diff --git "a/log.txt" "b/log.txt"
new file mode 100644--- /dev/null
+++ "b/log.txt"
@@ -0,0 +1,814 @@
+The following values were not passed to `accelerate launch` and had defaults used instead:
+	`--num_processes` was set to a value of `1`
+	`--num_machines` was set to a value of `1`
+	`--mixed_precision` was set to a value of `'no'`
+	`--dynamo_backend` was set to a value of `'no'`
+To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.
+/workspace/thumbs_up/train_dreambooth_lora_sdxl.py:122: DeprecationWarning: BILINEAR is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BILINEAR instead.
+  def resize_image(image, size, interpolation=Image.BILINEAR):
+10/13/2023 10:53:26 - INFO - __main__ - Current working directory: /workspace/thumbs_up
+10/13/2023 10:53:26 - INFO - __main__ - Distributed environment: NO
+Num processes: 1
+Process index: 0
+Local process index: 0
+Device: cuda
+
+Mixed precision type: fp16
+
+You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
+You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
+{'dynamic_thresholding_ratio', 'clip_sample_range', 'variance_type', 'thresholding'} was not found in config. Values will be initialized to default values.
+{'dropout', 'attention_type'} was not found in config. Values will be initialized to default values.
+`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["id2label"]` will be overriden.
+`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["bos_token_id"]` will be overriden.
+`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["eos_token_id"]` will be overriden.
+`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["id2label"]` will be overriden.
+`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["bos_token_id"]` will be overriden.
+`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["eos_token_id"]` will be overriden.
+Some weights of ViTModel were not initialized from the model checkpoint at facebook/dino-vits16 and are newly initialized: ['pooler.dense.bias', 'pooler.dense.weight']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+wandb: Currently logged in as: berglund. Use `wandb login --relogin` to force relogin
+wandb: Tracking run with wandb version 0.15.12
+wandb: Run data is saved locally in /workspace/thumbs_up/wandb/run-20231013_105346-9l8ww0bd
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run dandy-wildflower-54
+wandb: ⭐️ View project at https://wandb.ai/berglund/dreambooth-lora-sd-xl
+wandb: 🚀 View run at https://wandb.ai/berglund/dreambooth-lora-sd-xl/runs/9l8ww0bd
+10/13/2023 10:53:47 - INFO - __main__ - ***** Running training *****
+10/13/2023 10:53:47 - INFO - __main__ -   Num examples = 21
+10/13/2023 10:53:47 - INFO - __main__ -   Num batches each epoch = 11
+10/13/2023 10:53:47 - INFO - __main__ -   Num Epochs = 55
+10/13/2023 10:53:47 - INFO - __main__ -   Instantaneous batch size per device = 2
+10/13/2023 10:53:47 - INFO - __main__ -   Total train batch size (w. parallel, distributed & accumulation) = 2
+10/13/2023 10:53:47 - INFO - __main__ -   Gradient Accumulation steps = 1
+10/13/2023 10:53:47 - INFO - __main__ -   Total optimization steps = 600
+
Steps:   0%|          | 0/600 [00:00<?, ?it/s]/usr/local/lib/python3.10/dist-packages/diffusers/models/attention_processor.py:1567: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`
+  deprecate(
+
Steps:   0%|          | 1/600 [00:02<24:57,  2.50s/it]
Steps:   0%|          | 1/600 [00:02<24:57,  2.50s/it, loss=0.0509, lr=1e-7]
Steps:   0%|          | 2/600 [00:04<20:25,  2.05s/it, loss=0.0509, lr=1e-7]
Steps:   0%|          | 2/600 [00:04<20:25,  2.05s/it, loss=0.0944, lr=1e-7]
Steps:   0%|          | 3/600 [00:06<20:11,  2.03s/it, loss=0.0944, lr=1e-7]
Steps:   0%|          | 3/600 [00:06<20:11,  2.03s/it, loss=0.235, lr=1e-7] 
Steps:   1%|          | 4/600 [00:07<18:53,  1.90s/it, loss=0.235, lr=1e-7]
Steps:   1%|          | 4/600 [00:07<18:53,  1.90s/it, loss=0.0463, lr=1e-7]
Steps:   1%|          | 5/600 [00:09<17:53,  1.80s/it, loss=0.0463, lr=1e-7]
Steps:   1%|          | 5/600 [00:09<17:53,  1.80s/it, loss=0.061, lr=1e-7] 
Steps:   1%|          | 6/600 [00:11<17:42,  1.79s/it, loss=0.061, lr=1e-7]
Steps:   1%|          | 6/600 [00:11<17:42,  1.79s/it, loss=0.00999, lr=1e-7]
Steps:   1%|          | 7/600 [00:12<16:37,  1.68s/it, loss=0.00999, lr=1e-7]
Steps:   1%|          | 7/600 [00:12<16:37,  1.68s/it, loss=0.132, lr=1e-7]  
Steps:   1%|▏         | 8/600 [00:14<15:53,  1.61s/it, loss=0.132, lr=1e-7]
Steps:   1%|▏         | 8/600 [00:14<15:53,  1.61s/it, loss=0.134, lr=1e-7]
Steps:   2%|▏         | 9/600 [00:16<16:28,  1.67s/it, loss=0.134, lr=1e-7]
Steps:   2%|▏         | 9/600 [00:16<16:28,  1.67s/it, loss=0.0906, lr=1e-7]
Steps:   2%|▏         | 10/600 [00:17<15:27,  1.57s/it, loss=0.0906, lr=1e-7]
Steps:   2%|▏         | 10/600 [00:17<15:27,  1.57s/it, loss=0.0586, lr=1e-7]
Steps:   2%|▏         | 11/600 [00:18<13:21,  1.36s/it, loss=0.0586, lr=1e-7]
Steps:   2%|▏         | 11/600 [00:18<13:21,  1.36s/it, loss=0.291, lr=1e-7] 10/13/2023 10:54:05 - INFO - __main__ - Running validation... 
+ Generating 4 images with prompts: "a photo of Brad Pitt in a suit and sunglasses showing <thumbs_up> thumbs up", "a photo of Barack Obama wearing a vest showing <thumbs_up> thumbs up", "a photo of a black man at the beach showing <thumbs_up> thumbs up".
+
+
Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]Loaded scheduler as EulerDiscreteScheduler from `scheduler` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
+Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
+Loaded tokenizer_2 as CLIPTokenizer from `tokenizer_2` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
+
Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 73.34it/s]
+{'dynamic_thresholding_ratio', 'algorithm_type', 'variance_type', 'lambda_min_clipped', 'solver_order', 'solver_type', 'lower_order_final', 'thresholding'} was not found in config. Values will be initialized to default values.
+10/13/2023 10:55:02 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
+10/13/2023 10:55:51 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
+10/13/2023 10:56:40 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
+
Steps:   2%|▏         | 12/600 [03:02<8:19:09, 50.93s/it, loss=0.291, lr=1e-7]
Steps:   2%|▏         | 12/600 [03:02<8:19:09, 50.93s/it, loss=0.143, lr=1e-7]
Steps:   2%|▏         | 13/600 [03:04<5:53:01, 36.08s/it, loss=0.143, lr=1e-7]
Steps:   2%|▏         | 13/600 [03:04<5:53:01, 36.08s/it, loss=0.104, lr=1e-7]
Steps:   2%|▏         | 14/600 [03:05<4:10:19, 25.63s/it, loss=0.104, lr=1e-7]
Steps:   2%|▏         | 14/600 [03:05<4:10:19, 25.63s/it, loss=0.185, lr=1e-7]
Steps:   2%|▎         | 15/600 [03:07<2:58:48, 18.34s/it, loss=0.185, lr=1e-7]
Steps:   2%|▎         | 15/600 [03:07<2:58:48, 18.34s/it, loss=0.137, lr=1e-7]
Steps:   3%|▎         | 16/600 [03:08<2:09:11, 13.27s/it, loss=0.137, lr=1e-7]
Steps:   3%|▎         | 16/600 [03:08<2:09:11, 13.27s/it, loss=0.0199, lr=1e-7]
Steps:   3%|▎         | 17/600 [03:10<1:35:20,  9.81s/it, loss=0.0199, lr=1e-7]
Steps:   3%|▎         | 17/600 [03:10<1:35:20,  9.81s/it, loss=0.15, lr=1e-7]  
Steps:   3%|▎         | 18/600 [03:12<1:11:46,  7.40s/it, loss=0.15, lr=1e-7]
Steps:   3%|▎         | 18/600 [03:12<1:11:46,  7.40s/it, loss=0.113, lr=1e-7]
Steps:   3%|▎         | 19/600 [03:14<54:31,  5.63s/it, loss=0.113, lr=1e-7]  
Steps:   3%|▎         | 19/600 [03:14<54:31,  5.63s/it, loss=0.184, lr=1e-7]
Steps:   3%|▎         | 20/600 [03:15<42:43,  4.42s/it, loss=0.184, lr=1e-7]
Steps:   3%|▎         | 20/600 [03:15<42:43,  4.42s/it, loss=0.144, lr=1e-7]
Steps:   4%|▎         | 21/600 [03:16<33:39,  3.49s/it, loss=0.144, lr=1e-7]
Steps:   4%|▎         | 21/600 [03:16<33:39,  3.49s/it, loss=0.103, lr=1e-7]
Steps:   4%|▎         | 22/600 [03:17<25:40,  2.66s/it, loss=0.103, lr=1e-7]
Steps:   4%|▎         | 22/600 [03:17<25:40,  2.66s/it, loss=0.319, lr=1e-7]
Steps:   4%|▍         | 23/600 [03:19<24:05,  2.51s/it, loss=0.319, lr=1e-7]
Steps:   4%|▍         | 23/600 [03:19<24:05,  2.51s/it, loss=0.0736, lr=1e-7]
Steps:   4%|▍         | 24/600 [03:21<20:56,  2.18s/it, loss=0.0736, lr=1e-7]
Steps:   4%|▍         | 24/600 [03:21<20:56,  2.18s/it, loss=0.0971, lr=1e-7]
Steps:   4%|▍         | 25/600 [03:22<19:22,  2.02s/it, loss=0.0971, lr=1e-7]
Steps:   4%|▍         | 25/600 [03:22<19:22,  2.02s/it, loss=0.0828, lr=1e-7]
Steps:   4%|▍         | 26/600 [03:24<18:23,  1.92s/it, loss=0.0828, lr=1e-7]
Steps:   4%|▍         | 26/600 [03:24<18:23,  1.92s/it, loss=0.0612, lr=1e-7]
Steps:   4%|▍         | 27/600 [03:26<17:45,  1.86s/it, loss=0.0612, lr=1e-7]
Steps:   4%|▍         | 27/600 [03:26<17:45,  1.86s/it, loss=0.197, lr=1e-7] 
Steps:   5%|▍         | 28/600 [03:27<16:03,  1.68s/it, loss=0.197, lr=1e-7]
Steps:   5%|▍         | 28/600 [03:27<16:03,  1.68s/it, loss=0.0579, lr=1e-7]
Steps:   5%|▍         | 29/600 [03:29<16:25,  1.73s/it, loss=0.0579, lr=1e-7]
Steps:   5%|▍         | 29/600 [03:29<16:25,  1.73s/it, loss=0.00545, lr=1e-7]
Steps:   5%|▌         | 30/600 [03:31<16:37,  1.75s/it, loss=0.00545, lr=1e-7]
Steps:   5%|▌         | 30/600 [03:31<16:37,  1.75s/it, loss=0.151, lr=1e-7]  
Steps:   5%|▌         | 31/600 [03:32<15:59,  1.69s/it, loss=0.151, lr=1e-7]
Steps:   5%|▌         | 31/600 [03:32<15:59,  1.69s/it, loss=0.0865, lr=1e-7]
Steps:   5%|▌         | 32/600 [03:33<14:22,  1.52s/it, loss=0.0865, lr=1e-7]
Steps:   5%|▌         | 32/600 [03:33<14:22,  1.52s/it, loss=0.142, lr=1e-7] 
Steps:   6%|▌         | 33/600 [03:34<12:09,  1.29s/it, loss=0.142, lr=1e-7]
Steps:   6%|▌         | 33/600 [03:34<12:09,  1.29s/it, loss=0.0126, lr=1e-7]
Steps:   6%|▌         | 34/600 [03:37<15:31,  1.65s/it, loss=0.0126, lr=1e-7]
Steps:   6%|▌         | 34/600 [03:37<15:31,  1.65s/it, loss=0.0879, lr=1e-7]
Steps:   6%|▌         | 35/600 [03:38<14:35,  1.55s/it, loss=0.0879, lr=1e-7]
Steps:   6%|▌         | 35/600 [03:38<14:35,  1.55s/it, loss=0.136, lr=1e-7] 
Steps:   6%|▌         | 36/600 [03:39<14:16,  1.52s/it, loss=0.136, lr=1e-7]
Steps:   6%|▌         | 36/600 [03:39<14:16,  1.52s/it, loss=0.0609, lr=1e-7]
Steps:   6%|▌         | 37/600 [03:41<13:59,  1.49s/it, loss=0.0609, lr=1e-7]
Steps:   6%|▌         | 37/600 [03:41<13:59,  1.49s/it, loss=0.197, lr=1e-7] 
Steps:   6%|▋         | 38/600 [03:42<14:22,  1.53s/it, loss=0.197, lr=1e-7]
Steps:   6%|▋         | 38/600 [03:42<14:22,  1.53s/it, loss=0.184, lr=1e-7]
Steps:   6%|▋         | 39/600 [03:44<14:15,  1.52s/it, loss=0.184, lr=1e-7]
Steps:   6%|▋         | 39/600 [03:44<14:15,  1.52s/it, loss=0.176, lr=1e-7]
Steps:   7%|▋         | 40/600 [03:45<14:16,  1.53s/it, loss=0.176, lr=1e-7]
Steps:   7%|▋         | 40/600 [03:45<14:16,  1.53s/it, loss=0.0726, lr=1e-7]
Steps:   7%|▋         | 41/600 [03:47<15:01,  1.61s/it, loss=0.0726, lr=1e-7]
Steps:   7%|▋         | 41/600 [03:47<15:01,  1.61s/it, loss=0.0252, lr=1e-7]
Steps:   7%|▋         | 42/600 [03:49<14:51,  1.60s/it, loss=0.0252, lr=1e-7]
Steps:   7%|▋         | 42/600 [03:49<14:51,  1.60s/it, loss=0.173, lr=1e-7] 
Steps:   7%|▋         | 43/600 [03:50<14:24,  1.55s/it, loss=0.173, lr=1e-7]
Steps:   7%|▋         | 43/600 [03:50<14:24,  1.55s/it, loss=0.248, lr=1e-7]
Steps:   7%|▋         | 44/600 [03:51<12:08,  1.31s/it, loss=0.248, lr=1e-7]
Steps:   7%|▋         | 44/600 [03:51<12:08,  1.31s/it, loss=0.0923, lr=1e-7]
Steps:   8%|▊         | 45/600 [03:53<13:18,  1.44s/it, loss=0.0923, lr=1e-7]
Steps:   8%|▊         | 45/600 [03:53<13:18,  1.44s/it, loss=0.0789, lr=1e-7]
Steps:   8%|▊         | 46/600 [03:54<13:34,  1.47s/it, loss=0.0789, lr=1e-7]
Steps:   8%|▊         | 46/600 [03:54<13:34,  1.47s/it, loss=0.241, lr=1e-7] 
Steps:   8%|▊         | 47/600 [03:56<14:14,  1.54s/it, loss=0.241, lr=1e-7]
Steps:   8%|▊         | 47/600 [03:56<14:14,  1.54s/it, loss=0.15, lr=1e-7] 
Steps:   8%|▊         | 48/600 [03:58<15:00,  1.63s/it, loss=0.15, lr=1e-7]
Steps:   8%|▊         | 48/600 [03:58<15:00,  1.63s/it, loss=0.0209, lr=1e-7]
Steps:   8%|▊         | 49/600 [03:59<14:58,  1.63s/it, loss=0.0209, lr=1e-7]
Steps:   8%|▊         | 49/600 [03:59<14:58,  1.63s/it, loss=0.264, lr=1e-7] 
Steps:   8%|▊         | 50/600 [04:01<14:56,  1.63s/it, loss=0.264, lr=1e-7]
Steps:   8%|▊         | 50/600 [04:01<14:56,  1.63s/it, loss=0.169, lr=1e-7]
Steps:   8%|▊         | 51/600 [04:03<14:56,  1.63s/it, loss=0.169, lr=1e-7]
Steps:   8%|▊         | 51/600 [04:03<14:56,  1.63s/it, loss=0.173, lr=1e-7]
Steps:   9%|▊         | 52/600 [04:04<15:05,  1.65s/it, loss=0.173, lr=1e-7]
Steps:   9%|▊         | 52/600 [04:04<15:05,  1.65s/it, loss=0.138, lr=1e-7]
Steps:   9%|▉         | 53/600 [04:06<14:08,  1.55s/it, loss=0.138, lr=1e-7]
Steps:   9%|▉         | 53/600 [04:06<14:08,  1.55s/it, loss=0.151, lr=1e-7]
Steps:   9%|▉         | 54/600 [04:07<13:53,  1.53s/it, loss=0.151, lr=1e-7]
Steps:   9%|▉         | 54/600 [04:07<13:53,  1.53s/it, loss=0.0256, lr=1e-7]
Steps:   9%|▉         | 55/600 [04:08<11:44,  1.29s/it, loss=0.0256, lr=1e-7]
Steps:   9%|▉         | 55/600 [04:08<11:44,  1.29s/it, loss=0.0722, lr=1e-7]
Steps:   9%|▉         | 56/600 [04:10<14:44,  1.63s/it, loss=0.0722, lr=1e-7]
Steps:   9%|▉         | 56/600 [04:10<14:44,  1.63s/it, loss=0.162, lr=1e-7] 
Steps:  10%|▉         | 57/600 [04:12<14:58,  1.65s/it, loss=0.162, lr=1e-7]
Steps:  10%|▉         | 57/600 [04:12<14:58,  1.65s/it, loss=0.0126, lr=1e-7]
Steps:  10%|▉         | 58/600 [04:13<14:06,  1.56s/it, loss=0.0126, lr=1e-7]
Steps:  10%|▉         | 58/600 [04:13<14:06,  1.56s/it, loss=0.17, lr=1e-7]  
Steps:  10%|▉         | 59/600 [04:15<14:00,  1.55s/it, loss=0.17, lr=1e-7]
Steps:  10%|▉         | 59/600 [04:15<14:00,  1.55s/it, loss=0.155, lr=1e-7]
Steps:  10%|█         | 60/600 [04:16<13:49,  1.54s/it, loss=0.155, lr=1e-7]
Steps:  10%|█         | 60/600 [04:16<13:49,  1.54s/it, loss=0.0707, lr=1e-7]
Steps:  10%|█         | 61/600 [04:18<13:57,  1.55s/it, loss=0.0707, lr=1e-7]
Steps:  10%|█         | 61/600 [04:18<13:57,  1.55s/it, loss=0.105, lr=1e-7] 
Steps:  10%|█         | 62/600 [04:19<13:28,  1.50s/it, loss=0.105, lr=1e-7]
Steps:  10%|█         | 62/600 [04:19<13:28,  1.50s/it, loss=0.0643, lr=1e-7]
Steps:  10%|█         | 63/600 [04:21<14:15,  1.59s/it, loss=0.0643, lr=1e-7]
Steps:  10%|█         | 63/600 [04:21<14:15,  1.59s/it, loss=0.136, lr=1e-7] 
Steps:  11%|█         | 64/600 [04:23<14:26,  1.62s/it, loss=0.136, lr=1e-7]
Steps:  11%|█         | 64/600 [04:23<14:26,  1.62s/it, loss=0.169, lr=1e-7]
Steps:  11%|█         | 65/600 [04:24<13:15,  1.49s/it, loss=0.169, lr=1e-7]
Steps:  11%|█         | 65/600 [04:24<13:15,  1.49s/it, loss=0.0594, lr=1e-7]
Steps:  11%|█         | 66/600 [04:25<11:15,  1.27s/it, loss=0.0594, lr=1e-7]
Steps:  11%|█         | 66/600 [04:25<11:15,  1.27s/it, loss=0.00238, lr=1e-7]
Steps:  11%|█         | 67/600 [04:27<13:40,  1.54s/it, loss=0.00238, lr=1e-7]
Steps:  11%|█         | 67/600 [04:27<13:40,  1.54s/it, loss=0.0979, lr=1e-7] 
Steps:  11%|█▏        | 68/600 [04:28<13:25,  1.51s/it, loss=0.0979, lr=1e-7]
Steps:  11%|█▏        | 68/600 [04:28<13:25,  1.51s/it, loss=0.1, lr=1e-7]   
Steps:  12%|█▏        | 69/600 [04:30<13:50,  1.56s/it, loss=0.1, lr=1e-7]
Steps:  12%|█▏        | 69/600 [04:30<13:50,  1.56s/it, loss=0.201, lr=1e-7]
Steps:  12%|█▏        | 70/600 [04:32<14:28,  1.64s/it, loss=0.201, lr=1e-7]
Steps:  12%|█▏        | 70/600 [04:32<14:28,  1.64s/it, loss=0.144, lr=1e-7]
Steps:  12%|█▏        | 71/600 [04:34<14:20,  1.63s/it, loss=0.144, lr=1e-7]
Steps:  12%|█▏        | 71/600 [04:34<14:20,  1.63s/it, loss=0.0463, lr=1e-7]
Steps:  12%|█▏        | 72/600 [04:35<13:59,  1.59s/it, loss=0.0463, lr=1e-7]
Steps:  12%|█▏        | 72/600 [04:35<13:59,  1.59s/it, loss=0.0287, lr=1e-7]
Steps:  12%|█▏        | 73/600 [04:37<13:35,  1.55s/it, loss=0.0287, lr=1e-7]
Steps:  12%|█▏        | 73/600 [04:37<13:35,  1.55s/it, loss=0.0163, lr=1e-7]
Steps:  12%|█▏        | 74/600 [04:38<13:53,  1.58s/it, loss=0.0163, lr=1e-7]
Steps:  12%|█▏        | 74/600 [04:38<13:53,  1.58s/it, loss=0.115, lr=1e-7] 
Steps:  12%|█▎        | 75/600 [04:40<14:06,  1.61s/it, loss=0.115, lr=1e-7]
Steps:  12%|█▎        | 75/600 [04:40<14:06,  1.61s/it, loss=0.0514, lr=1e-7]
Steps:  13%|█▎        | 76/600 [04:41<13:09,  1.51s/it, loss=0.0514, lr=1e-7]
Steps:  13%|█▎        | 76/600 [04:41<13:09,  1.51s/it, loss=0.141, lr=1e-7] 
Steps:  13%|█▎        | 77/600 [04:42<11:09,  1.28s/it, loss=0.141, lr=1e-7]
Steps:  13%|█▎        | 77/600 [04:42<11:09,  1.28s/it, loss=0.00221, lr=1e-7]
Steps:  13%|█▎        | 78/600 [04:44<13:27,  1.55s/it, loss=0.00221, lr=1e-7]
Steps:  13%|█▎        | 78/600 [04:44<13:27,  1.55s/it, loss=0.0585, lr=1e-7] 
Steps:  13%|█▎        | 79/600 [04:46<13:45,  1.59s/it, loss=0.0585, lr=1e-7]
Steps:  13%|█▎        | 79/600 [04:46<13:45,  1.59s/it, loss=0.211, lr=1e-7] 
Steps:  13%|█▎        | 80/600 [04:47<13:30,  1.56s/it, loss=0.211, lr=1e-7]
Steps:  13%|█▎        | 80/600 [04:47<13:30,  1.56s/it, loss=0.0342, lr=1e-7]
Steps:  14%|█▎        | 81/600 [04:49<13:54,  1.61s/it, loss=0.0342, lr=1e-7]
