log.txt

/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 09:36:24 - INFO - __main__ - Current working directory: /workspace/thumbs_up
10/13/2023 09:36:24 - 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.
{'thresholding', 'dynamic_thresholding_ratio', 'clip_sample_range', 'variance_type'} was not found in config. Values will be initialized to default values.
{'attention_type', 'dropout'} 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.weight', 'pooler.dense.bias']
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_093643-j7bfqg1u
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run fast-cloud-48
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/j7bfqg1u
10/13/2023 09:36:44 - INFO - __main__ - ***** Running training *****
10/13/2023 09:36:44 - INFO - __main__ -   Num examples = 21
10/13/2023 09:36:44 - INFO - __main__ -   Num batches each epoch = 11
10/13/2023 09:36:44 - INFO - __main__ -   Num Epochs = 55
10/13/2023 09:36:44 - INFO - __main__ -   Instantaneous batch size per device = 2
10/13/2023 09:36:44 - INFO - __main__ -   Total train batch size (w. parallel, distributed & accumulation) = 2
10/13/2023 09:36:44 - INFO - __main__ -   Gradient Accumulation steps = 1
10/13/2023 09:36:44 - 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<25:34,  2.56s/it]
Steps:   0%|          | 1/600 [00:02<25:34,  2.56s/it, loss=0.0509, lr=1e-5]
Steps:   0%|          | 2/600 [00:04<20:55,  2.10s/it, loss=0.0509, lr=1e-5]
Steps:   0%|          | 2/600 [00:04<20:55,  2.10s/it, loss=0.0944, lr=1e-5]
Steps:   0%|          | 3/600 [00:06<20:42,  2.08s/it, loss=0.0944, lr=1e-5]
Steps:   0%|          | 3/600 [00:06<20:42,  2.08s/it, loss=0.235, lr=1e-5] 
Steps:   1%|          | 4/600 [00:08<19:23,  1.95s/it, loss=0.235, lr=1e-5]
Steps:   1%|          | 4/600 [00:08<19:23,  1.95s/it, loss=0.0463, lr=1e-5]
Steps:   1%|          | 5/600 [00:09<18:16,  1.84s/it, loss=0.0463, lr=1e-5]
Steps:   1%|          | 5/600 [00:09<18:16,  1.84s/it, loss=0.061, lr=1e-5] 
Steps:   1%|          | 6/600 [00:11<18:07,  1.83s/it, loss=0.061, lr=1e-5]
Steps:   1%|          | 6/600 [00:11<18:07,  1.83s/it, loss=0.00999, lr=1e-5]
Steps:   1%|          | 7/600 [00:13<17:01,  1.72s/it, loss=0.00999, lr=1e-5]
Steps:   1%|          | 7/600 [00:13<17:01,  1.72s/it, loss=0.132, lr=1e-5]  
Steps:   1%|▏         | 8/600 [00:14<16:09,  1.64s/it, loss=0.132, lr=1e-5]
Steps:   1%|▏         | 8/600 [00:14<16:09,  1.64s/it, loss=0.134, lr=1e-5]
Steps:   2%|▏         | 9/600 [00:16<16:40,  1.69s/it, loss=0.134, lr=1e-5]
Steps:   2%|▏         | 9/600 [00:16<16:40,  1.69s/it, loss=0.0905, lr=1e-5]
Steps:   2%|▏         | 10/600 [00:17<15:44,  1.60s/it, loss=0.0905, lr=1e-5]
Steps:   2%|▏         | 10/600 [00:17<15:44,  1.60s/it, loss=0.0586, lr=1e-5]
Steps:   2%|▏         | 11/600 [00:18<13:39,  1.39s/it, loss=0.0586, lr=1e-5]
Steps:   2%|▏         | 11/600 [00:18<13:39,  1.39s/it, loss=0.291, lr=1e-5] 10/13/2023 09:37:03 - 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 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...:  57%|█████▋    | 4/7 [00:00<00:00, 39.78it/s]Loaded scheduler as EulerDiscreteScheduler from `scheduler` subfolder of stabilityai/stable-diffusion-xl-base-1.0.

Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 67.51it/s]
{'solver_type', 'algorithm_type', 'lambda_min_clipped', 'lower_order_final', 'variance_type', 'solver_order', 'thresholding', 'dynamic_thresholding_ratio'} was not found in config. Values will be initialized to default values.
10/13/2023 09:38:01 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
10/13/2023 09:38:50 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
10/13/2023 09:39:40 - INFO - __main__ - Image features shape: torch.Size([5, 75648])

