|
/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): |
|
10/12/2023 14:46:04 - INFO - __main__ - Current working directory: /workspace/thumbs_up |
|
10/12/2023 14:46:04 - INFO - __main__ - Distributed environment: NO |
|
Num processes: 1 |
|
Process index: 0 |
|
Local process index: 0 |
|
Device: cuda |
|
|
|
Mixed precision type: fp16 |
|
|
|
You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors. |
|
You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors. |
|
{'dynamic_thresholding_ratio', 'variance_type', 'thresholding', 'clip_sample_range'} was not found in config. Values will be initialized to default values. |
|
{'dropout', 'attention_type'} was not found in config. Values will be initialized to default values. |
|
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["id2label"]` will be overriden. |
|
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["bos_token_id"]` will be overriden. |
|
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["eos_token_id"]` will be overriden. |
|
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["id2label"]` will be overriden. |
|
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["bos_token_id"]` will be overriden. |
|
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["eos_token_id"]` will be overriden. |
|
Some weights of ViTModel were not initialized from the model checkpoint at facebook/dino-vits16 and are newly initialized: ['pooler.dense.bias', 'pooler.dense.weight'] |
|
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. |
|
wandb: Currently logged in as: berglund. Use `wandb login --relogin` to force relogin |
|
wandb: Tracking run with wandb version 0.15.12 |
|
wandb: Run data is saved locally in /workspace/thumbs_up/wandb/run-20231012_144623-7kmb1yms |
|
wandb: Run `wandb offline` to turn off syncing. |
|
wandb: Syncing run driven-cherry-43 |
|
wandb: βοΈ View project at https://wandb.ai/berglund/dreambooth-lora-sd-xl |
|
wandb: π View run at https://wandb.ai/berglund/dreambooth-lora-sd-xl/runs/7kmb1yms |
|
10/12/2023 14:46:24 - INFO - __main__ - ***** Running training ***** |
|
10/12/2023 14:46:24 - INFO - __main__ - Num examples = 21 |
|
10/12/2023 14:46:24 - INFO - __main__ - Num batches each epoch = 11 |
|
10/12/2023 14:46:24 - INFO - __main__ - Num Epochs = 55 |
|
10/12/2023 14:46:24 - INFO - __main__ - Instantaneous batch size per device = 2 |
|
10/12/2023 14:46:24 - INFO - __main__ - Total train batch size (w. parallel, distributed & accumulation) = 2 |
|
10/12/2023 14:46:24 - INFO - __main__ - Gradient Accumulation steps = 1 |
|
10/12/2023 14:46:24 - 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<25:13, 2.53s/it]
Steps: 0%| | 1/600 [00:02<25:13, 2.53s/it, loss=0.0509, lr=1e-5]
Steps: 0%| | 2/600 [00:04<20:42, 2.08s/it, loss=0.0509, lr=1e-5]
Steps: 0%| | 2/600 [00:04<20:42, 2.08s/it, loss=0.0944, lr=1e-5]
Steps: 0%| | 3/600 [00:06<20:52, 2.10s/it, loss=0.0944, lr=1e-5]
Steps: 0%| | 3/600 [00:06<20:52, 2.10s/it, loss=0.235, lr=1e-5]
Steps: 1%| | 4/600 [00:08<19:29, 1.96s/it, loss=0.235, lr=1e-5]
Steps: 1%| | 4/600 [00:08<19:29, 1.96s/it, loss=0.0463, lr=1e-5]
Steps: 1%| | 5/600 [00:09<18:24, 1.86s/it, loss=0.0463, lr=1e-5]
Steps: 1%| | 5/600 [00:09<18:24, 1.86s/it, loss=0.061, lr=1e-5]
Steps: 1%| | 6/600 [00:11<18:16, 1.85s/it, loss=0.061, lr=1e-5]
Steps: 1%| | 6/600 [00:11<18:16, 1.85s/it, loss=0.00999, lr=1e-5]
Steps: 1%| | 7/600 [00:13<17:09, 1.74s/it, loss=0.00999, lr=1e-5]
Steps: 1%| | 7/600 [00:13<17:09, 1.74s/it, loss=0.132, lr=1e-5]
Steps: 1%|β | 8/600 [00:14<16:19, 1.65s/it, loss=0.132, lr=1e-5]
Steps: 1%|β | 8/600 [00:14<16:19, 1.65s/it, loss=0.134, lr=1e-5]
Steps: 2%|β | 9/600 [00:16<16:54, 1.72s/it, loss=0.134, lr=1e-5]
Steps: 2%|β | 9/600 [00:16<16:54, 1.72s/it, loss=0.0905, lr=1e-5]
Steps: 2%|β | 10/600 [00:17<15:50, 1.61s/it, loss=0.0905, lr=1e-5]
Steps: 2%|β | 10/600 [00:17<15:50, 1.61s/it, loss=0.0586, lr=1e-5]
Steps: 2%|β | 11/600 [00:18<13:40, 1.39s/it, loss=0.0586, lr=1e-5]
Steps: 2%|β | 11/600 [00:18<13:40, 1.39s/it, loss=0.291, lr=1e-5] 10/12/2023 14:46:43 - 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][ALoaded scheduler as EulerDiscreteScheduler from `scheduler` 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. |
|
Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of stabilityai/stable-diffusion-xl-base-1.0. |
|
|
|
Loading pipeline components...: 100%|ββββββββββ| 7/7 [00:00<00:00, 64.94it/s][A
Loading pipeline components...: 100%|ββββββββββ| 7/7 [00:00<00:00, 64.60it/s] |
|
{'dynamic_thresholding_ratio', 'thresholding', 'lower_order_final', 'variance_type', 'lambda_min_clipped', 'solver_type', 'solver_order', 'algorithm_type'} was not found in config. Values will be initialized to default values. |
|
10/12/2023 14:47:40 - INFO - __main__ - Image features shape: torch.Size([5, 75648]) |
|
10/12/2023 14:48:30 - INFO - __main__ - Image features shape: torch.Size([5, 75648]) |
|
10/12/2023 14:49:20 - INFO - __main__ - Image features shape: torch.Size([5, 75648]) |
|
Steps: 2%|β | 12/600 [03:04<8:24:24, 51.47s/it, loss=0.291, lr=1e-5]
Steps: 2%|β | 12/600 [03:04<8:24:24, 51.47s/it, loss=0.143, lr=1e-5]
Steps: 2%|β | 13/600 [03:06<5:56:39, 36.46s/it, loss=0.143, lr=1e-5]
Steps: 2%|β | 13/600 [03:06<5:56:39, 36.46s/it, loss=0.103, lr=1e-5]
Steps: 2%|β | 14/600 [03:08<4:12:56, 25.90s/it, loss=0.103, lr=1e-5]
Steps: 2%|β | 14/600 [03:08<4:12:56, 25.90s/it, loss=0.185, lr=1e-5]
Steps: 2%|β | 15/600 [03:09<3:00:35, 18.52s/it, loss=0.185, lr=1e-5]
Steps: 2%|β | 15/600 [03:09<3:00:35, 18.52s/it, loss=0.137, lr=1e-5]
Steps: 3%|β | 16/600 [03:11<2:10:30, 13.41s/it, loss=0.137, lr=1e-5]
Steps: 3%|β | 16/600 [03:11<2:10:30, 13.41s/it, loss=0.0199, lr=1e-5]
Steps: 3%|β | 17/600 [03:12<1:36:23, 9.92s/it, loss=0.0199, lr=1e-5]
Steps: 3%|β | 17/600 [03:12<1:36:23, 9.92s/it, loss=0.15, lr=1e-5]
Steps: 3%|β | 18/600 [03:14<1:12:34, 7.48s/it, loss=0.15, lr=1e-5]
Steps: 3%|β | 18/600 [03:14<1:12:34, 7.48s/it, loss=0.113, lr=1e-5]
Steps: 3%|β | 19/600 [03:16<55:04, 5.69s/it, loss=0.113, lr=1e-5]
Steps: 3%|β | 19/600 [03:16<55:04, 5.69s/it, loss=0.184, lr=1e-5]
Steps: 3%|β | 20/600 [03:17<43:08, 4.46s/it, loss=0.184, lr=1e-5]
Steps: 3%|β | 20/600 [03:17<43:08, 4.46s/it, loss=0.144, lr=1e-5]
Steps: 4%|β | 21/600 [03:19<33:59, 3.52s/it, loss=0.144, lr=1e-5]
Steps: 4%|β | 21/600 [03:19<33:59, 3.52s/it, loss=0.103, lr=1e-5]
Steps: 4%|β | 22/600 [03:19<25:58, 2.70s/it, loss=0.103, lr=1e-5]
Steps: 4%|β | 22/600 [03:19<25:58, 2.70s/it, loss=0.319, lr=1e-5]
Steps: 4%|β | 23/600 [03:22<24:24, 2.54s/it, loss=0.319, lr=1e-5]
Steps: 4%|β | 23/600 [03:22<24:24, 2.54s/it, loss=0.0735, lr=1e-5]
Steps: 4%|β | 24/600 [03:23<21:13, 2.21s/it, loss=0.0735, lr=1e-5]
Steps: 4%|β | 24/600 [03:23<21:13, 2.21s/it, loss=0.097, lr=1e-5]
Steps: 4%|β | 25/600 [03:25<19:39, 2.05s/it, loss=0.097, lr=1e-5]
Steps: 4%|β | 25/600 [03:25<19:39, 2.05s/it, loss=0.0828, lr=1e-5]
Steps: 4%|β | 26/600 [03:26<18:36, 1.94s/it, loss=0.0828, lr=1e-5]
Steps: 4%|β | 26/600 [03:26<18:36, 1.94s/it, loss=0.0611, lr=1e-5]
Steps: 4%|β | 27/600 [03:28<17:58, 1.88s/it, loss=0.0611, lr=1e-5]
Steps: 4%|β | 27/600 [03:28<17:58, 1.88s/it, loss=0.197, lr=1e-5]
Steps: 5%|β | 28/600 [03:29<16:13, 1.70s/it, loss=0.197, lr=1e-5]
Steps: 5%|β | 28/600 [03:29<16:13, 1.70s/it, loss=0.0579, lr=1e-5]
Steps: 5%|β | 29/600 [03:31<16:31, 1.74s/it, loss=0.0579, lr=1e-5]