Steps:  14%|█▎        | 81/600 [04:49<13:54,  1.61s/it, loss=0.111, lr=1e-7] 
Steps:  14%|█▎        | 82/600 [04:51<13:59,  1.62s/it, loss=0.111, lr=1e-7]
Steps:  14%|█▎        | 82/600 [04:51<13:59,  1.62s/it, loss=0.0387, lr=1e-7]
Steps:  14%|█▍        | 83/600 [04:52<12:53,  1.50s/it, loss=0.0387, lr=1e-7]
Steps:  14%|█▍        | 83/600 [04:52<12:53,  1.50s/it, loss=0.0331, lr=1e-7]
Steps:  14%|█▍        | 84/600 [04:54<13:42,  1.59s/it, loss=0.0331, lr=1e-7]
Steps:  14%|█▍        | 84/600 [04:54<13:42,  1.59s/it, loss=0.0771, lr=1e-7]
Steps:  14%|█▍        | 85/600 [04:55<13:38,  1.59s/it, loss=0.0771, lr=1e-7]
Steps:  14%|█▍        | 85/600 [04:55<13:38,  1.59s/it, loss=0.202, lr=1e-7] 
Steps:  14%|█▍        | 86/600 [04:57<13:41,  1.60s/it, loss=0.202, lr=1e-7]
Steps:  14%|█▍        | 86/600 [04:57<13:41,  1.60s/it, loss=0.03, lr=1e-7] 
Steps:  14%|█▍        | 87/600 [04:58<12:41,  1.49s/it, loss=0.03, lr=1e-7]
Steps:  14%|█▍        | 87/600 [04:58<12:41,  1.49s/it, loss=0.195, lr=1e-7]
Steps:  15%|█▍        | 88/600 [04:59<10:47,  1.26s/it, loss=0.195, lr=1e-7]
Steps:  15%|█▍        | 88/600 [04:59<10:47,  1.26s/it, loss=0.397, lr=1e-7]
Steps:  15%|█▍        | 89/600 [05:01<13:02,  1.53s/it, loss=0.397, lr=1e-7]
Steps:  15%|█▍        | 89/600 [05:01<13:02,  1.53s/it, loss=0.0853, lr=1e-7]
Steps:  15%|█▌        | 90/600 [05:02<12:43,  1.50s/it, loss=0.0853, lr=1e-7]
Steps:  15%|█▌        | 90/600 [05:02<12:43,  1.50s/it, loss=0.157, lr=1e-7] 
Steps:  15%|█▌        | 91/600 [05:04<13:07,  1.55s/it, loss=0.157, lr=1e-7]
Steps:  15%|█▌        | 91/600 [05:04<13:07,  1.55s/it, loss=0.0632, lr=1e-7]
Steps:  15%|█▌        | 92/600 [05:06<13:16,  1.57s/it, loss=0.0632, lr=1e-7]
Steps:  15%|█▌        | 92/600 [05:06<13:16,  1.57s/it, loss=0.143, lr=1e-7] 
Steps:  16%|█▌        | 93/600 [05:07<13:37,  1.61s/it, loss=0.143, lr=1e-7]
Steps:  16%|█▌        | 93/600 [05:07<13:37,  1.61s/it, loss=0.00503, lr=1e-7]
Steps:  16%|█▌        | 94/600 [05:09<13:38,  1.62s/it, loss=0.00503, lr=1e-7]
Steps:  16%|█▌        | 94/600 [05:09<13:38,  1.62s/it, loss=0.112, lr=1e-7]  
Steps:  16%|█▌        | 95/600 [05:11<13:36,  1.62s/it, loss=0.112, lr=1e-7]
Steps:  16%|█▌        | 95/600 [05:11<13:36,  1.62s/it, loss=0.0727, lr=1e-7]
Steps:  16%|█▌        | 96/600 [05:12<12:55,  1.54s/it, loss=0.0727, lr=1e-7]
Steps:  16%|█▌        | 96/600 [05:12<12:55,  1.54s/it, loss=0.0151, lr=1e-7]
Steps:  16%|█▌        | 97/600 [05:14<13:12,  1.58s/it, loss=0.0151, lr=1e-7]
Steps:  16%|█▌        | 97/600 [05:14<13:12,  1.58s/it, loss=0.00491, lr=1e-7]
Steps:  16%|█▋        | 98/600 [05:15<12:41,  1.52s/it, loss=0.00491, lr=1e-7]
Steps:  16%|█▋        | 98/600 [05:15<12:41,  1.52s/it, loss=0.131, lr=1e-7]  
Steps:  16%|█▋        | 99/600 [05:16<10:43,  1.29s/it, loss=0.131, lr=1e-7]
Steps:  16%|█▋        | 99/600 [05:16<10:43,  1.29s/it, loss=0.251, lr=1e-7]
Steps:  17%|█▋        | 100/600 [05:18<12:07,  1.45s/it, loss=0.251, lr=1e-7]
Steps:  17%|█▋        | 100/600 [05:18<12:07,  1.45s/it, loss=0.229, lr=1e-7]
Steps:  17%|█▋        | 101/600 [05:19<12:49,  1.54s/it, loss=0.229, lr=1e-7]
Steps:  17%|█▋        | 101/600 [05:19<12:49,  1.54s/it, loss=0.0423, lr=1e-7]
Steps:  17%|█▋        | 102/600 [05:21<12:43,  1.53s/it, loss=0.0423, lr=1e-7]
Steps:  17%|█▋        | 102/600 [05:21<12:43,  1.53s/it, loss=0.00851, lr=1e-7]
Steps:  17%|█▋        | 103/600 [05:22<12:37,  1.52s/it, loss=0.00851, lr=1e-7]
Steps:  17%|█▋        | 103/600 [05:22<12:37,  1.52s/it, loss=0.11, lr=1e-7]   
Steps:  17%|█▋        | 104/600 [05:24<13:06,  1.59s/it, loss=0.11, lr=1e-7]
Steps:  17%|█▋        | 104/600 [05:24<13:06,  1.59s/it, loss=0.0145, lr=1e-7]
Steps:  18%|█▊        | 105/600 [05:26<13:31,  1.64s/it, loss=0.0145, lr=1e-7]
Steps:  18%|█▊        | 105/600 [05:26<13:31,  1.64s/it, loss=0.187, lr=1e-7] 
Steps:  18%|█▊        | 106/600 [05:28<13:33,  1.65s/it, loss=0.187, lr=1e-7]
Steps:  18%|█▊        | 106/600 [05:28<13:33,  1.65s/it, loss=0.0982, lr=1e-7]
Steps:  18%|█▊        | 107/600 [05:29<13:30,  1.64s/it, loss=0.0982, lr=1e-7]
Steps:  18%|█▊        | 107/600 [05:29<13:30,  1.64s/it, loss=0.206, lr=1e-7] 
Steps:  18%|█▊        | 108/600 [05:31<13:15,  1.62s/it, loss=0.206, lr=1e-7]
Steps:  18%|█▊        | 108/600 [05:31<13:15,  1.62s/it, loss=0.0551, lr=1e-7]
Steps:  18%|█▊        | 109/600 [05:32<12:08,  1.48s/it, loss=0.0551, lr=1e-7]
Steps:  18%|█▊        | 109/600 [05:32<12:08,  1.48s/it, loss=0.0296, lr=1e-7]
Steps:  18%|█▊        | 110/600 [05:33<10:18,  1.26s/it, loss=0.0296, lr=1e-7]
Steps:  18%|█▊        | 110/600 [05:33<10:18,  1.26s/it, loss=0.322, lr=1e-7] 
Steps:  18%|█▊        | 111/600 [05:35<12:26,  1.53s/it, loss=0.322, lr=1e-7]
Steps:  18%|█▊        | 111/600 [05:35<12:26,  1.53s/it, loss=0.12, lr=1e-7] 
Steps:  19%|█▊        | 112/600 [05:36<12:18,  1.51s/it, loss=0.12, lr=1e-7]
Steps:  19%|█▊        | 112/600 [05:36<12:18,  1.51s/it, loss=0.16, lr=1e-7]
Steps:  19%|█▉        | 113/600 [05:38<12:23,  1.53s/it, loss=0.16, lr=1e-7]
Steps:  19%|█▉        | 113/600 [05:38<12:23,  1.53s/it, loss=0.199, lr=1e-7]
Steps:  19%|█▉        | 114/600 [05:40<13:01,  1.61s/it, loss=0.199, lr=1e-7]
Steps:  19%|█▉        | 114/600 [05:40<13:01,  1.61s/it, loss=0.0346, lr=1e-7]
Steps:  19%|█▉        | 115/600 [05:41<13:13,  1.64s/it, loss=0.0346, lr=1e-7]
Steps:  19%|█▉        | 115/600 [05:41<13:13,  1.64s/it, loss=0.265, lr=1e-7] 
Steps:  19%|█▉        | 116/600 [05:43<12:29,  1.55s/it, loss=0.265, lr=1e-7]
Steps:  19%|█▉        | 116/600 [05:43<12:29,  1.55s/it, loss=0.0032, lr=1e-7]
Steps:  20%|█▉        | 117/600 [05:44<13:08,  1.63s/it, loss=0.0032, lr=1e-7]
Steps:  20%|█▉        | 117/600 [05:44<13:08,  1.63s/it, loss=0.0198, lr=1e-7]
Steps:  20%|█▉        | 118/600 [05:46<12:31,  1.56s/it, loss=0.0198, lr=1e-7]
Steps:  20%|█▉        | 118/600 [05:46<12:31,  1.56s/it, loss=0.0514, lr=1e-7]
Steps:  20%|█▉        | 119/600 [05:47<12:37,  1.57s/it, loss=0.0514, lr=1e-7]
Steps:  20%|█▉        | 119/600 [05:47<12:37,  1.57s/it, loss=0.0172, lr=1e-7]
Steps:  20%|██        | 120/600 [05:49<12:08,  1.52s/it, loss=0.0172, lr=1e-7]
Steps:  20%|██        | 120/600 [05:49<12:08,  1.52s/it, loss=0.201, lr=1e-7] 
Steps:  20%|██        | 121/600 [05:50<10:16,  1.29s/it, loss=0.201, lr=1e-7]
Steps:  20%|██        | 121/600 [05:50<10:16,  1.29s/it, loss=0.36, lr=1e-7] 
Steps:  20%|██        | 122/600 [05:52<13:13,  1.66s/it, loss=0.36, lr=1e-7]
Steps:  20%|██        | 122/600 [05:52<13:13,  1.66s/it, loss=0.0329, lr=1e-7]
Steps:  20%|██        | 123/600 [05:54<13:01,  1.64s/it, loss=0.0329, lr=1e-7]
Steps:  20%|██        | 123/600 [05:54<13:01,  1.64s/it, loss=0.021, lr=1e-7] 
Steps:  21%|██        | 124/600 [05:55<12:43,  1.60s/it, loss=0.021, lr=1e-7]
Steps:  21%|██        | 124/600 [05:55<12:43,  1.60s/it, loss=0.0855, lr=1e-7]
Steps:  21%|██        | 125/600 [05:57<12:41,  1.60s/it, loss=0.0855, lr=1e-7]
Steps:  21%|██        | 125/600 [05:57<12:41,  1.60s/it, loss=0.0881, lr=1e-7]
Steps:  21%|██        | 126/600 [05:58<12:36,  1.60s/it, loss=0.0881, lr=1e-7]
Steps:  21%|██        | 126/600 [05:58<12:36,  1.60s/it, loss=0.132, lr=1e-7] 
Steps:  21%|██        | 127/600 [06:00<12:14,  1.55s/it, loss=0.132, lr=1e-7]
Steps:  21%|██        | 127/600 [06:00<12:14,  1.55s/it, loss=0.101, lr=1e-7]
Steps:  21%|██▏       | 128/600 [06:01<12:03,  1.53s/it, loss=0.101, lr=1e-7]
Steps:  21%|██▏       | 128/600 [06:01<12:03,  1.53s/it, loss=0.0356, lr=1e-7]
Steps:  22%|██▏       | 129/600 [06:03<12:19,  1.57s/it, loss=0.0356, lr=1e-7]
Steps:  22%|██▏       | 129/600 [06:03<12:19,  1.57s/it, loss=0.0893, lr=1e-7]
Steps:  22%|██▏       | 130/600 [06:05<12:21,  1.58s/it, loss=0.0893, lr=1e-7]
Steps:  22%|██▏       | 130/600 [06:05<12:21,  1.58s/it, loss=0.0572, lr=1e-7]
Steps:  22%|██▏       | 131/600 [06:06<11:14,  1.44s/it, loss=0.0572, lr=1e-7]
Steps:  22%|██▏       | 131/600 [06:06<11:14,  1.44s/it, loss=0.156, lr=1e-7] 
Steps:  22%|██▏       | 132/600 [06:07<09:35,  1.23s/it, loss=0.156, lr=1e-7]
Steps:  22%|██▏       | 132/600 [06:07<09:35,  1.23s/it, loss=0.364, lr=1e-7]
Steps:  22%|██▏       | 133/600 [06:09<11:38,  1.50s/it, loss=0.364, lr=1e-7]
Steps:  22%|██▏       | 133/600 [06:09<11:38,  1.50s/it, loss=0.0942, lr=1e-7]
Steps:  22%|██▏       | 134/600 [06:10<11:56,  1.54s/it, loss=0.0942, lr=1e-7]
Steps:  22%|██▏       | 134/600 [06:10<11:56,  1.54s/it, loss=0.0819, lr=1e-7]
Steps:  22%|██▎       | 135/600 [06:12<12:17,  1.59s/it, loss=0.0819, lr=1e-7]
Steps:  22%|██▎       | 135/600 [06:12<12:17,  1.59s/it, loss=0.0718, lr=1e-7]
Steps:  23%|██▎       | 136/600 [06:14<12:38,  1.63s/it, loss=0.0718, lr=1e-7]
Steps:  23%|██▎       | 136/600 [06:14<12:38,  1.63s/it, loss=0.114, lr=1e-7] 
Steps:  23%|██▎       | 137/600 [06:15<12:49,  1.66s/it, loss=0.114, lr=1e-7]
Steps:  23%|██▎       | 137/600 [06:15<12:49,  1.66s/it, loss=0.105, lr=1e-7]
Steps:  23%|██▎       | 138/600 [06:17<12:43,  1.65s/it, loss=0.105, lr=1e-7]
Steps:  23%|██▎       | 138/600 [06:17<12:43,  1.65s/it, loss=0.128, lr=1e-7]
Steps:  23%|██▎       | 139/600 [06:19<12:32,  1.63s/it, loss=0.128, lr=1e-7]
Steps:  23%|██▎       | 139/600 [06:19<12:32,  1.63s/it, loss=0.0208, lr=1e-7]
Steps:  23%|██▎       | 140/600 [06:20<12:14,  1.60s/it, loss=0.0208, lr=1e-7]
Steps:  23%|██▎       | 140/600 [06:20<12:14,  1.60s/it, loss=0.187, lr=1e-7] 
Steps:  24%|██▎       | 141/600 [06:21<11:36,  1.52s/it, loss=0.187, lr=1e-7]
Steps:  24%|██▎       | 141/600 [06:21<11:36,  1.52s/it, loss=0.0777, lr=1e-7]
Steps:  24%|██▎       | 142/600 [06:23<10:42,  1.40s/it, loss=0.0777, lr=1e-7]
Steps:  24%|██▎       | 142/600 [06:23<10:42,  1.40s/it, loss=0.104, lr=1e-7] 
Steps:  24%|██▍       | 143/600 [06:23<09:10,  1.21s/it, loss=0.104, lr=1e-7]
Steps:  24%|██▍       | 143/600 [06:23<09:10,  1.21s/it, loss=0.112, lr=1e-7]
Steps:  24%|██▍       | 144/600 [06:26<11:59,  1.58s/it, loss=0.112, lr=1e-7]
Steps:  24%|██▍       | 144/600 [06:26<11:59,  1.58s/it, loss=0.0306, lr=1e-7]
Steps:  24%|██▍       | 145/600 [06:28<12:17,  1.62s/it, loss=0.0306, lr=1e-7]
Steps:  24%|██▍       | 145/600 [06:28<12:17,  1.62s/it, loss=0.0496, lr=1e-7]
Steps:  24%|██▍       | 146/600 [06:29<11:53,  1.57s/it, loss=0.0496, lr=1e-7]
Steps:  24%|██▍       | 146/600 [06:29<11:53,  1.57s/it, loss=0.0275, lr=1e-7]
Steps:  24%|██▍       | 147/600 [06:31<11:57,  1.58s/it, loss=0.0275, lr=1e-7]
Steps:  24%|██▍       | 147/600 [06:31<11:57,  1.58s/it, loss=0.148, lr=1e-7] 
Steps:  25%|██▍       | 148/600 [06:32<11:47,  1.56s/it, loss=0.148, lr=1e-7]
Steps:  25%|██▍       | 148/600 [06:32<11:47,  1.56s/it, loss=0.0484, lr=1e-7]
Steps:  25%|██▍       | 149/600 [06:34<12:02,  1.60s/it, loss=0.0484, lr=1e-7]
Steps:  25%|██▍       | 149/600 [06:34<12:02,  1.60s/it, loss=0.0316, lr=1e-7]
Steps:  25%|██▌       | 150/600 [06:35<11:59,  1.60s/it, loss=0.0316, lr=1e-7]
Steps:  25%|██▌       | 150/600 [06:35<11:59,  1.60s/it, loss=0.301, lr=1e-7] 
Steps:  25%|██▌       | 151/600 [06:37<11:47,  1.58s/it, loss=0.301, lr=1e-7]
Steps:  25%|██▌       | 151/600 [06:37<11:47,  1.58s/it, loss=0.215, lr=1e-7]
Steps:  25%|██▌       | 152/600 [06:38<11:08,  1.49s/it, loss=0.215, lr=1e-7]
Steps:  25%|██▌       | 152/600 [06:38<11:08,  1.49s/it, loss=0.103, lr=1e-7]
Steps:  26%|██▌       | 153/600 [06:39<10:37,  1.43s/it, loss=0.103, lr=1e-7]
Steps:  26%|██▌       | 153/600 [06:40<10:37,  1.43s/it, loss=0.173, lr=1e-7]
Steps:  26%|██▌       | 154/600 [06:40<09:05,  1.22s/it, loss=0.173, lr=1e-7]
Steps:  26%|██▌       | 154/600 [06:40<09:05,  1.22s/it, loss=0.00466, lr=1e-7]
Steps:  26%|██▌       | 155/600 [06:43<12:11,  1.64s/it, loss=0.00466, lr=1e-7]
Steps:  26%|██▌       | 155/600 [06:43<12:11,  1.64s/it, loss=0.203, lr=1e-7]  
Steps:  26%|██▌       | 156/600 [06:44<11:42,  1.58s/it, loss=0.203, lr=1e-7]
Steps:  26%|██▌       | 156/600 [06:44<11:42,  1.58s/it, loss=0.188, lr=1e-7]
Steps:  26%|██▌       | 157/600 [06:46<11:17,  1.53s/it, loss=0.188, lr=1e-7]
Steps:  26%|██▌       | 157/600 [06:46<11:17,  1.53s/it, loss=0.0756, lr=1e-7]
Steps:  26%|██▋       | 158/600 [06:47<11:08,  1.51s/it, loss=0.0756, lr=1e-7]
Steps:  26%|██▋       | 158/600 [06:47<11:08,  1.51s/it, loss=0.114, lr=1e-7] 
Steps:  26%|██▋       | 159/600 [06:49<11:52,  1.62s/it, loss=0.114, lr=1e-7]
Steps:  26%|██▋       | 159/600 [06:49<11:52,  1.62s/it, loss=0.0806, lr=1e-7]
Steps:  27%|██▋       | 160/600 [06:51<12:06,  1.65s/it, loss=0.0806, lr=1e-7]
Steps:  27%|██▋       | 160/600 [06:51<12:06,  1.65s/it, loss=0.135, lr=1e-7] 
Steps:  27%|██▋       | 161/600 [06:52<11:28,  1.57s/it, loss=0.135, lr=1e-7]
Steps:  27%|██▋       | 161/600 [06:52<11:28,  1.57s/it, loss=0.0399, lr=1e-7]
Steps:  27%|██▋       | 162/600 [06:54<11:14,  1.54s/it, loss=0.0399, lr=1e-7]
Steps:  27%|██▋       | 162/600 [06:54<11:14,  1.54s/it, loss=0.0591, lr=1e-7]
Steps:  27%|██▋       | 163/600 [06:55<11:11,  1.54s/it, loss=0.0591, lr=1e-7]
Steps:  27%|██▋       | 163/600 [06:55<11:11,  1.54s/it, loss=0.00946, lr=1e-7]
Steps:  27%|██▋       | 164/600 [06:56<10:33,  1.45s/it, loss=0.00946, lr=1e-7]
Steps:  27%|██▋       | 164/600 [06:56<10:33,  1.45s/it, loss=0.116, lr=1e-7]  
Steps:  28%|██▊       | 165/600 [06:57<08:59,  1.24s/it, loss=0.116, lr=1e-7]
Steps:  28%|██▊       | 165/600 [06:57<08:59,  1.24s/it, loss=0.322, lr=1e-7]
Steps:  28%|██▊       | 166/600 [06:59<10:05,  1.40s/it, loss=0.322, lr=1e-7]
Steps:  28%|██▊       | 166/600 [06:59<10:05,  1.40s/it, loss=0.126, lr=1e-7]
Steps:  28%|██▊       | 167/600 [07:01<10:35,  1.47s/it, loss=0.126, lr=1e-7]
Steps:  28%|██▊       | 167/600 [07:01<10:35,  1.47s/it, loss=0.0785, lr=1e-7]
Steps:  28%|██▊       | 168/600 [07:02<11:07,  1.54s/it, loss=0.0785, lr=1e-7]
Steps:  28%|██▊       | 168/600 [07:02<11:07,  1.54s/it, loss=0.0383, lr=1e-7]
Steps:  28%|██▊       | 169/600 [07:04<11:47,  1.64s/it, loss=0.0383, lr=1e-7]
Steps:  28%|██▊       | 169/600 [07:04<11:47,  1.64s/it, loss=0.189, lr=1e-7] 
Steps:  28%|██▊       | 170/600 [07:06<12:00,  1.68s/it, loss=0.189, lr=1e-7]
Steps:  28%|██▊       | 170/600 [07:06<12:00,  1.68s/it, loss=0.142, lr=1e-7]
Steps:  28%|██▊       | 171/600 [07:07<11:45,  1.64s/it, loss=0.142, lr=1e-7]
Steps:  28%|██▊       | 171/600 [07:07<11:45,  1.64s/it, loss=0.217, lr=1e-7]
Steps:  29%|██▊       | 172/600 [07:09<11:31,  1.62s/it, loss=0.217, lr=1e-7]
Steps:  29%|██▊       | 172/600 [07:09<11:31,  1.62s/it, loss=0.196, lr=1e-7]
Steps:  29%|██▉       | 173/600 [07:11<11:16,  1.58s/it, loss=0.196, lr=1e-7]
Steps:  29%|██▉       | 173/600 [07:11<11:16,  1.58s/it, loss=0.13, lr=1e-7] 
Steps:  29%|██▉       | 174/600 [07:12<11:07,  1.57s/it, loss=0.13, lr=1e-7]
Steps:  29%|██▉       | 174/600 [07:12<11:07,  1.57s/it, loss=0.0101, lr=1e-7]
Steps:  29%|██▉       | 175/600 [07:13<10:29,  1.48s/it, loss=0.0101, lr=1e-7]
Steps:  29%|██▉       | 175/600 [07:13<10:29,  1.48s/it, loss=0.18, lr=1e-7]  
Steps:  29%|██▉       | 176/600 [07:14<08:54,  1.26s/it, loss=0.18, lr=1e-7]
Steps:  29%|██▉       | 176/600 [07:14<08:54,  1.26s/it, loss=0.0226, lr=1e-7]
Steps:  30%|██▉       | 177/600 [07:17<11:54,  1.69s/it, loss=0.0226, lr=1e-7]
Steps:  30%|██▉       | 177/600 [07:17<11:54,  1.69s/it, loss=0.0306, lr=1e-7]
Steps:  30%|██▉       | 178/600 [07:18<11:46,  1.67s/it, loss=0.0306, lr=1e-7]
Steps:  30%|██▉       | 178/600 [07:18<11:46,  1.67s/it, loss=0.0419, lr=1e-7]
Steps:  30%|██▉       | 179/600 [07:20<11:07,  1.59s/it, loss=0.0419, lr=1e-7]
Steps:  30%|██▉       | 179/600 [07:20<11:07,  1.59s/it, loss=0.0123, lr=1e-7]
Steps:  30%|███       | 180/600 [07:21<11:05,  1.58s/it, loss=0.0123, lr=1e-7]
Steps:  30%|███       | 180/600 [07:21<11:05,  1.58s/it, loss=0.159, lr=1e-7] 
Steps:  30%|███       | 181/600 [07:23<10:58,  1.57s/it, loss=0.159, lr=1e-7]
Steps:  30%|███       | 181/600 [07:23<10:58,  1.57s/it, loss=0.0306, lr=1e-7]
Steps:  30%|███       | 182/600 [07:24<10:56,  1.57s/it, loss=0.0306, lr=1e-7]
Steps:  30%|███       | 182/600 [07:24<10:56,  1.57s/it, loss=0.0696, lr=1e-7]
Steps:  30%|███       | 183/600 [07:26<10:43,  1.54s/it, loss=0.0696, lr=1e-7]
Steps:  30%|███       | 183/600 [07:26<10:43,  1.54s/it, loss=0.0929, lr=1e-7]
Steps:  31%|███       | 184/600 [07:27<10:29,  1.51s/it, loss=0.0929, lr=1e-7]
Steps:  31%|███       | 184/600 [07:27<10:29,  1.51s/it, loss=0.193, lr=1e-7] 
Steps:  31%|███       | 185/600 [07:29<10:36,  1.53s/it, loss=0.193, lr=1e-7]
Steps:  31%|███       | 185/600 [07:29<10:36,  1.53s/it, loss=0.00993, lr=1e-7]
Steps:  31%|███       | 186/600 [07:30<09:57,  1.44s/it, loss=0.00993, lr=1e-7]
Steps:  31%|███       | 186/600 [07:30<09:57,  1.44s/it, loss=0.0849, lr=1e-7] 
Steps:  31%|███       | 187/600 [07:31<08:30,  1.24s/it, loss=0.0849, lr=1e-7]
Steps:  31%|███       | 187/600 [07:31<08:30,  1.24s/it, loss=0.0337, lr=1e-7]
Steps:  31%|███▏      | 188/600 [07:34<11:14,  1.64s/it, loss=0.0337, lr=1e-7]
Steps:  31%|███▏      | 188/600 [07:34<11:14,  1.64s/it, loss=0.0579, lr=1e-7]
Steps:  32%|███▏      | 189/600 [07:35<10:57,  1.60s/it, loss=0.0579, lr=1e-7]
Steps:  32%|███▏      | 189/600 [07:35<10:57,  1.60s/it, loss=0.118, lr=1e-7] 
