loss: 3.270e-01]
leoprint:  77%|#######7  | 1855/2400 [53:22<29:53,  3.29s/it, lr: 5.0e-05 loss: 3.413e-01]
leoprint:  77%|#######7  | 1855/2400 [53:22<29:53,  3.29s/it, lr: 5.0e-05 loss: 3.413e-01]
leoprint:  77%|#######7  | 1856/2400 [53:22<30:22,  3.35s/it, lr: 5.0e-05 loss: 3.413e-01]
leoprint:  77%|#######7  | 1856/2400 [53:22<30:22,  3.35s/it, lr: 5.0e-05 loss: 3.413e-01]
leoprint:  77%|#######7  | 1856/2400 [53:25<30:22,  3.35s/it, lr: 5.0e-05 loss: 3.696e-01]
leoprint:  77%|#######7  | 1856/2400 [53:25<30:22,  3.35s/it, lr: 5.0e-05 loss: 3.696e-01]
leoprint:  77%|#######7  | 1857/2400 [53:25<31:02,  3.43s/it, lr: 5.0e-05 loss: 3.696e-01]
leoprint:  77%|#######7  | 1857/2400 [53:25<31:02,  3.43s/it, lr: 5.0e-05 loss: 3.696e-01]
leoprint:  77%|#######7  | 1857/2400 [53:29<31:02,  3.43s/it, lr: 5.0e-05 loss: 2.860e-01]
leoprint:  77%|#######7  | 1857/2400 [53:29<31:02,  3.43s/it, lr: 5.0e-05 loss: 2.860e-01]
leoprint:  77%|#######7  | 1858/2400 [53:29<31:51,  3.53s/it, lr: 5.0e-05 loss: 2.860e-01]
leoprint:  77%|#######7  | 1858/2400 [53:29<31:51,  3.53s/it, lr: 5.0e-05 loss: 2.860e-01]
leoprint:  77%|#######7  | 1858/2400 [53:33<31:51,  3.53s/it, lr: 5.0e-05 loss: 2.440e-01]
leoprint:  77%|#######7  | 1858/2400 [53:33<31:51,  3.53s/it, lr: 5.0e-05 loss: 2.440e-01]
leoprint:  77%|#######7  | 1859/2400 [53:33<32:03,  3.56s/it, lr: 5.0e-05 loss: 2.440e-01]
leoprint:  77%|#######7  | 1859/2400 [53:33<32:03,  3.56s/it, lr: 5.0e-05 loss: 2.440e-01]
leoprint:  77%|#######7  | 1859/2400 [53:36<32:03,  3.56s/it, lr: 5.0e-05 loss: 3.194e-01]
leoprint:  77%|#######7  | 1859/2400 [53:36<32:03,  3.56s/it, lr: 5.0e-05 loss: 3.194e-01]
leoprint:  78%|#######7  | 1860/2400 [53:40<32:00,  3.56s/it, lr: 5.0e-05 loss: 3.053e-01]
leoprint:  78%|#######7  | 1860/2400 [53:40<32:00,  3.56s/it, lr: 5.0e-05 loss: 3.053e-01]
leoprint:  78%|#######7  | 1861/2400 [53:40<24:32,  2.73s/it, lr: 5.0e-05 loss: 3.053e-01]
leoprint:  78%|#######7  | 1861/2400 [53:40<24:32,  2.73s/it, lr: 5.0e-05 loss: 3.053e-01]
leoprint:  78%|#######7  | 1861/2400 [53:43<24:32,  2.73s/it, lr: 5.0e-05 loss: 2.026e-01]
leoprint:  78%|#######7  | 1861/2400 [53:43<24:32,  2.73s/it, lr: 5.0e-05 loss: 2.026e-01]
leoprint:  78%|#######7  | 1862/2400 [53:43<26:11,  2.92s/it, lr: 5.0e-05 loss: 2.026e-01]
leoprint:  78%|#######7  | 1862/2400 [53:43<26:11,  2.92s/it, lr: 5.0e-05 loss: 2.026e-01]
leoprint:  78%|#######7  | 1862/2400 [53:47<26:11,  2.92s/it, lr: 5.0e-05 loss: 2.259e-01]
leoprint:  78%|#######7  | 1862/2400 [53:47<26:11,  2.92s/it, lr: 5.0e-05 loss: 2.259e-01]
leoprint:  78%|#######7  | 1863/2400 [53:47<27:46,  3.10s/it, lr: 5.0e-05 loss: 2.259e-01]
leoprint:  78%|#######7  | 1863/2400 [53:47<27:46,  3.10s/it, lr: 5.0e-05 loss: 2.259e-01]
leoprint:  78%|#######7  | 1863/2400 [53:51<27:46,  3.10s/it, lr: 5.0e-05 loss: 2.759e-01]
leoprint:  78%|#######7  | 1863/2400 [53:51<27:46,  3.10s/it, lr: 5.0e-05 loss: 2.759e-01]
leoprint:  78%|#######7  | 1864/2400 [53:51<29:01,  3.25s/it, lr: 5.0e-05 loss: 2.759e-01]
leoprint:  78%|#######7  | 1864/2400 [53:51<29:01,  3.25s/it, lr: 5.0e-05 loss: 2.759e-01]
leoprint:  78%|#######7  | 1864/2400 [53:54<29:01,  3.25s/it, lr: 5.0e-05 loss: 3.212e-01]
leoprint:  78%|#######7  | 1864/2400 [53:54<29:01,  3.25s/it, lr: 5.0e-05 loss: 3.212e-01]
leoprint:  78%|#######7  | 1865/2400 [53:54<29:53,  3.35s/it, lr: 5.0e-05 loss: 3.212e-01]
leoprint:  78%|#######7  | 1865/2400 [53:54<29:53,  3.35s/it, lr: 5.0e-05 loss: 3.212e-01]
leoprint:  78%|#######7  | 1865/2400 [53:58<29:53,  3.35s/it, lr: 5.0e-05 loss: 3.266e-01]
leoprint:  78%|#######7  | 1865/2400 [53:58<29:53,  3.35s/it, lr: 5.0e-05 loss: 3.266e-01]
leoprint:  78%|#######7  | 1866/2400 [53:58<30:12,  3.39s/it, lr: 5.0e-05 loss: 3.266e-01]
leoprint:  78%|#######7  | 1866/2400 [53:58<30:12,  3.39s/it, lr: 5.0e-05 loss: 3.266e-01]
leoprint:  78%|#######7  | 1866/2400 [54:01<30:12,  3.39s/it, lr: 5.0e-05 loss: 2.835e-01]
leoprint:  78%|#######7  | 1866/2400 [54:01<30:12,  3.39s/it, lr: 5.0e-05 loss: 2.835e-01]
leoprint:  78%|#######7  | 1867/2400 [54:01<30:24,  3.42s/it, lr: 5.0e-05 loss: 2.835e-01]
leoprint:  78%|#######7  | 1867/2400 [54:01<30:24,  3.42s/it, lr: 5.0e-05 loss: 2.835e-01]
leoprint:  78%|#######7  | 1867/2400 [54:05<30:24,  3.42s/it, lr: 5.0e-05 loss: 3.566e-01]
leoprint:  78%|#######7  | 1867/2400 [54:05<30:24,  3.42s/it, lr: 5.0e-05 loss: 3.566e-01]
leoprint:  78%|#######7  | 1868/2400 [54:05<30:33,  3.45s/it, lr: 5.0e-05 loss: 3.566e-01]
leoprint:  78%|#######7  | 1868/2400 [54:05<30:33,  3.45s/it, lr: 5.0e-05 loss: 3.566e-01]
leoprint:  78%|#######7  | 1868/2400 [54:08<30:33,  3.45s/it, lr: 5.0e-05 loss: 2.794e-01]
leoprint:  78%|#######7  | 1868/2400 [54:08<30:33,  3.45s/it, lr: 5.0e-05 loss: 2.794e-01]
leoprint:  78%|#######7  | 1869/2400 [54:08<31:06,  3.51s/it, lr: 5.0e-05 loss: 2.794e-01]
leoprint:  78%|#######7  | 1869/2400 [54:08<31:06,  3.51s/it, lr: 5.0e-05 loss: 2.794e-01]
leoprint:  78%|#######7  | 1869/2400 [54:12<31:06,  3.51s/it, lr: 5.0e-05 loss: 3.018e-01]
leoprint:  78%|#######7  | 1869/2400 [54:12<31:06,  3.51s/it, lr: 5.0e-05 loss: 3.018e-01]
leoprint:  78%|#######7  | 1870/2400 [54:15<31:02,  3.51s/it, lr: 5.0e-05 loss: 3.052e-01]
leoprint:  78%|#######7  | 1870/2400 [54:15<31:02,  3.51s/it, lr: 5.0e-05 loss: 3.052e-01]
leoprint:  78%|#######7  | 1871/2400 [54:15<23:52,  2.71s/it, lr: 5.0e-05 loss: 3.052e-01]
leoprint:  78%|#######7  | 1871/2400 [54:15<23:52,  2.71s/it, lr: 5.0e-05 loss: 3.052e-01]
leoprint:  78%|#######7  | 1871/2400 [54:19<23:52,  2.71s/it, lr: 5.0e-05 loss: 2.788e-01]
leoprint:  78%|#######7  | 1871/2400 [54:19<23:52,  2.71s/it, lr: 5.0e-05 loss: 2.788e-01]
leoprint:  78%|#######8  | 1872/2400 [54:19<25:33,  2.90s/it, lr: 5.0e-05 loss: 2.788e-01]
leoprint:  78%|#######8  | 1872/2400 [54:19<25:33,  2.90s/it, lr: 5.0e-05 loss: 2.788e-01]
leoprint:  78%|#######8  | 1872/2400 [54:23<25:33,  2.90s/it, lr: 5.0e-05 loss: 2.026e-01]
leoprint:  78%|#######8  | 1872/2400 [54:23<25:33,  2.90s/it, lr: 5.0e-05 loss: 2.026e-01]
leoprint:  78%|#######8  | 1873/2400 [54:23<27:09,  3.09s/it, lr: 5.0e-05 loss: 2.026e-01]
leoprint:  78%|#######8  | 1873/2400 [54:23<27:09,  3.09s/it, lr: 5.0e-05 loss: 2.026e-01]
leoprint:  78%|#######8  | 1873/2400 [54:26<27:09,  3.09s/it, lr: 5.0e-05 loss: 3.897e-01]
leoprint:  78%|#######8  | 1873/2400 [54:26<27:09,  3.09s/it, lr: 5.0e-05 loss: 3.897e-01]
leoprint:  78%|#######8  | 1874/2400 [54:26<28:04,  3.20s/it, lr: 5.0e-05 loss: 3.897e-01]
leoprint:  78%|#######8  | 1874/2400 [54:26<28:04,  3.20s/it, lr: 5.0e-05 loss: 3.897e-01]
leoprint:  78%|#######8  | 1874/2400 [54:30<28:04,  3.20s/it, lr: 5.0e-05 loss: 3.096e-01]
leoprint:  78%|#######8  | 1874/2400 [54:30<28:04,  3.20s/it, lr: 5.0e-05 loss: 3.096e-01]
leoprint:  78%|#######8  | 1875/2400 [54:30<29:14,  3.34s/it, lr: 5.0e-05 loss: 3.096e-01]
leoprint:  78%|#######8  | 1875/2400 [54:30<29:14,  3.34s/it, lr: 5.0e-05 loss: 3.096e-01]
leoprint:  78%|#######8  | 1875/2400 [54:33<29:14,  3.34s/it, lr: 5.0e-05 loss: 2.870e-01]
leoprint:  78%|#######8  | 1875/2400 [54:33<29:14,  3.34s/it, lr: 5.0e-05 loss: 2.870e-01]
leoprint:  78%|#######8  | 1876/2400 [54:33<29:35,  3.39s/it, lr: 5.0e-05 loss: 2.870e-01]
leoprint:  78%|#######8  | 1876/2400 [54:33<29:35,  3.39s/it, lr: 5.0e-05 loss: 2.870e-01]
leoprint:  78%|#######8  | 1876/2400 [54:37<29:35,  3.39s/it, lr: 5.0e-05 loss: 4.076e-01]
leoprint:  78%|#######8  | 1876/2400 [54:37<29:35,  3.39s/it, lr: 5.0e-05 loss: 4.076e-01]
leoprint:  78%|#######8  | 1877/2400 [54:37<29:47,  3.42s/it, lr: 5.0e-05 loss: 4.076e-01]
leoprint:  78%|#######8  | 1877/2400 [54:37<29:47,  3.42s/it, lr: 5.0e-05 loss: 4.076e-01]
leoprint:  78%|#######8  | 1877/2400 [54:40<29:47,  3.42s/it, lr: 5.0e-05 loss: 2.449e-01]
leoprint:  78%|#######8  | 1877/2400 [54:40<29:47,  3.42s/it, lr: 5.0e-05 loss: 2.449e-01]
leoprint:  78%|#######8  | 1878/2400 [54:40<30:15,  3.48s/it, lr: 5.0e-05 loss: 2.449e-01]
leoprint:  78%|#######8  | 1878/2400 [54:40<30:15,  3.48s/it, lr: 5.0e-05 loss: 2.449e-01]
leoprint:  78%|#######8  | 1878/2400 [54:44<30:15,  3.48s/it, lr: 5.0e-05 loss: 2.237e-01]
leoprint:  78%|#######8  | 1878/2400 [54:44<30:15,  3.48s/it, lr: 5.0e-05 loss: 2.237e-01]
leoprint:  78%|#######8  | 1879/2400 [54:44<30:15,  3.48s/it, lr: 5.0e-05 loss: 2.237e-01]
leoprint:  78%|#######8  | 1879/2400 [54:44<30:15,  3.48s/it, lr: 5.0e-05 loss: 2.237e-01]
leoprint:  78%|#######8  | 1879/2400 [54:48<30:15,  3.48s/it, lr: 5.0e-05 loss: 2.696e-01]
leoprint:  78%|#######8  | 1879/2400 [54:48<30:15,  3.48s/it, lr: 5.0e-05 loss: 2.696e-01]
leoprint:  78%|#######8  | 1880/2400 [54:51<30:11,  3.48s/it, lr: 5.0e-05 loss: 3.173e-01]
leoprint:  78%|#######8  | 1880/2400 [54:51<30:11,  3.48s/it, lr: 5.0e-05 loss: 3.173e-01]
leoprint:  78%|#######8  | 1881/2400 [54:51<23:44,  2.74s/it, lr: 5.0e-05 loss: 3.173e-01]
leoprint:  78%|#######8  | 1881/2400 [54:51<23:44,  2.74s/it, lr: 5.0e-05 loss: 3.173e-01]
leoprint:  78%|#######8  | 1881/2400 [54:55<23:44,  2.74s/it, lr: 5.0e-05 loss: 2.800e-01]
leoprint:  78%|#######8  | 1881/2400 [54:55<23:44,  2.74s/it, lr: 5.0e-05 loss: 2.800e-01]
leoprint:  78%|#######8  | 1882/2400 [54:55<25:18,  2.93s/it, lr: 5.0e-05 loss: 2.800e-01]
leoprint:  78%|#######8  | 1882/2400 [54:55<25:18,  2.93s/it, lr: 5.0e-05 loss: 2.800e-01]
leoprint:  78%|#######8  | 1882/2400 [54:58<25:18,  2.93s/it, lr: 5.0e-05 loss: 2.837e-01]
leoprint:  78%|#######8  | 1882/2400 [54:58<25:18,  2.93s/it, lr: 5.0e-05 loss: 2.837e-01]
leoprint:  78%|#######8  | 1883/2400 [54:58<26:32,  3.08s/it, lr: 5.0e-05 loss: 2.837e-01]
leoprint:  78%|#######8  | 1883/2400 [54:58<26:32,  3.08s/it, lr: 5.0e-05 loss: 2.837e-01]
leoprint:  78%|#######8  | 1883/2400 [55:02<26:32,  3.08s/it, lr: 5.0e-05 loss: 2.094e-01]
leoprint:  78%|#######8  | 1883/2400 [55:02<26:32,  3.08s/it, lr: 5.0e-05 loss: 2.094e-01]
leoprint:  78%|#######8  | 1884/2400 [55:02<27:45,  3.23s/it, lr: 5.0e-05 loss: 2.094e-01]
leoprint:  78%|#######8  | 1884/2400 [55:02<27:45,  3.23s/it, lr: 5.0e-05 loss: 2.094e-01]
leoprint:  78%|#######8  | 1884/2400 [55:05<27:45,  3.23s/it, lr: 5.0e-05 loss: 3.565e-01]
leoprint:  78%|#######8  | 1884/2400 [55:05<27:45,  3.23s/it, lr: 5.0e-05 loss: 3.565e-01]
leoprint:  79%|#######8  | 1885/2400 [55:05<28:20,  3.30s/it, lr: 5.0e-05 loss: 3.565e-01]
leoprint:  79%|#######8  | 1885/2400 [55:05<28:20,  3.30s/it, lr: 5.0e-05 loss: 3.565e-01]
leoprint:  79%|#######8  | 1885/2400 [55:09<28:20,  3.30s/it, lr: 5.0e-05 loss: 2.611e-01]
leoprint:  79%|#######8  | 1885/2400 [55:09<28:20,  3.30s/it, lr: 5.0e-05 loss: 2.611e-01]
leoprint:  79%|#######8  | 1886/2400 [55:09<28:46,  3.36s/it, lr: 5.0e-05 loss: 2.611e-01]
leoprint:  79%|#######8  | 1886/2400 [55:09<28:46,  3.36s/it, lr: 5.0e-05 loss: 2.611e-01]
leoprint:  79%|#######8  | 1886/2400 [55:12<28:46,  3.36s/it, lr: 5.0e-05 loss: 2.753e-01]
leoprint:  79%|#######8  | 1886/2400 [55:12<28:46,  3.36s/it, lr: 5.0e-05 loss: 2.753e-01]
leoprint:  79%|#######8  | 1887/2400 [55:13<29:23,  3.44s/it, lr: 5.0e-05 loss: 2.753e-01]
leoprint:  79%|#######8  | 1887/2400 [55:13<29:23,  3.44s/it, lr: 5.0e-05 loss: 2.753e-01]
leoprint:  79%|#######8  | 1887/2400 [55:16<29:23,  3.44s/it, lr: 5.0e-05 loss: 1.935e-01]
leoprint:  79%|#######8  | 1887/2400 [55:16<29:23,  3.44s/it, lr: 5.0e-05 loss: 1.935e-01]
leoprint:  79%|#######8  | 1888/2400 [55:16<29:47,  3.49s/it, lr: 5.0e-05 loss: 1.935e-01]
leoprint:  79%|#######8  | 1888/2400 [55:16<29:47,  3.49s/it, lr: 5.0e-05 loss: 1.935e-01]
leoprint:  79%|#######8  | 1888/2400 [55:20<29:47,  3.49s/it, lr: 5.0e-05 loss: 3.992e-01]
leoprint:  79%|#######8  | 1888/2400 [55:20<29:47,  3.49s/it, lr: 5.0e-05 loss: 3.992e-01]
leoprint:  79%|#######8  | 1889/2400 [55:20<29:45,  3.49s/it, lr: 5.0e-05 loss: 3.992e-01]
leoprint:  79%|#######8  | 1889/2400 [55:20<29:45,  3.49s/it, lr: 5.0e-05 loss: 3.992e-01]
leoprint:  79%|#######8  | 1889/2400 [55:23<29:45,  3.49s/it, lr: 5.0e-05 loss: 2.337e-01]
leoprint:  79%|#######8  | 1889/2400 [55:23<29:45,  3.49s/it, lr: 5.0e-05 loss: 2.337e-01]
leoprint:  79%|#######8  | 1890/2400 [55:27<29:42,  3.49s/it, lr: 5.0e-05 loss: 3.045e-01]
leoprint:  79%|#######8  | 1890/2400 [55:27<29:42,  3.49s/it, lr: 5.0e-05 loss: 3.045e-01]
leoprint:  79%|#######8  | 1891/2400 [55:27<22:53,  2.70s/it, lr: 5.0e-05 loss: 3.045e-01]
leoprint:  79%|#######8  | 1891/2400 [55:27<22:53,  2.70s/it, lr: 5.0e-05 loss: 3.045e-01]
leoprint:  79%|#######8  | 1891/2400 [55:31<22:53,  2.70s/it, lr: 5.0e-05 loss: 1.917e-01]
leoprint:  79%|#######8  | 1891/2400 [55:31<22:53,  2.70s/it, lr: 5.0e-05 loss: 1.917e-01]
leoprint:  79%|#######8  | 1892/2400 [55:31<25:06,  2.97s/it, lr: 5.0e-05 loss: 1.917e-01]
leoprint:  79%|#######8  | 1892/2400 [55:31<25:06,  2.97s/it, lr: 5.0e-05 loss: 1.917e-01]
leoprint:  79%|#######8  | 1892/2400 [55:34<25:06,  2.97s/it, lr: 5.0e-05 loss: 2.882e-01]
leoprint:  79%|#######8  | 1892/2400 [55:34<25:06,  2.97s/it, lr: 5.0e-05 loss: 2.882e-01]
leoprint:  79%|#######8  | 1893/2400 [55:34<26:13,  3.10s/it, lr: 5.0e-05 loss: 2.882e-01]
leoprint:  79%|#######8  | 1893/2400 [55:34<26:13,  3.10s/it, lr: 5.0e-05 loss: 2.882e-01]
leoprint:  79%|#######8  | 1893/2400 [55:38<26:13,  3.10s/it, lr: 5.0e-05 loss: 2.605e-01]
leoprint:  79%|#######8  | 1893/2400 [55:38<26:13,  3.10s/it, lr: 5.0e-05 loss: 2.605e-01]
leoprint:  79%|#######8  | 1894/2400 [55:38<27:04,  3.21s/it, lr: 5.0e-05 loss: 2.605e-01]
leoprint:  79%|#######8  | 1894/2400 [55:38<27:04,  3.21s/it, lr: 5.0e-05 loss: 2.605e-01]
leoprint:  79%|#######8  | 1894/2400 [55:41<27:04,  3.21s/it, lr: 5.0e-05 loss: 2.174e-01]
leoprint:  79%|#######8  | 1894/2400 [55:41<27:04,  3.21s/it, lr: 5.0e-05 loss: 2.174e-01]
leoprint:  79%|#######8  | 1895/2400 [55:41<27:59,  3.33s/it, lr: 5.0e-05 loss: 2.174e-01]
leoprint:  79%|#######8  | 1895/2400 [55:41<27:59,  3.33s/it, lr: 5.0e-05 loss: 2.174e-01]
leoprint:  79%|#######8  | 1895/2400 [55:45<27:59,  3.33s/it, lr: 5.0e-05 loss: 3.335e-01]
leoprint:  79%|#######8  | 1895/2400 [55:45<27:59,  3.33s/it, lr: 5.0e-05 loss: 3.335e-01]
leoprint:  79%|#######9  | 1896/2400 [55:45<28:22,  3.38s/it, lr: 5.0e-05 loss: 3.335e-01]
leoprint:  79%|#######9  | 1896/2400 [55:45<28:22,  3.38s/it, lr: 5.0e-05 loss: 3.335e-01]
leoprint:  79%|#######9  | 1896/2400 [55:48<28:22,  3.38s/it, lr: 5.0e-05 loss: 3.331e-01]
leoprint:  79%|#######9  | 1896/2400 [55:48<28:22,  3.38s/it, lr: 5.0e-05 loss: 3.331e-01]
leoprint:  79%|#######9  | 1897/2400 [55:48<28:37,  3.41s/it, lr: 5.0e-05 loss: 3.331e-01]
leoprint:  79%|#######9  | 1897/2400 [55:48<28:37,  3.41s/it, lr: 5.0e-05 loss: 3.331e-01]
leoprint:  79%|#######9  | 1897/2400 [55:52<28:37,  3.41s/it, lr: 5.0e-05 loss: 2.188e-01]
leoprint:  79%|#######9  | 1897/2400 [55:52<28:37,  3.41s/it, lr: 5.0e-05 loss: 2.188e-01]
leoprint:  79%|#######9  | 1898/2400 [55:52<29:00,  3.47s/it, lr: 5.0e-05 loss: 2.188e-01]
leoprint:  79%|#######9  | 1898/2400 [55:52<29:00,  3.47s/it, lr: 5.0e-05 loss: 2.188e-01]
leoprint:  79%|#######9  | 1898/2400 [55:55<29:00,  3.47s/it, lr: 5.0e-05 loss: 3.457e-01]
leoprint:  79%|#######9  | 1898/2400 [55:55<29:00,  3.47s/it, lr: 5.0e-05 loss: 3.457e-01]
leoprint:  79%|#######9  | 1899/2400 [55:55<29:02,  3.48s/it, lr: 5.0e-05 loss: 3.457e-01]
leoprint:  79%|#######9  | 1899/2400 [55:55<29:02,  3.48s/it, lr: 5.0e-05 loss: 3.457e-01]
leoprint:  79%|#######9  | 1899/2400 [55:59<29:02,  3.48s/it, lr: 5.0e-05 loss: 2.789e-01]
leoprint:  79%|#######9  | 1899/2400 [55:59<29:02,  3.48s/it, lr: 5.0e-05 loss: 2.789e-01]
leoprint:  79%|#######9  | 1900/2400 [56:02<28:59,  3.48s/it, lr: 5.0e-05 loss: 2.510e-01]
leoprint:  79%|#######9  | 1900/2400 [56:02<28:59,  3.48s/it, lr: 5.0e-05 loss: 2.510e-01]
leoprint:  79%|#######9  | 1901/2400 [56:02<22:21,  2.69s/it, lr: 5.0e-05 loss: 2.510e-01]
leoprint:  79%|#######9  | 1901/2400 [56:02<22:21,  2.69s/it, lr: 5.0e-05 loss: 2.510e-01]
leoprint:  79%|#######9  | 1901/2400 [56:06<22:21,  2.69s/it, lr: 5.0e-05 loss: 2.767e-01]
leoprint:  79%|#######9  | 1901/2400 [56:06<22:21,  2.69s/it, lr: 5.0e-05 loss: 2.767e-01]
leoprint:  79%|#######9  | 1902/2400 [56:06<23:58,  2.89s/it, lr: 5.0e-05 loss: 2.767e-01]
leoprint:  79%|#######9  | 1902/2400 [56:06<23:58,  2.89s/it, lr: 5.0e-05 loss: 2.767e-01]
leoprint:  79%|#######9  | 1902/2400 [56:10<23:58,  2.89s/it, lr: 5.0e-05 loss: 2.882e-01]
leoprint:  79%|#######9  | 1902/2400 [56:10<23:58,  2.89s/it, lr: 5.0e-05 loss: 2.882e-01]
leoprint:  79%|#######9  | 1903/2400 [56:10<25:15,  3.05s/it, lr: 5.0e-05 loss: 2.882e-01]
leoprint:  79%|#######9  | 1903/2400 [56:10<25:15,  3.05s/it, lr: 5.0e-05 loss: 2.882e-01]
leoprint:  79%|#######9  | 1903/2400 [56:13<25:15,  3.05s/it, lr: 5.0e-05 loss: 3.223e-01]
leoprint:  79%|#######9  | 1903/2400 [56:13<25:15,  3.05s/it, lr: 5.0e-05 loss: 3.223e-01]
leoprint:  79%|#######9  | 1904/2400 [56:13<26:46,  3.24s/it, lr: 5.0e-05 loss: 3.223e-01]
leoprint:  79%|#######9  | 1904/2400 [56:13<26:46,  3.24s/it, lr: 5.0e-05 loss: 3.223e-01]
leoprint:  79%|#######9  | 1904/2400 [56:17<26:46,  3.24s/it, lr: 5.0e-05 loss: 3.285e-01]
leoprint:  79%|#######9  | 1904/2400 [56:17<26:46,  3.24s/it, lr: 5.0e-05 loss: 3.285e-01]
leoprint:  79%|#######9  | 1905/2400 [56:17<27:19,  3.31s/it, lr: 5.0e-05 loss: 3.285e-01]
leoprint:  79%|#######9  | 1905/2400 [56:17<27:19,  3.31s/it, lr: 5.0e-05 loss: 3.285e-01]
leoprint:  79%|#######9  | 1905/2400 [56:20<27:19,  3.31s/it, lr: 5.0e-05 loss: 2.530e-01]
leoprint:  79%|#######9  | 1905/2400 [56:20<27:19,  3.31s/it, lr: 5.0e-05 loss: 2.530e-01]
leoprint:  79%|#######9  | 1906/2400 [56:20<27:43,  3.37s/it, lr: 5.0e-05 loss: 2.530e-01]
leoprint:  79%|#######9  | 1906/2400 [56:20<27:43,  3.37s/it, lr: 5.0e-05 loss: 2.530e-01]
leoprint:  79%|#######9  | 1906/2400 [56:24<27:43,  3.37s/it, lr: 5.0e-05 loss: 2.953e-01]
leoprint:  79%|#######9  | 1906/2400 [56:24<27:43,  3.37s/it, lr: 5.0e-05 loss: 2.953e-01]
leoprint:  79%|#######9  | 1907/2400 [56:24<27:58,  3.40s/it, lr: 5.0e-05 loss: 2.953e-01]
leoprint:  79%|#######9  | 1907/2400 [56:24<27:58,  3.40s/it, lr: 5.0e-05 loss: 2.953e-01]
leoprint:  79%|#######9  | 1907/2400 [56:27<27:58,  3.40s/it, lr: 5.0e-05 loss: 2.314e-01]
leoprint:  79%|#######9  | 1907/2400 [56:27<27:58,  3.40s/it, lr: 5.0e-05 loss: 2.314e-01]
leoprint:  80%|#######9  | 1908/2400 [56:27<28:09,  3.43s/it, lr: 5.0e-05 loss: 2.314e-01]
leoprint:  80%|#######9  | 1908/2400 [56:27<28:09,  3.43s/it, lr: 5.0e-05 loss: 2.314e-01]
leoprint:  80%|#######9  | 1908/2400 [56:31<28:09,  3.43s/it, lr: 5.0e-05 loss: 2.950e-01]
leoprint:  80%|#######9  | 1908/2400 [56:31<28:09,  3.43s/it, lr: 5.0e-05 loss: 2.950e-01]
leoprint:  80%|#######9  | 1909/2400 [56:31<28:32,  3.49s/it, lr: 5.0e-05 loss: 2.950e-01]
leoprint:  80%|#######9  | 1909/2400 [56:31<28:32,  3.49s/it, lr: 5.0e-05 loss: 2.950e-01]
leoprint:  80%|#######9  | 1909/2400 [56:35<28:32,  3.49s/it, lr: 5.0e-05 loss: 2.352e-01]
leoprint:  80%|#######9  | 1909/2400 [56:35<28:32,  3.49s/it, lr: 5.0e-05 loss: 2.352e-01]
leoprint:  80%|#######9  | 1910/2400 [56:38<28:29,  3.49s/it, lr: 5.0e-05 loss: 3.685e-01]
leoprint:  80%|#######9  | 1910/2400 [56:38<28:29,  3.49s/it, lr: 5.0e-05 loss: 3.685e-01]
leoprint:  80%|#######9  | 1911/2400 [56:38<21:57,  2.69s/it, lr: 5.0e-05 loss: 3.685e-01]
leoprint:  80%|#######9  | 1911/2400 [56:38<21:57,  2.69s/it, lr: 5.0e-05 loss: 3.685e-01]
leoprint:  80%|#######9  | 1911/2400 [56:42<21:57,  2.69s/it, lr: 5.0e-05 loss: 2.917e-01]
leoprint:  80%|#######9  | 1911/2400 [56:42<21:57,  2.69s/it, lr: 5.0e-05 loss: 2.917e-01]
leoprint:  80%|#######9  | 1912/2400 [56:42<23:46,  2.92s/it, lr: 5.0e-05 loss: 2.917e-01]
leoprint:  80%|#######9  | 1912/2400 [56:42<23:46,  2.92s/it, lr: 5.0e-05 loss: 2.917e-01]
leoprint:  80%|#######9  | 1912/2400 [56:45<23:46,  2.92s/it, lr: 5.0e-05 loss: 2.136e-01]
leoprint:  80%|#######9  | 1912/2400 [56:45<23:46,  2.92s/it, lr: 5.0e-05 loss: 2.136e-01]
leoprint:  80%|#######9  | 1913/2400 [56:45<24:57,  3.08s/it, lr: 5.0e-05 loss: 2.136e-01]
leoprint:  80%|#######9  | 1913/2400 [56:45<24:57,  3.08s/it, lr: 5.0e-05 loss: 2.136e-01]
leoprint:  80%|#######9  | 1913/2400 [56:49<24:57,  3.08s/it, lr: 5.0e-05 loss: 2.674e-01]
leoprint:  80%|#######9  | 1913/2400 [56:49<24:57,  3.08s/it, lr: 5.0e-05 loss: 2.674e-01]
leoprint:  80%|#######9  | 1914/2400 [56:49<26:07,  3.22s/it, lr: 5.0e-05 loss: 2.674e-01]
leoprint:  80%|#######9  | 1914/2400 [56:49<26:07,  3.22s/it, lr: 5.0e-05 loss: 2.674e-01]
leoprint:  80%|#######9  | 1914/2400 [56:53<26:07,  3.22s/it, lr: 5.0e-05 loss: 2.569e-01]
leoprint:  80%|#######9  | 1914/2400 [56:53<26:07,  3.22s/it, lr: 5.0e-05 loss: 2.569e-01]
leoprint:  80%|#######9  | 1915/2400 [56:53<27:06,  3.35s/it, lr: 5.0e-05 loss: 2.569e-01]
leoprint:  80%|#######9  | 1915/2400 [56:53<27:06,  3.35s/it, lr: 5.0e-05 loss: 2.569e-01]
leoprint:  80%|#######9  | 1915/2400 [56:56<27:06,  3.35s/it, lr: 5.0e-05 loss: 2.834e-01]
leoprint:  80%|#######9  | 1915/2400 [56:56<27:06,  3.35s/it, lr: 5.0e-05 loss: 2.834e-01]
leoprint:  80%|#######9  | 1916/2400 [56:56<27:40,  3.43s/it, lr: 5.0e-05 loss: 2.834e-01]
leoprint:  80%|#######9  | 1916/2400 [56:56<27:40,  3.43s/it, lr: 5.0e-05 loss: 2.834e-01]
leoprint:  80%|#######9  | 1916/2400 [57:00<27:40,  3.43s/it, lr: 5.0e-05 loss: 3.733e-01]
leoprint:  80%|#######9  | 1916/2400 [57:00<27:40,  3.43s/it, lr: 5.0e-05 loss: 3.733e-01]
leoprint:  80%|#######9  | 1917/2400 [57:00<27:46,  3.45s/it, lr: 5.0e-05 loss: 3.733e-01]
leoprint:  80%|#######9  | 1917/2400 [57:00<27:46,  3.45s/it, lr: 5.0e-05 loss: 3.733e-01]
leoprint:  80%|#######9  | 1917/2400 [57:03<27:46,  3.45s/it, lr: 5.0e-05 loss: 3.515e-01]
leoprint:  80%|#######9  | 1917/2400 [57:03<27:46,  3.45s/it, lr: 5.0e-05 loss: 3.515e-01]
leoprint:  80%|#######9  | 1918/2400 [57:03<27:50,  3.47s/it, lr: 5.0e-05 loss: 3.515e-01]
leoprint:  80%|#######9  | 1918/2400 [57:03<27:50,  3.47s/it, lr: 5.0e-05 loss: 3.515e-01]
leoprint:  80%|#######9  | 1918/2400 [57:07<27:50,  3.47s/it, lr: 5.0e-05 loss: 3.558e-01]
leoprint:  80%|#######9  | 1918/2400 [57:07<27:50,  3.47s/it, lr: 5.0e-05 loss: 3.558e-01]
leoprint:  80%|#######9  | 1919/2400 [57:07<27:52,  3.48s/it, lr: 5.0e-05 loss: 3.558e-01]
leoprint:  80%|#######9  | 1919/2400 [57:07<27:52,  3.48s/it, lr: 5.0e-05 loss: 3.558e-01]
leoprint:  80%|#######9  | 1919/2400 [57:10<27:52,  3.48s/it, lr: 5.0e-05 loss: 2.396e-01]
leoprint:  80%|#######9  | 1919/2400 [57:10<27:52,  3.48s/it, lr: 5.0e-05 loss: 2.396e-01]
leoprint:  80%|########  | 1920/2400 [57:14<27:48,  3.48s/it, lr: 5.0e-05 loss: 3.305e-01]
leoprint:  80%|########  | 1920/2400 [57:14<27:48,  3.48s/it, lr: 5.0e-05 loss: 3.305e-01]
leoprint:  80%|########  | 1921/2400 [57:14<21:35,  2.70s/it, lr: 5.0e-05 loss: 3.305e-01]
leoprint:  80%|########  | 1921/2400 [57:14<21:35,  2.70s/it, lr: 5.0e-05 loss: 3.305e-01]
leoprint:  80%|########  | 1921/2400 [57:18<21:35,  2.70s/it, lr: 5.0e-05 loss: 2.444e-01]
leoprint:  80%|########  | 1921/2400 [57:18<21:35,  2.70s/it, lr: 5.0e-05 loss: 2.444e-01]
leoprint:  80%|########  | 1922/2400 [57:18<23:06,  2.90s/it, lr: 5.0e-05 loss: 2.444e-01]
leoprint:  80%|########  | 1922/2400 [57:18<23:06,  2.90s/it, lr: 5.0e-05 loss: 2.444e-01]
leoprint:  80%|########  | 1922/2400 [57:21<23:06,  2.90s/it, lr: 5.0e-05 loss: 2.915e-01]
leoprint:  80%|########  | 1922/2400 [57:21<23:06,  2.90s/it, lr: 5.0e-05 loss: 2.915e-01]
leoprint:  80%|########  | 1923/2400 [57:21<24:18,  3.06s/it, lr: 5.0e-05 loss: 2.915e-01]
leoprint:  80%|########  | 1923/2400 [57:21<24:18,  3.06s/it, lr: 5.0e-05 loss: 2.915e-01]
leoprint:  80%|########  | 1923/2400 [57:25<24:18,  3.06s/it, lr: 5.0e-05 loss: 3.643e-01]
leoprint:  80%|########  | 1923/2400 [57:25<24:18,  3.06s/it, lr: 5.0e-05 loss: 3.643e-01]
leoprint:  80%|########  | 1924/2400 [57:25<25:14,  3.18s/it, lr: 5.0e-05 loss: 3.643e-01]
leoprint:  80%|########  | 1924/2400 [57:25<25:14,  3.18s/it, lr: 5.0e-05 loss: 3.643e-01]
leoprint:  80%|########  | 1924/2400 [57:28<25:14,  3.18s/it, lr: 5.0e-05 loss: 3.557e-01]
leoprint:  80%|########  | 1924/2400 [57:28<25:14,  3.18s/it, lr: 5.0e-05 loss: 3.557e-01]
leoprint:  80%|########  | 1925/2400 [57:28<25:54,  3.27s/it, lr: 5.0e-05 loss: 3.557e-01]
leoprint:  80%|########  | 1925/2400 [57:28<25:54,  3.27s/it, lr: 5.0e-05 loss: 3.557e-01]
leoprint:  80%|########  | 1925/2400 [57:32<25:54,  3.27s/it, lr: 5.0e-05 loss: 2.608e-01]
leoprint:  80%|########  | 1925/2400 [57:32<25:54,  3.27s/it, lr: 5.0e-05 loss: 2.608e-01]