Steps: 5%|β | 29/600 [03:31<16:31, 1.74s/it, loss=0.00545, lr=1e-5]
Steps: 5%|β | 30/600 [03:33<16:48, 1.77s/it, loss=0.00545, lr=1e-5]
Steps: 5%|β | 30/600 [03:33<16:48, 1.77s/it, loss=0.151, lr=1e-5]
Steps: 5%|β | 31/600 [03:35<16:08, 1.70s/it, loss=0.151, lr=1e-5]
Steps: 5%|β | 31/600 [03:35<16:08, 1.70s/it, loss=0.0865, lr=1e-5]
Steps: 5%|β | 32/600 [03:36<14:30, 1.53s/it, loss=0.0865, lr=1e-5]
Steps: 5%|β | 32/600 [03:36<14:30, 1.53s/it, loss=0.142, lr=1e-5]
Steps: 6%|β | 33/600 [03:37<12:18, 1.30s/it, loss=0.142, lr=1e-5]
Steps: 6%|β | 33/600 [03:37<12:18, 1.30s/it, loss=0.0126, lr=1e-5]
Steps: 6%|β | 34/600 [03:39<15:40, 1.66s/it, loss=0.0126, lr=1e-5]
Steps: 6%|β | 34/600 [03:39<15:40, 1.66s/it, loss=0.0877, lr=1e-5]
Steps: 6%|β | 35/600 [03:40<14:47, 1.57s/it, loss=0.0877, lr=1e-5]
Steps: 6%|β | 35/600 [03:40<14:47, 1.57s/it, loss=0.136, lr=1e-5]
Steps: 6%|β | 36/600 [03:42<14:29, 1.54s/it, loss=0.136, lr=1e-5]
Steps: 6%|β | 36/600 [03:42<14:29, 1.54s/it, loss=0.0608, lr=1e-5]
Steps: 6%|β | 37/600 [03:43<14:14, 1.52s/it, loss=0.0608, lr=1e-5]
Steps: 6%|β | 37/600 [03:43<14:14, 1.52s/it, loss=0.197, lr=1e-5]
Steps: 6%|β | 38/600 [03:45<14:37, 1.56s/it, loss=0.197, lr=1e-5]
Steps: 6%|β | 38/600 [03:45<14:37, 1.56s/it, loss=0.184, lr=1e-5]
Steps: 6%|β | 39/600 [03:47<14:26, 1.54s/it, loss=0.184, lr=1e-5]
Steps: 6%|β | 39/600 [03:47<14:26, 1.54s/it, loss=0.175, lr=1e-5]
Steps: 7%|β | 40/600 [03:48<14:28, 1.55s/it, loss=0.175, lr=1e-5]
Steps: 7%|β | 40/600 [03:48<14:28, 1.55s/it, loss=0.0726, lr=1e-5]
Steps: 7%|β | 41/600 [03:50<15:15, 1.64s/it, loss=0.0726, lr=1e-5]
Steps: 7%|β | 41/600 [03:50<15:15, 1.64s/it, loss=0.0252, lr=1e-5]
Steps: 7%|β | 42/600 [03:52<15:05, 1.62s/it, loss=0.0252, lr=1e-5]
Steps: 7%|β | 42/600 [03:52<15:05, 1.62s/it, loss=0.173, lr=1e-5]
Steps: 7%|β | 43/600 [03:53<14:33, 1.57s/it, loss=0.173, lr=1e-5]
Steps: 7%|β | 43/600 [03:53<14:33, 1.57s/it, loss=0.247, lr=1e-5]
Steps: 7%|β | 44/600 [03:54<12:18, 1.33s/it, loss=0.247, lr=1e-5]
Steps: 7%|β | 44/600 [03:54<12:18, 1.33s/it, loss=0.0923, lr=1e-5]
Steps: 8%|β | 45/600 [03:56<13:29, 1.46s/it, loss=0.0923, lr=1e-5]
Steps: 8%|β | 45/600 [03:56<13:29, 1.46s/it, loss=0.0788, lr=1e-5]
Steps: 8%|β | 46/600 [03:57<13:42, 1.48s/it, loss=0.0788, lr=1e-5]
Steps: 8%|β | 46/600 [03:57<13:42, 1.48s/it, loss=0.24, lr=1e-5]
Steps: 8%|β | 47/600 [03:59<14:37, 1.59s/it, loss=0.24, lr=1e-5]
Steps: 8%|β | 47/600 [03:59<14:37, 1.59s/it, loss=0.15, lr=1e-5]
Steps: 8%|β | 48/600 [04:01<15:26, 1.68s/it, loss=0.15, lr=1e-5]
Steps: 8%|β | 48/600 [04:01<15:26, 1.68s/it, loss=0.0207, lr=1e-5]
Steps: 8%|β | 49/600 [04:02<15:21, 1.67s/it, loss=0.0207, lr=1e-5]
Steps: 8%|β | 49/600 [04:02<15:21, 1.67s/it, loss=0.263, lr=1e-5]
Steps: 8%|β | 50/600 [04:04<15:18, 1.67s/it, loss=0.263, lr=1e-5]
Steps: 8%|β | 50/600 [04:04<15:18, 1.67s/it, loss=0.169, lr=1e-5]
Steps: 8%|β | 51/600 [04:06<15:16, 1.67s/it, loss=0.169, lr=1e-5]
Steps: 8%|β | 51/600 [04:06<15:16, 1.67s/it, loss=0.172, lr=1e-5]
Steps: 9%|β | 52/600 [04:08<15:21, 1.68s/it, loss=0.172, lr=1e-5]
Steps: 9%|β | 52/600 [04:08<15:21, 1.68s/it, loss=0.138, lr=1e-5]
Steps: 9%|β | 53/600 [04:09<14:23, 1.58s/it, loss=0.138, lr=1e-5]
Steps: 9%|β | 53/600 [04:09<14:23, 1.58s/it, loss=0.151, lr=1e-5]
Steps: 9%|β | 54/600 [04:10<13:58, 1.54s/it, loss=0.151, lr=1e-5]
Steps: 9%|β | 54/600 [04:10<13:58, 1.54s/it, loss=0.0254, lr=1e-5]
Steps: 9%|β | 55/600 [04:11<11:49, 1.30s/it, loss=0.0254, lr=1e-5]
Steps: 9%|β | 55/600 [04:11<11:49, 1.30s/it, loss=0.0718, lr=1e-5]
Steps: 9%|β | 56/600 [04:13<14:53, 1.64s/it, loss=0.0718, lr=1e-5]
Steps: 9%|β | 56/600 [04:13<14:53, 1.64s/it, loss=0.162, lr=1e-5]
Steps: 10%|β | 57/600 [04:15<15:08, 1.67s/it, loss=0.162, lr=1e-5]
Steps: 10%|β | 57/600 [04:15<15:08, 1.67s/it, loss=0.0126, lr=1e-5]
Steps: 10%|β | 58/600 [04:17<14:16, 1.58s/it, loss=0.0126, lr=1e-5]
Steps: 10%|β | 58/600 [04:17<14:16, 1.58s/it, loss=0.169, lr=1e-5]
Steps: 10%|β | 59/600 [04:18<14:08, 1.57s/it, loss=0.169, lr=1e-5]
Steps: 10%|β | 59/600 [04:18<14:08, 1.57s/it, loss=0.155, lr=1e-5]
Steps: 10%|β | 60/600 [04:20<14:04, 1.56s/it, loss=0.155, lr=1e-5]
Steps: 10%|β | 60/600 [04:20<14:04, 1.56s/it, loss=0.0706, lr=1e-5]
Steps: 10%|β | 61/600 [04:21<14:15, 1.59s/it, loss=0.0706, lr=1e-5]
Steps: 10%|β | 61/600 [04:21<14:15, 1.59s/it, loss=0.105, lr=1e-5]
Steps: 10%|β | 62/600 [04:23<13:48, 1.54s/it, loss=0.105, lr=1e-5]
Steps: 10%|β | 62/600 [04:23<13:48, 1.54s/it, loss=0.0642, lr=1e-5]
Steps: 10%|β | 63/600 [04:25<14:34, 1.63s/it, loss=0.0642, lr=1e-5]
Steps: 10%|β | 63/600 [04:25<14:34, 1.63s/it, loss=0.136, lr=1e-5]
Steps: 11%|β | 64/600 [04:26<14:44, 1.65s/it, loss=0.136, lr=1e-5]
Steps: 11%|β | 64/600 [04:26<14:44, 1.65s/it, loss=0.169, lr=1e-5]
Steps: 11%|β | 65/600 [04:27<13:28, 1.51s/it, loss=0.169, lr=1e-5]
Steps: 11%|β | 65/600 [04:27<13:28, 1.51s/it, loss=0.0593, lr=1e-5]
Steps: 11%|β | 66/600 [04:28<11:28, 1.29s/it, loss=0.0593, lr=1e-5]
Steps: 11%|β | 66/600 [04:28<11:28, 1.29s/it, loss=0.00237, lr=1e-5]
Steps: 11%|β | 67/600 [04:30<13:54, 1.57s/it, loss=0.00237, lr=1e-5]
Steps: 11%|β | 67/600 [04:30<13:54, 1.57s/it, loss=0.0978, lr=1e-5]
Steps: 11%|ββ | 68/600 [04:32<13:37, 1.54s/it, loss=0.0978, lr=1e-5]
Steps: 11%|ββ | 68/600 [04:32<13:37, 1.54s/it, loss=0.1, lr=1e-5]
Steps: 12%|ββ | 69/600 [04:34<14:01, 1.58s/it, loss=0.1, lr=1e-5]
Steps: 12%|ββ | 69/600 [04:34<14:01, 1.58s/it, loss=0.201, lr=1e-5]
Steps: 12%|ββ | 70/600 [04:35<14:41, 1.66s/it, loss=0.201, lr=1e-5]
Steps: 12%|ββ | 70/600 [04:35<14:41, 1.66s/it, loss=0.144, lr=1e-5]
Steps: 12%|ββ | 71/600 [04:37<14:37, 1.66s/it, loss=0.144, lr=1e-5]
Steps: 12%|ββ | 71/600 [04:37<14:37, 1.66s/it, loss=0.0462, lr=1e-5]
Steps: 12%|ββ | 72/600 [04:39<14:20, 1.63s/it, loss=0.0462, lr=1e-5]
Steps: 12%|ββ | 72/600 [04:39<14:20, 1.63s/it, loss=0.0287, lr=1e-5]
Steps: 12%|ββ | 73/600 [04:40<13:52, 1.58s/it, loss=0.0287, lr=1e-5]
Steps: 12%|ββ | 73/600 [04:40<13:52, 1.58s/it, loss=0.0162, lr=1e-5]
Steps: 12%|ββ | 74/600 [04:42<14:12, 1.62s/it, loss=0.0162, lr=1e-5]
Steps: 12%|ββ | 74/600 [04:42<14:12, 1.62s/it, loss=0.114, lr=1e-5]
Steps: 12%|ββ | 75/600 [04:44<14:20, 1.64s/it, loss=0.114, lr=1e-5]
Steps: 12%|ββ | 75/600 [04:44<14:20, 1.64s/it, loss=0.0513, lr=1e-5]
Steps: 13%|ββ | 76/600 [04:45<13:20, 1.53s/it, loss=0.0513, lr=1e-5]
Steps: 13%|ββ | 76/600 [04:45<13:20, 1.53s/it, loss=0.141, lr=1e-5]
Steps: 13%|ββ | 77/600 [04:46<11:18, 1.30s/it, loss=0.141, lr=1e-5]
Steps: 13%|ββ | 77/600 [04:46<11:18, 1.30s/it, loss=0.00219, lr=1e-5]
Steps: 13%|ββ | 78/600 [04:48<13:39, 1.57s/it, loss=0.00219, lr=1e-5]
Steps: 13%|ββ | 78/600 [04:48<13:39, 1.57s/it, loss=0.0584, lr=1e-5]
Steps: 13%|ββ | 79/600 [04:49<13:58, 1.61s/it, loss=0.0584, lr=1e-5]
Steps: 13%|ββ | 79/600 [04:49<13:58, 1.61s/it, loss=0.21, lr=1e-5]
Steps: 13%|ββ | 80/600 [04:51<13:37, 1.57s/it, loss=0.21, lr=1e-5]
Steps: 13%|ββ | 80/600 [04:51<13:37, 1.57s/it, loss=0.0341, lr=1e-5]
Steps: 14%|ββ | 81/600 [04:53<14:01, 1.62s/it, loss=0.0341, lr=1e-5]
Steps: 14%|ββ | 81/600 [04:53<14:01, 1.62s/it, loss=0.111, lr=1e-5]
Steps: 14%|ββ | 82/600 [04:54<14:08, 1.64s/it, loss=0.111, lr=1e-5]
Steps: 14%|ββ | 82/600 [04:54<14:08, 1.64s/it, loss=0.0387, lr=1e-5]
Steps: 14%|ββ | 83/600 [04:56<13:01, 1.51s/it, loss=0.0387, lr=1e-5]
Steps: 14%|ββ | 83/600 [04:56<13:01, 1.51s/it, loss=0.0327, lr=1e-5]