Steps:   2%|▏         | 12/600 [03:05<8:27:28, 51.78s/it, loss=0.291, lr=1e-5]
Steps:   2%|▏         | 12/600 [03:05<8:27:28, 51.78s/it, loss=0.143, lr=1e-5]
Steps:   2%|▏         | 13/600 [03:07<5:59:00, 36.70s/it, loss=0.143, lr=1e-5]
Steps:   2%|▏         | 13/600 [03:07<5:59:00, 36.70s/it, loss=0.103, lr=1e-5]
Steps:   2%|▏         | 14/600 [03:09<4:14:35, 26.07s/it, loss=0.103, lr=1e-5]
Steps:   2%|▏         | 14/600 [03:09<4:14:35, 26.07s/it, loss=0.185, lr=1e-5]
Steps:   2%|▎         | 15/600 [03:10<3:01:49, 18.65s/it, loss=0.185, lr=1e-5]
Steps:   2%|▎         | 15/600 [03:10<3:01:49, 18.65s/it, loss=0.137, lr=1e-5]
Steps:   3%|▎         | 16/600 [03:12<2:11:25, 13.50s/it, loss=0.137, lr=1e-5]
Steps:   3%|▎         | 16/600 [03:12<2:11:25, 13.50s/it, loss=0.0199, lr=1e-5]
Steps:   3%|▎         | 17/600 [03:14<1:37:05,  9.99s/it, loss=0.0199, lr=1e-5]
Steps:   3%|▎         | 17/600 [03:14<1:37:05,  9.99s/it, loss=0.15, lr=1e-5]  
Steps:   3%|▎         | 18/600 [03:15<1:13:15,  7.55s/it, loss=0.15, lr=1e-5]
Steps:   3%|▎         | 18/600 [03:15<1:13:15,  7.55s/it, loss=0.113, lr=1e-5]
Steps:   3%|▎         | 19/600 [03:17<55:40,  5.75s/it, loss=0.113, lr=1e-5]  
Steps:   3%|▎         | 19/600 [03:17<55:40,  5.75s/it, loss=0.184, lr=1e-5]
Steps:   3%|▎         | 20/600 [03:19<43:45,  4.53s/it, loss=0.184, lr=1e-5]
Steps:   3%|▎         | 20/600 [03:19<43:45,  4.53s/it, loss=0.144, lr=1e-5]
Steps:   4%|▎         | 21/600 [03:20<34:30,  3.58s/it, loss=0.144, lr=1e-5]
Steps:   4%|▎         | 21/600 [03:20<34:30,  3.58s/it, loss=0.103, lr=1e-5]
Steps:   4%|▎         | 22/600 [03:21<26:19,  2.73s/it, loss=0.103, lr=1e-5]
Steps:   4%|▎         | 22/600 [03:21<26:19,  2.73s/it, loss=0.319, lr=1e-5]
Steps:   4%|▍         | 23/600 [03:23<24:48,  2.58s/it, loss=0.319, lr=1e-5]
Steps:   4%|▍         | 23/600 [03:23<24:48,  2.58s/it, loss=0.0735, lr=1e-5]
Steps:   4%|▍         | 24/600 [03:24<21:30,  2.24s/it, loss=0.0735, lr=1e-5]
Steps:   4%|▍         | 24/600 [03:24<21:30,  2.24s/it, loss=0.097, lr=1e-5] 
Steps:   4%|▍         | 25/600 [03:26<19:59,  2.09s/it, loss=0.097, lr=1e-5]
Steps:   4%|▍         | 25/600 [03:26<19:59,  2.09s/it, loss=0.0828, lr=1e-5]
Steps:   4%|▍         | 26/600 [03:28<18:54,  1.98s/it, loss=0.0828, lr=1e-5]
Steps:   4%|▍         | 26/600 [03:28<18:54,  1.98s/it, loss=0.0611, lr=1e-5]
Steps:   4%|▍         | 27/600 [03:30<18:13,  1.91s/it, loss=0.0611, lr=1e-5]
Steps:   4%|▍         | 27/600 [03:30<18:13,  1.91s/it, loss=0.197, lr=1e-5] 
Steps:   5%|▍         | 28/600 [03:31<16:27,  1.73s/it, loss=0.197, lr=1e-5]
Steps:   5%|▍         | 28/600 [03:31<16:27,  1.73s/it, loss=0.0579, lr=1e-5]
Steps:   5%|▍         | 29/600 [03:33<16:44,  1.76s/it, loss=0.0579, lr=1e-5]
Steps:   5%|▍         | 29/600 [03:33<16:44,  1.76s/it, loss=0.00545, lr=1e-5]
Steps:   5%|▌         | 30/600 [03:35<16:58,  1.79s/it, loss=0.00545, lr=1e-5]
Steps:   5%|▌         | 30/600 [03:35<16:58,  1.79s/it, loss=0.151, lr=1e-5]  
Steps:   5%|▌         | 31/600 [03:36<16:17,  1.72s/it, loss=0.151, lr=1e-5]
Steps:   5%|▌         | 31/600 [03:36<16:17,  1.72s/it, loss=0.0865, lr=1e-5]
Steps:   5%|▌         | 32/600 [03:37<14:35,  1.54s/it, loss=0.0865, lr=1e-5]
Steps:   5%|▌         | 32/600 [03:37<14:35,  1.54s/it, loss=0.142, lr=1e-5] 
Steps:   6%|▌         | 33/600 [03:38<12:18,  1.30s/it, loss=0.142, lr=1e-5]
Steps:   6%|▌         | 33/600 [03:38<12:18,  1.30s/it, loss=0.0126, lr=1e-5]
Steps:   6%|▌         | 34/600 [03:41<15:32,  1.65s/it, loss=0.0126, lr=1e-5]
Steps:   6%|▌         | 34/600 [03:41<15:32,  1.65s/it, loss=0.0877, lr=1e-5]
Steps:   6%|▌         | 35/600 [03:42<14:39,  1.56s/it, loss=0.0877, lr=1e-5]
Steps:   6%|▌         | 35/600 [03:42<14:39,  1.56s/it, loss=0.136, lr=1e-5] 
Steps:   6%|▌         | 36/600 [03:43<14:22,  1.53s/it, loss=0.136, lr=1e-5]
Steps:   6%|▌         | 36/600 [03:43<14:22,  1.53s/it, loss=0.0608, lr=1e-5]
Steps:   6%|▌         | 37/600 [03:45<14:08,  1.51s/it, loss=0.0608, lr=1e-5]
Steps:   6%|▌         | 37/600 [03:45<14:08,  1.51s/it, loss=0.197, lr=1e-5] 
Steps:   6%|▋         | 38/600 [03:46<14:34,  1.56s/it, loss=0.197, lr=1e-5]
Steps:   6%|▋         | 38/600 [03:46<14:34,  1.56s/it, loss=0.184, lr=1e-5]
Steps:   6%|▋         | 39/600 [03:48<14:27,  1.55s/it, loss=0.184, lr=1e-5]
Steps:   6%|▋         | 39/600 [03:48<14:27,  1.55s/it, loss=0.175, lr=1e-5]
Steps:   7%|▋         | 40/600 [03:50<14:27,  1.55s/it, loss=0.175, lr=1e-5]
Steps:   7%|▋         | 40/600 [03:50<14:27,  1.55s/it, loss=0.0726, lr=1e-5]
Steps:   7%|▋         | 41/600 [03:51<15:14,  1.64s/it, loss=0.0726, lr=1e-5]
Steps:   7%|▋         | 41/600 [03:51<15:14,  1.64s/it, loss=0.0252, lr=1e-5]
Steps:   7%|▋         | 42/600 [03:53<15:07,  1.63s/it, loss=0.0252, lr=1e-5]
Steps:   7%|▋         | 42/600 [03:53<15:07,  1.63s/it, loss=0.173, lr=1e-5] 
Steps:   7%|▋         | 43/600 [03:54<14:34,  1.57s/it, loss=0.173, lr=1e-5]
Steps:   7%|▋         | 43/600 [03:54<14:34,  1.57s/it, loss=0.247, lr=1e-5]
Steps:   7%|▋         | 44/600 [03:55<12:15,  1.32s/it, loss=0.247, lr=1e-5]
Steps:   7%|▋         | 44/600 [03:55<12:15,  1.32s/it, loss=0.0923, lr=1e-5]
Steps:   8%|▊         | 45/600 [03:57<13:23,  1.45s/it, loss=0.0923, lr=1e-5]
Steps:   8%|▊         | 45/600 [03:57<13:23,  1.45s/it, loss=0.0788, lr=1e-5]
Steps:   8%|▊         | 46/600 [03:58<13:36,  1.47s/it, loss=0.0788, lr=1e-5]
Steps:   8%|▊         | 46/600 [03:58<13:36,  1.47s/it, loss=0.24, lr=1e-5]  
Steps:   8%|▊         | 47/600 [04:00<14:14,  1.55s/it, loss=0.24, lr=1e-5]
Steps:   8%|▊         | 47/600 [04:00<14:14,  1.55s/it, loss=0.15, lr=1e-5]
Steps:   8%|▊         | 48/600 [04:02<15:01,  1.63s/it, loss=0.15, lr=1e-5]
Steps:   8%|▊         | 48/600 [04:02<15:01,  1.63s/it, loss=0.0207, lr=1e-5]
Steps:   8%|▊         | 49/600 [04:04<14:55,  1.63s/it, loss=0.0207, lr=1e-5]
Steps:   8%|▊         | 49/600 [04:04<14:55,  1.63s/it, loss=0.263, lr=1e-5] 
Steps:   8%|▊         | 50/600 [04:05<14:53,  1.62s/it, loss=0.263, lr=1e-5]
Steps:   8%|▊         | 50/600 [04:05<14:53,  1.62s/it, loss=0.169, lr=1e-5]
Steps:   8%|▊         | 51/600 [04:07<14:57,  1.64s/it, loss=0.169, lr=1e-5]
Steps:   8%|▊         | 51/600 [04:07<14:57,  1.64s/it, loss=0.172, lr=1e-5]
Steps:   9%|▊         | 52/600 [04:09<15:07,  1.66s/it, loss=0.172, lr=1e-5]
Steps:   9%|▊         | 52/600 [04:09<15:07,  1.66s/it, loss=0.138, lr=1e-5]
Steps:   9%|▉         | 53/600 [04:10<14:12,  1.56s/it, loss=0.138, lr=1e-5]
Steps:   9%|▉         | 53/600 [04:10<14:12,  1.56s/it, loss=0.151, lr=1e-5]
Steps:   9%|▉         | 54/600 [04:11<13:48,  1.52s/it, loss=0.151, lr=1e-5]
Steps:   9%|▉         | 54/600 [04:11<13:48,  1.52s/it, loss=0.0254, lr=1e-5]
Steps:   9%|▉         | 55/600 [04:12<11:40,  1.29s/it, loss=0.0254, lr=1e-5]
Steps:   9%|▉         | 55/600 [04:12<11:40,  1.29s/it, loss=0.0718, lr=1e-5]
Steps:   9%|▉         | 56/600 [04:14<14:39,  1.62s/it, loss=0.0718, lr=1e-5]
Steps:   9%|▉         | 56/600 [04:14<14:39,  1.62s/it, loss=0.162, lr=1e-5] 
Steps:  10%|▉         | 57/600 [04:16<14:53,  1.65s/it, loss=0.162, lr=1e-5]
Steps:  10%|▉         | 57/600 [04:16<14:53,  1.65s/it, loss=0.0126, lr=1e-5]
Steps:  10%|▉         | 58/600 [04:18<14:02,  1.55s/it, loss=0.0126, lr=1e-5]
Steps:  10%|▉         | 58/600 [04:18<14:02,  1.55s/it, loss=0.169, lr=1e-5] 
Steps:  10%|▉         | 59/600 [04:19<13:56,  1.55s/it, loss=0.169, lr=1e-5]
Steps:  10%|▉         | 59/600 [04:19<13:56,  1.55s/it, loss=0.155, lr=1e-5]
Steps:  10%|█         | 60/600 [04:21<13:46,  1.53s/it, loss=0.155, lr=1e-5]
Steps:  10%|█         | 60/600 [04:21<13:46,  1.53s/it, loss=0.0706, lr=1e-5]
Steps:  10%|█         | 61/600 [04:22<13:56,  1.55s/it, loss=0.0706, lr=1e-5]
Steps:  10%|█         | 61/600 [04:22<13:56,  1.55s/it, loss=0.105, lr=1e-5] 
Steps:  10%|█         | 62/600 [04:24<13:27,  1.50s/it, loss=0.105, lr=1e-5]
Steps:  10%|█         | 62/600 [04:24<13:27,  1.50s/it, loss=0.0642, lr=1e-5]
Steps:  10%|█         | 63/600 [04:25<14:15,  1.59s/it, loss=0.0642, lr=1e-5]
Steps:  10%|█         | 63/600 [04:25<14:15,  1.59s/it, loss=0.136, lr=1e-5] 
Steps:  11%|█         | 64/600 [04:27<14:25,  1.62s/it, loss=0.136, lr=1e-5]
Steps:  11%|█         | 64/600 [04:27<14:25,  1.62s/it, loss=0.169, lr=1e-5]
Steps:  11%|█         | 65/600 [04:28<13:18,  1.49s/it, loss=0.169, lr=1e-5]
Steps:  11%|█         | 65/600 [04:28<13:18,  1.49s/it, loss=0.0593, lr=1e-5]
Steps:  11%|█         | 66/600 [04:29<11:18,  1.27s/it, loss=0.0593, lr=1e-5]
Steps:  11%|█         | 66/600 [04:29<11:18,  1.27s/it, loss=0.00237, lr=1e-5]
Steps:  11%|█         | 67/600 [04:31<13:49,  1.56s/it, loss=0.00237, lr=1e-5]
Steps:  11%|█         | 67/600 [04:31<13:49,  1.56s/it, loss=0.0978, lr=1e-5] 
Steps:  11%|█▏        | 68/600 [04:33<13:36,  1.53s/it, loss=0.0978, lr=1e-5]
Steps:  11%|█▏        | 68/600 [04:33<13:36,  1.53s/it, loss=0.1, lr=1e-5]   
Steps:  12%|█▏        | 69/600 [04:34<14:04,  1.59s/it, loss=0.1, lr=1e-5]
Steps:  12%|█▏        | 69/600 [04:34<14:04,  1.59s/it, loss=0.201, lr=1e-5]
Steps:  12%|█▏        | 70/600 [04:36<14:44,  1.67s/it, loss=0.201, lr=1e-5]
Steps:  12%|█▏        | 70/600 [04:36<14:44,  1.67s/it, loss=0.144, lr=1e-5]
Steps:  12%|█▏        | 71/600 [04:38<14:34,  1.65s/it, loss=0.144, lr=1e-5]
Steps:  12%|█▏        | 71/600 [04:38<14:34,  1.65s/it, loss=0.0462, lr=1e-5]
Steps:  12%|█▏        | 72/600 [04:39<14:15,  1.62s/it, loss=0.0462, lr=1e-5]
Steps:  12%|█▏        | 72/600 [04:39<14:15,  1.62s/it, loss=0.0287, lr=1e-5]
Steps:  12%|█▏        | 73/600 [04:41<13:50,  1.58s/it, loss=0.0287, lr=1e-5]
Steps:  12%|█▏        | 73/600 [04:41<13:50,  1.58s/it, loss=0.0162, lr=1e-5]
Steps:  12%|█▏        | 74/600 [04:43<14:07,  1.61s/it, loss=0.0162, lr=1e-5]
Steps:  12%|█▏        | 74/600 [04:43<14:07,  1.61s/it, loss=0.114, lr=1e-5] 
Steps:  12%|█▎        | 75/600 [04:44<14:18,  1.64s/it, loss=0.114, lr=1e-5]
Steps:  12%|█▎        | 75/600 [04:44<14:18,  1.64s/it, loss=0.0513, lr=1e-5]
Steps:  13%|█▎        | 76/600 [04:46<13:19,  1.53s/it, loss=0.0513, lr=1e-5]
Steps:  13%|█▎        | 76/600 [04:46<13:19,  1.53s/it, loss=0.141, lr=1e-5] 
Steps:  13%|█▎        | 77/600 [04:46<11:17,  1.30s/it, loss=0.141, lr=1e-5]
Steps:  13%|█▎        | 77/600 [04:46<11:17,  1.30s/it, loss=0.00219, lr=1e-5]
Steps:  13%|█▎        | 78/600 [04:49<13:39,  1.57s/it, loss=0.00219, lr=1e-5]
Steps:  13%|█▎        | 78/600 [04:49<13:39,  1.57s/it, loss=0.0584, lr=1e-5] 
Steps:  13%|█▎        | 79/600 [04:50<13:54,  1.60s/it, loss=0.0584, lr=1e-5]
Steps:  13%|█▎        | 79/600 [04:50<13:54,  1.60s/it, loss=0.21, lr=1e-5]  
Steps:  13%|█▎        | 80/600 [04:52<13:37,  1.57s/it, loss=0.21, lr=1e-5]
Steps:  13%|█▎        | 80/600 [04:52<13:37,  1.57s/it, loss=0.0341, lr=1e-5]
Steps:  14%|█▎        | 81/600 [04:53<14:02,  1.62s/it, loss=0.0341, lr=1e-5]
Steps:  14%|█▎        | 81/600 [04:53<14:02,  1.62s/it, loss=0.111, lr=1e-5] 
Steps:  14%|█▎        | 82/600 [04:55<14:10,  1.64s/it, loss=0.111, lr=1e-5]
Steps:  14%|█▎        | 82/600 [04:55<14:10,  1.64s/it, loss=0.0387, lr=1e-5]
Steps:  14%|█▍        | 83/600 [04:56<13:03,  1.51s/it, loss=0.0387, lr=1e-5]
Steps:  14%|█▍        | 83/600 [04:56<13:03,  1.51s/it, loss=0.0327, lr=1e-5]
Steps:  14%|█▍        | 84/600 [04:58<13:57,  1.62s/it, loss=0.0327, lr=1e-5]
Steps:  14%|█▍        | 84/600 [04:58<13:57,  1.62s/it, loss=0.0769, lr=1e-5]
Steps:  14%|█▍        | 85/600 [05:00<13:55,  1.62s/it, loss=0.0769, lr=1e-5]
Steps:  14%|█▍        | 85/600 [05:00<13:55,  1.62s/it, loss=0.202, lr=1e-5] 
Steps:  14%|█▍        | 86/600 [05:01<13:59,  1.63s/it, loss=0.202, lr=1e-5]
Steps:  14%|█▍        | 86/600 [05:01<13:59,  1.63s/it, loss=0.03, lr=1e-5] 
Steps:  14%|█▍        | 87/600 [05:03<12:57,  1.51s/it, loss=0.03, lr=1e-5]
Steps:  14%|█▍        | 87/600 [05:03<12:57,  1.51s/it, loss=0.195, lr=1e-5]
Steps:  15%|█▍        | 88/600 [05:03<11:00,  1.29s/it, loss=0.195, lr=1e-5]
Steps:  15%|█▍        | 88/600 [05:03<11:00,  1.29s/it, loss=0.397, lr=1e-5]
Steps:  15%|█▍        | 89/600 [05:06<13:15,  1.56s/it, loss=0.397, lr=1e-5]
Steps:  15%|█▍        | 89/600 [05:06<13:15,  1.56s/it, loss=0.0852, lr=1e-5]
Steps:  15%|█▌        | 90/600 [05:07<12:55,  1.52s/it, loss=0.0852, lr=1e-5]
Steps:  15%|█▌        | 90/600 [05:07<12:55,  1.52s/it, loss=0.156, lr=1e-5] 
Steps:  15%|█▌        | 91/600 [05:09<13:23,  1.58s/it, loss=0.156, lr=1e-5]
Steps:  15%|█▌        | 91/600 [05:09<13:23,  1.58s/it, loss=0.063, lr=1e-5]
Steps:  15%|█▌        | 92/600 [05:10<13:34,  1.60s/it, loss=0.063, lr=1e-5]
Steps:  15%|█▌        | 92/600 [05:10<13:34,  1.60s/it, loss=0.143, lr=1e-5]
Steps:  16%|█▌        | 93/600 [05:12<13:54,  1.65s/it, loss=0.143, lr=1e-5]
Steps:  16%|█▌        | 93/600 [05:12<13:54,  1.65s/it, loss=0.00501, lr=1e-5]
Steps:  16%|█▌        | 94/600 [05:14<13:53,  1.65s/it, loss=0.00501, lr=1e-5]
Steps:  16%|█▌        | 94/600 [05:14<13:53,  1.65s/it, loss=0.112, lr=1e-5]  
Steps:  16%|█▌        | 95/600 [05:16<13:52,  1.65s/it, loss=0.112, lr=1e-5]
Steps:  16%|█▌        | 95/600 [05:16<13:52,  1.65s/it, loss=0.0725, lr=1e-5]
Steps:  16%|█▌        | 96/600 [05:17<13:11,  1.57s/it, loss=0.0725, lr=1e-5]
Steps:  16%|█▌        | 96/600 [05:17<13:11,  1.57s/it, loss=0.0149, lr=1e-5]
Steps:  16%|█▌        | 97/600 [05:19<13:30,  1.61s/it, loss=0.0149, lr=1e-5]
Steps:  16%|█▌        | 97/600 [05:19<13:30,  1.61s/it, loss=0.00489, lr=1e-5]
Steps:  16%|█▋        | 98/600 [05:20<12:59,  1.55s/it, loss=0.00489, lr=1e-5]
Steps:  16%|█▋        | 98/600 [05:20<12:59,  1.55s/it, loss=0.131, lr=1e-5]  
Steps:  16%|█▋        | 99/600 [05:21<10:58,  1.31s/it, loss=0.131, lr=1e-5]
Steps:  16%|█▋        | 99/600 [05:21<10:58,  1.31s/it, loss=0.251, lr=1e-5]
Steps:  17%|█▋        | 100/600 [05:23<12:26,  1.49s/it, loss=0.251, lr=1e-5]
Steps:  17%|█▋        | 100/600 [05:23<12:26,  1.49s/it, loss=0.228, lr=1e-5]
Steps:  17%|█▋        | 101/600 [05:24<13:08,  1.58s/it, loss=0.228, lr=1e-5]
Steps:  17%|█▋        | 101/600 [05:24<13:08,  1.58s/it, loss=0.0422, lr=1e-5]
Steps:  17%|█▋        | 102/600 [05:26<12:59,  1.56s/it, loss=0.0422, lr=1e-5]
Steps:  17%|█▋        | 102/600 [05:26<12:59,  1.56s/it, loss=0.0085, lr=1e-5]
Steps:  17%|█▋        | 103/600 [05:28<12:52,  1.55s/it, loss=0.0085, lr=1e-5]
Steps:  17%|█▋        | 103/600 [05:28<12:52,  1.55s/it, loss=0.11, lr=1e-5]  
Steps:  17%|█▋        | 104/600 [05:29<13:17,  1.61s/it, loss=0.11, lr=1e-5]
Steps:  17%|█▋        | 104/600 [05:29<13:17,  1.61s/it, loss=0.0145, lr=1e-5]
Steps:  18%|█▊        | 105/600 [05:31<13:46,  1.67s/it, loss=0.0145, lr=1e-5]
Steps:  18%|█▊        | 105/600 [05:31<13:46,  1.67s/it, loss=0.186, lr=1e-5] 
Steps:  18%|█▊        | 106/600 [05:33<13:40,  1.66s/it, loss=0.186, lr=1e-5]
Steps:  18%|█▊        | 106/600 [05:33<13:40,  1.66s/it, loss=0.0979, lr=1e-5]
Steps:  18%|█▊        | 107/600 [05:34<13:36,  1.66s/it, loss=0.0979, lr=1e-5]
Steps:  18%|█▊        | 107/600 [05:34<13:36,  1.66s/it, loss=0.206, lr=1e-5] 
Steps:  18%|█▊        | 108/600 [05:36<13:24,  1.63s/it, loss=0.206, lr=1e-5]
Steps:  18%|█▊        | 108/600 [05:36<13:24,  1.63s/it, loss=0.055, lr=1e-5]
Steps:  18%|█▊        | 109/600 [05:37<12:15,  1.50s/it, loss=0.055, lr=1e-5]
Steps:  18%|█▊        | 109/600 [05:37<12:15,  1.50s/it, loss=0.0296, lr=1e-5]
Steps:  18%|█▊        | 110/600 [05:38<10:23,  1.27s/it, loss=0.0296, lr=1e-5]
Steps:  18%|█▊        | 110/600 [05:38<10:23,  1.27s/it, loss=0.321, lr=1e-5] 
Steps:  18%|█▊        | 111/600 [05:40<12:27,  1.53s/it, loss=0.321, lr=1e-5]
Steps:  18%|█▊        | 111/600 [05:40<12:27,  1.53s/it, loss=0.12, lr=1e-5] 
Steps:  19%|█▊        | 112/600 [05:41<12:18,  1.51s/it, loss=0.12, lr=1e-5]
Steps:  19%|█▊        | 112/600 [05:41<12:18,  1.51s/it, loss=0.159, lr=1e-5]
Steps:  19%|█▉        | 113/600 [05:43<12:25,  1.53s/it, loss=0.159, lr=1e-5]
Steps:  19%|█▉        | 113/600 [05:43<12:25,  1.53s/it, loss=0.198, lr=1e-5]
Steps:  19%|█▉        | 114/600 [05:45<13:08,  1.62s/it, loss=0.198, lr=1e-5]
Steps:  19%|█▉        | 114/600 [05:45<13:08,  1.62s/it, loss=0.0345, lr=1e-5]
Steps:  19%|█▉        | 115/600 [05:47<13:16,  1.64s/it, loss=0.0345, lr=1e-5]
Steps:  19%|█▉        | 115/600 [05:47<13:16,  1.64s/it, loss=0.265, lr=1e-5] 
Steps:  19%|█▉        | 116/600 [05:48<12:31,  1.55s/it, loss=0.265, lr=1e-5]
Steps:  19%|█▉        | 116/600 [05:48<12:31,  1.55s/it, loss=0.00317, lr=1e-5]
Steps:  20%|█▉        | 117/600 [05:50<13:14,  1.64s/it, loss=0.00317, lr=1e-5]
Steps:  20%|█▉        | 117/600 [05:50<13:14,  1.64s/it, loss=0.0196, lr=1e-5] 
Steps:  20%|█▉        | 118/600 [05:51<12:38,  1.57s/it, loss=0.0196, lr=1e-5]
Steps:  20%|█▉        | 118/600 [05:51<12:38,  1.57s/it, loss=0.051, lr=1e-5] 
Steps:  20%|█▉        | 119/600 [05:53<12:51,  1.60s/it, loss=0.051, lr=1e-5]
Steps:  20%|█▉        | 119/600 [05:53<12:51,  1.60s/it, loss=0.0172, lr=1e-5]
Steps:  20%|██        | 120/600 [05:54<12:19,  1.54s/it, loss=0.0172, lr=1e-5]
Steps:  20%|██        | 120/600 [05:54<12:19,  1.54s/it, loss=0.2, lr=1e-5]   
Steps:  20%|██        | 121/600 [05:55<10:26,  1.31s/it, loss=0.2, lr=1e-5]
Steps:  20%|██        | 121/600 [05:55<10:26,  1.31s/it, loss=0.359, lr=1e-5]
Steps:  20%|██        | 122/600 [05:58<13:32,  1.70s/it, loss=0.359, lr=1e-5]
Steps:  20%|██        | 122/600 [05:58<13:32,  1.70s/it, loss=0.0328, lr=1e-5]
Steps:  20%|██        | 123/600 [05:59<13:16,  1.67s/it, loss=0.0328, lr=1e-5]
Steps:  20%|██        | 123/600 [05:59<13:16,  1.67s/it, loss=0.0208, lr=1e-5]
Steps:  21%|██        | 124/600 [06:01<12:59,  1.64s/it, loss=0.0208, lr=1e-5]
Steps:  21%|██        | 124/600 [06:01<12:59,  1.64s/it, loss=0.0853, lr=1e-5]
Steps:  21%|██        | 125/600 [06:02<13:00,  1.64s/it, loss=0.0853, lr=1e-5]
Steps:  21%|██        | 125/600 [06:02<13:00,  1.64s/it, loss=0.0879, lr=1e-5]
Steps:  21%|██        | 126/600 [06:04<12:55,  1.64s/it, loss=0.0879, lr=1e-5]
Steps:  21%|██        | 126/600 [06:04<12:55,  1.64s/it, loss=0.132, lr=1e-5] 
Steps:  21%|██        | 127/600 [06:06<12:32,  1.59s/it, loss=0.132, lr=1e-5]
Steps:  21%|██        | 127/600 [06:06<12:32,  1.59s/it, loss=0.1, lr=1e-5]  
Steps:  21%|██▏       | 128/600 [06:07<12:21,  1.57s/it, loss=0.1, lr=1e-5]
Steps:  21%|██▏       | 128/600 [06:07<12:21,  1.57s/it, loss=0.0353, lr=1e-5]
Steps:  22%|██▏       | 129/600 [06:09<12:37,  1.61s/it, loss=0.0353, lr=1e-5]
Steps:  22%|██▏       | 129/600 [06:09<12:37,  1.61s/it, loss=0.0891, lr=1e-5]
Steps:  22%|██▏       | 130/600 [06:10<12:41,  1.62s/it, loss=0.0891, lr=1e-5]
Steps:  22%|██▏       | 130/600 [06:10<12:41,  1.62s/it, loss=0.0567, lr=1e-5]
Steps:  22%|██▏       | 131/600 [06:12<11:27,  1.47s/it, loss=0.0567, lr=1e-5]
Steps:  22%|██▏       | 131/600 [06:12<11:27,  1.47s/it, loss=0.155, lr=1e-5] 
Steps:  22%|██▏       | 132/600 [06:12<09:47,  1.26s/it, loss=0.155, lr=1e-5]
Steps:  22%|██▏       | 132/600 [06:12<09:47,  1.26s/it, loss=0.364, lr=1e-5]
Steps:  22%|██▏       | 133/600 [06:14<11:53,  1.53s/it, loss=0.364, lr=1e-5]
Steps:  22%|██▏       | 133/600 [06:14<11:53,  1.53s/it, loss=0.0939, lr=1e-5]
Steps:  22%|██▏       | 134/600 [06:16<12:13,  1.57s/it, loss=0.0939, lr=1e-5]
Steps:  22%|██▏       | 134/600 [06:16<12:13,  1.57s/it, loss=0.0813, lr=1e-5]
Steps:  22%|██▎       | 135/600 [06:18<12:35,  1.63s/it, loss=0.0813, lr=1e-5]
Steps:  22%|██▎       | 135/600 [06:18<12:35,  1.63s/it, loss=0.0717, lr=1e-5]
Steps:  23%|██▎       | 136/600 [06:20<12:56,  1.67s/it, loss=0.0717, lr=1e-5]