leoprint:  80%|########  | 1926/2400 [57:32<26:23,  3.34s/it, lr: 5.0e-05 loss: 2.608e-01]
leoprint:  80%|########  | 1926/2400 [57:32<26:23,  3.34s/it, lr: 5.0e-05 loss: 2.608e-01]
leoprint:  80%|########  | 1926/2400 [57:35<26:23,  3.34s/it, lr: 5.0e-05 loss: 2.577e-01]
leoprint:  80%|########  | 1926/2400 [57:35<26:23,  3.34s/it, lr: 5.0e-05 loss: 2.577e-01]
leoprint:  80%|########  | 1927/2400 [57:35<27:16,  3.46s/it, lr: 5.0e-05 loss: 2.577e-01]
leoprint:  80%|########  | 1927/2400 [57:35<27:16,  3.46s/it, lr: 5.0e-05 loss: 2.577e-01]
leoprint:  80%|########  | 1927/2400 [57:39<27:16,  3.46s/it, lr: 5.0e-05 loss: 2.826e-01]
leoprint:  80%|########  | 1927/2400 [57:39<27:16,  3.46s/it, lr: 5.0e-05 loss: 2.826e-01]
leoprint:  80%|########  | 1928/2400 [57:39<27:20,  3.48s/it, lr: 5.0e-05 loss: 2.826e-01]
leoprint:  80%|########  | 1928/2400 [57:39<27:20,  3.48s/it, lr: 5.0e-05 loss: 2.826e-01]
leoprint:  80%|########  | 1928/2400 [57:42<27:20,  3.48s/it, lr: 5.0e-05 loss: 3.232e-01]
leoprint:  80%|########  | 1928/2400 [57:42<27:20,  3.48s/it, lr: 5.0e-05 loss: 3.232e-01]
leoprint:  80%|########  | 1929/2400 [57:42<27:19,  3.48s/it, lr: 5.0e-05 loss: 3.232e-01]
leoprint:  80%|########  | 1929/2400 [57:42<27:19,  3.48s/it, lr: 5.0e-05 loss: 3.232e-01]
leoprint:  80%|########  | 1929/2400 [57:46<27:19,  3.48s/it, lr: 5.0e-05 loss: 2.926e-01]
leoprint:  80%|########  | 1929/2400 [57:46<27:19,  3.48s/it, lr: 5.0e-05 loss: 2.926e-01]
leoprint:  80%|########  | 1930/2400 [57:50<27:16,  3.48s/it, lr: 5.0e-05 loss: 3.193e-01]
leoprint:  80%|########  | 1930/2400 [57:50<27:16,  3.48s/it, lr: 5.0e-05 loss: 3.193e-01]
leoprint:  80%|########  | 1931/2400 [57:50<21:15,  2.72s/it, lr: 5.0e-05 loss: 3.193e-01]
leoprint:  80%|########  | 1931/2400 [57:50<21:15,  2.72s/it, lr: 5.0e-05 loss: 3.193e-01]
leoprint:  80%|########  | 1931/2400 [57:53<21:15,  2.72s/it, lr: 5.0e-05 loss: 2.160e-01]
leoprint:  80%|########  | 1931/2400 [57:53<21:15,  2.72s/it, lr: 5.0e-05 loss: 2.160e-01]
leoprint:  80%|########  | 1932/2400 [57:53<22:56,  2.94s/it, lr: 5.0e-05 loss: 2.160e-01]
leoprint:  80%|########  | 1932/2400 [57:53<22:56,  2.94s/it, lr: 5.0e-05 loss: 2.160e-01]
leoprint:  80%|########  | 1932/2400 [57:57<22:56,  2.94s/it, lr: 5.0e-05 loss: 2.711e-01]
leoprint:  80%|########  | 1932/2400 [57:57<22:56,  2.94s/it, lr: 5.0e-05 loss: 2.711e-01]
leoprint:  81%|########  | 1933/2400 [57:57<24:18,  3.12s/it, lr: 5.0e-05 loss: 2.711e-01]
leoprint:  81%|########  | 1933/2400 [57:57<24:18,  3.12s/it, lr: 5.0e-05 loss: 2.711e-01]
leoprint:  81%|########  | 1933/2400 [58:00<24:18,  3.12s/it, lr: 5.0e-05 loss: 2.187e-01]
leoprint:  81%|########  | 1933/2400 [58:00<24:18,  3.12s/it, lr: 5.0e-05 loss: 2.187e-01]
leoprint:  81%|########  | 1934/2400 [58:00<25:04,  3.23s/it, lr: 5.0e-05 loss: 2.187e-01]
leoprint:  81%|########  | 1934/2400 [58:00<25:04,  3.23s/it, lr: 5.0e-05 loss: 2.187e-01]
leoprint:  81%|########  | 1934/2400 [58:04<25:04,  3.23s/it, lr: 5.0e-05 loss: 2.116e-01]
leoprint:  81%|########  | 1934/2400 [58:04<25:04,  3.23s/it, lr: 5.0e-05 loss: 2.116e-01]
leoprint:  81%|########  | 1935/2400 [58:04<25:53,  3.34s/it, lr: 5.0e-05 loss: 2.116e-01]
leoprint:  81%|########  | 1935/2400 [58:04<25:53,  3.34s/it, lr: 5.0e-05 loss: 2.116e-01]
leoprint:  81%|########  | 1935/2400 [58:08<25:53,  3.34s/it, lr: 5.0e-05 loss: 2.813e-01]
leoprint:  81%|########  | 1935/2400 [58:08<25:53,  3.34s/it, lr: 5.0e-05 loss: 2.813e-01]
leoprint:  81%|########  | 1936/2400 [58:08<26:12,  3.39s/it, lr: 5.0e-05 loss: 2.813e-01]
leoprint:  81%|########  | 1936/2400 [58:08<26:12,  3.39s/it, lr: 5.0e-05 loss: 2.813e-01]
leoprint:  81%|########  | 1936/2400 [58:11<26:12,  3.39s/it, lr: 5.0e-05 loss: 2.792e-01]
leoprint:  81%|########  | 1936/2400 [58:11<26:12,  3.39s/it, lr: 5.0e-05 loss: 2.792e-01]
leoprint:  81%|########  | 1937/2400 [58:11<26:25,  3.42s/it, lr: 5.0e-05 loss: 2.792e-01]
leoprint:  81%|########  | 1937/2400 [58:11<26:25,  3.42s/it, lr: 5.0e-05 loss: 2.792e-01]
leoprint:  81%|########  | 1937/2400 [58:15<26:25,  3.42s/it, lr: 5.0e-05 loss: 2.605e-01]
leoprint:  81%|########  | 1937/2400 [58:15<26:25,  3.42s/it, lr: 5.0e-05 loss: 2.605e-01]
leoprint:  81%|########  | 1938/2400 [58:15<27:11,  3.53s/it, lr: 5.0e-05 loss: 2.605e-01]
leoprint:  81%|########  | 1938/2400 [58:15<27:11,  3.53s/it, lr: 5.0e-05 loss: 2.605e-01]
leoprint:  81%|########  | 1938/2400 [58:19<27:11,  3.53s/it, lr: 5.0e-05 loss: 3.024e-01]
leoprint:  81%|########  | 1938/2400 [58:19<27:11,  3.53s/it, lr: 5.0e-05 loss: 3.024e-01]
leoprint:  81%|########  | 1939/2400 [58:19<27:05,  3.53s/it, lr: 5.0e-05 loss: 3.024e-01]
leoprint:  81%|########  | 1939/2400 [58:19<27:05,  3.53s/it, lr: 5.0e-05 loss: 3.024e-01]
leoprint:  81%|########  | 1939/2400 [58:22<27:05,  3.53s/it, lr: 5.0e-05 loss: 3.213e-01]
leoprint:  81%|########  | 1939/2400 [58:22<27:05,  3.53s/it, lr: 5.0e-05 loss: 3.213e-01]
leoprint:  81%|########  | 1940/2400 [58:26<27:01,  3.53s/it, lr: 5.0e-05 loss: 3.519e-01]
leoprint:  81%|########  | 1940/2400 [58:26<27:01,  3.53s/it, lr: 5.0e-05 loss: 3.519e-01]
leoprint:  81%|########  | 1941/2400 [58:26<20:46,  2.71s/it, lr: 5.0e-05 loss: 3.519e-01]
leoprint:  81%|########  | 1941/2400 [58:26<20:46,  2.71s/it, lr: 5.0e-05 loss: 3.519e-01]
leoprint:  81%|########  | 1941/2400 [58:29<20:46,  2.71s/it, lr: 5.0e-05 loss: 3.288e-01]
leoprint:  81%|########  | 1941/2400 [58:29<20:46,  2.71s/it, lr: 5.0e-05 loss: 3.288e-01]
leoprint:  81%|########  | 1942/2400 [58:29<22:12,  2.91s/it, lr: 5.0e-05 loss: 3.288e-01]
leoprint:  81%|########  | 1942/2400 [58:29<22:12,  2.91s/it, lr: 5.0e-05 loss: 3.288e-01]
leoprint:  81%|########  | 1942/2400 [58:33<22:12,  2.91s/it, lr: 5.0e-05 loss: 3.624e-01]
leoprint:  81%|########  | 1942/2400 [58:33<22:12,  2.91s/it, lr: 5.0e-05 loss: 3.624e-01]
leoprint:  81%|########  | 1943/2400 [58:33<23:21,  3.07s/it, lr: 5.0e-05 loss: 3.624e-01]
leoprint:  81%|########  | 1943/2400 [58:33<23:21,  3.07s/it, lr: 5.0e-05 loss: 3.624e-01]
leoprint:  81%|########  | 1943/2400 [58:36<23:21,  3.07s/it, lr: 5.0e-05 loss: 2.477e-01]
leoprint:  81%|########  | 1943/2400 [58:36<23:21,  3.07s/it, lr: 5.0e-05 loss: 2.477e-01]
leoprint:  81%|########1 | 1944/2400 [58:36<24:37,  3.24s/it, lr: 5.0e-05 loss: 2.477e-01]
leoprint:  81%|########1 | 1944/2400 [58:36<24:37,  3.24s/it, lr: 5.0e-05 loss: 2.477e-01]
leoprint:  81%|########1 | 1944/2400 [58:40<24:37,  3.24s/it, lr: 5.0e-05 loss: 2.775e-01]
leoprint:  81%|########1 | 1944/2400 [58:40<24:37,  3.24s/it, lr: 5.0e-05 loss: 2.775e-01]
leoprint:  81%|########1 | 1945/2400 [58:40<25:06,  3.31s/it, lr: 5.0e-05 loss: 2.775e-01]
leoprint:  81%|########1 | 1945/2400 [58:40<25:06,  3.31s/it, lr: 5.0e-05 loss: 2.775e-01]
leoprint:  81%|########1 | 1945/2400 [58:43<25:06,  3.31s/it, lr: 5.0e-05 loss: 3.992e-01]
leoprint:  81%|########1 | 1945/2400 [58:43<25:06,  3.31s/it, lr: 5.0e-05 loss: 3.992e-01]
leoprint:  81%|########1 | 1946/2400 [58:43<25:28,  3.37s/it, lr: 5.0e-05 loss: 3.992e-01]
leoprint:  81%|########1 | 1946/2400 [58:43<25:28,  3.37s/it, lr: 5.0e-05 loss: 3.992e-01]
leoprint:  81%|########1 | 1946/2400 [58:47<25:28,  3.37s/it, lr: 5.0e-05 loss: 2.859e-01]
leoprint:  81%|########1 | 1946/2400 [58:47<25:28,  3.37s/it, lr: 5.0e-05 loss: 2.859e-01]
leoprint:  81%|########1 | 1947/2400 [58:47<25:58,  3.44s/it, lr: 5.0e-05 loss: 2.859e-01]
leoprint:  81%|########1 | 1947/2400 [58:47<25:58,  3.44s/it, lr: 5.0e-05 loss: 2.859e-01]
leoprint:  81%|########1 | 1947/2400 [58:50<25:58,  3.44s/it, lr: 5.0e-05 loss: 3.707e-01]
leoprint:  81%|########1 | 1947/2400 [58:50<25:58,  3.44s/it, lr: 5.0e-05 loss: 3.707e-01]
leoprint:  81%|########1 | 1948/2400 [58:50<26:04,  3.46s/it, lr: 5.0e-05 loss: 3.707e-01]
leoprint:  81%|########1 | 1948/2400 [58:50<26:04,  3.46s/it, lr: 5.0e-05 loss: 3.707e-01]
leoprint:  81%|########1 | 1948/2400 [58:54<26:04,  3.46s/it, lr: 5.0e-05 loss: 2.829e-01]
leoprint:  81%|########1 | 1948/2400 [58:54<26:04,  3.46s/it, lr: 5.0e-05 loss: 2.829e-01]
leoprint:  81%|########1 | 1949/2400 [58:54<26:23,  3.51s/it, lr: 5.0e-05 loss: 2.829e-01]
leoprint:  81%|########1 | 1949/2400 [58:54<26:23,  3.51s/it, lr: 5.0e-05 loss: 2.829e-01]
leoprint:  81%|########1 | 1949/2400 [58:58<26:23,  3.51s/it, lr: 5.0e-05 loss: 3.623e-01]
leoprint:  81%|########1 | 1949/2400 [58:58<26:23,  3.51s/it, lr: 5.0e-05 loss: 3.623e-01]
leoprint:  81%|########1 | 1950/2400 [59:01<26:19,  3.51s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  81%|########1 | 1950/2400 [59:01<26:19,  3.51s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  81%|########1 | 1951/2400 [59:01<20:27,  2.73s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  81%|########1 | 1951/2400 [59:01<20:27,  2.73s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  81%|########1 | 1951/2400 [59:05<20:27,  2.73s/it, lr: 5.0e-05 loss: 3.783e-01]
leoprint:  81%|########1 | 1951/2400 [59:05<20:27,  2.73s/it, lr: 5.0e-05 loss: 3.783e-01]
leoprint:  81%|########1 | 1952/2400 [59:05<21:49,  2.92s/it, lr: 5.0e-05 loss: 3.783e-01]
leoprint:  81%|########1 | 1952/2400 [59:05<21:49,  2.92s/it, lr: 5.0e-05 loss: 3.783e-01]
leoprint:  81%|########1 | 1952/2400 [59:08<21:49,  2.92s/it, lr: 5.0e-05 loss: 3.903e-01]
leoprint:  81%|########1 | 1952/2400 [59:08<21:49,  2.92s/it, lr: 5.0e-05 loss: 3.903e-01]
leoprint:  81%|########1 | 1953/2400 [59:08<22:54,  3.08s/it, lr: 5.0e-05 loss: 3.903e-01]
leoprint:  81%|########1 | 1953/2400 [59:08<22:54,  3.08s/it, lr: 5.0e-05 loss: 3.903e-01]
leoprint:  81%|########1 | 1953/2400 [59:12<22:54,  3.08s/it, lr: 5.0e-05 loss: 3.348e-01]
leoprint:  81%|########1 | 1953/2400 [59:12<22:54,  3.08s/it, lr: 5.0e-05 loss: 3.348e-01]
leoprint:  81%|########1 | 1954/2400 [59:12<23:43,  3.19s/it, lr: 5.0e-05 loss: 3.348e-01]
leoprint:  81%|########1 | 1954/2400 [59:12<23:43,  3.19s/it, lr: 5.0e-05 loss: 3.348e-01]
leoprint:  81%|########1 | 1954/2400 [59:15<23:43,  3.19s/it, lr: 5.0e-05 loss: 2.716e-01]
leoprint:  81%|########1 | 1954/2400 [59:15<23:43,  3.19s/it, lr: 5.0e-05 loss: 2.716e-01]
leoprint:  81%|########1 | 1955/2400 [59:15<24:19,  3.28s/it, lr: 5.0e-05 loss: 2.716e-01]
leoprint:  81%|########1 | 1955/2400 [59:15<24:19,  3.28s/it, lr: 5.0e-05 loss: 2.716e-01]
leoprint:  81%|########1 | 1955/2400 [59:19<24:19,  3.28s/it, lr: 5.0e-05 loss: 2.792e-01]
leoprint:  81%|########1 | 1955/2400 [59:19<24:19,  3.28s/it, lr: 5.0e-05 loss: 2.792e-01]
leoprint:  82%|########1 | 1956/2400 [59:19<25:01,  3.38s/it, lr: 5.0e-05 loss: 2.792e-01]
leoprint:  82%|########1 | 1956/2400 [59:19<25:01,  3.38s/it, lr: 5.0e-05 loss: 2.792e-01]
leoprint:  82%|########1 | 1956/2400 [59:23<25:01,  3.38s/it, lr: 5.0e-05 loss: 2.200e-01]
leoprint:  82%|########1 | 1956/2400 [59:23<25:01,  3.38s/it, lr: 5.0e-05 loss: 2.200e-01]
leoprint:  82%|########1 | 1957/2400 [59:23<25:14,  3.42s/it, lr: 5.0e-05 loss: 2.200e-01]
leoprint:  82%|########1 | 1957/2400 [59:23<25:14,  3.42s/it, lr: 5.0e-05 loss: 2.200e-01]
leoprint:  82%|########1 | 1957/2400 [59:26<25:14,  3.42s/it, lr: 5.0e-05 loss: 3.659e-01]
leoprint:  82%|########1 | 1957/2400 [59:26<25:14,  3.42s/it, lr: 5.0e-05 loss: 3.659e-01]
leoprint:  82%|########1 | 1958/2400 [59:26<25:22,  3.44s/it, lr: 5.0e-05 loss: 3.659e-01]
leoprint:  82%|########1 | 1958/2400 [59:26<25:22,  3.44s/it, lr: 5.0e-05 loss: 3.659e-01]
leoprint:  82%|########1 | 1958/2400 [59:30<25:22,  3.44s/it, lr: 5.0e-05 loss: 2.479e-01]
leoprint:  82%|########1 | 1958/2400 [59:30<25:22,  3.44s/it, lr: 5.0e-05 loss: 2.479e-01]
leoprint:  82%|########1 | 1959/2400 [59:30<25:42,  3.50s/it, lr: 5.0e-05 loss: 2.479e-01]
leoprint:  82%|########1 | 1959/2400 [59:30<25:42,  3.50s/it, lr: 5.0e-05 loss: 2.479e-01]
leoprint:  82%|########1 | 1959/2400 [59:33<25:42,  3.50s/it, lr: 5.0e-05 loss: 3.215e-01]
leoprint:  82%|########1 | 1959/2400 [59:33<25:42,  3.50s/it, lr: 5.0e-05 loss: 3.215e-01]
leoprint:  82%|########1 | 1960/2400 [59:37<25:39,  3.50s/it, lr: 5.0e-05 loss: 2.735e-01]
leoprint:  82%|########1 | 1960/2400 [59:37<25:39,  3.50s/it, lr: 5.0e-05 loss: 2.735e-01]
leoprint:  82%|########1 | 1961/2400 [59:37<20:10,  2.76s/it, lr: 5.0e-05 loss: 2.735e-01]
leoprint:  82%|########1 | 1961/2400 [59:37<20:10,  2.76s/it, lr: 5.0e-05 loss: 2.735e-01]
leoprint:  82%|########1 | 1961/2400 [59:41<20:10,  2.76s/it, lr: 5.0e-05 loss: 2.659e-01]
leoprint:  82%|########1 | 1961/2400 [59:41<20:10,  2.76s/it, lr: 5.0e-05 loss: 2.659e-01]
leoprint:  82%|########1 | 1962/2400 [59:41<21:27,  2.94s/it, lr: 5.0e-05 loss: 2.659e-01]
leoprint:  82%|########1 | 1962/2400 [59:41<21:27,  2.94s/it, lr: 5.0e-05 loss: 2.659e-01]
leoprint:  82%|########1 | 1962/2400 [59:44<21:27,  2.94s/it, lr: 5.0e-05 loss: 2.862e-01]
leoprint:  82%|########1 | 1962/2400 [59:44<21:27,  2.94s/it, lr: 5.0e-05 loss: 2.862e-01]
leoprint:  82%|########1 | 1963/2400 [59:44<22:29,  3.09s/it, lr: 5.0e-05 loss: 2.862e-01]
leoprint:  82%|########1 | 1963/2400 [59:44<22:29,  3.09s/it, lr: 5.0e-05 loss: 2.862e-01]
leoprint:  82%|########1 | 1963/2400 [59:48<22:29,  3.09s/it, lr: 5.0e-05 loss: 3.120e-01]
leoprint:  82%|########1 | 1963/2400 [59:48<22:29,  3.09s/it, lr: 5.0e-05 loss: 3.120e-01]
leoprint:  82%|########1 | 1964/2400 [59:48<23:15,  3.20s/it, lr: 5.0e-05 loss: 3.120e-01]
leoprint:  82%|########1 | 1964/2400 [59:48<23:15,  3.20s/it, lr: 5.0e-05 loss: 3.120e-01]
leoprint:  82%|########1 | 1964/2400 [59:51<23:15,  3.20s/it, lr: 5.0e-05 loss: 2.957e-01]
leoprint:  82%|########1 | 1964/2400 [59:51<23:15,  3.20s/it, lr: 5.0e-05 loss: 2.957e-01]
leoprint:  82%|########1 | 1965/2400 [59:51<23:48,  3.28s/it, lr: 5.0e-05 loss: 2.957e-01]
leoprint:  82%|########1 | 1965/2400 [59:51<23:48,  3.28s/it, lr: 5.0e-05 loss: 2.957e-01]
leoprint:  82%|########1 | 1965/2400 [59:55<23:48,  3.28s/it, lr: 5.0e-05 loss: 3.769e-01]
leoprint:  82%|########1 | 1965/2400 [59:55<23:48,  3.28s/it, lr: 5.0e-05 loss: 3.769e-01]
leoprint:  82%|########1 | 1966/2400 [59:55<24:11,  3.34s/it, lr: 5.0e-05 loss: 3.769e-01]
leoprint:  82%|########1 | 1966/2400 [59:55<24:11,  3.34s/it, lr: 5.0e-05 loss: 3.769e-01]
leoprint:  82%|########1 | 1966/2400 [59:58<24:11,  3.34s/it, lr: 5.0e-05 loss: 2.652e-01]
leoprint:  82%|########1 | 1966/2400 [59:58<24:11,  3.34s/it, lr: 5.0e-05 loss: 2.652e-01]
leoprint:  82%|########1 | 1967/2400 [59:58<24:51,  3.44s/it, lr: 5.0e-05 loss: 2.652e-01]
leoprint:  82%|########1 | 1967/2400 [59:58<24:51,  3.44s/it, lr: 5.0e-05 loss: 2.652e-01]
leoprint:  82%|########1 | 1967/2400 [1:00:02<24:51,  3.44s/it, lr: 5.0e-05 loss: 2.450e-01]
leoprint:  82%|########1 | 1967/2400 [1:00:02<24:51,  3.44s/it, lr: 5.0e-05 loss: 2.450e-01]
leoprint:  82%|########2 | 1968/2400 [1:00:02<25:10,  3.50s/it, lr: 5.0e-05 loss: 2.450e-01]
leoprint:  82%|########2 | 1968/2400 [1:00:02<25:10,  3.50s/it, lr: 5.0e-05 loss: 2.450e-01]
leoprint:  82%|########2 | 1968/2400 [1:00:05<25:10,  3.50s/it, lr: 5.0e-05 loss: 3.113e-01]
leoprint:  82%|########2 | 1968/2400 [1:00:05<25:10,  3.50s/it, lr: 5.0e-05 loss: 3.113e-01]
leoprint:  82%|########2 | 1969/2400 [1:00:05<25:08,  3.50s/it, lr: 5.0e-05 loss: 3.113e-01]
leoprint:  82%|########2 | 1969/2400 [1:00:05<25:08,  3.50s/it, lr: 5.0e-05 loss: 3.113e-01]
leoprint:  82%|########2 | 1969/2400 [1:00:09<25:08,  3.50s/it, lr: 5.0e-05 loss: 2.589e-01]
leoprint:  82%|########2 | 1969/2400 [1:00:09<25:08,  3.50s/it, lr: 5.0e-05 loss: 2.589e-01]
leoprint:  82%|########2 | 1970/2400 [1:00:12<25:05,  3.50s/it, lr: 5.0e-05 loss: 2.376e-01]
leoprint:  82%|########2 | 1970/2400 [1:00:12<25:05,  3.50s/it, lr: 5.0e-05 loss: 2.376e-01]
leoprint:  82%|########2 | 1971/2400 [1:00:12<19:18,  2.70s/it, lr: 5.0e-05 loss: 2.376e-01]
leoprint:  82%|########2 | 1971/2400 [1:00:12<19:18,  2.70s/it, lr: 5.0e-05 loss: 2.376e-01]
leoprint:  82%|########2 | 1971/2400 [1:00:16<19:18,  2.70s/it, lr: 5.0e-05 loss: 2.371e-01]
leoprint:  82%|########2 | 1971/2400 [1:00:16<19:18,  2.70s/it, lr: 5.0e-05 loss: 2.371e-01]
leoprint:  82%|########2 | 1972/2400 [1:00:16<20:53,  2.93s/it, lr: 5.0e-05 loss: 2.371e-01]
leoprint:  82%|########2 | 1972/2400 [1:00:16<20:53,  2.93s/it, lr: 5.0e-05 loss: 2.371e-01]
leoprint:  82%|########2 | 1972/2400 [1:00:20<20:53,  2.93s/it, lr: 5.0e-05 loss: 3.602e-01]
leoprint:  82%|########2 | 1972/2400 [1:00:20<20:53,  2.93s/it, lr: 5.0e-05 loss: 3.602e-01]
leoprint:  82%|########2 | 1973/2400 [1:00:20<22:21,  3.14s/it, lr: 5.0e-05 loss: 3.602e-01]
leoprint:  82%|########2 | 1973/2400 [1:00:20<22:21,  3.14s/it, lr: 5.0e-05 loss: 3.602e-01]
leoprint:  82%|########2 | 1973/2400 [1:00:23<22:21,  3.14s/it, lr: 5.0e-05 loss: 2.888e-01]
leoprint:  82%|########2 | 1973/2400 [1:00:23<22:21,  3.14s/it, lr: 5.0e-05 loss: 2.888e-01]
leoprint:  82%|########2 | 1974/2400 [1:00:23<23:00,  3.24s/it, lr: 5.0e-05 loss: 2.888e-01]
leoprint:  82%|########2 | 1974/2400 [1:00:23<23:00,  3.24s/it, lr: 5.0e-05 loss: 2.888e-01]
leoprint:  82%|########2 | 1974/2400 [1:00:27<23:00,  3.24s/it, lr: 5.0e-05 loss: 2.802e-01]
leoprint:  82%|########2 | 1974/2400 [1:00:27<23:00,  3.24s/it, lr: 5.0e-05 loss: 2.802e-01]
leoprint:  82%|########2 | 1975/2400 [1:00:27<23:29,  3.32s/it, lr: 5.0e-05 loss: 2.802e-01]
leoprint:  82%|########2 | 1975/2400 [1:00:27<23:29,  3.32s/it, lr: 5.0e-05 loss: 2.802e-01]
leoprint:  82%|########2 | 1975/2400 [1:00:30<23:29,  3.32s/it, lr: 5.0e-05 loss: 2.273e-01]
leoprint:  82%|########2 | 1975/2400 [1:00:30<23:29,  3.32s/it, lr: 5.0e-05 loss: 2.273e-01]
leoprint:  82%|########2 | 1976/2400 [1:00:30<23:48,  3.37s/it, lr: 5.0e-05 loss: 2.273e-01]
leoprint:  82%|########2 | 1976/2400 [1:00:30<23:48,  3.37s/it, lr: 5.0e-05 loss: 2.273e-01]
leoprint:  82%|########2 | 1976/2400 [1:00:34<23:48,  3.37s/it, lr: 5.0e-05 loss: 3.161e-01]
leoprint:  82%|########2 | 1976/2400 [1:00:34<23:48,  3.37s/it, lr: 5.0e-05 loss: 3.161e-01]
leoprint:  82%|########2 | 1977/2400 [1:00:34<24:17,  3.45s/it, lr: 5.0e-05 loss: 3.161e-01]
leoprint:  82%|########2 | 1977/2400 [1:00:34<24:17,  3.45s/it, lr: 5.0e-05 loss: 3.161e-01]
leoprint:  82%|########2 | 1977/2400 [1:00:38<24:17,  3.45s/it, lr: 5.0e-05 loss: 2.726e-01]
leoprint:  82%|########2 | 1977/2400 [1:00:38<24:17,  3.45s/it, lr: 5.0e-05 loss: 2.726e-01]
leoprint:  82%|########2 | 1978/2400 [1:00:38<24:22,  3.47s/it, lr: 5.0e-05 loss: 2.726e-01]
leoprint:  82%|########2 | 1978/2400 [1:00:38<24:22,  3.47s/it, lr: 5.0e-05 loss: 2.726e-01]
leoprint:  82%|########2 | 1978/2400 [1:00:41<24:22,  3.47s/it, lr: 5.0e-05 loss: 2.559e-01]
leoprint:  82%|########2 | 1978/2400 [1:00:41<24:22,  3.47s/it, lr: 5.0e-05 loss: 2.559e-01]
leoprint:  82%|########2 | 1979/2400 [1:00:41<24:57,  3.56s/it, lr: 5.0e-05 loss: 2.559e-01]
leoprint:  82%|########2 | 1979/2400 [1:00:41<24:57,  3.56s/it, lr: 5.0e-05 loss: 2.559e-01]
leoprint:  82%|########2 | 1979/2400 [1:00:45<24:57,  3.56s/it, lr: 5.0e-05 loss: 2.899e-01]
leoprint:  82%|########2 | 1979/2400 [1:00:45<24:57,  3.56s/it, lr: 5.0e-05 loss: 2.899e-01]
leoprint:  82%|########2 | 1980/2400 [1:00:49<24:54,  3.56s/it, lr: 5.0e-05 loss: 2.584e-01]
leoprint:  82%|########2 | 1980/2400 [1:00:49<24:54,  3.56s/it, lr: 5.0e-05 loss: 2.584e-01]
leoprint:  83%|########2 | 1981/2400 [1:00:49<19:16,  2.76s/it, lr: 5.0e-05 loss: 2.584e-01]
leoprint:  83%|########2 | 1981/2400 [1:00:49<19:16,  2.76s/it, lr: 5.0e-05 loss: 2.584e-01]
leoprint:  83%|########2 | 1981/2400 [1:00:52<19:16,  2.76s/it, lr: 5.0e-05 loss: 3.429e-01]
leoprint:  83%|########2 | 1981/2400 [1:00:52<19:16,  2.76s/it, lr: 5.0e-05 loss: 3.429e-01]
leoprint:  83%|########2 | 1982/2400 [1:00:52<20:30,  2.94s/it, lr: 5.0e-05 loss: 3.429e-01]
leoprint:  83%|########2 | 1982/2400 [1:00:52<20:30,  2.94s/it, lr: 5.0e-05 loss: 3.429e-01]
leoprint:  83%|########2 | 1982/2400 [1:00:56<20:30,  2.94s/it, lr: 5.0e-05 loss: 1.926e-01]
leoprint:  83%|########2 | 1982/2400 [1:00:56<20:30,  2.94s/it, lr: 5.0e-05 loss: 1.926e-01]
leoprint:  83%|########2 | 1983/2400 [1:00:56<21:44,  3.13s/it, lr: 5.0e-05 loss: 1.926e-01]
leoprint:  83%|########2 | 1983/2400 [1:00:56<21:44,  3.13s/it, lr: 5.0e-05 loss: 1.926e-01]
leoprint:  83%|########2 | 1983/2400 [1:00:59<21:44,  3.13s/it, lr: 5.0e-05 loss: 3.301e-01]
leoprint:  83%|########2 | 1983/2400 [1:00:59<21:44,  3.13s/it, lr: 5.0e-05 loss: 3.301e-01]
leoprint:  83%|########2 | 1984/2400 [1:00:59<22:32,  3.25s/it, lr: 5.0e-05 loss: 3.301e-01]
leoprint:  83%|########2 | 1984/2400 [1:00:59<22:32,  3.25s/it, lr: 5.0e-05 loss: 3.301e-01]
leoprint:  83%|########2 | 1984/2400 [1:01:03<22:32,  3.25s/it, lr: 5.0e-05 loss: 1.954e-01]
leoprint:  83%|########2 | 1984/2400 [1:01:03<22:32,  3.25s/it, lr: 5.0e-05 loss: 1.954e-01]
leoprint:  83%|########2 | 1985/2400 [1:01:03<23:13,  3.36s/it, lr: 5.0e-05 loss: 1.954e-01]
leoprint:  83%|########2 | 1985/2400 [1:01:03<23:13,  3.36s/it, lr: 5.0e-05 loss: 1.954e-01]
leoprint:  83%|########2 | 1985/2400 [1:01:06<23:13,  3.36s/it, lr: 5.0e-05 loss: 3.672e-01]
leoprint:  83%|########2 | 1985/2400 [1:01:06<23:13,  3.36s/it, lr: 5.0e-05 loss: 3.672e-01]
leoprint:  83%|########2 | 1986/2400 [1:01:06<23:27,  3.40s/it, lr: 5.0e-05 loss: 3.672e-01]
leoprint:  83%|########2 | 1986/2400 [1:01:06<23:27,  3.40s/it, lr: 5.0e-05 loss: 3.672e-01]
leoprint:  83%|########2 | 1986/2400 [1:01:10<23:27,  3.40s/it, lr: 5.0e-05 loss: 2.952e-01]
leoprint:  83%|########2 | 1986/2400 [1:01:10<23:27,  3.40s/it, lr: 5.0e-05 loss: 2.952e-01]
leoprint:  83%|########2 | 1987/2400 [1:01:10<23:37,  3.43s/it, lr: 5.0e-05 loss: 2.952e-01]
leoprint:  83%|########2 | 1987/2400 [1:01:10<23:37,  3.43s/it, lr: 5.0e-05 loss: 2.952e-01]
leoprint:  83%|########2 | 1987/2400 [1:01:13<23:37,  3.43s/it, lr: 5.0e-05 loss: 4.158e-01]
leoprint:  83%|########2 | 1987/2400 [1:01:13<23:37,  3.43s/it, lr: 5.0e-05 loss: 4.158e-01]
leoprint:  83%|########2 | 1988/2400 [1:01:13<23:43,  3.46s/it, lr: 5.0e-05 loss: 4.158e-01]
leoprint:  83%|########2 | 1988/2400 [1:01:13<23:43,  3.46s/it, lr: 5.0e-05 loss: 4.158e-01]
leoprint:  83%|########2 | 1988/2400 [1:01:17<23:43,  3.46s/it, lr: 5.0e-05 loss: 2.877e-01]
leoprint:  83%|########2 | 1988/2400 [1:01:17<23:43,  3.46s/it, lr: 5.0e-05 loss: 2.877e-01]
leoprint:  83%|########2 | 1989/2400 [1:01:17<23:46,  3.47s/it, lr: 5.0e-05 loss: 2.877e-01]
leoprint:  83%|########2 | 1989/2400 [1:01:17<23:46,  3.47s/it, lr: 5.0e-05 loss: 2.877e-01]
leoprint:  83%|########2 | 1989/2400 [1:01:21<23:46,  3.47s/it, lr: 5.0e-05 loss: 3.800e-01]
leoprint:  83%|########2 | 1989/2400 [1:01:21<23:46,  3.47s/it, lr: 5.0e-05 loss: 3.800e-01]
leoprint:  83%|########2 | 1990/2400 [1:01:24<23:42,  3.47s/it, lr: 5.0e-05 loss: 3.026e-01]
leoprint:  83%|########2 | 1990/2400 [1:01:24<23:42,  3.47s/it, lr: 5.0e-05 loss: 3.026e-01]
leoprint:  83%|########2 | 1991/2400 [1:01:24<18:17,  2.68s/it, lr: 5.0e-05 loss: 3.026e-01]
leoprint:  83%|########2 | 1991/2400 [1:01:24<18:17,  2.68s/it, lr: 5.0e-05 loss: 3.026e-01]
leoprint:  83%|########2 | 1991/2400 [1:01:28<18:17,  2.68s/it, lr: 5.0e-05 loss: 3.021e-01]
leoprint:  83%|########2 | 1991/2400 [1:01:28<18:17,  2.68s/it, lr: 5.0e-05 loss: 3.021e-01]
leoprint:  83%|########2 | 1992/2400 [1:01:28<19:37,  2.89s/it, lr: 5.0e-05 loss: 3.021e-01]
leoprint:  83%|########2 | 1992/2400 [1:01:28<19:37,  2.89s/it, lr: 5.0e-05 loss: 3.021e-01]
leoprint:  83%|########2 | 1992/2400 [1:01:31<19:37,  2.89s/it, lr: 5.0e-05 loss: 2.284e-01]
leoprint:  83%|########2 | 1992/2400 [1:01:31<19:37,  2.89s/it, lr: 5.0e-05 loss: 2.284e-01]
leoprint:  83%|########3 | 1993/2400 [1:01:31<20:52,  3.08s/it, lr: 5.0e-05 loss: 2.284e-01]
leoprint:  83%|########3 | 1993/2400 [1:01:31<20:52,  3.08s/it, lr: 5.0e-05 loss: 2.284e-01]
leoprint:  83%|########3 | 1993/2400 [1:01:35<20:52,  3.08s/it, lr: 5.0e-05 loss: 3.648e-01]
leoprint:  83%|########3 | 1993/2400 [1:01:35<20:52,  3.08s/it, lr: 5.0e-05 loss: 3.648e-01]
leoprint:  83%|########3 | 1994/2400 [1:01:35<21:36,  3.19s/it, lr: 5.0e-05 loss: 3.648e-01]
leoprint:  83%|########3 | 1994/2400 [1:01:35<21:36,  3.19s/it, lr: 5.0e-05 loss: 3.648e-01]
leoprint:  83%|########3 | 1994/2400 [1:01:38<21:36,  3.19s/it, lr: 5.0e-05 loss: 2.661e-01]
leoprint:  83%|########3 | 1994/2400 [1:01:38<21:36,  3.19s/it, lr: 5.0e-05 loss: 2.661e-01]
leoprint:  83%|########3 | 1995/2400 [1:01:38<22:22,  3.31s/it, lr: 5.0e-05 loss: 2.661e-01]
leoprint:  83%|########3 | 1995/2400 [1:01:38<22:22,  3.31s/it, lr: 5.0e-05 loss: 2.661e-01]
leoprint:  83%|########3 | 1995/2400 [1:01:42<22:22,  3.31s/it, lr: 5.0e-05 loss: 3.636e-01]