Steps: 14%|ββ | 84/600 [04:57<13:54, 1.62s/it, loss=0.0327, lr=1e-5]
Steps: 14%|ββ | 84/600 [04:57<13:54, 1.62s/it, loss=0.0769, lr=1e-5]
Steps: 14%|ββ | 85/600 [04:59<13:51, 1.61s/it, loss=0.0769, lr=1e-5]
Steps: 14%|ββ | 85/600 [04:59<13:51, 1.61s/it, loss=0.202, lr=1e-5]
Steps: 14%|ββ | 86/600 [05:01<13:54, 1.62s/it, loss=0.202, lr=1e-5]
Steps: 14%|ββ | 86/600 [05:01<13:54, 1.62s/it, loss=0.03, lr=1e-5]
Steps: 14%|ββ | 87/600 [05:02<12:51, 1.50s/it, loss=0.03, lr=1e-5]
Steps: 14%|ββ | 87/600 [05:02<12:51, 1.50s/it, loss=0.195, lr=1e-5]
Steps: 15%|ββ | 88/600 [05:03<10:57, 1.29s/it, loss=0.195, lr=1e-5]
Steps: 15%|ββ | 88/600 [05:03<10:57, 1.29s/it, loss=0.397, lr=1e-5]
Steps: 15%|ββ | 89/600 [05:05<13:08, 1.54s/it, loss=0.397, lr=1e-5]
Steps: 15%|ββ | 89/600 [05:05<13:08, 1.54s/it, loss=0.0852, lr=1e-5]
Steps: 15%|ββ | 90/600 [05:06<12:51, 1.51s/it, loss=0.0852, lr=1e-5]
Steps: 15%|ββ | 90/600 [05:06<12:51, 1.51s/it, loss=0.156, lr=1e-5]
Steps: 15%|ββ | 91/600 [05:08<13:20, 1.57s/it, loss=0.156, lr=1e-5]
Steps: 15%|ββ | 91/600 [05:08<13:20, 1.57s/it, loss=0.063, lr=1e-5]
Steps: 15%|ββ | 92/600 [05:10<13:29, 1.59s/it, loss=0.063, lr=1e-5]
Steps: 15%|ββ | 92/600 [05:10<13:29, 1.59s/it, loss=0.143, lr=1e-5]
Steps: 16%|ββ | 93/600 [05:11<13:50, 1.64s/it, loss=0.143, lr=1e-5]
Steps: 16%|ββ | 93/600 [05:11<13:50, 1.64s/it, loss=0.00501, lr=1e-5]
Steps: 16%|ββ | 94/600 [05:13<13:50, 1.64s/it, loss=0.00501, lr=1e-5]
Steps: 16%|ββ | 94/600 [05:13<13:50, 1.64s/it, loss=0.112, lr=1e-5]
Steps: 16%|ββ | 95/600 [05:15<13:48, 1.64s/it, loss=0.112, lr=1e-5]
Steps: 16%|ββ | 95/600 [05:15<13:48, 1.64s/it, loss=0.0725, lr=1e-5]
Steps: 16%|ββ | 96/600 [05:16<13:09, 1.57s/it, loss=0.0725, lr=1e-5]
Steps: 16%|ββ | 96/600 [05:16<13:09, 1.57s/it, loss=0.0149, lr=1e-5]
Steps: 16%|ββ | 97/600 [05:18<13:32, 1.62s/it, loss=0.0149, lr=1e-5]
Steps: 16%|ββ | 97/600 [05:18<13:32, 1.62s/it, loss=0.00489, lr=1e-5]
Steps: 16%|ββ | 98/600 [05:19<12:59, 1.55s/it, loss=0.00489, lr=1e-5]
Steps: 16%|ββ | 98/600 [05:19<12:59, 1.55s/it, loss=0.131, lr=1e-5]
Steps: 16%|ββ | 99/600 [05:20<11:00, 1.32s/it, loss=0.131, lr=1e-5]
Steps: 16%|ββ | 99/600 [05:20<11:00, 1.32s/it, loss=0.251, lr=1e-5]
Steps: 17%|ββ | 100/600 [05:22<12:22, 1.48s/it, loss=0.251, lr=1e-5]
Steps: 17%|ββ | 100/600 [05:22<12:22, 1.48s/it, loss=0.228, lr=1e-5]
Steps: 17%|ββ | 101/600 [05:24<13:01, 1.57s/it, loss=0.228, lr=1e-5]
Steps: 17%|ββ | 101/600 [05:24<13:01, 1.57s/it, loss=0.0422, lr=1e-5]
Steps: 17%|ββ | 102/600 [05:25<12:55, 1.56s/it, loss=0.0422, lr=1e-5]
Steps: 17%|ββ | 102/600 [05:25<12:55, 1.56s/it, loss=0.0085, lr=1e-5]
Steps: 17%|ββ | 103/600 [05:27<12:49, 1.55s/it, loss=0.0085, lr=1e-5]
Steps: 17%|ββ | 103/600 [05:27<12:49, 1.55s/it, loss=0.11, lr=1e-5]
Steps: 17%|ββ | 104/600 [05:28<13:17, 1.61s/it, loss=0.11, lr=1e-5]
Steps: 17%|ββ | 104/600 [05:28<13:17, 1.61s/it, loss=0.0145, lr=1e-5]
Steps: 18%|ββ | 105/600 [05:30<13:44, 1.66s/it, loss=0.0145, lr=1e-5]
Steps: 18%|ββ | 105/600 [05:30<13:44, 1.66s/it, loss=0.186, lr=1e-5]
Steps: 18%|ββ | 106/600 [05:32<13:42, 1.66s/it, loss=0.186, lr=1e-5]
Steps: 18%|ββ | 106/600 [05:32<13:42, 1.66s/it, loss=0.0979, lr=1e-5]
Steps: 18%|ββ | 107/600 [05:34<13:40, 1.67s/it, loss=0.0979, lr=1e-5]
Steps: 18%|ββ | 107/600 [05:34<13:40, 1.67s/it, loss=0.206, lr=1e-5]
Steps: 18%|ββ | 108/600 [05:35<13:30, 1.65s/it, loss=0.206, lr=1e-5]
Steps: 18%|ββ | 108/600 [05:35<13:30, 1.65s/it, loss=0.055, lr=1e-5]
Steps: 18%|ββ | 109/600 [05:36<12:24, 1.52s/it, loss=0.055, lr=1e-5]
Steps: 18%|ββ | 109/600 [05:36<12:24, 1.52s/it, loss=0.0296, lr=1e-5]
Steps: 18%|ββ | 110/600 [05:37<10:32, 1.29s/it, loss=0.0296, lr=1e-5]
Steps: 18%|ββ | 110/600 [05:37<10:32, 1.29s/it, loss=0.321, lr=1e-5]
Steps: 18%|ββ | 111/600 [05:39<12:46, 1.57s/it, loss=0.321, lr=1e-5]
Steps: 18%|ββ | 111/600 [05:39<12:46, 1.57s/it, loss=0.12, lr=1e-5]
Steps: 19%|ββ | 112/600 [05:41<12:34, 1.55s/it, loss=0.12, lr=1e-5]
Steps: 19%|ββ | 112/600 [05:41<12:34, 1.55s/it, loss=0.159, lr=1e-5]
Steps: 19%|ββ | 113/600 [05:42<12:36, 1.55s/it, loss=0.159, lr=1e-5]
Steps: 19%|ββ | 113/600 [05:42<12:36, 1.55s/it, loss=0.198, lr=1e-5]
Steps: 19%|ββ | 114/600 [05:44<13:11, 1.63s/it, loss=0.198, lr=1e-5]
Steps: 19%|ββ | 114/600 [05:44<13:11, 1.63s/it, loss=0.0345, lr=1e-5]
Steps: 19%|ββ | 115/600 [05:46<13:20, 1.65s/it, loss=0.0345, lr=1e-5]
Steps: 19%|ββ | 115/600 [05:46<13:20, 1.65s/it, loss=0.265, lr=1e-5]
Steps: 19%|ββ | 116/600 [05:47<12:34, 1.56s/it, loss=0.265, lr=1e-5]
Steps: 19%|ββ | 116/600 [05:47<12:34, 1.56s/it, loss=0.00317, lr=1e-5]
Steps: 20%|ββ | 117/600 [05:49<13:19, 1.66s/it, loss=0.00317, lr=1e-5]
Steps: 20%|ββ | 117/600 [05:49<13:19, 1.66s/it, loss=0.0196, lr=1e-5]
Steps: 20%|ββ | 118/600 [05:51<12:39, 1.58s/it, loss=0.0196, lr=1e-5]
Steps: 20%|ββ | 118/600 [05:51<12:39, 1.58s/it, loss=0.051, lr=1e-5]
Steps: 20%|ββ | 119/600 [05:52<12:45, 1.59s/it, loss=0.051, lr=1e-5]
Steps: 20%|ββ | 119/600 [05:52<12:45, 1.59s/it, loss=0.0172, lr=1e-5]
Steps: 20%|ββ | 120/600 [05:54<12:13, 1.53s/it, loss=0.0172, lr=1e-5]
Steps: 20%|ββ | 120/600 [05:54<12:13, 1.53s/it, loss=0.2, lr=1e-5]
Steps: 20%|ββ | 121/600 [05:54<10:22, 1.30s/it, loss=0.2, lr=1e-5]
Steps: 20%|ββ | 121/600 [05:54<10:22, 1.30s/it, loss=0.359, lr=1e-5]
Steps: 20%|ββ | 122/600 [05:57<13:30, 1.70s/it, loss=0.359, lr=1e-5]
Steps: 20%|ββ | 122/600 [05:57<13:30, 1.70s/it, loss=0.0328, lr=1e-5]
Steps: 20%|ββ | 123/600 [05:59<13:13, 1.66s/it, loss=0.0328, lr=1e-5]
Steps: 20%|ββ | 123/600 [05:59<13:13, 1.66s/it, loss=0.0208, lr=1e-5]
Steps: 21%|ββ | 124/600 [06:00<12:59, 1.64s/it, loss=0.0208, lr=1e-5]
Steps: 21%|ββ | 124/600 [06:00<12:59, 1.64s/it, loss=0.0853, lr=1e-5]
Steps: 21%|ββ | 125/600 [06:02<13:04, 1.65s/it, loss=0.0853, lr=1e-5]
Steps: 21%|ββ | 125/600 [06:02<13:04, 1.65s/it, loss=0.0879, lr=1e-5]
Steps: 21%|ββ | 126/600 [06:03<13:02, 1.65s/it, loss=0.0879, lr=1e-5]
Steps: 21%|ββ | 126/600 [06:03<13:02, 1.65s/it, loss=0.132, lr=1e-5]
Steps: 21%|ββ | 127/600 [06:05<12:39, 1.60s/it, loss=0.132, lr=1e-5]
Steps: 21%|ββ | 127/600 [06:05<12:39, 1.60s/it, loss=0.1, lr=1e-5]
Steps: 21%|βββ | 128/600 [06:06<12:23, 1.58s/it, loss=0.1, lr=1e-5]
Steps: 21%|βββ | 128/600 [06:06<12:23, 1.58s/it, loss=0.0353, lr=1e-5]
Steps: 22%|βββ | 129/600 [06:08<12:39, 1.61s/it, loss=0.0353, lr=1e-5]
Steps: 22%|βββ | 129/600 [06:08<12:39, 1.61s/it, loss=0.0891, lr=1e-5]
Steps: 22%|βββ | 130/600 [06:10<12:39, 1.62s/it, loss=0.0891, lr=1e-5]
Steps: 22%|βββ | 130/600 [06:10<12:39, 1.62s/it, loss=0.0567, lr=1e-5]
Steps: 22%|βββ | 131/600 [06:11<11:26, 1.46s/it, loss=0.0567, lr=1e-5]
Steps: 22%|βββ | 131/600 [06:11<11:26, 1.46s/it, loss=0.155, lr=1e-5]
Steps: 22%|βββ | 132/600 [06:12<09:46, 1.25s/it, loss=0.155, lr=1e-5]
Steps: 22%|βββ | 132/600 [06:12<09:46, 1.25s/it, loss=0.364, lr=1e-5]
Steps: 22%|βββ | 133/600 [06:14<11:56, 1.53s/it, loss=0.364, lr=1e-5]
Steps: 22%|βββ | 133/600 [06:14<11:56, 1.53s/it, loss=0.0939, lr=1e-5]
Steps: 22%|βββ | 134/600 [06:15<12:13, 1.57s/it, loss=0.0939, lr=1e-5]
Steps: 22%|βββ | 134/600 [06:15<12:13, 1.57s/it, loss=0.0813, lr=1e-5]
Steps: 22%|βββ | 135/600 [06:17<12:30, 1.61s/it, loss=0.0813, lr=1e-5]
Steps: 22%|βββ | 135/600 [06:17<12:30, 1.61s/it, loss=0.0717, lr=1e-5]
Steps: 23%|βββ | 136/600 [06:19<12:49, 1.66s/it, loss=0.0717, lr=1e-5]
Steps: 23%|βββ | 136/600 [06:19<12:49, 1.66s/it, loss=0.113, lr=1e-5]