Steps:  32%|███▏      | 190/600 [07:37<11:11,  1.64s/it, loss=0.118, lr=1e-7]
Steps:  32%|███▏      | 190/600 [07:37<11:11,  1.64s/it, loss=0.194, lr=1e-7]
Steps:  32%|███▏      | 191/600 [07:38<10:53,  1.60s/it, loss=0.194, lr=1e-7]
Steps:  32%|███▏      | 191/600 [07:38<10:53,  1.60s/it, loss=0.2, lr=1e-7]  
Steps:  32%|███▏      | 192/600 [07:40<10:12,  1.50s/it, loss=0.2, lr=1e-7]
Steps:  32%|███▏      | 192/600 [07:40<10:12,  1.50s/it, loss=0.0975, lr=1e-7]
Steps:  32%|███▏      | 193/600 [07:41<10:45,  1.59s/it, loss=0.0975, lr=1e-7]
Steps:  32%|███▏      | 193/600 [07:41<10:45,  1.59s/it, loss=0.125, lr=1e-7] 
Steps:  32%|███▏      | 194/600 [07:43<10:54,  1.61s/it, loss=0.125, lr=1e-7]
Steps:  32%|███▏      | 194/600 [07:43<10:54,  1.61s/it, loss=0.125, lr=1e-7]
Steps:  32%|███▎      | 195/600 [07:45<10:37,  1.57s/it, loss=0.125, lr=1e-7]
Steps:  32%|███▎      | 195/600 [07:45<10:37,  1.57s/it, loss=0.00831, lr=1e-7]
Steps:  33%|███▎      | 196/600 [07:46<10:11,  1.51s/it, loss=0.00831, lr=1e-7]
Steps:  33%|███▎      | 196/600 [07:46<10:11,  1.51s/it, loss=0.0212, lr=1e-7] 
Steps:  33%|███▎      | 197/600 [07:47<09:41,  1.44s/it, loss=0.0212, lr=1e-7]
Steps:  33%|███▎      | 197/600 [07:47<09:41,  1.44s/it, loss=0.038, lr=1e-7] 
Steps:  33%|███▎      | 198/600 [07:48<08:16,  1.24s/it, loss=0.038, lr=1e-7]
Steps:  33%|███▎      | 198/600 [07:48<08:16,  1.24s/it, loss=0.135, lr=1e-7]
Steps:  33%|███▎      | 199/600 [07:50<09:47,  1.46s/it, loss=0.135, lr=1e-7]
Steps:  33%|███▎      | 199/600 [07:50<09:47,  1.46s/it, loss=0.0286, lr=1e-7]
Steps:  33%|███▎      | 200/600 [07:51<09:44,  1.46s/it, loss=0.0286, lr=1e-7]
Steps:  33%|███▎      | 200/600 [07:51<09:44,  1.46s/it, loss=0.143, lr=1e-7] 
Steps:  34%|███▎      | 201/600 [07:53<10:12,  1.54s/it, loss=0.143, lr=1e-7]
Steps:  34%|███▎      | 201/600 [07:53<10:12,  1.54s/it, loss=0.128, lr=1e-7]
Steps:  34%|███▎      | 202/600 [07:55<10:47,  1.63s/it, loss=0.128, lr=1e-7]
Steps:  34%|███▎      | 202/600 [07:55<10:47,  1.63s/it, loss=0.00997, lr=1e-7]
Steps:  34%|███▍      | 203/600 [07:57<10:50,  1.64s/it, loss=0.00997, lr=1e-7]
Steps:  34%|███▍      | 203/600 [07:57<10:50,  1.64s/it, loss=0.156, lr=1e-7]  
Steps:  34%|███▍      | 204/600 [07:58<10:55,  1.65s/it, loss=0.156, lr=1e-7]
Steps:  34%|███▍      | 204/600 [07:58<10:55,  1.65s/it, loss=0.0107, lr=1e-7]
Steps:  34%|███▍      | 205/600 [08:00<11:00,  1.67s/it, loss=0.0107, lr=1e-7]
Steps:  34%|███▍      | 205/600 [08:00<11:00,  1.67s/it, loss=0.0953, lr=1e-7]
Steps:  34%|███▍      | 206/600 [08:02<10:57,  1.67s/it, loss=0.0953, lr=1e-7]
Steps:  34%|███▍      | 206/600 [08:02<10:57,  1.67s/it, loss=0.127, lr=1e-7] 
Steps:  34%|███▍      | 207/600 [08:03<10:56,  1.67s/it, loss=0.127, lr=1e-7]
Steps:  34%|███▍      | 207/600 [08:03<10:56,  1.67s/it, loss=0.13, lr=1e-7] 
Steps:  35%|███▍      | 208/600 [08:05<10:07,  1.55s/it, loss=0.13, lr=1e-7]
Steps:  35%|███▍      | 208/600 [08:05<10:07,  1.55s/it, loss=0.0312, lr=1e-7]
Steps:  35%|███▍      | 209/600 [08:05<08:31,  1.31s/it, loss=0.0312, lr=1e-7]
Steps:  35%|███▍      | 209/600 [08:05<08:31,  1.31s/it, loss=0.0228, lr=1e-7]
Steps:  35%|███▌      | 210/600 [08:08<10:37,  1.63s/it, loss=0.0228, lr=1e-7]
Steps:  35%|███▌      | 210/600 [08:08<10:37,  1.63s/it, loss=0.102, lr=1e-7] 
Steps:  35%|███▌      | 211/600 [08:09<10:16,  1.59s/it, loss=0.102, lr=1e-7]
Steps:  35%|███▌      | 211/600 [08:09<10:16,  1.59s/it, loss=0.0855, lr=1e-7]
Steps:  35%|███▌      | 212/600 [08:11<10:07,  1.57s/it, loss=0.0855, lr=1e-7]
Steps:  35%|███▌      | 212/600 [08:11<10:07,  1.57s/it, loss=0.0158, lr=1e-7]
Steps:  36%|███▌      | 213/600 [08:13<10:38,  1.65s/it, loss=0.0158, lr=1e-7]
Steps:  36%|███▌      | 213/600 [08:13<10:38,  1.65s/it, loss=0.00724, lr=1e-7]
Steps:  36%|███▌      | 214/600 [08:14<10:06,  1.57s/it, loss=0.00724, lr=1e-7]
Steps:  36%|███▌      | 214/600 [08:14<10:06,  1.57s/it, loss=0.00751, lr=1e-7]
Steps:  36%|███▌      | 215/600 [08:15<09:54,  1.54s/it, loss=0.00751, lr=1e-7]
Steps:  36%|███▌      | 215/600 [08:15<09:54,  1.54s/it, loss=0.156, lr=1e-7]  
Steps:  36%|███▌      | 216/600 [08:17<09:57,  1.56s/it, loss=0.156, lr=1e-7]
Steps:  36%|███▌      | 216/600 [08:17<09:57,  1.56s/it, loss=0.132, lr=1e-7]
Steps:  36%|███▌      | 217/600 [08:19<10:36,  1.66s/it, loss=0.132, lr=1e-7]
Steps:  36%|███▌      | 217/600 [08:19<10:36,  1.66s/it, loss=0.0999, lr=1e-7]
Steps:  36%|███▋      | 218/600 [08:20<10:07,  1.59s/it, loss=0.0999, lr=1e-7]
Steps:  36%|███▋      | 218/600 [08:20<10:07,  1.59s/it, loss=0.132, lr=1e-7] 
Steps:  36%|███▋      | 219/600 [08:22<09:30,  1.50s/it, loss=0.132, lr=1e-7]
Steps:  36%|███▋      | 219/600 [08:22<09:30,  1.50s/it, loss=0.0642, lr=1e-7]
Steps:  37%|███▋      | 220/600 [08:22<08:03,  1.27s/it, loss=0.0642, lr=1e-7]
Steps:  37%|███▋      | 220/600 [08:22<08:03,  1.27s/it, loss=0.0302, lr=1e-7]
Steps:  37%|███▋      | 221/600 [08:24<09:22,  1.48s/it, loss=0.0302, lr=1e-7]
Steps:  37%|███▋      | 221/600 [08:24<09:22,  1.48s/it, loss=0.0978, lr=1e-7]
Steps:  37%|███▋      | 222/600 [08:26<09:38,  1.53s/it, loss=0.0978, lr=1e-7]
Steps:  37%|███▋      | 222/600 [08:26<09:38,  1.53s/it, loss=0.0815, lr=1e-7]
Steps:  37%|███▋      | 223/600 [08:28<09:50,  1.57s/it, loss=0.0815, lr=1e-7]
Steps:  37%|███▋      | 223/600 [08:28<09:50,  1.57s/it, loss=0.261, lr=1e-7] 
Steps:  37%|███▋      | 224/600 [08:29<09:48,  1.57s/it, loss=0.261, lr=1e-7]
Steps:  37%|███▋      | 224/600 [08:29<09:48,  1.57s/it, loss=0.0115, lr=1e-7]
Steps:  38%|███▊      | 225/600 [08:31<09:59,  1.60s/it, loss=0.0115, lr=1e-7]
Steps:  38%|███▊      | 225/600 [08:31<09:59,  1.60s/it, loss=0.13, lr=1e-7]  
Steps:  38%|███▊      | 226/600 [08:33<10:03,  1.61s/it, loss=0.13, lr=1e-7]
Steps:  38%|███▊      | 226/600 [08:33<10:03,  1.61s/it, loss=0.093, lr=1e-7]
Steps:  38%|███▊      | 227/600 [08:34<09:53,  1.59s/it, loss=0.093, lr=1e-7]
Steps:  38%|███▊      | 227/600 [08:34<09:53,  1.59s/it, loss=0.17, lr=1e-7] 
Steps:  38%|███▊      | 228/600 [08:36<10:03,  1.62s/it, loss=0.17, lr=1e-7]
Steps:  38%|███▊      | 228/600 [08:36<10:03,  1.62s/it, loss=0.304, lr=1e-7]
Steps:  38%|███▊      | 229/600 [08:37<09:40,  1.56s/it, loss=0.304, lr=1e-7]
Steps:  38%|███▊      | 229/600 [08:37<09:40,  1.56s/it, loss=0.0859, lr=1e-7]
Steps:  38%|███▊      | 230/600 [08:39<09:18,  1.51s/it, loss=0.0859, lr=1e-7]
Steps:  38%|███▊      | 230/600 [08:39<09:18,  1.51s/it, loss=0.0258, lr=1e-7]
Steps:  38%|███▊      | 231/600 [08:39<07:52,  1.28s/it, loss=0.0258, lr=1e-7]
Steps:  38%|███▊      | 231/600 [08:39<07:52,  1.28s/it, loss=0.0238, lr=1e-7]
Steps:  39%|███▊      | 232/600 [08:42<10:03,  1.64s/it, loss=0.0238, lr=1e-7]
Steps:  39%|███▊      | 232/600 [08:42<10:03,  1.64s/it, loss=0.0661, lr=1e-7]
Steps:  39%|███▉      | 233/600 [08:43<09:55,  1.62s/it, loss=0.0661, lr=1e-7]
Steps:  39%|███▉      | 233/600 [08:43<09:55,  1.62s/it, loss=0.134, lr=1e-7] 
Steps:  39%|███▉      | 234/600 [08:45<09:37,  1.58s/it, loss=0.134, lr=1e-7]
Steps:  39%|███▉      | 234/600 [08:45<09:37,  1.58s/it, loss=0.0541, lr=1e-7]
Steps:  39%|███▉      | 235/600 [08:47<09:56,  1.63s/it, loss=0.0541, lr=1e-7]
Steps:  39%|███▉      | 235/600 [08:47<09:56,  1.63s/it, loss=0.0954, lr=1e-7]
Steps:  39%|███▉      | 236/600 [08:48<09:38,  1.59s/it, loss=0.0954, lr=1e-7]
Steps:  39%|███▉      | 236/600 [08:48<09:38,  1.59s/it, loss=0.0111, lr=1e-7]
Steps:  40%|███▉      | 237/600 [08:50<09:19,  1.54s/it, loss=0.0111, lr=1e-7]
Steps:  40%|███▉      | 237/600 [08:50<09:19,  1.54s/it, loss=0.0577, lr=1e-7]
Steps:  40%|███▉      | 238/600 [08:51<09:01,  1.50s/it, loss=0.0577, lr=1e-7]
Steps:  40%|███▉      | 238/600 [08:51<09:01,  1.50s/it, loss=0.0608, lr=1e-7]
Steps:  40%|███▉      | 239/600 [08:53<09:36,  1.60s/it, loss=0.0608, lr=1e-7]
Steps:  40%|███▉      | 239/600 [08:53<09:36,  1.60s/it, loss=0.0454, lr=1e-7]
Steps:  40%|████      | 240/600 [08:54<09:25,  1.57s/it, loss=0.0454, lr=1e-7]
Steps:  40%|████      | 240/600 [08:54<09:25,  1.57s/it, loss=0.139, lr=1e-7] 
Steps:  40%|████      | 241/600 [08:56<08:49,  1.47s/it, loss=0.139, lr=1e-7]
Steps:  40%|████      | 241/600 [08:56<08:49,  1.47s/it, loss=0.0687, lr=1e-7]
Steps:  40%|████      | 242/600 [08:56<07:29,  1.26s/it, loss=0.0687, lr=1e-7]
Steps:  40%|████      | 242/600 [08:56<07:29,  1.26s/it, loss=0.0111, lr=1e-7]
Steps:  40%|████      | 243/600 [08:58<09:02,  1.52s/it, loss=0.0111, lr=1e-7]
Steps:  40%|████      | 243/600 [08:58<09:02,  1.52s/it, loss=0.204, lr=1e-7] 
Steps:  41%|████      | 244/600 [09:00<09:10,  1.55s/it, loss=0.204, lr=1e-7]
Steps:  41%|████      | 244/600 [09:00<09:10,  1.55s/it, loss=0.0119, lr=1e-7]
Steps:  41%|████      | 245/600 [09:01<09:00,  1.52s/it, loss=0.0119, lr=1e-7]
Steps:  41%|████      | 245/600 [09:01<09:00,  1.52s/it, loss=0.143, lr=1e-7] 
Steps:  41%|████      | 246/600 [09:03<09:01,  1.53s/it, loss=0.143, lr=1e-7]
Steps:  41%|████      | 246/600 [09:03<09:01,  1.53s/it, loss=0.168, lr=1e-7]
Steps:  41%|████      | 247/600 [09:05<09:00,  1.53s/it, loss=0.168, lr=1e-7]
Steps:  41%|████      | 247/600 [09:05<09:00,  1.53s/it, loss=0.127, lr=1e-7]
Steps:  41%|████▏     | 248/600 [09:06<09:14,  1.57s/it, loss=0.127, lr=1e-7]
Steps:  41%|████▏     | 248/600 [09:06<09:14,  1.57s/it, loss=0.277, lr=1e-7]
Steps:  42%|████▏     | 249/600 [09:08<09:10,  1.57s/it, loss=0.277, lr=1e-7]
Steps:  42%|████▏     | 249/600 [09:08<09:10,  1.57s/it, loss=0.128, lr=1e-7]
Steps:  42%|████▏     | 250/600 [09:09<09:08,  1.57s/it, loss=0.128, lr=1e-7]
Steps:  42%|████▏     | 250/600 [09:09<09:08,  1.57s/it, loss=0.133, lr=1e-7]
Steps:  42%|████▏     | 251/600 [09:11<09:13,  1.59s/it, loss=0.133, lr=1e-7]
Steps:  42%|████▏     | 251/600 [09:11<09:13,  1.59s/it, loss=0.2, lr=1e-7]  
Steps:  42%|████▏     | 252/600 [09:12<09:00,  1.55s/it, loss=0.2, lr=1e-7]
Steps:  42%|████▏     | 252/600 [09:12<09:00,  1.55s/it, loss=0.19, lr=1e-7]
Steps:  42%|████▏     | 253/600 [09:13<07:36,  1.31s/it, loss=0.19, lr=1e-7]
Steps:  42%|████▏     | 253/600 [09:13<07:36,  1.31s/it, loss=0.0962, lr=1e-7]
Steps:  42%|████▏     | 254/600 [09:16<09:18,  1.61s/it, loss=0.0962, lr=1e-7]
Steps:  42%|████▏     | 254/600 [09:16<09:18,  1.61s/it, loss=0.162, lr=1e-7] 
Steps:  42%|████▎     | 255/600 [09:17<08:50,  1.54s/it, loss=0.162, lr=1e-7]
Steps:  42%|████▎     | 255/600 [09:17<08:50,  1.54s/it, loss=0.0811, lr=1e-7]
Steps:  43%|████▎     | 256/600 [09:19<09:01,  1.57s/it, loss=0.0811, lr=1e-7]
Steps:  43%|████▎     | 256/600 [09:19<09:01,  1.57s/it, loss=0.151, lr=1e-7] 
Steps:  43%|████▎     | 257/600 [09:20<09:02,  1.58s/it, loss=0.151, lr=1e-7]
Steps:  43%|████▎     | 257/600 [09:20<09:02,  1.58s/it, loss=0.142, lr=1e-7]
Steps:  43%|████▎     | 258/600 [09:22<08:41,  1.53s/it, loss=0.142, lr=1e-7]
Steps:  43%|████▎     | 258/600 [09:22<08:41,  1.53s/it, loss=0.166, lr=1e-7]
Steps:  43%|████▎     | 259/600 [09:23<08:30,  1.50s/it, loss=0.166, lr=1e-7]
Steps:  43%|████▎     | 259/600 [09:23<08:30,  1.50s/it, loss=0.0145, lr=1e-7]
Steps:  43%|████▎     | 260/600 [09:25<08:53,  1.57s/it, loss=0.0145, lr=1e-7]
Steps:  43%|████▎     | 260/600 [09:25<08:53,  1.57s/it, loss=0.223, lr=1e-7] 
Steps:  44%|████▎     | 261/600 [09:26<09:03,  1.60s/it, loss=0.223, lr=1e-7]
Steps:  44%|████▎     | 261/600 [09:26<09:03,  1.60s/it, loss=0.0999, lr=1e-7]
Steps:  44%|████▎     | 262/600 [09:28<09:13,  1.64s/it, loss=0.0999, lr=1e-7]
Steps:  44%|████▎     | 262/600 [09:28<09:13,  1.64s/it, loss=0.0818, lr=1e-7]
Steps:  44%|████▍     | 263/600 [09:30<08:47,  1.57s/it, loss=0.0818, lr=1e-7]
Steps:  44%|████▍     | 263/600 [09:30<08:47,  1.57s/it, loss=0.0822, lr=1e-7]
Steps:  44%|████▍     | 264/600 [09:30<07:23,  1.32s/it, loss=0.0822, lr=1e-7]
Steps:  44%|████▍     | 264/600 [09:30<07:23,  1.32s/it, loss=0.354, lr=1e-7] 
Steps:  44%|████▍     | 265/600 [09:33<09:23,  1.68s/it, loss=0.354, lr=1e-7]
Steps:  44%|████▍     | 265/600 [09:33<09:23,  1.68s/it, loss=0.031, lr=1e-7]
Steps:  44%|████▍     | 266/600 [09:35<09:32,  1.71s/it, loss=0.031, lr=1e-7]
Steps:  44%|████▍     | 266/600 [09:35<09:32,  1.71s/it, loss=0.143, lr=1e-7]
Steps:  44%|████▍     | 267/600 [09:36<09:26,  1.70s/it, loss=0.143, lr=1e-7]
Steps:  44%|████▍     | 267/600 [09:36<09:26,  1.70s/it, loss=0.191, lr=1e-7]
Steps:  45%|████▍     | 268/600 [09:38<09:10,  1.66s/it, loss=0.191, lr=1e-7]
Steps:  45%|████▍     | 268/600 [09:38<09:10,  1.66s/it, loss=0.189, lr=1e-7]
Steps:  45%|████▍     | 269/600 [09:39<08:35,  1.56s/it, loss=0.189, lr=1e-7]
Steps:  45%|████▍     | 269/600 [09:39<08:35,  1.56s/it, loss=0.162, lr=1e-7]
Steps:  45%|████▌     | 270/600 [09:41<08:29,  1.54s/it, loss=0.162, lr=1e-7]
Steps:  45%|████▌     | 270/600 [09:41<08:29,  1.54s/it, loss=0.202, lr=1e-7]
Steps:  45%|████▌     | 271/600 [09:42<08:01,  1.46s/it, loss=0.202, lr=1e-7]
Steps:  45%|████▌     | 271/600 [09:42<08:01,  1.46s/it, loss=0.25, lr=1e-7] 
Steps:  45%|████▌     | 272/600 [09:44<08:16,  1.51s/it, loss=0.25, lr=1e-7]
Steps:  45%|████▌     | 272/600 [09:44<08:16,  1.51s/it, loss=0.0324, lr=1e-7]
Steps:  46%|████▌     | 273/600 [09:45<08:15,  1.51s/it, loss=0.0324, lr=1e-7]
Steps:  46%|████▌     | 273/600 [09:45<08:15,  1.51s/it, loss=0.0218, lr=1e-7]
Steps:  46%|████▌     | 274/600 [09:46<08:00,  1.47s/it, loss=0.0218, lr=1e-7]
Steps:  46%|████▌     | 274/600 [09:46<08:00,  1.47s/it, loss=0.15, lr=1e-7]  
Steps:  46%|████▌     | 275/600 [09:47<06:50,  1.26s/it, loss=0.15, lr=1e-7]
Steps:  46%|████▌     | 275/600 [09:47<06:50,  1.26s/it, loss=0.0137, lr=1e-7]
Steps:  46%|████▌     | 276/600 [09:49<08:26,  1.56s/it, loss=0.0137, lr=1e-7]
Steps:  46%|████▌     | 276/600 [09:49<08:26,  1.56s/it, loss=0.198, lr=1e-7] 
Steps:  46%|████▌     | 277/600 [09:51<08:31,  1.58s/it, loss=0.198, lr=1e-7]
Steps:  46%|████▌     | 277/600 [09:51<08:31,  1.58s/it, loss=0.0147, lr=1e-7]
Steps:  46%|████▋     | 278/600 [09:53<08:54,  1.66s/it, loss=0.0147, lr=1e-7]
Steps:  46%|████▋     | 278/600 [09:53<08:54,  1.66s/it, loss=0.22, lr=1e-7]  
Steps:  46%|████▋     | 279/600 [09:55<08:49,  1.65s/it, loss=0.22, lr=1e-7]
Steps:  46%|████▋     | 279/600 [09:55<08:49,  1.65s/it, loss=0.316, lr=1e-7]
Steps:  47%|████▋     | 280/600 [09:56<08:25,  1.58s/it, loss=0.316, lr=1e-7]
Steps:  47%|████▋     | 280/600 [09:56<08:25,  1.58s/it, loss=0.0261, lr=1e-7]
Steps:  47%|████▋     | 281/600 [09:57<08:03,  1.52s/it, loss=0.0261, lr=1e-7]
Steps:  47%|████▋     | 281/600 [09:57<08:03,  1.52s/it, loss=0.0655, lr=1e-7]
Steps:  47%|████▋     | 282/600 [09:59<08:14,  1.56s/it, loss=0.0655, lr=1e-7]
Steps:  47%|████▋     | 282/600 [09:59<08:14,  1.56s/it, loss=0.164, lr=1e-7] 
Steps:  47%|████▋     | 283/600 [10:00<08:03,  1.53s/it, loss=0.164, lr=1e-7]
Steps:  47%|████▋     | 283/600 [10:00<08:03,  1.53s/it, loss=0.142, lr=1e-7]
Steps:  47%|████▋     | 284/600 [10:02<08:18,  1.58s/it, loss=0.142, lr=1e-7]
Steps:  47%|████▋     | 284/600 [10:02<08:18,  1.58s/it, loss=0.134, lr=1e-7]
Steps:  48%|████▊     | 285/600 [10:03<07:48,  1.49s/it, loss=0.134, lr=1e-7]
Steps:  48%|████▊     | 285/600 [10:03<07:48,  1.49s/it, loss=0.179, lr=1e-7]
Steps:  48%|████▊     | 286/600 [10:04<06:37,  1.27s/it, loss=0.179, lr=1e-7]
Steps:  48%|████▊     | 286/600 [10:04<06:37,  1.27s/it, loss=0.134, lr=1e-7]
Steps:  48%|████▊     | 287/600 [10:06<08:07,  1.56s/it, loss=0.134, lr=1e-7]
Steps:  48%|████▊     | 287/600 [10:06<08:07,  1.56s/it, loss=0.027, lr=1e-7]
Steps:  48%|████▊     | 288/600 [10:08<08:07,  1.56s/it, loss=0.027, lr=1e-7]
Steps:  48%|████▊     | 288/600 [10:08<08:07,  1.56s/it, loss=0.205, lr=1e-7]
Steps:  48%|████▊     | 289/600 [10:10<08:16,  1.60s/it, loss=0.205, lr=1e-7]
Steps:  48%|████▊     | 289/600 [10:10<08:16,  1.60s/it, loss=0.0264, lr=1e-7]
Steps:  48%|████▊     | 290/600 [10:11<08:16,  1.60s/it, loss=0.0264, lr=1e-7]
Steps:  48%|████▊     | 290/600 [10:11<08:16,  1.60s/it, loss=0.0271, lr=1e-7]
Steps:  48%|████▊     | 291/600 [10:13<07:50,  1.52s/it, loss=0.0271, lr=1e-7]
Steps:  48%|████▊     | 291/600 [10:13<07:50,  1.52s/it, loss=0.191, lr=1e-7] 
Steps:  49%|████▊     | 292/600 [10:14<07:34,  1.48s/it, loss=0.191, lr=1e-7]
Steps:  49%|████▊     | 292/600 [10:14<07:34,  1.48s/it, loss=0.0225, lr=1e-7]
Steps:  49%|████▉     | 293/600 [10:16<08:03,  1.58s/it, loss=0.0225, lr=1e-7]
Steps:  49%|████▉     | 293/600 [10:16<08:03,  1.58s/it, loss=0.0589, lr=1e-7]
Steps:  49%|████▉     | 294/600 [10:17<07:53,  1.55s/it, loss=0.0589, lr=1e-7]
Steps:  49%|████▉     | 294/600 [10:17<07:53,  1.55s/it, loss=0.143, lr=1e-7] 
Steps:  49%|████▉     | 295/600 [10:19<08:06,  1.59s/it, loss=0.143, lr=1e-7]
Steps:  49%|████▉     | 295/600 [10:19<08:06,  1.59s/it, loss=0.00962, lr=1e-7]
Steps:  49%|████▉     | 296/600 [10:20<07:45,  1.53s/it, loss=0.00962, lr=1e-7]
Steps:  49%|████▉     | 296/600 [10:20<07:45,  1.53s/it, loss=0.193, lr=1e-7]  
Steps:  50%|████▉     | 297/600 [10:21<06:32,  1.30s/it, loss=0.193, lr=1e-7]
Steps:  50%|████▉     | 297/600 [10:21<06:32,  1.30s/it, loss=0.32, lr=1e-7] 
Steps:  50%|████▉     | 298/600 [10:23<07:57,  1.58s/it, loss=0.32, lr=1e-7]