leoprint:  83%|########3 | 1995/2400 [1:01:42<22:22,  3.31s/it, lr: 5.0e-05 loss: 3.636e-01]
leoprint:  83%|########3 | 1996/2400 [1:01:42<22:58,  3.41s/it, lr: 5.0e-05 loss: 3.636e-01]
leoprint:  83%|########3 | 1996/2400 [1:01:42<22:58,  3.41s/it, lr: 5.0e-05 loss: 3.636e-01]
leoprint:  83%|########3 | 1996/2400 [1:01:46<22:58,  3.41s/it, lr: 5.0e-05 loss: 2.820e-01]
leoprint:  83%|########3 | 1996/2400 [1:01:46<22:58,  3.41s/it, lr: 5.0e-05 loss: 2.820e-01]
leoprint:  83%|########3 | 1997/2400 [1:01:46<23:06,  3.44s/it, lr: 5.0e-05 loss: 2.820e-01]
leoprint:  83%|########3 | 1997/2400 [1:01:46<23:06,  3.44s/it, lr: 5.0e-05 loss: 2.820e-01]
leoprint:  83%|########3 | 1997/2400 [1:01:49<23:06,  3.44s/it, lr: 5.0e-05 loss: 2.615e-01]
leoprint:  83%|########3 | 1997/2400 [1:01:49<23:06,  3.44s/it, lr: 5.0e-05 loss: 2.615e-01]
leoprint:  83%|########3 | 1998/2400 [1:01:49<23:25,  3.50s/it, lr: 5.0e-05 loss: 2.615e-01]
leoprint:  83%|########3 | 1998/2400 [1:01:49<23:25,  3.50s/it, lr: 5.0e-05 loss: 2.615e-01]
leoprint:  83%|########3 | 1998/2400 [1:01:53<23:25,  3.50s/it, lr: 5.0e-05 loss: 2.903e-01]
leoprint:  83%|########3 | 1998/2400 [1:01:53<23:25,  3.50s/it, lr: 5.0e-05 loss: 2.903e-01]
leoprint:  83%|########3 | 1999/2400 [1:01:53<23:22,  3.50s/it, lr: 5.0e-05 loss: 2.903e-01]
leoprint:  83%|########3 | 1999/2400 [1:01:53<23:22,  3.50s/it, lr: 5.0e-05 loss: 2.903e-01]
leoprint:  83%|########3 | 1999/2400 [1:01:56<23:22,  3.50s/it, lr: 5.0e-05 loss: 2.444e-01]
leoprint:  83%|########3 | 1999/2400 [1:01:56<23:22,  3.50s/it, lr: 5.0e-05 loss: 2.444e-01]
+
+
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
+
+
Generating Images:  20%|##        | 1/5 [00:14<00:57, 14.39s/it]
Generating Images:  20%|##        | 1/5 [00:14<00:57, 14.39s/it]
+
+
Generating Images:  40%|####      | 2/5 [00:28<00:43, 14.40s/it]
Generating Images:  40%|####      | 2/5 [00:28<00:43, 14.40s/it]
+
+
Generating Images:  60%|######    | 3/5 [00:43<00:28, 14.41s/it]
Generating Images:  60%|######    | 3/5 [00:43<00:28, 14.41s/it]
+
+
Generating Images:  80%|########  | 4/5 [00:57<00:14, 14.42s/it]
Generating Images:  80%|########  | 4/5 [00:57<00:14, 14.42s/it]
+
+
Generating Images: 100%|##########| 5/5 [01:12<00:00, 14.42s/it]
Generating Images: 100%|##########| 5/5 [01:12<00:00, 14.42s/it]
+
+
                                                                
                                                                
+Saving at step 2000
+Saved checkpoint to /app/ai-toolkit/output/leoprint/leoprint_000002000.safetensors
+Saved optimizer to /app/ai-toolkit/output/leoprint/optimizer.pt
+
leoprint:  83%|########3 | 2000/2400 [1:02:00<23:18,  3.50s/it, lr: 5.0e-05 loss: 3.398e-01]
leoprint:  83%|########3 | 2000/2400 [1:02:00<23:18,  3.50s/it, lr: 5.0e-05 loss: 3.398e-01]
leoprint:  83%|########3 | 2001/2400 [1:02:00<17:55,  2.70s/it, lr: 5.0e-05 loss: 3.398e-01]
leoprint:  83%|########3 | 2001/2400 [1:02:00<17:55,  2.70s/it, lr: 5.0e-05 loss: 3.398e-01]
leoprint:  83%|########3 | 2001/2400 [1:02:04<17:55,  2.70s/it, lr: 5.0e-05 loss: 3.001e-01]
leoprint:  83%|########3 | 2001/2400 [1:02:04<17:55,  2.70s/it, lr: 5.0e-05 loss: 3.001e-01]
leoprint:  83%|########3 | 2002/2400 [1:02:04<19:10,  2.89s/it, lr: 5.0e-05 loss: 3.001e-01]
leoprint:  83%|########3 | 2002/2400 [1:02:04<19:10,  2.89s/it, lr: 5.0e-05 loss: 3.001e-01]
leoprint:  83%|########3 | 2002/2400 [1:02:07<19:10,  2.89s/it, lr: 5.0e-05 loss: 2.572e-01]
leoprint:  83%|########3 | 2002/2400 [1:02:07<19:10,  2.89s/it, lr: 5.0e-05 loss: 2.572e-01]
leoprint:  83%|########3 | 2003/2400 [1:02:07<20:10,  3.05s/it, lr: 5.0e-05 loss: 2.572e-01]
leoprint:  83%|########3 | 2003/2400 [1:02:07<20:10,  3.05s/it, lr: 5.0e-05 loss: 2.572e-01]
leoprint:  83%|########3 | 2003/2400 [1:02:11<20:10,  3.05s/it, lr: 5.0e-05 loss: 2.711e-01]
leoprint:  83%|########3 | 2003/2400 [1:02:11<20:10,  3.05s/it, lr: 5.0e-05 loss: 2.711e-01]
leoprint:  84%|########3 | 2004/2400 [1:02:11<21:07,  3.20s/it, lr: 5.0e-05 loss: 2.711e-01]
leoprint:  84%|########3 | 2004/2400 [1:02:11<21:07,  3.20s/it, lr: 5.0e-05 loss: 2.711e-01]
leoprint:  84%|########3 | 2004/2400 [1:02:14<21:07,  3.20s/it, lr: 5.0e-05 loss: 3.426e-01]
leoprint:  84%|########3 | 2004/2400 [1:02:14<21:07,  3.20s/it, lr: 5.0e-05 loss: 3.426e-01]
leoprint:  84%|########3 | 2005/2400 [1:02:14<21:37,  3.29s/it, lr: 5.0e-05 loss: 3.426e-01]
leoprint:  84%|########3 | 2005/2400 [1:02:14<21:37,  3.29s/it, lr: 5.0e-05 loss: 3.426e-01]
leoprint:  84%|########3 | 2005/2400 [1:02:18<21:37,  3.29s/it, lr: 5.0e-05 loss: 2.271e-01]
leoprint:  84%|########3 | 2005/2400 [1:02:18<21:37,  3.29s/it, lr: 5.0e-05 loss: 2.271e-01]
leoprint:  84%|########3 | 2006/2400 [1:02:18<22:18,  3.40s/it, lr: 5.0e-05 loss: 2.271e-01]
leoprint:  84%|########3 | 2006/2400 [1:02:18<22:18,  3.40s/it, lr: 5.0e-05 loss: 2.271e-01]
leoprint:  84%|########3 | 2006/2400 [1:02:21<22:18,  3.40s/it, lr: 5.0e-05 loss: 2.981e-01]
leoprint:  84%|########3 | 2006/2400 [1:02:21<22:18,  3.40s/it, lr: 5.0e-05 loss: 2.981e-01]
leoprint:  84%|########3 | 2007/2400 [1:02:21<22:42,  3.47s/it, lr: 5.0e-05 loss: 2.981e-01]
leoprint:  84%|########3 | 2007/2400 [1:02:21<22:42,  3.47s/it, lr: 5.0e-05 loss: 2.981e-01]
leoprint:  84%|########3 | 2007/2400 [1:02:25<22:42,  3.47s/it, lr: 5.0e-05 loss: 2.659e-01]
leoprint:  84%|########3 | 2007/2400 [1:02:25<22:42,  3.47s/it, lr: 5.0e-05 loss: 2.659e-01]
leoprint:  84%|########3 | 2008/2400 [1:02:25<22:44,  3.48s/it, lr: 5.0e-05 loss: 2.659e-01]
leoprint:  84%|########3 | 2008/2400 [1:02:25<22:44,  3.48s/it, lr: 5.0e-05 loss: 2.659e-01]
leoprint:  84%|########3 | 2008/2400 [1:02:28<22:44,  3.48s/it, lr: 5.0e-05 loss: 3.144e-01]
leoprint:  84%|########3 | 2008/2400 [1:02:28<22:44,  3.48s/it, lr: 5.0e-05 loss: 3.144e-01]
leoprint:  84%|########3 | 2009/2400 [1:02:28<22:43,  3.49s/it, lr: 5.0e-05 loss: 3.144e-01]
leoprint:  84%|########3 | 2009/2400 [1:02:28<22:43,  3.49s/it, lr: 5.0e-05 loss: 3.144e-01]
leoprint:  84%|########3 | 2009/2400 [1:02:33<22:43,  3.49s/it, lr: 5.0e-05 loss: 3.367e-01]
leoprint:  84%|########3 | 2009/2400 [1:02:33<22:43,  3.49s/it, lr: 5.0e-05 loss: 3.367e-01]
leoprint:  84%|########3 | 2010/2400 [1:02:37<22:40,  3.49s/it, lr: 5.0e-05 loss: 2.018e-01]
leoprint:  84%|########3 | 2010/2400 [1:02:37<22:40,  3.49s/it, lr: 5.0e-05 loss: 2.018e-01]
leoprint:  84%|########3 | 2011/2400 [1:02:37<17:37,  2.72s/it, lr: 5.0e-05 loss: 2.018e-01]
leoprint:  84%|########3 | 2011/2400 [1:02:37<17:37,  2.72s/it, lr: 5.0e-05 loss: 2.018e-01]
leoprint:  84%|########3 | 2011/2400 [1:02:40<17:37,  2.72s/it, lr: 5.0e-05 loss: 2.536e-01]
leoprint:  84%|########3 | 2011/2400 [1:02:40<17:37,  2.72s/it, lr: 5.0e-05 loss: 2.536e-01]
leoprint:  84%|########3 | 2012/2400 [1:02:40<19:12,  2.97s/it, lr: 5.0e-05 loss: 2.536e-01]
leoprint:  84%|########3 | 2012/2400 [1:02:40<19:12,  2.97s/it, lr: 5.0e-05 loss: 2.536e-01]
leoprint:  84%|########3 | 2012/2400 [1:02:44<19:12,  2.97s/it, lr: 5.0e-05 loss: 2.781e-01]
leoprint:  84%|########3 | 2012/2400 [1:02:44<19:12,  2.97s/it, lr: 5.0e-05 loss: 2.781e-01]
leoprint:  84%|########3 | 2013/2400 [1:02:44<20:14,  3.14s/it, lr: 5.0e-05 loss: 2.781e-01]
leoprint:  84%|########3 | 2013/2400 [1:02:44<20:14,  3.14s/it, lr: 5.0e-05 loss: 2.781e-01]
leoprint:  84%|########3 | 2013/2400 [1:02:48<20:14,  3.14s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  84%|########3 | 2013/2400 [1:02:48<20:14,  3.14s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  84%|########3 | 2014/2400 [1:02:48<20:50,  3.24s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  84%|########3 | 2014/2400 [1:02:48<20:50,  3.24s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  84%|########3 | 2014/2400 [1:02:51<20:50,  3.24s/it, lr: 5.0e-05 loss: 3.077e-01]
leoprint:  84%|########3 | 2014/2400 [1:02:51<20:50,  3.24s/it, lr: 5.0e-05 loss: 3.077e-01]
leoprint:  84%|########3 | 2015/2400 [1:02:51<21:15,  3.31s/it, lr: 5.0e-05 loss: 3.077e-01]
leoprint:  84%|########3 | 2015/2400 [1:02:51<21:15,  3.31s/it, lr: 5.0e-05 loss: 3.077e-01]
leoprint:  84%|########3 | 2015/2400 [1:02:55<21:15,  3.31s/it, lr: 5.0e-05 loss: 3.702e-01]
leoprint:  84%|########3 | 2015/2400 [1:02:55<21:15,  3.31s/it, lr: 5.0e-05 loss: 3.702e-01]
leoprint:  84%|########4 | 2016/2400 [1:02:55<21:33,  3.37s/it, lr: 5.0e-05 loss: 3.702e-01]
leoprint:  84%|########4 | 2016/2400 [1:02:55<21:33,  3.37s/it, lr: 5.0e-05 loss: 3.702e-01]
leoprint:  84%|########4 | 2016/2400 [1:02:58<21:33,  3.37s/it, lr: 5.0e-05 loss: 2.767e-01]
leoprint:  84%|########4 | 2016/2400 [1:02:58<21:33,  3.37s/it, lr: 5.0e-05 loss: 2.767e-01]
leoprint:  84%|########4 | 2017/2400 [1:02:58<21:45,  3.41s/it, lr: 5.0e-05 loss: 2.767e-01]
leoprint:  84%|########4 | 2017/2400 [1:02:58<21:45,  3.41s/it, lr: 5.0e-05 loss: 2.767e-01]
leoprint:  84%|########4 | 2017/2400 [1:03:02<21:45,  3.41s/it, lr: 5.0e-05 loss: 2.663e-01]
leoprint:  84%|########4 | 2017/2400 [1:03:02<21:45,  3.41s/it, lr: 5.0e-05 loss: 2.663e-01]
leoprint:  84%|########4 | 2018/2400 [1:03:02<22:20,  3.51s/it, lr: 5.0e-05 loss: 2.663e-01]
leoprint:  84%|########4 | 2018/2400 [1:03:02<22:20,  3.51s/it, lr: 5.0e-05 loss: 2.663e-01]
leoprint:  84%|########4 | 2018/2400 [1:03:05<22:20,  3.51s/it, lr: 5.0e-05 loss: 2.306e-01]
leoprint:  84%|########4 | 2018/2400 [1:03:05<22:20,  3.51s/it, lr: 5.0e-05 loss: 2.306e-01]
leoprint:  84%|########4 | 2019/2400 [1:03:05<22:29,  3.54s/it, lr: 5.0e-05 loss: 2.306e-01]
leoprint:  84%|########4 | 2019/2400 [1:03:05<22:29,  3.54s/it, lr: 5.0e-05 loss: 2.306e-01]
leoprint:  84%|########4 | 2019/2400 [1:03:09<22:29,  3.54s/it, lr: 5.0e-05 loss: 3.798e-01]
leoprint:  84%|########4 | 2019/2400 [1:03:09<22:29,  3.54s/it, lr: 5.0e-05 loss: 3.798e-01]
leoprint:  84%|########4 | 2020/2400 [1:03:12<22:26,  3.54s/it, lr: 5.0e-05 loss: 3.715e-01]
leoprint:  84%|########4 | 2020/2400 [1:03:12<22:26,  3.54s/it, lr: 5.0e-05 loss: 3.715e-01]
leoprint:  84%|########4 | 2021/2400 [1:03:12<17:12,  2.72s/it, lr: 5.0e-05 loss: 3.715e-01]
leoprint:  84%|########4 | 2021/2400 [1:03:12<17:12,  2.72s/it, lr: 5.0e-05 loss: 3.715e-01]
leoprint:  84%|########4 | 2021/2400 [1:03:16<17:12,  2.72s/it, lr: 5.0e-05 loss: 2.605e-01]
leoprint:  84%|########4 | 2021/2400 [1:03:16<17:12,  2.72s/it, lr: 5.0e-05 loss: 2.605e-01]
leoprint:  84%|########4 | 2022/2400 [1:03:16<18:22,  2.92s/it, lr: 5.0e-05 loss: 2.605e-01]
leoprint:  84%|########4 | 2022/2400 [1:03:16<18:22,  2.92s/it, lr: 5.0e-05 loss: 2.605e-01]
leoprint:  84%|########4 | 2022/2400 [1:03:20<18:22,  2.92s/it, lr: 5.0e-05 loss: 2.667e-01]
leoprint:  84%|########4 | 2022/2400 [1:03:20<18:22,  2.92s/it, lr: 5.0e-05 loss: 2.667e-01]
leoprint:  84%|########4 | 2023/2400 [1:03:20<19:45,  3.14s/it, lr: 5.0e-05 loss: 2.667e-01]
leoprint:  84%|########4 | 2023/2400 [1:03:20<19:45,  3.14s/it, lr: 5.0e-05 loss: 2.667e-01]
leoprint:  84%|########4 | 2023/2400 [1:03:24<19:45,  3.14s/it, lr: 5.0e-05 loss: 3.487e-01]
leoprint:  84%|########4 | 2023/2400 [1:03:24<19:45,  3.14s/it, lr: 5.0e-05 loss: 3.487e-01]
leoprint:  84%|########4 | 2024/2400 [1:03:24<21:49,  3.48s/it, lr: 5.0e-05 loss: 3.487e-01]
leoprint:  84%|########4 | 2024/2400 [1:03:24<21:49,  3.48s/it, lr: 5.0e-05 loss: 3.487e-01]
leoprint:  84%|########4 | 2024/2400 [1:03:32<21:49,  3.48s/it, lr: 5.0e-05 loss: 3.337e-01]
leoprint:  84%|########4 | 2024/2400 [1:03:32<21:49,  3.48s/it, lr: 5.0e-05 loss: 3.337e-01]
leoprint:  84%|########4 | 2025/2400 [1:03:32<28:51,  4.62s/it, lr: 5.0e-05 loss: 3.337e-01]
leoprint:  84%|########4 | 2025/2400 [1:03:32<28:51,  4.62s/it, lr: 5.0e-05 loss: 3.337e-01]
leoprint:  84%|########4 | 2025/2400 [1:03:41<28:51,  4.62s/it, lr: 5.0e-05 loss: 2.276e-01]
leoprint:  84%|########4 | 2025/2400 [1:03:41<28:51,  4.62s/it, lr: 5.0e-05 loss: 2.276e-01]
leoprint:  84%|########4 | 2026/2400 [1:03:41<37:41,  6.05s/it, lr: 5.0e-05 loss: 2.276e-01]
leoprint:  84%|########4 | 2026/2400 [1:03:41<37:41,  6.05s/it, lr: 5.0e-05 loss: 2.276e-01]
leoprint:  84%|########4 | 2026/2400 [1:03:51<37:41,  6.05s/it, lr: 5.0e-05 loss: 2.364e-01]
leoprint:  84%|########4 | 2026/2400 [1:03:51<37:41,  6.05s/it, lr: 5.0e-05 loss: 2.364e-01]
leoprint:  84%|########4 | 2027/2400 [1:03:51<44:30,  7.16s/it, lr: 5.0e-05 loss: 2.364e-01]
leoprint:  84%|########4 | 2027/2400 [1:03:51<44:30,  7.16s/it, lr: 5.0e-05 loss: 2.364e-01]
leoprint:  84%|########4 | 2027/2400 [1:03:57<44:30,  7.16s/it, lr: 5.0e-05 loss: 3.168e-01]
leoprint:  84%|########4 | 2027/2400 [1:03:57<44:30,  7.16s/it, lr: 5.0e-05 loss: 3.168e-01]
leoprint:  84%|########4 | 2028/2400 [1:03:57<41:32,  6.70s/it, lr: 5.0e-05 loss: 3.168e-01]
leoprint:  84%|########4 | 2028/2400 [1:03:57<41:32,  6.70s/it, lr: 5.0e-05 loss: 3.168e-01]
leoprint:  84%|########4 | 2028/2400 [1:04:00<41:32,  6.70s/it, lr: 5.0e-05 loss: 3.947e-01]
leoprint:  84%|########4 | 2028/2400 [1:04:00<41:32,  6.70s/it, lr: 5.0e-05 loss: 3.947e-01]
leoprint:  85%|########4 | 2029/2400 [1:04:00<35:45,  5.78s/it, lr: 5.0e-05 loss: 3.947e-01]
leoprint:  85%|########4 | 2029/2400 [1:04:00<35:45,  5.78s/it, lr: 5.0e-05 loss: 3.947e-01]
leoprint:  85%|########4 | 2029/2400 [1:04:04<35:45,  5.78s/it, lr: 5.0e-05 loss: 2.073e-01]
leoprint:  85%|########4 | 2029/2400 [1:04:04<35:45,  5.78s/it, lr: 5.0e-05 loss: 2.073e-01]
leoprint:  85%|########4 | 2030/2400 [1:04:07<35:40,  5.78s/it, lr: 5.0e-05 loss: 3.447e-01]
leoprint:  85%|########4 | 2030/2400 [1:04:07<35:40,  5.78s/it, lr: 5.0e-05 loss: 3.447e-01]
leoprint:  85%|########4 | 2031/2400 [1:04:07<24:14,  3.94s/it, lr: 5.0e-05 loss: 3.447e-01]
leoprint:  85%|########4 | 2031/2400 [1:04:07<24:14,  3.94s/it, lr: 5.0e-05 loss: 3.447e-01]
leoprint:  85%|########4 | 2031/2400 [1:04:11<24:14,  3.94s/it, lr: 5.0e-05 loss: 2.871e-01]
leoprint:  85%|########4 | 2031/2400 [1:04:11<24:14,  3.94s/it, lr: 5.0e-05 loss: 2.871e-01]
leoprint:  85%|########4 | 2032/2400 [1:04:11<23:31,  3.84s/it, lr: 5.0e-05 loss: 2.871e-01]
leoprint:  85%|########4 | 2032/2400 [1:04:11<23:31,  3.84s/it, lr: 5.0e-05 loss: 2.871e-01]
leoprint:  85%|########4 | 2032/2400 [1:04:15<23:31,  3.84s/it, lr: 5.0e-05 loss: 2.306e-01]
leoprint:  85%|########4 | 2032/2400 [1:04:15<23:31,  3.84s/it, lr: 5.0e-05 loss: 2.306e-01]
leoprint:  85%|########4 | 2033/2400 [1:04:15<23:08,  3.78s/it, lr: 5.0e-05 loss: 2.306e-01]
leoprint:  85%|########4 | 2033/2400 [1:04:15<23:08,  3.78s/it, lr: 5.0e-05 loss: 2.306e-01]
leoprint:  85%|########4 | 2033/2400 [1:04:18<23:08,  3.78s/it, lr: 5.0e-05 loss: 3.023e-01]
leoprint:  85%|########4 | 2033/2400 [1:04:18<23:08,  3.78s/it, lr: 5.0e-05 loss: 3.023e-01]
leoprint:  85%|########4 | 2034/2400 [1:04:18<22:38,  3.71s/it, lr: 5.0e-05 loss: 3.023e-01]
leoprint:  85%|########4 | 2034/2400 [1:04:18<22:38,  3.71s/it, lr: 5.0e-05 loss: 3.023e-01]
leoprint:  85%|########4 | 2034/2400 [1:04:22<22:38,  3.71s/it, lr: 5.0e-05 loss: 2.034e-01]
leoprint:  85%|########4 | 2034/2400 [1:04:22<22:38,  3.71s/it, lr: 5.0e-05 loss: 2.034e-01]
leoprint:  85%|########4 | 2035/2400 [1:04:22<22:50,  3.76s/it, lr: 5.0e-05 loss: 2.034e-01]
leoprint:  85%|########4 | 2035/2400 [1:04:22<22:50,  3.76s/it, lr: 5.0e-05 loss: 2.034e-01]
leoprint:  85%|########4 | 2035/2400 [1:04:26<22:50,  3.76s/it, lr: 5.0e-05 loss: 3.279e-01]
leoprint:  85%|########4 | 2035/2400 [1:04:26<22:50,  3.76s/it, lr: 5.0e-05 loss: 3.279e-01]
leoprint:  85%|########4 | 2036/2400 [1:04:26<22:21,  3.69s/it, lr: 5.0e-05 loss: 3.279e-01]
leoprint:  85%|########4 | 2036/2400 [1:04:26<22:21,  3.69s/it, lr: 5.0e-05 loss: 3.279e-01]
leoprint:  85%|########4 | 2036/2400 [1:04:29<22:21,  3.69s/it, lr: 5.0e-05 loss: 1.794e-01]
leoprint:  85%|########4 | 2036/2400 [1:04:29<22:21,  3.69s/it, lr: 5.0e-05 loss: 1.794e-01]
leoprint:  85%|########4 | 2037/2400 [1:04:29<22:11,  3.67s/it, lr: 5.0e-05 loss: 1.794e-01]
leoprint:  85%|########4 | 2037/2400 [1:04:29<22:11,  3.67s/it, lr: 5.0e-05 loss: 1.794e-01]
leoprint:  85%|########4 | 2037/2400 [1:04:33<22:11,  3.67s/it, lr: 5.0e-05 loss: 3.076e-01]
leoprint:  85%|########4 | 2037/2400 [1:04:33<22:11,  3.67s/it, lr: 5.0e-05 loss: 3.076e-01]
leoprint:  85%|########4 | 2038/2400 [1:04:33<21:51,  3.62s/it, lr: 5.0e-05 loss: 3.076e-01]
leoprint:  85%|########4 | 2038/2400 [1:04:33<21:51,  3.62s/it, lr: 5.0e-05 loss: 3.076e-01]
leoprint:  85%|########4 | 2038/2400 [1:04:36<21:51,  3.62s/it, lr: 5.0e-05 loss: 3.198e-01]
leoprint:  85%|########4 | 2038/2400 [1:04:36<21:51,  3.62s/it, lr: 5.0e-05 loss: 3.198e-01]
leoprint:  85%|########4 | 2039/2400 [1:04:36<21:37,  3.59s/it, lr: 5.0e-05 loss: 3.198e-01]
leoprint:  85%|########4 | 2039/2400 [1:04:36<21:37,  3.59s/it, lr: 5.0e-05 loss: 3.198e-01]
leoprint:  85%|########4 | 2039/2400 [1:04:40<21:37,  3.59s/it, lr: 5.0e-05 loss: 3.137e-01]
leoprint:  85%|########4 | 2039/2400 [1:04:40<21:37,  3.59s/it, lr: 5.0e-05 loss: 3.137e-01]
leoprint:  85%|########5 | 2040/2400 [1:04:43<21:33,  3.59s/it, lr: 5.0e-05 loss: 3.399e-01]
leoprint:  85%|########5 | 2040/2400 [1:04:43<21:33,  3.59s/it, lr: 5.0e-05 loss: 3.399e-01]
leoprint:  85%|########5 | 2041/2400 [1:04:43<16:39,  2.78s/it, lr: 5.0e-05 loss: 3.399e-01]
leoprint:  85%|########5 | 2041/2400 [1:04:43<16:39,  2.78s/it, lr: 5.0e-05 loss: 3.399e-01]
leoprint:  85%|########5 | 2041/2400 [1:04:47<16:39,  2.78s/it, lr: 5.0e-05 loss: 2.384e-01]
leoprint:  85%|########5 | 2041/2400 [1:04:47<16:39,  2.78s/it, lr: 5.0e-05 loss: 2.384e-01]
leoprint:  85%|########5 | 2042/2400 [1:04:47<17:42,  2.97s/it, lr: 5.0e-05 loss: 2.384e-01]
leoprint:  85%|########5 | 2042/2400 [1:04:47<17:42,  2.97s/it, lr: 5.0e-05 loss: 2.384e-01]
leoprint:  85%|########5 | 2042/2400 [1:04:50<17:42,  2.97s/it, lr: 5.0e-05 loss: 4.050e-01]
leoprint:  85%|########5 | 2042/2400 [1:04:50<17:42,  2.97s/it, lr: 5.0e-05 loss: 4.050e-01]
leoprint:  85%|########5 | 2043/2400 [1:04:50<18:28,  3.11s/it, lr: 5.0e-05 loss: 4.050e-01]
leoprint:  85%|########5 | 2043/2400 [1:04:50<18:28,  3.11s/it, lr: 5.0e-05 loss: 4.050e-01]
leoprint:  85%|########5 | 2043/2400 [1:04:54<18:28,  3.11s/it, lr: 5.0e-05 loss: 1.870e-01]
leoprint:  85%|########5 | 2043/2400 [1:04:54<18:28,  3.11s/it, lr: 5.0e-05 loss: 1.870e-01]
leoprint:  85%|########5 | 2044/2400 [1:04:54<19:16,  3.25s/it, lr: 5.0e-05 loss: 1.870e-01]
leoprint:  85%|########5 | 2044/2400 [1:04:54<19:16,  3.25s/it, lr: 5.0e-05 loss: 1.870e-01]
leoprint:  85%|########5 | 2044/2400 [1:04:58<19:16,  3.25s/it, lr: 5.0e-05 loss: 3.588e-01]
leoprint:  85%|########5 | 2044/2400 [1:04:58<19:16,  3.25s/it, lr: 5.0e-05 loss: 3.588e-01]
leoprint:  85%|########5 | 2045/2400 [1:04:58<19:38,  3.32s/it, lr: 5.0e-05 loss: 3.588e-01]
leoprint:  85%|########5 | 2045/2400 [1:04:58<19:38,  3.32s/it, lr: 5.0e-05 loss: 3.588e-01]
leoprint:  85%|########5 | 2045/2400 [1:05:01<19:38,  3.32s/it, lr: 5.0e-05 loss: 1.844e-01]
leoprint:  85%|########5 | 2045/2400 [1:05:01<19:38,  3.32s/it, lr: 5.0e-05 loss: 1.844e-01]
leoprint:  85%|########5 | 2046/2400 [1:05:01<20:23,  3.46s/it, lr: 5.0e-05 loss: 1.844e-01]
leoprint:  85%|########5 | 2046/2400 [1:05:01<20:23,  3.46s/it, lr: 5.0e-05 loss: 1.844e-01]
leoprint:  85%|########5 | 2046/2400 [1:05:05<20:23,  3.46s/it, lr: 5.0e-05 loss: 2.347e-01]
leoprint:  85%|########5 | 2046/2400 [1:05:05<20:23,  3.46s/it, lr: 5.0e-05 loss: 2.347e-01]
leoprint:  85%|########5 | 2047/2400 [1:05:05<20:26,  3.47s/it, lr: 5.0e-05 loss: 2.347e-01]
leoprint:  85%|########5 | 2047/2400 [1:05:05<20:26,  3.47s/it, lr: 5.0e-05 loss: 2.347e-01]
leoprint:  85%|########5 | 2047/2400 [1:05:08<20:26,  3.47s/it, lr: 5.0e-05 loss: 3.249e-01]
leoprint:  85%|########5 | 2047/2400 [1:05:08<20:26,  3.47s/it, lr: 5.0e-05 loss: 3.249e-01]
leoprint:  85%|########5 | 2048/2400 [1:05:08<20:25,  3.48s/it, lr: 5.0e-05 loss: 3.249e-01]
leoprint:  85%|########5 | 2048/2400 [1:05:08<20:25,  3.48s/it, lr: 5.0e-05 loss: 3.249e-01]
leoprint:  85%|########5 | 2048/2400 [1:05:12<20:25,  3.48s/it, lr: 5.0e-05 loss: 3.702e-01]
leoprint:  85%|########5 | 2048/2400 [1:05:12<20:25,  3.48s/it, lr: 5.0e-05 loss: 3.702e-01]
leoprint:  85%|########5 | 2049/2400 [1:05:12<20:24,  3.49s/it, lr: 5.0e-05 loss: 3.702e-01]
leoprint:  85%|########5 | 2049/2400 [1:05:12<20:24,  3.49s/it, lr: 5.0e-05 loss: 3.702e-01]
leoprint:  85%|########5 | 2049/2400 [1:05:15<20:24,  3.49s/it, lr: 5.0e-05 loss: 2.817e-01]
leoprint:  85%|########5 | 2049/2400 [1:05:15<20:24,  3.49s/it, lr: 5.0e-05 loss: 2.817e-01]
leoprint:  85%|########5 | 2050/2400 [1:05:19<20:20,  3.49s/it, lr: 5.0e-05 loss: 3.027e-01]
leoprint:  85%|########5 | 2050/2400 [1:05:19<20:20,  3.49s/it, lr: 5.0e-05 loss: 3.027e-01]
leoprint:  85%|########5 | 2051/2400 [1:05:19<15:40,  2.69s/it, lr: 5.0e-05 loss: 3.027e-01]
leoprint:  85%|########5 | 2051/2400 [1:05:19<15:40,  2.69s/it, lr: 5.0e-05 loss: 3.027e-01]
leoprint:  85%|########5 | 2051/2400 [1:05:23<15:40,  2.69s/it, lr: 5.0e-05 loss: 1.801e-01]
leoprint:  85%|########5 | 2051/2400 [1:05:23<15:40,  2.69s/it, lr: 5.0e-05 loss: 1.801e-01]
leoprint:  86%|########5 | 2052/2400 [1:05:23<17:03,  2.94s/it, lr: 5.0e-05 loss: 1.801e-01]
leoprint:  86%|########5 | 2052/2400 [1:05:23<17:03,  2.94s/it, lr: 5.0e-05 loss: 1.801e-01]
leoprint:  86%|########5 | 2052/2400 [1:05:26<17:03,  2.94s/it, lr: 5.0e-05 loss: 3.830e-01]
leoprint:  86%|########5 | 2052/2400 [1:05:26<17:03,  2.94s/it, lr: 5.0e-05 loss: 3.830e-01]
leoprint:  86%|########5 | 2053/2400 [1:05:26<17:51,  3.09s/it, lr: 5.0e-05 loss: 3.830e-01]
leoprint:  86%|########5 | 2053/2400 [1:05:26<17:51,  3.09s/it, lr: 5.0e-05 loss: 3.830e-01]
leoprint:  86%|########5 | 2053/2400 [1:05:30<17:51,  3.09s/it, lr: 5.0e-05 loss: 3.024e-01]
leoprint:  86%|########5 | 2053/2400 [1:05:30<17:51,  3.09s/it, lr: 5.0e-05 loss: 3.024e-01]
leoprint:  86%|########5 | 2054/2400 [1:05:30<18:27,  3.20s/it, lr: 5.0e-05 loss: 3.024e-01]
leoprint:  86%|########5 | 2054/2400 [1:05:30<18:27,  3.20s/it, lr: 5.0e-05 loss: 3.024e-01]
leoprint:  86%|########5 | 2054/2400 [1:05:33<18:27,  3.20s/it, lr: 5.0e-05 loss: 2.760e-01]
leoprint:  86%|########5 | 2054/2400 [1:05:33<18:27,  3.20s/it, lr: 5.0e-05 loss: 2.760e-01]
leoprint:  86%|########5 | 2055/2400 [1:05:33<19:04,  3.32s/it, lr: 5.0e-05 loss: 2.760e-01]
leoprint:  86%|########5 | 2055/2400 [1:05:33<19:04,  3.32s/it, lr: 5.0e-05 loss: 2.760e-01]
leoprint:  86%|########5 | 2055/2400 [1:05:37<19:04,  3.32s/it, lr: 5.0e-05 loss: 3.016e-01]
leoprint:  86%|########5 | 2055/2400 [1:05:37<19:04,  3.32s/it, lr: 5.0e-05 loss: 3.016e-01]
leoprint:  86%|########5 | 2056/2400 [1:05:37<19:19,  3.37s/it, lr: 5.0e-05 loss: 3.016e-01]
leoprint:  86%|########5 | 2056/2400 [1:05:37<19:19,  3.37s/it, lr: 5.0e-05 loss: 3.016e-01]
leoprint:  86%|########5 | 2056/2400 [1:05:40<19:19,  3.37s/it, lr: 5.0e-05 loss: 3.544e-01]
leoprint:  86%|########5 | 2056/2400 [1:05:40<19:19,  3.37s/it, lr: 5.0e-05 loss: 3.544e-01]
leoprint:  86%|########5 | 2057/2400 [1:05:40<19:29,  3.41s/it, lr: 5.0e-05 loss: 3.544e-01]
leoprint:  86%|########5 | 2057/2400 [1:05:40<19:29,  3.41s/it, lr: 5.0e-05 loss: 3.544e-01]
leoprint:  86%|########5 | 2057/2400 [1:05:44<19:29,  3.41s/it, lr: 5.0e-05 loss: 2.713e-01]
leoprint:  86%|########5 | 2057/2400 [1:05:44<19:29,  3.41s/it, lr: 5.0e-05 loss: 2.713e-01]
leoprint:  86%|########5 | 2058/2400 [1:05:44<20:11,  3.54s/it, lr: 5.0e-05 loss: 2.713e-01]
leoprint:  86%|########5 | 2058/2400 [1:05:44<20:11,  3.54s/it, lr: 5.0e-05 loss: 2.713e-01]
leoprint:  86%|########5 | 2058/2400 [1:05:48<20:11,  3.54s/it, lr: 5.0e-05 loss: 2.067e-01]
leoprint:  86%|########5 | 2058/2400 [1:05:48<20:11,  3.54s/it, lr: 5.0e-05 loss: 2.067e-01]
leoprint:  86%|########5 | 2059/2400 [1:05:48<20:16,  3.57s/it, lr: 5.0e-05 loss: 2.067e-01]
leoprint:  86%|########5 | 2059/2400 [1:05:48<20:16,  3.57s/it, lr: 5.0e-05 loss: 2.067e-01]
leoprint:  86%|########5 | 2059/2400 [1:05:52<20:16,  3.57s/it, lr: 5.0e-05 loss: 3.038e-01]
leoprint:  86%|########5 | 2059/2400 [1:05:52<20:16,  3.57s/it, lr: 5.0e-05 loss: 3.038e-01]
leoprint:  86%|########5 | 2060/2400 [1:05:55<20:12,  3.57s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  86%|########5 | 2060/2400 [1:05:55<20:12,  3.57s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  86%|########5 | 2061/2400 [1:05:55<15:27,  2.74s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  86%|########5 | 2061/2400 [1:05:55<15:27,  2.74s/it, lr: 5.0e-05 loss: 3.017e-01]
leoprint:  86%|########5 | 2061/2400 [1:05:59<15:27,  2.74s/it, lr: 5.0e-05 loss: 2.571e-01]