Steps: 23%|βββ | 137/600 [06:21<13:05, 1.70s/it, loss=0.113, lr=1e-5]
Steps: 23%|βββ | 137/600 [06:21<13:05, 1.70s/it, loss=0.104, lr=1e-5]
Steps: 23%|βββ | 138/600 [06:22<13:00, 1.69s/it, loss=0.104, lr=1e-5]
Steps: 23%|βββ | 138/600 [06:22<13:00, 1.69s/it, loss=0.127, lr=1e-5]
Steps: 23%|βββ | 139/600 [06:24<12:45, 1.66s/it, loss=0.127, lr=1e-5]
Steps: 23%|βββ | 139/600 [06:24<12:45, 1.66s/it, loss=0.0207, lr=1e-5]
Steps: 23%|βββ | 140/600 [06:26<12:25, 1.62s/it, loss=0.0207, lr=1e-5]
Steps: 23%|βββ | 140/600 [06:26<12:25, 1.62s/it, loss=0.187, lr=1e-5]
Steps: 24%|βββ | 141/600 [06:27<11:48, 1.54s/it, loss=0.187, lr=1e-5]
Steps: 24%|βββ | 141/600 [06:27<11:48, 1.54s/it, loss=0.0773, lr=1e-5]
Steps: 24%|βββ | 142/600 [06:28<10:48, 1.42s/it, loss=0.0773, lr=1e-5]
Steps: 24%|βββ | 142/600 [06:28<10:48, 1.42s/it, loss=0.104, lr=1e-5]
Steps: 24%|βββ | 143/600 [06:29<09:16, 1.22s/it, loss=0.104, lr=1e-5]
Steps: 24%|βββ | 143/600 [06:29<09:16, 1.22s/it, loss=0.112, lr=1e-5]
Steps: 24%|βββ | 144/600 [06:31<12:05, 1.59s/it, loss=0.112, lr=1e-5]
Steps: 24%|βββ | 144/600 [06:31<12:05, 1.59s/it, loss=0.0305, lr=1e-5]
Steps: 24%|βββ | 145/600 [06:33<12:33, 1.66s/it, loss=0.0305, lr=1e-5]
Steps: 24%|βββ | 145/600 [06:33<12:33, 1.66s/it, loss=0.0494, lr=1e-5]
Steps: 24%|βββ | 146/600 [06:34<12:05, 1.60s/it, loss=0.0494, lr=1e-5]
Steps: 24%|βββ | 146/600 [06:34<12:05, 1.60s/it, loss=0.0274, lr=1e-5]
Steps: 24%|βββ | 147/600 [06:36<12:04, 1.60s/it, loss=0.0274, lr=1e-5]
Steps: 24%|βββ | 147/600 [06:36<12:04, 1.60s/it, loss=0.148, lr=1e-5]
Steps: 25%|βββ | 148/600 [06:38<11:53, 1.58s/it, loss=0.148, lr=1e-5]
Steps: 25%|βββ | 148/600 [06:38<11:53, 1.58s/it, loss=0.0483, lr=1e-5]
Steps: 25%|βββ | 149/600 [06:39<12:09, 1.62s/it, loss=0.0483, lr=1e-5]
Steps: 25%|βββ | 149/600 [06:39<12:09, 1.62s/it, loss=0.0314, lr=1e-5]
Steps: 25%|βββ | 150/600 [06:41<12:05, 1.61s/it, loss=0.0314, lr=1e-5]
Steps: 25%|βββ | 150/600 [06:41<12:05, 1.61s/it, loss=0.3, lr=1e-5]
Steps: 25%|βββ | 151/600 [06:42<11:53, 1.59s/it, loss=0.3, lr=1e-5]
Steps: 25%|βββ | 151/600 [06:42<11:53, 1.59s/it, loss=0.215, lr=1e-5]
Steps: 25%|βββ | 152/600 [06:44<11:18, 1.51s/it, loss=0.215, lr=1e-5]
Steps: 25%|βββ | 152/600 [06:44<11:18, 1.51s/it, loss=0.103, lr=1e-5]
Steps: 26%|βββ | 153/600 [06:45<10:50, 1.45s/it, loss=0.103, lr=1e-5]
Steps: 26%|βββ | 153/600 [06:45<10:50, 1.45s/it, loss=0.172, lr=1e-5]
Steps: 26%|βββ | 154/600 [06:46<09:15, 1.24s/it, loss=0.172, lr=1e-5]
Steps: 26%|βββ | 154/600 [06:46<09:15, 1.24s/it, loss=0.00458, lr=1e-5]
Steps: 26%|βββ | 155/600 [06:49<12:21, 1.67s/it, loss=0.00458, lr=1e-5]
Steps: 26%|βββ | 155/600 [06:49<12:21, 1.67s/it, loss=0.202, lr=1e-5]
Steps: 26%|βββ | 156/600 [06:50<11:47, 1.59s/it, loss=0.202, lr=1e-5]
Steps: 26%|βββ | 156/600 [06:50<11:47, 1.59s/it, loss=0.187, lr=1e-5]
Steps: 26%|βββ | 157/600 [06:51<11:24, 1.55s/it, loss=0.187, lr=1e-5]
Steps: 26%|βββ | 157/600 [06:51<11:24, 1.55s/it, loss=0.0753, lr=1e-5]
Steps: 26%|βββ | 158/600 [06:53<11:15, 1.53s/it, loss=0.0753, lr=1e-5]
Steps: 26%|βββ | 158/600 [06:53<11:15, 1.53s/it, loss=0.114, lr=1e-5]
Steps: 26%|βββ | 159/600 [06:55<11:54, 1.62s/it, loss=0.114, lr=1e-5]
Steps: 26%|βββ | 159/600 [06:55<11:54, 1.62s/it, loss=0.0804, lr=1e-5]
Steps: 27%|βββ | 160/600 [06:56<12:08, 1.66s/it, loss=0.0804, lr=1e-5]
Steps: 27%|βββ | 160/600 [06:56<12:08, 1.66s/it, loss=0.134, lr=1e-5]
Steps: 27%|βββ | 161/600 [06:58<11:30, 1.57s/it, loss=0.134, lr=1e-5]
Steps: 27%|βββ | 161/600 [06:58<11:30, 1.57s/it, loss=0.0393, lr=1e-5]
Steps: 27%|βββ | 162/600 [06:59<11:17, 1.55s/it, loss=0.0393, lr=1e-5]
Steps: 27%|βββ | 162/600 [06:59<11:17, 1.55s/it, loss=0.0587, lr=1e-5]
Steps: 27%|βββ | 163/600 [07:01<11:14, 1.54s/it, loss=0.0587, lr=1e-5]
Steps: 27%|βββ | 163/600 [07:01<11:14, 1.54s/it, loss=0.0094, lr=1e-5]
Steps: 27%|βββ | 164/600 [07:02<10:33, 1.45s/it, loss=0.0094, lr=1e-5]
Steps: 27%|βββ | 164/600 [07:02<10:33, 1.45s/it, loss=0.116, lr=1e-5]
Steps: 28%|βββ | 165/600 [07:03<09:01, 1.25s/it, loss=0.116, lr=1e-5]
Steps: 28%|βββ | 165/600 [07:03<09:01, 1.25s/it, loss=0.322, lr=1e-5]
Steps: 28%|βββ | 166/600 [07:05<10:09, 1.40s/it, loss=0.322, lr=1e-5]
Steps: 28%|βββ | 166/600 [07:05<10:09, 1.40s/it, loss=0.126, lr=1e-5]
Steps: 28%|βββ | 167/600 [07:06<10:40, 1.48s/it, loss=0.126, lr=1e-5]
Steps: 28%|βββ | 167/600 [07:06<10:40, 1.48s/it, loss=0.0783, lr=1e-5]
Steps: 28%|βββ | 168/600 [07:08<11:07, 1.54s/it, loss=0.0783, lr=1e-5]
Steps: 28%|βββ | 168/600 [07:08<11:07, 1.54s/it, loss=0.0381, lr=1e-5]
Steps: 28%|βββ | 169/600 [07:10<11:48, 1.64s/it, loss=0.0381, lr=1e-5]
Steps: 28%|βββ | 169/600 [07:10<11:48, 1.64s/it, loss=0.189, lr=1e-5]
Steps: 28%|βββ | 170/600 [07:12<12:01, 1.68s/it, loss=0.189, lr=1e-5]
Steps: 28%|βββ | 170/600 [07:12<12:01, 1.68s/it, loss=0.141, lr=1e-5]
Steps: 28%|βββ | 171/600 [07:13<11:51, 1.66s/it, loss=0.141, lr=1e-5]
Steps: 28%|βββ | 171/600 [07:13<11:51, 1.66s/it, loss=0.217, lr=1e-5]
Steps: 29%|βββ | 172/600 [07:15<11:36, 1.63s/it, loss=0.217, lr=1e-5]
Steps: 29%|βββ | 172/600 [07:15<11:36, 1.63s/it, loss=0.196, lr=1e-5]
Steps: 29%|βββ | 173/600 [07:16<11:23, 1.60s/it, loss=0.196, lr=1e-5]
Steps: 29%|βββ | 173/600 [07:16<11:23, 1.60s/it, loss=0.13, lr=1e-5]
Steps: 29%|βββ | 174/600 [07:18<11:13, 1.58s/it, loss=0.13, lr=1e-5]
Steps: 29%|βββ | 174/600 [07:18<11:13, 1.58s/it, loss=0.0101, lr=1e-5]
Steps: 29%|βββ | 175/600 [07:19<10:34, 1.49s/it, loss=0.0101, lr=1e-5]
Steps: 29%|βββ | 175/600 [07:19<10:34, 1.49s/it, loss=0.18, lr=1e-5]
Steps: 29%|βββ | 176/600 [07:20<08:58, 1.27s/it, loss=0.18, lr=1e-5]
Steps: 29%|βββ | 176/600 [07:20<08:58, 1.27s/it, loss=0.0225, lr=1e-5]
Steps: 30%|βββ | 177/600 [07:23<11:59, 1.70s/it, loss=0.0225, lr=1e-5]
Steps: 30%|βββ | 177/600 [07:23<11:59, 1.70s/it, loss=0.0305, lr=1e-5]
Steps: 30%|βββ | 178/600 [07:24<11:53, 1.69s/it, loss=0.0305, lr=1e-5]
Steps: 30%|βββ | 178/600 [07:24<11:53, 1.69s/it, loss=0.0418, lr=1e-5]
Steps: 30%|βββ | 179/600 [07:26<11:14, 1.60s/it, loss=0.0418, lr=1e-5]
Steps: 30%|βββ | 179/600 [07:26<11:14, 1.60s/it, loss=0.0119, lr=1e-5]
Steps: 30%|βββ | 180/600 [07:27<11:14, 1.60s/it, loss=0.0119, lr=1e-5]
Steps: 30%|βββ | 180/600 [07:27<11:14, 1.60s/it, loss=0.159, lr=1e-5]
Steps: 30%|βββ | 181/600 [07:29<11:07, 1.59s/it, loss=0.159, lr=1e-5]
Steps: 30%|βββ | 181/600 [07:29<11:07, 1.59s/it, loss=0.03, lr=1e-5]
Steps: 30%|βββ | 182/600 [07:30<11:03, 1.59s/it, loss=0.03, lr=1e-5]
Steps: 30%|βββ | 182/600 [07:30<11:03, 1.59s/it, loss=0.0694, lr=1e-5]
Steps: 30%|βββ | 183/600 [07:32<10:46, 1.55s/it, loss=0.0694, lr=1e-5]
Steps: 30%|βββ | 183/600 [07:32<10:46, 1.55s/it, loss=0.0926, lr=1e-5]
Steps: 31%|βββ | 184/600 [07:33<10:35, 1.53s/it, loss=0.0926, lr=1e-5]
Steps: 31%|βββ | 184/600 [07:33<10:35, 1.53s/it, loss=0.192, lr=1e-5]
Steps: 31%|βββ | 185/600 [07:35<10:42, 1.55s/it, loss=0.192, lr=1e-5]
Steps: 31%|βββ | 185/600 [07:35<10:42, 1.55s/it, loss=0.00984, lr=1e-5]
Steps: 31%|βββ | 186/600 [07:36<10:02, 1.46s/it, loss=0.00984, lr=1e-5]
Steps: 31%|βββ | 186/600 [07:36<10:02, 1.46s/it, loss=0.0847, lr=1e-5]
Steps: 31%|βββ | 187/600 [07:37<08:35, 1.25s/it, loss=0.0847, lr=1e-5]
Steps: 31%|βββ | 187/600 [07:37<08:35, 1.25s/it, loss=0.0335, lr=1e-5]
Steps: 31%|ββββ | 188/600 [07:40<11:19, 1.65s/it, loss=0.0335, lr=1e-5]
Steps: 31%|ββββ | 188/600 [07:40<11:19, 1.65s/it, loss=0.0577, lr=1e-5]
Steps: 32%|ββββ | 189/600 [07:41<11:03, 1.62s/it, loss=0.0577, lr=1e-5]