Steps:  23%|██▎       | 136/600 [06:20<12:56,  1.67s/it, loss=0.113, lr=1e-5] 
Steps:  23%|██▎       | 137/600 [06:21<13:09,  1.71s/it, loss=0.113, lr=1e-5]
Steps:  23%|██▎       | 137/600 [06:21<13:09,  1.71s/it, loss=0.104, lr=1e-5]
Steps:  23%|██▎       | 138/600 [06:23<13:09,  1.71s/it, loss=0.104, lr=1e-5]
Steps:  23%|██▎       | 138/600 [06:23<13:09,  1.71s/it, loss=0.127, lr=1e-5]
Steps:  23%|██▎       | 139/600 [06:25<12:56,  1.68s/it, loss=0.127, lr=1e-5]
Steps:  23%|██▎       | 139/600 [06:25<12:56,  1.68s/it, loss=0.0207, lr=1e-5]
Steps:  23%|██▎       | 140/600 [06:26<12:34,  1.64s/it, loss=0.0207, lr=1e-5]
Steps:  23%|██▎       | 140/600 [06:26<12:34,  1.64s/it, loss=0.187, lr=1e-5] 
Steps:  24%|██▎       | 141/600 [06:28<11:55,  1.56s/it, loss=0.187, lr=1e-5]
Steps:  24%|██▎       | 141/600 [06:28<11:55,  1.56s/it, loss=0.0773, lr=1e-5]
Steps:  24%|██▎       | 142/600 [06:29<10:56,  1.43s/it, loss=0.0773, lr=1e-5]
Steps:  24%|██▎       | 142/600 [06:29<10:56,  1.43s/it, loss=0.104, lr=1e-5] 
Steps:  24%|██▍       | 143/600 [06:30<09:23,  1.23s/it, loss=0.104, lr=1e-5]
Steps:  24%|██▍       | 143/600 [06:30<09:23,  1.23s/it, loss=0.112, lr=1e-5]
Steps:  24%|██▍       | 144/600 [06:32<12:21,  1.63s/it, loss=0.112, lr=1e-5]
Steps:  24%|██▍       | 144/600 [06:32<12:21,  1.63s/it, loss=0.0305, lr=1e-5]
Steps:  24%|██▍       | 145/600 [06:34<12:40,  1.67s/it, loss=0.0305, lr=1e-5]
Steps:  24%|██▍       | 145/600 [06:34<12:40,  1.67s/it, loss=0.0494, lr=1e-5]
Steps:  24%|██▍       | 146/600 [06:35<12:12,  1.61s/it, loss=0.0494, lr=1e-5]
Steps:  24%|██▍       | 146/600 [06:35<12:12,  1.61s/it, loss=0.0274, lr=1e-5]
Steps:  24%|██▍       | 147/600 [06:37<12:15,  1.62s/it, loss=0.0274, lr=1e-5]
Steps:  24%|██▍       | 147/600 [06:37<12:15,  1.62s/it, loss=0.148, lr=1e-5] 
Steps:  25%|██▍       | 148/600 [06:39<12:04,  1.60s/it, loss=0.148, lr=1e-5]
Steps:  25%|██▍       | 148/600 [06:39<12:04,  1.60s/it, loss=0.0483, lr=1e-5]
Steps:  25%|██▍       | 149/600 [06:40<12:19,  1.64s/it, loss=0.0483, lr=1e-5]
Steps:  25%|██▍       | 149/600 [06:40<12:19,  1.64s/it, loss=0.0314, lr=1e-5]
Steps:  25%|██▌       | 150/600 [06:42<12:17,  1.64s/it, loss=0.0314, lr=1e-5]
Steps:  25%|██▌       | 150/600 [06:42<12:17,  1.64s/it, loss=0.3, lr=1e-5]   
Steps:  25%|██▌       | 151/600 [06:44<12:03,  1.61s/it, loss=0.3, lr=1e-5]
Steps:  25%|██▌       | 151/600 [06:44<12:03,  1.61s/it, loss=0.215, lr=1e-5]
Steps:  25%|██▌       | 152/600 [06:45<11:19,  1.52s/it, loss=0.215, lr=1e-5]
Steps:  25%|██▌       | 152/600 [06:45<11:19,  1.52s/it, loss=0.103, lr=1e-5]
Steps:  26%|██▌       | 153/600 [06:46<10:47,  1.45s/it, loss=0.103, lr=1e-5]
Steps:  26%|██▌       | 153/600 [06:46<10:47,  1.45s/it, loss=0.172, lr=1e-5]
Steps:  26%|██▌       | 154/600 [06:47<09:12,  1.24s/it, loss=0.172, lr=1e-5]
Steps:  26%|██▌       | 154/600 [06:47<09:12,  1.24s/it, loss=0.00458, lr=1e-5]
Steps:  26%|██▌       | 155/600 [06:50<12:19,  1.66s/it, loss=0.00458, lr=1e-5]
Steps:  26%|██▌       | 155/600 [06:50<12:19,  1.66s/it, loss=0.202, lr=1e-5]  
Steps:  26%|██▌       | 156/600 [06:51<11:47,  1.59s/it, loss=0.202, lr=1e-5]
Steps:  26%|██▌       | 156/600 [06:51<11:47,  1.59s/it, loss=0.187, lr=1e-5]
Steps:  26%|██▌       | 157/600 [06:52<11:22,  1.54s/it, loss=0.187, lr=1e-5]
Steps:  26%|██▌       | 157/600 [06:52<11:22,  1.54s/it, loss=0.0753, lr=1e-5]
Steps:  26%|██▋       | 158/600 [06:54<11:16,  1.53s/it, loss=0.0753, lr=1e-5]
Steps:  26%|██▋       | 158/600 [06:54<11:16,  1.53s/it, loss=0.114, lr=1e-5] 
Steps:  26%|██▋       | 159/600 [06:56<11:58,  1.63s/it, loss=0.114, lr=1e-5]
Steps:  26%|██▋       | 159/600 [06:56<11:58,  1.63s/it, loss=0.0804, lr=1e-5]
Steps:  27%|██▋       | 160/600 [06:58<12:15,  1.67s/it, loss=0.0804, lr=1e-5]
Steps:  27%|██▋       | 160/600 [06:58<12:15,  1.67s/it, loss=0.134, lr=1e-5] 
Steps:  27%|██▋       | 161/600 [06:59<11:36,  1.59s/it, loss=0.134, lr=1e-5]
Steps:  27%|██▋       | 161/600 [06:59<11:36,  1.59s/it, loss=0.0393, lr=1e-5]
Steps:  27%|██▋       | 162/600 [07:00<11:23,  1.56s/it, loss=0.0393, lr=1e-5]
Steps:  27%|██▋       | 162/600 [07:00<11:23,  1.56s/it, loss=0.0587, lr=1e-5]
Steps:  27%|██▋       | 163/600 [07:02<11:19,  1.55s/it, loss=0.0587, lr=1e-5]
Steps:  27%|██▋       | 163/600 [07:02<11:19,  1.55s/it, loss=0.0094, lr=1e-5]
Steps:  27%|██▋       | 164/600 [07:03<10:39,  1.47s/it, loss=0.0094, lr=1e-5]
Steps:  27%|██▋       | 164/600 [07:03<10:39,  1.47s/it, loss=0.116, lr=1e-5] 
Steps:  28%|██▊       | 165/600 [07:04<09:05,  1.25s/it, loss=0.116, lr=1e-5]
Steps:  28%|██▊       | 165/600 [07:04<09:05,  1.25s/it, loss=0.322, lr=1e-5]
Steps:  28%|██▊       | 166/600 [07:06<10:18,  1.43s/it, loss=0.322, lr=1e-5]
Steps:  28%|██▊       | 166/600 [07:06<10:18,  1.43s/it, loss=0.126, lr=1e-5]
Steps:  28%|██▊       | 167/600 [07:07<10:50,  1.50s/it, loss=0.126, lr=1e-5]
Steps:  28%|██▊       | 167/600 [07:07<10:50,  1.50s/it, loss=0.0783, lr=1e-5]
Steps:  28%|██▊       | 168/600 [07:09<11:20,  1.57s/it, loss=0.0783, lr=1e-5]
Steps:  28%|██▊       | 168/600 [07:09<11:20,  1.57s/it, loss=0.0381, lr=1e-5]
Steps:  28%|██▊       | 169/600 [07:11<12:03,  1.68s/it, loss=0.0381, lr=1e-5]
Steps:  28%|██▊       | 169/600 [07:11<12:03,  1.68s/it, loss=0.189, lr=1e-5] 
Steps:  28%|██▊       | 170/600 [07:13<12:12,  1.70s/it, loss=0.189, lr=1e-5]
Steps:  28%|██▊       | 170/600 [07:13<12:12,  1.70s/it, loss=0.141, lr=1e-5]
Steps:  28%|██▊       | 171/600 [07:14<11:59,  1.68s/it, loss=0.141, lr=1e-5]
Steps:  28%|██▊       | 171/600 [07:14<11:59,  1.68s/it, loss=0.217, lr=1e-5]
Steps:  29%|██▊       | 172/600 [07:16<11:46,  1.65s/it, loss=0.217, lr=1e-5]
Steps:  29%|██▊       | 172/600 [07:16<11:46,  1.65s/it, loss=0.196, lr=1e-5]
Steps:  29%|██▉       | 173/600 [07:18<11:29,  1.61s/it, loss=0.196, lr=1e-5]
Steps:  29%|██▉       | 173/600 [07:18<11:29,  1.61s/it, loss=0.13, lr=1e-5] 
Steps:  29%|██▉       | 174/600 [07:19<11:19,  1.60s/it, loss=0.13, lr=1e-5]
Steps:  29%|██▉       | 174/600 [07:19<11:19,  1.60s/it, loss=0.0101, lr=1e-5]
Steps:  29%|██▉       | 175/600 [07:20<10:40,  1.51s/it, loss=0.0101, lr=1e-5]
Steps:  29%|██▉       | 175/600 [07:20<10:40,  1.51s/it, loss=0.18, lr=1e-5]  
Steps:  29%|██▉       | 176/600 [07:21<09:04,  1.28s/it, loss=0.18, lr=1e-5]
Steps:  29%|██▉       | 176/600 [07:21<09:04,  1.28s/it, loss=0.0225, lr=1e-5]
Steps:  30%|██▉       | 177/600 [07:24<12:16,  1.74s/it, loss=0.0225, lr=1e-5]
Steps:  30%|██▉       | 177/600 [07:24<12:16,  1.74s/it, loss=0.0305, lr=1e-5]
Steps:  30%|██▉       | 178/600 [07:26<12:07,  1.72s/it, loss=0.0305, lr=1e-5]
Steps:  30%|██▉       | 178/600 [07:26<12:07,  1.72s/it, loss=0.0418, lr=1e-5]
Steps:  30%|██▉       | 179/600 [07:27<11:26,  1.63s/it, loss=0.0418, lr=1e-5]
Steps:  30%|██▉       | 179/600 [07:27<11:26,  1.63s/it, loss=0.0119, lr=1e-5]
Steps:  30%|███       | 180/600 [07:29<11:23,  1.63s/it, loss=0.0119, lr=1e-5]
Steps:  30%|███       | 180/600 [07:29<11:23,  1.63s/it, loss=0.159, lr=1e-5] 
Steps:  30%|███       | 181/600 [07:30<11:15,  1.61s/it, loss=0.159, lr=1e-5]
Steps:  30%|███       | 181/600 [07:30<11:15,  1.61s/it, loss=0.03, lr=1e-5] 
Steps:  30%|███       | 182/600 [07:32<11:14,  1.61s/it, loss=0.03, lr=1e-5]
Steps:  30%|███       | 182/600 [07:32<11:14,  1.61s/it, loss=0.0694, lr=1e-5]
Steps:  30%|███       | 183/600 [07:33<10:56,  1.57s/it, loss=0.0694, lr=1e-5]
Steps:  30%|███       | 183/600 [07:33<10:56,  1.57s/it, loss=0.0926, lr=1e-5]
Steps:  31%|███       | 184/600 [07:35<10:44,  1.55s/it, loss=0.0926, lr=1e-5]
Steps:  31%|███       | 184/600 [07:35<10:44,  1.55s/it, loss=0.192, lr=1e-5] 
Steps:  31%|███       | 185/600 [07:37<10:50,  1.57s/it, loss=0.192, lr=1e-5]
Steps:  31%|███       | 185/600 [07:37<10:50,  1.57s/it, loss=0.00984, lr=1e-5]
Steps:  31%|███       | 186/600 [07:38<10:11,  1.48s/it, loss=0.00984, lr=1e-5]
Steps:  31%|███       | 186/600 [07:38<10:11,  1.48s/it, loss=0.0847, lr=1e-5] 
Steps:  31%|███       | 187/600 [07:39<08:40,  1.26s/it, loss=0.0847, lr=1e-5]
Steps:  31%|███       | 187/600 [07:39<08:40,  1.26s/it, loss=0.0335, lr=1e-5]
Steps:  31%|███▏      | 188/600 [07:41<11:31,  1.68s/it, loss=0.0335, lr=1e-5]
Steps:  31%|███▏      | 188/600 [07:41<11:31,  1.68s/it, loss=0.0577, lr=1e-5]
Steps:  32%|███▏      | 189/600 [07:43<11:15,  1.64s/it, loss=0.0577, lr=1e-5]
Steps:  32%|███▏      | 189/600 [07:43<11:15,  1.64s/it, loss=0.117, lr=1e-5] 
Steps:  32%|███▏      | 190/600 [07:45<11:30,  1.68s/it, loss=0.117, lr=1e-5]
Steps:  32%|███▏      | 190/600 [07:45<11:30,  1.68s/it, loss=0.193, lr=1e-5]
Steps:  32%|███▏      | 191/600 [07:46<11:11,  1.64s/it, loss=0.193, lr=1e-5]
Steps:  32%|███▏      | 191/600 [07:46<11:11,  1.64s/it, loss=0.199, lr=1e-5]
Steps:  32%|███▏      | 192/600 [07:47<10:24,  1.53s/it, loss=0.199, lr=1e-5]
Steps:  32%|███▏      | 192/600 [07:47<10:24,  1.53s/it, loss=0.0973, lr=1e-5]
Steps:  32%|███▏      | 193/600 [07:49<10:59,  1.62s/it, loss=0.0973, lr=1e-5]
Steps:  32%|███▏      | 193/600 [07:49<10:59,  1.62s/it, loss=0.124, lr=1e-5] 
Steps:  32%|███▏      | 194/600 [07:51<11:08,  1.65s/it, loss=0.124, lr=1e-5]
Steps:  32%|███▏      | 194/600 [07:51<11:08,  1.65s/it, loss=0.125, lr=1e-5]
Steps:  32%|███▎      | 195/600 [07:52<10:48,  1.60s/it, loss=0.125, lr=1e-5]
Steps:  32%|███▎      | 195/600 [07:52<10:48,  1.60s/it, loss=0.00813, lr=1e-5]
Steps:  33%|███▎      | 196/600 [07:54<10:21,  1.54s/it, loss=0.00813, lr=1e-5]
Steps:  33%|███▎      | 196/600 [07:54<10:21,  1.54s/it, loss=0.0211, lr=1e-5] 
Steps:  33%|███▎      | 197/600 [07:55<09:50,  1.47s/it, loss=0.0211, lr=1e-5]
Steps:  33%|███▎      | 197/600 [07:55<09:50,  1.47s/it, loss=0.0378, lr=1e-5]
Steps:  33%|███▎      | 198/600 [07:56<08:23,  1.25s/it, loss=0.0378, lr=1e-5]
Steps:  33%|███▎      | 198/600 [07:56<08:23,  1.25s/it, loss=0.135, lr=1e-5] 
Steps:  33%|███▎      | 199/600 [07:58<10:01,  1.50s/it, loss=0.135, lr=1e-5]
Steps:  33%|███▎      | 199/600 [07:58<10:01,  1.50s/it, loss=0.0284, lr=1e-5]
Steps:  33%|███▎      | 200/600 [07:59<09:57,  1.49s/it, loss=0.0284, lr=1e-5]
Steps:  33%|███▎      | 200/600 [07:59<09:57,  1.49s/it, loss=0.142, lr=1e-5] 
Steps:  34%|███▎      | 201/600 [08:01<10:27,  1.57s/it, loss=0.142, lr=1e-5]
Steps:  34%|███▎      | 201/600 [08:01<10:27,  1.57s/it, loss=0.128, lr=1e-5]
Steps:  34%|███▎      | 202/600 [08:03<11:05,  1.67s/it, loss=0.128, lr=1e-5]
Steps:  34%|███▎      | 202/600 [08:03<11:05,  1.67s/it, loss=0.0099, lr=1e-5]
Steps:  34%|███▍      | 203/600 [08:05<11:53,  1.80s/it, loss=0.0099, lr=1e-5]
Steps:  34%|███▍      | 203/600 [08:05<11:53,  1.80s/it, loss=0.156, lr=1e-5] 
Steps:  34%|███▍      | 204/600 [08:07<11:50,  1.79s/it, loss=0.156, lr=1e-5]
Steps:  34%|███▍      | 204/600 [08:07<11:50,  1.79s/it, loss=0.0103, lr=1e-5]
Steps:  34%|███▍      | 205/600 [08:08<10:57,  1.66s/it, loss=0.0103, lr=1e-5]
Steps:  34%|███▍      | 205/600 [08:08<10:57,  1.66s/it, loss=0.0948, lr=1e-5]
Steps:  34%|███▍      | 206/600 [08:10<10:56,  1.67s/it, loss=0.0948, lr=1e-5]
Steps:  34%|███▍      | 206/600 [08:10<10:56,  1.67s/it, loss=0.126, lr=1e-5] 
Steps:  34%|███▍      | 207/600 [08:12<10:56,  1.67s/it, loss=0.126, lr=1e-5]
Steps:  34%|███▍      | 207/600 [08:12<10:56,  1.67s/it, loss=0.129, lr=1e-5]
Steps:  35%|███▍      | 208/600 [08:13<10:07,  1.55s/it, loss=0.129, lr=1e-5]
Steps:  35%|███▍      | 208/600 [08:13<10:07,  1.55s/it, loss=0.0311, lr=1e-5]
Steps:  35%|███▍      | 209/600 [08:14<08:33,  1.31s/it, loss=0.0311, lr=1e-5]
Steps:  35%|███▍      | 209/600 [08:14<08:33,  1.31s/it, loss=0.0226, lr=1e-5]
Steps:  35%|███▌      | 210/600 [08:16<10:44,  1.65s/it, loss=0.0226, lr=1e-5]
Steps:  35%|███▌      | 210/600 [08:16<10:44,  1.65s/it, loss=0.102, lr=1e-5] 
Steps:  35%|███▌      | 211/600 [08:18<10:23,  1.60s/it, loss=0.102, lr=1e-5]
Steps:  35%|███▌      | 211/600 [08:18<10:23,  1.60s/it, loss=0.0853, lr=1e-5]
Steps:  35%|███▌      | 212/600 [08:19<10:13,  1.58s/it, loss=0.0853, lr=1e-5]
Steps:  35%|███▌      | 212/600 [08:19<10:13,  1.58s/it, loss=0.0156, lr=1e-5]
Steps:  36%|███▌      | 213/600 [08:21<10:46,  1.67s/it, loss=0.0156, lr=1e-5]
Steps:  36%|███▌      | 213/600 [08:21<10:46,  1.67s/it, loss=0.00713, lr=1e-5]
Steps:  36%|███▌      | 214/600 [08:22<10:13,  1.59s/it, loss=0.00713, lr=1e-5]
Steps:  36%|███▌      | 214/600 [08:22<10:13,  1.59s/it, loss=0.00706, lr=1e-5]
Steps:  36%|███▌      | 215/600 [08:24<10:00,  1.56s/it, loss=0.00706, lr=1e-5]
Steps:  36%|███▌      | 215/600 [08:24<10:00,  1.56s/it, loss=0.156, lr=1e-5]  
Steps:  36%|███▌      | 216/600 [08:26<10:03,  1.57s/it, loss=0.156, lr=1e-5]
Steps:  36%|███▌      | 216/600 [08:26<10:03,  1.57s/it, loss=0.131, lr=1e-5]
Steps:  36%|███▌      | 217/600 [08:27<10:46,  1.69s/it, loss=0.131, lr=1e-5]
Steps:  36%|███▌      | 217/600 [08:27<10:46,  1.69s/it, loss=0.0997, lr=1e-5]
Steps:  36%|███▋      | 218/600 [08:29<10:17,  1.62s/it, loss=0.0997, lr=1e-5]
Steps:  36%|███▋      | 218/600 [08:29<10:17,  1.62s/it, loss=0.132, lr=1e-5] 
Steps:  36%|███▋      | 219/600 [08:30<09:39,  1.52s/it, loss=0.132, lr=1e-5]
Steps:  36%|███▋      | 219/600 [08:30<09:39,  1.52s/it, loss=0.0638, lr=1e-5]
Steps:  37%|███▋      | 220/600 [08:31<08:11,  1.29s/it, loss=0.0638, lr=1e-5]
Steps:  37%|███▋      | 220/600 [08:31<08:11,  1.29s/it, loss=0.0301, lr=1e-5]
Steps:  37%|███▋      | 221/600 [08:33<09:36,  1.52s/it, loss=0.0301, lr=1e-5]
Steps:  37%|███▋      | 221/600 [08:33<09:36,  1.52s/it, loss=0.0974, lr=1e-5]
Steps:  37%|███▋      | 222/600 [08:35<09:53,  1.57s/it, loss=0.0974, lr=1e-5]
Steps:  37%|███▋      | 222/600 [08:35<09:53,  1.57s/it, loss=0.0812, lr=1e-5]
Steps:  37%|███▋      | 223/600 [08:36<10:06,  1.61s/it, loss=0.0812, lr=1e-5]
Steps:  37%|███▋      | 223/600 [08:36<10:06,  1.61s/it, loss=0.261, lr=1e-5] 
Steps:  37%|███▋      | 224/600 [08:38<10:03,  1.61s/it, loss=0.261, lr=1e-5]
Steps:  37%|███▋      | 224/600 [08:38<10:03,  1.61s/it, loss=0.0112, lr=1e-5]
Steps:  38%|███▊      | 225/600 [08:40<10:15,  1.64s/it, loss=0.0112, lr=1e-5]
Steps:  38%|███▊      | 225/600 [08:40<10:15,  1.64s/it, loss=0.129, lr=1e-5] 
Steps:  38%|███▊      | 226/600 [08:41<10:17,  1.65s/it, loss=0.129, lr=1e-5]
Steps:  38%|███▊      | 226/600 [08:41<10:17,  1.65s/it, loss=0.0926, lr=1e-5]
Steps:  38%|███▊      | 227/600 [08:43<10:05,  1.62s/it, loss=0.0926, lr=1e-5]
Steps:  38%|███▊      | 227/600 [08:43<10:05,  1.62s/it, loss=0.169, lr=1e-5] 
Steps:  38%|███▊      | 228/600 [08:45<10:10,  1.64s/it, loss=0.169, lr=1e-5]
Steps:  38%|███▊      | 228/600 [08:45<10:10,  1.64s/it, loss=0.304, lr=1e-5]
Steps:  38%|███▊      | 229/600 [08:46<09:50,  1.59s/it, loss=0.304, lr=1e-5]
Steps:  38%|███▊      | 229/600 [08:46<09:50,  1.59s/it, loss=0.0854, lr=1e-5]
Steps:  38%|███▊      | 230/600 [08:48<09:27,  1.53s/it, loss=0.0854, lr=1e-5]
Steps:  38%|███▊      | 230/600 [08:48<09:27,  1.53s/it, loss=0.0256, lr=1e-5]
Steps:  38%|███▊      | 231/600 [08:48<08:00,  1.30s/it, loss=0.0256, lr=1e-5]
Steps:  38%|███▊      | 231/600 [08:48<08:00,  1.30s/it, loss=0.0236, lr=1e-5]
Steps:  39%|███▊      | 232/600 [08:51<10:17,  1.68s/it, loss=0.0236, lr=1e-5]
Steps:  39%|███▊      | 232/600 [08:51<10:17,  1.68s/it, loss=0.0653, lr=1e-5]
Steps:  39%|███▉      | 233/600 [08:52<10:07,  1.66s/it, loss=0.0653, lr=1e-5]
Steps:  39%|███▉      | 233/600 [08:52<10:07,  1.66s/it, loss=0.133, lr=1e-5] 
Steps:  39%|███▉      | 234/600 [08:54<09:47,  1.60s/it, loss=0.133, lr=1e-5]
Steps:  39%|███▉      | 234/600 [08:54<09:47,  1.60s/it, loss=0.0539, lr=1e-5]
Steps:  39%|███▉      | 235/600 [08:56<10:05,  1.66s/it, loss=0.0539, lr=1e-5]
Steps:  39%|███▉      | 235/600 [08:56<10:05,  1.66s/it, loss=0.095, lr=1e-5] 
Steps:  39%|███▉      | 236/600 [08:57<09:47,  1.61s/it, loss=0.095, lr=1e-5]
Steps:  39%|███▉      | 236/600 [08:57<09:47,  1.61s/it, loss=0.011, lr=1e-5]
Steps:  40%|███▉      | 237/600 [08:59<09:27,  1.56s/it, loss=0.011, lr=1e-5]
Steps:  40%|███▉      | 237/600 [08:59<09:27,  1.56s/it, loss=0.0569, lr=1e-5]
Steps:  40%|███▉      | 238/600 [09:00<09:08,  1.52s/it, loss=0.0569, lr=1e-5]
Steps:  40%|███▉      | 238/600 [09:00<09:08,  1.52s/it, loss=0.0605, lr=1e-5]
Steps:  40%|███▉      | 239/600 [09:02<09:46,  1.62s/it, loss=0.0605, lr=1e-5]
Steps:  40%|███▉      | 239/600 [09:02<09:46,  1.62s/it, loss=0.0451, lr=1e-5]
Steps:  40%|████      | 240/600 [09:03<09:35,  1.60s/it, loss=0.0451, lr=1e-5]
Steps:  40%|████      | 240/600 [09:03<09:35,  1.60s/it, loss=0.138, lr=1e-5] 
Steps:  40%|████      | 241/600 [09:05<08:58,  1.50s/it, loss=0.138, lr=1e-5]
Steps:  40%|████      | 241/600 [09:05<08:58,  1.50s/it, loss=0.0685, lr=1e-5]
Steps:  40%|████      | 242/600 [09:06<07:37,  1.28s/it, loss=0.0685, lr=1e-5]
Steps:  40%|████      | 242/600 [09:06<07:37,  1.28s/it, loss=0.011, lr=1e-5] 
Steps:  40%|████      | 243/600 [09:08<09:17,  1.56s/it, loss=0.011, lr=1e-5]
Steps:  40%|████      | 243/600 [09:08<09:17,  1.56s/it, loss=0.203, lr=1e-5]
Steps:  41%|████      | 244/600 [09:09<09:24,  1.59s/it, loss=0.203, lr=1e-5]
Steps:  41%|████      | 244/600 [09:09<09:24,  1.59s/it, loss=0.0117, lr=1e-5]
Steps:  41%|████      | 245/600 [09:11<09:12,  1.56s/it, loss=0.0117, lr=1e-5]
Steps:  41%|████      | 245/600 [09:11<09:12,  1.56s/it, loss=0.142, lr=1e-5] 
Steps:  41%|████      | 246/600 [09:12<09:13,  1.56s/it, loss=0.142, lr=1e-5]
Steps:  41%|████      | 246/600 [09:12<09:13,  1.56s/it, loss=0.168, lr=1e-5]
Steps:  41%|████      | 247/600 [09:14<09:12,  1.56s/it, loss=0.168, lr=1e-5]
Steps:  41%|████      | 247/600 [09:14<09:12,  1.56s/it, loss=0.126, lr=1e-5]
Steps:  41%|████▏     | 248/600 [09:16<09:24,  1.60s/it, loss=0.126, lr=1e-5]
Steps:  41%|████▏     | 248/600 [09:16<09:24,  1.60s/it, loss=0.276, lr=1e-5]
Steps:  42%|████▏     | 249/600 [09:17<09:24,  1.61s/it, loss=0.276, lr=1e-5]
Steps:  42%|████▏     | 249/600 [09:17<09:24,  1.61s/it, loss=0.128, lr=1e-5]
Steps:  42%|████▏     | 250/600 [09:19<09:21,  1.60s/it, loss=0.128, lr=1e-5]
Steps:  42%|████▏     | 250/600 [09:19<09:21,  1.60s/it, loss=0.132, lr=1e-5]
Steps:  42%|████▏     | 251/600 [09:21<09:22,  1.61s/it, loss=0.132, lr=1e-5]
Steps:  42%|████▏     | 251/600 [09:21<09:22,  1.61s/it, loss=0.2, lr=1e-5]  
Steps:  42%|████▏     | 252/600 [09:22<09:07,  1.57s/it, loss=0.2, lr=1e-5]
Steps:  42%|████▏     | 252/600 [09:22<09:07,  1.57s/it, loss=0.189, lr=1e-5]
Steps:  42%|████▏     | 253/600 [09:23<07:39,  1.32s/it, loss=0.189, lr=1e-5]
Steps:  42%|████▏     | 253/600 [09:23<07:39,  1.32s/it, loss=0.0957, lr=1e-5]
Steps:  42%|████▏     | 254/600 [09:25<09:26,  1.64s/it, loss=0.0957, lr=1e-5]
Steps:  42%|████▏     | 254/600 [09:25<09:26,  1.64s/it, loss=0.161, lr=1e-5] 
Steps:  42%|████▎     | 255/600 [09:27<08:56,  1.56s/it, loss=0.161, lr=1e-5]
Steps:  42%|████▎     | 255/600 [09:27<08:56,  1.56s/it, loss=0.0807, lr=1e-5]
Steps:  43%|████▎     | 256/600 [09:28<09:10,  1.60s/it, loss=0.0807, lr=1e-5]
Steps:  43%|████▎     | 256/600 [09:28<09:10,  1.60s/it, loss=0.15, lr=1e-5]  
Steps:  43%|████▎     | 257/600 [09:30<09:12,  1.61s/it, loss=0.15, lr=1e-5]
Steps:  43%|████▎     | 257/600 [09:30<09:12,  1.61s/it, loss=0.141, lr=1e-5]
Steps:  43%|████▎     | 258/600 [09:31<08:48,  1.54s/it, loss=0.141, lr=1e-5]
Steps:  43%|████▎     | 258/600 [09:31<08:48,  1.54s/it, loss=0.165, lr=1e-5]
Steps:  43%|████▎     | 259/600 [09:33<08:34,  1.51s/it, loss=0.165, lr=1e-5]