leoprint:  86%|########5 | 2061/2400 [1:05:59<15:27,  2.74s/it, lr: 5.0e-05 loss: 2.571e-01]
leoprint:  86%|########5 | 2062/2400 [1:05:59<16:29,  2.93s/it, lr: 5.0e-05 loss: 2.571e-01]
leoprint:  86%|########5 | 2062/2400 [1:05:59<16:29,  2.93s/it, lr: 5.0e-05 loss: 2.571e-01]
leoprint:  86%|########5 | 2062/2400 [1:06:02<16:29,  2.93s/it, lr: 5.0e-05 loss: 2.920e-01]
leoprint:  86%|########5 | 2062/2400 [1:06:02<16:29,  2.93s/it, lr: 5.0e-05 loss: 2.920e-01]
leoprint:  86%|########5 | 2063/2400 [1:06:02<17:16,  3.08s/it, lr: 5.0e-05 loss: 2.920e-01]
leoprint:  86%|########5 | 2063/2400 [1:06:02<17:16,  3.08s/it, lr: 5.0e-05 loss: 2.920e-01]
leoprint:  86%|########5 | 2063/2400 [1:06:06<17:16,  3.08s/it, lr: 5.0e-05 loss: 2.772e-01]
leoprint:  86%|########5 | 2063/2400 [1:06:06<17:16,  3.08s/it, lr: 5.0e-05 loss: 2.772e-01]
leoprint:  86%|########6 | 2064/2400 [1:06:06<18:05,  3.23s/it, lr: 5.0e-05 loss: 2.772e-01]
leoprint:  86%|########6 | 2064/2400 [1:06:06<18:05,  3.23s/it, lr: 5.0e-05 loss: 2.772e-01]
leoprint:  86%|########6 | 2064/2400 [1:06:09<18:05,  3.23s/it, lr: 5.0e-05 loss: 2.330e-01]
leoprint:  86%|########6 | 2064/2400 [1:06:09<18:05,  3.23s/it, lr: 5.0e-05 loss: 2.330e-01]
leoprint:  86%|########6 | 2065/2400 [1:06:09<18:27,  3.30s/it, lr: 5.0e-05 loss: 2.330e-01]
leoprint:  86%|########6 | 2065/2400 [1:06:09<18:27,  3.30s/it, lr: 5.0e-05 loss: 2.330e-01]
leoprint:  86%|########6 | 2065/2400 [1:06:13<18:27,  3.30s/it, lr: 5.0e-05 loss: 2.923e-01]
leoprint:  86%|########6 | 2065/2400 [1:06:13<18:27,  3.30s/it, lr: 5.0e-05 loss: 2.923e-01]
leoprint:  86%|########6 | 2066/2400 [1:06:13<18:42,  3.36s/it, lr: 5.0e-05 loss: 2.923e-01]
leoprint:  86%|########6 | 2066/2400 [1:06:13<18:42,  3.36s/it, lr: 5.0e-05 loss: 2.923e-01]
leoprint:  86%|########6 | 2066/2400 [1:06:16<18:42,  3.36s/it, lr: 5.0e-05 loss: 2.708e-01]
leoprint:  86%|########6 | 2066/2400 [1:06:16<18:42,  3.36s/it, lr: 5.0e-05 loss: 2.708e-01]
leoprint:  86%|########6 | 2067/2400 [1:06:16<19:05,  3.44s/it, lr: 5.0e-05 loss: 2.708e-01]
leoprint:  86%|########6 | 2067/2400 [1:06:16<19:05,  3.44s/it, lr: 5.0e-05 loss: 2.708e-01]
leoprint:  86%|########6 | 2067/2400 [1:06:20<19:05,  3.44s/it, lr: 5.0e-05 loss: 3.226e-01]
leoprint:  86%|########6 | 2067/2400 [1:06:20<19:05,  3.44s/it, lr: 5.0e-05 loss: 3.226e-01]
leoprint:  86%|########6 | 2068/2400 [1:06:20<19:08,  3.46s/it, lr: 5.0e-05 loss: 3.226e-01]
leoprint:  86%|########6 | 2068/2400 [1:06:20<19:08,  3.46s/it, lr: 5.0e-05 loss: 3.226e-01]
leoprint:  86%|########6 | 2068/2400 [1:06:24<19:08,  3.46s/it, lr: 5.0e-05 loss: 2.978e-01]
leoprint:  86%|########6 | 2068/2400 [1:06:24<19:08,  3.46s/it, lr: 5.0e-05 loss: 2.978e-01]
leoprint:  86%|########6 | 2069/2400 [1:06:24<19:27,  3.53s/it, lr: 5.0e-05 loss: 2.978e-01]
leoprint:  86%|########6 | 2069/2400 [1:06:24<19:27,  3.53s/it, lr: 5.0e-05 loss: 2.978e-01]
leoprint:  86%|########6 | 2069/2400 [1:06:27<19:27,  3.53s/it, lr: 5.0e-05 loss: 3.527e-01]
leoprint:  86%|########6 | 2069/2400 [1:06:27<19:27,  3.53s/it, lr: 5.0e-05 loss: 3.527e-01]
leoprint:  86%|########6 | 2070/2400 [1:06:31<19:23,  3.53s/it, lr: 5.0e-05 loss: 2.870e-01]
leoprint:  86%|########6 | 2070/2400 [1:06:31<19:23,  3.53s/it, lr: 5.0e-05 loss: 2.870e-01]
leoprint:  86%|########6 | 2071/2400 [1:06:31<14:53,  2.72s/it, lr: 5.0e-05 loss: 2.870e-01]
leoprint:  86%|########6 | 2071/2400 [1:06:31<14:53,  2.72s/it, lr: 5.0e-05 loss: 2.870e-01]
leoprint:  86%|########6 | 2071/2400 [1:06:34<14:53,  2.72s/it, lr: 5.0e-05 loss: 2.695e-01]
leoprint:  86%|########6 | 2071/2400 [1:06:34<14:53,  2.72s/it, lr: 5.0e-05 loss: 2.695e-01]
leoprint:  86%|########6 | 2072/2400 [1:06:34<16:04,  2.94s/it, lr: 5.0e-05 loss: 2.695e-01]
leoprint:  86%|########6 | 2072/2400 [1:06:34<16:04,  2.94s/it, lr: 5.0e-05 loss: 2.695e-01]
leoprint:  86%|########6 | 2072/2400 [1:06:38<16:04,  2.94s/it, lr: 5.0e-05 loss: 3.021e-01]
leoprint:  86%|########6 | 2072/2400 [1:06:38<16:04,  2.94s/it, lr: 5.0e-05 loss: 3.021e-01]
leoprint:  86%|########6 | 2073/2400 [1:06:38<16:50,  3.09s/it, lr: 5.0e-05 loss: 3.021e-01]
leoprint:  86%|########6 | 2073/2400 [1:06:38<16:50,  3.09s/it, lr: 5.0e-05 loss: 3.021e-01]
leoprint:  86%|########6 | 2073/2400 [1:06:41<16:50,  3.09s/it, lr: 5.0e-05 loss: 3.212e-01]
leoprint:  86%|########6 | 2073/2400 [1:06:41<16:50,  3.09s/it, lr: 5.0e-05 loss: 3.212e-01]
leoprint:  86%|########6 | 2074/2400 [1:06:41<17:23,  3.20s/it, lr: 5.0e-05 loss: 3.212e-01]
leoprint:  86%|########6 | 2074/2400 [1:06:41<17:23,  3.20s/it, lr: 5.0e-05 loss: 3.212e-01]
leoprint:  86%|########6 | 2074/2400 [1:06:45<17:23,  3.20s/it, lr: 5.0e-05 loss: 2.577e-01]
leoprint:  86%|########6 | 2074/2400 [1:06:45<17:23,  3.20s/it, lr: 5.0e-05 loss: 2.577e-01]
leoprint:  86%|########6 | 2075/2400 [1:06:45<17:54,  3.31s/it, lr: 5.0e-05 loss: 2.577e-01]
leoprint:  86%|########6 | 2075/2400 [1:06:45<17:54,  3.31s/it, lr: 5.0e-05 loss: 2.577e-01]
leoprint:  86%|########6 | 2075/2400 [1:06:48<17:54,  3.31s/it, lr: 5.0e-05 loss: 2.671e-01]
leoprint:  86%|########6 | 2075/2400 [1:06:48<17:54,  3.31s/it, lr: 5.0e-05 loss: 2.671e-01]
leoprint:  86%|########6 | 2076/2400 [1:06:48<18:21,  3.40s/it, lr: 5.0e-05 loss: 2.671e-01]
leoprint:  86%|########6 | 2076/2400 [1:06:48<18:21,  3.40s/it, lr: 5.0e-05 loss: 2.671e-01]
leoprint:  86%|########6 | 2076/2400 [1:06:52<18:21,  3.40s/it, lr: 5.0e-05 loss: 2.328e-01]
leoprint:  86%|########6 | 2076/2400 [1:06:52<18:21,  3.40s/it, lr: 5.0e-05 loss: 2.328e-01]
leoprint:  87%|########6 | 2077/2400 [1:06:52<18:28,  3.43s/it, lr: 5.0e-05 loss: 2.328e-01]
leoprint:  87%|########6 | 2077/2400 [1:06:52<18:28,  3.43s/it, lr: 5.0e-05 loss: 2.328e-01]
leoprint:  87%|########6 | 2077/2400 [1:06:56<18:28,  3.43s/it, lr: 5.0e-05 loss: 2.820e-01]
leoprint:  87%|########6 | 2077/2400 [1:06:56<18:28,  3.43s/it, lr: 5.0e-05 loss: 2.820e-01]
leoprint:  87%|########6 | 2078/2400 [1:06:56<18:32,  3.46s/it, lr: 5.0e-05 loss: 2.820e-01]
leoprint:  87%|########6 | 2078/2400 [1:06:56<18:32,  3.46s/it, lr: 5.0e-05 loss: 2.820e-01]
leoprint:  87%|########6 | 2078/2400 [1:06:59<18:32,  3.46s/it, lr: 5.0e-05 loss: 1.941e-01]
leoprint:  87%|########6 | 2078/2400 [1:06:59<18:32,  3.46s/it, lr: 5.0e-05 loss: 1.941e-01]
leoprint:  87%|########6 | 2079/2400 [1:06:59<18:45,  3.51s/it, lr: 5.0e-05 loss: 1.941e-01]
leoprint:  87%|########6 | 2079/2400 [1:06:59<18:45,  3.51s/it, lr: 5.0e-05 loss: 1.941e-01]
leoprint:  87%|########6 | 2079/2400 [1:07:03<18:45,  3.51s/it, lr: 5.0e-05 loss: 2.138e-01]
leoprint:  87%|########6 | 2079/2400 [1:07:03<18:45,  3.51s/it, lr: 5.0e-05 loss: 2.138e-01]
leoprint:  87%|########6 | 2080/2400 [1:07:06<18:42,  3.51s/it, lr: 5.0e-05 loss: 3.773e-01]
leoprint:  87%|########6 | 2080/2400 [1:07:06<18:42,  3.51s/it, lr: 5.0e-05 loss: 3.773e-01]
leoprint:  87%|########6 | 2081/2400 [1:07:06<14:39,  2.76s/it, lr: 5.0e-05 loss: 3.773e-01]
leoprint:  87%|########6 | 2081/2400 [1:07:06<14:39,  2.76s/it, lr: 5.0e-05 loss: 3.773e-01]
leoprint:  87%|########6 | 2081/2400 [1:07:10<14:39,  2.76s/it, lr: 5.0e-05 loss: 1.934e-01]
leoprint:  87%|########6 | 2081/2400 [1:07:10<14:39,  2.76s/it, lr: 5.0e-05 loss: 1.934e-01]
leoprint:  87%|########6 | 2082/2400 [1:07:10<15:45,  2.97s/it, lr: 5.0e-05 loss: 1.934e-01]
leoprint:  87%|########6 | 2082/2400 [1:07:10<15:45,  2.97s/it, lr: 5.0e-05 loss: 1.934e-01]
leoprint:  87%|########6 | 2082/2400 [1:07:14<15:45,  2.97s/it, lr: 5.0e-05 loss: 2.851e-01]
leoprint:  87%|########6 | 2082/2400 [1:07:14<15:45,  2.97s/it, lr: 5.0e-05 loss: 2.851e-01]
leoprint:  87%|########6 | 2083/2400 [1:07:14<16:27,  3.11s/it, lr: 5.0e-05 loss: 2.851e-01]
leoprint:  87%|########6 | 2083/2400 [1:07:14<16:27,  3.11s/it, lr: 5.0e-05 loss: 2.851e-01]
leoprint:  87%|########6 | 2083/2400 [1:07:17<16:27,  3.11s/it, lr: 5.0e-05 loss: 3.187e-01]
leoprint:  87%|########6 | 2083/2400 [1:07:17<16:27,  3.11s/it, lr: 5.0e-05 loss: 3.187e-01]
leoprint:  87%|########6 | 2084/2400 [1:07:17<16:58,  3.22s/it, lr: 5.0e-05 loss: 3.187e-01]
leoprint:  87%|########6 | 2084/2400 [1:07:17<16:58,  3.22s/it, lr: 5.0e-05 loss: 3.187e-01]
leoprint:  87%|########6 | 2084/2400 [1:07:21<16:58,  3.22s/it, lr: 5.0e-05 loss: 2.684e-01]
leoprint:  87%|########6 | 2084/2400 [1:07:21<16:58,  3.22s/it, lr: 5.0e-05 loss: 2.684e-01]
leoprint:  87%|########6 | 2085/2400 [1:07:21<17:20,  3.30s/it, lr: 5.0e-05 loss: 2.684e-01]
leoprint:  87%|########6 | 2085/2400 [1:07:21<17:20,  3.30s/it, lr: 5.0e-05 loss: 2.684e-01]
leoprint:  87%|########6 | 2085/2400 [1:07:24<17:20,  3.30s/it, lr: 5.0e-05 loss: 1.807e-01]
leoprint:  87%|########6 | 2085/2400 [1:07:24<17:20,  3.30s/it, lr: 5.0e-05 loss: 1.807e-01]
leoprint:  87%|########6 | 2086/2400 [1:07:24<17:45,  3.39s/it, lr: 5.0e-05 loss: 1.807e-01]
leoprint:  87%|########6 | 2086/2400 [1:07:24<17:45,  3.39s/it, lr: 5.0e-05 loss: 1.807e-01]
leoprint:  87%|########6 | 2086/2400 [1:07:28<17:45,  3.39s/it, lr: 5.0e-05 loss: 3.084e-01]
leoprint:  87%|########6 | 2086/2400 [1:07:28<17:45,  3.39s/it, lr: 5.0e-05 loss: 3.084e-01]
leoprint:  87%|########6 | 2087/2400 [1:07:28<18:04,  3.47s/it, lr: 5.0e-05 loss: 3.084e-01]
leoprint:  87%|########6 | 2087/2400 [1:07:28<18:04,  3.47s/it, lr: 5.0e-05 loss: 3.084e-01]
leoprint:  87%|########6 | 2087/2400 [1:07:31<18:04,  3.47s/it, lr: 5.0e-05 loss: 2.901e-01]
leoprint:  87%|########6 | 2087/2400 [1:07:31<18:04,  3.47s/it, lr: 5.0e-05 loss: 2.901e-01]
leoprint:  87%|########7 | 2088/2400 [1:07:31<18:04,  3.48s/it, lr: 5.0e-05 loss: 2.901e-01]
leoprint:  87%|########7 | 2088/2400 [1:07:31<18:04,  3.48s/it, lr: 5.0e-05 loss: 2.901e-01]
leoprint:  87%|########7 | 2088/2400 [1:07:35<18:04,  3.48s/it, lr: 5.0e-05 loss: 2.096e-01]
leoprint:  87%|########7 | 2088/2400 [1:07:35<18:04,  3.48s/it, lr: 5.0e-05 loss: 2.096e-01]
leoprint:  87%|########7 | 2089/2400 [1:07:35<18:15,  3.52s/it, lr: 5.0e-05 loss: 2.096e-01]
leoprint:  87%|########7 | 2089/2400 [1:07:35<18:15,  3.52s/it, lr: 5.0e-05 loss: 2.096e-01]
leoprint:  87%|########7 | 2089/2400 [1:07:39<18:15,  3.52s/it, lr: 5.0e-05 loss: 2.030e-01]
leoprint:  87%|########7 | 2089/2400 [1:07:39<18:15,  3.52s/it, lr: 5.0e-05 loss: 2.030e-01]
leoprint:  87%|########7 | 2090/2400 [1:07:42<18:12,  3.52s/it, lr: 5.0e-05 loss: 3.249e-01]
leoprint:  87%|########7 | 2090/2400 [1:07:42<18:12,  3.52s/it, lr: 5.0e-05 loss: 3.249e-01]
leoprint:  87%|########7 | 2091/2400 [1:07:42<13:58,  2.71s/it, lr: 5.0e-05 loss: 3.249e-01]
leoprint:  87%|########7 | 2091/2400 [1:07:42<13:58,  2.71s/it, lr: 5.0e-05 loss: 3.249e-01]
leoprint:  87%|########7 | 2091/2400 [1:07:46<13:58,  2.71s/it, lr: 5.0e-05 loss: 2.447e-01]
leoprint:  87%|########7 | 2091/2400 [1:07:46<13:58,  2.71s/it, lr: 5.0e-05 loss: 2.447e-01]
leoprint:  87%|########7 | 2092/2400 [1:07:46<15:17,  2.98s/it, lr: 5.0e-05 loss: 2.447e-01]
leoprint:  87%|########7 | 2092/2400 [1:07:46<15:17,  2.98s/it, lr: 5.0e-05 loss: 2.447e-01]
leoprint:  87%|########7 | 2092/2400 [1:07:50<15:17,  2.98s/it, lr: 5.0e-05 loss: 2.209e-01]
leoprint:  87%|########7 | 2092/2400 [1:07:50<15:17,  2.98s/it, lr: 5.0e-05 loss: 2.209e-01]
leoprint:  87%|########7 | 2093/2400 [1:07:50<15:57,  3.12s/it, lr: 5.0e-05 loss: 2.209e-01]
leoprint:  87%|########7 | 2093/2400 [1:07:50<15:57,  3.12s/it, lr: 5.0e-05 loss: 2.209e-01]
leoprint:  87%|########7 | 2093/2400 [1:07:53<15:57,  3.12s/it, lr: 5.0e-05 loss: 3.403e-01]
leoprint:  87%|########7 | 2093/2400 [1:07:53<15:57,  3.12s/it, lr: 5.0e-05 loss: 3.403e-01]
leoprint:  87%|########7 | 2094/2400 [1:07:53<16:26,  3.22s/it, lr: 5.0e-05 loss: 3.403e-01]
leoprint:  87%|########7 | 2094/2400 [1:07:53<16:26,  3.22s/it, lr: 5.0e-05 loss: 3.403e-01]
leoprint:  87%|########7 | 2094/2400 [1:07:57<16:26,  3.22s/it, lr: 5.0e-05 loss: 3.721e-01]
leoprint:  87%|########7 | 2094/2400 [1:07:57<16:26,  3.22s/it, lr: 5.0e-05 loss: 3.721e-01]
leoprint:  87%|########7 | 2095/2400 [1:07:57<16:46,  3.30s/it, lr: 5.0e-05 loss: 3.721e-01]
leoprint:  87%|########7 | 2095/2400 [1:07:57<16:46,  3.30s/it, lr: 5.0e-05 loss: 3.721e-01]
leoprint:  87%|########7 | 2095/2400 [1:08:00<16:46,  3.30s/it, lr: 5.0e-05 loss: 3.258e-01]
leoprint:  87%|########7 | 2095/2400 [1:08:00<16:46,  3.30s/it, lr: 5.0e-05 loss: 3.258e-01]
leoprint:  87%|########7 | 2096/2400 [1:08:00<17:01,  3.36s/it, lr: 5.0e-05 loss: 3.258e-01]
leoprint:  87%|########7 | 2096/2400 [1:08:00<17:01,  3.36s/it, lr: 5.0e-05 loss: 3.258e-01]
leoprint:  87%|########7 | 2096/2400 [1:08:04<17:01,  3.36s/it, lr: 5.0e-05 loss: 3.471e-01]
leoprint:  87%|########7 | 2096/2400 [1:08:04<17:01,  3.36s/it, lr: 5.0e-05 loss: 3.471e-01]
leoprint:  87%|########7 | 2097/2400 [1:08:04<17:11,  3.40s/it, lr: 5.0e-05 loss: 3.471e-01]
leoprint:  87%|########7 | 2097/2400 [1:08:04<17:11,  3.40s/it, lr: 5.0e-05 loss: 3.471e-01]
leoprint:  87%|########7 | 2097/2400 [1:08:07<17:11,  3.40s/it, lr: 5.0e-05 loss: 3.090e-01]
leoprint:  87%|########7 | 2097/2400 [1:08:07<17:11,  3.40s/it, lr: 5.0e-05 loss: 3.090e-01]
leoprint:  87%|########7 | 2098/2400 [1:08:07<17:23,  3.45s/it, lr: 5.0e-05 loss: 3.090e-01]
leoprint:  87%|########7 | 2098/2400 [1:08:07<17:23,  3.45s/it, lr: 5.0e-05 loss: 3.090e-01]
leoprint:  87%|########7 | 2098/2400 [1:08:11<17:23,  3.45s/it, lr: 5.0e-05 loss: 2.586e-01]
leoprint:  87%|########7 | 2098/2400 [1:08:11<17:23,  3.45s/it, lr: 5.0e-05 loss: 2.586e-01]
leoprint:  87%|########7 | 2099/2400 [1:08:11<17:24,  3.47s/it, lr: 5.0e-05 loss: 2.586e-01]
leoprint:  87%|########7 | 2099/2400 [1:08:11<17:24,  3.47s/it, lr: 5.0e-05 loss: 2.586e-01]
leoprint:  87%|########7 | 2099/2400 [1:08:14<17:24,  3.47s/it, lr: 5.0e-05 loss: 2.423e-01]
leoprint:  87%|########7 | 2099/2400 [1:08:14<17:24,  3.47s/it, lr: 5.0e-05 loss: 2.423e-01]
leoprint:  88%|########7 | 2100/2400 [1:08:18<17:20,  3.47s/it, lr: 5.0e-05 loss: 3.070e-01]
leoprint:  88%|########7 | 2100/2400 [1:08:18<17:20,  3.47s/it, lr: 5.0e-05 loss: 3.070e-01]
leoprint:  88%|########7 | 2101/2400 [1:08:18<13:22,  2.68s/it, lr: 5.0e-05 loss: 3.070e-01]
leoprint:  88%|########7 | 2101/2400 [1:08:18<13:22,  2.68s/it, lr: 5.0e-05 loss: 3.070e-01]
leoprint:  88%|########7 | 2101/2400 [1:08:21<13:22,  2.68s/it, lr: 5.0e-05 loss: 2.562e-01]
leoprint:  88%|########7 | 2101/2400 [1:08:21<13:22,  2.68s/it, lr: 5.0e-05 loss: 2.562e-01]
leoprint:  88%|########7 | 2102/2400 [1:08:21<14:20,  2.89s/it, lr: 5.0e-05 loss: 2.562e-01]
leoprint:  88%|########7 | 2102/2400 [1:08:21<14:20,  2.89s/it, lr: 5.0e-05 loss: 2.562e-01]
leoprint:  88%|########7 | 2102/2400 [1:08:25<14:20,  2.89s/it, lr: 5.0e-05 loss: 1.965e-01]
leoprint:  88%|########7 | 2102/2400 [1:08:25<14:20,  2.89s/it, lr: 5.0e-05 loss: 1.965e-01]
leoprint:  88%|########7 | 2103/2400 [1:08:25<15:14,  3.08s/it, lr: 5.0e-05 loss: 1.965e-01]
leoprint:  88%|########7 | 2103/2400 [1:08:25<15:14,  3.08s/it, lr: 5.0e-05 loss: 1.965e-01]
leoprint:  88%|########7 | 2103/2400 [1:08:29<15:14,  3.08s/it, lr: 5.0e-05 loss: 3.096e-01]
leoprint:  88%|########7 | 2103/2400 [1:08:29<15:14,  3.08s/it, lr: 5.0e-05 loss: 3.096e-01]
leoprint:  88%|########7 | 2104/2400 [1:08:29<16:13,  3.29s/it, lr: 5.0e-05 loss: 3.096e-01]
leoprint:  88%|########7 | 2104/2400 [1:08:29<16:13,  3.29s/it, lr: 5.0e-05 loss: 3.096e-01]
leoprint:  88%|########7 | 2104/2400 [1:08:32<16:13,  3.29s/it, lr: 5.0e-05 loss: 2.114e-01]
leoprint:  88%|########7 | 2104/2400 [1:08:32<16:13,  3.29s/it, lr: 5.0e-05 loss: 2.114e-01]
leoprint:  88%|########7 | 2105/2400 [1:08:32<16:27,  3.35s/it, lr: 5.0e-05 loss: 2.114e-01]
leoprint:  88%|########7 | 2105/2400 [1:08:32<16:27,  3.35s/it, lr: 5.0e-05 loss: 2.114e-01]
leoprint:  88%|########7 | 2105/2400 [1:08:36<16:27,  3.35s/it, lr: 5.0e-05 loss: 4.114e-01]
leoprint:  88%|########7 | 2105/2400 [1:08:36<16:27,  3.35s/it, lr: 5.0e-05 loss: 4.114e-01]
leoprint:  88%|########7 | 2106/2400 [1:08:36<16:38,  3.39s/it, lr: 5.0e-05 loss: 4.114e-01]
leoprint:  88%|########7 | 2106/2400 [1:08:36<16:38,  3.39s/it, lr: 5.0e-05 loss: 4.114e-01]
leoprint:  88%|########7 | 2106/2400 [1:08:39<16:38,  3.39s/it, lr: 5.0e-05 loss: 3.529e-01]
leoprint:  88%|########7 | 2106/2400 [1:08:39<16:38,  3.39s/it, lr: 5.0e-05 loss: 3.529e-01]
leoprint:  88%|########7 | 2107/2400 [1:08:39<16:43,  3.43s/it, lr: 5.0e-05 loss: 3.529e-01]
leoprint:  88%|########7 | 2107/2400 [1:08:39<16:43,  3.43s/it, lr: 5.0e-05 loss: 3.529e-01]
leoprint:  88%|########7 | 2107/2400 [1:08:43<16:43,  3.43s/it, lr: 5.0e-05 loss: 1.818e-01]
leoprint:  88%|########7 | 2107/2400 [1:08:43<16:43,  3.43s/it, lr: 5.0e-05 loss: 1.818e-01]
leoprint:  88%|########7 | 2108/2400 [1:08:43<16:57,  3.48s/it, lr: 5.0e-05 loss: 1.818e-01]
leoprint:  88%|########7 | 2108/2400 [1:08:43<16:57,  3.48s/it, lr: 5.0e-05 loss: 1.818e-01]
leoprint:  88%|########7 | 2108/2400 [1:08:46<16:57,  3.48s/it, lr: 5.0e-05 loss: 4.064e-01]
leoprint:  88%|########7 | 2108/2400 [1:08:46<16:57,  3.48s/it, lr: 5.0e-05 loss: 4.064e-01]
leoprint:  88%|########7 | 2109/2400 [1:08:46<16:56,  3.49s/it, lr: 5.0e-05 loss: 4.064e-01]
leoprint:  88%|########7 | 2109/2400 [1:08:46<16:56,  3.49s/it, lr: 5.0e-05 loss: 4.064e-01]
leoprint:  88%|########7 | 2109/2400 [1:08:50<16:56,  3.49s/it, lr: 5.0e-05 loss: 3.887e-01]
leoprint:  88%|########7 | 2109/2400 [1:08:50<16:56,  3.49s/it, lr: 5.0e-05 loss: 3.887e-01]
leoprint:  88%|########7 | 2110/2400 [1:08:54<16:52,  3.49s/it, lr: 5.0e-05 loss: 2.849e-01]
leoprint:  88%|########7 | 2110/2400 [1:08:54<16:52,  3.49s/it, lr: 5.0e-05 loss: 2.849e-01]
leoprint:  88%|########7 | 2111/2400 [1:08:54<12:59,  2.70s/it, lr: 5.0e-05 loss: 2.849e-01]
leoprint:  88%|########7 | 2111/2400 [1:08:54<12:59,  2.70s/it, lr: 5.0e-05 loss: 2.849e-01]
leoprint:  88%|########7 | 2111/2400 [1:08:57<12:59,  2.70s/it, lr: 5.0e-05 loss: 3.525e-01]
leoprint:  88%|########7 | 2111/2400 [1:08:57<12:59,  2.70s/it, lr: 5.0e-05 loss: 3.525e-01]
leoprint:  88%|########8 | 2112/2400 [1:08:57<13:54,  2.90s/it, lr: 5.0e-05 loss: 3.525e-01]
leoprint:  88%|########8 | 2112/2400 [1:08:57<13:54,  2.90s/it, lr: 5.0e-05 loss: 3.525e-01]
leoprint:  88%|########8 | 2112/2400 [1:09:01<13:54,  2.90s/it, lr: 5.0e-05 loss: 3.292e-01]
leoprint:  88%|########8 | 2112/2400 [1:09:01<13:54,  2.90s/it, lr: 5.0e-05 loss: 3.292e-01]
leoprint:  88%|########8 | 2113/2400 [1:09:01<14:36,  3.06s/it, lr: 5.0e-05 loss: 3.292e-01]
leoprint:  88%|########8 | 2113/2400 [1:09:01<14:36,  3.06s/it, lr: 5.0e-05 loss: 3.292e-01]
leoprint:  88%|########8 | 2113/2400 [1:09:04<14:36,  3.06s/it, lr: 5.0e-05 loss: 2.385e-01]
leoprint:  88%|########8 | 2113/2400 [1:09:04<14:36,  3.06s/it, lr: 5.0e-05 loss: 2.385e-01]
leoprint:  88%|########8 | 2114/2400 [1:09:04<15:08,  3.18s/it, lr: 5.0e-05 loss: 2.385e-01]
leoprint:  88%|########8 | 2114/2400 [1:09:04<15:08,  3.18s/it, lr: 5.0e-05 loss: 2.385e-01]
leoprint:  88%|########8 | 2114/2400 [1:09:08<15:08,  3.18s/it, lr: 5.0e-05 loss: 3.494e-01]
leoprint:  88%|########8 | 2114/2400 [1:09:08<15:08,  3.18s/it, lr: 5.0e-05 loss: 3.494e-01]
leoprint:  88%|########8 | 2115/2400 [1:09:08<15:44,  3.31s/it, lr: 5.0e-05 loss: 3.494e-01]
leoprint:  88%|########8 | 2115/2400 [1:09:08<15:44,  3.31s/it, lr: 5.0e-05 loss: 3.494e-01]
leoprint:  88%|########8 | 2115/2400 [1:09:11<15:44,  3.31s/it, lr: 5.0e-05 loss: 3.398e-01]
leoprint:  88%|########8 | 2115/2400 [1:09:11<15:44,  3.31s/it, lr: 5.0e-05 loss: 3.398e-01]
leoprint:  88%|########8 | 2116/2400 [1:09:11<15:56,  3.37s/it, lr: 5.0e-05 loss: 3.398e-01]
leoprint:  88%|########8 | 2116/2400 [1:09:11<15:56,  3.37s/it, lr: 5.0e-05 loss: 3.398e-01]
leoprint:  88%|########8 | 2116/2400 [1:09:15<15:56,  3.37s/it, lr: 5.0e-05 loss: 2.388e-01]
leoprint:  88%|########8 | 2116/2400 [1:09:15<15:56,  3.37s/it, lr: 5.0e-05 loss: 2.388e-01]
leoprint:  88%|########8 | 2117/2400 [1:09:15<16:14,  3.44s/it, lr: 5.0e-05 loss: 2.388e-01]
leoprint:  88%|########8 | 2117/2400 [1:09:15<16:14,  3.44s/it, lr: 5.0e-05 loss: 2.388e-01]
leoprint:  88%|########8 | 2117/2400 [1:09:19<16:14,  3.44s/it, lr: 5.0e-05 loss: 2.348e-01]
leoprint:  88%|########8 | 2117/2400 [1:09:19<16:14,  3.44s/it, lr: 5.0e-05 loss: 2.348e-01]
leoprint:  88%|########8 | 2118/2400 [1:09:19<16:27,  3.50s/it, lr: 5.0e-05 loss: 2.348e-01]
leoprint:  88%|########8 | 2118/2400 [1:09:19<16:27,  3.50s/it, lr: 5.0e-05 loss: 2.348e-01]
leoprint:  88%|########8 | 2118/2400 [1:09:22<16:27,  3.50s/it, lr: 5.0e-05 loss: 1.758e-01]
leoprint:  88%|########8 | 2118/2400 [1:09:22<16:27,  3.50s/it, lr: 5.0e-05 loss: 1.758e-01]
leoprint:  88%|########8 | 2119/2400 [1:09:22<16:35,  3.54s/it, lr: 5.0e-05 loss: 1.758e-01]
leoprint:  88%|########8 | 2119/2400 [1:09:22<16:35,  3.54s/it, lr: 5.0e-05 loss: 1.758e-01]
leoprint:  88%|########8 | 2119/2400 [1:09:26<16:35,  3.54s/it, lr: 5.0e-05 loss: 2.568e-01]
leoprint:  88%|########8 | 2119/2400 [1:09:26<16:35,  3.54s/it, lr: 5.0e-05 loss: 2.568e-01]
leoprint:  88%|########8 | 2120/2400 [1:09:29<16:31,  3.54s/it, lr: 5.0e-05 loss: 2.988e-01]
leoprint:  88%|########8 | 2120/2400 [1:09:29<16:31,  3.54s/it, lr: 5.0e-05 loss: 2.988e-01]
leoprint:  88%|########8 | 2121/2400 [1:09:29<12:44,  2.74s/it, lr: 5.0e-05 loss: 2.988e-01]
leoprint:  88%|########8 | 2121/2400 [1:09:29<12:44,  2.74s/it, lr: 5.0e-05 loss: 2.988e-01]
leoprint:  88%|########8 | 2121/2400 [1:09:33<12:44,  2.74s/it, lr: 5.0e-05 loss: 2.311e-01]
leoprint:  88%|########8 | 2121/2400 [1:09:33<12:44,  2.74s/it, lr: 5.0e-05 loss: 2.311e-01]
leoprint:  88%|########8 | 2122/2400 [1:09:33<13:34,  2.93s/it, lr: 5.0e-05 loss: 2.311e-01]
leoprint:  88%|########8 | 2122/2400 [1:09:33<13:34,  2.93s/it, lr: 5.0e-05 loss: 2.311e-01]
leoprint:  88%|########8 | 2122/2400 [1:09:36<13:34,  2.93s/it, lr: 5.0e-05 loss: 3.203e-01]
leoprint:  88%|########8 | 2122/2400 [1:09:36<13:34,  2.93s/it, lr: 5.0e-05 loss: 3.203e-01]
leoprint:  88%|########8 | 2123/2400 [1:09:36<14:13,  3.08s/it, lr: 5.0e-05 loss: 3.203e-01]
leoprint:  88%|########8 | 2123/2400 [1:09:36<14:13,  3.08s/it, lr: 5.0e-05 loss: 3.203e-01]
leoprint:  88%|########8 | 2123/2400 [1:09:40<14:13,  3.08s/it, lr: 5.0e-05 loss: 3.683e-01]
leoprint:  88%|########8 | 2123/2400 [1:09:40<14:13,  3.08s/it, lr: 5.0e-05 loss: 3.683e-01]
leoprint:  88%|########8 | 2124/2400 [1:09:40<14:42,  3.20s/it, lr: 5.0e-05 loss: 3.683e-01]
leoprint:  88%|########8 | 2124/2400 [1:09:40<14:42,  3.20s/it, lr: 5.0e-05 loss: 3.683e-01]
leoprint:  88%|########8 | 2124/2400 [1:09:44<14:42,  3.20s/it, lr: 5.0e-05 loss: 2.567e-01]
leoprint:  88%|########8 | 2124/2400 [1:09:44<14:42,  3.20s/it, lr: 5.0e-05 loss: 2.567e-01]
leoprint:  89%|########8 | 2125/2400 [1:09:44<15:12,  3.32s/it, lr: 5.0e-05 loss: 2.567e-01]
leoprint:  89%|########8 | 2125/2400 [1:09:44<15:12,  3.32s/it, lr: 5.0e-05 loss: 2.567e-01]
leoprint:  89%|########8 | 2125/2400 [1:09:47<15:12,  3.32s/it, lr: 5.0e-05 loss: 2.869e-01]
leoprint:  89%|########8 | 2125/2400 [1:09:47<15:12,  3.32s/it, lr: 5.0e-05 loss: 2.869e-01]
leoprint:  89%|########8 | 2126/2400 [1:09:47<15:24,  3.37s/it, lr: 5.0e-05 loss: 2.869e-01]
leoprint:  89%|########8 | 2126/2400 [1:09:47<15:24,  3.37s/it, lr: 5.0e-05 loss: 2.869e-01]
leoprint:  89%|########8 | 2126/2400 [1:09:51<15:24,  3.37s/it, lr: 5.0e-05 loss: 3.786e-01]
leoprint:  89%|########8 | 2126/2400 [1:09:51<15:24,  3.37s/it, lr: 5.0e-05 loss: 3.786e-01]
leoprint:  89%|########8 | 2127/2400 [1:09:51<15:48,  3.48s/it, lr: 5.0e-05 loss: 3.786e-01]
leoprint:  89%|########8 | 2127/2400 [1:09:51<15:48,  3.48s/it, lr: 5.0e-05 loss: 3.786e-01]
leoprint:  89%|########8 | 2127/2400 [1:09:54<15:48,  3.48s/it, lr: 5.0e-05 loss: 2.084e-01]
leoprint:  89%|########8 | 2127/2400 [1:09:54<15:48,  3.48s/it, lr: 5.0e-05 loss: 2.084e-01]
leoprint:  89%|########8 | 2128/2400 [1:09:54<15:57,  3.52s/it, lr: 5.0e-05 loss: 2.084e-01]
leoprint:  89%|########8 | 2128/2400 [1:09:54<15:57,  3.52s/it, lr: 5.0e-05 loss: 2.084e-01]
leoprint:  89%|########8 | 2128/2400 [1:09:58<15:57,  3.52s/it, lr: 5.0e-05 loss: 2.947e-01]
leoprint:  89%|########8 | 2128/2400 [1:09:58<15:57,  3.52s/it, lr: 5.0e-05 loss: 2.947e-01]
leoprint:  89%|########8 | 2129/2400 [1:09:58<15:52,  3.52s/it, lr: 5.0e-05 loss: 2.947e-01]
leoprint:  89%|########8 | 2129/2400 [1:09:58<15:52,  3.52s/it, lr: 5.0e-05 loss: 2.947e-01]
leoprint:  89%|########8 | 2129/2400 [1:10:02<15:52,  3.52s/it, lr: 5.0e-05 loss: 3.117e-01]
leoprint:  89%|########8 | 2129/2400 [1:10:02<15:52,  3.52s/it, lr: 5.0e-05 loss: 3.117e-01]
leoprint:  89%|########8 | 2130/2400 [1:10:05<15:49,  3.52s/it, lr: 5.0e-05 loss: 3.824e-01]