Steps: 32%|ββββ | 189/600 [07:41<11:03, 1.62s/it, loss=0.117, lr=1e-5]
Steps: 32%|ββββ | 190/600 [07:43<11:17, 1.65s/it, loss=0.117, lr=1e-5]
Steps: 32%|ββββ | 190/600 [07:43<11:17, 1.65s/it, loss=0.193, lr=1e-5]
Steps: 32%|ββββ | 191/600 [07:44<10:59, 1.61s/it, loss=0.193, lr=1e-5]
Steps: 32%|ββββ | 191/600 [07:44<10:59, 1.61s/it, loss=0.199, lr=1e-5]
Steps: 32%|ββββ | 192/600 [07:46<10:17, 1.51s/it, loss=0.199, lr=1e-5]
Steps: 32%|ββββ | 192/600 [07:46<10:17, 1.51s/it, loss=0.0973, lr=1e-5]
Steps: 32%|ββββ | 193/600 [07:47<10:52, 1.60s/it, loss=0.0973, lr=1e-5]
Steps: 32%|ββββ | 193/600 [07:47<10:52, 1.60s/it, loss=0.124, lr=1e-5]
Steps: 32%|ββββ | 194/600 [07:49<11:00, 1.63s/it, loss=0.124, lr=1e-5]
Steps: 32%|ββββ | 194/600 [07:49<11:00, 1.63s/it, loss=0.125, lr=1e-5]
Steps: 32%|ββββ | 195/600 [07:51<10:41, 1.58s/it, loss=0.125, lr=1e-5]
Steps: 32%|ββββ | 195/600 [07:51<10:41, 1.58s/it, loss=0.00813, lr=1e-5]
Steps: 33%|ββββ | 196/600 [07:52<10:15, 1.52s/it, loss=0.00813, lr=1e-5]
Steps: 33%|ββββ | 196/600 [07:52<10:15, 1.52s/it, loss=0.0211, lr=1e-5]
Steps: 33%|ββββ | 197/600 [07:53<09:46, 1.46s/it, loss=0.0211, lr=1e-5]
Steps: 33%|ββββ | 197/600 [07:53<09:46, 1.46s/it, loss=0.0378, lr=1e-5]
Steps: 33%|ββββ | 198/600 [07:54<08:19, 1.24s/it, loss=0.0378, lr=1e-5]
Steps: 33%|ββββ | 198/600 [07:54<08:19, 1.24s/it, loss=0.135, lr=1e-5]
Steps: 33%|ββββ | 199/600 [07:56<09:51, 1.48s/it, loss=0.135, lr=1e-5]
Steps: 33%|ββββ | 199/600 [07:56<09:51, 1.48s/it, loss=0.0284, lr=1e-5]
Steps: 33%|ββββ | 200/600 [07:58<09:50, 1.48s/it, loss=0.0284, lr=1e-5]
Steps: 33%|ββββ | 200/600 [07:58<09:50, 1.48s/it, loss=0.142, lr=1e-5]
Steps: 34%|ββββ | 201/600 [07:59<10:17, 1.55s/it, loss=0.142, lr=1e-5]
Steps: 34%|ββββ | 201/600 [07:59<10:17, 1.55s/it, loss=0.128, lr=1e-5]
Steps: 34%|ββββ | 202/600 [08:01<10:50, 1.63s/it, loss=0.128, lr=1e-5]
Steps: 34%|ββββ | 202/600 [08:01<10:50, 1.63s/it, loss=0.0099, lr=1e-5]
Steps: 34%|ββββ | 203/600 [08:03<11:51, 1.79s/it, loss=0.0099, lr=1e-5]
Steps: 34%|ββββ | 203/600 [08:03<11:51, 1.79s/it, loss=0.156, lr=1e-5]
Steps: 34%|ββββ | 204/600 [08:05<11:45, 1.78s/it, loss=0.156, lr=1e-5]
Steps: 34%|ββββ | 204/600 [08:05<11:45, 1.78s/it, loss=0.0103, lr=1e-5]
Steps: 34%|ββββ | 205/600 [08:06<10:53, 1.65s/it, loss=0.0103, lr=1e-5]
Steps: 34%|ββββ | 205/600 [08:06<10:53, 1.65s/it, loss=0.0948, lr=1e-5]
Steps: 34%|ββββ | 206/600 [08:08<10:52, 1.66s/it, loss=0.0948, lr=1e-5]
Steps: 34%|ββββ | 206/600 [08:08<10:52, 1.66s/it, loss=0.126, lr=1e-5]
Steps: 34%|ββββ | 207/600 [08:10<10:50, 1.66s/it, loss=0.126, lr=1e-5]
Steps: 34%|ββββ | 207/600 [08:10<10:50, 1.66s/it, loss=0.129, lr=1e-5]
Steps: 35%|ββββ | 208/600 [08:11<10:02, 1.54s/it, loss=0.129, lr=1e-5]
Steps: 35%|ββββ | 208/600 [08:11<10:02, 1.54s/it, loss=0.0311, lr=1e-5]
Steps: 35%|ββββ | 209/600 [08:12<08:30, 1.30s/it, loss=0.0311, lr=1e-5]
Steps: 35%|ββββ | 209/600 [08:12<08:30, 1.30s/it, loss=0.0226, lr=1e-5]
Steps: 35%|ββββ | 210/600 [08:14<10:36, 1.63s/it, loss=0.0226, lr=1e-5]
Steps: 35%|ββββ | 210/600 [08:14<10:36, 1.63s/it, loss=0.102, lr=1e-5]
Steps: 35%|ββββ | 211/600 [08:16<10:15, 1.58s/it, loss=0.102, lr=1e-5]
Steps: 35%|ββββ | 211/600 [08:16<10:15, 1.58s/it, loss=0.0853, lr=1e-5]
Steps: 35%|ββββ | 212/600 [08:17<10:07, 1.57s/it, loss=0.0853, lr=1e-5]
Steps: 35%|ββββ | 212/600 [08:17<10:07, 1.57s/it, loss=0.0156, lr=1e-5]
Steps: 36%|ββββ | 213/600 [08:19<10:39, 1.65s/it, loss=0.0156, lr=1e-5]
Steps: 36%|ββββ | 213/600 [08:19<10:39, 1.65s/it, loss=0.00713, lr=1e-5]
Steps: 36%|ββββ | 214/600 [08:20<10:08, 1.58s/it, loss=0.00713, lr=1e-5]
Steps: 36%|ββββ | 214/600 [08:20<10:08, 1.58s/it, loss=0.00706, lr=1e-5]
Steps: 36%|ββββ | 215/600 [08:22<09:57, 1.55s/it, loss=0.00706, lr=1e-5]
Steps: 36%|ββββ | 215/600 [08:22<09:57, 1.55s/it, loss=0.156, lr=1e-5]
Steps: 36%|ββββ | 216/600 [08:23<09:59, 1.56s/it, loss=0.156, lr=1e-5]
Steps: 36%|ββββ | 216/600 [08:23<09:59, 1.56s/it, loss=0.131, lr=1e-5]
Steps: 36%|ββββ | 217/600 [08:25<10:39, 1.67s/it, loss=0.131, lr=1e-5]
Steps: 36%|ββββ | 217/600 [08:25<10:39, 1.67s/it, loss=0.0997, lr=1e-5]
Steps: 36%|ββββ | 218/600 [08:27<10:12, 1.60s/it, loss=0.0997, lr=1e-5]
Steps: 36%|ββββ | 218/600 [08:27<10:12, 1.60s/it, loss=0.132, lr=1e-5]
Steps: 36%|ββββ | 219/600 [08:28<09:34, 1.51s/it, loss=0.132, lr=1e-5]
Steps: 36%|ββββ | 219/600 [08:28<09:34, 1.51s/it, loss=0.0638, lr=1e-5]
Steps: 37%|ββββ | 220/600 [08:29<08:06, 1.28s/it, loss=0.0638, lr=1e-5]
Steps: 37%|ββββ | 220/600 [08:29<08:06, 1.28s/it, loss=0.0301, lr=1e-5]
Steps: 37%|ββββ | 221/600 [08:31<09:28, 1.50s/it, loss=0.0301, lr=1e-5]
Steps: 37%|ββββ | 221/600 [08:31<09:28, 1.50s/it, loss=0.0974, lr=1e-5]
Steps: 37%|ββββ | 222/600 [08:32<09:46, 1.55s/it, loss=0.0974, lr=1e-5]
Steps: 37%|ββββ | 222/600 [08:32<09:46, 1.55s/it, loss=0.0812, lr=1e-5]
Steps: 37%|ββββ | 223/600 [08:34<09:57, 1.59s/it, loss=0.0812, lr=1e-5]
Steps: 37%|ββββ | 223/600 [08:34<09:57, 1.59s/it, loss=0.261, lr=1e-5]
Steps: 37%|ββββ | 224/600 [08:36<09:55, 1.58s/it, loss=0.261, lr=1e-5]
Steps: 37%|ββββ | 224/600 [08:36<09:55, 1.58s/it, loss=0.0112, lr=1e-5]
Steps: 38%|ββββ | 225/600 [08:37<10:09, 1.63s/it, loss=0.0112, lr=1e-5]
Steps: 38%|ββββ | 225/600 [08:37<10:09, 1.63s/it, loss=0.129, lr=1e-5]
Steps: 38%|ββββ | 226/600 [08:39<10:13, 1.64s/it, loss=0.129, lr=1e-5]
Steps: 38%|ββββ | 226/600 [08:39<10:13, 1.64s/it, loss=0.0926, lr=1e-5]
Steps: 38%|ββββ | 227/600 [08:41<10:00, 1.61s/it, loss=0.0926, lr=1e-5]
Steps: 38%|ββββ | 227/600 [08:41<10:00, 1.61s/it, loss=0.169, lr=1e-5]
Steps: 38%|ββββ | 228/600 [08:42<10:04, 1.62s/it, loss=0.169, lr=1e-5]
Steps: 38%|ββββ | 228/600 [08:42<10:04, 1.62s/it, loss=0.304, lr=1e-5]
Steps: 38%|ββββ | 229/600 [08:44<09:44, 1.58s/it, loss=0.304, lr=1e-5]
Steps: 38%|ββββ | 229/600 [08:44<09:44, 1.58s/it, loss=0.0854, lr=1e-5]
Steps: 38%|ββββ | 230/600 [08:45<09:22, 1.52s/it, loss=0.0854, lr=1e-5]
Steps: 38%|ββββ | 230/600 [08:45<09:22, 1.52s/it, loss=0.0256, lr=1e-5]
Steps: 38%|ββββ | 231/600 [08:46<07:55, 1.29s/it, loss=0.0256, lr=1e-5]
Steps: 38%|ββββ | 231/600 [08:46<07:55, 1.29s/it, loss=0.0236, lr=1e-5]
Steps: 39%|ββββ | 232/600 [08:48<10:14, 1.67s/it, loss=0.0236, lr=1e-5]
Steps: 39%|ββββ | 232/600 [08:48<10:14, 1.67s/it, loss=0.0653, lr=1e-5]
Steps: 39%|ββββ | 233/600 [08:50<10:02, 1.64s/it, loss=0.0653, lr=1e-5]
Steps: 39%|ββββ | 233/600 [08:50<10:02, 1.64s/it, loss=0.133, lr=1e-5]
Steps: 39%|ββββ | 234/600 [08:52<09:41, 1.59s/it, loss=0.133, lr=1e-5]
Steps: 39%|ββββ | 234/600 [08:52<09:41, 1.59s/it, loss=0.0539, lr=1e-5]
Steps: 39%|ββββ | 235/600 [08:53<09:58, 1.64s/it, loss=0.0539, lr=1e-5]
Steps: 39%|ββββ | 235/600 [08:53<09:58, 1.64s/it, loss=0.095, lr=1e-5]
Steps: 39%|ββββ | 236/600 [08:55<09:41, 1.60s/it, loss=0.095, lr=1e-5]
Steps: 39%|ββββ | 236/600 [08:55<09:41, 1.60s/it, loss=0.011, lr=1e-5]
Steps: 40%|ββββ | 237/600 [08:56<09:22, 1.55s/it, loss=0.011, lr=1e-5]
Steps: 40%|ββββ | 237/600 [08:56<09:22, 1.55s/it, loss=0.0569, lr=1e-5]
Steps: 40%|ββββ | 238/600 [08:58<09:04, 1.50s/it, loss=0.0569, lr=1e-5]
Steps: 40%|ββββ | 238/600 [08:58<09:04, 1.50s/it, loss=0.0605, lr=1e-5]
Steps: 40%|ββββ | 239/600 [08:59<09:41, 1.61s/it, loss=0.0605, lr=1e-5]
Steps: 40%|ββββ | 239/600 [08:59<09:41, 1.61s/it, loss=0.0451, lr=1e-5]
Steps: 40%|ββββ | 240/600 [09:01<09:30, 1.59s/it, loss=0.0451, lr=1e-5]