Steps:  50%|████▉     | 298/600 [10:23<07:57,  1.58s/it, loss=0.0165, lr=1e-7]
Steps:  50%|████▉     | 299/600 [10:25<08:04,  1.61s/it, loss=0.0165, lr=1e-7]
Steps:  50%|████▉     | 299/600 [10:25<08:04,  1.61s/it, loss=0.233, lr=1e-7] 
Steps:  50%|█████     | 300/600 [10:27<08:15,  1.65s/it, loss=0.233, lr=1e-7]
Steps:  50%|█████     | 300/600 [10:27<08:15,  1.65s/it, loss=0.0172, lr=1e-7]
Steps:  50%|█████     | 301/600 [10:28<08:12,  1.65s/it, loss=0.0172, lr=1e-7]
Steps:  50%|█████     | 301/600 [10:28<08:12,  1.65s/it, loss=0.284, lr=1e-7] 
Steps:  50%|█████     | 302/600 [10:30<07:41,  1.55s/it, loss=0.284, lr=1e-7]
Steps:  50%|█████     | 302/600 [10:30<07:41,  1.55s/it, loss=0.236, lr=1e-7]
Steps:  50%|█████     | 303/600 [10:31<07:28,  1.51s/it, loss=0.236, lr=1e-7]
Steps:  50%|█████     | 303/600 [10:31<07:28,  1.51s/it, loss=0.163, lr=1e-7]
Steps:  51%|█████     | 304/600 [10:33<07:49,  1.59s/it, loss=0.163, lr=1e-7]
Steps:  51%|█████     | 304/600 [10:33<07:49,  1.59s/it, loss=0.22, lr=1e-7] 
Steps:  51%|█████     | 305/600 [10:35<07:55,  1.61s/it, loss=0.22, lr=1e-7]
Steps:  51%|█████     | 305/600 [10:35<07:55,  1.61s/it, loss=0.219, lr=1e-7]
Steps:  51%|█████     | 306/600 [10:36<07:45,  1.58s/it, loss=0.219, lr=1e-7]
Steps:  51%|█████     | 306/600 [10:36<07:45,  1.58s/it, loss=0.00363, lr=1e-7]
Steps:  51%|█████     | 307/600 [10:37<07:14,  1.48s/it, loss=0.00363, lr=1e-7]
Steps:  51%|█████     | 307/600 [10:37<07:14,  1.48s/it, loss=0.136, lr=1e-7]  
Steps:  51%|█████▏    | 308/600 [10:38<06:08,  1.26s/it, loss=0.136, lr=1e-7]
Steps:  51%|█████▏    | 308/600 [10:38<06:08,  1.26s/it, loss=0.292, lr=1e-7]
Steps:  52%|█████▏    | 309/600 [10:40<07:13,  1.49s/it, loss=0.292, lr=1e-7]
Steps:  52%|█████▏    | 309/600 [10:40<07:13,  1.49s/it, loss=0.213, lr=1e-7]
Steps:  52%|█████▏    | 310/600 [10:42<07:25,  1.54s/it, loss=0.213, lr=1e-7]
Steps:  52%|█████▏    | 310/600 [10:42<07:25,  1.54s/it, loss=0.161, lr=1e-7]
Steps:  52%|█████▏    | 311/600 [10:43<07:16,  1.51s/it, loss=0.161, lr=1e-7]
Steps:  52%|█████▏    | 311/600 [10:43<07:16,  1.51s/it, loss=0.103, lr=1e-7]
Steps:  52%|█████▏    | 312/600 [10:45<07:33,  1.57s/it, loss=0.103, lr=1e-7]
Steps:  52%|█████▏    | 312/600 [10:45<07:33,  1.57s/it, loss=0.0259, lr=1e-7]
Steps:  52%|█████▏    | 313/600 [10:47<07:41,  1.61s/it, loss=0.0259, lr=1e-7]
Steps:  52%|█████▏    | 313/600 [10:47<07:41,  1.61s/it, loss=0.164, lr=1e-7] 
Steps:  52%|█████▏    | 314/600 [10:48<07:46,  1.63s/it, loss=0.164, lr=1e-7]
Steps:  52%|█████▏    | 314/600 [10:48<07:46,  1.63s/it, loss=0.0721, lr=1e-7]
Steps:  52%|█████▎    | 315/600 [10:50<07:42,  1.62s/it, loss=0.0721, lr=1e-7]
Steps:  52%|█████▎    | 315/600 [10:50<07:42,  1.62s/it, loss=0.0126, lr=1e-7]
Steps:  53%|█████▎    | 316/600 [10:52<07:40,  1.62s/it, loss=0.0126, lr=1e-7]
Steps:  53%|█████▎    | 316/600 [10:52<07:40,  1.62s/it, loss=0.299, lr=1e-7] 
Steps:  53%|█████▎    | 317/600 [10:53<07:42,  1.63s/it, loss=0.299, lr=1e-7]
Steps:  53%|█████▎    | 317/600 [10:53<07:42,  1.63s/it, loss=0.0487, lr=1e-7]
Steps:  53%|█████▎    | 318/600 [10:54<06:56,  1.48s/it, loss=0.0487, lr=1e-7]
Steps:  53%|█████▎    | 318/600 [10:54<06:56,  1.48s/it, loss=0.046, lr=1e-7] 
Steps:  53%|█████▎    | 319/600 [10:55<05:54,  1.26s/it, loss=0.046, lr=1e-7]
Steps:  53%|█████▎    | 319/600 [10:55<05:54,  1.26s/it, loss=0.0432, lr=1e-7]
Steps:  53%|█████▎    | 320/600 [10:57<07:14,  1.55s/it, loss=0.0432, lr=1e-7]
Steps:  53%|█████▎    | 320/600 [10:57<07:14,  1.55s/it, loss=0.013, lr=1e-7] 
Steps:  54%|█████▎    | 321/600 [10:59<07:26,  1.60s/it, loss=0.013, lr=1e-7]
Steps:  54%|█████▎    | 321/600 [10:59<07:26,  1.60s/it, loss=0.229, lr=1e-7]
Steps:  54%|█████▎    | 322/600 [11:01<07:14,  1.56s/it, loss=0.229, lr=1e-7]
Steps:  54%|█████▎    | 322/600 [11:01<07:14,  1.56s/it, loss=0.147, lr=1e-7]
Steps:  54%|█████▍    | 323/600 [11:02<07:26,  1.61s/it, loss=0.147, lr=1e-7]
Steps:  54%|█████▍    | 323/600 [11:02<07:26,  1.61s/it, loss=0.142, lr=1e-7]
Steps:  54%|█████▍    | 324/600 [11:04<07:34,  1.65s/it, loss=0.142, lr=1e-7]
Steps:  54%|█████▍    | 324/600 [11:04<07:34,  1.65s/it, loss=0.231, lr=1e-7]
Steps:  54%|█████▍    | 325/600 [11:06<07:34,  1.65s/it, loss=0.231, lr=1e-7]
Steps:  54%|█████▍    | 325/600 [11:06<07:34,  1.65s/it, loss=0.23, lr=1e-7] 
Steps:  54%|█████▍    | 326/600 [11:07<07:08,  1.56s/it, loss=0.23, lr=1e-7]
Steps:  54%|█████▍    | 326/600 [11:07<07:08,  1.56s/it, loss=0.0907, lr=1e-7]
Steps:  55%|█████▍    | 327/600 [11:09<07:17,  1.60s/it, loss=0.0907, lr=1e-7]
Steps:  55%|█████▍    | 327/600 [11:09<07:17,  1.60s/it, loss=0.119, lr=1e-7] 
Steps:  55%|█████▍    | 328/600 [11:10<07:19,  1.62s/it, loss=0.119, lr=1e-7]
Steps:  55%|█████▍    | 328/600 [11:10<07:19,  1.62s/it, loss=0.127, lr=1e-7]
Steps:  55%|█████▍    | 329/600 [11:11<06:36,  1.46s/it, loss=0.127, lr=1e-7]
Steps:  55%|█████▍    | 329/600 [11:11<06:36,  1.46s/it, loss=0.0299, lr=1e-7]
Steps:  55%|█████▌    | 330/600 [11:12<05:38,  1.25s/it, loss=0.0299, lr=1e-7]
Steps:  55%|█████▌    | 330/600 [11:12<05:38,  1.25s/it, loss=0.169, lr=1e-7] 
Steps:  55%|█████▌    | 331/600 [11:14<06:50,  1.53s/it, loss=0.169, lr=1e-7]
Steps:  55%|█████▌    | 331/600 [11:14<06:50,  1.53s/it, loss=0.0212, lr=1e-7]
Steps:  55%|█████▌    | 332/600 [11:16<06:58,  1.56s/it, loss=0.0212, lr=1e-7]
Steps:  55%|█████▌    | 332/600 [11:16<06:58,  1.56s/it, loss=0.00365, lr=1e-7]
Steps:  56%|█████▌    | 333/600 [11:18<07:03,  1.59s/it, loss=0.00365, lr=1e-7]
Steps:  56%|█████▌    | 333/600 [11:18<07:03,  1.59s/it, loss=0.139, lr=1e-7]  
Steps:  56%|█████▌    | 334/600 [11:20<07:25,  1.67s/it, loss=0.139, lr=1e-7]
Steps:  56%|█████▌    | 334/600 [11:20<07:25,  1.67s/it, loss=0.192, lr=1e-7]
Steps:  56%|█████▌    | 335/600 [11:21<07:23,  1.67s/it, loss=0.192, lr=1e-7]
Steps:  56%|█████▌    | 335/600 [11:21<07:23,  1.67s/it, loss=0.132, lr=1e-7]
Steps:  56%|█████▌    | 336/600 [11:23<07:16,  1.65s/it, loss=0.132, lr=1e-7]
Steps:  56%|█████▌    | 336/600 [11:23<07:16,  1.65s/it, loss=0.0126, lr=1e-7]
Steps:  56%|█████▌    | 337/600 [11:24<07:06,  1.62s/it, loss=0.0126, lr=1e-7]
Steps:  56%|█████▌    | 337/600 [11:24<07:06,  1.62s/it, loss=0.0962, lr=1e-7]
Steps:  56%|█████▋    | 338/600 [11:26<06:43,  1.54s/it, loss=0.0962, lr=1e-7]
Steps:  56%|█████▋    | 338/600 [11:26<06:43,  1.54s/it, loss=0.158, lr=1e-7] 
Steps:  56%|█████▋    | 339/600 [11:27<06:38,  1.53s/it, loss=0.158, lr=1e-7]
Steps:  56%|█████▋    | 339/600 [11:27<06:38,  1.53s/it, loss=0.125, lr=1e-7]
Steps:  57%|█████▋    | 340/600 [11:28<06:12,  1.43s/it, loss=0.125, lr=1e-7]
Steps:  57%|█████▋    | 340/600 [11:28<06:12,  1.43s/it, loss=0.152, lr=1e-7]
Steps:  57%|█████▋    | 341/600 [11:29<05:18,  1.23s/it, loss=0.152, lr=1e-7]
Steps:  57%|█████▋    | 341/600 [11:29<05:18,  1.23s/it, loss=0.195, lr=1e-7]
Steps:  57%|█████▋    | 342/600 [11:31<06:29,  1.51s/it, loss=0.195, lr=1e-7]
Steps:  57%|█████▋    | 342/600 [11:31<06:29,  1.51s/it, loss=0.0468, lr=1e-7]
Steps:  57%|█████▋    | 343/600 [11:33<06:22,  1.49s/it, loss=0.0468, lr=1e-7]
Steps:  57%|█████▋    | 343/600 [11:33<06:22,  1.49s/it, loss=0.137, lr=1e-7] 
Steps:  57%|█████▋    | 344/600 [11:34<06:34,  1.54s/it, loss=0.137, lr=1e-7]
Steps:  57%|█████▋    | 344/600 [11:34<06:34,  1.54s/it, loss=0.0629, lr=1e-7]
Steps:  57%|█████▊    | 345/600 [11:36<06:32,  1.54s/it, loss=0.0629, lr=1e-7]
Steps:  57%|█████▊    | 345/600 [11:36<06:32,  1.54s/it, loss=0.164, lr=1e-7] 
Steps:  58%|█████▊    | 346/600 [11:37<06:26,  1.52s/it, loss=0.164, lr=1e-7]
Steps:  58%|█████▊    | 346/600 [11:37<06:26,  1.52s/it, loss=0.00682, lr=1e-7]
Steps:  58%|█████▊    | 347/600 [11:39<06:28,  1.53s/it, loss=0.00682, lr=1e-7]
Steps:  58%|█████▊    | 347/600 [11:39<06:28,  1.53s/it, loss=0.0856, lr=1e-7] 
Steps:  58%|█████▊    | 348/600 [11:41<06:37,  1.58s/it, loss=0.0856, lr=1e-7]
Steps:  58%|█████▊    | 348/600 [11:41<06:37,  1.58s/it, loss=0.19, lr=1e-7]  
Steps:  58%|█████▊    | 349/600 [11:42<06:46,  1.62s/it, loss=0.19, lr=1e-7]
Steps:  58%|█████▊    | 349/600 [11:42<06:46,  1.62s/it, loss=0.124, lr=1e-7]
Steps:  58%|█████▊    | 350/600 [11:44<06:31,  1.57s/it, loss=0.124, lr=1e-7]
Steps:  58%|█████▊    | 350/600 [11:44<06:31,  1.57s/it, loss=0.273, lr=1e-7]
Steps:  58%|█████▊    | 351/600 [11:45<06:23,  1.54s/it, loss=0.273, lr=1e-7]
Steps:  58%|█████▊    | 351/600 [11:45<06:23,  1.54s/it, loss=0.0197, lr=1e-7]
Steps:  59%|█████▊    | 352/600 [11:46<05:23,  1.30s/it, loss=0.0197, lr=1e-7]
Steps:  59%|█████▊    | 352/600 [11:46<05:23,  1.30s/it, loss=0.0685, lr=1e-7]
Steps:  59%|█████▉    | 353/600 [11:48<06:35,  1.60s/it, loss=0.0685, lr=1e-7]
Steps:  59%|█████▉    | 353/600 [11:48<06:35,  1.60s/it, loss=0.00358, lr=1e-7]
Steps:  59%|█████▉    | 354/600 [11:50<06:38,  1.62s/it, loss=0.00358, lr=1e-7]
Steps:  59%|█████▉    | 354/600 [11:50<06:38,  1.62s/it, loss=0.146, lr=1e-7]  
Steps:  59%|█████▉    | 355/600 [11:52<06:38,  1.63s/it, loss=0.146, lr=1e-7]
Steps:  59%|█████▉    | 355/600 [11:52<06:38,  1.63s/it, loss=0.0926, lr=1e-7]
Steps:  59%|█████▉    | 356/600 [11:53<06:44,  1.66s/it, loss=0.0926, lr=1e-7]
Steps:  59%|█████▉    | 356/600 [11:53<06:44,  1.66s/it, loss=0.138, lr=1e-7] 
Steps:  60%|█████▉    | 357/600 [11:55<06:33,  1.62s/it, loss=0.138, lr=1e-7]
Steps:  60%|█████▉    | 357/600 [11:55<06:33,  1.62s/it, loss=0.269, lr=1e-7]
Steps:  60%|█████▉    | 358/600 [11:56<06:15,  1.55s/it, loss=0.269, lr=1e-7]
Steps:  60%|█████▉    | 358/600 [11:56<06:15,  1.55s/it, loss=0.157, lr=1e-7]
Steps:  60%|█████▉    | 359/600 [11:58<06:07,  1.53s/it, loss=0.157, lr=1e-7]
Steps:  60%|█████▉    | 359/600 [11:58<06:07,  1.53s/it, loss=0.171, lr=1e-7]
Steps:  60%|██████    | 360/600 [11:59<06:09,  1.54s/it, loss=0.171, lr=1e-7]
Steps:  60%|██████    | 360/600 [11:59<06:09,  1.54s/it, loss=0.0758, lr=1e-7]
Steps:  60%|██████    | 361/600 [12:01<06:15,  1.57s/it, loss=0.0758, lr=1e-7]
Steps:  60%|██████    | 361/600 [12:01<06:15,  1.57s/it, loss=0.0359, lr=1e-7]
Steps:  60%|██████    | 362/600 [12:02<05:49,  1.47s/it, loss=0.0359, lr=1e-7]
Steps:  60%|██████    | 362/600 [12:02<05:49,  1.47s/it, loss=0.114, lr=1e-7] 
Steps:  60%|██████    | 363/600 [12:03<04:56,  1.25s/it, loss=0.114, lr=1e-7]
Steps:  60%|██████    | 363/600 [12:03<04:56,  1.25s/it, loss=0.0127, lr=1e-7]
Steps:  61%|██████    | 364/600 [12:05<05:37,  1.43s/it, loss=0.0127, lr=1e-7]
Steps:  61%|██████    | 364/600 [12:05<05:37,  1.43s/it, loss=0.134, lr=1e-7] 
Steps:  61%|██████    | 365/600 [12:06<05:39,  1.44s/it, loss=0.134, lr=1e-7]
Steps:  61%|██████    | 365/600 [12:06<05:39,  1.44s/it, loss=0.0535, lr=1e-7]
Steps:  61%|██████    | 366/600 [12:08<05:57,  1.53s/it, loss=0.0535, lr=1e-7]
Steps:  61%|██████    | 366/600 [12:08<05:57,  1.53s/it, loss=0.0241, lr=1e-7]
Steps:  61%|██████    | 367/600 [12:10<06:06,  1.57s/it, loss=0.0241, lr=1e-7]
Steps:  61%|██████    | 367/600 [12:10<06:06,  1.57s/it, loss=0.0552, lr=1e-7]
Steps:  61%|██████▏   | 368/600 [12:12<06:20,  1.64s/it, loss=0.0552, lr=1e-7]
Steps:  61%|██████▏   | 368/600 [12:12<06:20,  1.64s/it, loss=0.0474, lr=1e-7]
Steps:  62%|██████▏   | 369/600 [12:13<06:26,  1.68s/it, loss=0.0474, lr=1e-7]
Steps:  62%|██████▏   | 369/600 [12:13<06:26,  1.68s/it, loss=0.16, lr=1e-7]  
Steps:  62%|██████▏   | 370/600 [12:15<06:06,  1.60s/it, loss=0.16, lr=1e-7]
Steps:  62%|██████▏   | 370/600 [12:15<06:06,  1.60s/it, loss=0.0938, lr=1e-7]
Steps:  62%|██████▏   | 371/600 [12:16<05:59,  1.57s/it, loss=0.0938, lr=1e-7]
Steps:  62%|██████▏   | 371/600 [12:16<05:59,  1.57s/it, loss=0.133, lr=1e-7] 
Steps:  62%|██████▏   | 372/600 [12:18<06:11,  1.63s/it, loss=0.133, lr=1e-7]
Steps:  62%|██████▏   | 372/600 [12:18<06:11,  1.63s/it, loss=0.00845, lr=1e-7]
Steps:  62%|██████▏   | 373/600 [12:19<05:42,  1.51s/it, loss=0.00845, lr=1e-7]
Steps:  62%|██████▏   | 373/600 [12:19<05:42,  1.51s/it, loss=0.0313, lr=1e-7] 
Steps:  62%|██████▏   | 374/600 [12:20<04:49,  1.28s/it, loss=0.0313, lr=1e-7]
Steps:  62%|██████▏   | 374/600 [12:20<04:49,  1.28s/it, loss=0.0269, lr=1e-7]
Steps:  62%|██████▎   | 375/600 [12:22<05:59,  1.60s/it, loss=0.0269, lr=1e-7]
Steps:  62%|██████▎   | 375/600 [12:22<05:59,  1.60s/it, loss=0.104, lr=1e-7] 
Steps:  63%|██████▎   | 376/600 [12:24<06:00,  1.61s/it, loss=0.104, lr=1e-7]
Steps:  63%|██████▎   | 376/600 [12:24<06:00,  1.61s/it, loss=0.107, lr=1e-7]
Steps:  63%|██████▎   | 377/600 [12:25<05:32,  1.49s/it, loss=0.107, lr=1e-7]
Steps:  63%|██████▎   | 377/600 [12:25<05:32,  1.49s/it, loss=0.152, lr=1e-7]
Steps:  63%|██████▎   | 378/600 [12:27<05:45,  1.56s/it, loss=0.152, lr=1e-7]
Steps:  63%|██████▎   | 378/600 [12:27<05:45,  1.56s/it, loss=0.131, lr=1e-7]
Steps:  63%|██████▎   | 379/600 [12:28<05:42,  1.55s/it, loss=0.131, lr=1e-7]
Steps:  63%|██████▎   | 379/600 [12:28<05:42,  1.55s/it, loss=0.244, lr=1e-7]
Steps:  63%|██████▎   | 380/600 [12:30<05:52,  1.60s/it, loss=0.244, lr=1e-7]
Steps:  63%|██████▎   | 380/600 [12:30<05:52,  1.60s/it, loss=0.11, lr=1e-7] 
Steps:  64%|██████▎   | 381/600 [12:32<05:45,  1.58s/it, loss=0.11, lr=1e-7]
Steps:  64%|██████▎   | 381/600 [12:32<05:45,  1.58s/it, loss=0.0224, lr=1e-7]
Steps:  64%|██████▎   | 382/600 [12:33<05:48,  1.60s/it, loss=0.0224, lr=1e-7]
Steps:  64%|██████▎   | 382/600 [12:33<05:48,  1.60s/it, loss=0.247, lr=1e-7] 
Steps:  64%|██████▍   | 383/600 [12:35<05:48,  1.61s/it, loss=0.247, lr=1e-7]
Steps:  64%|██████▍   | 383/600 [12:35<05:48,  1.61s/it, loss=0.0937, lr=1e-7]
Steps:  64%|██████▍   | 384/600 [12:36<05:22,  1.49s/it, loss=0.0937, lr=1e-7]
Steps:  64%|██████▍   | 384/600 [12:36<05:22,  1.49s/it, loss=0.0239, lr=1e-7]
Steps:  64%|██████▍   | 385/600 [12:37<04:32,  1.27s/it, loss=0.0239, lr=1e-7]
Steps:  64%|██████▍   | 385/600 [12:37<04:32,  1.27s/it, loss=0.231, lr=1e-7] 
Steps:  64%|██████▍   | 386/600 [12:39<05:40,  1.59s/it, loss=0.231, lr=1e-7]
Steps:  64%|██████▍   | 386/600 [12:39<05:40,  1.59s/it, loss=0.0097, lr=1e-7]
Steps:  64%|██████▍   | 387/600 [12:41<05:42,  1.61s/it, loss=0.0097, lr=1e-7]
Steps:  64%|██████▍   | 387/600 [12:41<05:42,  1.61s/it, loss=0.0839, lr=1e-7]
Steps:  65%|██████▍   | 388/600 [12:42<05:30,  1.56s/it, loss=0.0839, lr=1e-7]
Steps:  65%|██████▍   | 388/600 [12:42<05:30,  1.56s/it, loss=0.128, lr=1e-7] 
Steps:  65%|██████▍   | 389/600 [12:44<05:35,  1.59s/it, loss=0.128, lr=1e-7]
Steps:  65%|██████▍   | 389/600 [12:44<05:35,  1.59s/it, loss=0.0224, lr=1e-7]
Steps:  65%|██████▌   | 390/600 [12:46<05:30,  1.58s/it, loss=0.0224, lr=1e-7]
Steps:  65%|██████▌   | 390/600 [12:46<05:30,  1.58s/it, loss=0.261, lr=1e-7] 
Steps:  65%|██████▌   | 391/600 [12:47<05:27,  1.56s/it, loss=0.261, lr=1e-7]
Steps:  65%|██████▌   | 391/600 [12:47<05:27,  1.56s/it, loss=0.183, lr=1e-7]
Steps:  65%|██████▌   | 392/600 [12:49<05:30,  1.59s/it, loss=0.183, lr=1e-7]
Steps:  65%|██████▌   | 392/600 [12:49<05:30,  1.59s/it, loss=0.0269, lr=1e-7]
Steps:  66%|██████▌   | 393/600 [12:50<05:24,  1.57s/it, loss=0.0269, lr=1e-7]
Steps:  66%|██████▌   | 393/600 [12:50<05:24,  1.57s/it, loss=0.0502, lr=1e-7]
Steps:  66%|██████▌   | 394/600 [12:52<05:18,  1.54s/it, loss=0.0502, lr=1e-7]
Steps:  66%|██████▌   | 394/600 [12:52<05:18,  1.54s/it, loss=0.142, lr=1e-7] 
Steps:  66%|██████▌   | 395/600 [12:53<05:10,  1.51s/it, loss=0.142, lr=1e-7]
Steps:  66%|██████▌   | 395/600 [12:53<05:10,  1.51s/it, loss=0.271, lr=1e-7]
Steps:  66%|██████▌   | 396/600 [12:54<04:22,  1.29s/it, loss=0.271, lr=1e-7]
Steps:  66%|██████▌   | 396/600 [12:54<04:22,  1.29s/it, loss=0.213, lr=1e-7]
Steps:  66%|██████▌   | 397/600 [12:56<05:25,  1.60s/it, loss=0.213, lr=1e-7]
Steps:  66%|██████▌   | 397/600 [12:56<05:25,  1.60s/it, loss=0.00305, lr=1e-7]
Steps:  66%|██████▋   | 398/600 [12:58<05:12,  1.55s/it, loss=0.00305, lr=1e-7]
Steps:  66%|██████▋   | 398/600 [12:58<05:12,  1.55s/it, loss=0.0654, lr=1e-7] 
Steps:  66%|██████▋   | 399/600 [12:59<05:16,  1.57s/it, loss=0.0654, lr=1e-7]
Steps:  66%|██████▋   | 399/600 [12:59<05:16,  1.57s/it, loss=0.0379, lr=1e-7]
Steps:  67%|██████▋   | 400/600 [13:01<05:10,  1.55s/it, loss=0.0379, lr=1e-7]
Steps:  67%|██████▋   | 400/600 [13:01<05:10,  1.55s/it, loss=0.0721, lr=1e-7]
Steps:  67%|██████▋   | 401/600 [13:03<05:19,  1.61s/it, loss=0.0721, lr=1e-7]
Steps:  67%|██████▋   | 401/600 [13:03<05:19,  1.61s/it, loss=0.041, lr=1e-7] 
Steps:  67%|██████▋   | 402/600 [13:04<05:15,  1.59s/it, loss=0.041, lr=1e-7]
Steps:  67%|██████▋   | 402/600 [13:04<05:15,  1.59s/it, loss=0.153, lr=1e-7]
Steps:  67%|██████▋   | 403/600 [13:06<05:12,  1.59s/it, loss=0.153, lr=1e-7]
Steps:  67%|██████▋   | 403/600 [13:06<05:12,  1.59s/it, loss=0.0685, lr=1e-7]
Steps:  67%|██████▋   | 404/600 [13:07<05:11,  1.59s/it, loss=0.0685, lr=1e-7]
Steps:  67%|██████▋   | 404/600 [13:07<05:11,  1.59s/it, loss=0.196, lr=1e-7] 
Steps:  68%|██████▊   | 405/600 [13:09<05:16,  1.62s/it, loss=0.196, lr=1e-7]
Steps:  68%|██████▊   | 405/600 [13:09<05:16,  1.62s/it, loss=0.227, lr=1e-7]
Steps:  68%|██████▊   | 406/600 [13:10<04:55,  1.52s/it, loss=0.227, lr=1e-7]
Steps:  68%|██████▊   | 406/600 [13:10<04:55,  1.52s/it, loss=0.197, lr=1e-7]