leoprint:  89%|########8 | 2130/2400 [1:10:05<15:49,  3.52s/it, lr: 5.0e-05 loss: 3.824e-01]
leoprint:  89%|########8 | 2131/2400 [1:10:05<12:08,  2.71s/it, lr: 5.0e-05 loss: 3.824e-01]
leoprint:  89%|########8 | 2131/2400 [1:10:05<12:08,  2.71s/it, lr: 5.0e-05 loss: 3.824e-01]
leoprint:  89%|########8 | 2131/2400 [1:10:09<12:08,  2.71s/it, lr: 5.0e-05 loss: 3.939e-01]
leoprint:  89%|########8 | 2131/2400 [1:10:09<12:08,  2.71s/it, lr: 5.0e-05 loss: 3.939e-01]
leoprint:  89%|########8 | 2132/2400 [1:10:09<12:58,  2.90s/it, lr: 5.0e-05 loss: 3.939e-01]
leoprint:  89%|########8 | 2132/2400 [1:10:09<12:58,  2.90s/it, lr: 5.0e-05 loss: 3.939e-01]
leoprint:  89%|########8 | 2132/2400 [1:10:12<12:58,  2.90s/it, lr: 5.0e-05 loss: 3.366e-01]
leoprint:  89%|########8 | 2132/2400 [1:10:12<12:58,  2.90s/it, lr: 5.0e-05 loss: 3.366e-01]
leoprint:  89%|########8 | 2133/2400 [1:10:12<13:54,  3.13s/it, lr: 5.0e-05 loss: 3.366e-01]
leoprint:  89%|########8 | 2133/2400 [1:10:12<13:54,  3.13s/it, lr: 5.0e-05 loss: 3.366e-01]
leoprint:  89%|########8 | 2133/2400 [1:10:16<13:54,  3.13s/it, lr: 5.0e-05 loss: 2.403e-01]
leoprint:  89%|########8 | 2133/2400 [1:10:16<13:54,  3.13s/it, lr: 5.0e-05 loss: 2.403e-01]
leoprint:  89%|########8 | 2134/2400 [1:10:16<14:27,  3.26s/it, lr: 5.0e-05 loss: 2.403e-01]
leoprint:  89%|########8 | 2134/2400 [1:10:16<14:27,  3.26s/it, lr: 5.0e-05 loss: 2.403e-01]
leoprint:  89%|########8 | 2134/2400 [1:10:19<14:27,  3.26s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  89%|########8 | 2134/2400 [1:10:19<14:27,  3.26s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  89%|########8 | 2135/2400 [1:10:20<14:42,  3.33s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  89%|########8 | 2135/2400 [1:10:20<14:42,  3.33s/it, lr: 5.0e-05 loss: 2.550e-01]
leoprint:  89%|########8 | 2135/2400 [1:10:23<14:42,  3.33s/it, lr: 5.0e-05 loss: 2.855e-01]
leoprint:  89%|########8 | 2135/2400 [1:10:23<14:42,  3.33s/it, lr: 5.0e-05 loss: 2.855e-01]
leoprint:  89%|########9 | 2136/2400 [1:10:23<14:52,  3.38s/it, lr: 5.0e-05 loss: 2.855e-01]
leoprint:  89%|########9 | 2136/2400 [1:10:23<14:52,  3.38s/it, lr: 5.0e-05 loss: 2.855e-01]
leoprint:  89%|########9 | 2136/2400 [1:10:27<14:52,  3.38s/it, lr: 5.0e-05 loss: 2.780e-01]
leoprint:  89%|########9 | 2136/2400 [1:10:27<14:52,  3.38s/it, lr: 5.0e-05 loss: 2.780e-01]
leoprint:  89%|########9 | 2137/2400 [1:10:27<14:58,  3.42s/it, lr: 5.0e-05 loss: 2.780e-01]
leoprint:  89%|########9 | 2137/2400 [1:10:27<14:58,  3.42s/it, lr: 5.0e-05 loss: 2.780e-01]
leoprint:  89%|########9 | 2137/2400 [1:10:30<14:58,  3.42s/it, lr: 5.0e-05 loss: 2.174e-01]
leoprint:  89%|########9 | 2137/2400 [1:10:30<14:58,  3.42s/it, lr: 5.0e-05 loss: 2.174e-01]
leoprint:  89%|########9 | 2138/2400 [1:10:30<15:08,  3.47s/it, lr: 5.0e-05 loss: 2.174e-01]
leoprint:  89%|########9 | 2138/2400 [1:10:30<15:08,  3.47s/it, lr: 5.0e-05 loss: 2.174e-01]
leoprint:  89%|########9 | 2138/2400 [1:10:34<15:08,  3.47s/it, lr: 5.0e-05 loss: 2.005e-01]
leoprint:  89%|########9 | 2138/2400 [1:10:34<15:08,  3.47s/it, lr: 5.0e-05 loss: 2.005e-01]
leoprint:  89%|########9 | 2139/2400 [1:10:34<15:17,  3.52s/it, lr: 5.0e-05 loss: 2.005e-01]
leoprint:  89%|########9 | 2139/2400 [1:10:34<15:17,  3.52s/it, lr: 5.0e-05 loss: 2.005e-01]
leoprint:  89%|########9 | 2139/2400 [1:10:37<15:17,  3.52s/it, lr: 5.0e-05 loss: 3.696e-01]
leoprint:  89%|########9 | 2139/2400 [1:10:37<15:17,  3.52s/it, lr: 5.0e-05 loss: 3.696e-01]
leoprint:  89%|########9 | 2140/2400 [1:10:41<15:14,  3.52s/it, lr: 5.0e-05 loss: 2.694e-01]
leoprint:  89%|########9 | 2140/2400 [1:10:41<15:14,  3.52s/it, lr: 5.0e-05 loss: 2.694e-01]
leoprint:  89%|########9 | 2141/2400 [1:10:41<11:41,  2.71s/it, lr: 5.0e-05 loss: 2.694e-01]
leoprint:  89%|########9 | 2141/2400 [1:10:41<11:41,  2.71s/it, lr: 5.0e-05 loss: 2.694e-01]
leoprint:  89%|########9 | 2141/2400 [1:10:44<11:41,  2.71s/it, lr: 5.0e-05 loss: 2.512e-01]
leoprint:  89%|########9 | 2141/2400 [1:10:44<11:41,  2.71s/it, lr: 5.0e-05 loss: 2.512e-01]
leoprint:  89%|########9 | 2142/2400 [1:10:44<12:29,  2.90s/it, lr: 5.0e-05 loss: 2.512e-01]
leoprint:  89%|########9 | 2142/2400 [1:10:44<12:29,  2.90s/it, lr: 5.0e-05 loss: 2.512e-01]
leoprint:  89%|########9 | 2142/2400 [1:10:48<12:29,  2.90s/it, lr: 5.0e-05 loss: 1.997e-01]
leoprint:  89%|########9 | 2142/2400 [1:10:48<12:29,  2.90s/it, lr: 5.0e-05 loss: 1.997e-01]
leoprint:  89%|########9 | 2143/2400 [1:10:48<13:14,  3.09s/it, lr: 5.0e-05 loss: 1.997e-01]
leoprint:  89%|########9 | 2143/2400 [1:10:48<13:14,  3.09s/it, lr: 5.0e-05 loss: 1.997e-01]
leoprint:  89%|########9 | 2143/2400 [1:10:52<13:14,  3.09s/it, lr: 5.0e-05 loss: 2.654e-01]
leoprint:  89%|########9 | 2143/2400 [1:10:52<13:14,  3.09s/it, lr: 5.0e-05 loss: 2.654e-01]
leoprint:  89%|########9 | 2144/2400 [1:10:52<13:53,  3.26s/it, lr: 5.0e-05 loss: 2.654e-01]
leoprint:  89%|########9 | 2144/2400 [1:10:52<13:53,  3.26s/it, lr: 5.0e-05 loss: 2.654e-01]
leoprint:  89%|########9 | 2144/2400 [1:10:55<13:53,  3.26s/it, lr: 5.0e-05 loss: 2.811e-01]
leoprint:  89%|########9 | 2144/2400 [1:10:55<13:53,  3.26s/it, lr: 5.0e-05 loss: 2.811e-01]
leoprint:  89%|########9 | 2145/2400 [1:10:55<14:08,  3.33s/it, lr: 5.0e-05 loss: 2.811e-01]
leoprint:  89%|########9 | 2145/2400 [1:10:55<14:08,  3.33s/it, lr: 5.0e-05 loss: 2.811e-01]
leoprint:  89%|########9 | 2145/2400 [1:10:59<14:08,  3.33s/it, lr: 5.0e-05 loss: 3.654e-01]
leoprint:  89%|########9 | 2145/2400 [1:10:59<14:08,  3.33s/it, lr: 5.0e-05 loss: 3.654e-01]
leoprint:  89%|########9 | 2146/2400 [1:10:59<14:17,  3.38s/it, lr: 5.0e-05 loss: 3.654e-01]
leoprint:  89%|########9 | 2146/2400 [1:10:59<14:17,  3.38s/it, lr: 5.0e-05 loss: 3.654e-01]
leoprint:  89%|########9 | 2146/2400 [1:11:02<14:17,  3.38s/it, lr: 5.0e-05 loss: 2.345e-01]
leoprint:  89%|########9 | 2146/2400 [1:11:02<14:17,  3.38s/it, lr: 5.0e-05 loss: 2.345e-01]
leoprint:  89%|########9 | 2147/2400 [1:11:02<14:24,  3.42s/it, lr: 5.0e-05 loss: 2.345e-01]
leoprint:  89%|########9 | 2147/2400 [1:11:02<14:24,  3.42s/it, lr: 5.0e-05 loss: 2.345e-01]
leoprint:  89%|########9 | 2147/2400 [1:11:06<14:24,  3.42s/it, lr: 5.0e-05 loss: 2.472e-01]
leoprint:  89%|########9 | 2147/2400 [1:11:06<14:24,  3.42s/it, lr: 5.0e-05 loss: 2.472e-01]
leoprint:  90%|########9 | 2148/2400 [1:11:06<14:36,  3.48s/it, lr: 5.0e-05 loss: 2.472e-01]
leoprint:  90%|########9 | 2148/2400 [1:11:06<14:36,  3.48s/it, lr: 5.0e-05 loss: 2.472e-01]
leoprint:  90%|########9 | 2148/2400 [1:11:09<14:36,  3.48s/it, lr: 5.0e-05 loss: 2.437e-01]
leoprint:  90%|########9 | 2148/2400 [1:11:09<14:36,  3.48s/it, lr: 5.0e-05 loss: 2.437e-01]
leoprint:  90%|########9 | 2149/2400 [1:11:09<14:35,  3.49s/it, lr: 5.0e-05 loss: 2.437e-01]
leoprint:  90%|########9 | 2149/2400 [1:11:09<14:35,  3.49s/it, lr: 5.0e-05 loss: 2.437e-01]
leoprint:  90%|########9 | 2149/2400 [1:11:13<14:35,  3.49s/it, lr: 5.0e-05 loss: 3.996e-01]
leoprint:  90%|########9 | 2149/2400 [1:11:13<14:35,  3.49s/it, lr: 5.0e-05 loss: 3.996e-01]
leoprint:  90%|########9 | 2150/2400 [1:11:17<14:32,  3.49s/it, lr: 5.0e-05 loss: 1.842e-01]
leoprint:  90%|########9 | 2150/2400 [1:11:17<14:32,  3.49s/it, lr: 5.0e-05 loss: 1.842e-01]
leoprint:  90%|########9 | 2151/2400 [1:11:17<11:17,  2.72s/it, lr: 5.0e-05 loss: 1.842e-01]
leoprint:  90%|########9 | 2151/2400 [1:11:17<11:17,  2.72s/it, lr: 5.0e-05 loss: 1.842e-01]
leoprint:  90%|########9 | 2151/2400 [1:11:20<11:17,  2.72s/it, lr: 5.0e-05 loss: 3.129e-01]
leoprint:  90%|########9 | 2151/2400 [1:11:20<11:17,  2.72s/it, lr: 5.0e-05 loss: 3.129e-01]
leoprint:  90%|########9 | 2152/2400 [1:11:20<12:09,  2.94s/it, lr: 5.0e-05 loss: 3.129e-01]
leoprint:  90%|########9 | 2152/2400 [1:11:20<12:09,  2.94s/it, lr: 5.0e-05 loss: 3.129e-01]
leoprint:  90%|########9 | 2152/2400 [1:11:24<12:09,  2.94s/it, lr: 5.0e-05 loss: 2.958e-01]
leoprint:  90%|########9 | 2152/2400 [1:11:24<12:09,  2.94s/it, lr: 5.0e-05 loss: 2.958e-01]
leoprint:  90%|########9 | 2153/2400 [1:11:24<12:43,  3.09s/it, lr: 5.0e-05 loss: 2.958e-01]
leoprint:  90%|########9 | 2153/2400 [1:11:24<12:43,  3.09s/it, lr: 5.0e-05 loss: 2.958e-01]
leoprint:  90%|########9 | 2153/2400 [1:11:27<12:43,  3.09s/it, lr: 5.0e-05 loss: 2.689e-01]
leoprint:  90%|########9 | 2153/2400 [1:11:27<12:43,  3.09s/it, lr: 5.0e-05 loss: 2.689e-01]
leoprint:  90%|########9 | 2154/2400 [1:11:27<13:07,  3.20s/it, lr: 5.0e-05 loss: 2.689e-01]
leoprint:  90%|########9 | 2154/2400 [1:11:27<13:07,  3.20s/it, lr: 5.0e-05 loss: 2.689e-01]
leoprint:  90%|########9 | 2154/2400 [1:11:31<13:07,  3.20s/it, lr: 5.0e-05 loss: 2.671e-01]
leoprint:  90%|########9 | 2154/2400 [1:11:31<13:07,  3.20s/it, lr: 5.0e-05 loss: 2.671e-01]
leoprint:  90%|########9 | 2155/2400 [1:11:31<13:38,  3.34s/it, lr: 5.0e-05 loss: 2.671e-01]
leoprint:  90%|########9 | 2155/2400 [1:11:31<13:38,  3.34s/it, lr: 5.0e-05 loss: 2.671e-01]
leoprint:  90%|########9 | 2155/2400 [1:11:35<13:38,  3.34s/it, lr: 5.0e-05 loss: 2.458e-01]
leoprint:  90%|########9 | 2155/2400 [1:11:35<13:38,  3.34s/it, lr: 5.0e-05 loss: 2.458e-01]
leoprint:  90%|########9 | 2156/2400 [1:11:35<13:54,  3.42s/it, lr: 5.0e-05 loss: 2.458e-01]
leoprint:  90%|########9 | 2156/2400 [1:11:35<13:54,  3.42s/it, lr: 5.0e-05 loss: 2.458e-01]
leoprint:  90%|########9 | 2156/2400 [1:11:38<13:54,  3.42s/it, lr: 5.0e-05 loss: 2.992e-01]
leoprint:  90%|########9 | 2156/2400 [1:11:38<13:54,  3.42s/it, lr: 5.0e-05 loss: 2.992e-01]
leoprint:  90%|########9 | 2157/2400 [1:11:38<13:57,  3.45s/it, lr: 5.0e-05 loss: 2.992e-01]
leoprint:  90%|########9 | 2157/2400 [1:11:38<13:57,  3.45s/it, lr: 5.0e-05 loss: 2.992e-01]
leoprint:  90%|########9 | 2157/2400 [1:11:42<13:57,  3.45s/it, lr: 5.0e-05 loss: 3.740e-01]
leoprint:  90%|########9 | 2157/2400 [1:11:42<13:57,  3.45s/it, lr: 5.0e-05 loss: 3.740e-01]
leoprint:  90%|########9 | 2158/2400 [1:11:42<13:58,  3.47s/it, lr: 5.0e-05 loss: 3.740e-01]
leoprint:  90%|########9 | 2158/2400 [1:11:42<13:58,  3.47s/it, lr: 5.0e-05 loss: 3.740e-01]
leoprint:  90%|########9 | 2158/2400 [1:11:45<13:58,  3.47s/it, lr: 5.0e-05 loss: 3.530e-01]
leoprint:  90%|########9 | 2158/2400 [1:11:45<13:58,  3.47s/it, lr: 5.0e-05 loss: 3.530e-01]
leoprint:  90%|########9 | 2159/2400 [1:11:45<13:58,  3.48s/it, lr: 5.0e-05 loss: 3.530e-01]
leoprint:  90%|########9 | 2159/2400 [1:11:45<13:58,  3.48s/it, lr: 5.0e-05 loss: 3.530e-01]
leoprint:  90%|########9 | 2159/2400 [1:11:49<13:58,  3.48s/it, lr: 5.0e-05 loss: 2.534e-01]
leoprint:  90%|########9 | 2159/2400 [1:11:49<13:58,  3.48s/it, lr: 5.0e-05 loss: 2.534e-01]
leoprint:  90%|######### | 2160/2400 [1:11:52<13:55,  3.48s/it, lr: 5.0e-05 loss: 2.468e-01]
leoprint:  90%|######### | 2160/2400 [1:11:52<13:55,  3.48s/it, lr: 5.0e-05 loss: 2.468e-01]
leoprint:  90%|######### | 2161/2400 [1:11:52<10:48,  2.71s/it, lr: 5.0e-05 loss: 2.468e-01]
leoprint:  90%|######### | 2161/2400 [1:11:52<10:48,  2.71s/it, lr: 5.0e-05 loss: 2.468e-01]
leoprint:  90%|######### | 2161/2400 [1:11:56<10:48,  2.71s/it, lr: 5.0e-05 loss: 2.068e-01]
leoprint:  90%|######### | 2161/2400 [1:11:56<10:48,  2.71s/it, lr: 5.0e-05 loss: 2.068e-01]
leoprint:  90%|######### | 2162/2400 [1:11:56<11:32,  2.91s/it, lr: 5.0e-05 loss: 2.068e-01]
leoprint:  90%|######### | 2162/2400 [1:11:56<11:32,  2.91s/it, lr: 5.0e-05 loss: 2.068e-01]
leoprint:  90%|######### | 2162/2400 [1:11:59<11:32,  2.91s/it, lr: 5.0e-05 loss: 3.746e-01]
leoprint:  90%|######### | 2162/2400 [1:11:59<11:32,  2.91s/it, lr: 5.0e-05 loss: 3.746e-01]
leoprint:  90%|######### | 2163/2400 [1:11:59<12:06,  3.07s/it, lr: 5.0e-05 loss: 3.746e-01]
leoprint:  90%|######### | 2163/2400 [1:11:59<12:06,  3.07s/it, lr: 5.0e-05 loss: 3.746e-01]
leoprint:  90%|######### | 2163/2400 [1:12:03<12:06,  3.07s/it, lr: 5.0e-05 loss: 2.253e-01]
leoprint:  90%|######### | 2163/2400 [1:12:03<12:06,  3.07s/it, lr: 5.0e-05 loss: 2.253e-01]
leoprint:  90%|######### | 2164/2400 [1:12:03<12:39,  3.22s/it, lr: 5.0e-05 loss: 2.253e-01]
leoprint:  90%|######### | 2164/2400 [1:12:03<12:39,  3.22s/it, lr: 5.0e-05 loss: 2.253e-01]
leoprint:  90%|######### | 2164/2400 [1:12:07<12:39,  3.22s/it, lr: 5.0e-05 loss: 3.687e-01]
leoprint:  90%|######### | 2164/2400 [1:12:07<12:39,  3.22s/it, lr: 5.0e-05 loss: 3.687e-01]
leoprint:  90%|######### | 2165/2400 [1:12:07<12:54,  3.30s/it, lr: 5.0e-05 loss: 3.687e-01]
leoprint:  90%|######### | 2165/2400 [1:12:07<12:54,  3.30s/it, lr: 5.0e-05 loss: 3.687e-01]
leoprint:  90%|######### | 2165/2400 [1:12:10<12:54,  3.30s/it, lr: 5.0e-05 loss: 3.624e-01]
leoprint:  90%|######### | 2165/2400 [1:12:10<12:54,  3.30s/it, lr: 5.0e-05 loss: 3.624e-01]
leoprint:  90%|######### | 2166/2400 [1:12:10<13:06,  3.36s/it, lr: 5.0e-05 loss: 3.624e-01]
leoprint:  90%|######### | 2166/2400 [1:12:10<13:06,  3.36s/it, lr: 5.0e-05 loss: 3.624e-01]
leoprint:  90%|######### | 2166/2400 [1:12:14<13:06,  3.36s/it, lr: 5.0e-05 loss: 2.739e-01]
leoprint:  90%|######### | 2166/2400 [1:12:14<13:06,  3.36s/it, lr: 5.0e-05 loss: 2.739e-01]
leoprint:  90%|######### | 2167/2400 [1:12:14<13:29,  3.47s/it, lr: 5.0e-05 loss: 2.739e-01]
leoprint:  90%|######### | 2167/2400 [1:12:14<13:29,  3.47s/it, lr: 5.0e-05 loss: 2.739e-01]
leoprint:  90%|######### | 2167/2400 [1:12:18<13:29,  3.47s/it, lr: 5.0e-05 loss: 2.437e-01]
leoprint:  90%|######### | 2167/2400 [1:12:18<13:29,  3.47s/it, lr: 5.0e-05 loss: 2.437e-01]
leoprint:  90%|######### | 2168/2400 [1:12:18<13:35,  3.52s/it, lr: 5.0e-05 loss: 2.437e-01]
leoprint:  90%|######### | 2168/2400 [1:12:18<13:35,  3.52s/it, lr: 5.0e-05 loss: 2.437e-01]
leoprint:  90%|######### | 2168/2400 [1:12:21<13:35,  3.52s/it, lr: 5.0e-05 loss: 1.989e-01]
leoprint:  90%|######### | 2168/2400 [1:12:21<13:35,  3.52s/it, lr: 5.0e-05 loss: 1.989e-01]
leoprint:  90%|######### | 2169/2400 [1:12:21<13:31,  3.52s/it, lr: 5.0e-05 loss: 1.989e-01]
leoprint:  90%|######### | 2169/2400 [1:12:21<13:31,  3.52s/it, lr: 5.0e-05 loss: 1.989e-01]
leoprint:  90%|######### | 2169/2400 [1:12:25<13:31,  3.52s/it, lr: 5.0e-05 loss: 2.272e-01]
leoprint:  90%|######### | 2169/2400 [1:12:25<13:31,  3.52s/it, lr: 5.0e-05 loss: 2.272e-01]
leoprint:  90%|######### | 2170/2400 [1:12:28<13:28,  3.52s/it, lr: 5.0e-05 loss: 3.182e-01]
leoprint:  90%|######### | 2170/2400 [1:12:28<13:28,  3.52s/it, lr: 5.0e-05 loss: 3.182e-01]
leoprint:  90%|######### | 2171/2400 [1:12:28<10:20,  2.71s/it, lr: 5.0e-05 loss: 3.182e-01]
leoprint:  90%|######### | 2171/2400 [1:12:28<10:20,  2.71s/it, lr: 5.0e-05 loss: 3.182e-01]
leoprint:  90%|######### | 2171/2400 [1:12:32<10:20,  2.71s/it, lr: 5.0e-05 loss: 3.234e-01]
leoprint:  90%|######### | 2171/2400 [1:12:32<10:20,  2.71s/it, lr: 5.0e-05 loss: 3.234e-01]
leoprint:  90%|######### | 2172/2400 [1:12:32<11:06,  2.92s/it, lr: 5.0e-05 loss: 3.234e-01]
leoprint:  90%|######### | 2172/2400 [1:12:32<11:06,  2.92s/it, lr: 5.0e-05 loss: 3.234e-01]
leoprint:  90%|######### | 2172/2400 [1:12:35<11:06,  2.92s/it, lr: 5.0e-05 loss: 2.526e-01]
leoprint:  90%|######### | 2172/2400 [1:12:35<11:06,  2.92s/it, lr: 5.0e-05 loss: 2.526e-01]
leoprint:  91%|######### | 2173/2400 [1:12:35<11:45,  3.11s/it, lr: 5.0e-05 loss: 2.526e-01]
leoprint:  91%|######### | 2173/2400 [1:12:35<11:45,  3.11s/it, lr: 5.0e-05 loss: 2.526e-01]
leoprint:  91%|######### | 2173/2400 [1:12:39<11:45,  3.11s/it, lr: 5.0e-05 loss: 3.190e-01]
leoprint:  91%|######### | 2173/2400 [1:12:39<11:45,  3.11s/it, lr: 5.0e-05 loss: 3.190e-01]
leoprint:  91%|######### | 2174/2400 [1:12:39<12:13,  3.25s/it, lr: 5.0e-05 loss: 3.190e-01]
leoprint:  91%|######### | 2174/2400 [1:12:39<12:13,  3.25s/it, lr: 5.0e-05 loss: 3.190e-01]
leoprint:  91%|######### | 2174/2400 [1:12:42<12:13,  3.25s/it, lr: 5.0e-05 loss: 3.031e-01]
leoprint:  91%|######### | 2174/2400 [1:12:42<12:13,  3.25s/it, lr: 5.0e-05 loss: 3.031e-01]
leoprint:  91%|######### | 2175/2400 [1:12:42<12:26,  3.32s/it, lr: 5.0e-05 loss: 3.031e-01]
leoprint:  91%|######### | 2175/2400 [1:12:42<12:26,  3.32s/it, lr: 5.0e-05 loss: 3.031e-01]
leoprint:  91%|######### | 2175/2400 [1:12:46<12:26,  3.32s/it, lr: 5.0e-05 loss: 2.261e-01]
leoprint:  91%|######### | 2175/2400 [1:12:46<12:26,  3.32s/it, lr: 5.0e-05 loss: 2.261e-01]
leoprint:  91%|######### | 2176/2400 [1:12:46<12:35,  3.37s/it, lr: 5.0e-05 loss: 2.261e-01]
leoprint:  91%|######### | 2176/2400 [1:12:46<12:35,  3.37s/it, lr: 5.0e-05 loss: 2.261e-01]
leoprint:  91%|######### | 2176/2400 [1:12:49<12:35,  3.37s/it, lr: 5.0e-05 loss: 3.253e-01]
leoprint:  91%|######### | 2176/2400 [1:12:49<12:35,  3.37s/it, lr: 5.0e-05 loss: 3.253e-01]
leoprint:  91%|######### | 2177/2400 [1:12:49<12:41,  3.41s/it, lr: 5.0e-05 loss: 3.253e-01]
leoprint:  91%|######### | 2177/2400 [1:12:49<12:41,  3.41s/it, lr: 5.0e-05 loss: 3.253e-01]
leoprint:  91%|######### | 2177/2400 [1:12:53<12:41,  3.41s/it, lr: 5.0e-05 loss: 2.125e-01]
leoprint:  91%|######### | 2177/2400 [1:12:53<12:41,  3.41s/it, lr: 5.0e-05 loss: 2.125e-01]
leoprint:  91%|######### | 2178/2400 [1:12:53<12:56,  3.50s/it, lr: 5.0e-05 loss: 2.125e-01]
leoprint:  91%|######### | 2178/2400 [1:12:53<12:56,  3.50s/it, lr: 5.0e-05 loss: 2.125e-01]
leoprint:  91%|######### | 2178/2400 [1:12:57<12:56,  3.50s/it, lr: 5.0e-05 loss: 3.709e-01]
leoprint:  91%|######### | 2178/2400 [1:12:57<12:56,  3.50s/it, lr: 5.0e-05 loss: 3.709e-01]
leoprint:  91%|######### | 2179/2400 [1:12:57<12:53,  3.50s/it, lr: 5.0e-05 loss: 3.709e-01]
leoprint:  91%|######### | 2179/2400 [1:12:57<12:53,  3.50s/it, lr: 5.0e-05 loss: 3.709e-01]
leoprint:  91%|######### | 2179/2400 [1:13:00<12:53,  3.50s/it, lr: 5.0e-05 loss: 2.755e-01]
leoprint:  91%|######### | 2179/2400 [1:13:00<12:53,  3.50s/it, lr: 5.0e-05 loss: 2.755e-01]
leoprint:  91%|######### | 2180/2400 [1:13:04<12:49,  3.50s/it, lr: 5.0e-05 loss: 3.052e-01]
leoprint:  91%|######### | 2180/2400 [1:13:04<12:49,  3.50s/it, lr: 5.0e-05 loss: 3.052e-01]
leoprint:  91%|######### | 2181/2400 [1:13:04<09:51,  2.70s/it, lr: 5.0e-05 loss: 3.052e-01]
leoprint:  91%|######### | 2181/2400 [1:13:04<09:51,  2.70s/it, lr: 5.0e-05 loss: 3.052e-01]
leoprint:  91%|######### | 2181/2400 [1:13:07<09:51,  2.70s/it, lr: 5.0e-05 loss: 2.466e-01]
leoprint:  91%|######### | 2181/2400 [1:13:07<09:51,  2.70s/it, lr: 5.0e-05 loss: 2.466e-01]
leoprint:  91%|######### | 2182/2400 [1:13:07<10:32,  2.90s/it, lr: 5.0e-05 loss: 2.466e-01]
leoprint:  91%|######### | 2182/2400 [1:13:07<10:32,  2.90s/it, lr: 5.0e-05 loss: 2.466e-01]
leoprint:  91%|######### | 2182/2400 [1:13:11<10:32,  2.90s/it, lr: 5.0e-05 loss: 3.177e-01]
leoprint:  91%|######### | 2182/2400 [1:13:11<10:32,  2.90s/it, lr: 5.0e-05 loss: 3.177e-01]
leoprint:  91%|######### | 2183/2400 [1:13:11<11:03,  3.06s/it, lr: 5.0e-05 loss: 3.177e-01]
leoprint:  91%|######### | 2183/2400 [1:13:11<11:03,  3.06s/it, lr: 5.0e-05 loss: 3.177e-01]
leoprint:  91%|######### | 2183/2400 [1:13:15<11:03,  3.06s/it, lr: 5.0e-05 loss: 2.277e-01]
leoprint:  91%|######### | 2183/2400 [1:13:15<11:03,  3.06s/it, lr: 5.0e-05 loss: 2.277e-01]
leoprint:  91%|#########1| 2184/2400 [1:13:15<11:42,  3.25s/it, lr: 5.0e-05 loss: 2.277e-01]
leoprint:  91%|#########1| 2184/2400 [1:13:15<11:42,  3.25s/it, lr: 5.0e-05 loss: 2.277e-01]
leoprint:  91%|#########1| 2184/2400 [1:13:18<11:42,  3.25s/it, lr: 5.0e-05 loss: 2.768e-01]
leoprint:  91%|#########1| 2184/2400 [1:13:18<11:42,  3.25s/it, lr: 5.0e-05 loss: 2.768e-01]
leoprint:  91%|#########1| 2185/2400 [1:13:18<11:53,  3.32s/it, lr: 5.0e-05 loss: 2.768e-01]
leoprint:  91%|#########1| 2185/2400 [1:13:18<11:53,  3.32s/it, lr: 5.0e-05 loss: 2.768e-01]
leoprint:  91%|#########1| 2185/2400 [1:13:22<11:53,  3.32s/it, lr: 5.0e-05 loss: 2.325e-01]
leoprint:  91%|#########1| 2185/2400 [1:13:22<11:53,  3.32s/it, lr: 5.0e-05 loss: 2.325e-01]
leoprint:  91%|#########1| 2186/2400 [1:13:22<12:08,  3.41s/it, lr: 5.0e-05 loss: 2.325e-01]
leoprint:  91%|#########1| 2186/2400 [1:13:22<12:08,  3.41s/it, lr: 5.0e-05 loss: 2.325e-01]
leoprint:  91%|#########1| 2186/2400 [1:13:25<12:08,  3.41s/it, lr: 5.0e-05 loss: 2.540e-01]
leoprint:  91%|#########1| 2186/2400 [1:13:25<12:08,  3.41s/it, lr: 5.0e-05 loss: 2.540e-01]
leoprint:  91%|#########1| 2187/2400 [1:13:25<12:11,  3.44s/it, lr: 5.0e-05 loss: 2.540e-01]
leoprint:  91%|#########1| 2187/2400 [1:13:25<12:11,  3.44s/it, lr: 5.0e-05 loss: 2.540e-01]
leoprint:  91%|#########1| 2187/2400 [1:13:29<12:11,  3.44s/it, lr: 5.0e-05 loss: 2.714e-01]
leoprint:  91%|#########1| 2187/2400 [1:13:29<12:11,  3.44s/it, lr: 5.0e-05 loss: 2.714e-01]
leoprint:  91%|#########1| 2188/2400 [1:13:29<12:20,  3.49s/it, lr: 5.0e-05 loss: 2.714e-01]
leoprint:  91%|#########1| 2188/2400 [1:13:29<12:20,  3.49s/it, lr: 5.0e-05 loss: 2.714e-01]
leoprint:  91%|#########1| 2188/2400 [1:13:33<12:20,  3.49s/it, lr: 5.0e-05 loss: 2.647e-01]
leoprint:  91%|#########1| 2188/2400 [1:13:33<12:20,  3.49s/it, lr: 5.0e-05 loss: 2.647e-01]
leoprint:  91%|#########1| 2189/2400 [1:13:33<12:28,  3.55s/it, lr: 5.0e-05 loss: 2.647e-01]
leoprint:  91%|#########1| 2189/2400 [1:13:33<12:28,  3.55s/it, lr: 5.0e-05 loss: 2.647e-01]
leoprint:  91%|#########1| 2189/2400 [1:13:36<12:28,  3.55s/it, lr: 5.0e-05 loss: 2.601e-01]
leoprint:  91%|#########1| 2189/2400 [1:13:36<12:28,  3.55s/it, lr: 5.0e-05 loss: 2.601e-01]
leoprint:  91%|#########1| 2190/2400 [1:13:40<12:24,  3.55s/it, lr: 5.0e-05 loss: 3.081e-01]
leoprint:  91%|#########1| 2190/2400 [1:13:40<12:24,  3.55s/it, lr: 5.0e-05 loss: 3.081e-01]
leoprint:  91%|#########1| 2191/2400 [1:13:40<09:29,  2.73s/it, lr: 5.0e-05 loss: 3.081e-01]
leoprint:  91%|#########1| 2191/2400 [1:13:40<09:29,  2.73s/it, lr: 5.0e-05 loss: 3.081e-01]
leoprint:  91%|#########1| 2191/2400 [1:13:43<09:29,  2.73s/it, lr: 5.0e-05 loss: 2.845e-01]
leoprint:  91%|#########1| 2191/2400 [1:13:43<09:29,  2.73s/it, lr: 5.0e-05 loss: 2.845e-01]
leoprint:  91%|#########1| 2192/2400 [1:13:43<10:07,  2.92s/it, lr: 5.0e-05 loss: 2.845e-01]
leoprint:  91%|#########1| 2192/2400 [1:13:43<10:07,  2.92s/it, lr: 5.0e-05 loss: 2.845e-01]
leoprint:  91%|#########1| 2192/2400 [1:13:47<10:07,  2.92s/it, lr: 5.0e-05 loss: 3.328e-01]
leoprint:  91%|#########1| 2192/2400 [1:13:47<10:07,  2.92s/it, lr: 5.0e-05 loss: 3.328e-01]
leoprint:  91%|#########1| 2193/2400 [1:13:47<10:36,  3.07s/it, lr: 5.0e-05 loss: 3.328e-01]
leoprint:  91%|#########1| 2193/2400 [1:13:47<10:36,  3.07s/it, lr: 5.0e-05 loss: 3.328e-01]
leoprint:  91%|#########1| 2193/2400 [1:13:50<10:36,  3.07s/it, lr: 5.0e-05 loss: 4.322e-01]
leoprint:  91%|#########1| 2193/2400 [1:13:50<10:36,  3.07s/it, lr: 5.0e-05 loss: 4.322e-01]
leoprint:  91%|#########1| 2194/2400 [1:13:50<10:57,  3.19s/it, lr: 5.0e-05 loss: 4.322e-01]
leoprint:  91%|#########1| 2194/2400 [1:13:50<10:57,  3.19s/it, lr: 5.0e-05 loss: 4.322e-01]
leoprint:  91%|#########1| 2194/2400 [1:13:54<10:57,  3.19s/it, lr: 5.0e-05 loss: 2.949e-01]
leoprint:  91%|#########1| 2194/2400 [1:13:54<10:57,  3.19s/it, lr: 5.0e-05 loss: 2.949e-01]
leoprint:  91%|#########1| 2195/2400 [1:13:54<11:17,  3.31s/it, lr: 5.0e-05 loss: 2.949e-01]
leoprint:  91%|#########1| 2195/2400 [1:13:54<11:17,  3.31s/it, lr: 5.0e-05 loss: 2.949e-01]
leoprint:  91%|#########1| 2195/2400 [1:13:57<11:17,  3.31s/it, lr: 5.0e-05 loss: 3.360e-01]
leoprint:  91%|#########1| 2195/2400 [1:13:57<11:17,  3.31s/it, lr: 5.0e-05 loss: 3.360e-01]
leoprint:  92%|#########1| 2196/2400 [1:13:57<11:25,  3.36s/it, lr: 5.0e-05 loss: 3.360e-01]
leoprint:  92%|#########1| 2196/2400 [1:13:57<11:25,  3.36s/it, lr: 5.0e-05 loss: 3.360e-01]
leoprint:  92%|#########1| 2196/2400 [1:14:01<11:25,  3.36s/it, lr: 5.0e-05 loss: 3.467e-01]
leoprint:  92%|#########1| 2196/2400 [1:14:01<11:25,  3.36s/it, lr: 5.0e-05 loss: 3.467e-01]
leoprint:  92%|#########1| 2197/2400 [1:14:01<11:31,  3.41s/it, lr: 5.0e-05 loss: 3.467e-01]
leoprint:  92%|#########1| 2197/2400 [1:14:01<11:31,  3.41s/it, lr: 5.0e-05 loss: 3.467e-01]
leoprint:  92%|#########1| 2197/2400 [1:14:05<11:31,  3.41s/it, lr: 5.0e-05 loss: 2.974e-01]
leoprint:  92%|#########1| 2197/2400 [1:14:05<11:31,  3.41s/it, lr: 5.0e-05 loss: 2.974e-01]
leoprint:  92%|#########1| 2198/2400 [1:14:05<11:41,  3.47s/it, lr: 5.0e-05 loss: 2.974e-01]
leoprint:  92%|#########1| 2198/2400 [1:14:05<11:41,  3.47s/it, lr: 5.0e-05 loss: 2.974e-01]
leoprint:  92%|#########1| 2198/2400 [1:14:08<11:41,  3.47s/it, lr: 5.0e-05 loss: 2.359e-01]
leoprint:  92%|#########1| 2198/2400 [1:14:08<11:41,  3.47s/it, lr: 5.0e-05 loss: 2.359e-01]