Steps: 40%|ββββ | 240/600 [09:01<09:30, 1.59s/it, loss=0.138, lr=1e-5]
Steps: 40%|ββββ | 241/600 [09:02<08:55, 1.49s/it, loss=0.138, lr=1e-5]
Steps: 40%|ββββ | 241/600 [09:02<08:55, 1.49s/it, loss=0.0685, lr=1e-5]
Steps: 40%|ββββ | 242/600 [09:03<07:35, 1.27s/it, loss=0.0685, lr=1e-5]
Steps: 40%|ββββ | 242/600 [09:03<07:35, 1.27s/it, loss=0.011, lr=1e-5]
Steps: 40%|ββββ | 243/600 [09:05<09:12, 1.55s/it, loss=0.011, lr=1e-5]
Steps: 40%|ββββ | 243/600 [09:05<09:12, 1.55s/it, loss=0.203, lr=1e-5]
Steps: 41%|ββββ | 244/600 [09:07<09:19, 1.57s/it, loss=0.203, lr=1e-5]
Steps: 41%|ββββ | 244/600 [09:07<09:19, 1.57s/it, loss=0.0117, lr=1e-5]
Steps: 41%|ββββ | 245/600 [09:08<09:08, 1.55s/it, loss=0.0117, lr=1e-5]
Steps: 41%|ββββ | 245/600 [09:08<09:08, 1.55s/it, loss=0.142, lr=1e-5]
Steps: 41%|ββββ | 246/600 [09:10<09:11, 1.56s/it, loss=0.142, lr=1e-5]
Steps: 41%|ββββ | 246/600 [09:10<09:11, 1.56s/it, loss=0.168, lr=1e-5]
Steps: 41%|ββββ | 247/600 [09:11<09:08, 1.55s/it, loss=0.168, lr=1e-5]
Steps: 41%|ββββ | 247/600 [09:11<09:08, 1.55s/it, loss=0.126, lr=1e-5]
Steps: 41%|βββββ | 248/600 [09:13<09:21, 1.59s/it, loss=0.126, lr=1e-5]
Steps: 41%|βββββ | 248/600 [09:13<09:21, 1.59s/it, loss=0.276, lr=1e-5]
Steps: 42%|βββββ | 249/600 [09:15<09:20, 1.60s/it, loss=0.276, lr=1e-5]
Steps: 42%|βββββ | 249/600 [09:15<09:20, 1.60s/it, loss=0.128, lr=1e-5]
Steps: 42%|βββββ | 250/600 [09:16<09:14, 1.59s/it, loss=0.128, lr=1e-5]
Steps: 42%|βββββ | 250/600 [09:16<09:14, 1.59s/it, loss=0.132, lr=1e-5]
Steps: 42%|βββββ | 251/600 [09:18<09:20, 1.61s/it, loss=0.132, lr=1e-5]
Steps: 42%|βββββ | 251/600 [09:18<09:20, 1.61s/it, loss=0.2, lr=1e-5]
Steps: 42%|βββββ | 252/600 [09:19<09:05, 1.57s/it, loss=0.2, lr=1e-5]
Steps: 42%|βββββ | 252/600 [09:19<09:05, 1.57s/it, loss=0.189, lr=1e-5]
Steps: 42%|βββββ | 253/600 [09:20<07:39, 1.32s/it, loss=0.189, lr=1e-5]
Steps: 42%|βββββ | 253/600 [09:20<07:39, 1.32s/it, loss=0.0957, lr=1e-5]
Steps: 42%|βββββ | 254/600 [09:23<09:21, 1.62s/it, loss=0.0957, lr=1e-5]
Steps: 42%|βββββ | 254/600 [09:23<09:21, 1.62s/it, loss=0.161, lr=1e-5]
Steps: 42%|βββββ | 255/600 [09:24<08:51, 1.54s/it, loss=0.161, lr=1e-5]
Steps: 42%|βββββ | 255/600 [09:24<08:51, 1.54s/it, loss=0.0807, lr=1e-5]
Steps: 43%|βββββ | 256/600 [09:26<09:01, 1.57s/it, loss=0.0807, lr=1e-5]
Steps: 43%|βββββ | 256/600 [09:26<09:01, 1.57s/it, loss=0.15, lr=1e-5]
Steps: 43%|βββββ | 257/600 [09:27<09:05, 1.59s/it, loss=0.15, lr=1e-5]
Steps: 43%|βββββ | 257/600 [09:27<09:05, 1.59s/it, loss=0.141, lr=1e-5]
Steps: 43%|βββββ | 258/600 [09:29<08:42, 1.53s/it, loss=0.141, lr=1e-5]
Steps: 43%|βββββ | 258/600 [09:29<08:42, 1.53s/it, loss=0.165, lr=1e-5]
Steps: 43%|βββββ | 259/600 [09:30<08:29, 1.49s/it, loss=0.165, lr=1e-5]
Steps: 43%|βββββ | 259/600 [09:30<08:29, 1.49s/it, loss=0.0144, lr=1e-5]
Steps: 43%|βββββ | 260/600 [09:32<08:51, 1.56s/it, loss=0.0144, lr=1e-5]
Steps: 43%|βββββ | 260/600 [09:32<08:51, 1.56s/it, loss=0.222, lr=1e-5]
Steps: 44%|βββββ | 261/600 [09:33<09:04, 1.61s/it, loss=0.222, lr=1e-5]
Steps: 44%|βββββ | 261/600 [09:33<09:04, 1.61s/it, loss=0.0995, lr=1e-5]
Steps: 44%|βββββ | 262/600 [09:35<09:13, 1.64s/it, loss=0.0995, lr=1e-5]
Steps: 44%|βββββ | 262/600 [09:35<09:13, 1.64s/it, loss=0.0815, lr=1e-5]
Steps: 44%|βββββ | 263/600 [09:36<08:44, 1.56s/it, loss=0.0815, lr=1e-5]
Steps: 44%|βββββ | 263/600 [09:36<08:44, 1.56s/it, loss=0.0819, lr=1e-5]
Steps: 44%|βββββ | 264/600 [09:37<07:22, 1.32s/it, loss=0.0819, lr=1e-5]
Steps: 44%|βββββ | 264/600 [09:37<07:22, 1.32s/it, loss=0.353, lr=1e-5]
Steps: 44%|βββββ | 265/600 [09:40<09:29, 1.70s/it, loss=0.353, lr=1e-5]
Steps: 44%|βββββ | 265/600 [09:40<09:29, 1.70s/it, loss=0.0303, lr=1e-5]
Steps: 44%|βββββ | 266/600 [09:42<09:44, 1.75s/it, loss=0.0303, lr=1e-5]
Steps: 44%|βββββ | 266/600 [09:42<09:44, 1.75s/it, loss=0.143, lr=1e-5]
Steps: 44%|βββββ | 267/600 [09:43<09:38, 1.74s/it, loss=0.143, lr=1e-5]
Steps: 44%|βββββ | 267/600 [09:43<09:38, 1.74s/it, loss=0.191, lr=1e-5]
Steps: 45%|βββββ | 268/600 [09:45<09:22, 1.70s/it, loss=0.191, lr=1e-5]
Steps: 45%|βββββ | 268/600 [09:45<09:22, 1.70s/it, loss=0.189, lr=1e-5]
Steps: 45%|βββββ | 269/600 [09:46<08:46, 1.59s/it, loss=0.189, lr=1e-5]
Steps: 45%|βββββ | 269/600 [09:46<08:46, 1.59s/it, loss=0.162, lr=1e-5]
Steps: 45%|βββββ | 270/600 [09:48<08:41, 1.58s/it, loss=0.162, lr=1e-5]
Steps: 45%|βββββ | 270/600 [09:48<08:41, 1.58s/it, loss=0.201, lr=1e-5]
Steps: 45%|βββββ | 271/600 [09:49<08:11, 1.49s/it, loss=0.201, lr=1e-5]
Steps: 45%|βββββ | 271/600 [09:49<08:11, 1.49s/it, loss=0.25, lr=1e-5]
Steps: 45%|βββββ | 272/600 [09:51<08:25, 1.54s/it, loss=0.25, lr=1e-5]
Steps: 45%|βββββ | 272/600 [09:51<08:25, 1.54s/it, loss=0.0321, lr=1e-5]
Steps: 46%|βββββ | 273/600 [09:52<08:25, 1.55s/it, loss=0.0321, lr=1e-5]
Steps: 46%|βββββ | 273/600 [09:52<08:25, 1.55s/it, loss=0.0212, lr=1e-5]
Steps: 46%|βββββ | 274/600 [09:54<08:09, 1.50s/it, loss=0.0212, lr=1e-5]
Steps: 46%|βββββ | 274/600 [09:54<08:09, 1.50s/it, loss=0.15, lr=1e-5]
Steps: 46%|βββββ | 275/600 [09:55<06:56, 1.28s/it, loss=0.15, lr=1e-5]
Steps: 46%|βββββ | 275/600 [09:55<06:56, 1.28s/it, loss=0.0136, lr=1e-5]
Steps: 46%|βββββ | 276/600 [09:57<08:36, 1.59s/it, loss=0.0136, lr=1e-5]
Steps: 46%|βββββ | 276/600 [09:57<08:36, 1.59s/it, loss=0.197, lr=1e-5]
Steps: 46%|βββββ | 277/600 [09:59<08:45, 1.63s/it, loss=0.197, lr=1e-5]
Steps: 46%|βββββ | 277/600 [09:59<08:45, 1.63s/it, loss=0.0146, lr=1e-5]
Steps: 46%|βββββ | 278/600 [10:01<09:17, 1.73s/it, loss=0.0146, lr=1e-5]
Steps: 46%|βββββ | 278/600 [10:01<09:17, 1.73s/it, loss=0.22, lr=1e-5]
Steps: 46%|βββββ | 279/600 [10:02<09:09, 1.71s/it, loss=0.22, lr=1e-5]
Steps: 46%|βββββ | 279/600 [10:02<09:09, 1.71s/it, loss=0.315, lr=1e-5]
Steps: 47%|βββββ | 280/600 [10:04<08:47, 1.65s/it, loss=0.315, lr=1e-5]
Steps: 47%|βββββ | 280/600 [10:04<08:47, 1.65s/it, loss=0.0259, lr=1e-5]
Steps: 47%|βββββ | 281/600 [10:05<08:24, 1.58s/it, loss=0.0259, lr=1e-5]
Steps: 47%|βββββ | 281/600 [10:05<08:24, 1.58s/it, loss=0.0652, lr=1e-5]
Steps: 47%|βββββ | 282/600 [10:07<08:34, 1.62s/it, loss=0.0652, lr=1e-5]
Steps: 47%|βββββ | 282/600 [10:07<08:34, 1.62s/it, loss=0.164, lr=1e-5]
Steps: 47%|βββββ | 283/600 [10:08<08:21, 1.58s/it, loss=0.164, lr=1e-5]
Steps: 47%|βββββ | 283/600 [10:08<08:21, 1.58s/it, loss=0.141, lr=1e-5]
Steps: 47%|βββββ | 284/600 [10:10<08:35, 1.63s/it, loss=0.141, lr=1e-5]
Steps: 47%|βββββ | 284/600 [10:10<08:35, 1.63s/it, loss=0.133, lr=1e-5]
Steps: 48%|βββββ | 285/600 [10:11<08:04, 1.54s/it, loss=0.133, lr=1e-5]
Steps: 48%|βββββ | 285/600 [10:11<08:04, 1.54s/it, loss=0.178, lr=1e-5]
Steps: 48%|βββββ | 286/600 [10:12<06:52, 1.31s/it, loss=0.178, lr=1e-5]
Steps: 48%|βββββ | 286/600 [10:12<06:52, 1.31s/it, loss=0.133, lr=1e-5]
Steps: 48%|βββββ | 287/600 [10:15<08:27, 1.62s/it, loss=0.133, lr=1e-5]
Steps: 48%|βββββ | 287/600 [10:15<08:27, 1.62s/it, loss=0.0267, lr=1e-5]
Steps: 48%|βββββ | 288/600 [10:16<08:28, 1.63s/it, loss=0.0267, lr=1e-5]
Steps: 48%|βββββ | 288/600 [10:16<08:28, 1.63s/it, loss=0.205, lr=1e-5]
Steps: 48%|βββββ | 289/600 [10:18<08:37, 1.66s/it, loss=0.205, lr=1e-5]
Steps: 48%|βββββ | 289/600 [10:18<08:37, 1.66s/it, loss=0.0263, lr=1e-5]
Steps: 48%|βββββ | 290/600 [10:20<08:37, 1.67s/it, loss=0.0263, lr=1e-5]
Steps: 48%|βββββ | 290/600 [10:20<08:37, 1.67s/it, loss=0.027, lr=1e-5]
Steps: 48%|βββββ | 291/600 [10:21<08:06, 1.58s/it, loss=0.027, lr=1e-5]