Steps:  68%|██████▊   | 407/600 [13:11<04:09,  1.29s/it, loss=0.197, lr=1e-7]
Steps:  68%|██████▊   | 407/600 [13:11<04:09,  1.29s/it, loss=0.0103, lr=1e-7]
Steps:  68%|██████▊   | 408/600 [13:13<04:48,  1.50s/it, loss=0.0103, lr=1e-7]
Steps:  68%|██████▊   | 408/600 [13:13<04:48,  1.50s/it, loss=0.0725, lr=1e-7]
Steps:  68%|██████▊   | 409/600 [13:15<04:55,  1.55s/it, loss=0.0725, lr=1e-7]
Steps:  68%|██████▊   | 409/600 [13:15<04:55,  1.55s/it, loss=0.247, lr=1e-7] 
Steps:  68%|██████▊   | 410/600 [13:16<04:48,  1.52s/it, loss=0.247, lr=1e-7]
Steps:  68%|██████▊   | 410/600 [13:16<04:48,  1.52s/it, loss=0.133, lr=1e-7]
Steps:  68%|██████▊   | 411/600 [13:18<05:07,  1.63s/it, loss=0.133, lr=1e-7]
Steps:  68%|██████▊   | 411/600 [13:18<05:07,  1.63s/it, loss=0.135, lr=1e-7]
Steps:  69%|██████▊   | 412/600 [13:20<05:04,  1.62s/it, loss=0.135, lr=1e-7]
Steps:  69%|██████▊   | 412/600 [13:20<05:04,  1.62s/it, loss=0.205, lr=1e-7]
Steps:  69%|██████▉   | 413/600 [13:21<05:05,  1.63s/it, loss=0.205, lr=1e-7]
Steps:  69%|██████▉   | 413/600 [13:21<05:05,  1.63s/it, loss=0.0224, lr=1e-7]
Steps:  69%|██████▉   | 414/600 [13:23<05:01,  1.62s/it, loss=0.0224, lr=1e-7]
Steps:  69%|██████▉   | 414/600 [13:23<05:01,  1.62s/it, loss=0.00685, lr=1e-7]
Steps:  69%|██████▉   | 415/600 [13:24<04:45,  1.54s/it, loss=0.00685, lr=1e-7]
Steps:  69%|██████▉   | 415/600 [13:24<04:45,  1.54s/it, loss=0.103, lr=1e-7]  
Steps:  69%|██████▉   | 416/600 [13:26<04:42,  1.54s/it, loss=0.103, lr=1e-7]
Steps:  69%|██████▉   | 416/600 [13:26<04:42,  1.54s/it, loss=0.092, lr=1e-7]
Steps:  70%|██████▉   | 417/600 [13:27<04:37,  1.52s/it, loss=0.092, lr=1e-7]
Steps:  70%|██████▉   | 417/600 [13:27<04:37,  1.52s/it, loss=0.166, lr=1e-7]
Steps:  70%|██████▉   | 418/600 [13:28<03:54,  1.29s/it, loss=0.166, lr=1e-7]
Steps:  70%|██████▉   | 418/600 [13:28<03:54,  1.29s/it, loss=0.041, lr=1e-7]
Steps:  70%|██████▉   | 419/600 [13:30<04:42,  1.56s/it, loss=0.041, lr=1e-7]
Steps:  70%|██████▉   | 419/600 [13:30<04:42,  1.56s/it, loss=0.042, lr=1e-7]
Steps:  70%|███████   | 420/600 [13:32<04:45,  1.59s/it, loss=0.042, lr=1e-7]
Steps:  70%|███████   | 420/600 [13:32<04:45,  1.59s/it, loss=0.015, lr=1e-7]
Steps:  70%|███████   | 421/600 [13:33<04:46,  1.60s/it, loss=0.015, lr=1e-7]
Steps:  70%|███████   | 421/600 [13:33<04:46,  1.60s/it, loss=0.0738, lr=1e-7]
Steps:  70%|███████   | 422/600 [13:35<04:32,  1.53s/it, loss=0.0738, lr=1e-7]
Steps:  70%|███████   | 422/600 [13:35<04:32,  1.53s/it, loss=0.313, lr=1e-7] 
Steps:  70%|███████   | 423/600 [13:37<04:47,  1.62s/it, loss=0.313, lr=1e-7]
Steps:  70%|███████   | 423/600 [13:37<04:47,  1.62s/it, loss=0.152, lr=1e-7]
Steps:  71%|███████   | 424/600 [13:38<04:36,  1.57s/it, loss=0.152, lr=1e-7]
Steps:  71%|███████   | 424/600 [13:38<04:36,  1.57s/it, loss=0.18, lr=1e-7] 
Steps:  71%|███████   | 425/600 [13:40<04:29,  1.54s/it, loss=0.18, lr=1e-7]
Steps:  71%|███████   | 425/600 [13:40<04:29,  1.54s/it, loss=0.129, lr=1e-7]
Steps:  71%|███████   | 426/600 [13:41<04:40,  1.61s/it, loss=0.129, lr=1e-7]
Steps:  71%|███████   | 426/600 [13:41<04:40,  1.61s/it, loss=0.0304, lr=1e-7]
Steps:  71%|███████   | 427/600 [13:43<04:47,  1.66s/it, loss=0.0304, lr=1e-7]
Steps:  71%|███████   | 427/600 [13:43<04:47,  1.66s/it, loss=0.216, lr=1e-7] 
Steps:  71%|███████▏  | 428/600 [13:44<04:18,  1.50s/it, loss=0.216, lr=1e-7]
Steps:  71%|███████▏  | 428/600 [13:44<04:18,  1.50s/it, loss=0.0218, lr=1e-7]
Steps:  72%|███████▏  | 429/600 [13:45<03:39,  1.28s/it, loss=0.0218, lr=1e-7]
Steps:  72%|███████▏  | 429/600 [13:45<03:39,  1.28s/it, loss=0.254, lr=1e-7] 
Steps:  72%|███████▏  | 430/600 [13:47<04:20,  1.53s/it, loss=0.254, lr=1e-7]
Steps:  72%|███████▏  | 430/600 [13:47<04:20,  1.53s/it, loss=0.115, lr=1e-7]
Steps:  72%|███████▏  | 431/600 [13:49<04:30,  1.60s/it, loss=0.115, lr=1e-7]
Steps:  72%|███████▏  | 431/600 [13:49<04:30,  1.60s/it, loss=0.172, lr=1e-7]
Steps:  72%|███████▏  | 432/600 [13:50<04:22,  1.56s/it, loss=0.172, lr=1e-7]
Steps:  72%|███████▏  | 432/600 [13:50<04:22,  1.56s/it, loss=0.118, lr=1e-7]
Steps:  72%|███████▏  | 433/600 [13:52<04:25,  1.59s/it, loss=0.118, lr=1e-7]
Steps:  72%|███████▏  | 433/600 [13:52<04:25,  1.59s/it, loss=0.0482, lr=1e-7]
Steps:  72%|███████▏  | 434/600 [13:54<04:34,  1.65s/it, loss=0.0482, lr=1e-7]
Steps:  72%|███████▏  | 434/600 [13:54<04:34,  1.65s/it, loss=0.0211, lr=1e-7]
Steps:  72%|███████▎  | 435/600 [13:55<04:25,  1.61s/it, loss=0.0211, lr=1e-7]
Steps:  72%|███████▎  | 435/600 [13:55<04:25,  1.61s/it, loss=0.132, lr=1e-7] 
Steps:  73%|███████▎  | 436/600 [13:57<04:15,  1.56s/it, loss=0.132, lr=1e-7]
Steps:  73%|███████▎  | 436/600 [13:57<04:15,  1.56s/it, loss=0.0407, lr=1e-7]
Steps:  73%|███████▎  | 437/600 [13:58<04:19,  1.59s/it, loss=0.0407, lr=1e-7]
Steps:  73%|███████▎  | 437/600 [13:58<04:19,  1.59s/it, loss=0.0828, lr=1e-7]
Steps:  73%|███████▎  | 438/600 [14:00<04:13,  1.56s/it, loss=0.0828, lr=1e-7]
Steps:  73%|███████▎  | 438/600 [14:00<04:13,  1.56s/it, loss=0.0511, lr=1e-7]
Steps:  73%|███████▎  | 439/600 [14:01<04:00,  1.49s/it, loss=0.0511, lr=1e-7]
Steps:  73%|███████▎  | 439/600 [14:01<04:00,  1.49s/it, loss=0.0292, lr=1e-7]
Steps:  73%|███████▎  | 440/600 [14:02<03:23,  1.27s/it, loss=0.0292, lr=1e-7]
Steps:  73%|███████▎  | 440/600 [14:02<03:23,  1.27s/it, loss=0.032, lr=1e-7] 
Steps:  74%|███████▎  | 441/600 [14:04<04:12,  1.59s/it, loss=0.032, lr=1e-7]
Steps:  74%|███████▎  | 441/600 [14:04<04:12,  1.59s/it, loss=0.161, lr=1e-7]
Steps:  74%|███████▎  | 442/600 [14:06<04:18,  1.64s/it, loss=0.161, lr=1e-7]
Steps:  74%|███████▎  | 442/600 [14:06<04:18,  1.64s/it, loss=0.0413, lr=1e-7]
Steps:  74%|███████▍  | 443/600 [14:07<04:05,  1.56s/it, loss=0.0413, lr=1e-7]
Steps:  74%|███████▍  | 443/600 [14:07<04:05,  1.56s/it, loss=0.154, lr=1e-7] 
Steps:  74%|███████▍  | 444/600 [14:09<04:06,  1.58s/it, loss=0.154, lr=1e-7]
Steps:  74%|███████▍  | 444/600 [14:09<04:06,  1.58s/it, loss=0.0941, lr=1e-7]
Steps:  74%|███████▍  | 445/600 [14:11<04:10,  1.61s/it, loss=0.0941, lr=1e-7]
Steps:  74%|███████▍  | 445/600 [14:11<04:10,  1.61s/it, loss=0.0115, lr=1e-7]
Steps:  74%|███████▍  | 446/600 [14:12<04:02,  1.58s/it, loss=0.0115, lr=1e-7]
Steps:  74%|███████▍  | 446/600 [14:12<04:02,  1.58s/it, loss=0.157, lr=1e-7] 
Steps:  74%|███████▍  | 447/600 [14:14<04:02,  1.58s/it, loss=0.157, lr=1e-7]
Steps:  74%|███████▍  | 447/600 [14:14<04:02,  1.58s/it, loss=0.0723, lr=1e-7]
Steps:  75%|███████▍  | 448/600 [14:15<04:02,  1.59s/it, loss=0.0723, lr=1e-7]
Steps:  75%|███████▍  | 448/600 [14:15<04:02,  1.59s/it, loss=0.0458, lr=1e-7]
Steps:  75%|███████▍  | 449/600 [14:17<04:02,  1.60s/it, loss=0.0458, lr=1e-7]
Steps:  75%|███████▍  | 449/600 [14:17<04:02,  1.60s/it, loss=0.0963, lr=1e-7]
Steps:  75%|███████▌  | 450/600 [14:19<03:51,  1.54s/it, loss=0.0963, lr=1e-7]
Steps:  75%|███████▌  | 450/600 [14:19<03:51,  1.54s/it, loss=0.00933, lr=1e-7]
Steps:  75%|███████▌  | 451/600 [14:19<03:14,  1.31s/it, loss=0.00933, lr=1e-7]
Steps:  75%|███████▌  | 451/600 [14:19<03:14,  1.31s/it, loss=0.25, lr=1e-7]   
Steps:  75%|███████▌  | 452/600 [14:22<04:03,  1.64s/it, loss=0.25, lr=1e-7]
Steps:  75%|███████▌  | 452/600 [14:22<04:03,  1.64s/it, loss=0.016, lr=1e-7]
Steps:  76%|███████▌  | 453/600 [14:23<03:57,  1.62s/it, loss=0.016, lr=1e-7]
Steps:  76%|███████▌  | 453/600 [14:23<03:57,  1.62s/it, loss=0.101, lr=1e-7]
Steps:  76%|███████▌  | 454/600 [14:25<03:50,  1.58s/it, loss=0.101, lr=1e-7]
Steps:  76%|███████▌  | 454/600 [14:25<03:50,  1.58s/it, loss=0.0537, lr=1e-7]
Steps:  76%|███████▌  | 455/600 [14:26<03:44,  1.55s/it, loss=0.0537, lr=1e-7]
Steps:  76%|███████▌  | 455/600 [14:26<03:44,  1.55s/it, loss=0.167, lr=1e-7] 
Steps:  76%|███████▌  | 456/600 [14:28<03:42,  1.54s/it, loss=0.167, lr=1e-7]
Steps:  76%|███████▌  | 456/600 [14:28<03:42,  1.54s/it, loss=0.137, lr=1e-7]
Steps:  76%|███████▌  | 457/600 [14:29<03:39,  1.53s/it, loss=0.137, lr=1e-7]
Steps:  76%|███████▌  | 457/600 [14:29<03:39,  1.53s/it, loss=0.122, lr=1e-7]
Steps:  76%|███████▋  | 458/600 [14:31<03:48,  1.61s/it, loss=0.122, lr=1e-7]
Steps:  76%|███████▋  | 458/600 [14:31<03:48,  1.61s/it, loss=0.0996, lr=1e-7]
Steps:  76%|███████▋  | 459/600 [14:32<03:29,  1.49s/it, loss=0.0996, lr=1e-7]
Steps:  76%|███████▋  | 459/600 [14:32<03:29,  1.49s/it, loss=0.178, lr=1e-7] 
Steps:  77%|███████▋  | 460/600 [14:34<03:42,  1.59s/it, loss=0.178, lr=1e-7]
Steps:  77%|███████▋  | 460/600 [14:34<03:42,  1.59s/it, loss=0.00747, lr=1e-7]
Steps:  77%|███████▋  | 461/600 [14:35<03:32,  1.53s/it, loss=0.00747, lr=1e-7]
Steps:  77%|███████▋  | 461/600 [14:35<03:32,  1.53s/it, loss=0.14, lr=1e-7]   
Steps:  77%|███████▋  | 462/600 [14:36<02:58,  1.30s/it, loss=0.14, lr=1e-7]
Steps:  77%|███████▋  | 462/600 [14:36<02:58,  1.30s/it, loss=0.00319, lr=1e-7]
Steps:  77%|███████▋  | 463/600 [14:39<03:40,  1.61s/it, loss=0.00319, lr=1e-7]
Steps:  77%|███████▋  | 463/600 [14:39<03:40,  1.61s/it, loss=0.0316, lr=1e-7] 
Steps:  77%|███████▋  | 464/600 [14:40<03:41,  1.63s/it, loss=0.0316, lr=1e-7]
Steps:  77%|███████▋  | 464/600 [14:40<03:41,  1.63s/it, loss=0.144, lr=1e-7] 
Steps:  78%|███████▊  | 465/600 [14:42<03:26,  1.53s/it, loss=0.144, lr=1e-7]
Steps:  78%|███████▊  | 465/600 [14:42<03:26,  1.53s/it, loss=0.015, lr=1e-7]
Steps:  78%|███████▊  | 466/600 [14:43<03:24,  1.52s/it, loss=0.015, lr=1e-7]
Steps:  78%|███████▊  | 466/600 [14:43<03:24,  1.52s/it, loss=0.21, lr=1e-7] 
Steps:  78%|███████▊  | 467/600 [14:45<03:27,  1.56s/it, loss=0.21, lr=1e-7]
Steps:  78%|███████▊  | 467/600 [14:45<03:27,  1.56s/it, loss=0.0163, lr=1e-7]
Steps:  78%|███████▊  | 468/600 [14:46<03:24,  1.55s/it, loss=0.0163, lr=1e-7]
Steps:  78%|███████▊  | 468/600 [14:46<03:24,  1.55s/it, loss=0.00439, lr=1e-7]
Steps:  78%|███████▊  | 469/600 [14:48<03:19,  1.52s/it, loss=0.00439, lr=1e-7]
Steps:  78%|███████▊  | 469/600 [14:48<03:19,  1.52s/it, loss=0.114, lr=1e-7]  
Steps:  78%|███████▊  | 470/600 [14:49<03:24,  1.58s/it, loss=0.114, lr=1e-7]
Steps:  78%|███████▊  | 470/600 [14:49<03:24,  1.58s/it, loss=0.017, lr=1e-7]
Steps:  78%|███████▊  | 471/600 [14:51<03:32,  1.64s/it, loss=0.017, lr=1e-7]
Steps:  78%|███████▊  | 471/600 [14:51<03:32,  1.64s/it, loss=0.0768, lr=1e-7]
Steps:  79%|███████▊  | 472/600 [14:52<03:13,  1.52s/it, loss=0.0768, lr=1e-7]
Steps:  79%|███████▊  | 472/600 [14:52<03:13,  1.52s/it, loss=0.0396, lr=1e-7]
Steps:  79%|███████▉  | 473/600 [14:53<02:43,  1.29s/it, loss=0.0396, lr=1e-7]
Steps:  79%|███████▉  | 473/600 [14:53<02:43,  1.29s/it, loss=0.121, lr=1e-7] 
Steps:  79%|███████▉  | 474/600 [14:55<03:19,  1.58s/it, loss=0.121, lr=1e-7]
Steps:  79%|███████▉  | 474/600 [14:55<03:19,  1.58s/it, loss=0.204, lr=1e-7]
Steps:  79%|███████▉  | 475/600 [14:57<03:10,  1.52s/it, loss=0.204, lr=1e-7]
Steps:  79%|███████▉  | 475/600 [14:57<03:10,  1.52s/it, loss=0.189, lr=1e-7]
Steps:  79%|███████▉  | 476/600 [14:58<03:01,  1.46s/it, loss=0.189, lr=1e-7]
Steps:  79%|███████▉  | 476/600 [14:58<03:01,  1.46s/it, loss=0.137, lr=1e-7]
Steps:  80%|███████▉  | 477/600 [15:00<03:02,  1.48s/it, loss=0.137, lr=1e-7]
Steps:  80%|███████▉  | 477/600 [15:00<03:02,  1.48s/it, loss=0.0472, lr=1e-7]
Steps:  80%|███████▉  | 478/600 [15:01<03:07,  1.54s/it, loss=0.0472, lr=1e-7]
Steps:  80%|███████▉  | 478/600 [15:01<03:07,  1.54s/it, loss=0.0106, lr=1e-7]
Steps:  80%|███████▉  | 479/600 [15:03<03:18,  1.64s/it, loss=0.0106, lr=1e-7]
Steps:  80%|███████▉  | 479/600 [15:03<03:18,  1.64s/it, loss=0.165, lr=1e-7] 
Steps:  80%|████████  | 480/600 [15:05<03:10,  1.58s/it, loss=0.165, lr=1e-7]
Steps:  80%|████████  | 480/600 [15:05<03:10,  1.58s/it, loss=0.0247, lr=1e-7]
Steps:  80%|████████  | 481/600 [15:06<03:14,  1.63s/it, loss=0.0247, lr=1e-7]
Steps:  80%|████████  | 481/600 [15:06<03:14,  1.63s/it, loss=0.144, lr=1e-7] 
Steps:  80%|████████  | 482/600 [15:08<03:12,  1.63s/it, loss=0.144, lr=1e-7]
Steps:  80%|████████  | 482/600 [15:08<03:12,  1.63s/it, loss=0.0659, lr=1e-7]
Steps:  80%|████████  | 483/600 [15:09<03:04,  1.57s/it, loss=0.0659, lr=1e-7]
Steps:  80%|████████  | 483/600 [15:09<03:04,  1.57s/it, loss=0.00861, lr=1e-7]
Steps:  81%|████████  | 484/600 [15:10<02:34,  1.33s/it, loss=0.00861, lr=1e-7]
Steps:  81%|████████  | 484/600 [15:10<02:34,  1.33s/it, loss=0.12, lr=1e-7]   
Steps:  81%|████████  | 485/600 [15:12<03:05,  1.61s/it, loss=0.12, lr=1e-7]
Steps:  81%|████████  | 485/600 [15:12<03:05,  1.61s/it, loss=0.0176, lr=1e-7]
Steps:  81%|████████  | 486/600 [15:14<03:00,  1.58s/it, loss=0.0176, lr=1e-7]
Steps:  81%|████████  | 486/600 [15:14<03:00,  1.58s/it, loss=0.0405, lr=1e-7]
Steps:  81%|████████  | 487/600 [15:16<03:05,  1.64s/it, loss=0.0405, lr=1e-7]
Steps:  81%|████████  | 487/600 [15:16<03:05,  1.64s/it, loss=0.0942, lr=1e-7]
Steps:  81%|████████▏ | 488/600 [15:18<03:08,  1.68s/it, loss=0.0942, lr=1e-7]
Steps:  81%|████████▏ | 488/600 [15:18<03:08,  1.68s/it, loss=0.0943, lr=1e-7]
Steps:  82%|████████▏ | 489/600 [15:19<02:54,  1.57s/it, loss=0.0943, lr=1e-7]
Steps:  82%|████████▏ | 489/600 [15:19<02:54,  1.57s/it, loss=0.0725, lr=1e-7]
Steps:  82%|████████▏ | 490/600 [15:21<02:54,  1.59s/it, loss=0.0725, lr=1e-7]
Steps:  82%|████████▏ | 490/600 [15:21<02:54,  1.59s/it, loss=0.289, lr=1e-7] 
Steps:  82%|████████▏ | 491/600 [15:22<02:45,  1.52s/it, loss=0.289, lr=1e-7]
Steps:  82%|████████▏ | 491/600 [15:22<02:45,  1.52s/it, loss=0.389, lr=1e-7]
Steps:  82%|████████▏ | 492/600 [15:23<02:41,  1.49s/it, loss=0.389, lr=1e-7]
Steps:  82%|████████▏ | 492/600 [15:23<02:41,  1.49s/it, loss=0.0212, lr=1e-7]
Steps:  82%|████████▏ | 493/600 [15:25<02:45,  1.55s/it, loss=0.0212, lr=1e-7]
Steps:  82%|████████▏ | 493/600 [15:25<02:45,  1.55s/it, loss=0.0905, lr=1e-7]
Steps:  82%|████████▏ | 494/600 [15:26<02:40,  1.52s/it, loss=0.0905, lr=1e-7]
Steps:  82%|████████▏ | 494/600 [15:26<02:40,  1.52s/it, loss=0.102, lr=1e-7] 
Steps:  82%|████████▎ | 495/600 [15:27<02:15,  1.29s/it, loss=0.102, lr=1e-7]
Steps:  82%|████████▎ | 495/600 [15:27<02:15,  1.29s/it, loss=0.114, lr=1e-7]
Steps:  83%|████████▎ | 496/600 [15:30<02:46,  1.60s/it, loss=0.114, lr=1e-7]
Steps:  83%|████████�� | 496/600 [15:30<02:46,  1.60s/it, loss=0.24, lr=1e-7] 
Steps:  83%|████████▎ | 497/600 [15:31<02:50,  1.65s/it, loss=0.24, lr=1e-7]
Steps:  83%|████████▎ | 497/600 [15:31<02:50,  1.65s/it, loss=0.208, lr=1e-7]
Steps:  83%|████████▎ | 498/600 [15:33<02:43,  1.61s/it, loss=0.208, lr=1e-7]
Steps:  83%|████████▎ | 498/600 [15:33<02:43,  1.61s/it, loss=0.0552, lr=1e-7]
Steps:  83%|████████▎ | 499/600 [15:34<02:37,  1.56s/it, loss=0.0552, lr=1e-7]
Steps:  83%|████████▎ | 499/600 [15:34<02:37,  1.56s/it, loss=0.174, lr=1e-7] 
Steps:  83%|████████▎ | 500/600 [15:36<02:34,  1.55s/it, loss=0.174, lr=1e-7]10/13/2023 11:09:23 - INFO - accelerate.accelerator - Saving current state to logs/sweep_final_3_20231013105322/checkpoint-500
+Model weights saved in logs/sweep_final_3_20231013105322/checkpoint-500/pytorch_lora_weights.safetensors
+10/13/2023 11:09:24 - INFO - accelerate.checkpointing - Optimizer state saved in logs/sweep_final_3_20231013105322/checkpoint-500/optimizer.bin
+10/13/2023 11:09:24 - INFO - accelerate.checkpointing - Scheduler state saved in logs/sweep_final_3_20231013105322/checkpoint-500/scheduler.bin
+10/13/2023 11:09:24 - INFO - accelerate.checkpointing - Gradient scaler state saved in logs/sweep_final_3_20231013105322/checkpoint-500/scaler.pt
+10/13/2023 11:09:24 - INFO - accelerate.checkpointing - Random states saved in logs/sweep_final_3_20231013105322/checkpoint-500/random_states_0.pkl
+10/13/2023 11:09:24 - INFO - __main__ - Saved state to logs/sweep_final_3_20231013105322/checkpoint-500
+
Steps:  83%|████████▎ | 500/600 [15:37<02:34,  1.55s/it, loss=0.00537, lr=1e-7]
Steps:  84%|████████▎ | 501/600 [15:38<03:07,  1.89s/it, loss=0.00537, lr=1e-7]
Steps:  84%|████████▎ | 501/600 [15:38<03:07,  1.89s/it, loss=0.0984, lr=1e-7] 
Steps:  84%|████████▎ | 502/600 [15:40<02:52,  1.76s/it, loss=0.0984, lr=1e-7]
Steps:  84%|████████▎ | 502/600 [15:40<02:52,  1.76s/it, loss=0.261, lr=1e-7] 
Steps:  84%|████████▍ | 503/600 [15:42<02:52,  1.78s/it, loss=0.261, lr=1e-7]
Steps:  84%|████████▍ | 503/600 [15:42<02:52,  1.78s/it, loss=0.107, lr=1e-7]
Steps:  84%|████████▍ | 504/600 [15:43<02:45,  1.72s/it, loss=0.107, lr=1e-7]
Steps:  84%|████████▍ | 504/600 [15:43<02:45,  1.72s/it, loss=0.027, lr=1e-7]
Steps:  84%|████████▍ | 505/600 [15:44<02:26,  1.54s/it, loss=0.027, lr=1e-7]
Steps:  84%|████████▍ | 505/600 [15:44<02:26,  1.54s/it, loss=0.156, lr=1e-7]
Steps:  84%|████████▍ | 506/600 [15:45<02:02,  1.31s/it, loss=0.156, lr=1e-7]
Steps:  84%|████████▍ | 506/600 [15:45<02:02,  1.31s/it, loss=0.0114, lr=1e-7]
Steps:  84%|████████▍ | 507/600 [15:47<02:24,  1.55s/it, loss=0.0114, lr=1e-7]
Steps:  84%|████████▍ | 507/600 [15:47<02:24,  1.55s/it, loss=0.0208, lr=1e-7]
Steps:  85%|████████▍ | 508/600 [15:49<02:24,  1.57s/it, loss=0.0208, lr=1e-7]
Steps:  85%|████████▍ | 508/600 [15:49<02:24,  1.57s/it, loss=0.14, lr=1e-7]  