leoprint:  92%|#########1| 2199/2400 [1:14:08<11:47,  3.52s/it, lr: 5.0e-05 loss: 2.359e-01]
leoprint:  92%|#########1| 2199/2400 [1:14:08<11:47,  3.52s/it, lr: 5.0e-05 loss: 2.359e-01]
leoprint:  92%|#########1| 2199/2400 [1:14:12<11:47,  3.52s/it, lr: 5.0e-05 loss: 1.989e-01]
leoprint:  92%|#########1| 2199/2400 [1:14:12<11:47,  3.52s/it, lr: 5.0e-05 loss: 1.989e-01]
+
+
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
+
+
Generating Images:  20%|##        | 1/5 [00:14<00:57, 14.42s/it]
Generating Images:  20%|##        | 1/5 [00:14<00:57, 14.42s/it]
+
+
Generating Images:  40%|####      | 2/5 [00:28<00:43, 14.43s/it]
Generating Images:  40%|####      | 2/5 [00:28<00:43, 14.43s/it]
+
+
Generating Images:  60%|######    | 3/5 [00:43<00:28, 14.42s/it]
Generating Images:  60%|######    | 3/5 [00:43<00:28, 14.42s/it]
+
+
Generating Images:  80%|########  | 4/5 [00:57<00:14, 14.43s/it]
Generating Images:  80%|########  | 4/5 [00:57<00:14, 14.43s/it]
+
+
Generating Images: 100%|##########| 5/5 [01:12<00:00, 14.43s/it]
Generating Images: 100%|##########| 5/5 [01:12<00:00, 14.43s/it]
+
+
                                                                
                                                                
+Saving at step 2200
+Saved checkpoint to /app/ai-toolkit/output/leoprint/leoprint_000002200.safetensors
+Saved optimizer to /app/ai-toolkit/output/leoprint/optimizer.pt
+
leoprint:  92%|#########1| 2200/2400 [1:14:15<11:44,  3.52s/it, lr: 5.0e-05 loss: 3.153e-01]
leoprint:  92%|#########1| 2200/2400 [1:14:15<11:44,  3.52s/it, lr: 5.0e-05 loss: 3.153e-01]
leoprint:  92%|#########1| 2201/2400 [1:14:15<09:08,  2.76s/it, lr: 5.0e-05 loss: 3.153e-01]
leoprint:  92%|#########1| 2201/2400 [1:14:15<09:08,  2.76s/it, lr: 5.0e-05 loss: 3.153e-01]
leoprint:  92%|#########1| 2201/2400 [1:14:19<09:08,  2.76s/it, lr: 5.0e-05 loss: 2.980e-01]
leoprint:  92%|#########1| 2201/2400 [1:14:19<09:08,  2.76s/it, lr: 5.0e-05 loss: 2.980e-01]
leoprint:  92%|#########1| 2202/2400 [1:14:19<09:41,  2.94s/it, lr: 5.0e-05 loss: 2.980e-01]
leoprint:  92%|#########1| 2202/2400 [1:14:19<09:41,  2.94s/it, lr: 5.0e-05 loss: 2.980e-01]
leoprint:  92%|#########1| 2202/2400 [1:14:22<09:41,  2.94s/it, lr: 5.0e-05 loss: 3.096e-01]
leoprint:  92%|#########1| 2202/2400 [1:14:22<09:41,  2.94s/it, lr: 5.0e-05 loss: 3.096e-01]
leoprint:  92%|#########1| 2203/2400 [1:14:22<10:07,  3.08s/it, lr: 5.0e-05 loss: 3.096e-01]
leoprint:  92%|#########1| 2203/2400 [1:14:22<10:07,  3.08s/it, lr: 5.0e-05 loss: 3.096e-01]
leoprint:  92%|#########1| 2203/2400 [1:14:26<10:07,  3.08s/it, lr: 5.0e-05 loss: 4.088e-01]
leoprint:  92%|#########1| 2203/2400 [1:14:26<10:07,  3.08s/it, lr: 5.0e-05 loss: 4.088e-01]
leoprint:  92%|#########1| 2204/2400 [1:14:26<10:26,  3.20s/it, lr: 5.0e-05 loss: 4.088e-01]
leoprint:  92%|#########1| 2204/2400 [1:14:26<10:26,  3.20s/it, lr: 5.0e-05 loss: 4.088e-01]
leoprint:  92%|#########1| 2204/2400 [1:14:30<10:26,  3.20s/it, lr: 5.0e-05 loss: 2.512e-01]
leoprint:  92%|#########1| 2204/2400 [1:14:30<10:26,  3.20s/it, lr: 5.0e-05 loss: 2.512e-01]
leoprint:  92%|#########1| 2205/2400 [1:14:30<10:46,  3.31s/it, lr: 5.0e-05 loss: 2.512e-01]
leoprint:  92%|#########1| 2205/2400 [1:14:30<10:46,  3.31s/it, lr: 5.0e-05 loss: 2.512e-01]
leoprint:  92%|#########1| 2205/2400 [1:14:33<10:46,  3.31s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  92%|#########1| 2205/2400 [1:14:33<10:46,  3.31s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  92%|#########1| 2206/2400 [1:14:33<11:04,  3.42s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  92%|#########1| 2206/2400 [1:14:33<11:04,  3.42s/it, lr: 5.0e-05 loss: 2.670e-01]
leoprint:  92%|#########1| 2206/2400 [1:14:37<11:04,  3.42s/it, lr: 5.0e-05 loss: 2.563e-01]
leoprint:  92%|#########1| 2206/2400 [1:14:37<11:04,  3.42s/it, lr: 5.0e-05 loss: 2.563e-01]
leoprint:  92%|#########1| 2207/2400 [1:14:37<11:05,  3.45s/it, lr: 5.0e-05 loss: 2.563e-01]
leoprint:  92%|#########1| 2207/2400 [1:14:37<11:05,  3.45s/it, lr: 5.0e-05 loss: 2.563e-01]
leoprint:  92%|#########1| 2207/2400 [1:14:40<11:05,  3.45s/it, lr: 5.0e-05 loss: 2.974e-01]
leoprint:  92%|#########1| 2207/2400 [1:14:40<11:05,  3.45s/it, lr: 5.0e-05 loss: 2.974e-01]
leoprint:  92%|#########2| 2208/2400 [1:14:40<11:04,  3.46s/it, lr: 5.0e-05 loss: 2.974e-01]
leoprint:  92%|#########2| 2208/2400 [1:14:40<11:04,  3.46s/it, lr: 5.0e-05 loss: 2.974e-01]
leoprint:  92%|#########2| 2208/2400 [1:14:44<11:04,  3.46s/it, lr: 5.0e-05 loss: 3.541e-01]
leoprint:  92%|#########2| 2208/2400 [1:14:44<11:04,  3.46s/it, lr: 5.0e-05 loss: 3.541e-01]
leoprint:  92%|#########2| 2209/2400 [1:14:44<11:03,  3.47s/it, lr: 5.0e-05 loss: 3.541e-01]
leoprint:  92%|#########2| 2209/2400 [1:14:44<11:03,  3.47s/it, lr: 5.0e-05 loss: 3.541e-01]
leoprint:  92%|#########2| 2209/2400 [1:14:49<11:03,  3.47s/it, lr: 5.0e-05 loss: 2.527e-01]
leoprint:  92%|#########2| 2209/2400 [1:14:49<11:03,  3.47s/it, lr: 5.0e-05 loss: 2.527e-01]
leoprint:  92%|#########2| 2210/2400 [1:14:52<11:00,  3.47s/it, lr: 5.0e-05 loss: 2.296e-01]
leoprint:  92%|#########2| 2210/2400 [1:14:52<11:00,  3.47s/it, lr: 5.0e-05 loss: 2.296e-01]
leoprint:  92%|#########2| 2211/2400 [1:14:52<08:27,  2.69s/it, lr: 5.0e-05 loss: 2.296e-01]
leoprint:  92%|#########2| 2211/2400 [1:14:52<08:27,  2.69s/it, lr: 5.0e-05 loss: 2.296e-01]
leoprint:  92%|#########2| 2211/2400 [1:14:56<08:27,  2.69s/it, lr: 5.0e-05 loss: 2.814e-01]
leoprint:  92%|#########2| 2211/2400 [1:14:56<08:27,  2.69s/it, lr: 5.0e-05 loss: 2.814e-01]
leoprint:  92%|#########2| 2212/2400 [1:14:56<09:13,  2.95s/it, lr: 5.0e-05 loss: 2.814e-01]
leoprint:  92%|#########2| 2212/2400 [1:14:56<09:13,  2.95s/it, lr: 5.0e-05 loss: 2.814e-01]
leoprint:  92%|#########2| 2212/2400 [1:15:00<09:13,  2.95s/it, lr: 5.0e-05 loss: 2.477e-01]
leoprint:  92%|#########2| 2212/2400 [1:15:00<09:13,  2.95s/it, lr: 5.0e-05 loss: 2.477e-01]
leoprint:  92%|#########2| 2213/2400 [1:15:00<09:43,  3.12s/it, lr: 5.0e-05 loss: 2.477e-01]
leoprint:  92%|#########2| 2213/2400 [1:15:00<09:43,  3.12s/it, lr: 5.0e-05 loss: 2.477e-01]
leoprint:  92%|#########2| 2213/2400 [1:15:03<09:43,  3.12s/it, lr: 5.0e-05 loss: 3.721e-01]
leoprint:  92%|#########2| 2213/2400 [1:15:03<09:43,  3.12s/it, lr: 5.0e-05 loss: 3.721e-01]
leoprint:  92%|#########2| 2214/2400 [1:15:03<10:00,  3.23s/it, lr: 5.0e-05 loss: 3.721e-01]
leoprint:  92%|#########2| 2214/2400 [1:15:03<10:00,  3.23s/it, lr: 5.0e-05 loss: 3.721e-01]
leoprint:  92%|#########2| 2214/2400 [1:15:07<10:00,  3.23s/it, lr: 5.0e-05 loss: 2.836e-01]
leoprint:  92%|#########2| 2214/2400 [1:15:07<10:00,  3.23s/it, lr: 5.0e-05 loss: 2.836e-01]
leoprint:  92%|#########2| 2215/2400 [1:15:07<10:11,  3.30s/it, lr: 5.0e-05 loss: 2.836e-01]
leoprint:  92%|#########2| 2215/2400 [1:15:07<10:11,  3.30s/it, lr: 5.0e-05 loss: 2.836e-01]
leoprint:  92%|#########2| 2215/2400 [1:15:10<10:11,  3.30s/it, lr: 5.0e-05 loss: 2.449e-01]
leoprint:  92%|#########2| 2215/2400 [1:15:10<10:11,  3.30s/it, lr: 5.0e-05 loss: 2.449e-01]
leoprint:  92%|#########2| 2216/2400 [1:15:10<10:18,  3.36s/it, lr: 5.0e-05 loss: 2.449e-01]
leoprint:  92%|#########2| 2216/2400 [1:15:10<10:18,  3.36s/it, lr: 5.0e-05 loss: 2.449e-01]
leoprint:  92%|#########2| 2216/2400 [1:15:14<10:18,  3.36s/it, lr: 5.0e-05 loss: 2.366e-01]
leoprint:  92%|#########2| 2216/2400 [1:15:14<10:18,  3.36s/it, lr: 5.0e-05 loss: 2.366e-01]
leoprint:  92%|#########2| 2217/2400 [1:15:14<10:23,  3.41s/it, lr: 5.0e-05 loss: 2.366e-01]
leoprint:  92%|#########2| 2217/2400 [1:15:14<10:23,  3.41s/it, lr: 5.0e-05 loss: 2.366e-01]
leoprint:  92%|#########2| 2217/2400 [1:15:17<10:23,  3.41s/it, lr: 5.0e-05 loss: 2.087e-01]
leoprint:  92%|#########2| 2217/2400 [1:15:17<10:23,  3.41s/it, lr: 5.0e-05 loss: 2.087e-01]
leoprint:  92%|#########2| 2218/2400 [1:15:17<10:33,  3.48s/it, lr: 5.0e-05 loss: 2.087e-01]
leoprint:  92%|#########2| 2218/2400 [1:15:17<10:33,  3.48s/it, lr: 5.0e-05 loss: 2.087e-01]
leoprint:  92%|#########2| 2218/2400 [1:15:21<10:33,  3.48s/it, lr: 5.0e-05 loss: 1.730e-01]
leoprint:  92%|#########2| 2218/2400 [1:15:21<10:33,  3.48s/it, lr: 5.0e-05 loss: 1.730e-01]
leoprint:  92%|#########2| 2219/2400 [1:15:21<10:38,  3.53s/it, lr: 5.0e-05 loss: 1.730e-01]
leoprint:  92%|#########2| 2219/2400 [1:15:21<10:38,  3.53s/it, lr: 5.0e-05 loss: 1.730e-01]
leoprint:  92%|#########2| 2219/2400 [1:15:24<10:38,  3.53s/it, lr: 5.0e-05 loss: 2.650e-01]
leoprint:  92%|#########2| 2219/2400 [1:15:24<10:38,  3.53s/it, lr: 5.0e-05 loss: 2.650e-01]
leoprint:  92%|#########2| 2220/2400 [1:15:28<10:34,  3.53s/it, lr: 5.0e-05 loss: 1.944e-01]
leoprint:  92%|#########2| 2220/2400 [1:15:28<10:34,  3.53s/it, lr: 5.0e-05 loss: 1.944e-01]
leoprint:  93%|#########2| 2221/2400 [1:15:28<08:11,  2.75s/it, lr: 5.0e-05 loss: 1.944e-01]
leoprint:  93%|#########2| 2221/2400 [1:15:28<08:11,  2.75s/it, lr: 5.0e-05 loss: 1.944e-01]
leoprint:  93%|#########2| 2221/2400 [1:15:32<08:11,  2.75s/it, lr: 5.0e-05 loss: 2.219e-01]
leoprint:  93%|#########2| 2221/2400 [1:15:32<08:11,  2.75s/it, lr: 5.0e-05 loss: 2.219e-01]
leoprint:  93%|#########2| 2222/2400 [1:15:32<08:47,  2.96s/it, lr: 5.0e-05 loss: 2.219e-01]
leoprint:  93%|#########2| 2222/2400 [1:15:32<08:47,  2.96s/it, lr: 5.0e-05 loss: 2.219e-01]
leoprint:  93%|#########2| 2222/2400 [1:15:36<08:47,  2.96s/it, lr: 5.0e-05 loss: 2.165e-01]
leoprint:  93%|#########2| 2222/2400 [1:15:36<08:47,  2.96s/it, lr: 5.0e-05 loss: 2.165e-01]
leoprint:  93%|#########2| 2223/2400 [1:15:36<09:17,  3.15s/it, lr: 5.0e-05 loss: 2.165e-01]
leoprint:  93%|#########2| 2223/2400 [1:15:36<09:17,  3.15s/it, lr: 5.0e-05 loss: 2.165e-01]
leoprint:  93%|#########2| 2223/2400 [1:15:39<09:17,  3.15s/it, lr: 5.0e-05 loss: 3.646e-01]
leoprint:  93%|#########2| 2223/2400 [1:15:39<09:17,  3.15s/it, lr: 5.0e-05 loss: 3.646e-01]
leoprint:  93%|#########2| 2224/2400 [1:15:39<09:31,  3.25s/it, lr: 5.0e-05 loss: 3.646e-01]
leoprint:  93%|#########2| 2224/2400 [1:15:39<09:31,  3.25s/it, lr: 5.0e-05 loss: 3.646e-01]
leoprint:  93%|#########2| 2224/2400 [1:15:43<09:31,  3.25s/it, lr: 5.0e-05 loss: 2.650e-01]
leoprint:  93%|#########2| 2224/2400 [1:15:43<09:31,  3.25s/it, lr: 5.0e-05 loss: 2.650e-01]
leoprint:  93%|#########2| 2225/2400 [1:15:43<09:40,  3.32s/it, lr: 5.0e-05 loss: 2.650e-01]
leoprint:  93%|#########2| 2225/2400 [1:15:43<09:40,  3.32s/it, lr: 5.0e-05 loss: 2.650e-01]
leoprint:  93%|#########2| 2225/2400 [1:15:46<09:40,  3.32s/it, lr: 5.0e-05 loss: 3.292e-01]
leoprint:  93%|#########2| 2225/2400 [1:15:46<09:40,  3.32s/it, lr: 5.0e-05 loss: 3.292e-01]
leoprint:  93%|#########2| 2226/2400 [1:15:46<09:47,  3.37s/it, lr: 5.0e-05 loss: 3.292e-01]
leoprint:  93%|#########2| 2226/2400 [1:15:46<09:47,  3.37s/it, lr: 5.0e-05 loss: 3.292e-01]
leoprint:  93%|#########2| 2226/2400 [1:15:50<09:47,  3.37s/it, lr: 5.0e-05 loss: 2.021e-01]
leoprint:  93%|#########2| 2226/2400 [1:15:50<09:47,  3.37s/it, lr: 5.0e-05 loss: 2.021e-01]
leoprint:  93%|#########2| 2227/2400 [1:15:50<09:50,  3.41s/it, lr: 5.0e-05 loss: 2.021e-01]
leoprint:  93%|#########2| 2227/2400 [1:15:50<09:50,  3.41s/it, lr: 5.0e-05 loss: 2.021e-01]
leoprint:  93%|#########2| 2227/2400 [1:15:53<09:50,  3.41s/it, lr: 5.0e-05 loss: 2.874e-01]
leoprint:  93%|#########2| 2227/2400 [1:15:53<09:50,  3.41s/it, lr: 5.0e-05 loss: 2.874e-01]
leoprint:  93%|#########2| 2228/2400 [1:15:53<09:51,  3.44s/it, lr: 5.0e-05 loss: 2.874e-01]
leoprint:  93%|#########2| 2228/2400 [1:15:53<09:51,  3.44s/it, lr: 5.0e-05 loss: 2.874e-01]
leoprint:  93%|#########2| 2228/2400 [1:15:57<09:51,  3.44s/it, lr: 5.0e-05 loss: 3.810e-01]
leoprint:  93%|#########2| 2228/2400 [1:15:57<09:51,  3.44s/it, lr: 5.0e-05 loss: 3.810e-01]
leoprint:  93%|#########2| 2229/2400 [1:15:57<09:54,  3.48s/it, lr: 5.0e-05 loss: 3.810e-01]
leoprint:  93%|#########2| 2229/2400 [1:15:57<09:54,  3.48s/it, lr: 5.0e-05 loss: 3.810e-01]
leoprint:  93%|#########2| 2229/2400 [1:16:00<09:54,  3.48s/it, lr: 5.0e-05 loss: 3.297e-01]
leoprint:  93%|#########2| 2229/2400 [1:16:00<09:54,  3.48s/it, lr: 5.0e-05 loss: 3.297e-01]
leoprint:  93%|#########2| 2230/2400 [1:16:04<09:51,  3.48s/it, lr: 5.0e-05 loss: 2.506e-01]
leoprint:  93%|#########2| 2230/2400 [1:16:04<09:51,  3.48s/it, lr: 5.0e-05 loss: 2.506e-01]
leoprint:  93%|#########2| 2231/2400 [1:16:04<07:39,  2.72s/it, lr: 5.0e-05 loss: 2.506e-01]
leoprint:  93%|#########2| 2231/2400 [1:16:04<07:39,  2.72s/it, lr: 5.0e-05 loss: 2.506e-01]
leoprint:  93%|#########2| 2231/2400 [1:16:07<07:39,  2.72s/it, lr: 5.0e-05 loss: 2.578e-01]
leoprint:  93%|#########2| 2231/2400 [1:16:07<07:39,  2.72s/it, lr: 5.0e-05 loss: 2.578e-01]
leoprint:  93%|#########3| 2232/2400 [1:16:07<08:09,  2.91s/it, lr: 5.0e-05 loss: 2.578e-01]
leoprint:  93%|#########3| 2232/2400 [1:16:07<08:09,  2.91s/it, lr: 5.0e-05 loss: 2.578e-01]
leoprint:  93%|#########3| 2232/2400 [1:16:11<08:09,  2.91s/it, lr: 5.0e-05 loss: 3.296e-01]
leoprint:  93%|#########3| 2232/2400 [1:16:11<08:09,  2.91s/it, lr: 5.0e-05 loss: 3.296e-01]
leoprint:  93%|#########3| 2233/2400 [1:16:11<08:32,  3.07s/it, lr: 5.0e-05 loss: 3.296e-01]
leoprint:  93%|#########3| 2233/2400 [1:16:11<08:32,  3.07s/it, lr: 5.0e-05 loss: 3.296e-01]
leoprint:  93%|#########3| 2233/2400 [1:16:14<08:32,  3.07s/it, lr: 5.0e-05 loss: 3.255e-01]
leoprint:  93%|#########3| 2233/2400 [1:16:14<08:32,  3.07s/it, lr: 5.0e-05 loss: 3.255e-01]
leoprint:  93%|#########3| 2234/2400 [1:16:14<08:49,  3.19s/it, lr: 5.0e-05 loss: 3.255e-01]
leoprint:  93%|#########3| 2234/2400 [1:16:14<08:49,  3.19s/it, lr: 5.0e-05 loss: 3.255e-01]
leoprint:  93%|#########3| 2234/2400 [1:16:18<08:49,  3.19s/it, lr: 5.0e-05 loss: 2.606e-01]
leoprint:  93%|#########3| 2234/2400 [1:16:18<08:49,  3.19s/it, lr: 5.0e-05 loss: 2.606e-01]
leoprint:  93%|#########3| 2235/2400 [1:16:18<09:17,  3.38s/it, lr: 5.0e-05 loss: 2.606e-01]
leoprint:  93%|#########3| 2235/2400 [1:16:18<09:17,  3.38s/it, lr: 5.0e-05 loss: 2.606e-01]
leoprint:  93%|#########3| 2235/2400 [1:16:22<09:17,  3.38s/it, lr: 5.0e-05 loss: 3.783e-01]
leoprint:  93%|#########3| 2235/2400 [1:16:22<09:17,  3.38s/it, lr: 5.0e-05 loss: 3.783e-01]
leoprint:  93%|#########3| 2236/2400 [1:16:22<09:20,  3.42s/it, lr: 5.0e-05 loss: 3.783e-01]
leoprint:  93%|#########3| 2236/2400 [1:16:22<09:20,  3.42s/it, lr: 5.0e-05 loss: 3.783e-01]
leoprint:  93%|#########3| 2236/2400 [1:16:25<09:20,  3.42s/it, lr: 5.0e-05 loss: 3.138e-01]
leoprint:  93%|#########3| 2236/2400 [1:16:25<09:20,  3.42s/it, lr: 5.0e-05 loss: 3.138e-01]
leoprint:  93%|#########3| 2237/2400 [1:16:25<09:20,  3.44s/it, lr: 5.0e-05 loss: 3.138e-01]
leoprint:  93%|#########3| 2237/2400 [1:16:25<09:20,  3.44s/it, lr: 5.0e-05 loss: 3.138e-01]
leoprint:  93%|#########3| 2237/2400 [1:16:29<09:20,  3.44s/it, lr: 5.0e-05 loss: 3.184e-01]
leoprint:  93%|#########3| 2237/2400 [1:16:29<09:20,  3.44s/it, lr: 5.0e-05 loss: 3.184e-01]
leoprint:  93%|#########3| 2238/2400 [1:16:29<09:26,  3.50s/it, lr: 5.0e-05 loss: 3.184e-01]
leoprint:  93%|#########3| 2238/2400 [1:16:29<09:26,  3.50s/it, lr: 5.0e-05 loss: 3.184e-01]
leoprint:  93%|#########3| 2238/2400 [1:16:32<09:26,  3.50s/it, lr: 5.0e-05 loss: 2.657e-01]
leoprint:  93%|#########3| 2238/2400 [1:16:32<09:26,  3.50s/it, lr: 5.0e-05 loss: 2.657e-01]
leoprint:  93%|#########3| 2239/2400 [1:16:32<09:23,  3.50s/it, lr: 5.0e-05 loss: 2.657e-01]
leoprint:  93%|#########3| 2239/2400 [1:16:32<09:23,  3.50s/it, lr: 5.0e-05 loss: 2.657e-01]
leoprint:  93%|#########3| 2239/2400 [1:16:36<09:23,  3.50s/it, lr: 5.0e-05 loss: 3.037e-01]
leoprint:  93%|#########3| 2239/2400 [1:16:36<09:23,  3.50s/it, lr: 5.0e-05 loss: 3.037e-01]
leoprint:  93%|#########3| 2240/2400 [1:16:40<09:20,  3.50s/it, lr: 5.0e-05 loss: 2.802e-01]
leoprint:  93%|#########3| 2240/2400 [1:16:40<09:20,  3.50s/it, lr: 5.0e-05 loss: 2.802e-01]
leoprint:  93%|#########3| 2241/2400 [1:16:40<07:14,  2.73s/it, lr: 5.0e-05 loss: 2.802e-01]
leoprint:  93%|#########3| 2241/2400 [1:16:40<07:14,  2.73s/it, lr: 5.0e-05 loss: 2.802e-01]
leoprint:  93%|#########3| 2241/2400 [1:16:43<07:14,  2.73s/it, lr: 5.0e-05 loss: 2.297e-01]
leoprint:  93%|#########3| 2241/2400 [1:16:43<07:14,  2.73s/it, lr: 5.0e-05 loss: 2.297e-01]
leoprint:  93%|#########3| 2242/2400 [1:16:43<07:46,  2.95s/it, lr: 5.0e-05 loss: 2.297e-01]
leoprint:  93%|#########3| 2242/2400 [1:16:43<07:46,  2.95s/it, lr: 5.0e-05 loss: 2.297e-01]
leoprint:  93%|#########3| 2242/2400 [1:16:47<07:46,  2.95s/it, lr: 5.0e-05 loss: 2.959e-01]
leoprint:  93%|#########3| 2242/2400 [1:16:47<07:46,  2.95s/it, lr: 5.0e-05 loss: 2.959e-01]
leoprint:  93%|#########3| 2243/2400 [1:16:47<08:06,  3.10s/it, lr: 5.0e-05 loss: 2.959e-01]
leoprint:  93%|#########3| 2243/2400 [1:16:47<08:06,  3.10s/it, lr: 5.0e-05 loss: 2.959e-01]
leoprint:  93%|#########3| 2243/2400 [1:16:50<08:06,  3.10s/it, lr: 5.0e-05 loss: 2.432e-01]
leoprint:  93%|#########3| 2243/2400 [1:16:50<08:06,  3.10s/it, lr: 5.0e-05 loss: 2.432e-01]
leoprint:  94%|#########3| 2244/2400 [1:16:50<08:25,  3.24s/it, lr: 5.0e-05 loss: 2.432e-01]
leoprint:  94%|#########3| 2244/2400 [1:16:50<08:25,  3.24s/it, lr: 5.0e-05 loss: 2.432e-01]
leoprint:  94%|#########3| 2244/2400 [1:16:54<08:25,  3.24s/it, lr: 5.0e-05 loss: 3.698e-01]
leoprint:  94%|#########3| 2244/2400 [1:16:54<08:25,  3.24s/it, lr: 5.0e-05 loss: 3.698e-01]
leoprint:  94%|#########3| 2245/2400 [1:16:54<08:33,  3.32s/it, lr: 5.0e-05 loss: 3.698e-01]
leoprint:  94%|#########3| 2245/2400 [1:16:54<08:33,  3.32s/it, lr: 5.0e-05 loss: 3.698e-01]
leoprint:  94%|#########3| 2245/2400 [1:16:58<08:33,  3.32s/it, lr: 5.0e-05 loss: 2.924e-01]
leoprint:  94%|#########3| 2245/2400 [1:16:58<08:33,  3.32s/it, lr: 5.0e-05 loss: 2.924e-01]
leoprint:  94%|#########3| 2246/2400 [1:16:58<08:46,  3.42s/it, lr: 5.0e-05 loss: 2.924e-01]
leoprint:  94%|#########3| 2246/2400 [1:16:58<08:46,  3.42s/it, lr: 5.0e-05 loss: 2.924e-01]
leoprint:  94%|#########3| 2246/2400 [1:17:01<08:46,  3.42s/it, lr: 5.0e-05 loss: 3.157e-01]
leoprint:  94%|#########3| 2246/2400 [1:17:01<08:46,  3.42s/it, lr: 5.0e-05 loss: 3.157e-01]
leoprint:  94%|#########3| 2247/2400 [1:17:01<08:52,  3.48s/it, lr: 5.0e-05 loss: 3.157e-01]
leoprint:  94%|#########3| 2247/2400 [1:17:01<08:52,  3.48s/it, lr: 5.0e-05 loss: 3.157e-01]
leoprint:  94%|#########3| 2247/2400 [1:17:05<08:52,  3.48s/it, lr: 5.0e-05 loss: 3.182e-01]
leoprint:  94%|#########3| 2247/2400 [1:17:05<08:52,  3.48s/it, lr: 5.0e-05 loss: 3.182e-01]
leoprint:  94%|#########3| 2248/2400 [1:17:05<08:50,  3.49s/it, lr: 5.0e-05 loss: 3.182e-01]
leoprint:  94%|#########3| 2248/2400 [1:17:05<08:50,  3.49s/it, lr: 5.0e-05 loss: 3.182e-01]
leoprint:  94%|#########3| 2248/2400 [1:17:08<08:50,  3.49s/it, lr: 5.0e-05 loss: 2.614e-01]
leoprint:  94%|#########3| 2248/2400 [1:17:08<08:50,  3.49s/it, lr: 5.0e-05 loss: 2.614e-01]
leoprint:  94%|#########3| 2249/2400 [1:17:08<08:47,  3.49s/it, lr: 5.0e-05 loss: 2.614e-01]
leoprint:  94%|#########3| 2249/2400 [1:17:08<08:47,  3.49s/it, lr: 5.0e-05 loss: 2.614e-01]
leoprint:  94%|#########3| 2249/2400 [1:17:12<08:47,  3.49s/it, lr: 5.0e-05 loss: 2.760e-01]
leoprint:  94%|#########3| 2249/2400 [1:17:12<08:47,  3.49s/it, lr: 5.0e-05 loss: 2.760e-01]
leoprint:  94%|#########3| 2250/2400 [1:17:15<08:44,  3.49s/it, lr: 5.0e-05 loss: 2.004e-01]
leoprint:  94%|#########3| 2250/2400 [1:17:15<08:44,  3.49s/it, lr: 5.0e-05 loss: 2.004e-01]
leoprint:  94%|#########3| 2251/2400 [1:17:15<06:46,  2.73s/it, lr: 5.0e-05 loss: 2.004e-01]
leoprint:  94%|#########3| 2251/2400 [1:17:15<06:46,  2.73s/it, lr: 5.0e-05 loss: 2.004e-01]
leoprint:  94%|#########3| 2251/2400 [1:17:19<06:46,  2.73s/it, lr: 5.0e-05 loss: 2.953e-01]
leoprint:  94%|#########3| 2251/2400 [1:17:19<06:46,  2.73s/it, lr: 5.0e-05 loss: 2.953e-01]
leoprint:  94%|#########3| 2252/2400 [1:17:19<07:24,  3.00s/it, lr: 5.0e-05 loss: 2.953e-01]
leoprint:  94%|#########3| 2252/2400 [1:17:19<07:24,  3.00s/it, lr: 5.0e-05 loss: 2.953e-01]
leoprint:  94%|#########3| 2252/2400 [1:17:23<07:24,  3.00s/it, lr: 5.0e-05 loss: 3.533e-01]
leoprint:  94%|#########3| 2252/2400 [1:17:23<07:24,  3.00s/it, lr: 5.0e-05 loss: 3.533e-01]
leoprint:  94%|#########3| 2253/2400 [1:17:23<07:40,  3.14s/it, lr: 5.0e-05 loss: 3.533e-01]
leoprint:  94%|#########3| 2253/2400 [1:17:23<07:40,  3.14s/it, lr: 5.0e-05 loss: 3.533e-01]
leoprint:  94%|#########3| 2253/2400 [1:17:26<07:40,  3.14s/it, lr: 5.0e-05 loss: 2.583e-01]
leoprint:  94%|#########3| 2253/2400 [1:17:26<07:40,  3.14s/it, lr: 5.0e-05 loss: 2.583e-01]
leoprint:  94%|#########3| 2254/2400 [1:17:26<07:52,  3.24s/it, lr: 5.0e-05 loss: 2.583e-01]
leoprint:  94%|#########3| 2254/2400 [1:17:26<07:52,  3.24s/it, lr: 5.0e-05 loss: 2.583e-01]
leoprint:  94%|#########3| 2254/2400 [1:17:30<07:52,  3.24s/it, lr: 5.0e-05 loss: 3.778e-01]
leoprint:  94%|#########3| 2254/2400 [1:17:30<07:52,  3.24s/it, lr: 5.0e-05 loss: 3.778e-01]
leoprint:  94%|#########3| 2255/2400 [1:17:30<08:00,  3.31s/it, lr: 5.0e-05 loss: 3.778e-01]
leoprint:  94%|#########3| 2255/2400 [1:17:30<08:00,  3.31s/it, lr: 5.0e-05 loss: 3.778e-01]
leoprint:  94%|#########3| 2255/2400 [1:17:33<08:00,  3.31s/it, lr: 5.0e-05 loss: 2.290e-01]
leoprint:  94%|#########3| 2255/2400 [1:17:33<08:00,  3.31s/it, lr: 5.0e-05 loss: 2.290e-01]
leoprint:  94%|#########3| 2256/2400 [1:17:33<08:05,  3.37s/it, lr: 5.0e-05 loss: 2.290e-01]
leoprint:  94%|#########3| 2256/2400 [1:17:33<08:05,  3.37s/it, lr: 5.0e-05 loss: 2.290e-01]
leoprint:  94%|#########3| 2256/2400 [1:17:37<08:05,  3.37s/it, lr: 5.0e-05 loss: 3.986e-01]
leoprint:  94%|#########3| 2256/2400 [1:17:37<08:05,  3.37s/it, lr: 5.0e-05 loss: 3.986e-01]
leoprint:  94%|#########4| 2257/2400 [1:17:37<08:07,  3.41s/it, lr: 5.0e-05 loss: 3.986e-01]
leoprint:  94%|#########4| 2257/2400 [1:17:37<08:07,  3.41s/it, lr: 5.0e-05 loss: 3.986e-01]
leoprint:  94%|#########4| 2257/2400 [1:17:41<08:07,  3.41s/it, lr: 5.0e-05 loss: 3.117e-01]
leoprint:  94%|#########4| 2257/2400 [1:17:41<08:07,  3.41s/it, lr: 5.0e-05 loss: 3.117e-01]
leoprint:  94%|#########4| 2258/2400 [1:17:41<08:18,  3.51s/it, lr: 5.0e-05 loss: 3.117e-01]
leoprint:  94%|#########4| 2258/2400 [1:17:41<08:18,  3.51s/it, lr: 5.0e-05 loss: 3.117e-01]
leoprint:  94%|#########4| 2258/2400 [1:17:44<08:18,  3.51s/it, lr: 5.0e-05 loss: 2.300e-01]
leoprint:  94%|#########4| 2258/2400 [1:17:44<08:18,  3.51s/it, lr: 5.0e-05 loss: 2.300e-01]
leoprint:  94%|#########4| 2259/2400 [1:17:44<08:14,  3.51s/it, lr: 5.0e-05 loss: 2.300e-01]
leoprint:  94%|#########4| 2259/2400 [1:17:44<08:14,  3.51s/it, lr: 5.0e-05 loss: 2.300e-01]
leoprint:  94%|#########4| 2259/2400 [1:17:48<08:14,  3.51s/it, lr: 5.0e-05 loss: 2.811e-01]
leoprint:  94%|#########4| 2259/2400 [1:17:48<08:14,  3.51s/it, lr: 5.0e-05 loss: 2.811e-01]
leoprint:  94%|#########4| 2260/2400 [1:17:51<08:11,  3.51s/it, lr: 5.0e-05 loss: 2.871e-01]
leoprint:  94%|#########4| 2260/2400 [1:17:51<08:11,  3.51s/it, lr: 5.0e-05 loss: 2.871e-01]
leoprint:  94%|#########4| 2261/2400 [1:17:51<06:19,  2.73s/it, lr: 5.0e-05 loss: 2.871e-01]
leoprint:  94%|#########4| 2261/2400 [1:17:51<06:19,  2.73s/it, lr: 5.0e-05 loss: 2.871e-01]
leoprint:  94%|#########4| 2261/2400 [1:17:55<06:19,  2.73s/it, lr: 5.0e-05 loss: 2.479e-01]
leoprint:  94%|#########4| 2261/2400 [1:17:55<06:19,  2.73s/it, lr: 5.0e-05 loss: 2.479e-01]
leoprint:  94%|#########4| 2262/2400 [1:17:55<06:47,  2.95s/it, lr: 5.0e-05 loss: 2.479e-01]
leoprint:  94%|#########4| 2262/2400 [1:17:55<06:47,  2.95s/it, lr: 5.0e-05 loss: 2.479e-01]
leoprint:  94%|#########4| 2262/2400 [1:17:58<06:47,  2.95s/it, lr: 5.0e-05 loss: 3.965e-01]
leoprint:  94%|#########4| 2262/2400 [1:17:58<06:47,  2.95s/it, lr: 5.0e-05 loss: 3.965e-01]
leoprint:  94%|#########4| 2263/2400 [1:17:58<07:04,  3.10s/it, lr: 5.0e-05 loss: 3.965e-01]
leoprint:  94%|#########4| 2263/2400 [1:17:58<07:04,  3.10s/it, lr: 5.0e-05 loss: 3.965e-01]
leoprint:  94%|#########4| 2263/2400 [1:18:02<07:04,  3.10s/it, lr: 5.0e-05 loss: 2.888e-01]
leoprint:  94%|#########4| 2263/2400 [1:18:02<07:04,  3.10s/it, lr: 5.0e-05 loss: 2.888e-01]
leoprint:  94%|#########4| 2264/2400 [1:18:02<07:25,  3.28s/it, lr: 5.0e-05 loss: 2.888e-01]
leoprint:  94%|#########4| 2264/2400 [1:18:02<07:25,  3.28s/it, lr: 5.0e-05 loss: 2.888e-01]
leoprint:  94%|#########4| 2264/2400 [1:18:06<07:25,  3.28s/it, lr: 5.0e-05 loss: 2.527e-01]
leoprint:  94%|#########4| 2264/2400 [1:18:06<07:25,  3.28s/it, lr: 5.0e-05 loss: 2.527e-01]
leoprint:  94%|#########4| 2265/2400 [1:18:06<07:35,  3.38s/it, lr: 5.0e-05 loss: 2.527e-01]