Steps: 48%|βββββ | 291/600 [10:21<08:06, 1.58s/it, loss=0.191, lr=1e-5]
Steps: 49%|βββββ | 292/600 [10:22<07:51, 1.53s/it, loss=0.191, lr=1e-5]
Steps: 49%|βββββ | 292/600 [10:22<07:51, 1.53s/it, loss=0.0223, lr=1e-5]
Steps: 49%|βββββ | 293/600 [10:24<08:25, 1.65s/it, loss=0.0223, lr=1e-5]
Steps: 49%|βββββ | 293/600 [10:24<08:25, 1.65s/it, loss=0.0584, lr=1e-5]
Steps: 49%|βββββ | 294/600 [10:26<08:13, 1.61s/it, loss=0.0584, lr=1e-5]
Steps: 49%|βββββ | 294/600 [10:26<08:13, 1.61s/it, loss=0.142, lr=1e-5]
Steps: 49%|βββββ | 295/600 [10:28<08:27, 1.66s/it, loss=0.142, lr=1e-5]
Steps: 49%|βββββ | 295/600 [10:28<08:27, 1.66s/it, loss=0.00949, lr=1e-5]
Steps: 49%|βββββ | 296/600 [10:29<08:02, 1.59s/it, loss=0.00949, lr=1e-5]
Steps: 49%|βββββ | 296/600 [10:29<08:02, 1.59s/it, loss=0.192, lr=1e-5]
Steps: 50%|βββββ | 297/600 [10:30<06:47, 1.34s/it, loss=0.192, lr=1e-5]
Steps: 50%|βββββ | 297/600 [10:30<06:47, 1.34s/it, loss=0.319, lr=1e-5]
Steps: 50%|βββββ | 298/600 [10:32<08:16, 1.64s/it, loss=0.319, lr=1e-5]
Steps: 50%|βββββ | 298/600 [10:32<08:16, 1.64s/it, loss=0.0163, lr=1e-5]
Steps: 50%|βββββ | 299/600 [10:34<08:26, 1.68s/it, loss=0.0163, lr=1e-5]
Steps: 50%|βββββ | 299/600 [10:34<08:26, 1.68s/it, loss=0.233, lr=1e-5]
Steps: 50%|βββββ | 300/600 [10:36<08:34, 1.71s/it, loss=0.233, lr=1e-5]
Steps: 50%|βββββ | 300/600 [10:36<08:34, 1.71s/it, loss=0.0167, lr=1e-5]
Steps: 50%|βββββ | 301/600 [10:37<08:31, 1.71s/it, loss=0.0167, lr=1e-5]
Steps: 50%|βββββ | 301/600 [10:37<08:31, 1.71s/it, loss=0.283, lr=1e-5]
Steps: 50%|βββββ | 302/600 [10:39<07:57, 1.60s/it, loss=0.283, lr=1e-5]
Steps: 50%|βββββ | 302/600 [10:39<07:57, 1.60s/it, loss=0.235, lr=1e-5]
Steps: 50%|βββββ | 303/600 [10:40<07:43, 1.56s/it, loss=0.235, lr=1e-5]
Steps: 50%|βββββ | 303/600 [10:40<07:43, 1.56s/it, loss=0.163, lr=1e-5]
Steps: 51%|βββββ | 304/600 [10:42<08:05, 1.64s/it, loss=0.163, lr=1e-5]
Steps: 51%|βββββ | 304/600 [10:42<08:05, 1.64s/it, loss=0.219, lr=1e-5]
Steps: 51%|βββββ | 305/600 [10:44<08:12, 1.67s/it, loss=0.219, lr=1e-5]
Steps: 51%|βββββ | 305/600 [10:44<08:12, 1.67s/it, loss=0.218, lr=1e-5]
Steps: 51%|βββββ | 306/600 [10:45<08:00, 1.64s/it, loss=0.218, lr=1e-5]
Steps: 51%|βββββ | 306/600 [10:45<08:00, 1.64s/it, loss=0.00358, lr=1e-5]
Steps: 51%|βββββ | 307/600 [10:47<07:29, 1.53s/it, loss=0.00358, lr=1e-5]
Steps: 51%|βββββ | 307/600 [10:47<07:29, 1.53s/it, loss=0.135, lr=1e-5]
Steps: 51%|ββββββ | 308/600 [10:47<06:20, 1.30s/it, loss=0.135, lr=1e-5]
Steps: 51%|ββββββ | 308/600 [10:47<06:20, 1.30s/it, loss=0.291, lr=1e-5]
Steps: 52%|ββββββ | 309/600 [10:50<07:28, 1.54s/it, loss=0.291, lr=1e-5]
Steps: 52%|ββββββ | 309/600 [10:50<07:28, 1.54s/it, loss=0.212, lr=1e-5]
Steps: 52%|ββββββ | 310/600 [10:51<07:40, 1.59s/it, loss=0.212, lr=1e-5]
Steps: 52%|ββββββ | 310/600 [10:51<07:40, 1.59s/it, loss=0.16, lr=1e-5]
Steps: 52%|ββββββ | 311/600 [10:53<07:31, 1.56s/it, loss=0.16, lr=1e-5]
Steps: 52%|ββββββ | 311/600 [10:53<07:31, 1.56s/it, loss=0.103, lr=1e-5]
Steps: 52%|ββββββ | 312/600 [10:54<07:47, 1.62s/it, loss=0.103, lr=1e-5]
Steps: 52%|ββββββ | 312/600 [10:54<07:47, 1.62s/it, loss=0.0256, lr=1e-5]
Steps: 52%|ββββββ | 313/600 [10:56<07:50, 1.64s/it, loss=0.0256, lr=1e-5]
Steps: 52%|ββββββ | 313/600 [10:56<07:50, 1.64s/it, loss=0.163, lr=1e-5]
Steps: 52%|ββββββ | 314/600 [10:58<07:53, 1.66s/it, loss=0.163, lr=1e-5]
Steps: 52%|ββββββ | 314/600 [10:58<07:53, 1.66s/it, loss=0.0719, lr=1e-5]
Steps: 52%|ββββββ | 315/600 [11:00<07:50, 1.65s/it, loss=0.0719, lr=1e-5]
Steps: 52%|ββββββ | 315/600 [11:00<07:50, 1.65s/it, loss=0.0119, lr=1e-5]
Steps: 53%|ββββββ | 316/600 [11:01<07:46, 1.64s/it, loss=0.0119, lr=1e-5]
Steps: 53%|ββββββ | 316/600 [11:01<07:46, 1.64s/it, loss=0.299, lr=1e-5]
Steps: 53%|ββββββ | 317/600 [11:03<07:48, 1.66s/it, loss=0.299, lr=1e-5]
Steps: 53%|ββββββ | 317/600 [11:03<07:48, 1.66s/it, loss=0.0484, lr=1e-5]
Steps: 53%|ββββββ | 318/600 [11:04<07:01, 1.49s/it, loss=0.0484, lr=1e-5]
Steps: 53%|ββββββ | 318/600 [11:04<07:01, 1.49s/it, loss=0.0449, lr=1e-5]
Steps: 53%|ββββββ | 319/600 [11:05<05:58, 1.28s/it, loss=0.0449, lr=1e-5]
Steps: 53%|ββββββ | 319/600 [11:05<05:58, 1.28s/it, loss=0.0425, lr=1e-5]
Steps: 53%|ββββββ | 320/600 [11:07<07:37, 1.63s/it, loss=0.0425, lr=1e-5]
Steps: 53%|ββββββ | 320/600 [11:07<07:37, 1.63s/it, loss=0.0127, lr=1e-5]
Steps: 54%|ββββββ | 321/600 [11:09<07:49, 1.68s/it, loss=0.0127, lr=1e-5]
Steps: 54%|ββββββ | 321/600 [11:09<07:49, 1.68s/it, loss=0.229, lr=1e-5]
Steps: 54%|ββββββ | 322/600 [11:11<07:39, 1.65s/it, loss=0.229, lr=1e-5]
Steps: 54%|ββββββ | 322/600 [11:11<07:39, 1.65s/it, loss=0.146, lr=1e-5]
Steps: 54%|ββββββ | 323/600 [11:12<07:51, 1.70s/it, loss=0.146, lr=1e-5]
Steps: 54%|ββββββ | 323/600 [11:12<07:51, 1.70s/it, loss=0.142, lr=1e-5]
Steps: 54%|ββββββ | 324/600 [11:14<07:57, 1.73s/it, loss=0.142, lr=1e-5]
Steps: 54%|ββββββ | 324/600 [11:14<07:57, 1.73s/it, loss=0.23, lr=1e-5]
Steps: 54%|ββββββ | 325/600 [11:16<07:56, 1.73s/it, loss=0.23, lr=1e-5]
Steps: 54%|ββββββ | 325/600 [11:16<07:56, 1.73s/it, loss=0.23, lr=1e-5]
Steps: 54%|ββββββ | 326/600 [11:17<07:23, 1.62s/it, loss=0.23, lr=1e-5]
Steps: 54%|ββββββ | 326/600 [11:17<07:23, 1.62s/it, loss=0.0901, lr=1e-5]
Steps: 55%|ββββββ | 327/600 [11:19<07:32, 1.66s/it, loss=0.0901, lr=1e-5]
Steps: 55%|ββββββ | 327/600 [11:19<07:32, 1.66s/it, loss=0.119, lr=1e-5]
Steps: 55%|ββββββ | 328/600 [11:21<07:35, 1.67s/it, loss=0.119, lr=1e-5]
Steps: 55%|ββββββ | 328/600 [11:21<07:35, 1.67s/it, loss=0.126, lr=1e-5]
Steps: 55%|ββββββ | 329/600 [11:22<06:49, 1.51s/it, loss=0.126, lr=1e-5]
Steps: 55%|ββββββ | 329/600 [11:22<06:49, 1.51s/it, loss=0.0292, lr=1e-5]
Steps: 55%|ββββββ | 330/600 [11:23<05:47, 1.29s/it, loss=0.0292, lr=1e-5]
Steps: 55%|ββββββ | 330/600 [11:23<05:47, 1.29s/it, loss=0.168, lr=1e-5]
Steps: 55%|ββββββ | 331/600 [11:25<07:00, 1.56s/it, loss=0.168, lr=1e-5]
Steps: 55%|ββββββ | 331/600 [11:25<07:00, 1.56s/it, loss=0.0205, lr=1e-5]
Steps: 55%|ββββββ | 332/600 [11:27<07:10, 1.61s/it, loss=0.0205, lr=1e-5]
Steps: 55%|ββββββ | 332/600 [11:27<07:10, 1.61s/it, loss=0.0035, lr=1e-5]
Steps: 56%|ββββββ | 333/600 [11:28<07:12, 1.62s/it, loss=0.0035, lr=1e-5]
Steps: 56%|ββββββ | 333/600 [11:28<07:12, 1.62s/it, loss=0.138, lr=1e-5]
Steps: 56%|ββββββ | 334/600 [11:30<07:36, 1.72s/it, loss=0.138, lr=1e-5]
Steps: 56%|ββββββ | 334/600 [11:30<07:36, 1.72s/it, loss=0.191, lr=1e-5]
Steps: 56%|ββββββ | 335/600 [11:32<07:30, 1.70s/it, loss=0.191, lr=1e-5]
Steps: 56%|ββββββ | 335/600 [11:32<07:30, 1.70s/it, loss=0.131, lr=1e-5]
Steps: 56%|ββββββ | 336/600 [11:33<07:26, 1.69s/it, loss=0.131, lr=1e-5]
Steps: 56%|ββββββ | 336/600 [11:33<07:26, 1.69s/it, loss=0.0125, lr=1e-5]
Steps: 56%|ββββββ | 337/600 [11:35<07:17, 1.66s/it, loss=0.0125, lr=1e-5]
Steps: 56%|ββββββ | 337/600 [11:35<07:17, 1.66s/it, loss=0.0956, lr=1e-5]
Steps: 56%|ββββββ | 338/600 [11:36<06:52, 1.57s/it, loss=0.0956, lr=1e-5]
Steps: 56%|ββββββ | 338/600 [11:36<06:52, 1.57s/it, loss=0.157, lr=1e-5]
Steps: 56%|ββββββ | 339/600 [11:38<06:46, 1.56s/it, loss=0.157, lr=1e-5]
Steps: 56%|ββββββ | 339/600 [11:38<06:46, 1.56s/it, loss=0.124, lr=1e-5]
Steps: 57%|ββββββ | 340/600 [11:39<06:18, 1.46s/it, loss=0.124, lr=1e-5]
Steps: 57%|ββββββ | 340/600 [11:39<06:18, 1.46s/it, loss=0.152, lr=1e-5]
Steps: 57%|ββββββ | 341/600 [11:40<05:23, 1.25s/it, loss=0.152, lr=1e-5]
Steps: 57%|ββββββ | 341/600 [11:40<05:23, 1.25s/it, loss=0.194, lr=1e-5]