Steps:  43%|████▎     | 259/600 [09:33<08:34,  1.51s/it, loss=0.0144, lr=1e-5]
Steps:  43%|████▎     | 260/600 [09:34<08:54,  1.57s/it, loss=0.0144, lr=1e-5]
Steps:  43%|████▎     | 260/600 [09:34<08:54,  1.57s/it, loss=0.222, lr=1e-5] 
Steps:  44%|████▎     | 261/600 [09:36<09:04,  1.60s/it, loss=0.222, lr=1e-5]
Steps:  44%|████▎     | 261/600 [09:36<09:04,  1.60s/it, loss=0.0995, lr=1e-5]
Steps:  44%|████▎     | 262/600 [09:38<09:11,  1.63s/it, loss=0.0995, lr=1e-5]
Steps:  44%|████▎     | 262/600 [09:38<09:11,  1.63s/it, loss=0.0815, lr=1e-5]
Steps:  44%|████▍     | 263/600 [09:39<08:44,  1.56s/it, loss=0.0815, lr=1e-5]
Steps:  44%|████▍     | 263/600 [09:39<08:44,  1.56s/it, loss=0.0819, lr=1e-5]
Steps:  44%|████▍     | 264/600 [09:40<07:21,  1.31s/it, loss=0.0819, lr=1e-5]
Steps:  44%|████▍     | 264/600 [09:40<07:21,  1.31s/it, loss=0.353, lr=1e-5] 
Steps:  44%|████▍     | 265/600 [09:42<09:19,  1.67s/it, loss=0.353, lr=1e-5]
Steps:  44%|████▍     | 265/600 [09:42<09:19,  1.67s/it, loss=0.0303, lr=1e-5]
Steps:  44%|████▍     | 266/600 [09:44<09:31,  1.71s/it, loss=0.0303, lr=1e-5]
Steps:  44%|████▍     | 266/600 [09:44<09:31,  1.71s/it, loss=0.143, lr=1e-5] 
Steps:  44%|████▍     | 267/600 [09:46<09:25,  1.70s/it, loss=0.143, lr=1e-5]
Steps:  44%|████▍     | 267/600 [09:46<09:25,  1.70s/it, loss=0.191, lr=1e-5]
Steps:  45%|████▍     | 268/600 [09:47<09:09,  1.66s/it, loss=0.191, lr=1e-5]
Steps:  45%|████▍     | 268/600 [09:47<09:09,  1.66s/it, loss=0.189, lr=1e-5]
Steps:  45%|████▍     | 269/600 [09:49<08:34,  1.56s/it, loss=0.189, lr=1e-5]
Steps:  45%|████▍     | 269/600 [09:49<08:34,  1.56s/it, loss=0.162, lr=1e-5]
Steps:  45%|████▌     | 270/600 [09:50<08:28,  1.54s/it, loss=0.162, lr=1e-5]
Steps:  45%|████▌     | 270/600 [09:50<08:28,  1.54s/it, loss=0.201, lr=1e-5]
Steps:  45%|████▌     | 271/600 [09:52<08:00,  1.46s/it, loss=0.201, lr=1e-5]
Steps:  45%|████▌     | 271/600 [09:52<08:00,  1.46s/it, loss=0.25, lr=1e-5] 
Steps:  45%|████▌     | 272/600 [09:53<08:14,  1.51s/it, loss=0.25, lr=1e-5]
Steps:  45%|████▌     | 272/600 [09:53<08:14,  1.51s/it, loss=0.0321, lr=1e-5]
Steps:  46%|████▌     | 273/600 [09:55<08:13,  1.51s/it, loss=0.0321, lr=1e-5]
Steps:  46%|████▌     | 273/600 [09:55<08:13,  1.51s/it, loss=0.0212, lr=1e-5]
Steps:  46%|████▌     | 274/600 [09:56<07:59,  1.47s/it, loss=0.0212, lr=1e-5]
Steps:  46%|████▌     | 274/600 [09:56<07:59,  1.47s/it, loss=0.15, lr=1e-5]  
Steps:  46%|████▌     | 275/600 [09:57<06:47,  1.25s/it, loss=0.15, lr=1e-5]
Steps:  46%|████▌     | 275/600 [09:57<06:47,  1.25s/it, loss=0.0136, lr=1e-5]
Steps:  46%|████▌     | 276/600 [09:59<08:19,  1.54s/it, loss=0.0136, lr=1e-5]
Steps:  46%|████▌     | 276/600 [09:59<08:19,  1.54s/it, loss=0.197, lr=1e-5] 
Steps:  46%|████▌     | 277/600 [10:01<08:24,  1.56s/it, loss=0.197, lr=1e-5]
Steps:  46%|████▌     | 277/600 [10:01<08:24,  1.56s/it, loss=0.0146, lr=1e-5]
Steps:  46%|████▋     | 278/600 [10:02<08:47,  1.64s/it, loss=0.0146, lr=1e-5]
Steps:  46%|████▋     | 278/600 [10:02<08:47,  1.64s/it, loss=0.22, lr=1e-5]  
Steps:  46%|████▋     | 279/600 [10:04<08:43,  1.63s/it, loss=0.22, lr=1e-5]
Steps:  46%|████▋     | 279/600 [10:04<08:43,  1.63s/it, loss=0.315, lr=1e-5]
Steps:  47%|████▋     | 280/600 [10:05<08:23,  1.57s/it, loss=0.315, lr=1e-5]
Steps:  47%|████▋     | 280/600 [10:05<08:23,  1.57s/it, loss=0.0259, lr=1e-5]
Steps:  47%|████▋     | 281/600 [10:07<08:04,  1.52s/it, loss=0.0259, lr=1e-5]
Steps:  47%|████▋     | 281/600 [10:07<08:04,  1.52s/it, loss=0.0652, lr=1e-5]
Steps:  47%|████▋     | 282/600 [10:09<08:16,  1.56s/it, loss=0.0652, lr=1e-5]
Steps:  47%|████▋     | 282/600 [10:09<08:16,  1.56s/it, loss=0.164, lr=1e-5] 
Steps:  47%|████▋     | 283/600 [10:10<08:04,  1.53s/it, loss=0.164, lr=1e-5]
Steps:  47%|████▋     | 283/600 [10:10<08:04,  1.53s/it, loss=0.141, lr=1e-5]
Steps:  47%|████▋     | 284/600 [10:12<08:16,  1.57s/it, loss=0.141, lr=1e-5]
Steps:  47%|████▋     | 284/600 [10:12<08:16,  1.57s/it, loss=0.133, lr=1e-5]
Steps:  48%|████▊     | 285/600 [10:13<07:47,  1.49s/it, loss=0.133, lr=1e-5]
Steps:  48%|████▊     | 285/600 [10:13<07:47,  1.49s/it, loss=0.178, lr=1e-5]
Steps:  48%|████▊     | 286/600 [10:14<06:36,  1.26s/it, loss=0.178, lr=1e-5]
Steps:  48%|████▊     | 286/600 [10:14<06:36,  1.26s/it, loss=0.133, lr=1e-5]
Steps:  48%|████▊     | 287/600 [10:16<08:05,  1.55s/it, loss=0.133, lr=1e-5]
Steps:  48%|████▊     | 287/600 [10:16<08:05,  1.55s/it, loss=0.0267, lr=1e-5]
Steps:  48%|████▊     | 288/600 [10:18<08:08,  1.56s/it, loss=0.0267, lr=1e-5]
Steps:  48%|████▊     | 288/600 [10:18<08:08,  1.56s/it, loss=0.205, lr=1e-5] 
Steps:  48%|████▊     | 289/600 [10:19<08:17,  1.60s/it, loss=0.205, lr=1e-5]
Steps:  48%|████▊     | 289/600 [10:19<08:17,  1.60s/it, loss=0.0263, lr=1e-5]
Steps:  48%|████▊     | 290/600 [10:21<08:17,  1.61s/it, loss=0.0263, lr=1e-5]
Steps:  48%|████▊     | 290/600 [10:21<08:17,  1.61s/it, loss=0.027, lr=1e-5] 
Steps:  48%|████▊     | 291/600 [10:22<07:50,  1.52s/it, loss=0.027, lr=1e-5]
Steps:  48%|████▊     | 291/600 [10:22<07:50,  1.52s/it, loss=0.191, lr=1e-5]
Steps:  49%|████▊     | 292/600 [10:24<07:35,  1.48s/it, loss=0.191, lr=1e-5]
Steps:  49%|████▊     | 292/600 [10:24<07:35,  1.48s/it, loss=0.0223, lr=1e-5]
Steps:  49%|████▉     | 293/600 [10:25<08:03,  1.58s/it, loss=0.0223, lr=1e-5]
Steps:  49%|████▉     | 293/600 [10:25<08:03,  1.58s/it, loss=0.0584, lr=1e-5]
Steps:  49%|████▉     | 294/600 [10:27<07:53,  1.55s/it, loss=0.0584, lr=1e-5]
Steps:  49%|████▉     | 294/600 [10:27<07:53,  1.55s/it, loss=0.142, lr=1e-5] 
Steps:  49%|████▉     | 295/600 [10:29<08:07,  1.60s/it, loss=0.142, lr=1e-5]
Steps:  49%|████▉     | 295/600 [10:29<08:07,  1.60s/it, loss=0.00949, lr=1e-5]
Steps:  49%|████▉     | 296/600 [10:30<07:47,  1.54s/it, loss=0.00949, lr=1e-5]
Steps:  49%|████▉     | 296/600 [10:30<07:47,  1.54s/it, loss=0.192, lr=1e-5]  
Steps:  50%|████▉     | 297/600 [10:31<06:35,  1.31s/it, loss=0.192, lr=1e-5]
Steps:  50%|████▉     | 297/600 [10:31<06:35,  1.31s/it, loss=0.319, lr=1e-5]
Steps:  50%|████▉     | 298/600 [10:33<08:01,  1.60s/it, loss=0.319, lr=1e-5]
Steps:  50%|████▉     | 298/600 [10:33<08:01,  1.60s/it, loss=0.0163, lr=1e-5]
Steps:  50%|████▉     | 299/600 [10:35<08:13,  1.64s/it, loss=0.0163, lr=1e-5]
Steps:  50%|████▉     | 299/600 [10:35<08:13,  1.64s/it, loss=0.233, lr=1e-5] 
Steps:  50%|█████     | 300/600 [10:36<08:20,  1.67s/it, loss=0.233, lr=1e-5]
Steps:  50%|█████     | 300/600 [10:36<08:20,  1.67s/it, loss=0.0167, lr=1e-5]
Steps:  50%|█████     | 301/600 [10:38<08:18,  1.67s/it, loss=0.0167, lr=1e-5]
Steps:  50%|█████     | 301/600 [10:38<08:18,  1.67s/it, loss=0.283, lr=1e-5] 
Steps:  50%|█████     | 302/600 [10:39<07:47,  1.57s/it, loss=0.283, lr=1e-5]
Steps:  50%|█████     | 302/600 [10:39<07:47,  1.57s/it, loss=0.235, lr=1e-5]
Steps:  50%|█████     | 303/600 [10:41<07:34,  1.53s/it, loss=0.235, lr=1e-5]
Steps:  50%|█████     | 303/600 [10:41<07:34,  1.53s/it, loss=0.163, lr=1e-5]
Steps:  51%|█████     | 304/600 [10:43<08:00,  1.62s/it, loss=0.163, lr=1e-5]
Steps:  51%|█████     | 304/600 [10:43<08:00,  1.62s/it, loss=0.219, lr=1e-5]
Steps:  51%|█████     | 305/600 [10:44<08:08,  1.65s/it, loss=0.219, lr=1e-5]
Steps:  51%|█████     | 305/600 [10:44<08:08,  1.65s/it, loss=0.218, lr=1e-5]
Steps:  51%|█████     | 306/600 [10:46<07:56,  1.62s/it, loss=0.218, lr=1e-5]
Steps:  51%|█████     | 306/600 [10:46<07:56,  1.62s/it, loss=0.00358, lr=1e-5]
Steps:  51%|█████     | 307/600 [10:47<07:24,  1.52s/it, loss=0.00358, lr=1e-5]
Steps:  51%|█████     | 307/600 [10:47<07:24,  1.52s/it, loss=0.135, lr=1e-5]  
Steps:  51%|█████▏    | 308/600 [10:48<06:17,  1.29s/it, loss=0.135, lr=1e-5]
Steps:  51%|█████▏    | 308/600 [10:48<06:17,  1.29s/it, loss=0.291, lr=1e-5]
Steps:  52%|█████▏    | 309/600 [10:50<07:25,  1.53s/it, loss=0.291, lr=1e-5]
Steps:  52%|█████▏    | 309/600 [10:50<07:25,  1.53s/it, loss=0.212, lr=1e-5]
Steps:  52%|█████▏    | 310/600 [10:52<07:37,  1.58s/it, loss=0.212, lr=1e-5]
Steps:  52%|█████▏    | 310/600 [10:52<07:37,  1.58s/it, loss=0.16, lr=1e-5] 
Steps:  52%|█████▏    | 311/600 [10:53<07:27,  1.55s/it, loss=0.16, lr=1e-5]
Steps:  52%|█████▏    | 311/600 [10:53<07:27,  1.55s/it, loss=0.103, lr=1e-5]
Steps:  52%|█████▏    | 312/600 [10:55<07:45,  1.62s/it, loss=0.103, lr=1e-5]
Steps:  52%|█████▏    | 312/600 [10:55<07:45,  1.62s/it, loss=0.0256, lr=1e-5]
Steps:  52%|█████▏    | 313/600 [10:57<07:53,  1.65s/it, loss=0.0256, lr=1e-5]
Steps:  52%|█████▏    | 313/600 [10:57<07:53,  1.65s/it, loss=0.163, lr=1e-5] 
Steps:  52%|█████▏    | 314/600 [10:59<07:58,  1.67s/it, loss=0.163, lr=1e-5]
Steps:  52%|█████▏    | 314/600 [10:59<07:58,  1.67s/it, loss=0.0719, lr=1e-5]
Steps:  52%|█████▎    | 315/600 [11:00<07:55,  1.67s/it, loss=0.0719, lr=1e-5]
Steps:  52%|█████▎    | 315/600 [11:00<07:55,  1.67s/it, loss=0.0119, lr=1e-5]
Steps:  53%|█████▎    | 316/600 [11:02<07:52,  1.66s/it, loss=0.0119, lr=1e-5]
Steps:  53%|█████▎    | 316/600 [11:02<07:52,  1.66s/it, loss=0.299, lr=1e-5] 
Steps:  53%|█████▎    | 317/600 [11:04<07:53,  1.67s/it, loss=0.299, lr=1e-5]
Steps:  53%|█████▎    | 317/600 [11:04<07:53,  1.67s/it, loss=0.0484, lr=1e-5]
Steps:  53%|█████▎    | 318/600 [11:05<07:04,  1.51s/it, loss=0.0484, lr=1e-5]
Steps:  53%|█████▎    | 318/600 [11:05<07:04,  1.51s/it, loss=0.0449, lr=1e-5]
Steps:  53%|█████▎    | 319/600 [11:05<06:01,  1.28s/it, loss=0.0449, lr=1e-5]
Steps:  53%|█████▎    | 319/600 [11:05<06:01,  1.28s/it, loss=0.0425, lr=1e-5]
Steps:  53%|█████▎    | 320/600 [11:08<07:27,  1.60s/it, loss=0.0425, lr=1e-5]
Steps:  53%|█████▎    | 320/600 [11:08<07:27,  1.60s/it, loss=0.0127, lr=1e-5]
Steps:  54%|█████▎    | 321/600 [11:10<07:40,  1.65s/it, loss=0.0127, lr=1e-5]
Steps:  54%|█████▎    | 321/600 [11:10<07:40,  1.65s/it, loss=0.229, lr=1e-5] 
Steps:  54%|█████▎    | 322/600 [11:11<07:26,  1.60s/it, loss=0.229, lr=1e-5]
Steps:  54%|█████▎    | 322/600 [11:11<07:26,  1.60s/it, loss=0.146, lr=1e-5]
Steps:  54%|█████▍    | 323/600 [11:13<07:35,  1.64s/it, loss=0.146, lr=1e-5]
Steps:  54%|█████▍    | 323/600 [11:13<07:35,  1.64s/it, loss=0.142, lr=1e-5]
Steps:  54%|█████▍    | 324/600 [11:14<07:41,  1.67s/it, loss=0.142, lr=1e-5]
Steps:  54%|█████▍    | 324/600 [11:14<07:41,  1.67s/it, loss=0.23, lr=1e-5] 
Steps:  54%|█████▍    | 325/600 [11:16<07:38,  1.67s/it, loss=0.23, lr=1e-5]
Steps:  54%|█████▍    | 325/600 [11:16<07:38,  1.67s/it, loss=0.23, lr=1e-5]
Steps:  54%|█████▍    | 326/600 [11:17<07:10,  1.57s/it, loss=0.23, lr=1e-5]
Steps:  54%|█████▍    | 326/600 [11:17<07:10,  1.57s/it, loss=0.0901, lr=1e-5]
Steps:  55%|█████▍    | 327/600 [11:19<07:21,  1.62s/it, loss=0.0901, lr=1e-5]
Steps:  55%|█████▍    | 327/600 [11:19<07:21,  1.62s/it, loss=0.119, lr=1e-5] 
Steps:  55%|█████▍    | 328/600 [11:21<07:23,  1.63s/it, loss=0.119, lr=1e-5]
Steps:  55%|█████▍    | 328/600 [11:21<07:23,  1.63s/it, loss=0.126, lr=1e-5]
Steps:  55%|█████▍    | 329/600 [11:22<06:40,  1.48s/it, loss=0.126, lr=1e-5]
Steps:  55%|█████▍    | 329/600 [11:22<06:40,  1.48s/it, loss=0.0292, lr=1e-5]
Steps:  55%|█████▌    | 330/600 [11:23<05:41,  1.27s/it, loss=0.0292, lr=1e-5]
Steps:  55%|█████▌    | 330/600 [11:23<05:41,  1.27s/it, loss=0.168, lr=1e-5] 
Steps:  55%|█████▌    | 331/600 [11:25<06:57,  1.55s/it, loss=0.168, lr=1e-5]
Steps:  55%|█████▌    | 331/600 [11:25<06:57,  1.55s/it, loss=0.0205, lr=1e-5]
Steps:  55%|█████▌    | 332/600 [11:27<07:07,  1.60s/it, loss=0.0205, lr=1e-5]
Steps:  55%|█████▌    | 332/600 [11:27<07:07,  1.60s/it, loss=0.0035, lr=1e-5]
Steps:  56%|█████▌    | 333/600 [11:28<07:13,  1.62s/it, loss=0.0035, lr=1e-5]
Steps:  56%|█████▌    | 333/600 [11:28<07:13,  1.62s/it, loss=0.138, lr=1e-5] 
Steps:  56%|█████▌    | 334/600 [11:30<07:38,  1.72s/it, loss=0.138, lr=1e-5]
Steps:  56%|█████▌    | 334/600 [11:30<07:38,  1.72s/it, loss=0.191, lr=1e-5]
Steps:  56%|█████▌    | 335/600 [11:32<07:33,  1.71s/it, loss=0.191, lr=1e-5]
Steps:  56%|█████▌    | 335/600 [11:32<07:33,  1.71s/it, loss=0.131, lr=1e-5]
Steps:  56%|█████▌    | 336/600 [11:34<07:27,  1.69s/it, loss=0.131, lr=1e-5]
Steps:  56%|█████▌    | 336/600 [11:34<07:27,  1.69s/it, loss=0.0125, lr=1e-5]
Steps:  56%|█████▌    | 337/600 [11:35<07:15,  1.66s/it, loss=0.0125, lr=1e-5]
Steps:  56%|█████▌    | 337/600 [11:35<07:15,  1.66s/it, loss=0.0956, lr=1e-5]
Steps:  56%|█████▋    | 338/600 [11:37<06:49,  1.56s/it, loss=0.0956, lr=1e-5]
Steps:  56%|█████▋    | 338/600 [11:37<06:49,  1.56s/it, loss=0.157, lr=1e-5] 
Steps:  56%|█████▋    | 339/600 [11:38<06:42,  1.54s/it, loss=0.157, lr=1e-5]
Steps:  56%|█████▋    | 339/600 [11:38<06:42,  1.54s/it, loss=0.124, lr=1e-5]
Steps:  57%|█████▋    | 340/600 [11:39<06:15,  1.44s/it, loss=0.124, lr=1e-5]
Steps:  57%|█████▋    | 340/600 [11:39<06:15,  1.44s/it, loss=0.152, lr=1e-5]
Steps:  57%|█████▋    | 341/600 [11:40<05:20,  1.24s/it, loss=0.152, lr=1e-5]
Steps:  57%|█████▋    | 341/600 [11:40<05:20,  1.24s/it, loss=0.194, lr=1e-5]
Steps:  57%|█████▋    | 342/600 [11:42<06:28,  1.50s/it, loss=0.194, lr=1e-5]
Steps:  57%|█████▋    | 342/600 [11:42<06:28,  1.50s/it, loss=0.0463, lr=1e-5]
Steps:  57%|█████▋    | 343/600 [11:44<06:23,  1.49s/it, loss=0.0463, lr=1e-5]
Steps:  57%|█████▋    | 343/600 [11:44<06:23,  1.49s/it, loss=0.135, lr=1e-5] 
Steps:  57%|█████▋    | 344/600 [11:45<06:34,  1.54s/it, loss=0.135, lr=1e-5]
Steps:  57%|█████▋    | 344/600 [11:45<06:34,  1.54s/it, loss=0.0626, lr=1e-5]
Steps:  57%|█████▊    | 345/600 [11:47<06:33,  1.54s/it, loss=0.0626, lr=1e-5]
Steps:  57%|█████▊    | 345/600 [11:47<06:33,  1.54s/it, loss=0.163, lr=1e-5] 
Steps:  58%|█████▊    | 346/600 [11:48<06:29,  1.54s/it, loss=0.163, lr=1e-5]
Steps:  58%|█████▊    | 346/600 [11:48<06:29,  1.54s/it, loss=0.00666, lr=1e-5]
Steps:  58%|█████▊    | 347/600 [11:50<06:30,  1.55s/it, loss=0.00666, lr=1e-5]
Steps:  58%|█████▊    | 347/600 [11:50<06:30,  1.55s/it, loss=0.0852, lr=1e-5] 
Steps:  58%|█████▊    | 348/600 [11:52<06:41,  1.59s/it, loss=0.0852, lr=1e-5]
Steps:  58%|█████▊    | 348/600 [11:52<06:41,  1.59s/it, loss=0.189, lr=1e-5] 
Steps:  58%|█████▊    | 349/600 [11:53<06:51,  1.64s/it, loss=0.189, lr=1e-5]
Steps:  58%|█████▊    | 349/600 [11:53<06:51,  1.64s/it, loss=0.124, lr=1e-5]
Steps:  58%|█████▊    | 350/600 [11:55<06:38,  1.59s/it, loss=0.124, lr=1e-5]
Steps:  58%|█████▊    | 350/600 [11:55<06:38,  1.59s/it, loss=0.272, lr=1e-5]
Steps:  58%|█████▊    | 351/600 [11:56<06:31,  1.57s/it, loss=0.272, lr=1e-5]
Steps:  58%|█████▊    | 351/600 [11:56<06:31,  1.57s/it, loss=0.0195, lr=1e-5]
Steps:  59%|█████▊    | 352/600 [11:57<05:29,  1.33s/it, loss=0.0195, lr=1e-5]
Steps:  59%|█████▊    | 352/600 [11:57<05:29,  1.33s/it, loss=0.0681, lr=1e-5]
Steps:  59%|█████▉    | 353/600 [12:00<06:48,  1.66s/it, loss=0.0681, lr=1e-5]
Steps:  59%|█████▉    | 353/600 [12:00<06:48,  1.66s/it, loss=0.00347, lr=1e-5]
Steps:  59%|█████▉    | 354/600 [12:01<06:49,  1.66s/it, loss=0.00347, lr=1e-5]
Steps:  59%|█████▉    | 354/600 [12:01<06:49,  1.66s/it, loss=0.146, lr=1e-5]  
Steps:  59%|█████▉    | 355/600 [12:03<06:49,  1.67s/it, loss=0.146, lr=1e-5]
Steps:  59%|█████▉    | 355/600 [12:03<06:49,  1.67s/it, loss=0.0924, lr=1e-5]
Steps:  59%|█████▉    | 356/600 [12:05<06:55,  1.70s/it, loss=0.0924, lr=1e-5]
Steps:  59%|█████▉    | 356/600 [12:05<06:55,  1.70s/it, loss=0.137, lr=1e-5] 
Steps:  60%|█████▉    | 357/600 [12:06<06:44,  1.66s/it, loss=0.137, lr=1e-5]
Steps:  60%|█████▉    | 357/600 [12:06<06:44,  1.66s/it, loss=0.269, lr=1e-5]
Steps:  60%|█████▉    | 358/600 [12:08<06:25,  1.59s/it, loss=0.269, lr=1e-5]
Steps:  60%|█████▉    | 358/600 [12:08<06:25,  1.59s/it, loss=0.156, lr=1e-5]
Steps:  60%|█████▉    | 359/600 [12:09<06:14,  1.55s/it, loss=0.156, lr=1e-5]
Steps:  60%|█████▉    | 359/600 [12:09<06:14,  1.55s/it, loss=0.171, lr=1e-5]
Steps:  60%|██████    | 360/600 [12:11<06:16,  1.57s/it, loss=0.171, lr=1e-5]
Steps:  60%|██████    | 360/600 [12:11<06:16,  1.57s/it, loss=0.0751, lr=1e-5]
Steps:  60%|██████    | 361/600 [12:12<06:22,  1.60s/it, loss=0.0751, lr=1e-5]
Steps:  60%|██████    | 361/600 [12:12<06:22,  1.60s/it, loss=0.0357, lr=1e-5]
Steps:  60%|██████    | 362/600 [12:14<05:54,  1.49s/it, loss=0.0357, lr=1e-5]
Steps:  60%|██████    | 362/600 [12:14<05:54,  1.49s/it, loss=0.114, lr=1e-5] 
Steps:  60%|██████    | 363/600 [12:14<05:01,  1.27s/it, loss=0.114, lr=1e-5]
Steps:  60%|██████    | 363/600 [12:14<05:01,  1.27s/it, loss=0.0126, lr=1e-5]
Steps:  61%|██████    | 364/600 [12:16<05:42,  1.45s/it, loss=0.0126, lr=1e-5]
Steps:  61%|██████    | 364/600 [12:16<05:42,  1.45s/it, loss=0.133, lr=1e-5] 
Steps:  61%|██████    | 365/600 [12:18<05:44,  1.47s/it, loss=0.133, lr=1e-5]
Steps:  61%|██████    | 365/600 [12:18<05:44,  1.47s/it, loss=0.0532, lr=1e-5]
Steps:  61%|██████    | 366/600 [12:20<06:03,  1.56s/it, loss=0.0532, lr=1e-5]
Steps:  61%|██████    | 366/600 [12:20<06:03,  1.56s/it, loss=0.0239, lr=1e-5]
Steps:  61%|██████    | 367/600 [12:21<06:14,  1.61s/it, loss=0.0239, lr=1e-5]
Steps:  61%|██████    | 367/600 [12:21<06:14,  1.61s/it, loss=0.0548, lr=1e-5]
Steps:  61%|██████▏   | 368/600 [12:23<06:30,  1.68s/it, loss=0.0548, lr=1e-5]
Steps:  61%|██████▏   | 368/600 [12:23<06:30,  1.68s/it, loss=0.0467, lr=1e-5]
Steps:  62%|██████▏   | 369/600 [12:25<06:38,  1.72s/it, loss=0.0467, lr=1e-5]
Steps:  62%|██████▏   | 369/600 [12:25<06:38,  1.72s/it, loss=0.16, lr=1e-5]  
Steps:  62%|██████▏   | 370/600 [12:26<06:17,  1.64s/it, loss=0.16, lr=1e-5]
Steps:  62%|██████▏   | 370/600 [12:26<06:17,  1.64s/it, loss=0.0933, lr=1e-5]
Steps:  62%|██████▏   | 371/600 [12:28<06:09,  1.61s/it, loss=0.0933, lr=1e-5]
Steps:  62%|██████▏   | 371/600 [12:28<06:09,  1.61s/it, loss=0.132, lr=1e-5] 
Steps:  62%|██████▏   | 372/600 [12:30<06:25,  1.69s/it, loss=0.132, lr=1e-5]
Steps:  62%|██████▏   | 372/600 [12:30<06:25,  1.69s/it, loss=0.00826, lr=1e-5]
Steps:  62%|██████▏   | 373/600 [12:31<05:53,  1.56s/it, loss=0.00826, lr=1e-5]
Steps:  62%|██████▏   | 373/600 [12:31<05:53,  1.56s/it, loss=0.0304, lr=1e-5] 
Steps:  62%|██████▏   | 374/600 [12:32<04:57,  1.32s/it, loss=0.0304, lr=1e-5]
Steps:  62%|██████▏   | 374/600 [12:32<04:57,  1.32s/it, loss=0.0266, lr=1e-5]
Steps:  62%|██████▎   | 375/600 [12:34<06:07,  1.63s/it, loss=0.0266, lr=1e-5]
Steps:  62%|██████▎   | 375/600 [12:34<06:07,  1.63s/it, loss=0.103, lr=1e-5] 
Steps:  63%|██████▎   | 376/600 [12:36<06:08,  1.64s/it, loss=0.103, lr=1e-5]
Steps:  63%|██████▎   | 376/600 [12:36<06:08,  1.64s/it, loss=0.107, lr=1e-5]
Steps:  63%|██████▎   | 377/600 [12:37<05:38,  1.52s/it, loss=0.107, lr=1e-5]
Steps:  63%|██████▎   | 377/600 [12:37<05:38,  1.52s/it, loss=0.151, lr=1e-5]
Steps:  63%|██████▎   | 378/600 [12:39<05:53,  1.59s/it, loss=0.151, lr=1e-5]
Steps:  63%|██████▎   | 378/600 [12:39<05:53,  1.59s/it, loss=0.129, lr=1e-5]
Steps:  63%|██████▎   | 379/600 [12:40<05:49,  1.58s/it, loss=0.129, lr=1e-5]
Steps:  63%|██████▎   | 379/600 [12:40<05:49,  1.58s/it, loss=0.244, lr=1e-5]
Steps:  63%|██████▎   | 380/600 [12:42<05:56,  1.62s/it, loss=0.244, lr=1e-5]
Steps:  63%|██████▎   | 380/600 [12:42<05:56,  1.62s/it, loss=0.11, lr=1e-5] 
Steps:  64%|██████▎   | 381/600 [12:44<05:47,  1.59s/it, loss=0.11, lr=1e-5]
Steps:  64%|██████▎   | 381/600 [12:44<05:47,  1.59s/it, loss=0.0221, lr=1e-5]
Steps:  64%|██████▎   | 382/600 [12:45<05:49,  1.60s/it, loss=0.0221, lr=1e-5]
Steps:  64%|██████▎   | 382/600 [12:45<05:49,  1.60s/it, loss=0.246, lr=1e-5] 