leoprint:  94%|#########4| 2265/2400 [1:18:06<07:35,  3.38s/it, lr: 5.0e-05 loss: 2.527e-01]
leoprint:  94%|#########4| 2265/2400 [1:18:09<07:35,  3.38s/it, lr: 5.0e-05 loss: 2.468e-01]
leoprint:  94%|#########4| 2265/2400 [1:18:09<07:35,  3.38s/it, lr: 5.0e-05 loss: 2.468e-01]
leoprint:  94%|#########4| 2266/2400 [1:18:09<07:37,  3.42s/it, lr: 5.0e-05 loss: 2.468e-01]
leoprint:  94%|#########4| 2266/2400 [1:18:09<07:37,  3.42s/it, lr: 5.0e-05 loss: 2.468e-01]
leoprint:  94%|#########4| 2266/2400 [1:18:13<07:37,  3.42s/it, lr: 5.0e-05 loss: 2.577e-01]
leoprint:  94%|#########4| 2266/2400 [1:18:13<07:37,  3.42s/it, lr: 5.0e-05 loss: 2.577e-01]
leoprint:  94%|#########4| 2267/2400 [1:18:13<07:42,  3.48s/it, lr: 5.0e-05 loss: 2.577e-01]
leoprint:  94%|#########4| 2267/2400 [1:18:13<07:42,  3.48s/it, lr: 5.0e-05 loss: 2.577e-01]
leoprint:  94%|#########4| 2267/2400 [1:18:16<07:42,  3.48s/it, lr: 5.0e-05 loss: 3.087e-01]
leoprint:  94%|#########4| 2267/2400 [1:18:16<07:42,  3.48s/it, lr: 5.0e-05 loss: 3.087e-01]
leoprint:  94%|#########4| 2268/2400 [1:18:16<07:39,  3.48s/it, lr: 5.0e-05 loss: 3.087e-01]
leoprint:  94%|#########4| 2268/2400 [1:18:16<07:39,  3.48s/it, lr: 5.0e-05 loss: 3.087e-01]
leoprint:  94%|#########4| 2268/2400 [1:18:20<07:39,  3.48s/it, lr: 5.0e-05 loss: 3.160e-01]
leoprint:  94%|#########4| 2268/2400 [1:18:20<07:39,  3.48s/it, lr: 5.0e-05 loss: 3.160e-01]
leoprint:  95%|#########4| 2269/2400 [1:18:20<07:44,  3.54s/it, lr: 5.0e-05 loss: 3.160e-01]
leoprint:  95%|#########4| 2269/2400 [1:18:20<07:44,  3.54s/it, lr: 5.0e-05 loss: 3.160e-01]
leoprint:  95%|#########4| 2269/2400 [1:18:24<07:44,  3.54s/it, lr: 5.0e-05 loss: 3.598e-01]
leoprint:  95%|#########4| 2269/2400 [1:18:24<07:44,  3.54s/it, lr: 5.0e-05 loss: 3.598e-01]
leoprint:  95%|#########4| 2270/2400 [1:18:27<07:40,  3.54s/it, lr: 5.0e-05 loss: 3.105e-01]
leoprint:  95%|#########4| 2270/2400 [1:18:27<07:40,  3.54s/it, lr: 5.0e-05 loss: 3.105e-01]
leoprint:  95%|#########4| 2271/2400 [1:18:27<05:51,  2.72s/it, lr: 5.0e-05 loss: 3.105e-01]
leoprint:  95%|#########4| 2271/2400 [1:18:27<05:51,  2.72s/it, lr: 5.0e-05 loss: 3.105e-01]
leoprint:  95%|#########4| 2271/2400 [1:18:31<05:51,  2.72s/it, lr: 5.0e-05 loss: 3.295e-01]
leoprint:  95%|#########4| 2271/2400 [1:18:31<05:51,  2.72s/it, lr: 5.0e-05 loss: 3.295e-01]
leoprint:  95%|#########4| 2272/2400 [1:18:31<06:13,  2.92s/it, lr: 5.0e-05 loss: 3.295e-01]
leoprint:  95%|#########4| 2272/2400 [1:18:31<06:13,  2.92s/it, lr: 5.0e-05 loss: 3.295e-01]
leoprint:  95%|#########4| 2272/2400 [1:18:34<06:13,  2.92s/it, lr: 5.0e-05 loss: 3.383e-01]
leoprint:  95%|#########4| 2272/2400 [1:18:34<06:13,  2.92s/it, lr: 5.0e-05 loss: 3.383e-01]
leoprint:  95%|#########4| 2273/2400 [1:18:34<06:29,  3.07s/it, lr: 5.0e-05 loss: 3.383e-01]
leoprint:  95%|#########4| 2273/2400 [1:18:34<06:29,  3.07s/it, lr: 5.0e-05 loss: 3.383e-01]
leoprint:  95%|#########4| 2273/2400 [1:18:38<06:29,  3.07s/it, lr: 5.0e-05 loss: 3.101e-01]
leoprint:  95%|#########4| 2273/2400 [1:18:38<06:29,  3.07s/it, lr: 5.0e-05 loss: 3.101e-01]
leoprint:  95%|#########4| 2274/2400 [1:18:38<06:41,  3.19s/it, lr: 5.0e-05 loss: 3.101e-01]
leoprint:  95%|#########4| 2274/2400 [1:18:38<06:41,  3.19s/it, lr: 5.0e-05 loss: 3.101e-01]
leoprint:  95%|#########4| 2274/2400 [1:18:41<06:41,  3.19s/it, lr: 5.0e-05 loss: 2.066e-01]
leoprint:  95%|#########4| 2274/2400 [1:18:41<06:41,  3.19s/it, lr: 5.0e-05 loss: 2.066e-01]
leoprint:  95%|#########4| 2275/2400 [1:18:41<06:56,  3.33s/it, lr: 5.0e-05 loss: 2.066e-01]
leoprint:  95%|#########4| 2275/2400 [1:18:41<06:56,  3.33s/it, lr: 5.0e-05 loss: 2.066e-01]
leoprint:  95%|#########4| 2275/2400 [1:18:45<06:56,  3.33s/it, lr: 5.0e-05 loss: 2.825e-01]
leoprint:  95%|#########4| 2275/2400 [1:18:45<06:56,  3.33s/it, lr: 5.0e-05 loss: 2.825e-01]
leoprint:  95%|#########4| 2276/2400 [1:18:45<06:59,  3.38s/it, lr: 5.0e-05 loss: 2.825e-01]
leoprint:  95%|#########4| 2276/2400 [1:18:45<06:59,  3.38s/it, lr: 5.0e-05 loss: 2.825e-01]
leoprint:  95%|#########4| 2276/2400 [1:18:48<06:59,  3.38s/it, lr: 5.0e-05 loss: 3.435e-01]
leoprint:  95%|#########4| 2276/2400 [1:18:48<06:59,  3.38s/it, lr: 5.0e-05 loss: 3.435e-01]
leoprint:  95%|#########4| 2277/2400 [1:18:48<07:00,  3.42s/it, lr: 5.0e-05 loss: 3.435e-01]
leoprint:  95%|#########4| 2277/2400 [1:18:48<07:00,  3.42s/it, lr: 5.0e-05 loss: 3.435e-01]
leoprint:  95%|#########4| 2277/2400 [1:18:52<07:00,  3.42s/it, lr: 5.0e-05 loss: 2.570e-01]
leoprint:  95%|#########4| 2277/2400 [1:18:52<07:00,  3.42s/it, lr: 5.0e-05 loss: 2.570e-01]
leoprint:  95%|#########4| 2278/2400 [1:18:52<07:04,  3.48s/it, lr: 5.0e-05 loss: 2.570e-01]
leoprint:  95%|#########4| 2278/2400 [1:18:52<07:04,  3.48s/it, lr: 5.0e-05 loss: 2.570e-01]
leoprint:  95%|#########4| 2278/2400 [1:18:56<07:04,  3.48s/it, lr: 5.0e-05 loss: 3.138e-01]
leoprint:  95%|#########4| 2278/2400 [1:18:56<07:04,  3.48s/it, lr: 5.0e-05 loss: 3.138e-01]
leoprint:  95%|#########4| 2279/2400 [1:18:56<07:02,  3.49s/it, lr: 5.0e-05 loss: 3.138e-01]
leoprint:  95%|#########4| 2279/2400 [1:18:56<07:02,  3.49s/it, lr: 5.0e-05 loss: 3.138e-01]
leoprint:  95%|#########4| 2279/2400 [1:18:59<07:02,  3.49s/it, lr: 5.0e-05 loss: 2.259e-01]
leoprint:  95%|#########4| 2279/2400 [1:18:59<07:02,  3.49s/it, lr: 5.0e-05 loss: 2.259e-01]
leoprint:  95%|#########5| 2280/2400 [1:19:03<06:58,  3.49s/it, lr: 5.0e-05 loss: 2.184e-01]
leoprint:  95%|#########5| 2280/2400 [1:19:03<06:58,  3.49s/it, lr: 5.0e-05 loss: 2.184e-01]
leoprint:  95%|#########5| 2281/2400 [1:19:03<05:27,  2.75s/it, lr: 5.0e-05 loss: 2.184e-01]
leoprint:  95%|#########5| 2281/2400 [1:19:03<05:27,  2.75s/it, lr: 5.0e-05 loss: 2.184e-01]
leoprint:  95%|#########5| 2281/2400 [1:19:06<05:27,  2.75s/it, lr: 5.0e-05 loss: 2.927e-01]
leoprint:  95%|#########5| 2281/2400 [1:19:06<05:27,  2.75s/it, lr: 5.0e-05 loss: 2.927e-01]
leoprint:  95%|#########5| 2282/2400 [1:19:07<05:50,  2.97s/it, lr: 5.0e-05 loss: 2.927e-01]
leoprint:  95%|#########5| 2282/2400 [1:19:07<05:50,  2.97s/it, lr: 5.0e-05 loss: 2.927e-01]
leoprint:  95%|#########5| 2282/2400 [1:19:10<05:50,  2.97s/it, lr: 5.0e-05 loss: 2.427e-01]
leoprint:  95%|#########5| 2282/2400 [1:19:10<05:50,  2.97s/it, lr: 5.0e-05 loss: 2.427e-01]
leoprint:  95%|#########5| 2283/2400 [1:19:10<06:07,  3.14s/it, lr: 5.0e-05 loss: 2.427e-01]
leoprint:  95%|#########5| 2283/2400 [1:19:10<06:07,  3.14s/it, lr: 5.0e-05 loss: 2.427e-01]
leoprint:  95%|#########5| 2283/2400 [1:19:14<06:07,  3.14s/it, lr: 5.0e-05 loss: 2.768e-01]
leoprint:  95%|#########5| 2283/2400 [1:19:14<06:07,  3.14s/it, lr: 5.0e-05 loss: 2.768e-01]
leoprint:  95%|#########5| 2284/2400 [1:19:14<06:15,  3.24s/it, lr: 5.0e-05 loss: 2.768e-01]
leoprint:  95%|#########5| 2284/2400 [1:19:14<06:15,  3.24s/it, lr: 5.0e-05 loss: 2.768e-01]
leoprint:  95%|#########5| 2284/2400 [1:19:17<06:15,  3.24s/it, lr: 5.0e-05 loss: 3.067e-01]
leoprint:  95%|#########5| 2284/2400 [1:19:17<06:15,  3.24s/it, lr: 5.0e-05 loss: 3.067e-01]
leoprint:  95%|#########5| 2285/2400 [1:19:17<06:21,  3.31s/it, lr: 5.0e-05 loss: 3.067e-01]
leoprint:  95%|#########5| 2285/2400 [1:19:17<06:21,  3.31s/it, lr: 5.0e-05 loss: 3.067e-01]
leoprint:  95%|#########5| 2285/2400 [1:19:21<06:21,  3.31s/it, lr: 5.0e-05 loss: 2.549e-01]
leoprint:  95%|#########5| 2285/2400 [1:19:21<06:21,  3.31s/it, lr: 5.0e-05 loss: 2.549e-01]
leoprint:  95%|#########5| 2286/2400 [1:19:21<06:24,  3.37s/it, lr: 5.0e-05 loss: 2.549e-01]
leoprint:  95%|#########5| 2286/2400 [1:19:21<06:24,  3.37s/it, lr: 5.0e-05 loss: 2.549e-01]
leoprint:  95%|#########5| 2286/2400 [1:19:24<06:24,  3.37s/it, lr: 5.0e-05 loss: 2.204e-01]
leoprint:  95%|#########5| 2286/2400 [1:19:24<06:24,  3.37s/it, lr: 5.0e-05 loss: 2.204e-01]
leoprint:  95%|#########5| 2287/2400 [1:19:25<06:33,  3.49s/it, lr: 5.0e-05 loss: 2.204e-01]
leoprint:  95%|#########5| 2287/2400 [1:19:25<06:33,  3.49s/it, lr: 5.0e-05 loss: 2.204e-01]
leoprint:  95%|#########5| 2287/2400 [1:19:28<06:33,  3.49s/it, lr: 5.0e-05 loss: 3.645e-01]
leoprint:  95%|#########5| 2287/2400 [1:19:28<06:33,  3.49s/it, lr: 5.0e-05 loss: 3.645e-01]
leoprint:  95%|#########5| 2288/2400 [1:19:28<06:31,  3.49s/it, lr: 5.0e-05 loss: 3.645e-01]
leoprint:  95%|#########5| 2288/2400 [1:19:28<06:31,  3.49s/it, lr: 5.0e-05 loss: 3.645e-01]
leoprint:  95%|#########5| 2288/2400 [1:19:32<06:31,  3.49s/it, lr: 5.0e-05 loss: 2.519e-01]
leoprint:  95%|#########5| 2288/2400 [1:19:32<06:31,  3.49s/it, lr: 5.0e-05 loss: 2.519e-01]
leoprint:  95%|#########5| 2289/2400 [1:19:32<06:32,  3.53s/it, lr: 5.0e-05 loss: 2.519e-01]
leoprint:  95%|#########5| 2289/2400 [1:19:32<06:32,  3.53s/it, lr: 5.0e-05 loss: 2.519e-01]
leoprint:  95%|#########5| 2289/2400 [1:19:35<06:32,  3.53s/it, lr: 5.0e-05 loss: 2.131e-01]
leoprint:  95%|#########5| 2289/2400 [1:19:35<06:32,  3.53s/it, lr: 5.0e-05 loss: 2.131e-01]
leoprint:  95%|#########5| 2290/2400 [1:19:39<06:28,  3.53s/it, lr: 5.0e-05 loss: 2.309e-01]
leoprint:  95%|#########5| 2290/2400 [1:19:39<06:28,  3.53s/it, lr: 5.0e-05 loss: 2.309e-01]
leoprint:  95%|#########5| 2291/2400 [1:19:39<04:56,  2.72s/it, lr: 5.0e-05 loss: 2.309e-01]
leoprint:  95%|#########5| 2291/2400 [1:19:39<04:56,  2.72s/it, lr: 5.0e-05 loss: 2.309e-01]
leoprint:  95%|#########5| 2291/2400 [1:19:42<04:56,  2.72s/it, lr: 5.0e-05 loss: 2.920e-01]
leoprint:  95%|#########5| 2291/2400 [1:19:42<04:56,  2.72s/it, lr: 5.0e-05 loss: 2.920e-01]
leoprint:  96%|#########5| 2292/2400 [1:19:42<05:16,  2.93s/it, lr: 5.0e-05 loss: 2.920e-01]
leoprint:  96%|#########5| 2292/2400 [1:19:42<05:16,  2.93s/it, lr: 5.0e-05 loss: 2.920e-01]
leoprint:  96%|#########5| 2292/2400 [1:19:46<05:16,  2.93s/it, lr: 5.0e-05 loss: 2.004e-01]
leoprint:  96%|#########5| 2292/2400 [1:19:46<05:16,  2.93s/it, lr: 5.0e-05 loss: 2.004e-01]
leoprint:  96%|#########5| 2293/2400 [1:19:46<05:29,  3.08s/it, lr: 5.0e-05 loss: 2.004e-01]
leoprint:  96%|#########5| 2293/2400 [1:19:46<05:29,  3.08s/it, lr: 5.0e-05 loss: 2.004e-01]
leoprint:  96%|#########5| 2293/2400 [1:19:49<05:29,  3.08s/it, lr: 5.0e-05 loss: 2.094e-01]
leoprint:  96%|#########5| 2293/2400 [1:19:49<05:29,  3.08s/it, lr: 5.0e-05 loss: 2.094e-01]
leoprint:  96%|#########5| 2294/2400 [1:19:49<05:38,  3.20s/it, lr: 5.0e-05 loss: 2.094e-01]
leoprint:  96%|#########5| 2294/2400 [1:19:49<05:38,  3.20s/it, lr: 5.0e-05 loss: 2.094e-01]
leoprint:  96%|#########5| 2294/2400 [1:19:53<05:38,  3.20s/it, lr: 5.0e-05 loss: 3.408e-01]
leoprint:  96%|#########5| 2294/2400 [1:19:53<05:38,  3.20s/it, lr: 5.0e-05 loss: 3.408e-01]
leoprint:  96%|#########5| 2295/2400 [1:19:53<05:44,  3.28s/it, lr: 5.0e-05 loss: 3.408e-01]
leoprint:  96%|#########5| 2295/2400 [1:19:53<05:44,  3.28s/it, lr: 5.0e-05 loss: 3.408e-01]
leoprint:  96%|#########5| 2295/2400 [1:19:56<05:44,  3.28s/it, lr: 5.0e-05 loss: 3.058e-01]
leoprint:  96%|#########5| 2295/2400 [1:19:56<05:44,  3.28s/it, lr: 5.0e-05 loss: 3.058e-01]
leoprint:  96%|#########5| 2296/2400 [1:19:56<05:51,  3.38s/it, lr: 5.0e-05 loss: 3.058e-01]
leoprint:  96%|#########5| 2296/2400 [1:19:56<05:51,  3.38s/it, lr: 5.0e-05 loss: 3.058e-01]
leoprint:  96%|#########5| 2296/2400 [1:20:00<05:51,  3.38s/it, lr: 5.0e-05 loss: 2.583e-01]
leoprint:  96%|#########5| 2296/2400 [1:20:00<05:51,  3.38s/it, lr: 5.0e-05 loss: 2.583e-01]
leoprint:  96%|#########5| 2297/2400 [1:20:00<05:55,  3.45s/it, lr: 5.0e-05 loss: 2.583e-01]
leoprint:  96%|#########5| 2297/2400 [1:20:00<05:55,  3.45s/it, lr: 5.0e-05 loss: 2.583e-01]
leoprint:  96%|#########5| 2297/2400 [1:20:04<05:55,  3.45s/it, lr: 5.0e-05 loss: 3.013e-01]
leoprint:  96%|#########5| 2297/2400 [1:20:04<05:55,  3.45s/it, lr: 5.0e-05 loss: 3.013e-01]
leoprint:  96%|#########5| 2298/2400 [1:20:04<05:59,  3.52s/it, lr: 5.0e-05 loss: 3.013e-01]
leoprint:  96%|#########5| 2298/2400 [1:20:04<05:59,  3.52s/it, lr: 5.0e-05 loss: 3.013e-01]
leoprint:  96%|#########5| 2298/2400 [1:20:07<05:59,  3.52s/it, lr: 5.0e-05 loss: 3.267e-01]
leoprint:  96%|#########5| 2298/2400 [1:20:07<05:59,  3.52s/it, lr: 5.0e-05 loss: 3.267e-01]
leoprint:  96%|#########5| 2299/2400 [1:20:07<05:55,  3.52s/it, lr: 5.0e-05 loss: 3.267e-01]
leoprint:  96%|#########5| 2299/2400 [1:20:07<05:55,  3.52s/it, lr: 5.0e-05 loss: 3.267e-01]
leoprint:  96%|#########5| 2299/2400 [1:20:11<05:55,  3.52s/it, lr: 5.0e-05 loss: 3.740e-01]
leoprint:  96%|#########5| 2299/2400 [1:20:11<05:55,  3.52s/it, lr: 5.0e-05 loss: 3.740e-01]
leoprint:  96%|#########5| 2300/2400 [1:20:14<05:52,  3.52s/it, lr: 5.0e-05 loss: 2.997e-01]
leoprint:  96%|#########5| 2300/2400 [1:20:14<05:52,  3.52s/it, lr: 5.0e-05 loss: 2.997e-01]
leoprint:  96%|#########5| 2301/2400 [1:20:14<04:31,  2.74s/it, lr: 5.0e-05 loss: 2.997e-01]
leoprint:  96%|#########5| 2301/2400 [1:20:14<04:31,  2.74s/it, lr: 5.0e-05 loss: 2.997e-01]
leoprint:  96%|#########5| 2301/2400 [1:20:18<04:31,  2.74s/it, lr: 5.0e-05 loss: 2.535e-01]
leoprint:  96%|#########5| 2301/2400 [1:20:18<04:31,  2.74s/it, lr: 5.0e-05 loss: 2.535e-01]
leoprint:  96%|#########5| 2302/2400 [1:20:18<04:49,  2.96s/it, lr: 5.0e-05 loss: 2.535e-01]
leoprint:  96%|#########5| 2302/2400 [1:20:18<04:49,  2.96s/it, lr: 5.0e-05 loss: 2.535e-01]
leoprint:  96%|#########5| 2302/2400 [1:20:22<04:49,  2.96s/it, lr: 5.0e-05 loss: 3.665e-01]
leoprint:  96%|#########5| 2302/2400 [1:20:22<04:49,  2.96s/it, lr: 5.0e-05 loss: 3.665e-01]
leoprint:  96%|#########5| 2303/2400 [1:20:22<05:00,  3.10s/it, lr: 5.0e-05 loss: 3.665e-01]
leoprint:  96%|#########5| 2303/2400 [1:20:22<05:00,  3.10s/it, lr: 5.0e-05 loss: 3.665e-01]
leoprint:  96%|#########5| 2303/2400 [1:20:25<05:00,  3.10s/it, lr: 5.0e-05 loss: 2.920e-01]
leoprint:  96%|#########5| 2303/2400 [1:20:25<05:00,  3.10s/it, lr: 5.0e-05 loss: 2.920e-01]
leoprint:  96%|#########6| 2304/2400 [1:20:25<05:12,  3.25s/it, lr: 5.0e-05 loss: 2.920e-01]
leoprint:  96%|#########6| 2304/2400 [1:20:25<05:12,  3.25s/it, lr: 5.0e-05 loss: 2.920e-01]
leoprint:  96%|#########6| 2304/2400 [1:20:29<05:12,  3.25s/it, lr: 5.0e-05 loss: 2.517e-01]
leoprint:  96%|#########6| 2304/2400 [1:20:29<05:12,  3.25s/it, lr: 5.0e-05 loss: 2.517e-01]
leoprint:  96%|#########6| 2305/2400 [1:20:29<05:19,  3.36s/it, lr: 5.0e-05 loss: 2.517e-01]
leoprint:  96%|#########6| 2305/2400 [1:20:29<05:19,  3.36s/it, lr: 5.0e-05 loss: 2.517e-01]
leoprint:  96%|#########6| 2305/2400 [1:20:32<05:19,  3.36s/it, lr: 5.0e-05 loss: 2.495e-01]
leoprint:  96%|#########6| 2305/2400 [1:20:32<05:19,  3.36s/it, lr: 5.0e-05 loss: 2.495e-01]
leoprint:  96%|#########6| 2306/2400 [1:20:32<05:19,  3.40s/it, lr: 5.0e-05 loss: 2.495e-01]
leoprint:  96%|#########6| 2306/2400 [1:20:32<05:19,  3.40s/it, lr: 5.0e-05 loss: 2.495e-01]
leoprint:  96%|#########6| 2306/2400 [1:20:36<05:19,  3.40s/it, lr: 5.0e-05 loss: 3.504e-01]
leoprint:  96%|#########6| 2306/2400 [1:20:36<05:19,  3.40s/it, lr: 5.0e-05 loss: 3.504e-01]
leoprint:  96%|#########6| 2307/2400 [1:20:36<05:19,  3.43s/it, lr: 5.0e-05 loss: 3.504e-01]
leoprint:  96%|#########6| 2307/2400 [1:20:36<05:19,  3.43s/it, lr: 5.0e-05 loss: 3.504e-01]
leoprint:  96%|#########6| 2307/2400 [1:20:39<05:19,  3.43s/it, lr: 5.0e-05 loss: 2.194e-01]
leoprint:  96%|#########6| 2307/2400 [1:20:39<05:19,  3.43s/it, lr: 5.0e-05 loss: 2.194e-01]
leoprint:  96%|#########6| 2308/2400 [1:20:39<05:17,  3.45s/it, lr: 5.0e-05 loss: 2.194e-01]
leoprint:  96%|#########6| 2308/2400 [1:20:39<05:17,  3.45s/it, lr: 5.0e-05 loss: 2.194e-01]
leoprint:  96%|#########6| 2308/2400 [1:20:43<05:17,  3.45s/it, lr: 5.0e-05 loss: 2.023e-01]
leoprint:  96%|#########6| 2308/2400 [1:20:43<05:17,  3.45s/it, lr: 5.0e-05 loss: 2.023e-01]
leoprint:  96%|#########6| 2309/2400 [1:20:43<05:24,  3.56s/it, lr: 5.0e-05 loss: 2.023e-01]
leoprint:  96%|#########6| 2309/2400 [1:20:43<05:24,  3.56s/it, lr: 5.0e-05 loss: 2.023e-01]
leoprint:  96%|#########6| 2309/2400 [1:20:47<05:24,  3.56s/it, lr: 5.0e-05 loss: 2.622e-01]
leoprint:  96%|#########6| 2309/2400 [1:20:47<05:24,  3.56s/it, lr: 5.0e-05 loss: 2.622e-01]
leoprint:  96%|#########6| 2310/2400 [1:20:50<05:20,  3.56s/it, lr: 5.0e-05 loss: 3.132e-01]
leoprint:  96%|#########6| 2310/2400 [1:20:50<05:20,  3.56s/it, lr: 5.0e-05 loss: 3.132e-01]
leoprint:  96%|#########6| 2311/2400 [1:20:50<04:03,  2.73s/it, lr: 5.0e-05 loss: 3.132e-01]
leoprint:  96%|#########6| 2311/2400 [1:20:50<04:03,  2.73s/it, lr: 5.0e-05 loss: 3.132e-01]
leoprint:  96%|#########6| 2311/2400 [1:20:54<04:03,  2.73s/it, lr: 5.0e-05 loss: 2.207e-01]
leoprint:  96%|#########6| 2311/2400 [1:20:54<04:03,  2.73s/it, lr: 5.0e-05 loss: 2.207e-01]
leoprint:  96%|#########6| 2312/2400 [1:20:54<04:17,  2.93s/it, lr: 5.0e-05 loss: 2.207e-01]
leoprint:  96%|#########6| 2312/2400 [1:20:54<04:17,  2.93s/it, lr: 5.0e-05 loss: 2.207e-01]
leoprint:  96%|#########6| 2312/2400 [1:20:57<04:17,  2.93s/it, lr: 5.0e-05 loss: 2.758e-01]
leoprint:  96%|#########6| 2312/2400 [1:20:57<04:17,  2.93s/it, lr: 5.0e-05 loss: 2.758e-01]
leoprint:  96%|#########6| 2313/2400 [1:20:57<04:27,  3.08s/it, lr: 5.0e-05 loss: 2.758e-01]
leoprint:  96%|#########6| 2313/2400 [1:20:57<04:27,  3.08s/it, lr: 5.0e-05 loss: 2.758e-01]
leoprint:  96%|#########6| 2313/2400 [1:21:01<04:27,  3.08s/it, lr: 5.0e-05 loss: 2.350e-01]
leoprint:  96%|#########6| 2313/2400 [1:21:01<04:27,  3.08s/it, lr: 5.0e-05 loss: 2.350e-01]
leoprint:  96%|#########6| 2314/2400 [1:21:01<04:34,  3.20s/it, lr: 5.0e-05 loss: 2.350e-01]
leoprint:  96%|#########6| 2314/2400 [1:21:01<04:34,  3.20s/it, lr: 5.0e-05 loss: 2.350e-01]
leoprint:  96%|#########6| 2314/2400 [1:21:05<04:34,  3.20s/it, lr: 5.0e-05 loss: 3.415e-01]
leoprint:  96%|#########6| 2314/2400 [1:21:05<04:34,  3.20s/it, lr: 5.0e-05 loss: 3.415e-01]
leoprint:  96%|#########6| 2315/2400 [1:21:05<04:41,  3.31s/it, lr: 5.0e-05 loss: 3.415e-01]
leoprint:  96%|#########6| 2315/2400 [1:21:05<04:41,  3.31s/it, lr: 5.0e-05 loss: 3.415e-01]
leoprint:  96%|#########6| 2315/2400 [1:21:08<04:41,  3.31s/it, lr: 5.0e-05 loss: 3.804e-01]
leoprint:  96%|#########6| 2315/2400 [1:21:08<04:41,  3.31s/it, lr: 5.0e-05 loss: 3.804e-01]
leoprint:  96%|#########6| 2316/2400 [1:21:08<04:42,  3.36s/it, lr: 5.0e-05 loss: 3.804e-01]
leoprint:  96%|#########6| 2316/2400 [1:21:08<04:42,  3.36s/it, lr: 5.0e-05 loss: 3.804e-01]
leoprint:  96%|#########6| 2316/2400 [1:21:12<04:42,  3.36s/it, lr: 5.0e-05 loss: 2.374e-01]
leoprint:  96%|#########6| 2316/2400 [1:21:12<04:42,  3.36s/it, lr: 5.0e-05 loss: 2.374e-01]
leoprint:  97%|#########6| 2317/2400 [1:21:12<04:45,  3.45s/it, lr: 5.0e-05 loss: 2.374e-01]
leoprint:  97%|#########6| 2317/2400 [1:21:12<04:45,  3.45s/it, lr: 5.0e-05 loss: 2.374e-01]
leoprint:  97%|#########6| 2317/2400 [1:21:15<04:45,  3.45s/it, lr: 5.0e-05 loss: 2.167e-01]
leoprint:  97%|#########6| 2317/2400 [1:21:15<04:45,  3.45s/it, lr: 5.0e-05 loss: 2.167e-01]
leoprint:  97%|#########6| 2318/2400 [1:21:15<04:43,  3.46s/it, lr: 5.0e-05 loss: 2.167e-01]
leoprint:  97%|#########6| 2318/2400 [1:21:15<04:43,  3.46s/it, lr: 5.0e-05 loss: 2.167e-01]
leoprint:  97%|#########6| 2318/2400 [1:21:19<04:43,  3.46s/it, lr: 5.0e-05 loss: 2.678e-01]
leoprint:  97%|#########6| 2318/2400 [1:21:19<04:43,  3.46s/it, lr: 5.0e-05 loss: 2.678e-01]
leoprint:  97%|#########6| 2319/2400 [1:21:19<04:41,  3.47s/it, lr: 5.0e-05 loss: 2.678e-01]
leoprint:  97%|#########6| 2319/2400 [1:21:19<04:41,  3.47s/it, lr: 5.0e-05 loss: 2.678e-01]
leoprint:  97%|#########6| 2319/2400 [1:21:22<04:41,  3.47s/it, lr: 5.0e-05 loss: 2.778e-01]
leoprint:  97%|#########6| 2319/2400 [1:21:22<04:41,  3.47s/it, lr: 5.0e-05 loss: 2.778e-01]
leoprint:  97%|#########6| 2320/2400 [1:21:26<04:37,  3.47s/it, lr: 5.0e-05 loss: 2.824e-01]
leoprint:  97%|#########6| 2320/2400 [1:21:26<04:37,  3.47s/it, lr: 5.0e-05 loss: 2.824e-01]
leoprint:  97%|#########6| 2321/2400 [1:21:26<03:35,  2.73s/it, lr: 5.0e-05 loss: 2.824e-01]
leoprint:  97%|#########6| 2321/2400 [1:21:26<03:35,  2.73s/it, lr: 5.0e-05 loss: 2.824e-01]
leoprint:  97%|#########6| 2321/2400 [1:21:30<03:35,  2.73s/it, lr: 5.0e-05 loss: 3.004e-01]
leoprint:  97%|#########6| 2321/2400 [1:21:30<03:35,  2.73s/it, lr: 5.0e-05 loss: 3.004e-01]
leoprint:  97%|#########6| 2322/2400 [1:21:30<03:47,  2.92s/it, lr: 5.0e-05 loss: 3.004e-01]
leoprint:  97%|#########6| 2322/2400 [1:21:30<03:47,  2.92s/it, lr: 5.0e-05 loss: 3.004e-01]
leoprint:  97%|#########6| 2322/2400 [1:21:33<03:47,  2.92s/it, lr: 5.0e-05 loss: 2.397e-01]
leoprint:  97%|#########6| 2322/2400 [1:21:33<03:47,  2.92s/it, lr: 5.0e-05 loss: 2.397e-01]
leoprint:  97%|#########6| 2323/2400 [1:21:33<03:56,  3.07s/it, lr: 5.0e-05 loss: 2.397e-01]
leoprint:  97%|#########6| 2323/2400 [1:21:33<03:56,  3.07s/it, lr: 5.0e-05 loss: 2.397e-01]
leoprint:  97%|#########6| 2323/2400 [1:21:37<03:56,  3.07s/it, lr: 5.0e-05 loss: 3.519e-01]
leoprint:  97%|#########6| 2323/2400 [1:21:37<03:56,  3.07s/it, lr: 5.0e-05 loss: 3.519e-01]
leoprint:  97%|#########6| 2324/2400 [1:21:37<04:02,  3.19s/it, lr: 5.0e-05 loss: 3.519e-01]
leoprint:  97%|#########6| 2324/2400 [1:21:37<04:02,  3.19s/it, lr: 5.0e-05 loss: 3.519e-01]
leoprint:  97%|#########6| 2324/2400 [1:21:40<04:02,  3.19s/it, lr: 5.0e-05 loss: 3.490e-01]
leoprint:  97%|#########6| 2324/2400 [1:21:40<04:02,  3.19s/it, lr: 5.0e-05 loss: 3.490e-01]
leoprint:  97%|#########6| 2325/2400 [1:21:40<04:05,  3.28s/it, lr: 5.0e-05 loss: 3.490e-01]
leoprint:  97%|#########6| 2325/2400 [1:21:40<04:05,  3.28s/it, lr: 5.0e-05 loss: 3.490e-01]
leoprint:  97%|#########6| 2325/2400 [1:21:44<04:05,  3.28s/it, lr: 5.0e-05 loss: 2.938e-01]
leoprint:  97%|#########6| 2325/2400 [1:21:44<04:05,  3.28s/it, lr: 5.0e-05 loss: 2.938e-01]
leoprint:  97%|#########6| 2326/2400 [1:21:44<04:07,  3.34s/it, lr: 5.0e-05 loss: 2.938e-01]
leoprint:  97%|#########6| 2326/2400 [1:21:44<04:07,  3.34s/it, lr: 5.0e-05 loss: 2.938e-01]
leoprint:  97%|#########6| 2326/2400 [1:21:47<04:07,  3.34s/it, lr: 5.0e-05 loss: 2.262e-01]
leoprint:  97%|#########6| 2326/2400 [1:21:47<04:07,  3.34s/it, lr: 5.0e-05 loss: 2.262e-01]
leoprint:  97%|#########6| 2327/2400 [1:21:47<04:12,  3.46s/it, lr: 5.0e-05 loss: 2.262e-01]
leoprint:  97%|#########6| 2327/2400 [1:21:47<04:12,  3.46s/it, lr: 5.0e-05 loss: 2.262e-01]
leoprint:  97%|#########6| 2327/2400 [1:21:51<04:12,  3.46s/it, lr: 5.0e-05 loss: 2.699e-01]
leoprint:  97%|#########6| 2327/2400 [1:21:51<04:12,  3.46s/it, lr: 5.0e-05 loss: 2.699e-01]
leoprint:  97%|#########7| 2328/2400 [1:21:51<04:10,  3.48s/it, lr: 5.0e-05 loss: 2.699e-01]
leoprint:  97%|#########7| 2328/2400 [1:21:51<04:10,  3.48s/it, lr: 5.0e-05 loss: 2.699e-01]
leoprint:  97%|#########7| 2328/2400 [1:21:54<04:10,  3.48s/it, lr: 5.0e-05 loss: 2.669e-01]
leoprint:  97%|#########7| 2328/2400 [1:21:54<04:10,  3.48s/it, lr: 5.0e-05 loss: 2.669e-01]
leoprint:  97%|#########7| 2329/2400 [1:21:54<04:07,  3.49s/it, lr: 5.0e-05 loss: 2.669e-01]
leoprint:  97%|#########7| 2329/2400 [1:21:54<04:07,  3.49s/it, lr: 5.0e-05 loss: 2.669e-01]
leoprint:  97%|#########7| 2329/2400 [1:21:58<04:07,  3.49s/it, lr: 5.0e-05 loss: 2.443e-01]
leoprint:  97%|#########7| 2329/2400 [1:21:58<04:07,  3.49s/it, lr: 5.0e-05 loss: 2.443e-01]
leoprint:  97%|#########7| 2330/2400 [1:22:02<04:04,  3.49s/it, lr: 5.0e-05 loss: 3.702e-01]
leoprint:  97%|#########7| 2330/2400 [1:22:02<04:04,  3.49s/it, lr: 5.0e-05 loss: 3.702e-01]
leoprint:  97%|#########7| 2331/2400 [1:22:02<03:06,  2.70s/it, lr: 5.0e-05 loss: 3.702e-01]
leoprint:  97%|#########7| 2331/2400 [1:22:02<03:06,  2.70s/it, lr: 5.0e-05 loss: 3.702e-01]
leoprint:  97%|#########7| 2331/2400 [1:22:05<03:06,  2.70s/it, lr: 5.0e-05 loss: 3.330e-01]
leoprint:  97%|#########7| 2331/2400 [1:22:05<03:06,  2.70s/it, lr: 5.0e-05 loss: 3.330e-01]
leoprint:  97%|#########7| 2332/2400 [1:22:05<03:20,  2.94s/it, lr: 5.0e-05 loss: 3.330e-01]
leoprint:  97%|#########7| 2332/2400 [1:22:05<03:20,  2.94s/it, lr: 5.0e-05 loss: 3.330e-01]
leoprint:  97%|#########7| 2332/2400 [1:22:09<03:20,  2.94s/it, lr: 5.0e-05 loss: 2.514e-01]
leoprint:  97%|#########7| 2332/2400 [1:22:09<03:20,  2.94s/it, lr: 5.0e-05 loss: 2.514e-01]
leoprint:  97%|#########7| 2333/2400 [1:22:09<03:26,  3.09s/it, lr: 5.0e-05 loss: 2.514e-01]
leoprint:  97%|#########7| 2333/2400 [1:22:09<03:26,  3.09s/it, lr: 5.0e-05 loss: 2.514e-01]
leoprint:  97%|#########7| 2333/2400 [1:22:12<03:26,  3.09s/it, lr: 5.0e-05 loss: 2.848e-01]
leoprint:  97%|#########7| 2333/2400 [1:22:12<03:26,  3.09s/it, lr: 5.0e-05 loss: 2.848e-01]
leoprint:  97%|#########7| 2334/2400 [1:22:12<03:31,  3.20s/it, lr: 5.0e-05 loss: 2.848e-01]