Steps:  85%|████████▍ | 509/600 [15:50<02:22,  1.57s/it, loss=0.14, lr=1e-7]
Steps:  85%|████████▍ | 509/600 [15:50<02:22,  1.57s/it, loss=0.147, lr=1e-7]
Steps:  85%|████████▌ | 510/600 [15:52<02:19,  1.55s/it, loss=0.147, lr=1e-7]
Steps:  85%|████████▌ | 510/600 [15:52<02:19,  1.55s/it, loss=0.0364, lr=1e-7]
Steps:  85%|████████▌ | 511/600 [15:54<02:17,  1.54s/it, loss=0.0364, lr=1e-7]
Steps:  85%|████████▌ | 511/600 [15:54<02:17,  1.54s/it, loss=0.0342, lr=1e-7]
Steps:  85%|████████▌ | 512/600 [15:55<02:17,  1.57s/it, loss=0.0342, lr=1e-7]
Steps:  85%|████████▌ | 512/600 [15:55<02:17,  1.57s/it, loss=0.316, lr=1e-7] 
Steps:  86%|████████▌ | 513/600 [15:57<02:18,  1.59s/it, loss=0.316, lr=1e-7]
Steps:  86%|████████▌ | 513/600 [15:57<02:18,  1.59s/it, loss=0.124, lr=1e-7]
Steps:  86%|████████▌ | 514/600 [15:58<02:19,  1.62s/it, loss=0.124, lr=1e-7]
Steps:  86%|████████▌ | 514/600 [15:58<02:19,  1.62s/it, loss=0.00831, lr=1e-7]
Steps:  86%|████████▌ | 515/600 [16:00<02:18,  1.63s/it, loss=0.00831, lr=1e-7]
Steps:  86%|████████▌ | 515/600 [16:00<02:18,  1.63s/it, loss=0.189, lr=1e-7]  
Steps:  86%|████████▌ | 516/600 [16:01<02:08,  1.53s/it, loss=0.189, lr=1e-7]
Steps:  86%|████████▌ | 516/600 [16:01<02:08,  1.53s/it, loss=0.229, lr=1e-7]
Steps:  86%|████████▌ | 517/600 [16:02<01:47,  1.30s/it, loss=0.229, lr=1e-7]
Steps:  86%|████████▌ | 517/600 [16:02<01:47,  1.30s/it, loss=0.00359, lr=1e-7]
Steps:  86%|████████▋ | 518/600 [16:04<02:04,  1.52s/it, loss=0.00359, lr=1e-7]
Steps:  86%|████████▋ | 518/600 [16:04<02:04,  1.52s/it, loss=0.201, lr=1e-7]  
Steps:  86%|████████▋ | 519/600 [16:06<02:03,  1.53s/it, loss=0.201, lr=1e-7]
Steps:  86%|████████▋ | 519/600 [16:06<02:03,  1.53s/it, loss=0.151, lr=1e-7]
Steps:  87%|████████▋ | 520/600 [16:07<02:01,  1.52s/it, loss=0.151, lr=1e-7]
Steps:  87%|████████▋ | 520/600 [16:07<02:01,  1.52s/it, loss=0.0265, lr=1e-7]
Steps:  87%|████████▋ | 521/600 [16:09<02:04,  1.58s/it, loss=0.0265, lr=1e-7]
Steps:  87%|████████▋ | 521/600 [16:09<02:04,  1.58s/it, loss=0.005, lr=1e-7] 
Steps:  87%|████████▋ | 522/600 [16:11<02:05,  1.61s/it, loss=0.005, lr=1e-7]
Steps:  87%|████████▋ | 522/600 [16:11<02:05,  1.61s/it, loss=0.0467, lr=1e-7]
Steps:  87%|████████▋ | 523/600 [16:12<02:09,  1.68s/it, loss=0.0467, lr=1e-7]
Steps:  87%|████████▋ | 523/600 [16:12<02:09,  1.68s/it, loss=0.285, lr=1e-7] 
Steps:  87%|████████▋ | 524/600 [16:14<02:03,  1.63s/it, loss=0.285, lr=1e-7]
Steps:  87%|████████▋ | 524/600 [16:14<02:03,  1.63s/it, loss=0.146, lr=1e-7]
Steps:  88%|████████▊ | 525/600 [16:15<01:58,  1.58s/it, loss=0.146, lr=1e-7]
Steps:  88%|████████▊ | 525/600 [16:15<01:58,  1.58s/it, loss=0.046, lr=1e-7]
Steps:  88%|████████▊ | 526/600 [16:17<01:55,  1.56s/it, loss=0.046, lr=1e-7]
Steps:  88%|████████▊ | 526/600 [16:17<01:55,  1.56s/it, loss=0.00622, lr=1e-7]
Steps:  88%|████████▊ | 527/600 [16:18<01:49,  1.51s/it, loss=0.00622, lr=1e-7]
Steps:  88%|████████▊ | 527/600 [16:18<01:49,  1.51s/it, loss=0.0547, lr=1e-7] 
Steps:  88%|████████▊ | 528/600 [16:19<01:32,  1.28s/it, loss=0.0547, lr=1e-7]
Steps:  88%|████████▊ | 528/600 [16:19<01:32,  1.28s/it, loss=0.333, lr=1e-7] 
Steps:  88%|████████▊ | 529/600 [16:21<01:50,  1.56s/it, loss=0.333, lr=1e-7]
Steps:  88%|████████▊ | 529/600 [16:21<01:50,  1.56s/it, loss=0.136, lr=1e-7]
Steps:  88%|████████▊ | 530/600 [16:23<01:48,  1.55s/it, loss=0.136, lr=1e-7]
Steps:  88%|████████▊ | 530/600 [16:23<01:48,  1.55s/it, loss=0.022, lr=1e-7]
Steps:  88%|████████▊ | 531/600 [16:25<01:52,  1.63s/it, loss=0.022, lr=1e-7]
Steps:  88%|████████▊ | 531/600 [16:25<01:52,  1.63s/it, loss=0.135, lr=1e-7]
Steps:  89%|████████▊ | 532/600 [16:27<01:55,  1.70s/it, loss=0.135, lr=1e-7]
Steps:  89%|████████▊ | 532/600 [16:27<01:55,  1.70s/it, loss=0.147, lr=1e-7]
Steps:  89%|████████▉ | 533/600 [16:28<01:51,  1.66s/it, loss=0.147, lr=1e-7]
Steps:  89%|████████▉ | 533/600 [16:28<01:51,  1.66s/it, loss=0.0377, lr=1e-7]
Steps:  89%|████████▉ | 534/600 [16:30<01:46,  1.62s/it, loss=0.0377, lr=1e-7]
Steps:  89%|████████▉ | 534/600 [16:30<01:46,  1.62s/it, loss=0.0641, lr=1e-7]
Steps:  89%|████████▉ | 535/600 [16:31<01:40,  1.55s/it, loss=0.0641, lr=1e-7]
Steps:  89%|████████▉ | 535/600 [16:31<01:40,  1.55s/it, loss=0.143, lr=1e-7] 
Steps:  89%|████████▉ | 536/600 [16:33<01:43,  1.61s/it, loss=0.143, lr=1e-7]
Steps:  89%|████████▉ | 536/600 [16:33<01:43,  1.61s/it, loss=0.225, lr=1e-7]
Steps:  90%|████████▉ | 537/600 [16:34<01:34,  1.50s/it, loss=0.225, lr=1e-7]
Steps:  90%|████████▉ | 537/600 [16:34<01:34,  1.50s/it, loss=0.107, lr=1e-7]
Steps:  90%|████████▉ | 538/600 [16:35<01:29,  1.44s/it, loss=0.107, lr=1e-7]
Steps:  90%|████████▉ | 538/600 [16:35<01:29,  1.44s/it, loss=0.271, lr=1e-7]
Steps:  90%|████████▉ | 539/600 [16:36<01:15,  1.23s/it, loss=0.271, lr=1e-7]
Steps:  90%|████████▉ | 539/600 [16:36<01:15,  1.23s/it, loss=0.28, lr=1e-7] 
Steps:  90%|█████████ | 540/600 [16:38<01:29,  1.49s/it, loss=0.28, lr=1e-7]
Steps:  90%|█████████ | 540/600 [16:38<01:29,  1.49s/it, loss=0.0145, lr=1e-7]
Steps:  90%|█████████ | 541/600 [16:40<01:31,  1.56s/it, loss=0.0145, lr=1e-7]
Steps:  90%|█████████ | 541/600 [16:40<01:31,  1.56s/it, loss=0.0145, lr=1e-7]
Steps:  90%|█████████ | 542/600 [16:42<01:32,  1.59s/it, loss=0.0145, lr=1e-7]
Steps:  90%|█████████ | 542/600 [16:42<01:32,  1.59s/it, loss=0.0138, lr=1e-7]
Steps:  90%|█████████ | 543/600 [16:43<01:34,  1.65s/it, loss=0.0138, lr=1e-7]
Steps:  90%|█████████ | 543/600 [16:43<01:34,  1.65s/it, loss=0.0927, lr=1e-7]
Steps:  91%|█████████ | 544/600 [16:45<01:27,  1.56s/it, loss=0.0927, lr=1e-7]
Steps:  91%|█████████ | 544/600 [16:45<01:27,  1.56s/it, loss=0.0328, lr=1e-7]
Steps:  91%|█████████ | 545/600 [16:46<01:24,  1.54s/it, loss=0.0328, lr=1e-7]
Steps:  91%|█████████ | 545/600 [16:46<01:24,  1.54s/it, loss=0.245, lr=1e-7] 
Steps:  91%|█████████ | 546/600 [16:48<01:23,  1.55s/it, loss=0.245, lr=1e-7]
Steps:  91%|█████████ | 546/600 [16:48<01:23,  1.55s/it, loss=0.0895, lr=1e-7]
Steps:  91%|█████████ | 547/600 [16:49<01:25,  1.61s/it, loss=0.0895, lr=1e-7]
Steps:  91%|█████████ | 547/600 [16:49<01:25,  1.61s/it, loss=0.0255, lr=1e-7]
Steps:  91%|█████████▏| 548/600 [16:51<01:21,  1.58s/it, loss=0.0255, lr=1e-7]
Steps:  91%|█████████▏| 548/600 [16:51<01:21,  1.58s/it, loss=0.0449, lr=1e-7]
Steps:  92%|█████████▏| 549/600 [16:52<01:15,  1.48s/it, loss=0.0449, lr=1e-7]
Steps:  92%|█████████▏| 549/600 [16:52<01:15,  1.48s/it, loss=0.171, lr=1e-7] 
Steps:  92%|█████████▏| 550/600 [16:53<01:02,  1.26s/it, loss=0.171, lr=1e-7]
Steps:  92%|█████████▏| 550/600 [16:53<01:02,  1.26s/it, loss=0.0461, lr=1e-7]
Steps:  92%|█████████▏| 551/600 [16:55<01:17,  1.58s/it, loss=0.0461, lr=1e-7]
Steps:  92%|█████████▏| 551/600 [16:55<01:17,  1.58s/it, loss=0.104, lr=1e-7] 
Steps:  92%|█████████▏| 552/600 [16:57<01:16,  1.60s/it, loss=0.104, lr=1e-7]
Steps:  92%|█████████▏| 552/600 [16:57<01:16,  1.60s/it, loss=0.328, lr=1e-7]
Steps:  92%|█████████▏| 553/600 [16:58<01:13,  1.57s/it, loss=0.328, lr=1e-7]
Steps:  92%|█████████▏| 553/600 [16:58<01:13,  1.57s/it, loss=0.0683, lr=1e-7]
Steps:  92%|█████████▏| 554/600 [17:00<01:16,  1.67s/it, loss=0.0683, lr=1e-7]
Steps:  92%|█████████▏| 554/600 [17:00<01:16,  1.67s/it, loss=0.159, lr=1e-7] 
Steps:  92%|█████████▎| 555/600 [17:02<01:13,  1.63s/it, loss=0.159, lr=1e-7]
Steps:  92%|█████████▎| 555/600 [17:02<01:13,  1.63s/it, loss=0.132, lr=1e-7]
Steps:  93%|█████████▎| 556/600 [17:03<01:10,  1.60s/it, loss=0.132, lr=1e-7]
Steps:  93%|█████████▎| 556/600 [17:03<01:10,  1.60s/it, loss=0.101, lr=1e-7]
Steps:  93%|█████████▎| 557/600 [17:05<01:08,  1.59s/it, loss=0.101, lr=1e-7]
Steps:  93%|█████████▎| 557/600 [17:05<01:08,  1.59s/it, loss=0.262, lr=1e-7]
Steps:  93%|█████████▎| 558/600 [17:07<01:09,  1.66s/it, loss=0.262, lr=1e-7]
Steps:  93%|█████████▎| 558/600 [17:07<01:09,  1.66s/it, loss=0.0782, lr=1e-7]
Steps:  93%|█████████▎| 559/600 [17:08<01:07,  1.64s/it, loss=0.0782, lr=1e-7]
Steps:  93%|█████████▎| 559/600 [17:08<01:07,  1.64s/it, loss=0.0333, lr=1e-7]
Steps:  93%|█████████▎| 560/600 [17:10<00:59,  1.48s/it, loss=0.0333, lr=1e-7]
Steps:  93%|█████████▎| 560/600 [17:10<00:59,  1.48s/it, loss=0.038, lr=1e-7] 
Steps:  94%|█████████▎| 561/600 [17:10<00:49,  1.26s/it, loss=0.038, lr=1e-7]
Steps:  94%|█████████▎| 561/600 [17:10<00:49,  1.26s/it, loss=0.149, lr=1e-7]10/13/2023 11:10:57 - INFO - __main__ - Running validation... 
+ Generating 4 images with prompts: "a photo of Brad Pitt in a suit and sunglasses showing <thumbs_up> thumbs up", "a photo of Barack Obama wearing a vest showing <thumbs_up> thumbs up", "a photo of a black man at the beach showing <thumbs_up> thumbs up".
+
+
Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]Loaded scheduler as EulerDiscreteScheduler from `scheduler` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
+Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
+Loaded tokenizer_2 as CLIPTokenizer from `tokenizer_2` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
+
Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 72.64it/s]
+{'dynamic_thresholding_ratio', 'algorithm_type', 'variance_type', 'lambda_min_clipped', 'solver_order', 'solver_type', 'lower_order_final', 'thresholding'} was not found in config. Values will be initialized to default values.
+10/13/2023 11:11:55 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
+10/13/2023 11:12:44 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
+10/13/2023 11:13:33 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
+
Steps:  94%|█████████▎| 562/600 [19:56<31:59, 50.51s/it, loss=0.149, lr=1e-7]
Steps:  94%|█████████▎| 562/600 [19:56<31:59, 50.51s/it, loss=0.224, lr=1e-7]
Steps:  94%|█████████▍| 563/600 [19:57<22:04, 35.81s/it, loss=0.224, lr=1e-7]
Steps:  94%|█████████▍| 563/600 [19:57<22:04, 35.81s/it, loss=0.015, lr=1e-7]
Steps:  94%|█████████▍| 564/600 [19:59<15:23, 25.64s/it, loss=0.015, lr=1e-7]
Steps:  94%|█████████▍| 564/600 [19:59<15:23, 25.64s/it, loss=0.0867, lr=1e-7]
Steps:  94%|█████████▍| 565/600 [20:01<10:43, 18.40s/it, loss=0.0867, lr=1e-7]
Steps:  94%|█████████▍| 565/600 [20:01<10:43, 18.40s/it, loss=0.103, lr=1e-7] 
Steps:  94%|█████████▍| 566/600 [20:02<07:34, 13.36s/it, loss=0.103, lr=1e-7]
Steps:  94%|█████████▍| 566/600 [20:02<07:34, 13.36s/it, loss=0.181, lr=1e-7]
Steps:  94%|█████████▍| 567/600 [20:04<05:26,  9.88s/it, loss=0.181, lr=1e-7]
Steps:  94%|█████████▍| 567/600 [20:04<05:26,  9.88s/it, loss=0.0474, lr=1e-7]
Steps:  95%|█████████▍| 568/600 [20:05<03:54,  7.33s/it, loss=0.0474, lr=1e-7]
Steps:  95%|█████████▍| 568/600 [20:05<03:54,  7.33s/it, loss=0.0238, lr=1e-7]
Steps:  95%|█████████▍| 569/600 [20:07<02:51,  5.53s/it, loss=0.0238, lr=1e-7]
Steps:  95%|█████████▍| 569/600 [20:07<02:51,  5.53s/it, loss=0.167, lr=1e-7] 
Steps:  95%|█████████▌| 570/600 [20:08<02:09,  4.32s/it, loss=0.167, lr=1e-7]
Steps:  95%|█████████▌| 570/600 [20:08<02:09,  4.32s/it, loss=0.138, lr=1e-7]
Steps:  95%|█████████▌| 571/600 [20:10<01:40,  3.46s/it, loss=0.138, lr=1e-7]
Steps:  95%|█████████▌| 571/600 [20:10<01:40,  3.46s/it, loss=0.18, lr=1e-7] 
Steps:  95%|█████████▌| 572/600 [20:10<01:14,  2.65s/it, loss=0.18, lr=1e-7]
Steps:  95%|█████████▌| 572/600 [20:10<01:14,  2.65s/it, loss=0.003, lr=1e-7]
Steps:  96%|█████████▌| 573/600 [20:12<01:06,  2.48s/it, loss=0.003, lr=1e-7]
Steps:  96%|█████████▌| 573/600 [20:12<01:06,  2.48s/it, loss=0.00295, lr=1e-7]
Steps:  96%|█████████▌| 574/600 [20:14<00:55,  2.14s/it, loss=0.00295, lr=1e-7]
Steps:  96%|█████████▌| 574/600 [20:14<00:55,  2.14s/it, loss=0.092, lr=1e-7]  
Steps:  96%|█████████▌| 575/600 [20:15<00:49,  2.00s/it, loss=0.092, lr=1e-7]
Steps:  96%|█████████▌| 575/600 [20:15<00:49,  2.00s/it, loss=0.01, lr=1e-7] 
Steps:  96%|█████████▌| 576/600 [20:17<00:45,  1.89s/it, loss=0.01, lr=1e-7]
Steps:  96%|█████████▌| 576/600 [20:17<00:45,  1.89s/it, loss=0.0496, lr=1e-7]
Steps:  96%|█████████▌| 577/600 [20:19<00:41,  1.79s/it, loss=0.0496, lr=1e-7]
Steps:  96%|█████████▌| 577/600 [20:19<00:41,  1.79s/it, loss=0.00438, lr=1e-7]
Steps:  96%|█████████▋| 578/600 [20:20<00:36,  1.67s/it, loss=0.00438, lr=1e-7]
Steps:  96%|█████████▋| 578/600 [20:20<00:36,  1.67s/it, loss=0.338, lr=1e-7]  
Steps:  96%|█████████▋| 579/600 [20:22<00:35,  1.69s/it, loss=0.338, lr=1e-7]
Steps:  96%|█████████▋| 579/600 [20:22<00:35,  1.69s/it, loss=0.0301, lr=1e-7]
Steps:  97%|█████████▋| 580/600 [20:24<00:34,  1.75s/it, loss=0.0301, lr=1e-7]
Steps:  97%|█████████▋| 580/600 [20:24<00:34,  1.75s/it, loss=0.234, lr=1e-7] 
Steps:  97%|█████████▋| 581/600 [20:25<00:31,  1.68s/it, loss=0.234, lr=1e-7]
Steps:  97%|█████████▋| 581/600 [20:25<00:31,  1.68s/it, loss=0.151, lr=1e-7]
Steps:  97%|█████████▋| 582/600 [20:27<00:28,  1.61s/it, loss=0.151, lr=1e-7]
Steps:  97%|█████████▋| 582/600 [20:27<00:28,  1.61s/it, loss=0.233, lr=1e-7]
Steps:  97%|█████████▋| 583/600 [20:27<00:23,  1.36s/it, loss=0.233, lr=1e-7]
Steps:  97%|█████████▋| 583/600 [20:27<00:23,  1.36s/it, loss=0.0961, lr=1e-7]
Steps:  97%|█████████▋| 584/600 [20:30<00:25,  1.58s/it, loss=0.0961, lr=1e-7]
Steps:  97%|█████████▋| 584/600 [20:30<00:25,  1.58s/it, loss=0.251, lr=1e-7] 
Steps:  98%|█████████▊| 585/600 [20:31<00:23,  1.54s/it, loss=0.251, lr=1e-7]
Steps:  98%|█████████▊| 585/600 [20:31<00:23,  1.54s/it, loss=0.169, lr=1e-7]
Steps:  98%|█████████▊| 586/600 [20:33<00:21,  1.56s/it, loss=0.169, lr=1e-7]
Steps:  98%|█████████▊| 586/600 [20:33<00:21,  1.56s/it, loss=0.0184, lr=1e-7]
Steps:  98%|█████████▊| 587/600 [20:34<00:20,  1.57s/it, loss=0.0184, lr=1e-7]
Steps:  98%|█████████▊| 587/600 [20:34<00:20,  1.57s/it, loss=0.152, lr=1e-7] 
Steps:  98%|█████████▊| 588/600 [20:36<00:19,  1.60s/it, loss=0.152, lr=1e-7]
Steps:  98%|█████████▊| 588/600 [20:36<00:19,  1.60s/it, loss=0.115, lr=1e-7]
Steps:  98%|█████████▊| 589/600 [20:38<00:18,  1.69s/it, loss=0.115, lr=1e-7]
Steps:  98%|█████████▊| 589/600 [20:38<00:18,  1.69s/it, loss=0.0174, lr=1e-7]
Steps:  98%|█████████▊| 590/600 [20:39<00:16,  1.66s/it, loss=0.0174, lr=1e-7]
Steps:  98%|█████████▊| 590/600 [20:39<00:16,  1.66s/it, loss=0.0726, lr=1e-7]
Steps:  98%|█████████▊| 591/600 [20:41<00:14,  1.57s/it, loss=0.0726, lr=1e-7]
Steps:  98%|█████████▊| 591/600 [20:41<00:14,  1.57s/it, loss=0.0307, lr=1e-7]
Steps:  99%|█████████▊| 592/600 [20:42<00:13,  1.64s/it, loss=0.0307, lr=1e-7]
Steps:  99%|█████████▊| 592/600 [20:42<00:13,  1.64s/it, loss=0.0744, lr=1e-7]
Steps:  99%|█████████▉| 593/600 [20:44<00:10,  1.52s/it, loss=0.0744, lr=1e-7]
Steps:  99%|█████████▉| 593/600 [20:44<00:10,  1.52s/it, loss=0.189, lr=1e-7] 
Steps:  99%|█████████▉| 594/600 [20:44<00:07,  1.29s/it, loss=0.189, lr=1e-7]
Steps:  99%|█████████▉| 594/600 [20:44<00:07,  1.29s/it, loss=0.00349, lr=1e-7]
Steps:  99%|█████████▉| 595/600 [20:47<00:07,  1.53s/it, loss=0.00349, lr=1e-7]
Steps:  99%|█████████▉| 595/600 [20:47<00:07,  1.53s/it, loss=0.194, lr=1e-7]  
Steps:  99%|█████████▉| 596/600 [20:48<00:06,  1.60s/it, loss=0.194, lr=1e-7]
Steps:  99%|█████████▉| 596/600 [20:48<00:06,  1.60s/it, loss=0.162, lr=1e-7]
Steps: 100%|█████████▉| 597/600 [20:50<00:04,  1.64s/it, loss=0.162, lr=1e-7]
Steps: 100%|█████████▉| 597/600 [20:50<00:04,  1.64s/it, loss=0.21, lr=1e-7] 
Steps: 100%|█████████▉| 598/600 [20:52<00:03,  1.60s/it, loss=0.21, lr=1e-7]
Steps: 100%|█████████▉| 598/600 [20:52<00:03,  1.60s/it, loss=0.203, lr=1e-7]
Steps: 100%|█████████▉| 599/600 [20:53<00:01,  1.59s/it, loss=0.203, lr=1e-7]
Steps: 100%|█████████▉| 599/600 [20:53<00:01,  1.59s/it, loss=0.101, lr=1e-7]
Steps: 100%|██████████| 600/600 [20:55<00:00,  1.55s/it, loss=0.101, lr=1e-7]
Steps: 100%|██████████| 600/600 [20:55<00:00,  1.55s/it, loss=0.0767, lr=1e-7]Model weights saved in logs/sweep_final_3_20231013105322/pytorch_lora_weights.safetensors
+
+
Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]{'dropout', 'attention_type'} was not found in config. Values will be initialized to default values.
+Loaded unet as UNet2DConditionModel from `unet` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
+
+
Loading pipeline components...:  14%|█▍        | 1/7 [00:02<00:17,  2.95s/it]Loaded scheduler as EulerDiscreteScheduler from `scheduler` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
+Loaded text_encoder as CLIPTextModel from `text_encoder` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
+
+
Loading pipeline components...:  43%|████▎     | 3/7 [00:03<00:03,  1.15it/s]Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
+Loaded text_encoder_2 as CLIPTextModelWithProjection from `text_encoder_2` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
+
+
Loading pipeline components...:  71%|███████▏  | 5/7 [00:04<00:01,  1.45it/s]Loaded tokenizer_2 as CLIPTokenizer from `tokenizer_2` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
+
Loading pipeline components...: 100%|██████████| 7/7 [00:04<00:00,  1.62it/s]
+{'dynamic_thresholding_ratio', 'algorithm_type', 'variance_type', 'lambda_min_clipped', 'solver_order', 'solver_type', 'lower_order_final', 'thresholding'} was not found in config. Values will be initialized to default values.
+Loading unet.