Steps:  64%|██████▍   | 383/600 [12:47<05:49,  1.61s/it, loss=0.246, lr=1e-5]
Steps:  64%|██████▍   | 383/600 [12:47<05:49,  1.61s/it, loss=0.0922, lr=1e-5]
Steps:  64%|██████▍   | 384/600 [12:48<05:22,  1.49s/it, loss=0.0922, lr=1e-5]
Steps:  64%|██████▍   | 384/600 [12:48<05:22,  1.49s/it, loss=0.0231, lr=1e-5]
Steps:  64%|██████▍   | 385/600 [12:49<04:33,  1.27s/it, loss=0.0231, lr=1e-5]
Steps:  64%|██████▍   | 385/600 [12:49<04:33,  1.27s/it, loss=0.23, lr=1e-5]  
Steps:  64%|██████▍   | 386/600 [12:51<05:43,  1.60s/it, loss=0.23, lr=1e-5]
Steps:  64%|██████▍   | 386/600 [12:51<05:43,  1.60s/it, loss=0.00951, lr=1e-5]
Steps:  64%|██████▍   | 387/600 [12:53<05:45,  1.62s/it, loss=0.00951, lr=1e-5]
Steps:  64%|██████▍   | 387/600 [12:53<05:45,  1.62s/it, loss=0.0834, lr=1e-5] 
Steps:  65%|██████▍   | 388/600 [12:54<05:34,  1.58s/it, loss=0.0834, lr=1e-5]
Steps:  65%|██████▍   | 388/600 [12:54<05:34,  1.58s/it, loss=0.128, lr=1e-5] 
Steps:  65%|██████▍   | 389/600 [12:56<05:37,  1.60s/it, loss=0.128, lr=1e-5]
Steps:  65%|██████▍   | 389/600 [12:56<05:37,  1.60s/it, loss=0.0221, lr=1e-5]
Steps:  65%|██████▌   | 390/600 [12:58<05:33,  1.59s/it, loss=0.0221, lr=1e-5]
Steps:  65%|██████▌   | 390/600 [12:58<05:33,  1.59s/it, loss=0.26, lr=1e-5]  
Steps:  65%|██████▌   | 391/600 [12:59<05:27,  1.57s/it, loss=0.26, lr=1e-5]
Steps:  65%|██████▌   | 391/600 [12:59<05:27,  1.57s/it, loss=0.182, lr=1e-5]
Steps:  65%|██████▌   | 392/600 [13:01<05:29,  1.59s/it, loss=0.182, lr=1e-5]
Steps:  65%|██████▌   | 392/600 [13:01<05:29,  1.59s/it, loss=0.0266, lr=1e-5]
Steps:  66%|██████▌   | 393/600 [13:02<05:24,  1.57s/it, loss=0.0266, lr=1e-5]
Steps:  66%|██████▌   | 393/600 [13:02<05:24,  1.57s/it, loss=0.0499, lr=1e-5]
Steps:  66%|██████▌   | 394/600 [13:04<05:20,  1.55s/it, loss=0.0499, lr=1e-5]
Steps:  66%|██████▌   | 394/600 [13:04<05:20,  1.55s/it, loss=0.141, lr=1e-5] 
Steps:  66%|██████▌   | 395/600 [13:05<05:13,  1.53s/it, loss=0.141, lr=1e-5]
Steps:  66%|██████▌   | 395/600 [13:05<05:13,  1.53s/it, loss=0.27, lr=1e-5] 
Steps:  66%|██████▌   | 396/600 [13:06<04:25,  1.30s/it, loss=0.27, lr=1e-5]
Steps:  66%|██████▌   | 396/600 [13:06<04:25,  1.30s/it, loss=0.212, lr=1e-5]
Steps:  66%|██████▌   | 397/600 [13:08<05:28,  1.62s/it, loss=0.212, lr=1e-5]
Steps:  66%|██████▌   | 397/600 [13:08<05:28,  1.62s/it, loss=0.00275, lr=1e-5]
Steps:  66%|██████▋   | 398/600 [13:10<05:16,  1.57s/it, loss=0.00275, lr=1e-5]
Steps:  66%|██████▋   | 398/600 [13:10<05:16,  1.57s/it, loss=0.0648, lr=1e-5] 
Steps:  66%|██████▋   | 399/600 [13:12<05:18,  1.59s/it, loss=0.0648, lr=1e-5]
Steps:  66%|██████▋   | 399/600 [13:12<05:18,  1.59s/it, loss=0.0372, lr=1e-5]
Steps:  67%|██████▋   | 400/600 [13:13<05:12,  1.56s/it, loss=0.0372, lr=1e-5]
Steps:  67%|██████▋   | 400/600 [13:13<05:12,  1.56s/it, loss=0.0716, lr=1e-5]
Steps:  67%|██████▋   | 401/600 [13:15<05:18,  1.60s/it, loss=0.0716, lr=1e-5]
Steps:  67%|██████▋   | 401/600 [13:15<05:18,  1.60s/it, loss=0.0401, lr=1e-5]
Steps:  67%|██████▋   | 402/600 [13:16<05:14,  1.59s/it, loss=0.0401, lr=1e-5]
Steps:  67%|██████▋   | 402/600 [13:16<05:14,  1.59s/it, loss=0.153, lr=1e-5] 
Steps:  67%|██████▋   | 403/600 [13:18<05:11,  1.58s/it, loss=0.153, lr=1e-5]
Steps:  67%|██████▋   | 403/600 [13:18<05:11,  1.58s/it, loss=0.068, lr=1e-5]
Steps:  67%|██████▋   | 404/600 [13:19<05:07,  1.57s/it, loss=0.068, lr=1e-5]
Steps:  67%|██████▋   | 404/600 [13:19<05:07,  1.57s/it, loss=0.195, lr=1e-5]
Steps:  68%|██████▊   | 405/600 [13:21<05:11,  1.60s/it, loss=0.195, lr=1e-5]
Steps:  68%|██████▊   | 405/600 [13:21<05:11,  1.60s/it, loss=0.226, lr=1e-5]
Steps:  68%|██████▊   | 406/600 [13:22<04:50,  1.50s/it, loss=0.226, lr=1e-5]
Steps:  68%|██████▊   | 406/600 [13:22<04:50,  1.50s/it, loss=0.197, lr=1e-5]
Steps:  68%|██████▊   | 407/600 [13:23<04:05,  1.27s/it, loss=0.197, lr=1e-5]
Steps:  68%|██████▊   | 407/600 [13:23<04:05,  1.27s/it, loss=0.0101, lr=1e-5]
Steps:  68%|██████▊   | 408/600 [13:25<04:46,  1.49s/it, loss=0.0101, lr=1e-5]
Steps:  68%|██████▊   | 408/600 [13:25<04:46,  1.49s/it, loss=0.0721, lr=1e-5]
Steps:  68%|██████▊   | 409/600 [13:27<04:57,  1.55s/it, loss=0.0721, lr=1e-5]
Steps:  68%|██████▊   | 409/600 [13:27<04:57,  1.55s/it, loss=0.246, lr=1e-5] 
Steps:  68%|██████▊   | 410/600 [13:28<04:50,  1.53s/it, loss=0.246, lr=1e-5]
Steps:  68%|██████▊   | 410/600 [13:28<04:50,  1.53s/it, loss=0.133, lr=1e-5]
Steps:  68%|██████▊   | 411/600 [13:30<05:12,  1.65s/it, loss=0.133, lr=1e-5]
Steps:  68%|██████▊   | 411/600 [13:30<05:12,  1.65s/it, loss=0.134, lr=1e-5]
Steps:  69%|██████▊   | 412/600 [13:32<05:11,  1.65s/it, loss=0.134, lr=1e-5]
Steps:  69%|██████▊   | 412/600 [13:32<05:11,  1.65s/it, loss=0.205, lr=1e-5]
Steps:  69%|██████▉   | 413/600 [13:34<05:11,  1.67s/it, loss=0.205, lr=1e-5]
Steps:  69%|██████▉   | 413/600 [13:34<05:11,  1.67s/it, loss=0.0221, lr=1e-5]
Steps:  69%|██████▉   | 414/600 [13:35<05:07,  1.65s/it, loss=0.0221, lr=1e-5]
Steps:  69%|██████▉   | 414/600 [13:35<05:07,  1.65s/it, loss=0.0067, lr=1e-5]
Steps:  69%|██████▉   | 415/600 [13:37<04:51,  1.58s/it, loss=0.0067, lr=1e-5]
Steps:  69%|██████▉   | 415/600 [13:37<04:51,  1.58s/it, loss=0.102, lr=1e-5] 
Steps:  69%|██████▉   | 416/600 [13:38<04:49,  1.57s/it, loss=0.102, lr=1e-5]
Steps:  69%|██████▉   | 416/600 [13:38<04:49,  1.57s/it, loss=0.0907, lr=1e-5]
Steps:  70%|██████▉   | 417/600 [13:40<04:43,  1.55s/it, loss=0.0907, lr=1e-5]
Steps:  70%|██████▉   | 417/600 [13:40<04:43,  1.55s/it, loss=0.165, lr=1e-5] 
Steps:  70%|██████▉   | 418/600 [13:40<03:59,  1.31s/it, loss=0.165, lr=1e-5]
Steps:  70%|██████▉   | 418/600 [13:40<03:59,  1.31s/it, loss=0.0407, lr=1e-5]
Steps:  70%|██████▉   | 419/600 [13:43<04:46,  1.58s/it, loss=0.0407, lr=1e-5]
Steps:  70%|██████▉   | 419/600 [13:43<04:46,  1.58s/it, loss=0.0417, lr=1e-5]
Steps:  70%|███████   | 420/600 [13:44<04:48,  1.60s/it, loss=0.0417, lr=1e-5]
Steps:  70%|███████   | 420/600 [13:44<04:48,  1.60s/it, loss=0.0147, lr=1e-5]
Steps:  70%|███████   | 421/600 [13:46<04:49,  1.62s/it, loss=0.0147, lr=1e-5]
Steps:  70%|███████   | 421/600 [13:46<04:49,  1.62s/it, loss=0.0732, lr=1e-5]
Steps:  70%|███████   | 422/600 [13:47<04:34,  1.54s/it, loss=0.0732, lr=1e-5]
Steps:  70%|███████   | 422/600 [13:47<04:34,  1.54s/it, loss=0.312, lr=1e-5] 
Steps:  70%|███████   | 423/600 [13:49<04:51,  1.64s/it, loss=0.312, lr=1e-5]
Steps:  70%|███████   | 423/600 [13:49<04:51,  1.64s/it, loss=0.151, lr=1e-5]
Steps:  71%|███████   | 424/600 [13:51<04:41,  1.60s/it, loss=0.151, lr=1e-5]
Steps:  71%|███████   | 424/600 [13:51<04:41,  1.60s/it, loss=0.179, lr=1e-5]
Steps:  71%|███████   | 425/600 [13:52<04:33,  1.56s/it, loss=0.179, lr=1e-5]
Steps:  71%|███████   | 425/600 [13:52<04:33,  1.56s/it, loss=0.129, lr=1e-5]
Steps:  71%|███████   | 426/600 [13:54<04:47,  1.65s/it, loss=0.129, lr=1e-5]
Steps:  71%|███████   | 426/600 [13:54<04:47,  1.65s/it, loss=0.0301, lr=1e-5]
Steps:  71%|███████   | 427/600 [13:56<04:54,  1.70s/it, loss=0.0301, lr=1e-5]
Steps:  71%|███████   | 427/600 [13:56<04:54,  1.70s/it, loss=0.215, lr=1e-5] 
Steps:  71%|███████▏  | 428/600 [13:57<04:23,  1.53s/it, loss=0.215, lr=1e-5]
Steps:  71%|███████▏  | 428/600 [13:57<04:23,  1.53s/it, loss=0.0211, lr=1e-5]
Steps:  72%|███████▏  | 429/600 [13:58<03:42,  1.30s/it, loss=0.0211, lr=1e-5]
Steps:  72%|███████▏  | 429/600 [13:58<03:42,  1.30s/it, loss=0.253, lr=1e-5] 
Steps:  72%|███████▏  | 430/600 [14:00<04:26,  1.57s/it, loss=0.253, lr=1e-5]
Steps:  72%|███████▏  | 430/600 [14:00<04:26,  1.57s/it, loss=0.114, lr=1e-5]
Steps:  72%|███████▏  | 431/600 [14:02<04:35,  1.63s/it, loss=0.114, lr=1e-5]
Steps:  72%|███████▏  | 431/600 [14:02<04:35,  1.63s/it, loss=0.171, lr=1e-5]
Steps:  72%|███████▏  | 432/600 [14:03<04:28,  1.60s/it, loss=0.171, lr=1e-5]
Steps:  72%|███████▏  | 432/600 [14:03<04:28,  1.60s/it, loss=0.117, lr=1e-5]
Steps:  72%|███████▏  | 433/600 [14:05<04:31,  1.63s/it, loss=0.117, lr=1e-5]
Steps:  72%|███████▏  | 433/600 [14:05<04:31,  1.63s/it, loss=0.0477, lr=1e-5]
Steps:  72%|███████▏  | 434/600 [14:07<04:41,  1.70s/it, loss=0.0477, lr=1e-5]
Steps:  72%|███████▏  | 434/600 [14:07<04:41,  1.70s/it, loss=0.0209, lr=1e-5]
Steps:  72%|███████▎  | 435/600 [14:08<04:31,  1.64s/it, loss=0.0209, lr=1e-5]
Steps:  72%|███████▎  | 435/600 [14:08<04:31,  1.64s/it, loss=0.131, lr=1e-5] 
Steps:  73%|███████▎  | 436/600 [14:10<04:21,  1.59s/it, loss=0.131, lr=1e-5]
Steps:  73%|███████▎  | 436/600 [14:10<04:21,  1.59s/it, loss=0.0404, lr=1e-5]
Steps:  73%|███████▎  | 437/600 [14:12<04:36,  1.70s/it, loss=0.0404, lr=1e-5]
Steps:  73%|███████▎  | 437/600 [14:12<04:36,  1.70s/it, loss=0.0824, lr=1e-5]
Steps:  73%|███████▎  | 438/600 [14:13<04:27,  1.65s/it, loss=0.0824, lr=1e-5]
Steps:  73%|███████▎  | 438/600 [14:13<04:27,  1.65s/it, loss=0.0499, lr=1e-5]
Steps:  73%|███████▎  | 439/600 [14:14<04:07,  1.54s/it, loss=0.0499, lr=1e-5]
Steps:  73%|███████▎  | 439/600 [14:14<04:07,  1.54s/it, loss=0.0285, lr=1e-5]
Steps:  73%|███████▎  | 440/600 [14:15<03:28,  1.30s/it, loss=0.0285, lr=1e-5]
Steps:  73%|███████▎  | 440/600 [14:15<03:28,  1.30s/it, loss=0.0314, lr=1e-5]
Steps:  74%|███████▎  | 441/600 [14:18<04:15,  1.61s/it, loss=0.0314, lr=1e-5]
Steps:  74%|███████▎  | 441/600 [14:18<04:15,  1.61s/it, loss=0.16, lr=1e-5]  
Steps:  74%|███████▎  | 442/600 [14:19<04:21,  1.66s/it, loss=0.16, lr=1e-5]
Steps:  74%|███████▎  | 442/600 [14:19<04:21,  1.66s/it, loss=0.0403, lr=1e-5]
Steps:  74%|███████▍  | 443/600 [14:21<04:07,  1.58s/it, loss=0.0403, lr=1e-5]
Steps:  74%|███████▍  | 443/600 [14:21<04:07,  1.58s/it, loss=0.153, lr=1e-5] 
Steps:  74%|███████▍  | 444/600 [14:22<04:08,  1.59s/it, loss=0.153, lr=1e-5]
Steps:  74%|███████▍  | 444/600 [14:22<04:08,  1.59s/it, loss=0.0932, lr=1e-5]
Steps:  74%|███████▍  | 445/600 [14:24<04:09,  1.61s/it, loss=0.0932, lr=1e-5]
Steps:  74%|███████▍  | 445/600 [14:24<04:09,  1.61s/it, loss=0.0112, lr=1e-5]
Steps:  74%|███████▍  | 446/600 [14:25<04:03,  1.58s/it, loss=0.0112, lr=1e-5]
Steps:  74%|███████▍  | 446/600 [14:25<04:03,  1.58s/it, loss=0.156, lr=1e-5] 
Steps:  74%|███████▍  | 447/600 [14:27<04:03,  1.59s/it, loss=0.156, lr=1e-5]
Steps:  74%|███████▍  | 447/600 [14:27<04:03,  1.59s/it, loss=0.0717, lr=1e-5]
Steps:  75%|███████▍  | 448/600 [14:29<04:05,  1.62s/it, loss=0.0717, lr=1e-5]
Steps:  75%|███████▍  | 448/600 [14:29<04:05,  1.62s/it, loss=0.0453, lr=1e-5]
Steps:  75%|███████▍  | 449/600 [14:30<04:05,  1.63s/it, loss=0.0453, lr=1e-5]
Steps:  75%|███████▍  | 449/600 [14:30<04:05,  1.63s/it, loss=0.0957, lr=1e-5]
Steps:  75%|███████▌  | 450/600 [14:32<03:53,  1.56s/it, loss=0.0957, lr=1e-5]
Steps:  75%|███████▌  | 450/600 [14:32<03:53,  1.56s/it, loss=0.00921, lr=1e-5]
Steps:  75%|███████▌  | 451/600 [14:33<03:16,  1.32s/it, loss=0.00921, lr=1e-5]
Steps:  75%|███████▌  | 451/600 [14:33<03:16,  1.32s/it, loss=0.249, lr=1e-5]  
Steps:  75%|███████▌  | 452/600 [14:35<04:07,  1.67s/it, loss=0.249, lr=1e-5]
Steps:  75%|███████▌  | 452/600 [14:35<04:07,  1.67s/it, loss=0.0159, lr=1e-5]
Steps:  76%|███████▌  | 453/600 [14:37<04:01,  1.65s/it, loss=0.0159, lr=1e-5]
Steps:  76%|███████▌  | 453/600 [14:37<04:01,  1.65s/it, loss=0.0996, lr=1e-5]
Steps:  76%|███████▌  | 454/600 [14:38<03:55,  1.61s/it, loss=0.0996, lr=1e-5]
Steps:  76%|███████▌  | 454/600 [14:38<03:55,  1.61s/it, loss=0.0535, lr=1e-5]
Steps:  76%|███████▌  | 455/600 [14:40<03:48,  1.57s/it, loss=0.0535, lr=1e-5]
Steps:  76%|███████▌  | 455/600 [14:40<03:48,  1.57s/it, loss=0.166, lr=1e-5] 
Steps:  76%|███████▌  | 456/600 [14:41<03:46,  1.57s/it, loss=0.166, lr=1e-5]
Steps:  76%|███████▌  | 456/600 [14:41<03:46,  1.57s/it, loss=0.136, lr=1e-5]
Steps:  76%|███████▌  | 457/600 [14:43<03:43,  1.57s/it, loss=0.136, lr=1e-5]
Steps:  76%|███████▌  | 457/600 [14:43<03:43,  1.57s/it, loss=0.121, lr=1e-5]
Steps:  76%|███████▋  | 458/600 [14:45<03:53,  1.64s/it, loss=0.121, lr=1e-5]
Steps:  76%|███████▋  | 458/600 [14:45<03:53,  1.64s/it, loss=0.0988, lr=1e-5]
Steps:  76%|███████▋  | 459/600 [14:46<03:33,  1.52s/it, loss=0.0988, lr=1e-5]
Steps:  76%|███████▋  | 459/600 [14:46<03:33,  1.52s/it, loss=0.177, lr=1e-5] 
Steps:  77%|███████▋  | 460/600 [14:48<03:48,  1.63s/it, loss=0.177, lr=1e-5]
Steps:  77%|███████▋  | 460/600 [14:48<03:48,  1.63s/it, loss=0.00735, lr=1e-5]
Steps:  77%|███████▋  | 461/600 [14:49<03:37,  1.56s/it, loss=0.00735, lr=1e-5]
Steps:  77%|███████▋  | 461/600 [14:49<03:37,  1.56s/it, loss=0.139, lr=1e-5]  
Steps:  77%|███████▋  | 462/600 [14:50<03:01,  1.32s/it, loss=0.139, lr=1e-5]
Steps:  77%|███████▋  | 462/600 [14:50<03:01,  1.32s/it, loss=0.00319, lr=1e-5]
Steps:  77%|███████▋  | 463/600 [14:52<03:46,  1.65s/it, loss=0.00319, lr=1e-5]
Steps:  77%|███████▋  | 463/600 [14:52<03:46,  1.65s/it, loss=0.0314, lr=1e-5] 
Steps:  77%|███████▋  | 464/600 [14:54<03:45,  1.66s/it, loss=0.0314, lr=1e-5]
Steps:  77%|███████▋  | 464/600 [14:54<03:45,  1.66s/it, loss=0.144, lr=1e-5] 
Steps:  78%|███████▊  | 465/600 [14:55<03:30,  1.56s/it, loss=0.144, lr=1e-5]
Steps:  78%|███████▊  | 465/600 [14:55<03:30,  1.56s/it, loss=0.0149, lr=1e-5]
Steps:  78%|███████▊  | 466/600 [14:57<03:28,  1.55s/it, loss=0.0149, lr=1e-5]
Steps:  78%|███████▊  | 466/600 [14:57<03:28,  1.55s/it, loss=0.209, lr=1e-5] 
Steps:  78%|███████▊  | 467/600 [14:59<03:31,  1.59s/it, loss=0.209, lr=1e-5]
Steps:  78%|███████▊  | 467/600 [14:59<03:31,  1.59s/it, loss=0.0161, lr=1e-5]
Steps:  78%|███████▊  | 468/600 [15:00<03:29,  1.59s/it, loss=0.0161, lr=1e-5]
Steps:  78%|███████▊  | 468/600 [15:00<03:29,  1.59s/it, loss=0.00397, lr=1e-5]
Steps:  78%|███████▊  | 469/600 [15:02<03:22,  1.55s/it, loss=0.00397, lr=1e-5]
Steps:  78%|███████▊  | 469/600 [15:02<03:22,  1.55s/it, loss=0.113, lr=1e-5]  
Steps:  78%|███████▊  | 470/600 [15:03<03:28,  1.60s/it, loss=0.113, lr=1e-5]
Steps:  78%|███████▊  | 470/600 [15:03<03:28,  1.60s/it, loss=0.0168, lr=1e-5]
Steps:  78%|███████▊  | 471/600 [15:05<03:36,  1.68s/it, loss=0.0168, lr=1e-5]
Steps:  78%|███████▊  | 471/600 [15:05<03:36,  1.68s/it, loss=0.0763, lr=1e-5]
Steps:  79%|███████▊  | 472/600 [15:06<03:17,  1.54s/it, loss=0.0763, lr=1e-5]
Steps:  79%|███████▊  | 472/600 [15:06<03:17,  1.54s/it, loss=0.0395, lr=1e-5]
Steps:  79%|███████▉  | 473/600 [15:07<02:45,  1.31s/it, loss=0.0395, lr=1e-5]
Steps:  79%|███████▉  | 473/600 [15:07<02:45,  1.31s/it, loss=0.12, lr=1e-5]  
Steps:  79%|███████▉  | 474/600 [15:09<03:22,  1.61s/it, loss=0.12, lr=1e-5]
Steps:  79%|███████▉  | 474/600 [15:09<03:22,  1.61s/it, loss=0.203, lr=1e-5]
Steps:  79%|███████▉  | 475/600 [15:11<03:12,  1.54s/it, loss=0.203, lr=1e-5]
Steps:  79%|███████▉  | 475/600 [15:11<03:12,  1.54s/it, loss=0.189, lr=1e-5]
Steps:  79%|███████▉  | 476/600 [15:12<03:03,  1.48s/it, loss=0.189, lr=1e-5]
Steps:  79%|███████▉  | 476/600 [15:12<03:03,  1.48s/it, loss=0.135, lr=1e-5]
Steps:  80%|███████▉  | 477/600 [15:14<03:04,  1.50s/it, loss=0.135, lr=1e-5]
Steps:  80%|███████▉  | 477/600 [15:14<03:04,  1.50s/it, loss=0.0469, lr=1e-5]
Steps:  80%|███████▉  | 478/600 [15:15<03:09,  1.55s/it, loss=0.0469, lr=1e-5]
Steps:  80%|███████▉  | 478/600 [15:15<03:09,  1.55s/it, loss=0.0105, lr=1e-5]
Steps:  80%|███████▉  | 479/600 [15:17<03:19,  1.65s/it, loss=0.0105, lr=1e-5]
Steps:  80%|███████▉  | 479/600 [15:17<03:19,  1.65s/it, loss=0.164, lr=1e-5] 
Steps:  80%|████████  | 480/600 [15:19<03:11,  1.59s/it, loss=0.164, lr=1e-5]
Steps:  80%|████████  | 480/600 [15:19<03:11,  1.59s/it, loss=0.0244, lr=1e-5]
Steps:  80%|████████  | 481/600 [15:21<03:14,  1.64s/it, loss=0.0244, lr=1e-5]
Steps:  80%|████████  | 481/600 [15:21<03:14,  1.64s/it, loss=0.143, lr=1e-5] 
Steps:  80%|████████  | 482/600 [15:22<03:13,  1.64s/it, loss=0.143, lr=1e-5]
Steps:  80%|████████  | 482/600 [15:22<03:13,  1.64s/it, loss=0.0649, lr=1e-5]
Steps:  80%|████████  | 483/600 [15:24<03:05,  1.59s/it, loss=0.0649, lr=1e-5]
Steps:  80%|████████  | 483/600 [15:24<03:05,  1.59s/it, loss=0.0085, lr=1e-5]
Steps:  81%|████████  | 484/600 [15:24<02:35,  1.34s/it, loss=0.0085, lr=1e-5]
Steps:  81%|████████  | 484/600 [15:24<02:35,  1.34s/it, loss=0.12, lr=1e-5]  
Steps:  81%|████████  | 485/600 [15:27<03:07,  1.63s/it, loss=0.12, lr=1e-5]
Steps:  81%|████████  | 485/600 [15:27<03:07,  1.63s/it, loss=0.0175, lr=1e-5]
Steps:  81%|████████  | 486/600 [15:28<03:02,  1.60s/it, loss=0.0175, lr=1e-5]
Steps:  81%|████████  | 486/600 [15:28<03:02,  1.60s/it, loss=0.0401, lr=1e-5]
Steps:  81%|████████  | 487/600 [15:30<03:09,  1.67s/it, loss=0.0401, lr=1e-5]
Steps:  81%|████████  | 487/600 [15:30<03:09,  1.67s/it, loss=0.0936, lr=1e-5]
Steps:  81%|████████▏ | 488/600 [15:32<03:12,  1.72s/it, loss=0.0936, lr=1e-5]
Steps:  81%|████████▏ | 488/600 [15:32<03:12,  1.72s/it, loss=0.0941, lr=1e-5]
Steps:  82%|████████▏ | 489/600 [15:33<02:58,  1.60s/it, loss=0.0941, lr=1e-5]
Steps:  82%|████████▏ | 489/600 [15:33<02:58,  1.60s/it, loss=0.0712, lr=1e-5]
Steps:  82%|████████▏ | 490/600 [15:35<02:58,  1.62s/it, loss=0.0712, lr=1e-5]
Steps:  82%|████████▏ | 490/600 [15:35<02:58,  1.62s/it, loss=0.288, lr=1e-5] 
Steps:  82%|████████▏ | 491/600 [15:36<02:48,  1.54s/it, loss=0.288, lr=1e-5]
Steps:  82%|████████▏ | 491/600 [15:36<02:48,  1.54s/it, loss=0.388, lr=1e-5]
Steps:  82%|████████▏ | 492/600 [15:38<02:43,  1.51s/it, loss=0.388, lr=1e-5]
Steps:  82%|████████▏ | 492/600 [15:38<02:43,  1.51s/it, loss=0.0207, lr=1e-5]
Steps:  82%|████████▏ | 493/600 [15:39<02:47,  1.56s/it, loss=0.0207, lr=1e-5]
Steps:  82%|████████▏ | 493/600 [15:39<02:47,  1.56s/it, loss=0.0899, lr=1e-5]
Steps:  82%|████████▏ | 494/600 [15:41<02:42,  1.53s/it, loss=0.0899, lr=1e-5]
Steps:  82%|████████▏ | 494/600 [15:41<02:42,  1.53s/it, loss=0.101, lr=1e-5] 
Steps:  82%|████████▎ | 495/600 [15:42<02:15,  1.29s/it, loss=0.101, lr=1e-5]
Steps:  82%|████████▎ | 495/600 [15:42<02:15,  1.29s/it, loss=0.114, lr=1e-5]
Steps:  83%|████████▎ | 496/600 [15:44<02:47,  1.61s/it, loss=0.114, lr=1e-5]
Steps:  83%|████████▎ | 496/600 [15:44<02:47,  1.61s/it, loss=0.239, lr=1e-5]
Steps:  83%|████████▎ | 497/600 [15:46<02:51,  1.66s/it, loss=0.239, lr=1e-5]
Steps:  83%|████████▎ | 497/600 [15:46<02:51,  1.66s/it, loss=0.207, lr=1e-5]
Steps:  83%|████████▎ | 498/600 [15:47<02:43,  1.61s/it, loss=0.207, lr=1e-5]
Steps:  83%|████████▎ | 498/600 [15:47<02:43,  1.61s/it, loss=0.0539, lr=1e-5]
Steps:  83%|████████▎ | 499/600 [15:49<02:37,  1.56s/it, loss=0.0539, lr=1e-5]
Steps:  83%|████████▎ | 499/600 [15:49<02:37,  1.56s/it, loss=0.173, lr=1e-5] 
Steps:  83%|████████▎ | 500/600 [15:50<02:34,  1.55s/it, loss=0.173, lr=1e-5]10/13/2023 09:52:35 - INFO - accelerate.accelerator - Saving current state to logs/sweep_final_1_20231013093620/checkpoint-500
Model weights saved in logs/sweep_final_1_20231013093620/checkpoint-500/pytorch_lora_weights.safetensors
10/13/2023 09:52:36 - INFO - accelerate.checkpointing - Optimizer state saved in logs/sweep_final_1_20231013093620/checkpoint-500/optimizer.bin
10/13/2023 09:52:36 - INFO - accelerate.checkpointing - Scheduler state saved in logs/sweep_final_1_20231013093620/checkpoint-500/scheduler.bin
10/13/2023 09:52:36 - INFO - accelerate.checkpointing - Gradient scaler state saved in logs/sweep_final_1_20231013093620/checkpoint-500/scaler.pt
10/13/2023 09:52:36 - INFO - accelerate.checkpointing - Random states saved in logs/sweep_final_1_20231013093620/checkpoint-500/random_states_0.pkl
10/13/2023 09:52:36 - INFO - __main__ - Saved state to logs/sweep_final_1_20231013093620/checkpoint-500