leoprint:  97%|#########7| 2334/2400 [1:22:12<03:31,  3.20s/it, lr: 5.0e-05 loss: 2.848e-01]
leoprint:  97%|#########7| 2334/2400 [1:22:16<03:31,  3.20s/it, lr: 5.0e-05 loss: 3.919e-01]
leoprint:  97%|#########7| 2334/2400 [1:22:16<03:31,  3.20s/it, lr: 5.0e-05 loss: 3.919e-01]
leoprint:  97%|#########7| 2335/2400 [1:22:16<03:33,  3.29s/it, lr: 5.0e-05 loss: 3.919e-01]
leoprint:  97%|#########7| 2335/2400 [1:22:16<03:33,  3.29s/it, lr: 5.0e-05 loss: 3.919e-01]
leoprint:  97%|#########7| 2335/2400 [1:22:19<03:33,  3.29s/it, lr: 5.0e-05 loss: 2.833e-01]
leoprint:  97%|#########7| 2335/2400 [1:22:19<03:33,  3.29s/it, lr: 5.0e-05 loss: 2.833e-01]
leoprint:  97%|#########7| 2336/2400 [1:22:19<03:36,  3.38s/it, lr: 5.0e-05 loss: 2.833e-01]
leoprint:  97%|#########7| 2336/2400 [1:22:19<03:36,  3.38s/it, lr: 5.0e-05 loss: 2.833e-01]
leoprint:  97%|#########7| 2336/2400 [1:22:23<03:36,  3.38s/it, lr: 5.0e-05 loss: 3.749e-01]
leoprint:  97%|#########7| 2336/2400 [1:22:23<03:36,  3.38s/it, lr: 5.0e-05 loss: 3.749e-01]
leoprint:  97%|#########7| 2337/2400 [1:22:23<03:35,  3.42s/it, lr: 5.0e-05 loss: 3.749e-01]
leoprint:  97%|#########7| 2337/2400 [1:22:23<03:35,  3.42s/it, lr: 5.0e-05 loss: 3.749e-01]
leoprint:  97%|#########7| 2337/2400 [1:22:27<03:35,  3.42s/it, lr: 5.0e-05 loss: 2.239e-01]
leoprint:  97%|#########7| 2337/2400 [1:22:27<03:35,  3.42s/it, lr: 5.0e-05 loss: 2.239e-01]
leoprint:  97%|#########7| 2338/2400 [1:22:27<03:37,  3.50s/it, lr: 5.0e-05 loss: 2.239e-01]
leoprint:  97%|#########7| 2338/2400 [1:22:27<03:37,  3.50s/it, lr: 5.0e-05 loss: 2.239e-01]
leoprint:  97%|#########7| 2338/2400 [1:22:30<03:37,  3.50s/it, lr: 5.0e-05 loss: 3.028e-01]
leoprint:  97%|#########7| 2338/2400 [1:22:30<03:37,  3.50s/it, lr: 5.0e-05 loss: 3.028e-01]
leoprint:  97%|#########7| 2339/2400 [1:22:30<03:33,  3.50s/it, lr: 5.0e-05 loss: 3.028e-01]
leoprint:  97%|#########7| 2339/2400 [1:22:30<03:33,  3.50s/it, lr: 5.0e-05 loss: 3.028e-01]
leoprint:  97%|#########7| 2339/2400 [1:22:34<03:33,  3.50s/it, lr: 5.0e-05 loss: 2.298e-01]
leoprint:  97%|#########7| 2339/2400 [1:22:34<03:33,  3.50s/it, lr: 5.0e-05 loss: 2.298e-01]
leoprint:  98%|#########7| 2340/2400 [1:22:37<03:30,  3.50s/it, lr: 5.0e-05 loss: 1.952e-01]
leoprint:  98%|#########7| 2340/2400 [1:22:37<03:30,  3.50s/it, lr: 5.0e-05 loss: 1.952e-01]
leoprint:  98%|#########7| 2341/2400 [1:22:37<02:41,  2.73s/it, lr: 5.0e-05 loss: 1.952e-01]
leoprint:  98%|#########7| 2341/2400 [1:22:37<02:41,  2.73s/it, lr: 5.0e-05 loss: 1.952e-01]
leoprint:  98%|#########7| 2341/2400 [1:22:41<02:41,  2.73s/it, lr: 5.0e-05 loss: 3.049e-01]
leoprint:  98%|#########7| 2341/2400 [1:22:41<02:41,  2.73s/it, lr: 5.0e-05 loss: 3.049e-01]
leoprint:  98%|#########7| 2342/2400 [1:22:41<02:51,  2.96s/it, lr: 5.0e-05 loss: 3.049e-01]
leoprint:  98%|#########7| 2342/2400 [1:22:41<02:51,  2.96s/it, lr: 5.0e-05 loss: 3.049e-01]
leoprint:  98%|#########7| 2342/2400 [1:22:45<02:51,  2.96s/it, lr: 5.0e-05 loss: 3.150e-01]
leoprint:  98%|#########7| 2342/2400 [1:22:45<02:51,  2.96s/it, lr: 5.0e-05 loss: 3.150e-01]
leoprint:  98%|#########7| 2343/2400 [1:22:45<02:56,  3.10s/it, lr: 5.0e-05 loss: 3.150e-01]
leoprint:  98%|#########7| 2343/2400 [1:22:45<02:56,  3.10s/it, lr: 5.0e-05 loss: 3.150e-01]
leoprint:  98%|#########7| 2343/2400 [1:22:48<02:56,  3.10s/it, lr: 5.0e-05 loss: 2.393e-01]
leoprint:  98%|#########7| 2343/2400 [1:22:48<02:56,  3.10s/it, lr: 5.0e-05 loss: 2.393e-01]
leoprint:  98%|#########7| 2344/2400 [1:22:48<03:04,  3.30s/it, lr: 5.0e-05 loss: 2.393e-01]
leoprint:  98%|#########7| 2344/2400 [1:22:48<03:04,  3.30s/it, lr: 5.0e-05 loss: 2.393e-01]
leoprint:  98%|#########7| 2344/2400 [1:22:52<03:04,  3.30s/it, lr: 5.0e-05 loss: 3.800e-01]
leoprint:  98%|#########7| 2344/2400 [1:22:52<03:04,  3.30s/it, lr: 5.0e-05 loss: 3.800e-01]
leoprint:  98%|#########7| 2345/2400 [1:22:52<03:04,  3.36s/it, lr: 5.0e-05 loss: 3.800e-01]
leoprint:  98%|#########7| 2345/2400 [1:22:52<03:04,  3.36s/it, lr: 5.0e-05 loss: 3.800e-01]
leoprint:  98%|#########7| 2345/2400 [1:22:56<03:04,  3.36s/it, lr: 5.0e-05 loss: 2.567e-01]
leoprint:  98%|#########7| 2345/2400 [1:22:56<03:04,  3.36s/it, lr: 5.0e-05 loss: 2.567e-01]
leoprint:  98%|#########7| 2346/2400 [1:22:56<03:05,  3.43s/it, lr: 5.0e-05 loss: 2.567e-01]
leoprint:  98%|#########7| 2346/2400 [1:22:56<03:05,  3.43s/it, lr: 5.0e-05 loss: 2.567e-01]
leoprint:  98%|#########7| 2346/2400 [1:22:59<03:05,  3.43s/it, lr: 5.0e-05 loss: 2.907e-01]
leoprint:  98%|#########7| 2346/2400 [1:22:59<03:05,  3.43s/it, lr: 5.0e-05 loss: 2.907e-01]
leoprint:  98%|#########7| 2347/2400 [1:22:59<03:03,  3.46s/it, lr: 5.0e-05 loss: 2.907e-01]
leoprint:  98%|#########7| 2347/2400 [1:22:59<03:03,  3.46s/it, lr: 5.0e-05 loss: 2.907e-01]
leoprint:  98%|#########7| 2347/2400 [1:23:03<03:03,  3.46s/it, lr: 5.0e-05 loss: 2.884e-01]
leoprint:  98%|#########7| 2347/2400 [1:23:03<03:03,  3.46s/it, lr: 5.0e-05 loss: 2.884e-01]
leoprint:  98%|#########7| 2348/2400 [1:23:03<03:00,  3.47s/it, lr: 5.0e-05 loss: 2.884e-01]
leoprint:  98%|#########7| 2348/2400 [1:23:03<03:00,  3.47s/it, lr: 5.0e-05 loss: 2.884e-01]
leoprint:  98%|#########7| 2348/2400 [1:23:06<03:00,  3.47s/it, lr: 5.0e-05 loss: 3.126e-01]
leoprint:  98%|#########7| 2348/2400 [1:23:06<03:00,  3.47s/it, lr: 5.0e-05 loss: 3.126e-01]
leoprint:  98%|#########7| 2349/2400 [1:23:06<02:57,  3.48s/it, lr: 5.0e-05 loss: 3.126e-01]
leoprint:  98%|#########7| 2349/2400 [1:23:06<02:57,  3.48s/it, lr: 5.0e-05 loss: 3.126e-01]
leoprint:  98%|#########7| 2349/2400 [1:23:10<02:57,  3.48s/it, lr: 5.0e-05 loss: 2.592e-01]
leoprint:  98%|#########7| 2349/2400 [1:23:10<02:57,  3.48s/it, lr: 5.0e-05 loss: 2.592e-01]
leoprint:  98%|#########7| 2350/2400 [1:23:13<02:54,  3.48s/it, lr: 5.0e-05 loss: 2.345e-01]
leoprint:  98%|#########7| 2350/2400 [1:23:13<02:54,  3.48s/it, lr: 5.0e-05 loss: 2.345e-01]
leoprint:  98%|#########7| 2351/2400 [1:23:13<02:11,  2.69s/it, lr: 5.0e-05 loss: 2.345e-01]
leoprint:  98%|#########7| 2351/2400 [1:23:13<02:11,  2.69s/it, lr: 5.0e-05 loss: 2.345e-01]
leoprint:  98%|#########7| 2351/2400 [1:23:17<02:11,  2.69s/it, lr: 5.0e-05 loss: 3.388e-01]
leoprint:  98%|#########7| 2351/2400 [1:23:17<02:11,  2.69s/it, lr: 5.0e-05 loss: 3.388e-01]
leoprint:  98%|#########8| 2352/2400 [1:23:17<02:18,  2.89s/it, lr: 5.0e-05 loss: 3.388e-01]
leoprint:  98%|#########8| 2352/2400 [1:23:17<02:18,  2.89s/it, lr: 5.0e-05 loss: 3.388e-01]
leoprint:  98%|#########8| 2352/2400 [1:23:20<02:18,  2.89s/it, lr: 5.0e-05 loss: 2.985e-01]
leoprint:  98%|#########8| 2352/2400 [1:23:20<02:18,  2.89s/it, lr: 5.0e-05 loss: 2.985e-01]
leoprint:  98%|#########8| 2353/2400 [1:23:20<02:23,  3.05s/it, lr: 5.0e-05 loss: 2.985e-01]
leoprint:  98%|#########8| 2353/2400 [1:23:20<02:23,  3.05s/it, lr: 5.0e-05 loss: 2.985e-01]
leoprint:  98%|#########8| 2353/2400 [1:23:24<02:23,  3.05s/it, lr: 5.0e-05 loss: 1.767e-01]
leoprint:  98%|#########8| 2353/2400 [1:23:24<02:23,  3.05s/it, lr: 5.0e-05 loss: 1.767e-01]
leoprint:  98%|#########8| 2354/2400 [1:23:24<02:27,  3.21s/it, lr: 5.0e-05 loss: 1.767e-01]
leoprint:  98%|#########8| 2354/2400 [1:23:24<02:27,  3.21s/it, lr: 5.0e-05 loss: 1.767e-01]
leoprint:  98%|#########8| 2354/2400 [1:23:28<02:27,  3.21s/it, lr: 5.0e-05 loss: 3.690e-01]
leoprint:  98%|#########8| 2354/2400 [1:23:28<02:27,  3.21s/it, lr: 5.0e-05 loss: 3.690e-01]
leoprint:  98%|#########8| 2355/2400 [1:23:28<02:30,  3.34s/it, lr: 5.0e-05 loss: 3.690e-01]
leoprint:  98%|#########8| 2355/2400 [1:23:28<02:30,  3.34s/it, lr: 5.0e-05 loss: 3.690e-01]
leoprint:  98%|#########8| 2355/2400 [1:23:31<02:30,  3.34s/it, lr: 5.0e-05 loss: 2.724e-01]
leoprint:  98%|#########8| 2355/2400 [1:23:31<02:30,  3.34s/it, lr: 5.0e-05 loss: 2.724e-01]
leoprint:  98%|#########8| 2356/2400 [1:23:31<02:29,  3.39s/it, lr: 5.0e-05 loss: 2.724e-01]
leoprint:  98%|#########8| 2356/2400 [1:23:31<02:29,  3.39s/it, lr: 5.0e-05 loss: 2.724e-01]
leoprint:  98%|#########8| 2356/2400 [1:23:35<02:29,  3.39s/it, lr: 5.0e-05 loss: 2.557e-01]
leoprint:  98%|#########8| 2356/2400 [1:23:35<02:29,  3.39s/it, lr: 5.0e-05 loss: 2.557e-01]
leoprint:  98%|#########8| 2357/2400 [1:23:35<02:28,  3.46s/it, lr: 5.0e-05 loss: 2.557e-01]
leoprint:  98%|#########8| 2357/2400 [1:23:35<02:28,  3.46s/it, lr: 5.0e-05 loss: 2.557e-01]
leoprint:  98%|#########8| 2357/2400 [1:23:38<02:28,  3.46s/it, lr: 5.0e-05 loss: 3.964e-01]
leoprint:  98%|#########8| 2357/2400 [1:23:38<02:28,  3.46s/it, lr: 5.0e-05 loss: 3.964e-01]
leoprint:  98%|#########8| 2358/2400 [1:23:38<02:25,  3.47s/it, lr: 5.0e-05 loss: 3.964e-01]
leoprint:  98%|#########8| 2358/2400 [1:23:38<02:25,  3.47s/it, lr: 5.0e-05 loss: 3.964e-01]
leoprint:  98%|#########8| 2358/2400 [1:23:42<02:25,  3.47s/it, lr: 5.0e-05 loss: 3.561e-01]
leoprint:  98%|#########8| 2358/2400 [1:23:42<02:25,  3.47s/it, lr: 5.0e-05 loss: 3.561e-01]
leoprint:  98%|#########8| 2359/2400 [1:23:42<02:22,  3.48s/it, lr: 5.0e-05 loss: 3.561e-01]
leoprint:  98%|#########8| 2359/2400 [1:23:42<02:22,  3.48s/it, lr: 5.0e-05 loss: 3.561e-01]
leoprint:  98%|#########8| 2359/2400 [1:23:45<02:22,  3.48s/it, lr: 5.0e-05 loss: 2.639e-01]
leoprint:  98%|#########8| 2359/2400 [1:23:45<02:22,  3.48s/it, lr: 5.0e-05 loss: 2.639e-01]
leoprint:  98%|#########8| 2360/2400 [1:23:49<02:19,  3.48s/it, lr: 5.0e-05 loss: 3.326e-01]
leoprint:  98%|#########8| 2360/2400 [1:23:49<02:19,  3.48s/it, lr: 5.0e-05 loss: 3.326e-01]
leoprint:  98%|#########8| 2361/2400 [1:23:49<01:45,  2.71s/it, lr: 5.0e-05 loss: 3.326e-01]
leoprint:  98%|#########8| 2361/2400 [1:23:49<01:45,  2.71s/it, lr: 5.0e-05 loss: 3.326e-01]
leoprint:  98%|#########8| 2361/2400 [1:23:52<01:45,  2.71s/it, lr: 5.0e-05 loss: 2.914e-01]
leoprint:  98%|#########8| 2361/2400 [1:23:52<01:45,  2.71s/it, lr: 5.0e-05 loss: 2.914e-01]
leoprint:  98%|#########8| 2362/2400 [1:23:53<01:50,  2.91s/it, lr: 5.0e-05 loss: 2.914e-01]
leoprint:  98%|#########8| 2362/2400 [1:23:53<01:50,  2.91s/it, lr: 5.0e-05 loss: 2.914e-01]
leoprint:  98%|#########8| 2362/2400 [1:23:56<01:50,  2.91s/it, lr: 5.0e-05 loss: 3.132e-01]
leoprint:  98%|#########8| 2362/2400 [1:23:56<01:50,  2.91s/it, lr: 5.0e-05 loss: 3.132e-01]
leoprint:  98%|#########8| 2363/2400 [1:23:56<01:53,  3.06s/it, lr: 5.0e-05 loss: 3.132e-01]
leoprint:  98%|#########8| 2363/2400 [1:23:56<01:53,  3.06s/it, lr: 5.0e-05 loss: 3.132e-01]
leoprint:  98%|#########8| 2363/2400 [1:24:00<01:53,  3.06s/it, lr: 5.0e-05 loss: 2.773e-01]
leoprint:  98%|#########8| 2363/2400 [1:24:00<01:53,  3.06s/it, lr: 5.0e-05 loss: 2.773e-01]
leoprint:  98%|#########8| 2364/2400 [1:24:00<01:54,  3.19s/it, lr: 5.0e-05 loss: 2.773e-01]
leoprint:  98%|#########8| 2364/2400 [1:24:00<01:54,  3.19s/it, lr: 5.0e-05 loss: 2.773e-01]
leoprint:  98%|#########8| 2364/2400 [1:24:03<01:54,  3.19s/it, lr: 5.0e-05 loss: 2.820e-01]
leoprint:  98%|#########8| 2364/2400 [1:24:03<01:54,  3.19s/it, lr: 5.0e-05 loss: 2.820e-01]
leoprint:  99%|#########8| 2365/2400 [1:24:03<01:54,  3.27s/it, lr: 5.0e-05 loss: 2.820e-01]
leoprint:  99%|#########8| 2365/2400 [1:24:03<01:54,  3.27s/it, lr: 5.0e-05 loss: 2.820e-01]
leoprint:  99%|#########8| 2365/2400 [1:24:07<01:54,  3.27s/it, lr: 5.0e-05 loss: 2.816e-01]
leoprint:  99%|#########8| 2365/2400 [1:24:07<01:54,  3.27s/it, lr: 5.0e-05 loss: 2.816e-01]
leoprint:  99%|#########8| 2366/2400 [1:24:07<01:54,  3.38s/it, lr: 5.0e-05 loss: 2.816e-01]
leoprint:  99%|#########8| 2366/2400 [1:24:07<01:54,  3.38s/it, lr: 5.0e-05 loss: 2.816e-01]
leoprint:  99%|#########8| 2366/2400 [1:24:11<01:54,  3.38s/it, lr: 5.0e-05 loss: 1.900e-01]
leoprint:  99%|#########8| 2366/2400 [1:24:11<01:54,  3.38s/it, lr: 5.0e-05 loss: 1.900e-01]
leoprint:  99%|#########8| 2367/2400 [1:24:11<01:55,  3.51s/it, lr: 5.0e-05 loss: 1.900e-01]
leoprint:  99%|#########8| 2367/2400 [1:24:11<01:55,  3.51s/it, lr: 5.0e-05 loss: 1.900e-01]
leoprint:  99%|#########8| 2367/2400 [1:24:14<01:55,  3.51s/it, lr: 5.0e-05 loss: 3.388e-01]
leoprint:  99%|#########8| 2367/2400 [1:24:14<01:55,  3.51s/it, lr: 5.0e-05 loss: 3.388e-01]
leoprint:  99%|#########8| 2368/2400 [1:24:14<01:52,  3.51s/it, lr: 5.0e-05 loss: 3.388e-01]
leoprint:  99%|#########8| 2368/2400 [1:24:14<01:52,  3.51s/it, lr: 5.0e-05 loss: 3.388e-01]
leoprint:  99%|#########8| 2368/2400 [1:24:18<01:52,  3.51s/it, lr: 5.0e-05 loss: 2.448e-01]
leoprint:  99%|#########8| 2368/2400 [1:24:18<01:52,  3.51s/it, lr: 5.0e-05 loss: 2.448e-01]
leoprint:  99%|#########8| 2369/2400 [1:24:18<01:49,  3.55s/it, lr: 5.0e-05 loss: 2.448e-01]
leoprint:  99%|#########8| 2369/2400 [1:24:18<01:49,  3.55s/it, lr: 5.0e-05 loss: 2.448e-01]
leoprint:  99%|#########8| 2369/2400 [1:24:21<01:49,  3.55s/it, lr: 5.0e-05 loss: 2.974e-01]
leoprint:  99%|#########8| 2369/2400 [1:24:21<01:49,  3.55s/it, lr: 5.0e-05 loss: 2.974e-01]
leoprint:  99%|#########8| 2370/2400 [1:24:25<01:46,  3.55s/it, lr: 5.0e-05 loss: 3.881e-01]
leoprint:  99%|#########8| 2370/2400 [1:24:25<01:46,  3.55s/it, lr: 5.0e-05 loss: 3.881e-01]
leoprint:  99%|#########8| 2371/2400 [1:24:25<01:19,  2.73s/it, lr: 5.0e-05 loss: 3.881e-01]
leoprint:  99%|#########8| 2371/2400 [1:24:25<01:19,  2.73s/it, lr: 5.0e-05 loss: 3.881e-01]
leoprint:  99%|#########8| 2371/2400 [1:24:28<01:19,  2.73s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  99%|#########8| 2371/2400 [1:24:28<01:19,  2.73s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  99%|#########8| 2372/2400 [1:24:28<01:21,  2.92s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  99%|#########8| 2372/2400 [1:24:28<01:21,  2.92s/it, lr: 5.0e-05 loss: 2.433e-01]
leoprint:  99%|#########8| 2372/2400 [1:24:32<01:21,  2.92s/it, lr: 5.0e-05 loss: 3.239e-01]
leoprint:  99%|#########8| 2372/2400 [1:24:32<01:21,  2.92s/it, lr: 5.0e-05 loss: 3.239e-01]
leoprint:  99%|#########8| 2373/2400 [1:24:32<01:23,  3.11s/it, lr: 5.0e-05 loss: 3.239e-01]
leoprint:  99%|#########8| 2373/2400 [1:24:32<01:23,  3.11s/it, lr: 5.0e-05 loss: 3.239e-01]
leoprint:  99%|#########8| 2373/2400 [1:24:35<01:23,  3.11s/it, lr: 5.0e-05 loss: 2.819e-01]
leoprint:  99%|#########8| 2373/2400 [1:24:35<01:23,  3.11s/it, lr: 5.0e-05 loss: 2.819e-01]
leoprint:  99%|#########8| 2374/2400 [1:24:35<01:23,  3.22s/it, lr: 5.0e-05 loss: 2.819e-01]
leoprint:  99%|#########8| 2374/2400 [1:24:35<01:23,  3.22s/it, lr: 5.0e-05 loss: 2.819e-01]
leoprint:  99%|#########8| 2374/2400 [1:24:39<01:23,  3.22s/it, lr: 5.0e-05 loss: 2.484e-01]
leoprint:  99%|#########8| 2374/2400 [1:24:39<01:23,  3.22s/it, lr: 5.0e-05 loss: 2.484e-01]
leoprint:  99%|#########8| 2375/2400 [1:24:39<01:22,  3.30s/it, lr: 5.0e-05 loss: 2.484e-01]
leoprint:  99%|#########8| 2375/2400 [1:24:39<01:22,  3.30s/it, lr: 5.0e-05 loss: 2.484e-01]
leoprint:  99%|#########8| 2375/2400 [1:24:43<01:22,  3.30s/it, lr: 5.0e-05 loss: 2.759e-01]
leoprint:  99%|#########8| 2375/2400 [1:24:43<01:22,  3.30s/it, lr: 5.0e-05 loss: 2.759e-01]
leoprint:  99%|#########9| 2376/2400 [1:24:43<01:21,  3.40s/it, lr: 5.0e-05 loss: 2.759e-01]
leoprint:  99%|#########9| 2376/2400 [1:24:43<01:21,  3.40s/it, lr: 5.0e-05 loss: 2.759e-01]
leoprint:  99%|#########9| 2376/2400 [1:24:46<01:21,  3.40s/it, lr: 5.0e-05 loss: 2.868e-01]
leoprint:  99%|#########9| 2376/2400 [1:24:46<01:21,  3.40s/it, lr: 5.0e-05 loss: 2.868e-01]
leoprint:  99%|#########9| 2377/2400 [1:24:46<01:18,  3.43s/it, lr: 5.0e-05 loss: 2.868e-01]
leoprint:  99%|#########9| 2377/2400 [1:24:46<01:18,  3.43s/it, lr: 5.0e-05 loss: 2.868e-01]
leoprint:  99%|#########9| 2377/2400 [1:24:50<01:18,  3.43s/it, lr: 5.0e-05 loss: 2.892e-01]
leoprint:  99%|#########9| 2377/2400 [1:24:50<01:18,  3.43s/it, lr: 5.0e-05 loss: 2.892e-01]
leoprint:  99%|#########9| 2378/2400 [1:24:50<01:17,  3.51s/it, lr: 5.0e-05 loss: 2.892e-01]
leoprint:  99%|#########9| 2378/2400 [1:24:50<01:17,  3.51s/it, lr: 5.0e-05 loss: 2.892e-01]
leoprint:  99%|#########9| 2378/2400 [1:24:53<01:17,  3.51s/it, lr: 5.0e-05 loss: 2.906e-01]
leoprint:  99%|#########9| 2378/2400 [1:24:53<01:17,  3.51s/it, lr: 5.0e-05 loss: 2.906e-01]
leoprint:  99%|#########9| 2379/2400 [1:24:53<01:13,  3.51s/it, lr: 5.0e-05 loss: 2.906e-01]
leoprint:  99%|#########9| 2379/2400 [1:24:53<01:13,  3.51s/it, lr: 5.0e-05 loss: 2.906e-01]
leoprint:  99%|#########9| 2379/2400 [1:24:57<01:13,  3.51s/it, lr: 5.0e-05 loss: 2.385e-01]
leoprint:  99%|#########9| 2379/2400 [1:24:57<01:13,  3.51s/it, lr: 5.0e-05 loss: 2.385e-01]
leoprint:  99%|#########9| 2380/2400 [1:25:00<01:10,  3.51s/it, lr: 5.0e-05 loss: 2.399e-01]
leoprint:  99%|#########9| 2380/2400 [1:25:00<01:10,  3.51s/it, lr: 5.0e-05 loss: 2.399e-01]
leoprint:  99%|#########9| 2381/2400 [1:25:00<00:51,  2.71s/it, lr: 5.0e-05 loss: 2.399e-01]
leoprint:  99%|#########9| 2381/2400 [1:25:00<00:51,  2.71s/it, lr: 5.0e-05 loss: 2.399e-01]
leoprint:  99%|#########9| 2381/2400 [1:25:04<00:51,  2.71s/it, lr: 5.0e-05 loss: 2.402e-01]
leoprint:  99%|#########9| 2381/2400 [1:25:04<00:51,  2.71s/it, lr: 5.0e-05 loss: 2.402e-01]
leoprint:  99%|#########9| 2382/2400 [1:25:04<00:52,  2.90s/it, lr: 5.0e-05 loss: 2.402e-01]
leoprint:  99%|#########9| 2382/2400 [1:25:04<00:52,  2.90s/it, lr: 5.0e-05 loss: 2.402e-01]
leoprint:  99%|#########9| 2382/2400 [1:25:08<00:52,  2.90s/it, lr: 5.0e-05 loss: 2.705e-01]
leoprint:  99%|#########9| 2382/2400 [1:25:08<00:52,  2.90s/it, lr: 5.0e-05 loss: 2.705e-01]
leoprint:  99%|#########9| 2383/2400 [1:25:08<00:52,  3.06s/it, lr: 5.0e-05 loss: 2.705e-01]
leoprint:  99%|#########9| 2383/2400 [1:25:08<00:52,  3.06s/it, lr: 5.0e-05 loss: 2.705e-01]
leoprint:  99%|#########9| 2383/2400 [1:25:11<00:52,  3.06s/it, lr: 5.0e-05 loss: 2.839e-01]
leoprint:  99%|#########9| 2383/2400 [1:25:11<00:52,  3.06s/it, lr: 5.0e-05 loss: 2.839e-01]
leoprint:  99%|#########9| 2384/2400 [1:25:11<00:51,  3.21s/it, lr: 5.0e-05 loss: 2.839e-01]
leoprint:  99%|#########9| 2384/2400 [1:25:11<00:51,  3.21s/it, lr: 5.0e-05 loss: 2.839e-01]
leoprint:  99%|#########9| 2384/2400 [1:25:15<00:51,  3.21s/it, lr: 5.0e-05 loss: 2.397e-01]
leoprint:  99%|#########9| 2384/2400 [1:25:15<00:51,  3.21s/it, lr: 5.0e-05 loss: 2.397e-01]
leoprint:  99%|#########9| 2385/2400 [1:25:15<00:49,  3.33s/it, lr: 5.0e-05 loss: 2.397e-01]
leoprint:  99%|#########9| 2385/2400 [1:25:15<00:49,  3.33s/it, lr: 5.0e-05 loss: 2.397e-01]
leoprint:  99%|#########9| 2385/2400 [1:25:18<00:49,  3.33s/it, lr: 5.0e-05 loss: 3.871e-01]
leoprint:  99%|#########9| 2385/2400 [1:25:18<00:49,  3.33s/it, lr: 5.0e-05 loss: 3.871e-01]
leoprint:  99%|#########9| 2386/2400 [1:25:18<00:47,  3.38s/it, lr: 5.0e-05 loss: 3.871e-01]
leoprint:  99%|#########9| 2386/2400 [1:25:18<00:47,  3.38s/it, lr: 5.0e-05 loss: 3.871e-01]
leoprint:  99%|#########9| 2386/2400 [1:25:22<00:47,  3.38s/it, lr: 5.0e-05 loss: 3.161e-01]
leoprint:  99%|#########9| 2386/2400 [1:25:22<00:47,  3.38s/it, lr: 5.0e-05 loss: 3.161e-01]
leoprint:  99%|#########9| 2387/2400 [1:25:22<00:44,  3.42s/it, lr: 5.0e-05 loss: 3.161e-01]
leoprint:  99%|#########9| 2387/2400 [1:25:22<00:44,  3.42s/it, lr: 5.0e-05 loss: 3.161e-01]
leoprint:  99%|#########9| 2387/2400 [1:25:25<00:44,  3.42s/it, lr: 5.0e-05 loss: 2.763e-01]
leoprint:  99%|#########9| 2387/2400 [1:25:25<00:44,  3.42s/it, lr: 5.0e-05 loss: 2.763e-01]
leoprint: 100%|#########9| 2388/2400 [1:25:25<00:41,  3.45s/it, lr: 5.0e-05 loss: 2.763e-01]
leoprint: 100%|#########9| 2388/2400 [1:25:25<00:41,  3.45s/it, lr: 5.0e-05 loss: 2.763e-01]
leoprint: 100%|#########9| 2388/2400 [1:25:29<00:41,  3.45s/it, lr: 5.0e-05 loss: 2.633e-01]
leoprint: 100%|#########9| 2388/2400 [1:25:29<00:41,  3.45s/it, lr: 5.0e-05 loss: 2.633e-01]
leoprint: 100%|#########9| 2389/2400 [1:25:29<00:38,  3.50s/it, lr: 5.0e-05 loss: 2.633e-01]
leoprint: 100%|#########9| 2389/2400 [1:25:29<00:38,  3.50s/it, lr: 5.0e-05 loss: 2.633e-01]
leoprint: 100%|#########9| 2389/2400 [1:25:33<00:38,  3.50s/it, lr: 5.0e-05 loss: 2.882e-01]
leoprint: 100%|#########9| 2389/2400 [1:25:33<00:38,  3.50s/it, lr: 5.0e-05 loss: 2.882e-01]
leoprint: 100%|#########9| 2390/2400 [1:25:36<00:35,  3.50s/it, lr: 5.0e-05 loss: 3.665e-01]
leoprint: 100%|#########9| 2390/2400 [1:25:36<00:35,  3.50s/it, lr: 5.0e-05 loss: 3.665e-01]
leoprint: 100%|#########9| 2391/2400 [1:25:36<00:24,  2.70s/it, lr: 5.0e-05 loss: 3.665e-01]
leoprint: 100%|#########9| 2391/2400 [1:25:36<00:24,  2.70s/it, lr: 5.0e-05 loss: 3.665e-01]
leoprint: 100%|#########9| 2391/2400 [1:25:40<00:24,  2.70s/it, lr: 5.0e-05 loss: 2.355e-01]
leoprint: 100%|#########9| 2391/2400 [1:25:40<00:24,  2.70s/it, lr: 5.0e-05 loss: 2.355e-01]
leoprint: 100%|#########9| 2392/2400 [1:25:40<00:23,  2.90s/it, lr: 5.0e-05 loss: 2.355e-01]
leoprint: 100%|#########9| 2392/2400 [1:25:40<00:23,  2.90s/it, lr: 5.0e-05 loss: 2.355e-01]
leoprint: 100%|#########9| 2392/2400 [1:25:43<00:23,  2.90s/it, lr: 5.0e-05 loss: 2.391e-01]
leoprint: 100%|#########9| 2392/2400 [1:25:43<00:23,  2.90s/it, lr: 5.0e-05 loss: 2.391e-01]
leoprint: 100%|#########9| 2393/2400 [1:25:43<00:21,  3.09s/it, lr: 5.0e-05 loss: 2.391e-01]
leoprint: 100%|#########9| 2393/2400 [1:25:43<00:21,  3.09s/it, lr: 5.0e-05 loss: 2.391e-01]
leoprint: 100%|#########9| 2393/2400 [1:25:47<00:21,  3.09s/it, lr: 5.0e-05 loss: 2.358e-01]
leoprint: 100%|#########9| 2393/2400 [1:25:47<00:21,  3.09s/it, lr: 5.0e-05 loss: 2.358e-01]
leoprint: 100%|#########9| 2394/2400 [1:25:47<00:19,  3.24s/it, lr: 5.0e-05 loss: 2.358e-01]
leoprint: 100%|#########9| 2394/2400 [1:25:47<00:19,  3.24s/it, lr: 5.0e-05 loss: 2.358e-01]
leoprint: 100%|#########9| 2394/2400 [1:25:50<00:19,  3.24s/it, lr: 5.0e-05 loss: 3.820e-01]
leoprint: 100%|#########9| 2394/2400 [1:25:50<00:19,  3.24s/it, lr: 5.0e-05 loss: 3.820e-01]
leoprint: 100%|#########9| 2395/2400 [1:25:50<00:16,  3.31s/it, lr: 5.0e-05 loss: 3.820e-01]
leoprint: 100%|#########9| 2395/2400 [1:25:50<00:16,  3.31s/it, lr: 5.0e-05 loss: 3.820e-01]
leoprint: 100%|#########9| 2395/2400 [1:25:54<00:16,  3.31s/it, lr: 5.0e-05 loss: 3.230e-01]
leoprint: 100%|#########9| 2395/2400 [1:25:54<00:16,  3.31s/it, lr: 5.0e-05 loss: 3.230e-01]
leoprint: 100%|#########9| 2396/2400 [1:25:54<00:13,  3.41s/it, lr: 5.0e-05 loss: 3.230e-01]
leoprint: 100%|#########9| 2396/2400 [1:25:54<00:13,  3.41s/it, lr: 5.0e-05 loss: 3.230e-01]
leoprint: 100%|#########9| 2396/2400 [1:25:58<00:13,  3.41s/it, lr: 5.0e-05 loss: 2.522e-01]
leoprint: 100%|#########9| 2396/2400 [1:25:58<00:13,  3.41s/it, lr: 5.0e-05 loss: 2.522e-01]
leoprint: 100%|#########9| 2397/2400 [1:25:58<00:10,  3.47s/it, lr: 5.0e-05 loss: 2.522e-01]
leoprint: 100%|#########9| 2397/2400 [1:25:58<00:10,  3.47s/it, lr: 5.0e-05 loss: 2.522e-01]
leoprint: 100%|#########9| 2397/2400 [1:26:01<00:10,  3.47s/it, lr: 5.0e-05 loss: 3.294e-01]
leoprint: 100%|#########9| 2397/2400 [1:26:01<00:10,  3.47s/it, lr: 5.0e-05 loss: 3.294e-01]
leoprint: 100%|#########9| 2398/2400 [1:26:01<00:06,  3.49s/it, lr: 5.0e-05 loss: 3.294e-01]
leoprint: 100%|#########9| 2398/2400 [1:26:01<00:06,  3.49s/it, lr: 5.0e-05 loss: 3.294e-01]
leoprint: 100%|#########9| 2398/2400 [1:26:05<00:06,  3.49s/it, lr: 5.0e-05 loss: 3.369e-01]
leoprint: 100%|#########9| 2398/2400 [1:26:05<00:06,  3.49s/it, lr: 5.0e-05 loss: 3.369e-01]
leoprint: 100%|#########9| 2399/2400 [1:26:05<00:03,  3.49s/it, lr: 5.0e-05 loss: 3.369e-01]
leoprint: 100%|#########9| 2399/2400 [1:26:05<00:03,  3.49s/it, lr: 5.0e-05 loss: 3.369e-01]
leoprint: 100%|#########9| 2399/2400 [1:26:05<00:03,  3.69s/it, lr: 5.0e-05 loss: 3.369e-01]
leoprint: 100%|#########9| 2399/2400 [1:26:05<00:03,  3.69s/it, lr: 5.0e-05 loss: 3.369e-01]
+
+
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
Generating Images:  20%|##        | 1/5 [00:14<00:57, 14.43s/it]
Generating Images:  20%|##        | 1/5 [00:14<00:57, 14.43s/it]
Generating Images:  40%|####      | 2/5 [00:28<00:43, 14.43s/it]
Generating Images:  40%|####      | 2/5 [00:28<00:43, 14.43s/it]
Generating Images:  60%|######    | 3/5 [00:43<00:28, 14.43s/it]
Generating Images:  60%|######    | 3/5 [00:43<00:28, 14.43s/it]
Generating Images:  80%|########  | 4/5 [00:57<00:14, 14.43s/it]
Generating Images:  80%|########  | 4/5 [00:57<00:14, 14.43s/it]
Generating Images: 100%|##########| 5/5 [01:12<00:00, 14.43s/it]
Generating Images: 100%|##########| 5/5 [01:12<00:00, 14.43s/it]
                                                                
                                                                

+Saved checkpoint to /app/ai-toolkit/output/leoprint/leoprint.safetensors
+Saved optimizer to /app/ai-toolkit/output/leoprint/optimizer.pt