+
+
  0%|          | 0/50 [00:00<?, ?it/s]
+
  2%|▏         | 1/50 [00:00<00:09,  5.40it/s]
+
  4%|▍         | 2/50 [00:00<00:07,  6.21it/s]
+
  6%|▌         | 3/50 [00:00<00:08,  5.78it/s]
+
  8%|▊         | 4/50 [00:00<00:08,  5.61it/s]
+
 10%|█         | 5/50 [00:00<00:08,  5.51it/s]
+
 12%|█▏        | 6/50 [00:01<00:08,  5.46it/s]
+
 14%|█▍        | 7/50 [00:01<00:07,  5.42it/s]
+
 16%|█▌        | 8/50 [00:01<00:07,  5.39it/s]
+
 18%|█▊        | 9/50 [00:01<00:07,  5.36it/s]
+
 20%|██        | 10/50 [00:01<00:07,  5.34it/s]
+
 22%|██▏       | 11/50 [00:02<00:07,  5.33it/s]
+
 24%|██▍       | 12/50 [00:02<00:07,  5.34it/s]
+
 26%|██▌       | 13/50 [00:02<00:06,  5.34it/s]
+
 28%|██▊       | 14/50 [00:02<00:06,  5.32it/s]
+
 30%|███       | 15/50 [00:02<00:06,  5.32it/s]
+
 32%|███▏      | 16/50 [00:02<00:06,  5.32it/s]
+
 34%|███▍      | 17/50 [00:03<00:06,  5.31it/s]
+
 36%|███▌      | 18/50 [00:03<00:06,  5.33it/s]
+
 38%|███▊      | 19/50 [00:03<00:05,  5.32it/s]
+
 40%|████      | 20/50 [00:03<00:05,  5.32it/s]
+
 42%|████▏     | 21/50 [00:03<00:05,  5.32it/s]
+
 44%|████▍     | 22/50 [00:04<00:05,  5.32it/s]
+
 46%|████▌     | 23/50 [00:04<00:05,  5.32it/s]
+
 48%|████▊     | 24/50 [00:04<00:04,  5.32it/s]
+
 50%|█████     | 25/50 [00:04<00:04,  5.30it/s]
+
 52%|█████▏    | 26/50 [00:04<00:04,  5.32it/s]
+
 54%|█████▍    | 27/50 [00:05<00:04,  5.32it/s]
+
 56%|█████▌    | 28/50 [00:05<00:04,  5.30it/s]
+
 58%|█████▊    | 29/50 [00:05<00:03,  5.32it/s]
+
 60%|██████    | 30/50 [00:05<00:03,  5.32it/s]
+
 62%|██████▏   | 31/50 [00:05<00:03,  5.30it/s]
+
 64%|██████▍   | 32/50 [00:05<00:03,  5.32it/s]
+
 66%|██████▌   | 33/50 [00:06<00:03,  5.33it/s]
+
 68%|██████▊   | 34/50 [00:06<00:03,  5.32it/s]
+
 70%|███████   | 35/50 [00:06<00:02,  5.32it/s]
+
 72%|███████▏  | 36/50 [00:06<00:02,  5.33it/s]
+
 74%|███████▍  | 37/50 [00:06<00:02,  5.32it/s]
+
 76%|███████▌  | 38/50 [00:07<00:02,  5.32it/s]
+
 78%|███████▊  | 39/50 [00:07<00:02,  5.31it/s]
+
 80%|████████  | 40/50 [00:07<00:01,  5.30it/s]
+
 82%|████████▏ | 41/50 [00:07<00:01,  5.30it/s]
+
 84%|████████▍ | 42/50 [00:07<00:01,  5.30it/s]
+
 86%|████████▌ | 43/50 [00:08<00:01,  5.30it/s]
+
 88%|████████▊ | 44/50 [00:08<00:01,  5.30it/s]
+
 90%|█████████ | 45/50 [00:08<00:00,  5.31it/s]
+
 92%|█████████▏| 46/50 [00:08<00:00,  5.31it/s]
+
 94%|█████████▍| 47/50 [00:08<00:00,  5.31it/s]
+
 96%|█████████▌| 48/50 [00:08<00:00,  5.31it/s]
+
 98%|█████████▊| 49/50 [00:09<00:00,  5.31it/s]
+
100%|██████████| 50/50 [00:09<00:00,  5.30it/s]
100%|██████████| 50/50 [00:09<00:00,  5.34it/s]
+
+
  0%|          | 0/50 [00:00<?, ?it/s]
+
  2%|▏         | 1/50 [00:00<00:09,  5.40it/s]
+
  4%|▍         | 2/50 [00:00<00:07,  6.20it/s]
+
  6%|▌         | 3/50 [00:00<00:08,  5.77it/s]
+
  8%|▊         | 4/50 [00:00<00:08,  5.58it/s]
+
 10%|█         | 5/50 [00:00<00:08,  5.47it/s]
+
 12%|█▏        | 6/50 [00:01<00:08,  5.42it/s]
+
 14%|█▍        | 7/50 [00:01<00:07,  5.38it/s]
+
 16%|█▌        | 8/50 [00:01<00:07,  5.36it/s]
+
 18%|█▊        | 9/50 [00:01<00:07,  5.34it/s]
+
 20%|██        | 10/50 [00:01<00:07,  5.34it/s]
+
 22%|██▏       | 11/50 [00:02<00:07,  5.33it/s]
+
 24%|██▍       | 12/50 [00:02<00:10,  3.75it/s]
+
 26%|██▌       | 13/50 [00:02<00:08,  4.15it/s]
+
 28%|██▊       | 14/50 [00:02<00:08,  4.44it/s]
+
 30%|███       | 15/50 [00:03<00:07,  4.68it/s]
+
 32%|███▏      | 16/50 [00:03<00:07,  4.85it/s]
+
 34%|███▍      | 17/50 [00:03<00:06,  4.97it/s]
+
 36%|███▌      | 18/50 [00:03<00:06,  5.08it/s]
+
 38%|███▊      | 19/50 [00:03<00:06,  5.15it/s]
+
 40%|████      | 20/50 [00:03<00:05,  5.19it/s]
+
 42%|████▏     | 21/50 [00:04<00:05,  5.23it/s]
+
 44%|████▍     | 22/50 [00:04<00:05,  5.25it/s]
+
 46%|████▌     | 23/50 [00:04<00:05,  5.26it/s]
+
 48%|████▊     | 24/50 [00:04<00:04,  5.28it/s]
+
 50%|█████     | 25/50 [00:04<00:04,  5.29it/s]
+
 52%|█████▏    | 26/50 [00:05<00:04,  5.30it/s]
+
 54%|█████▍    | 27/50 [00:05<00:04,  5.30it/s]
+
 56%|█████▌    | 28/50 [00:05<00:04,  5.31it/s]
+
 58%|█████▊    | 29/50 [00:05<00:03,  5.31it/s]
+
 60%|██████    | 30/50 [00:05<00:03,  5.30it/s]
+
 62%|██████▏   | 31/50 [00:06<00:03,  5.31it/s]
+
 64%|██████▍   | 32/50 [00:06<00:03,  5.31it/s]
+
 66%|██████▌   | 33/50 [00:06<00:03,  5.31it/s]
+
 68%|██████▊   | 34/50 [00:06<00:03,  5.31it/s]
+
 70%|███████   | 35/50 [00:06<00:02,  5.30it/s]
+
 72%|███████▏  | 36/50 [00:06<00:02,  5.30it/s]
+
 74%|███████▍  | 37/50 [00:07<00:02,  5.31it/s]
+
 76%|███████▌  | 38/50 [00:07<00:02,  5.31it/s]
+
 78%|███████▊  | 39/50 [00:07<00:02,  5.31it/s]
+
 80%|████████  | 40/50 [00:07<00:01,  5.30it/s]
+
 82%|████████▏ | 41/50 [00:07<00:01,  5.30it/s]
+
 84%|████████▍ | 42/50 [00:08<00:01,  5.30it/s]
+
 86%|████████▌ | 43/50 [00:08<00:01,  5.30it/s]
+
 88%|████████▊ | 44/50 [00:08<00:01,  5.31it/s]
+
 90%|█████████ | 45/50 [00:08<00:00,  5.31it/s]
+
 92%|█████████▏| 46/50 [00:08<00:00,  5.31it/s]
+
 94%|█████████▍| 47/50 [00:09<00:00,  5.31it/s]
+
 96%|█████████▌| 48/50 [00:09<00:00,  5.30it/s]
+
 98%|█████████▊| 49/50 [00:09<00:00,  5.31it/s]
+
100%|██████████| 50/50 [00:09<00:00,  5.31it/s]
100%|██████████| 50/50 [00:09<00:00,  5.20it/s]
+
+
  0%|          | 0/50 [00:00<?, ?it/s]
+
  2%|▏         | 1/50 [00:00<00:09,  5.41it/s]
+
  4%|▍         | 2/50 [00:00<00:07,  6.22it/s]
+
  6%|▌         | 3/50 [00:00<00:08,  5.78it/s]
+
  8%|▊         | 4/50 [00:00<00:08,  5.58it/s]
+
 10%|█         | 5/50 [00:00<00:08,  5.48it/s]
+
 12%|█▏        | 6/50 [00:01<00:08,  5.40it/s]
+
 14%|█▍        | 7/50 [00:01<00:08,  5.37it/s]
+
 16%|█▌        | 8/50 [00:01<00:07,  5.35it/s]
+
 18%|█▊        | 9/50 [00:01<00:07,  5.34it/s]
+
 20%|██        | 10/50 [00:01<00:07,  5.32it/s]
+
 22%|██▏       | 11/50 [00:02<00:07,  5.31it/s]
+
 24%|██▍       | 12/50 [00:02<00:07,  5.30it/s]
+
 26%|██▌       | 13/50 [00:02<00:06,  5.29it/s]
+
 28%|██▊       | 14/50 [00:02<00:06,  5.30it/s]
+
 30%|███       | 15/50 [00:02<00:06,  5.29it/s]
+
 32%|███▏      | 16/50 [00:02<00:06,  5.29it/s]
+
 34%|███▍      | 17/50 [00:03<00:06,  5.29it/s]
+
 36%|███▌      | 18/50 [00:03<00:06,  5.29it/s]
+
 38%|███▊      | 19/50 [00:03<00:05,  5.28it/s]
+
 40%|████      | 20/50 [00:03<00:05,  5.30it/s]
+
 42%|████▏     | 21/50 [00:03<00:05,  5.30it/s]
+
 44%|████▍     | 22/50 [00:04<00:05,  5.30it/s]
+
 46%|████▌     | 23/50 [00:04<00:05,  5.30it/s]
+
 48%|████▊     | 24/50 [00:04<00:04,  5.29it/s]
+
 50%|█████     | 25/50 [00:04<00:04,  5.28it/s]
+
 52%|█████▏    | 26/50 [00:04<00:04,  5.28it/s]
+
 54%|█████▍    | 27/50 [00:05<00:04,  5.29it/s]
+
 56%|█████▌    | 28/50 [00:05<00:04,  5.29it/s]
+
 58%|█████▊    | 29/50 [00:05<00:03,  5.30it/s]
+
 60%|██████    | 30/50 [00:05<00:03,  5.30it/s]
+
 62%|██████▏   | 31/50 [00:05<00:03,  5.30it/s]
+
 64%|██████▍   | 32/50 [00:05<00:03,  5.29it/s]
+
 66%|██████▌   | 33/50 [00:06<00:03,  5.30it/s]
+
 68%|██████▊   | 34/50 [00:06<00:03,  5.29it/s]
+
 70%|███████   | 35/50 [00:06<00:02,  5.28it/s]
+
 72%|███████▏  | 36/50 [00:06<00:02,  5.28it/s]
+
 74%|███████▍  | 37/50 [00:06<00:02,  5.30it/s]
+
 76%|███████▌  | 38/50 [00:07<00:02,  5.30it/s]
+
 78%|███████▊  | 39/50 [00:07<00:02,  5.28it/s]
+
 80%|████████  | 40/50 [00:07<00:01,  5.29it/s]
+
 82%|████████▏ | 41/50 [00:07<00:01,  5.30it/s]
+
 84%|████████▍ | 42/50 [00:07<00:01,  5.31it/s]
+
 86%|████████▌ | 43/50 [00:08<00:01,  5.30it/s]
+
 88%|████████▊ | 44/50 [00:08<00:01,  5.30it/s]
+
 90%|█████████ | 45/50 [00:08<00:00,  5.29it/s]
+
 92%|█████████▏| 46/50 [00:08<00:00,  5.28it/s]
+
 94%|█████████▍| 47/50 [00:08<00:00,  5.29it/s]
+
 96%|█████████▌| 48/50 [00:09<00:00,  5.28it/s]
+
 98%|█████████▊| 49/50 [00:09<00:00,  5.29it/s]
+
100%|██████████| 50/50 [00:09<00:00,  5.28it/s]
100%|██████████| 50/50 [00:09<00:00,  5.32it/s]
+
+
  0%|          | 0/50 [00:00<?, ?it/s]
+
  2%|▏         | 1/50 [00:00<00:09,  5.39it/s]
+
  4%|▍         | 2/50 [00:00<00:07,  6.20it/s]
+
  6%|▌         | 3/50 [00:00<00:08,  5.75it/s]
+
  8%|▊         | 4/50 [00:00<00:08,  5.57it/s]
+
 10%|█         | 5/50 [00:00<00:08,  5.46it/s]
+
 12%|█▏        | 6/50 [00:01<00:08,  5.40it/s]
+
 14%|█▍        | 7/50 [00:01<00:08,  5.37it/s]
+
 16%|█▌        | 8/50 [00:01<00:07,  5.35it/s]
+
 18%|█▊        | 9/50 [00:01<00:07,  5.33it/s]
+
 20%|██        | 10/50 [00:01<00:07,  5.32it/s]
+
 22%|██▏       | 11/50 [00:02<00:07,  5.30it/s]
+
 24%|██▍       | 12/50 [00:02<00:07,  5.29it/s]
+
 26%|██▌       | 13/50 [00:02<00:06,  5.30it/s]
+
 28%|██▊       | 14/50 [00:02<00:06,  5.30it/s]
+
 30%|███       | 15/50 [00:02<00:06,  5.30it/s]
+
 32%|███▏      | 16/50 [00:02<00:06,  5.29it/s]
+
 34%|███▍      | 17/50 [00:03<00:06,  5.28it/s]
+
 36%|███▌      | 18/50 [00:03<00:06,  5.28it/s]
+
 38%|███▊      | 19/50 [00:03<00:05,  5.28it/s]
+
 40%|████      | 20/50 [00:03<00:05,  5.29it/s]
+
 42%|████▏     | 21/50 [00:03<00:05,  5.27it/s]
+
 44%|████▍     | 22/50 [00:04<00:05,  5.28it/s]
+
 46%|████▌     | 23/50 [00:04<00:05,  5.29it/s]
+
 48%|████▊     | 24/50 [00:04<00:04,  5.29it/s]
+
 50%|█████     | 25/50 [00:04<00:04,  5.29it/s]
+
 52%|█████▏    | 26/50 [00:04<00:04,  5.29it/s]
+
 54%|█████▍    | 27/50 [00:05<00:04,  5.29it/s]
+
 56%|█████▌    | 28/50 [00:05<00:04,  5.30it/s]
+
 58%|█████▊    | 29/50 [00:05<00:03,  5.29it/s]
+
 60%|██████    | 30/50 [00:05<00:03,  5.30it/s]
+
 62%|██████▏   | 31/50 [00:05<00:03,  5.29it/s]
+
 64%|██████▍   | 32/50 [00:05<00:03,  5.31it/s]
+
 66%|██████▌   | 33/50 [00:06<00:03,  5.30it/s]
+
 68%|██████▊   | 34/50 [00:06<00:03,  5.29it/s]
+
 70%|███████   | 35/50 [00:06<00:02,  5.29it/s]
+
 72%|███████▏  | 36/50 [00:06<00:02,  5.29it/s]
+
 74%|███████▍  | 37/50 [00:06<00:02,  5.29it/s]
+
 76%|███████▌  | 38/50 [00:07<00:02,  5.30it/s]
+
 78%|███████▊  | 39/50 [00:07<00:02,  5.28it/s]
+
 80%|████████  | 40/50 [00:07<00:01,  5.29it/s]
+
 82%|████████▏ | 41/50 [00:07<00:01,  5.29it/s]
+
 84%|████████▍ | 42/50 [00:07<00:01,  5.29it/s]
+
 86%|████████▌ | 43/50 [00:08<00:01,  5.29it/s]
+
 88%|████████▊ | 44/50 [00:08<00:01,  5.29it/s]
+
 90%|█████████ | 45/50 [00:08<00:00,  5.28it/s]
+
 92%|█████████▏| 46/50 [00:08<00:00,  5.29it/s]
+
 94%|█████████▍| 47/50 [00:08<00:00,  5.29it/s]
+
 96%|█████████▌| 48/50 [00:09<00:00,  5.30it/s]
+
 98%|█████████▊| 49/50 [00:09<00:00,  5.29it/s]
+
100%|██████████| 50/50 [00:09<00:00,  5.28it/s]
100%|██████████| 50/50 [00:09<00:00,  5.32it/s]
+10/13/2023 11:15:38 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
+
+
  0%|          | 0/50 [00:00<?, ?it/s]
+
  2%|▏         | 1/50 [00:00<00:09,  5.41it/s]
+
  4%|▍         | 2/50 [00:00<00:07,  6.18it/s]
+
  6%|▌         | 3/50 [00:00<00:08,  5.81it/s]
+
  8%|▊         | 4/50 [00:00<00:08,  5.60it/s]
+
 10%|█         | 5/50 [00:00<00:08,  5.50it/s]
+
 12%|█▏        | 6/50 [00:01<00:08,  5.43it/s]
+
 14%|█▍        | 7/50 [00:01<00:07,  5.39it/s]
+
 16%|█▌        | 8/50 [00:01<00:07,  5.36it/s]
+
 18%|█▊        | 9/50 [00:01<00:07,  5.35it/s]
+
 20%|██        | 10/50 [00:01<00:07,  5.34it/s]
+
 22%|██▏       | 11/50 [00:02<00:07,  5.33it/s]
+
 24%|██▍       | 12/50 [00:02<00:07,  5.32it/s]
+
 26%|██▌       | 13/50 [00:02<00:06,  5.32it/s]
+
 28%|██▊       | 14/50 [00:02<00:06,  5.31it/s]
+
 30%|███       | 15/50 [00:02<00:06,  5.30it/s]
+
 32%|███▏      | 16/50 [00:02<00:06,  5.30it/s]
+
 34%|███▍      | 17/50 [00:03<00:06,  5.30it/s]
+
 36%|███▌      | 18/50 [00:03<00:06,  5.30it/s]
+
 38%|███▊      | 19/50 [00:03<00:05,  5.30it/s]
+
 40%|████      | 20/50 [00:03<00:05,  5.31it/s]
+
 42%|████▏     | 21/50 [00:03<00:05,  5.30it/s]
+
 44%|████▍     | 22/50 [00:04<00:05,  5.29it/s]
+
 46%|████▌     | 23/50 [00:04<00:05,  5.30it/s]
+
 48%|████▊     | 24/50 [00:04<00:04,  5.30it/s]
+
 50%|█████     | 25/50 [00:04<00:04,  5.30it/s]
+
 52%|█████▏    | 26/50 [00:04<00:04,  5.29it/s]
+
 54%|█████▍    | 27/50 [00:05<00:04,  5.30it/s]
+
 56%|█████▌    | 28/50 [00:05<00:04,  5.30it/s]
+
 58%|█████▊    | 29/50 [00:05<00:03,  5.30it/s]
+
 60%|██████    | 30/50 [00:05<00:03,  5.30it/s]
+
 62%|██████▏   | 31/50 [00:05<00:03,  5.30it/s]
+
 64%|██████▍   | 32/50 [00:05<00:03,  5.30it/s]
+
 66%|██████▌   | 33/50 [00:06<00:03,  5.31it/s]
+
 68%|██████▊   | 34/50 [00:06<00:03,  5.31it/s]
+
 70%|███████   | 35/50 [00:06<00:02,  5.30it/s]
+
 72%|███████▏  | 36/50 [00:06<00:02,  5.31it/s]
+
 74%|███████▍  | 37/50 [00:06<00:02,  5.30it/s]
+
 76%|███████▌  | 38/50 [00:07<00:02,  5.30it/s]
+
 78%|███████▊  | 39/50 [00:07<00:02,  5.30it/s]
+
 80%|████████  | 40/50 [00:07<00:01,  5.30it/s]
+
 82%|████████▏ | 41/50 [00:07<00:01,  5.29it/s]
+
 84%|████████▍ | 42/50 [00:07<00:01,  5.29it/s]
+
 86%|████████▌ | 43/50 [00:08<00:01,  5.28it/s]
+
 88%|████████▊ | 44/50 [00:08<00:01,  5.29it/s]
+
 90%|█████████ | 45/50 [00:08<00:00,  5.30it/s]
+
 92%|█████████▏| 46/50 [00:08<00:00,  5.29it/s]
+
 94%|█████████▍| 47/50 [00:08<00:00,  5.28it/s]
+
 96%|█████████▌| 48/50 [00:09<00:00,  5.29it/s]
+
 98%|█████████▊| 49/50 [00:09<00:00,  5.30it/s]
+
100%|██████████| 50/50 [00:09<00:00,  5.30it/s]
100%|██████████| 50/50 [00:09<00:00,  5.33it/s]
+
+
  0%|          | 0/50 [00:00<?, ?it/s]
+
  2%|▏         | 1/50 [00:00<00:09,  5.40it/s]
+
  4%|▍         | 2/50 [00:00<00:07,  6.22it/s]
+
  6%|▌         | 3/50 [00:00<00:08,  5.80it/s]
+
  8%|▊         | 4/50 [00:00<00:08,  5.59it/s]
+
 10%|█         | 5/50 [00:00<00:08,  5.48it/s]
+
 12%|█▏        | 6/50 [00:01<00:08,  5.41it/s]
+
 14%|█▍        | 7/50 [00:01<00:08,  5.36it/s]
+
 16%|█▌        | 8/50 [00:01<00:07,  5.34it/s]
+
 18%|█▊        | 9/50 [00:01<00:07,  5.33it/s]
+
 20%|██        | 10/50 [00:01<00:07,  5.33it/s]
+
 22%|██▏       | 11/50 [00:02<00:07,  5.32it/s]
+
 24%|██▍       | 12/50 [00:02<00:07,  5.30it/s]
+
 26%|██▌       | 13/50 [00:02<00:06,  5.30it/s]
+
 28%|██▊       | 14/50 [00:02<00:06,  5.29it/s]
+
 30%|███       | 15/50 [00:02<00:06,  5.30it/s]
+
 32%|███▏      | 16/50 [00:02<00:06,  5.30it/s]
+
 34%|███▍      | 17/50 [00:03<00:06,  5.31it/s]
+
 36%|███▌      | 18/50 [00:03<00:06,  5.30it/s]
+
 38%|███▊      | 19/50 [00:03<00:05,  5.31it/s]
+
 40%|████      | 20/50 [00:03<00:05,  5.30it/s]
+
 42%|████▏     | 21/50 [00:03<00:05,  5.29it/s]
+
 44%|████▍     | 22/50 [00:04<00:05,  5.29it/s]
+
 46%|████▌     | 23/50 [00:04<00:05,  5.29it/s]
+
 48%|████▊     | 24/50 [00:04<00:04,  5.28it/s]
+
 50%|█████     | 25/50 [00:04<00:04,  5.28it/s]
+
 52%|█████▏    | 26/50 [00:04<00:04,  5.29it/s]
+
 54%|█████▍    | 27/50 [00:05<00:04,  5.29it/s]
+
 56%|█████▌    | 28/50 [00:05<00:04,  5.29it/s]
+
 58%|█████▊    | 29/50 [00:05<00:03,  5.29it/s]
+
 60%|██████    | 30/50 [00:05<00:03,  5.31it/s]
+
 62%|██████▏   | 31/50 [00:05<00:03,  5.29it/s]
+
 64%|██████▍   | 32/50 [00:05<00:03,  5.29it/s]
+
 66%|██████▌   | 33/50 [00:06<00:03,  5.29it/s]
+
 68%|██████▊   | 34/50 [00:06<00:03,  5.28it/s]
+
 70%|███████   | 35/50 [00:06<00:02,  5.28it/s]
+
 72%|███████▏  | 36/50 [00:06<00:02,  5.29it/s]
+
 74%|███████▍  | 37/50 [00:06<00:02,  5.29it/s]
+
 76%|███████▌  | 38/50 [00:07<00:02,  5.29it/s]
+
 78%|███████▊  | 39/50 [00:07<00:02,  5.30it/s]
+
 80%|████████  | 40/50 [00:07<00:01,  5.29it/s]
+
 82%|████████▏ | 41/50 [00:07<00:01,  5.28it/s]
+
 84%|████████▍ | 42/50 [00:07<00:01,  5.28it/s]
+
 86%|████████▌ | 43/50 [00:08<00:01,  5.29it/s]
+
 88%|████████▊ | 44/50 [00:08<00:01,  5.29it/s]
+
 90%|█████████ | 45/50 [00:08<00:00,  5.29it/s]
+
 92%|█████████▏| 46/50 [00:08<00:00,  5.29it/s]
+
 94%|█████████▍| 47/50 [00:08<00:00,  5.29it/s]
+
 96%|█████████▌| 48/50 [00:09<00:00,  5.28it/s]
+
 98%|█████████▊| 49/50 [00:09<00:00,  5.29it/s]
+
100%|██████████| 50/50 [00:09<00:00,  5.29it/s]
100%|██████████| 50/50 [00:09<00:00,  5.32it/s]
+
+
  0%|          | 0/50 [00:00<?, ?it/s]
+
  2%|▏         | 1/50 [00:00<00:09,  5.40it/s]
+
  4%|▍         | 2/50 [00:00<00:07,  6.20it/s]
+
  6%|▌         | 3/50 [00:00<00:08,  5.75it/s]
+
  8%|▊         | 4/50 [00:00<00:08,  5.56it/s]
+
 10%|█         | 5/50 [00:00<00:08,  5.46it/s]
+
 12%|█▏        | 6/50 [00:01<00:08,  5.40it/s]
+
 14%|█▍        | 7/50 [00:01<00:08,  5.36it/s]
+
 16%|█▌        | 8/50 [00:01<00:07,  5.33it/s]
+
 18%|█▊        | 9/50 [00:01<00:07,  5.31it/s]
+
 20%|██        | 10/50 [00:01<00:07,  5.31it/s]
+
 22%|██▏       | 11/50 [00:02<00:07,  5.30it/s]
+
 24%|██▍       | 12/50 [00:02<00:07,  5.30it/s]
+
 26%|██▌       | 13/50 [00:02<00:06,  5.30it/s]
+
 28%|██▊       | 14/50 [00:02<00:06,  5.28it/s]
+
 30%|███       | 15/50 [00:02<00:06,  5.29it/s]
+
 32%|███▏      | 16/50 [00:02<00:06,  5.27it/s]
+
 34%|███▍      | 17/50 [00:03<00:06,  5.28it/s]
+
 36%|███▌      | 18/50 [00:03<00:06,  5.28it/s]
+
 38%|███▊      | 19/50 [00:03<00:05,  5.28it/s]
+
 40%|████      | 20/50 [00:03<00:05,  5.28it/s]
+
 42%|████▏     | 21/50 [00:03<00:05,  5.29it/s]
+
 44%|████▍     | 22/50 [00:04<00:05,  5.29it/s]
+
 46%|████▌     | 23/50 [00:04<00:05,  5.29it/s]
+
 48%|████▊     | 24/50 [00:04<00:04,  5.29it/s]
+
 50%|█████     | 25/50 [00:04<00:04,  5.29it/s]
+
 52%|█████▏    | 26/50 [00:04<00:04,  5.29it/s]
+
 54%|█████▍    | 27/50 [00:05<00:04,  5.29it/s]
+
 56%|█████▌    | 28/50 [00:05<00:04,  5.29it/s]
+
 58%|█████▊    | 29/50 [00:05<00:03,  5.28it/s]
+
 60%|██████    | 30/50 [00:05<00:03,  5.29it/s]
+
 62%|██████▏   | 31/50 [00:05<00:03,  5.28it/s]
+
 64%|██████▍   | 32/50 [00:06<00:03,  5.28it/s]
+