Steps:  83%|████████▎ | 500/600 [15:51<02:34,  1.55s/it, loss=0.00523, lr=1e-5]
Steps:  84%|████████▎ | 501/600 [15:53<03:07,  1.90s/it, loss=0.00523, lr=1e-5]
Steps:  84%|████████▎ | 501/600 [15:53<03:07,  1.90s/it, loss=0.0977, lr=1e-5] 
Steps:  84%|████████▎ | 502/600 [15:54<02:51,  1.75s/it, loss=0.0977, lr=1e-5]
Steps:  84%|████████▎ | 502/600 [15:54<02:51,  1.75s/it, loss=0.261, lr=1e-5] 
Steps:  84%|████████▍ | 503/600 [15:56<02:53,  1.79s/it, loss=0.261, lr=1e-5]
Steps:  84%|████████▍ | 503/600 [15:56<02:53,  1.79s/it, loss=0.107, lr=1e-5]
Steps:  84%|████████▍ | 504/600 [15:58<02:45,  1.72s/it, loss=0.107, lr=1e-5]
Steps:  84%|████████▍ | 504/600 [15:58<02:45,  1.72s/it, loss=0.0263, lr=1e-5]
Steps:  84%|████████▍ | 505/600 [15:59<02:26,  1.54s/it, loss=0.0263, lr=1e-5]
Steps:  84%|████████▍ | 505/600 [15:59<02:26,  1.54s/it, loss=0.156, lr=1e-5] 
Steps:  84%|████████▍ | 506/600 [16:00<02:02,  1.31s/it, loss=0.156, lr=1e-5]
Steps:  84%|████████▍ | 506/600 [16:00<02:02,  1.31s/it, loss=0.0112, lr=1e-5]
Steps:  84%|████████▍ | 507/600 [16:02<02:24,  1.55s/it, loss=0.0112, lr=1e-5]
Steps:  84%|████████▍ | 507/600 [16:02<02:24,  1.55s/it, loss=0.0207, lr=1e-5]
Steps:  85%|████████▍ | 508/600 [16:03<02:24,  1.57s/it, loss=0.0207, lr=1e-5]
Steps:  85%|████████▍ | 508/600 [16:03<02:24,  1.57s/it, loss=0.138, lr=1e-5] 
Steps:  85%|████████▍ | 509/600 [16:05<02:24,  1.59s/it, loss=0.138, lr=1e-5]
Steps:  85%|████████▍ | 509/600 [16:05<02:24,  1.59s/it, loss=0.146, lr=1e-5]
Steps:  85%|████████▌ | 510/600 [16:06<02:21,  1.57s/it, loss=0.146, lr=1e-5]
Steps:  85%|████████▌ | 510/600 [16:06<02:21,  1.57s/it, loss=0.0362, lr=1e-5]
Steps:  85%|████████▌ | 511/600 [16:08<02:18,  1.56s/it, loss=0.0362, lr=1e-5]
Steps:  85%|████████▌ | 511/600 [16:08<02:18,  1.56s/it, loss=0.0338, lr=1e-5]
Steps:  85%|████████▌ | 512/600 [16:10<02:18,  1.57s/it, loss=0.0338, lr=1e-5]
Steps:  85%|████████▌ | 512/600 [16:10<02:18,  1.57s/it, loss=0.315, lr=1e-5] 
Steps:  86%|████████▌ | 513/600 [16:11<02:18,  1.60s/it, loss=0.315, lr=1e-5]
Steps:  86%|████████▌ | 513/600 [16:11<02:18,  1.60s/it, loss=0.123, lr=1e-5]
Steps:  86%|████████▌ | 514/600 [16:13<02:19,  1.63s/it, loss=0.123, lr=1e-5]
Steps:  86%|████████▌ | 514/600 [16:13<02:19,  1.63s/it, loss=0.00737, lr=1e-5]
Steps:  86%|████████▌ | 515/600 [16:15<02:18,  1.63s/it, loss=0.00737, lr=1e-5]
Steps:  86%|████████▌ | 515/600 [16:15<02:18,  1.63s/it, loss=0.189, lr=1e-5]  
Steps:  86%|████████▌ | 516/600 [16:16<02:07,  1.52s/it, loss=0.189, lr=1e-5]
Steps:  86%|████████▌ | 516/600 [16:16<02:07,  1.52s/it, loss=0.228, lr=1e-5]
Steps:  86%|████████▌ | 517/600 [16:17<01:47,  1.29s/it, loss=0.228, lr=1e-5]
Steps:  86%|████████▌ | 517/600 [16:17<01:47,  1.29s/it, loss=0.00354, lr=1e-5]
Steps:  86%|████████▋ | 518/600 [16:19<02:04,  1.52s/it, loss=0.00354, lr=1e-5]
Steps:  86%|████████▋ | 518/600 [16:19<02:04,  1.52s/it, loss=0.2, lr=1e-5]    
Steps:  86%|████████▋ | 519/600 [16:20<02:04,  1.54s/it, loss=0.2, lr=1e-5]
Steps:  86%|████████▋ | 519/600 [16:20<02:04,  1.54s/it, loss=0.15, lr=1e-5]
Steps:  87%|████████▋ | 520/600 [16:22<02:02,  1.53s/it, loss=0.15, lr=1e-5]
Steps:  87%|████████▋ | 520/600 [16:22<02:02,  1.53s/it, loss=0.0263, lr=1e-5]
Steps:  87%|████████▋ | 521/600 [16:24<02:05,  1.59s/it, loss=0.0263, lr=1e-5]
Steps:  87%|████████▋ | 521/600 [16:24<02:05,  1.59s/it, loss=0.00485, lr=1e-5]
Steps:  87%|████████▋ | 522/600 [16:25<02:07,  1.63s/it, loss=0.00485, lr=1e-5]
Steps:  87%|████████▋ | 522/600 [16:25<02:07,  1.63s/it, loss=0.0463, lr=1e-5] 
Steps:  87%|████████▋ | 523/600 [16:27<02:10,  1.70s/it, loss=0.0463, lr=1e-5]
Steps:  87%|████████▋ | 523/600 [16:27<02:10,  1.70s/it, loss=0.285, lr=1e-5] 
Steps:  87%|████████▋ | 524/600 [16:29<02:05,  1.65s/it, loss=0.285, lr=1e-5]
Steps:  87%|████████▋ | 524/600 [16:29<02:05,  1.65s/it, loss=0.146, lr=1e-5]
Steps:  88%|████████▊ | 525/600 [16:30<01:59,  1.59s/it, loss=0.146, lr=1e-5]
Steps:  88%|████████▊ | 525/600 [16:30<01:59,  1.59s/it, loss=0.0456, lr=1e-5]
Steps:  88%|████████▊ | 526/600 [16:32<01:56,  1.58s/it, loss=0.0456, lr=1e-5]
Steps:  88%|████████▊ | 526/600 [16:32<01:56,  1.58s/it, loss=0.0061, lr=1e-5]
Steps:  88%|████████▊ | 527/600 [16:33<01:50,  1.52s/it, loss=0.0061, lr=1e-5]
Steps:  88%|████████▊ | 527/600 [16:33<01:50,  1.52s/it, loss=0.0539, lr=1e-5]
Steps:  88%|████████▊ | 528/600 [16:34<01:32,  1.29s/it, loss=0.0539, lr=1e-5]
Steps:  88%|████████▊ | 528/600 [16:34<01:32,  1.29s/it, loss=0.331, lr=1e-5] 
Steps:  88%|████████▊ | 529/600 [16:36<01:51,  1.58s/it, loss=0.331, lr=1e-5]
Steps:  88%|████████▊ | 529/600 [16:36<01:51,  1.58s/it, loss=0.134, lr=1e-5]
Steps:  88%|████████▊ | 530/600 [16:38<01:49,  1.56s/it, loss=0.134, lr=1e-5]
Steps:  88%|████████▊ | 530/600 [16:38<01:49,  1.56s/it, loss=0.0219, lr=1e-5]
Steps:  88%|████████▊ | 531/600 [16:39<01:53,  1.65s/it, loss=0.0219, lr=1e-5]
Steps:  88%|████████▊ | 531/600 [16:39<01:53,  1.65s/it, loss=0.134, lr=1e-5] 
Steps:  89%|████████▊ | 532/600 [16:41<01:56,  1.71s/it, loss=0.134, lr=1e-5]
Steps:  89%|████████▊ | 532/600 [16:41<01:56,  1.71s/it, loss=0.146, lr=1e-5]
Steps:  89%|████████▉ | 533/600 [16:43<01:52,  1.67s/it, loss=0.146, lr=1e-5]
Steps:  89%|████████▉ | 533/600 [16:43<01:52,  1.67s/it, loss=0.0368, lr=1e-5]
Steps:  89%|████████▉ | 534/600 [16:44<01:47,  1.63s/it, loss=0.0368, lr=1e-5]
Steps:  89%|████████▉ | 534/600 [16:44<01:47,  1.63s/it, loss=0.0638, lr=1e-5]
Steps:  89%|████████▉ | 535/600 [16:46<01:41,  1.57s/it, loss=0.0638, lr=1e-5]
Steps:  89%|████████▉ | 535/600 [16:46<01:41,  1.57s/it, loss=0.142, lr=1e-5] 
Steps:  89%|████████▉ | 536/600 [16:48<01:43,  1.62s/it, loss=0.142, lr=1e-5]
Steps:  89%|████████▉ | 536/600 [16:48<01:43,  1.62s/it, loss=0.223, lr=1e-5]
Steps:  90%|████████▉ | 537/600 [16:49<01:34,  1.49s/it, loss=0.223, lr=1e-5]
Steps:  90%|████████▉ | 537/600 [16:49<01:34,  1.49s/it, loss=0.106, lr=1e-5]
Steps:  90%|████████▉ | 538/600 [16:50<01:28,  1.43s/it, loss=0.106, lr=1e-5]
Steps:  90%|████████▉ | 538/600 [16:50<01:28,  1.43s/it, loss=0.269, lr=1e-5]
Steps:  90%|████████▉ | 539/600 [16:51<01:14,  1.23s/it, loss=0.269, lr=1e-5]
Steps:  90%|████████▉ | 539/600 [16:51<01:14,  1.23s/it, loss=0.279, lr=1e-5]
Steps:  90%|█████████ | 540/600 [16:53<01:29,  1.49s/it, loss=0.279, lr=1e-5]
Steps:  90%|█████████ | 540/600 [16:53<01:29,  1.49s/it, loss=0.0144, lr=1e-5]
Steps:  90%|█████████ | 541/600 [16:55<01:31,  1.54s/it, loss=0.0144, lr=1e-5]
Steps:  90%|█████████ | 541/600 [16:55<01:31,  1.54s/it, loss=0.0143, lr=1e-5]
Steps:  90%|█████████ | 542/600 [16:56<01:32,  1.59s/it, loss=0.0143, lr=1e-5]
Steps:  90%|█████████ | 542/600 [16:56<01:32,  1.59s/it, loss=0.0137, lr=1e-5]
Steps:  90%|█████████ | 543/600 [16:58<01:34,  1.66s/it, loss=0.0137, lr=1e-5]
Steps:  90%|█████████ | 543/600 [16:58<01:34,  1.66s/it, loss=0.0924, lr=1e-5]
Steps:  91%|█████████ | 544/600 [16:59<01:27,  1.56s/it, loss=0.0924, lr=1e-5]
Steps:  91%|█████████ | 544/600 [16:59<01:27,  1.56s/it, loss=0.0326, lr=1e-5]
Steps:  91%|█████████ | 545/600 [17:01<01:24,  1.54s/it, loss=0.0326, lr=1e-5]
Steps:  91%|█████████ | 545/600 [17:01<01:24,  1.54s/it, loss=0.244, lr=1e-5] 
Steps:  91%|█████████ | 546/600 [17:02<01:23,  1.55s/it, loss=0.244, lr=1e-5]
Steps:  91%|█████████ | 546/600 [17:02<01:23,  1.55s/it, loss=0.0889, lr=1e-5]
Steps:  91%|█████████ | 547/600 [17:04<01:26,  1.64s/it, loss=0.0889, lr=1e-5]
Steps:  91%|█████████ | 547/600 [17:04<01:26,  1.64s/it, loss=0.0244, lr=1e-5]
Steps:  91%|█████████▏| 548/600 [17:06<01:23,  1.60s/it, loss=0.0244, lr=1e-5]
Steps:  91%|█████████▏| 548/600 [17:06<01:23,  1.60s/it, loss=0.0442, lr=1e-5]
Steps:  92%|█████████▏| 549/600 [17:07<01:16,  1.50s/it, loss=0.0442, lr=1e-5]
Steps:  92%|█████████▏| 549/600 [17:07<01:16,  1.50s/it, loss=0.17, lr=1e-5]  
Steps:  92%|█████████▏| 550/600 [17:08<01:03,  1.28s/it, loss=0.17, lr=1e-5]
Steps:  92%|█████████▏| 550/600 [17:08<01:03,  1.28s/it, loss=0.0453, lr=1e-5]
Steps:  92%|█████████▏| 551/600 [17:10<01:17,  1.59s/it, loss=0.0453, lr=1e-5]
Steps:  92%|█████████▏| 551/600 [17:10<01:17,  1.59s/it, loss=0.104, lr=1e-5] 
Steps:  92%|█████████▏| 552/600 [17:12<01:16,  1.59s/it, loss=0.104, lr=1e-5]
Steps:  92%|█████████▏| 552/600 [17:12<01:16,  1.59s/it, loss=0.327, lr=1e-5]
Steps:  92%|█████████▏| 553/600 [17:13<01:13,  1.57s/it, loss=0.327, lr=1e-5]
Steps:  92%|█████████▏| 553/600 [17:13<01:13,  1.57s/it, loss=0.0674, lr=1e-5]
Steps:  92%|█████████▏| 554/600 [17:15<01:15,  1.65s/it, loss=0.0674, lr=1e-5]
Steps:  92%|█████████▏| 554/600 [17:15<01:15,  1.65s/it, loss=0.159, lr=1e-5] 
Steps:  92%|█████████▎| 555/600 [17:17<01:12,  1.60s/it, loss=0.159, lr=1e-5]
Steps:  92%|█████████▎| 555/600 [17:17<01:12,  1.60s/it, loss=0.131, lr=1e-5]
Steps:  93%|█████████▎| 556/600 [17:18<01:09,  1.58s/it, loss=0.131, lr=1e-5]
Steps:  93%|█████████▎| 556/600 [17:18<01:09,  1.58s/it, loss=0.0999, lr=1e-5]
Steps:  93%|█████████▎| 557/600 [17:20<01:07,  1.56s/it, loss=0.0999, lr=1e-5]
Steps:  93%|█████████▎| 557/600 [17:20<01:07,  1.56s/it, loss=0.261, lr=1e-5] 
Steps:  93%|█████████▎| 558/600 [17:21<01:07,  1.61s/it, loss=0.261, lr=1e-5]
Steps:  93%|█████████▎| 558/600 [17:21<01:07,  1.61s/it, loss=0.0776, lr=1e-5]
Steps:  93%|█████████▎| 559/600 [17:23<01:05,  1.60s/it, loss=0.0776, lr=1e-5]
Steps:  93%|█████████▎| 559/600 [17:23<01:05,  1.60s/it, loss=0.0331, lr=1e-5]
Steps:  93%|█████████▎| 560/600 [17:24<00:58,  1.46s/it, loss=0.0331, lr=1e-5]
Steps:  93%|█████████▎| 560/600 [17:24<00:58,  1.46s/it, loss=0.0378, lr=1e-5]
Steps:  94%|█████████▎| 561/600 [17:25<00:48,  1.25s/it, loss=0.0378, lr=1e-5]
Steps:  94%|█████████▎| 561/600 [17:25<00:48,  1.25s/it, loss=0.148, lr=1e-5] 10/13/2023 09:54:10 - 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 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...:  57%|█████▋    | 4/7 [00:00<00:00, 36.01it/s]Loaded scheduler as EulerDiscreteScheduler from `scheduler` subfolder of stabilityai/stable-diffusion-xl-base-1.0.

Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 61.20it/s]
{'solver_type', 'algorithm_type', 'lambda_min_clipped', 'lower_order_final', 'variance_type', 'solver_order', 'thresholding', 'dynamic_thresholding_ratio'} was not found in config. Values will be initialized to default values.
10/13/2023 09:55:07 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
10/13/2023 09:55:56 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
10/13/2023 09:56:45 - INFO - __main__ - Image features shape: torch.Size([5, 75648])

Steps:  94%|█████████▎| 562/600 [20:10<31:54, 50.37s/it, loss=0.148, lr=1e-5]
Steps:  94%|█████████▎| 562/600 [20:10<31:54, 50.37s/it, loss=0.223, lr=1e-5]
Steps:  94%|█████████▍| 563/600 [20:11<22:01, 35.71s/it, loss=0.223, lr=1e-5]
Steps:  94%|█████████▍| 563/600 [20:11<22:01, 35.71s/it, loss=0.014, lr=1e-5]
Steps:  94%|█████████▍| 564/600 [20:13<15:20, 25.56s/it, loss=0.014, lr=1e-5]
Steps:  94%|█████████▍| 564/600 [20:13<15:20, 25.56s/it, loss=0.0861, lr=1e-5]
Steps:  94%|█████████▍| 565/600 [20:15<10:41, 18.33s/it, loss=0.0861, lr=1e-5]
Steps:  94%|█████████▍| 565/600 [20:15<10:41, 18.33s/it, loss=0.102, lr=1e-5] 
Steps:  94%|█████████▍| 566/600 [20:16<07:32, 13.30s/it, loss=0.102, lr=1e-5]
Steps:  94%|█████████▍| 566/600 [20:16<07:32, 13.30s/it, loss=0.18, lr=1e-5] 
Steps:  94%|█████████▍| 567/600 [20:18<05:25,  9.85s/it, loss=0.18, lr=1e-5]
Steps:  94%|█████████▍| 567/600 [20:18<05:25,  9.85s/it, loss=0.0471, lr=1e-5]
Steps:  95%|█████████▍| 568/600 [20:19<03:53,  7.30s/it, loss=0.0471, lr=1e-5]
Steps:  95%|█████████▍| 568/600 [20:19<03:53,  7.30s/it, loss=0.0226, lr=1e-5]
Steps:  95%|█████████▍| 569/600 [20:21<02:50,  5.50s/it, loss=0.0226, lr=1e-5]
Steps:  95%|█████████▍| 569/600 [20:21<02:50,  5.50s/it, loss=0.165, lr=1e-5] 
Steps:  95%|█████████▌| 570/600 [20:22<02:08,  4.29s/it, loss=0.165, lr=1e-5]
Steps:  95%|█████████▌| 570/600 [20:22<02:08,  4.29s/it, loss=0.138, lr=1e-5]
Steps:  95%|█████████▌| 571/600 [20:24<01:39,  3.44s/it, loss=0.138, lr=1e-5]
Steps:  95%|█████████▌| 571/600 [20:24<01:39,  3.44s/it, loss=0.179, lr=1e-5]
Steps:  95%|█████████▌| 572/600 [20:24<01:13,  2.63s/it, loss=0.179, lr=1e-5]
Steps:  95%|█████████▌| 572/600 [20:24<01:13,  2.63s/it, loss=0.00285, lr=1e-5]
Steps:  96%|█████████▌| 573/600 [20:26<01:06,  2.46s/it, loss=0.00285, lr=1e-5]
Steps:  96%|█████████▌| 573/600 [20:26<01:06,  2.46s/it, loss=0.00285, lr=1e-5]
Steps:  96%|█████████▌| 574/600 [20:28<00:55,  2.13s/it, loss=0.00285, lr=1e-5]
Steps:  96%|█████████▌| 574/600 [20:28<00:55,  2.13s/it, loss=0.0914, lr=1e-5] 
Steps:  96%|█████████▌| 575/600 [20:30<00:50,  2.02s/it, loss=0.0914, lr=1e-5]
Steps:  96%|█████████▌| 575/600 [20:30<00:50,  2.02s/it, loss=0.00982, lr=1e-5]
Steps:  96%|█████████▌| 576/600 [20:31<00:45,  1.91s/it, loss=0.00982, lr=1e-5]
Steps:  96%|█████████▌| 576/600 [20:31<00:45,  1.91s/it, loss=0.0492, lr=1e-5] 
Steps:  96%|█████████▌| 577/600 [20:33<00:41,  1.81s/it, loss=0.0492, lr=1e-5]
Steps:  96%|█████████▌| 577/600 [20:33<00:41,  1.81s/it, loss=0.00427, lr=1e-5]
Steps:  96%|█████████▋| 578/600 [20:34<00:37,  1.69s/it, loss=0.00427, lr=1e-5]
Steps:  96%|█████████▋| 578/600 [20:34<00:37,  1.69s/it, loss=0.336, lr=1e-5]  
Steps:  96%|█████████▋| 579/600 [20:36<00:35,  1.71s/it, loss=0.336, lr=1e-5]
Steps:  96%|█████████▋| 579/600 [20:36<00:35,  1.71s/it, loss=0.0298, lr=1e-5]
Steps:  97%|█████████▋| 580/600 [20:38<00:34,  1.75s/it, loss=0.0298, lr=1e-5]
Steps:  97%|█████████▋| 580/600 [20:38<00:34,  1.75s/it, loss=0.233, lr=1e-5] 
Steps:  97%|█████████▋| 581/600 [20:39<00:32,  1.69s/it, loss=0.233, lr=1e-5]
Steps:  97%|█████████▋| 581/600 [20:39<00:32,  1.69s/it, loss=0.15, lr=1e-5] 
Steps:  97%|█████████▋| 582/600 [20:41<00:29,  1.62s/it, loss=0.15, lr=1e-5]
Steps:  97%|█████████▋| 582/600 [20:41<00:29,  1.62s/it, loss=0.233, lr=1e-5]
Steps:  97%|█████████▋| 583/600 [20:42<00:23,  1.35s/it, loss=0.233, lr=1e-5]
Steps:  97%|█████████▋| 583/600 [20:42<00:23,  1.35s/it, loss=0.0953, lr=1e-5]
Steps:  97%|█████████▋| 584/600 [20:44<00:25,  1.58s/it, loss=0.0953, lr=1e-5]
Steps:  97%|█████████▋| 584/600 [20:44<00:25,  1.58s/it, loss=0.25, lr=1e-5]  
Steps:  98%|█████████▊| 585/600 [20:45<00:23,  1.54s/it, loss=0.25, lr=1e-5]
Steps:  98%|█████████▊| 585/600 [20:45<00:23,  1.54s/it, loss=0.168, lr=1e-5]
Steps:  98%|█████████▊| 586/600 [20:47<00:21,  1.55s/it, loss=0.168, lr=1e-5]
Steps:  98%|█████████▊| 586/600 [20:47<00:21,  1.55s/it, loss=0.0179, lr=1e-5]
Steps:  98%|█████████▊| 587/600 [20:48<00:20,  1.56s/it, loss=0.0179, lr=1e-5]
Steps:  98%|█████████▊| 587/600 [20:48<00:20,  1.56s/it, loss=0.151, lr=1e-5] 
Steps:  98%|█████████▊| 588/600 [20:50<00:19,  1.59s/it, loss=0.151, lr=1e-5]
Steps:  98%|█████████▊| 588/600 [20:50<00:19,  1.59s/it, loss=0.114, lr=1e-5]
Steps:  98%|█████████▊| 589/600 [20:52<00:18,  1.66s/it, loss=0.114, lr=1e-5]
Steps:  98%|█████████▊| 589/600 [20:52<00:18,  1.66s/it, loss=0.017, lr=1e-5]
Steps:  98%|█████████▊| 590/600 [20:53<00:16,  1.64s/it, loss=0.017, lr=1e-5]
Steps:  98%|█████████▊| 590/600 [20:53<00:16,  1.64s/it, loss=0.0722, lr=1e-5]
Steps:  98%|█████████▊| 591/600 [20:55<00:14,  1.56s/it, loss=0.0722, lr=1e-5]
Steps:  98%|█████████▊| 591/600 [20:55<00:14,  1.56s/it, loss=0.0304, lr=1e-5]
Steps:  99%|█████████▊| 592/600 [20:56<00:13,  1.63s/it, loss=0.0304, lr=1e-5]
Steps:  99%|█████████▊| 592/600 [20:56<00:13,  1.63s/it, loss=0.0739, lr=1e-5]
Steps:  99%|█████████▉| 593/600 [20:58<00:10,  1.52s/it, loss=0.0739, lr=1e-5]
Steps:  99%|█████████▉| 593/600 [20:58<00:10,  1.52s/it, loss=0.188, lr=1e-5] 
Steps:  99%|█████████▉| 594/600 [20:58<00:07,  1.29s/it, loss=0.188, lr=1e-5]
Steps:  99%|█████████▉| 594/600 [20:58<00:07,  1.29s/it, loss=0.00331, lr=1e-5]
Steps:  99%|█████████▉| 595/600 [21:01<00:07,  1.53s/it, loss=0.00331, lr=1e-5]
Steps:  99%|█████████▉| 595/600 [21:01<00:07,  1.53s/it, loss=0.193, lr=1e-5]  
Steps:  99%|█████████▉| 596/600 [21:02<00:06,  1.59s/it, loss=0.193, lr=1e-5]
Steps:  99%|█████████▉| 596/600 [21:02<00:06,  1.59s/it, loss=0.161, lr=1e-5]
Steps: 100%|█████████▉| 597/600 [21:04<00:04,  1.65s/it, loss=0.161, lr=1e-5]
Steps: 100%|█████████▉| 597/600 [21:04<00:04,  1.65s/it, loss=0.208, lr=1e-5]
Steps: 100%|█████████▉| 598/600 [21:06<00:03,  1.62s/it, loss=0.208, lr=1e-5]
Steps: 100%|█████████▉| 598/600 [21:06<00:03,  1.62s/it, loss=0.201, lr=1e-5]
Steps: 100%|█████████▉| 599/600 [21:07<00:01,  1.61s/it, loss=0.201, lr=1e-5]
Steps: 100%|█████████▉| 599/600 [21:07<00:01,  1.61s/it, loss=0.101, lr=1e-5]
Steps: 100%|██████████| 600/600 [21:09<00:00,  1.56s/it, loss=0.101, lr=1e-5]
Steps: 100%|██████████| 600/600 [21:09<00:00,  1.56s/it, loss=0.0761, lr=1e-5]Model weights saved in logs/sweep_final_1_20231013093620/pytorch_lora_weights.safetensors


Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/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...:  43%|████▎     | 3/7 [00:00<00:01,  3.18it/s]Loaded tokenizer_2 as CLIPTokenizer from `tokenizer_2` 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...:  71%|███████▏  | 5/7 [00:01<00:00,  4.30it/s]Loaded scheduler as EulerDiscreteScheduler from `scheduler` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
{'attention_type', 'dropout'} 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...: 100%|██████████| 7/7 [00:04<00:00,  1.40it/s]
Loading pipeline components...: 100%|██████████| 7/7 [00:04<00:00,  1.73it/s]
{'solver_type', 'algorithm_type', 'lambda_min_clipped', 'lower_order_final', 'variance_type', 'solver_order', 'thresholding', 'dynamic_thresholding_ratio'} 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,  5.41it/s]

  4%|▍         | 2/50 [00:00<00:07,  6.25it/s]

  6%|▌         | 3/50 [00:00<00:08,  5.84it/s]

  8%|▊         | 4/50 [00:00<00:08,  5.63it/s]

 10%|█         | 5/50 [00:00<00:08,  5.52it/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,  5.38it/s]

 18%|█▊        | 9/50 [00:01<00:07,  5.37it/s]

 20%|██        | 10/50 [00:01<00:07,  5.36it/s]

 22%|██▏       | 11/50 [00:02<00:07,  5.35it/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,  5.34it/s]

 30%|███       | 15/50 [00:02<00:06,  5.33it/s]

 32%|███▏      | 16/50 [00:02<00:06,  5.34it/s]

 34%|███▍      | 17/50 [00:03<00:06,  5.33it/s]

 36%|███▌      | 18/50 [00:03<00:05,  5.34it/s]

 38%|███▊      | 19/50 [00:03<00:05,  5.33it/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,  5.33it/s]

 46%|████▌     | 23/50 [00:04<00:05,  5.33it/s]

 48%|████▊     | 24/50 [00:04<00:04,  5.32it/s]

 50%|█████     | 25/50 [00:04<00:04,  5.33it/s]

 52%|█████▏    | 26/50 [00:04<00:04,  5.33it/s]

 54%|█████▍    | 27/50 [00:05<00:04,  5.33it/s]

 56%|█████▌    | 28/50 [00:05<00:04,  5.32it/s]

 58%|█████▊    | 29/50 [00:05<00:03,  5.32it/s]

 60%|██████    | 30/50 [00:05<00:03,  5.33it/s]

 62%|██████▏   | 31/50 [00:05<00:03,  5.32it/s]

 64%|██████▍   | 32/50 [00:05<00:03,  5.32it/s]

 66%|██████▌   | 33/50 [00:06<00:03,  5.32it/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,  5.32it/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,  5.32it/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,  5.31it/s]

 86%|████████▌ | 43/50 [00:08<00:01,  5.31it/s]

 88%|████████▊ | 44/50 [00:08<00:01,  5.32it/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,  5.29it/s]

 96%|█████████▌| 48/50 [00:08<00:00,  5.30it/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,  5.35it/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,  6.23it/s]

  6%|▌         | 3/50 [00:00<00:08,  5.79it/s]

  8%|▊         | 4/50 [00:00<00:08,  5.61it/s]

 10%|█         | 5/50 [00:00<00:08,  5.48it/s]

 12%|█▏        | 6/50 [00:01<00:08,  5.39it/s]

 14%|█▍        | 7/50 [00:01<00:07,  5.39it/s]

 16%|█▌        | 8/50 [00:01<00:12,  3.24it/s]

 18%|█▊        | 9/50 [00:02<00:11,  3.72it/s]

 20%|██        | 10/50 [00:02<00:09,  4.10it/s]

 22%|██▏       | 11/50 [00:02<00:08,  4.41it/s]

 24%|██▍       | 12/50 [00:02<00:08,  4.64it/s]

 26%|██▌       | 13/50 [00:02<00:07,  4.81it/s]

 28%|██▊       | 14/50 [00:02<00:07,  4.95it/s]

 30%|███       | 15/50 [00:03<00:06,  5.05it/s]

 32%|███▏      | 16/50 [00:03<00:06,  5.13it/s]

 34%|███▍      | 17/50 [00:03<00:06,  5.18it/s]

 36%|███▌      | 18/50 [00:03<00:06,  5.22it/s]

 38%|███▊      | 19/50 [00:03<00:05,  5.24it/s]

 40%|████      | 20/50 [00:04<00:05,  5.25it/s]

 42%|████▏     | 21/50 [00:04<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 [00:05<00:04,  5.29it/s]

 52%|█████▏    | 26/50 [00:05<00:04,  5.30it/s]

 54%|█████▍    | 27/50 [00:05<00:04,  5.31it/s]

 56%|█████▌    | 28/50 [00:05<00:04,  5.32it/s]

 58%|█████▊    | 29/50 [00:05<00:03,  5.31it/s]

 60%|██████    | 30/50 [00:05<00:03,  5.31it/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,  5.31it/s]

 72%|███████▏  | 36/50 [00:07<00:02,  5.31it/s]

 74%|███████▍  | 37/50 [00:07<00:02,  5.30it/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,  5.31it/s]

 82%|████████▏ | 41/50 [00:08<00:01,  5.31it/s]

 84%|████████▍ | 42/50 [00:08<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,  5.30it/s]

 92%|█████████▏| 46/50 [00:08<00:00,  5.31it/s]

 94%|█████████▍| 47/50 [00:09<00:00,  5.29it/s]

 96%|█████████▌| 48/50 [00:09<00:00,  5.29it/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,  5.12it/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,  5.57it/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,  5.37it/s]

 16%|█▌        | 8/50 [00:01<00:07,  5.35it/s]

 18%|█▊        | 9/50 [00:01<00:07,  5.35it/s]

 20%|██        | 10/50 [00:01<00:07,  5.33it/s]

 22%|██▏       | 11/50 [00:02<00:07,  5.31it/s]

 24%|██▍       | 12/50 [00:02<00:07,  5.31it/s]

 26%|██▌       | 13/50 [00:02<00:06,  5.31it/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,  5.29it/s]

 36%|███▌      | 18/50 [00:03<00:06,  5.28it/s]

 38%|███▊      | 19/50 [00:03<00:05,  5.29it/s]

 40%|████      | 20/50 [00:03<00:05,  5.29it/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,  5.28it/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,  5.29it/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,  5.28it/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<00:02,  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,  5.29it/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,  5.30it/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,  5.29it/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,  5.32it/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,  5.55it/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,  5.34it/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,  5.31it/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,  5.28it/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,  5.27it/s]

 40%|████      | 20/50 [00:03<00:05,  5.28it/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,  5.29it/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,  5.30it/s]

 58%|█████▊    | 29/50 [00:05<00:03,  5.29it/s]

 60%|██████    | 30/50 [00:05<00:03,  5.28it/s]

 62%|██████▏   | 31/50 [00:05<00:03,  5.29it/s]

 64%|██████▍   | 32/50 [00:06<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,  5.29it/s]

 72%|███████▏  | 36/50 [00:06<00:02,  5.28it/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,  5.31it/s]

 82%|████████▏ | 41/50 [00:07<00:01,  5.30it/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,  5.29it/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,  5.30it/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,  5.31it/s]
10/13/2023 09:58:51 - 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,  5.78it/s]

  8%|▊         | 4/50 [00:00<00:08,  5.59it/s]

 10%|█         | 5/50 [00:00<00:08,  5.49it/s]

 12%|█▏        | 6/50 [00:01<00:08,  5.45it/s]

 14%|█▍        | 7/50 [00:01<00:07,  5.41it/s]

 16%|█▌        | 8/50 [00:01<00:07,  5.38it/s]

 18%|█▊        | 9/50 [00:01<00:07,  5.36it/s]

 20%|██        | 10/50 [00:01<00:07,  5.35it/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,  5.32it/s]

 30%|███       | 15/50 [00:02<00:06,  5.31it/s]

 32%|███▏      | 16/50 [00:02<00:06,  5.29it/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,  5.30it/s]

 42%|████▏     | 21/50 [00:03<00:05,  5.31it/s]

 44%|████▍     | 22/50 [00:04<00:05,  5.31it/s]

 46%|████▌     | 23/50 [00:04<00:05,  5.31it/s]

 48%|████▊     | 24/50 [00:04<00:04,  5.31it/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,  5.30it/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,  5.29it/s]

 66%|██████▌   | 33/50 [00:06<00:03,  5.29it/s]

 68%|██████▊   | 34/50 [00:06<00:03,  5.30it/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,  5.31it/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,  5.28it/s]

 84%|████████▍ | 42/50 [00:07<00:01,  5.28it/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,  5.29it/s]

 92%|█████████▏| 46/50 [00:08<00:00,  5.30it/s]

 94%|█████████▍| 47/50 [00:08<00:00,  5.29it/s]

 96%|█████████▌| 48/50 [00:09<00:00,  5.29it/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,  5.33it/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,  6.23it/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,  5.33it/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,  5.30it/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,  5.28it/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,  5.29it/s]

 38%|███▊      | 19/50 [00:03<00:05,  5.29it/s]

 40%|████      | 20/50 [00:03<00:05,  5.29it/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,  5.30it/s]

 58%|█████▊    | 29/50 [00:05<00:03,  5.30it/s]

 60%|██████    | 30/50 [00:05<00:03,  5.29it/s]

 62%|██████▏   | 31/50 [00:05<00:03,  5.29it/s]

 64%|██████▍   | 32/50 [00:06<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,  5.29it/s]

 76%|███████▌  | 38/50 [00:07<00:02,  5.29it/s]

 78%|███████▊  | 39/50 [00:07<00:02,  5.29it/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,  5.28it/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,  5.27it/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,  5.28it/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,  5.31it/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,  5.76it/s]

  8%|▊         | 4/50 [00:00<00:08,  5.57it/s]

 10%|█         | 5/50 [00:00<00:08,  5.47it/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,  5.35it/s]

 18%|█▊        | 9/50 [00:01<00:07,  5.32it/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,  5.31it/s]

 26%|██▌       | 13/50 [00:02<00:06,  5.31it/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,  5.29it/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,  5.28it/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,  5.27it/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,  5.29it/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,  5.27it/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,  5.28it/s]

 74%|███████▍  | 37/50 [00:06<00:02,  5.28it/s]

 76%|███████▌  | 38/50 [00:07<00:02,  5.29it/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,  5.29it/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,  5.29it/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,  5.29it/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,  5.31it/s]


  0%|          | 0/50 [00:00<?, ?it/s]

  2%|▏         | 1/50 [00:00<00:09,  5.38it/s]

  4%|▍         | 2/50 [00:00<00:07,  6.18it/s]

  6%|▌         | 3/50 [00:00<00:08,  5.74it/s]

  8%|▊         | 4/50 [00:00<00:08,  5.55it/s]

 10%|█         | 5/50 [00:00<00:08,  5.44it/s]

 12%|█▏        | 6/50 [00:01<00:08,  5.39it/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,  5.30it/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,  5.30it/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,  5.29it/s]

 40%|████      | 20/50 [00:03<00:05,  5.29it/s]

 42%|████▏     | 21/50 [00:03<00:05,  5.29it/s]

 44%|████▍     | 22/50 [00:04<00:05,  5.30it/s]

 46%|████▌     | 23/50 [00:04<00:05,  5.29it/s]

 48%|████▊     | 24/50 [00:04<00:04,  5.30it/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,  5.29it/s]

 60%|██████    | 30/50 [00:05<00:03,  5.27it/s]

 62%|██████▏   | 31/50 [00:05<00:03,  5.28it/s]

 64%|██████▍   | 32/50 [00:06<00:03,  5.29it/s]

 66%|██████▌   | 33/50 [00:06<00:04,  4.10it/s]

 68%|██████▊   | 34/50 [00:06<00:03,  4.39it/s]

 70%|███████   | 35/50 [00:06<00:03,  4.62it/s]

 72%|███████▏  | 36/50 [00:06<00:02,  4.81it/s]

 74%|███████▍  | 37/50 [00:07<00:02,  4.94it/s]

 76%|███████▌  | 38/50 [00:07<00:02,  5.03it/s]

 78%|███████▊  | 39/50 [00:07<00:02,  5.10it/s]

 80%|████████  | 40/50 [00:07<00:01,  5.15it/s]

 82%|████████▏ | 41/50 [00:07<00:01,  5.19it/s]

 84%|████████▍ | 42/50 [00:08<00:01,  5.22it/s]

 86%|████████▌ | 43/50 [00:08<00:01,  5.24it/s]

 88%|████████▊ | 44/50 [00:08<00:01,  5.25it/s]

 90%|█████████ | 45/50 [00:08<00:00,  5.26it/s]

 92%|█████████▏| 46/50 [00:08<00:00,  5.26it/s]

 94%|█████████▍| 47/50 [00:09<00:00,  5.26it/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,  5.27it/s]
100%|██████████| 50/50 [00:09<00:00,  5.21it/s]
10/13/2023 09:59:41 - 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,  6.23it/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,  5.42it/s]

 14%|█▍        | 7/50 [00:01<00:07,  5.38it/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,  5.34it/s]

 22%|██▏       | 11/50 [00:02<00:07,  5.33it/s]

 24%|██▍       | 12/50 [00:02<00:07,  5.33it/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,  5.32it/s]

 32%|███▏      | 16/50 [00:02<00:06,  5.31it/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,  5.29it/s]

 40%|████      | 20/50 [00:03<00:05,  5.29it/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,  5.29it/s]

 50%|█████     | 25/50 [00:04<00:04,  5.29it/s]

 52%|█████▏    | 26/50 [00:04<00:04,  5.30it/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,  5.31it/s]

 70%|███████   | 35/50 [00:06<00:02,  5.29it/s]

 72%|███████▏  | 36/50 [00:06<00:02,  5.30it/s]

 74%|███████▍  | 37/50 [00:06<00:02,  5.31it/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,  5.29it/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,  5.31it/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,  5.30it/s]

 94%|█████████▍| 47/50 [00:08<00:00,  5.30it/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,  5.30it/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,  5.39it/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,  5.55it/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,  5.32it/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,  5.30it/s]

 26%|██▌       | 13/50 [00:02<00:06,  5.29it/s]

 28%|██▊       | 14/50 [00:02<00:06,  5.29it/s]

 30%|███       | 15/50 [00:02<00:06,  5.28it/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,  5.30it/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,  5.29it/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,  5.29it/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,  5.29it/s]

 60%|██████    | 30/50 [00:05<00:03,  5.30it/s]

 62%|██████▏   | 31/50 [00:05<00:03,  5.29it/s]

 64%|██████▍   | 32/50 [00:06<00:03,  5.29it/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,  5.30it/s]

 72%|███████▏  | 36/50 [00:06<00:02,  5.30it/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,  5.29it/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,  5.29it/s]

 86%|████████▌ | 43/50 [00:08<00:01,  5.29it/s]

 88%|████████▊ | 44/50 [00:08<00:01,  5.28it/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,  5.28it/s]

100%|██████████| 50/50 [00:09<00:00,  5.27it/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,  5.37it/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,  5.57it/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,  5.37it/s]

 16%|█▌        | 8/50 [00:01<00:07,  5.34it/s]

 18%|█▊        | 9/50 [00:01<00:07,  5.32it/s]

 20%|██        | 10/50 [00:01<00:07,  5.02it/s]

 22%|██▏       | 11/50 [00:02<00:07,  5.15it/s]

 24%|██▍       | 12/50 [00:02<00:07,  5.19it/s]

 26%|██▌       | 13/50 [00:02<00:07,  5.22it/s]

 28%|██▊       | 14/50 [00:02<00:06,  5.24it/s]

 30%|███       | 15/50 [00:02<00:06,  5.25it/s]

 32%|███▏      | 16/50 [00:03<00:06,  5.27it/s]

 34%|███▍      | 17/50 [00:03<00:06,  5.27it/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,  5.29it/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,  5.29it/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,  5.29it/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,  5.28it/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,  5.29it/s]

 72%|███████▏  | 36/50 [00:06<00:02,  5.30it/s]

 74%|███████▍  | 37/50 [00:06<00:02,  5.28it/s]

 76%|███████▌  | 38/50 [00:07<00:02,  5.29it/s]

 78%|███████▊  | 39/50 [00:07<00:02,  5.29it/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,  5.28it/s]

 86%|████████▌ | 43/50 [00:08<00:01,  5.28it/s]

 88%|████████▊ | 44/50 [00:08<00:01,  5.28it/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,  5.29it/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,  5.30it/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,  6.19it/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,  5.35it/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,  5.31it/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,  5.29it/s]

 28%|██▊       | 14/50 [00:02<00:06,  5.29it/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,  5.28it/s]

 36%|███▌      | 18/50 [00:03<00:06,  5.28it/s]

 38%|███▊      | 19/50 [00:03<00:05,  5.29it/s]

 40%|████      | 20/50 [00:03<00:05,  5.29it/s]

 42%|████▏     | 21/50 [00:03<00:05,  5.28it/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,  5.28it/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,  5.29it/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,  5.29it/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,  5.28it/s]

 78%|███████▊  | 39/50 [00:07<00:02,  5.27it/s]

 80%|████████  | 40/50 [00:07<00:01,  5.28it/s]

 82%|████████▏ | 41/50 [00:07<00:01,  5.29it/s]

 84%|████████▍ | 42/50 [00:07<00:01,  5.28it/s]

 86%|████████▌ | 43/50 [00:08<00:01,  5.28it/s]

 88%|████████▊ | 44/50 [00:08<00:01,  5.28it/s]

 90%|█████████ | 45/50 [00:08<00:00,  5.28it/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,  5.28it/s]
100%|██████████| 50/50 [00:09<00:00,  5.31it/s]
10/13/2023 10:00:30 - INFO - __main__ - Image features shape: torch.Size([5, 75648])


Upload 6 LFS files:   0%|          | 0/6 [00:00<?, ?it/s]




pytorch_lora_weights.safetensors:   0%|          | 0.00/23.4M [00:00<?, ?B/s]


optimizer.bin:   0%|          | 0.00/47.4M [00:00<?, ?B/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]




pytorch_lora_weights.safetensors:   0%|          | 8.19k/23.4M [00:00<29:52, 13.1kB/s]


optimizer.bin:   0%|          | 8.19k/47.4M [00:00<1:03:47, 12.4kB/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, 12.5kB/s]





scaler.pt: 100%|██████████| 557/557 [00:00<00:00, 846B/s]




pytorch_lora_weights.safetensors:   1%|          | 279k/23.4M [00:00<00:45, 505kB/s]  
scaler.pt: 100%|██████████| 557/557 [00:00<00:00, 742B/s]



optimizer.bin:   1%|          | 369k/47.4M [00:00<01:14, 631kB/s]    
scheduler.bin: 100%|██████████| 563/563 [00:00<00:00, 709B/s]





pytorch_lora_weights.safetensors:   7%|▋         | 1.74M/23.4M [00:00<00:06, 3.40MB/s]
random_states_0.pkl: 100%|██████████| 14.6k/14.6k [00:00<00:00, 16.9kB/s]



optimizer.bin:   3%|▎         | 1.65M/47.4M [00:00<00:15, 2.95MB/s]




pytorch_lora_weights.safetensors:  23%|██▎       | 5.46M/23.4M [00:00<00:01, 10.9MB/s]


optimizer.bin:  16%|█▌        | 7.36M/47.4M [00:01<00:02, 14.0MB/s]




pytorch_lora_weights.safetensors:  52%|█████▏    | 12.1M/23.4M [00:01<00:00, 24.3MB/s]



pytorch_lora_weights.safetensors:   0%|          | 0.00/23.4M [00:00<?, ?B/s]


optimizer.bin:  32%|███▏      | 15.2M/47.4M [00:01<00:01, 27.7MB/s]



pytorch_lora_weights.safetensors:   1%|          | 279k/23.4M [00:00<00:09, 2.31MB/s]




pytorch_lora_weights.safetensors:  68%|██████▊   | 16.0M/23.4M [00:01<00:00, 22.4MB/s]



pytorch_lora_weights.safetensors:   8%|▊         | 1.84M/23.4M [00:00<00:02, 8.73MB/s]



pytorch_lora_weights.safetensors:  26%|██▌       | 6.08M/23.4M [00:00<00:00, 21.0MB/s]



pytorch_lora_weights.safetensors:  56%|█████▌    | 13.0M/23.4M [00:00<00:00, 38.3MB/s]
pytorch_lora_weights.safetensors: 100%|██████████| 23.4M/23.4M [00:01<00:00, 15.2MB/s]



optimizer.bin:  40%|████      | 19.1M/47.4M [00:01<00:01, 15.7MB/s]


optimizer.bin:  55%|█████▌    | 26.1M/47.4M [00:01<00:00, 23.2MB/s]



pytorch_lora_weights.safetensors:  73%|███████▎  | 17.1M/23.4M [00:00<00:00, 25.9MB/s]


optimizer.bin:  68%|██████▊   | 32.0M/47.4M [00:02<00:00, 21.9MB/s]
pytorch_lora_weights.safetensors: 100%|██████████| 23.4M/23.4M [00:01<00:00, 21.4MB/s]



optimizer.bin:  89%|████████▉ | 42.1M/47.4M [00:02<00:00, 33.0MB/s]
optimizer.bin: 100%|██████████| 47.4M/47.4M [00:02<00:00, 19.8MB/s]


Upload 6 LFS files:  17%|█▋        | 1/6 [00:02<00:13,  2.71s/it]
Upload 6 LFS files: 100%|██████████| 6/6 [00:02<00:00,  2.21it/s]