 66%|█████���▌   | 33/50 [00:06<00:03,  5.29it/s]
+
 68%|██████▊   | 34/50 [00:06<00:03,  5.28it/s]
+
 70%|███████   | 35/50 [00:06<00:02,  5.28it/s]
+
 72%|███████▏  | 36/50 [00:06<00:02,  5.29it/s]
+
 74%|███████▍  | 37/50 [00:06<00:02,  5.28it/s]
+
 76%|███████▌  | 38/50 [00:07<00:02,  5.28it/s]
+
 78%|███████▊  | 39/50 [00:07<00:02,  5.28it/s]
+
 80%|████████  | 40/50 [00:07<00:01,  5.29it/s]
+
 82%|████████▏ | 41/50 [00:07<00:01,  5.28it/s]
+
 84%|████████▍ | 42/50 [00:07<00:01,  5.27it/s]
+
 86%|████████▌ | 43/50 [00:08<00:01,  5.27it/s]
+
 88%|████████▊ | 44/50 [00:08<00:01,  5.27it/s]
+
 90%|█████████ | 45/50 [00:08<00:00,  5.27it/s]
+
 92%|█████████▏| 46/50 [00:08<00:00,  5.26it/s]
+
 94%|█████████▍| 47/50 [00:08<00:00,  5.26it/s]
+
 96%|█████████▌| 48/50 [00:09<00:00,  5.27it/s]
+
 98%|█████████▊| 49/50 [00:09<00:00,  5.28it/s]
+
100%|██████████| 50/50 [00:09<00:00,  5.27it/s]
100%|██████████| 50/50 [00:09<00:00,  5.31it/s]
+
+
  0%|          | 0/50 [00:00<?, ?it/s]
+
  2%|▏         | 1/50 [00:00<00:09,  5.37it/s]
+
  4%|▍         | 2/50 [00:00<00:07,  6.18it/s]
+
  6%|▌         | 3/50 [00:00<00:08,  5.73it/s]
+
  8%|▊         | 4/50 [00:00<00:08,  5.55it/s]
+
 10%|█         | 5/50 [00:00<00:08,  5.45it/s]
+
 12%|█▏        | 6/50 [00:01<00:08,  5.39it/s]
+
 14%|█▍        | 7/50 [00:01<00:08,  5.36it/s]
+
 16%|█▌        | 8/50 [00:01<00:07,  5.33it/s]
+
 18%|█▊        | 9/50 [00:01<00:07,  5.31it/s]
+
 20%|██        | 10/50 [00:01<00:07,  5.30it/s]
+
 22%|██▏       | 11/50 [00:02<00:07,  5.29it/s]
+
 24%|██▍       | 12/50 [00:02<00:07,  5.29it/s]
+
 26%|██▌       | 13/50 [00:02<00:07,  5.28it/s]
+
 28%|██▊       | 14/50 [00:02<00:06,  5.26it/s]
+
 30%|███       | 15/50 [00:02<00:06,  5.28it/s]
+
 32%|███▏      | 16/50 [00:02<00:06,  5.28it/s]
+
 34%|███▍      | 17/50 [00:03<00:06,  5.28it/s]
+
 36%|███▌      | 18/50 [00:03<00:06,  5.27it/s]
+
 38%|███▊      | 19/50 [00:03<00:05,  5.28it/s]
+
 40%|████      | 20/50 [00:03<00:05,  5.27it/s]
+
 42%|████▏     | 21/50 [00:03<00:05,  5.27it/s]
+
 44%|████▍     | 22/50 [00:04<00:05,  5.28it/s]
+
 46%|████▌     | 23/50 [00:04<00:05,  5.28it/s]
+
 48%|████▊     | 24/50 [00:04<00:04,  5.28it/s]
+
 50%|█████     | 25/50 [00:04<00:04,  5.28it/s]
+
 52%|█████▏    | 26/50 [00:04<00:04,  5.29it/s]
+
 54%|█████▍    | 27/50 [00:05<00:04,  5.28it/s]
+
 56%|█████▌    | 28/50 [00:05<00:04,  5.28it/s]
+
 58%|█████▊    | 29/50 [00:05<00:03,  5.27it/s]
+
 60%|██████    | 30/50 [00:05<00:03,  5.28it/s]
+
 62%|██████▏   | 31/50 [00:05<00:03,  5.28it/s]
+
 64%|██████▍   | 32/50 [00:06<00:03,  5.28it/s]
+
 66%|██████▌   | 33/50 [00:06<00:03,  5.28it/s]
+
 68%|██████▊   | 34/50 [00:06<00:03,  5.29it/s]
+
 70%|███████   | 35/50 [00:06<00:02,  5.28it/s]
+
 72%|███████▏  | 36/50 [00:06<00:03,  4.31it/s]
+
 74%|███████▍  | 37/50 [00:07<00:02,  4.57it/s]
+
 76%|███████▌  | 38/50 [00:07<00:02,  4.76it/s]
+
 78%|███████▊  | 39/50 [00:07<00:02,  4.91it/s]
+
 80%|████████  | 40/50 [00:07<00:01,  5.02it/s]
+
 82%|████████▏ | 41/50 [00:07<00:01,  5.08it/s]
+
 84%|████████▍ | 42/50 [00:08<00:01,  5.14it/s]
+
 86%|████████▌ | 43/50 [00:08<00:01,  5.19it/s]
+
 88%|████████▊ | 44/50 [00:08<00:01,  5.22it/s]
+
 90%|█████████ | 45/50 [00:08<00:00,  5.24it/s]
+
 92%|█████████▏| 46/50 [00:08<00:00,  5.26it/s]
+
 94%|█████████▍| 47/50 [00:08<00:00,  5.25it/s]
+
 96%|█████████▌| 48/50 [00:09<00:00,  5.26it/s]
+
 98%|█████████▊| 49/50 [00:09<00:00,  5.27it/s]
+
100%|██████████| 50/50 [00:09<00:00,  5.28it/s]
100%|██████████| 50/50 [00:09<00:00,  5.23it/s]
+10/13/2023 11:16:28 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
+
+
  0%|          | 0/50 [00:00<?, ?it/s]
+
  2%|▏         | 1/50 [00:00<00:09,  5.42it/s]
+
  4%|▍         | 2/50 [00:00<00:07,  6.24it/s]
+
  6%|▌         | 3/50 [00:00<00:08,  5.80it/s]
+
  8%|▊         | 4/50 [00:00<00:08,  5.59it/s]
+
 10%|█         | 5/50 [00:00<00:08,  5.47it/s]
+
 12%|█▏        | 6/50 [00:01<00:08,  5.40it/s]
+
 14%|█▍        | 7/50 [00:01<00:08,  5.36it/s]
+
 16%|█▌        | 8/50 [00:01<00:07,  5.34it/s]
+
 18%|█▊        | 9/50 [00:01<00:07,  5.34it/s]
+
 20%|██        | 10/50 [00:01<00:07,  5.32it/s]
+
 22%|██▏       | 11/50 [00:02<00:07,  5.32it/s]
+
 24%|██▍       | 12/50 [00:02<00:07,  5.30it/s]
+
 26%|██▌       | 13/50 [00:02<00:06,  5.30it/s]
+
 28%|██▊       | 14/50 [00:02<00:06,  5.30it/s]
+
 30%|███       | 15/50 [00:02<00:06,  5.30it/s]
+
 32%|███▏      | 16/50 [00:02<00:06,  5.29it/s]
+
 34%|███▍      | 17/50 [00:03<00:06,  5.28it/s]
+
 36%|███▌      | 18/50 [00:03<00:06,  5.28it/s]
+
 38%|███▊      | 19/50 [00:03<00:05,  5.28it/s]
+
 40%|████      | 20/50 [00:03<00:05,  5.28it/s]
+
 42%|████▏     | 21/50 [00:03<00:05,  5.29it/s]
+
 44%|████▍     | 22/50 [00:04<00:05,  5.29it/s]
+
 46%|████▌     | 23/50 [00:04<00:05,  5.30it/s]
+
 48%|████▊     | 24/50 [00:04<00:04,  5.30it/s]
+
 50%|█████     | 25/50 [00:04<00:04,  5.31it/s]
+
 52%|█████▏    | 26/50 [00:04<00:04,  5.31it/s]
+
 54%|█████▍    | 27/50 [00:05<00:04,  5.30it/s]
+
 56%|█████▌    | 28/50 [00:05<00:04,  5.30it/s]
+
 58%|█████▊    | 29/50 [00:05<00:03,  5.31it/s]
+
 60%|██████    | 30/50 [00:05<00:03,  5.30it/s]
+
 62%|██████▏   | 31/50 [00:05<00:03,  5.30it/s]
+
 64%|██████▍   | 32/50 [00:05<00:03,  5.29it/s]
+
 66%|██████▌   | 33/50 [00:06<00:03,  5.29it/s]
+
 68%|██████▊   | 34/50 [00:06<00:03,  5.29it/s]
+
 70%|███████   | 35/50 [00:06<00:02,  5.29it/s]
+
 72%|███████▏  | 36/50 [00:06<00:02,  5.29it/s]
+
 74%|███████▍  | 37/50 [00:06<00:02,  5.30it/s]
+
 76%|███████▌  | 38/50 [00:07<00:02,  5.30it/s]
+
 78%|███████▊  | 39/50 [00:07<00:02,  5.30it/s]
+
 80%|████████  | 40/50 [00:07<00:01,  5.30it/s]
+
 82%|████████▏ | 41/50 [00:07<00:01,  5.30it/s]
+
 84%|████████▍ | 42/50 [00:07<00:01,  5.30it/s]
+
 86%|████████▌ | 43/50 [00:08<00:01,  5.30it/s]
+
 88%|████████▊ | 44/50 [00:08<00:01,  5.30it/s]
+
 90%|█████████ | 45/50 [00:08<00:00,  5.29it/s]
+
 92%|█████████▏| 46/50 [00:08<00:00,  5.29it/s]
+
 94%|█████████▍| 47/50 [00:08<00:00,  5.31it/s]
+
 96%|█████████▌| 48/50 [00:09<00:00,  5.30it/s]
+
 98%|█████████▊| 49/50 [00:09<00:00,  5.29it/s]
+
100%|██████████| 50/50 [00:09<00:00,  5.29it/s]
100%|██████████| 50/50 [00:09<00:00,  5.32it/s]
+
+
  0%|          | 0/50 [00:00<?, ?it/s]
+
  2%|▏         | 1/50 [00:00<00:09,  5.40it/s]
+
  4%|▍         | 2/50 [00:00<00:07,  6.22it/s]
+
  6%|▌         | 3/50 [00:00<00:08,  5.81it/s]
+
  8%|▊         | 4/50 [00:00<00:08,  5.60it/s]
+
 10%|█         | 5/50 [00:00<00:08,  5.48it/s]
+
 12%|█▏        | 6/50 [00:01<00:08,  5.36it/s]
+
 14%|█▍        | 7/50 [00:01<00:08,  5.33it/s]
+
 16%|█▌        | 8/50 [00:01<00:07,  5.33it/s]
+
 18%|█▊        | 9/50 [00:01<00:07,  5.32it/s]
+
 20%|██        | 10/50 [00:01<00:07,  5.31it/s]
+
 22%|██▏       | 11/50 [00:02<00:07,  5.27it/s]
+
 24%|██▍       | 12/50 [00:02<00:07,  5.28it/s]
+
 26%|██▌       | 13/50 [00:02<00:07,  5.27it/s]
+
 28%|██▊       | 14/50 [00:02<00:06,  5.28it/s]
+
 30%|███       | 15/50 [00:02<00:06,  5.29it/s]
+
 32%|███▏      | 16/50 [00:02<00:06,  5.29it/s]
+
 34%|███▍      | 17/50 [00:03<00:06,  5.27it/s]
+
 36%|███▌      | 18/50 [00:03<00:06,  5.26it/s]
+
 38%|███▊      | 19/50 [00:03<00:05,  5.26it/s]
+
 40%|████      | 20/50 [00:03<00:05,  5.28it/s]
+
 42%|████▏     | 21/50 [00:03<00:05,  5.29it/s]
+
 44%|████▍     | 22/50 [00:04<00:05,  5.28it/s]
+
 46%|████▌     | 23/50 [00:04<00:05,  5.28it/s]
+
 48%|████▊     | 24/50 [00:04<00:04,  5.28it/s]
+
 50%|█████     | 25/50 [00:04<00:04,  5.29it/s]
+
 52%|█████▏    | 26/50 [00:04<00:04,  5.28it/s]
+
 54%|█████▍    | 27/50 [00:05<00:04,  5.28it/s]
+
 56%|█████▌    | 28/50 [00:05<00:04,  5.29it/s]
+
 58%|█████▊    | 29/50 [00:05<00:03,  5.29it/s]
+
 60%|██████    | 30/50 [00:05<00:03,  5.29it/s]
+
 62%|██████▏   | 31/50 [00:05<00:03,  5.27it/s]
+
 64%|██████▍   | 32/50 [00:06<00:03,  5.27it/s]
+
 66%|██████▌   | 33/50 [00:06<00:03,  5.28it/s]
+
 68%|██████▊   | 34/50 [00:06<00:03,  5.28it/s]
+
 70%|███████   | 35/50 [00:06<00:02,  5.27it/s]
+
 72%|███████▏  | 36/50 [00:06<00:02,  5.25it/s]
+
 74%|███████▍  | 37/50 [00:06<00:02,  5.26it/s]
+
 76%|███████▌  | 38/50 [00:07<00:02,  5.26it/s]
+
 78%|███████▊  | 39/50 [00:07<00:02,  5.28it/s]
+
 80%|████████  | 40/50 [00:07<00:01,  5.28it/s]
+
 82%|████████▏ | 41/50 [00:07<00:01,  5.28it/s]
+
 84%|████████▍ | 42/50 [00:07<00:01,  5.28it/s]
+
 86%|████████▌ | 43/50 [00:08<00:01,  5.27it/s]
+
 88%|████████▊ | 44/50 [00:08<00:01,  5.26it/s]
+
 90%|█████████ | 45/50 [00:08<00:00,  5.27it/s]
+
 92%|█████████▏| 46/50 [00:08<00:00,  5.27it/s]
+
 94%|█████████▍| 47/50 [00:08<00:00,  5.28it/s]
+
 96%|█████████▌| 48/50 [00:09<00:00,  5.28it/s]
+
 98%|█████████▊| 49/50 [00:09<00:00,  5.29it/s]
+
100%|██████████| 50/50 [00:09<00:00,  5.29it/s]
100%|██████████| 50/50 [00:09<00:00,  5.30it/s]
+
+
  0%|          | 0/50 [00:00<?, ?it/s]
+
  2%|▏         | 1/50 [00:00<00:09,  5.40it/s]
+
  4%|▍         | 2/50 [00:00<00:07,  6.19it/s]
+
  6%|▌         | 3/50 [00:00<00:08,  5.75it/s]
+
  8%|▊         | 4/50 [00:00<00:08,  5.55it/s]
+
 10%|█         | 5/50 [00:00<00:08,  5.45it/s]
+
 12%|█▏        | 6/50 [00:01<00:08,  5.34it/s]
+
 14%|█▍        | 7/50 [00:01<00:08,  5.33it/s]
+
 16%|█▌        | 8/50 [00:01<00:07,  5.31it/s]
+
 18%|█▊        | 9/50 [00:01<00:07,  5.30it/s]
+
 20%|██        | 10/50 [00:01<00:07,  5.29it/s]
+
 22%|██▏       | 11/50 [00:02<00:07,  5.28it/s]
+
 24%|██▍       | 12/50 [00:02<00:07,  5.28it/s]
+
 26%|██▌       | 13/50 [00:02<00:07,  5.27it/s]
+
 28%|██▊       | 14/50 [00:02<00:06,  5.26it/s]
+
 30%|███       | 15/50 [00:02<00:06,  5.27it/s]
+
 32%|███▏      | 16/50 [00:02<00:06,  5.26it/s]
+
 34%|███▍      | 17/50 [00:03<00:06,  5.27it/s]
+
 36%|███▌      | 18/50 [00:03<00:06,  5.26it/s]
+
 38%|███▊      | 19/50 [00:03<00:05,  5.27it/s]
+
 40%|████      | 20/50 [00:03<00:05,  5.26it/s]
+
 42%|████▏     | 21/50 [00:03<00:05,  5.26it/s]
+
 44%|████▍     | 22/50 [00:04<00:05,  5.26it/s]
+
 46%|████▌     | 23/50 [00:04<00:05,  5.27it/s]
+
 48%|████▊     | 24/50 [00:04<00:04,  5.26it/s]
+
 50%|█████     | 25/50 [00:04<00:04,  5.27it/s]
+
 52%|█████▏    | 26/50 [00:04<00:04,  5.26it/s]
+
 54%|█████▍    | 27/50 [00:05<00:04,  5.27it/s]
+
 56%|█████▌    | 28/50 [00:05<00:04,  5.28it/s]
+
 58%|█████▊    | 29/50 [00:05<00:03,  5.26it/s]
+
 60%|██████    | 30/50 [00:05<00:03,  5.26it/s]
+
 62%|██████▏   | 31/50 [00:05<00:03,  5.26it/s]
+
 64%|██████▍   | 32/50 [00:06<00:03,  5.27it/s]
+
 66%|██████▌   | 33/50 [00:06<00:03,  5.27it/s]
+
 68%|██████▊   | 34/50 [00:06<00:03,  5.26it/s]
+
 70%|███████   | 35/50 [00:06<00:02,  5.27it/s]
+
 72%|███████▏  | 36/50 [00:06<00:02,  5.26it/s]
+
 74%|███████▍  | 37/50 [00:06<00:02,  5.27it/s]
+
 76%|███████▌  | 38/50 [00:07<00:02,  5.27it/s]
+
 78%|███████▊  | 39/50 [00:07<00:02,  5.27it/s]
+
 80%|████████  | 40/50 [00:07<00:01,  5.25it/s]
+
 82%|████████▏ | 41/50 [00:07<00:01,  5.27it/s]
+
 84%|████████▍ | 42/50 [00:07<00:01,  5.26it/s]
+
 86%|████████▌ | 43/50 [00:08<00:01,  5.26it/s]
+
 88%|████████▊ | 44/50 [00:08<00:01,  5.27it/s]
+
 90%|█████████ | 45/50 [00:08<00:00,  5.27it/s]
+
 92%|█████████▏| 46/50 [00:08<00:00,  5.28it/s]
+
 94%|█████████▍| 47/50 [00:08<00:00,  5.27it/s]
+
 96%|█████████▌| 48/50 [00:09<00:00,  5.27it/s]
+
 98%|█████████▊| 49/50 [00:09<00:00,  5.26it/s]
+
100%|██████████| 50/50 [00:09<00:00,  5.26it/s]
100%|██████████| 50/50 [00:09<00:00,  5.29it/s]
+
+
  0%|          | 0/50 [00:00<?, ?it/s]
+
  2%|▏         | 1/50 [00:00<00:09,  5.39it/s]
+
  4%|▍         | 2/50 [00:00<00:07,  6.22it/s]
+
  6%|▌         | 3/50 [00:00<00:08,  5.77it/s]
+
  8%|▊         | 4/50 [00:00<00:08,  5.58it/s]
+
 10%|█         | 5/50 [00:00<00:08,  5.46it/s]
+
 12%|█▏        | 6/50 [00:01<00:08,  5.35it/s]
+
 14%|█▍        | 7/50 [00:01<00:08,  5.35it/s]
+
 16%|█▌        | 8/50 [00:01<00:07,  5.32it/s]
+
 18%|█▊        | 9/50 [00:01<00:07,  5.31it/s]
+
 20%|██        | 10/50 [00:01<00:07,  5.31it/s]
+
 22%|██▏       | 11/50 [00:02<00:07,  5.28it/s]
+
 24%|██▍       | 12/50 [00:02<00:07,  5.28it/s]
+
 26%|██▌       | 13/50 [00:02<00:07,  5.28it/s]
+
 28%|██▊       | 14/50 [00:02<00:06,  5.28it/s]
+
 30%|███       | 15/50 [00:02<00:06,  5.27it/s]
+
 32%|███▏      | 16/50 [00:02<00:06,  5.26it/s]
+
 34%|███▍      | 17/50 [00:03<00:06,  5.27it/s]
+
 36%|███▌      | 18/50 [00:03<00:06,  5.26it/s]
+
 38%|███▊      | 19/50 [00:03<00:05,  5.26it/s]
+
 40%|████      | 20/50 [00:03<00:05,  5.26it/s]
+
 42%|████▏     | 21/50 [00:03<00:05,  5.27it/s]
+
 44%|████▍     | 22/50 [00:04<00:05,  5.27it/s]
+
 46%|████▌     | 23/50 [00:04<00:05,  5.27it/s]
+
 48%|████▊     | 24/50 [00:04<00:04,  5.26it/s]
+
 50%|█████     | 25/50 [00:04<00:04,  5.27it/s]
+
 52%|█████▏    | 26/50 [00:04<00:04,  5.26it/s]
+
 54%|█████▍    | 27/50 [00:05<00:04,  5.27it/s]
+
 56%|█████▌    | 28/50 [00:05<00:04,  5.27it/s]
+
 58%|█████▊    | 29/50 [00:05<00:03,  5.27it/s]
+
 60%|██████    | 30/50 [00:05<00:03,  5.25it/s]
+
 62%|██████▏   | 31/50 [00:05<00:03,  5.26it/s]
+
 64%|██████▍   | 32/50 [00:06<00:03,  5.27it/s]
+
 66%|██████▌   | 33/50 [00:06<00:03,  5.26it/s]
+
 68%|██████▊   | 34/50 [00:06<00:03,  5.26it/s]
+
 70%|███████   | 35/50 [00:06<00:02,  5.26it/s]
+
 72%|███████▏  | 36/50 [00:06<00:02,  5.27it/s]
+
 74%|███████▍  | 37/50 [00:06<00:02,  5.26it/s]
+
 76%|███████▌  | 38/50 [00:07<00:02,  5.26it/s]
+
 78%|███████▊  | 39/50 [00:07<00:02,  5.27it/s]
+
 80%|████████  | 40/50 [00:07<00:01,  5.27it/s]
+
 82%|████████▏ | 41/50 [00:07<00:01,  5.27it/s]
+
 84%|████████▍ | 42/50 [00:07<00:01,  5.28it/s]
+
 86%|████████▌ | 43/50 [00:08<00:01,  5.26it/s]
+
 88%|████████▊ | 44/50 [00:08<00:01,  5.26it/s]
+
 90%|█████████ | 45/50 [00:08<00:00,  5.26it/s]
+
 92%|█████████▏| 46/50 [00:08<00:00,  5.26it/s]
+
 94%|█████████▍| 47/50 [00:08<00:00,  5.27it/s]
+
 96%|█████████▌| 48/50 [00:09<00:00,  5.27it/s]
+
 98%|█████████▊| 49/50 [00:09<00:00,  5.26it/s]
+
100%|██████████| 50/50 [00:09<00:00,  5.27it/s]
100%|██████████| 50/50 [00:09<00:00,  5.29it/s]
+10/13/2023 11:17:16 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
+
+
optimizer.bin:   0%|          | 0.00/47.4M [00:00<?, ?B/s]
+
+
pytorch_lora_weights.safetensors:   0%|          | 0.00/23.4M [00:00<?, ?B/s]
+
+
+
Upload 6 LFS files:   0%|          | 0/6 [00:00<?, ?it/s]
+
+
+
+
random_states_0.pkl:   0%|          | 0.00/14.6k [00:00<?, ?B/s]
+
+
+
+
+
scaler.pt:   0%|          | 0.00/557 [00:00<?, ?B/s]
+
+
+
+
+
+
scheduler.bin:   0%|          | 0.00/563 [00:00<?, ?B/s]
+
optimizer.bin:   0%|          | 8.19k/47.4M [00:00<57:56, 13.6kB/s]
+
+
pytorch_lora_weights.safetensors:   0%|          | 8.19k/23.4M [00:00<30:21, 12.8kB/s]
+
+
+
+
+
scaler.pt: 100%|██████████| 557/557 [00:00<00:00, 861B/s]
+
+
+
+
+
+
scheduler.bin: 100%|██████████| 563/563 [00:00<00:00, 873B/s]
+
+
+
+
random_states_0.pkl:  56%|█████▌    | 8.19k/14.6k [00:00<00:00, 12.3kB/s]
+
optimizer.bin:   1%|▏         | 614k/47.4M [00:00<00:41, 1.13MB/s] 
scaler.pt: 100%|██████████| 557/557 [00:00<00:00, 781B/s]
+
scheduler.bin: 100%|██████████| 563/563 [00:00<00:00, 776B/s]
+
+
+
pytorch_lora_weights.safetensors:   2%|▏         | 541k/23.4M [00:00<00:24, 934kB/s]  
random_states_0.pkl: 100%|██████████| 14.6k/14.6k [00:00<00:00, 18.5kB/s]
+
+
optimizer.bin:  12%|█▏        | 5.58M/47.4M [00:00<00:03, 10.7MB/s]
+
+
pytorch_lora_weights.safetensors:  16%|█▌        | 3.79M/23.4M [00:00<00:02, 7.21MB/s]
+
optimizer.bin:  32%|███▏      | 15.0M/47.4M [00:00<00:01, 27.7MB/s]
+
+
pytorch_lora_weights.safetensors:  25%|██▍       | 5.84M/23.4M [00:00<00:01, 10.1MB/s]
+
+
+
+
pytorch_lora_weights.safetensors:   0%|          | 0.00/23.4M [00:00<?, ?B/s]
+
optimizer.bin:  41%|████      | 19.2M/47.4M [00:01<00:01, 26.9MB/s]
+
+
+
+
pytorch_lora_weights.safetensors:   2%|▏         | 524k/23.4M [00:00<00:05, 4.02MB/s]
+
+
pytorch_lora_weights.safetensors:  36%|███▌      | 8.38M/23.4M [00:01<00:01, 11.4MB/s]
+
+
+
+
pytorch_lora_weights.safetensors:  23%|██▎       | 5.40M/23.4M [00:00<00:00, 27.4MB/s]
+
optimizer.bin:  59%|█████▉    | 28.1M/47.4M [00:01<00:00, 39.1MB/s]
+
+
pytorch_lora_weights.safetensors:  44%|████▍     | 10.3M/23.4M [00:01<00:00, 13.1MB/s]
+
+
+
+
pytorch_lora_weights.safetensors:  45%|████▌     | 10.6M/23.4M [00:00<00:00, 37.9MB/s]
+
+
pytorch_lora_weights.safetensors:  52%|█████▏    | 12.1M/23.4M [00:01<00:00, 13.8MB/s]
+
optimizer.bin:  70%|██████▉   | 33.1M/47.4M [00:01<00:00, 31.6MB/s]
+
+
+
+
pytorch_lora_weights.safetensors:  68%|██████▊   | 16.0M/23.4M [00:00<00:00, 34.8MB/s]
+
+
pytorch_lora_weights.safetensors:  63%|██████▎   | 14.8M/23.4M [00:01<00:00, 14.1MB/s]
+
optimizer.bin:  91%|█████████ | 43.0M/47.4M [00:01<00:00, 45.3MB/s]
optimizer.bin: 100%|██████████| 47.4M/47.4M [00:01<00:00, 26.1MB/s]
+
pytorch_lora_weights.safetensors: 100%|██████████| 23.4M/23.4M [00:00<00:00, 28.7MB/s]
+
+
+
pytorch_lora_weights.safetensors:  70%|███████   | 16.4M/23.4M [00:01<00:00, 10.4MB/s]
+
+
pytorch_lora_weights.safetensors:  91%|█████████ | 21.3M/23.4M [00:01<00:00, 17.6MB/s]
+
+
+
Upload 6 LFS files:  17%|█▋        | 1/6 [00:02<00:10,  2.06s/it]
pytorch_lora_weights.safetensors: 100%|██████████| 23.4M/23.4M [00:02<00:00, 9.71MB/s]
+
+
+
+
Upload 6 LFS files:  33%|███▎      | 2/6 [00:02<00:04,  1.21s/it]
Upload 6 LFS files: 100%|██████████| 6/6 [00:02<00:00,  2.25it/s]