Steps: 57%|ββββββ | 342/600 [11:42<06:37, 1.54s/it, loss=0.194, lr=1e-5]
Steps: 57%|ββββββ | 342/600 [11:42<06:37, 1.54s/it, loss=0.0463, lr=1e-5]
Steps: 57%|ββββββ | 343/600 [11:44<06:30, 1.52s/it, loss=0.0463, lr=1e-5]
Steps: 57%|ββββββ | 343/600 [11:44<06:30, 1.52s/it, loss=0.135, lr=1e-5]
Steps: 57%|ββββββ | 344/600 [11:45<06:43, 1.58s/it, loss=0.135, lr=1e-5]
Steps: 57%|ββββββ | 344/600 [11:45<06:43, 1.58s/it, loss=0.0626, lr=1e-5]
Steps: 57%|ββββββ | 345/600 [11:47<06:41, 1.57s/it, loss=0.0626, lr=1e-5]
Steps: 57%|ββββββ | 345/600 [11:47<06:41, 1.57s/it, loss=0.163, lr=1e-5]
Steps: 58%|ββββββ | 346/600 [11:48<06:33, 1.55s/it, loss=0.163, lr=1e-5]
Steps: 58%|ββββββ | 346/600 [11:48<06:33, 1.55s/it, loss=0.00666, lr=1e-5]
Steps: 58%|ββββββ | 347/600 [11:50<06:33, 1.55s/it, loss=0.00666, lr=1e-5]
Steps: 58%|ββββββ | 347/600 [11:50<06:33, 1.55s/it, loss=0.0852, lr=1e-5]
Steps: 58%|ββββββ | 348/600 [11:52<06:44, 1.60s/it, loss=0.0852, lr=1e-5]
Steps: 58%|ββββββ | 348/600 [11:52<06:44, 1.60s/it, loss=0.189, lr=1e-5]
Steps: 58%|ββββββ | 349/600 [11:53<06:57, 1.66s/it, loss=0.189, lr=1e-5]
Steps: 58%|ββββββ | 349/600 [11:53<06:57, 1.66s/it, loss=0.124, lr=1e-5]
Steps: 58%|ββββββ | 350/600 [11:55<06:42, 1.61s/it, loss=0.124, lr=1e-5]
Steps: 58%|ββββββ | 350/600 [11:55<06:42, 1.61s/it, loss=0.272, lr=1e-5]
Steps: 58%|ββββββ | 351/600 [11:56<06:35, 1.59s/it, loss=0.272, lr=1e-5]
Steps: 58%|ββββββ | 351/600 [11:56<06:35, 1.59s/it, loss=0.0195, lr=1e-5]
Steps: 59%|ββββββ | 352/600 [11:57<05:32, 1.34s/it, loss=0.0195, lr=1e-5]
Steps: 59%|ββββββ | 352/600 [11:57<05:32, 1.34s/it, loss=0.0681, lr=1e-5]
Steps: 59%|ββββββ | 353/600 [12:00<06:54, 1.68s/it, loss=0.0681, lr=1e-5]
Steps: 59%|ββββββ | 353/600 [12:00<06:54, 1.68s/it, loss=0.00347, lr=1e-5]
Steps: 59%|ββββββ | 354/600 [12:01<06:54, 1.68s/it, loss=0.00347, lr=1e-5]
Steps: 59%|ββββββ | 354/600 [12:01<06:54, 1.68s/it, loss=0.146, lr=1e-5]
Steps: 59%|ββββββ | 355/600 [12:03<06:54, 1.69s/it, loss=0.146, lr=1e-5]
Steps: 59%|ββββββ | 355/600 [12:03<06:54, 1.69s/it, loss=0.0924, lr=1e-5]
Steps: 59%|ββββββ | 356/600 [12:05<07:00, 1.72s/it, loss=0.0924, lr=1e-5]
Steps: 59%|ββββββ | 356/600 [12:05<07:00, 1.72s/it, loss=0.137, lr=1e-5]
Steps: 60%|ββββββ | 357/600 [12:06<06:49, 1.68s/it, loss=0.137, lr=1e-5]
Steps: 60%|ββββββ | 357/600 [12:06<06:49, 1.68s/it, loss=0.269, lr=1e-5]
Steps: 60%|ββββββ | 358/600 [12:08<06:29, 1.61s/it, loss=0.269, lr=1e-5]
Steps: 60%|ββββββ | 358/600 [12:08<06:29, 1.61s/it, loss=0.156, lr=1e-5]
Steps: 60%|ββββββ | 359/600 [12:09<06:20, 1.58s/it, loss=0.156, lr=1e-5]
Steps: 60%|ββββββ | 359/600 [12:09<06:20, 1.58s/it, loss=0.171, lr=1e-5]
Steps: 60%|ββββββ | 360/600 [12:11<06:25, 1.61s/it, loss=0.171, lr=1e-5]
Steps: 60%|ββββββ | 360/600 [12:11<06:25, 1.61s/it, loss=0.0751, lr=1e-5]
Steps: 60%|ββββββ | 361/600 [12:13<06:34, 1.65s/it, loss=0.0751, lr=1e-5]
Steps: 60%|ββββββ | 361/600 [12:13<06:34, 1.65s/it, loss=0.0357, lr=1e-5]
Steps: 60%|ββββββ | 362/600 [12:14<06:04, 1.53s/it, loss=0.0357, lr=1e-5]
Steps: 60%|ββββββ | 362/600 [12:14<06:04, 1.53s/it, loss=0.114, lr=1e-5]
Steps: 60%|ββββββ | 363/600 [12:15<05:09, 1.31s/it, loss=0.114, lr=1e-5]
Steps: 60%|ββββββ | 363/600 [12:15<05:09, 1.31s/it, loss=0.0126, lr=1e-5]
Steps: 61%|ββββββ | 364/600 [12:17<05:52, 1.50s/it, loss=0.0126, lr=1e-5]
Steps: 61%|ββββββ | 364/600 [12:17<05:52, 1.50s/it, loss=0.133, lr=1e-5]
Steps: 61%|ββββββ | 365/600 [12:18<05:52, 1.50s/it, loss=0.133, lr=1e-5]
Steps: 61%|ββββββ | 365/600 [12:18<05:52, 1.50s/it, loss=0.0532, lr=1e-5]
Steps: 61%|ββββββ | 366/600 [12:20<06:11, 1.59s/it, loss=0.0532, lr=1e-5]
Steps: 61%|ββββββ | 366/600 [12:20<06:11, 1.59s/it, loss=0.0239, lr=1e-5]
Steps: 61%|ββββββ | 367/600 [12:22<06:24, 1.65s/it, loss=0.0239, lr=1e-5]
Steps: 61%|ββββββ | 367/600 [12:22<06:24, 1.65s/it, loss=0.0548, lr=1e-5]
Steps: 61%|βββββββ | 368/600 [12:24<06:39, 1.72s/it, loss=0.0548, lr=1e-5]
Steps: 61%|βββββββ | 368/600 [12:24<06:39, 1.72s/it, loss=0.0467, lr=1e-5]
Steps: 62%|βββββββ | 369/600 [12:26<06:43, 1.75s/it, loss=0.0467, lr=1e-5]
Steps: 62%|βββββββ | 369/600 [12:26<06:43, 1.75s/it, loss=0.16, lr=1e-5]
Steps: 62%|βββββββ | 370/600 [12:27<06:22, 1.66s/it, loss=0.16, lr=1e-5]
Steps: 62%|βββββββ | 370/600 [12:27<06:22, 1.66s/it, loss=0.0933, lr=1e-5]
Steps: 62%|βββββββ | 371/600 [12:29<06:14, 1.63s/it, loss=0.0933, lr=1e-5]
Steps: 62%|βββββββ | 371/600 [12:29<06:14, 1.63s/it, loss=0.132, lr=1e-5]
Steps: 62%|βββββββ | 372/600 [12:31<06:28, 1.70s/it, loss=0.132, lr=1e-5]
Steps: 62%|βββββββ | 372/600 [12:31<06:28, 1.70s/it, loss=0.00826, lr=1e-5]
Steps: 62%|βββββββ | 373/600 [12:32<05:56, 1.57s/it, loss=0.00826, lr=1e-5]
Steps: 62%|βββββββ | 373/600 [12:32<05:56, 1.57s/it, loss=0.0304, lr=1e-5]
Steps: 62%|βββββββ | 374/600 [12:33<05:01, 1.33s/it, loss=0.0304, lr=1e-5]
Steps: 62%|βββββββ | 374/600 [12:33<05:01, 1.33s/it, loss=0.0266, lr=1e-5]
Steps: 62%|βββββββ | 375/600 [12:35<06:15, 1.67s/it, loss=0.0266, lr=1e-5]
Steps: 62%|βββββββ | 375/600 [12:35<06:15, 1.67s/it, loss=0.103, lr=1e-5]
Steps: 63%|βββββββ | 376/600 [12:37<06:18, 1.69s/it, loss=0.103, lr=1e-5]
Steps: 63%|βββββββ | 376/600 [12:37<06:18, 1.69s/it, loss=0.107, lr=1e-5]
Steps: 63%|βββββββ | 377/600 [12:38<05:47, 1.56s/it, loss=0.107, lr=1e-5]
Steps: 63%|βββββββ | 377/600 [12:38<05:47, 1.56s/it, loss=0.151, lr=1e-5]
Steps: 63%|βββββββ | 378/600 [12:40<06:00, 1.63s/it, loss=0.151, lr=1e-5]
Steps: 63%|βββββββ | 378/600 [12:40<06:00, 1.63s/it, loss=0.129, lr=1e-5]
Steps: 63%|βββββββ | 379/600 [12:41<05:56, 1.61s/it, loss=0.129, lr=1e-5]
Steps: 63%|βββββββ | 379/600 [12:41<05:56, 1.61s/it, loss=0.244, lr=1e-5]
Steps: 63%|βββββββ | 380/600 [12:43<06:07, 1.67s/it, loss=0.244, lr=1e-5]
Steps: 63%|βββββββ | 380/600 [12:43<06:07, 1.67s/it, loss=0.11, lr=1e-5]
Steps: 64%|βββββββ | 381/600 [12:45<05:58, 1.64s/it, loss=0.11, lr=1e-5]
Steps: 64%|βββββββ | 381/600 [12:45<05:58, 1.64s/it, loss=0.0221, lr=1e-5]
Steps: 64%|βββββββ | 382/600 [12:46<06:03, 1.67s/it, loss=0.0221, lr=1e-5]
Steps: 64%|βββββββ | 382/600 [12:46<06:03, 1.67s/it, loss=0.246, lr=1e-5]
Steps: 64%|βββββββ | 383/600 [12:48<06:03, 1.67s/it, loss=0.246, lr=1e-5]
Steps: 64%|βββββββ | 383/600 [12:48<06:03, 1.67s/it, loss=0.0922, lr=1e-5]
Steps: 64%|βββββββ | 384/600 [12:49<05:33, 1.55s/it, loss=0.0922, lr=1e-5]
Steps: 64%|βββββββ | 384/600 [12:49<05:33, 1.55s/it, loss=0.0231, lr=1e-5]
Steps: 64%|βββββββ | 385/600 [12:50<04:42, 1.31s/it, loss=0.0231, lr=1e-5]
Steps: 64%|βββββββ | 385/600 [12:50<04:42, 1.31s/it, loss=0.23, lr=1e-5]
Steps: 64%|βββββββ | 386/600 [12:53<05:53, 1.65s/it, loss=0.23, lr=1e-5]
Steps: 64%|βββββββ | 386/600 [12:53<05:53, 1.65s/it, loss=0.00951, lr=1e-5]
Steps: 64%|βββββββ | 387/600 [12:54<05:56, 1.67s/it, loss=0.00951, lr=1e-5]
Steps: 64%|βββββββ | 387/600 [12:54<05:56, 1.67s/it, loss=0.0834, lr=1e-5]
Steps: 65%|βββββββ | 388/600 [12:56<05:42, 1.62s/it, loss=0.0834, lr=1e-5]
Steps: 65%|βββββββ | 388/600 [12:56<05:42, 1.62s/it, loss=0.128, lr=1e-5]
Steps: 65%|βββββββ | 389/600 [12:58<05:46, 1.64s/it, loss=0.128, lr=1e-5]
Steps: 65%|βββββββ | 389/600 [12:58<05:46, 1.64s/it, loss=0.0221, lr=1e-5]
Steps: 65%|βββββββ | 390/600 [12:59<05:38, 1.61s/it, loss=0.0221, lr=1e-5]
Steps: 65%|βββββββ | 390/600 [12:59<05:38, 1.61s/it, loss=0.26, lr=1e-5]
Steps: 65%|βββββββ | 391/600 [13:01<05:31, 1.59s/it, loss=0.26, lr=1e-5]
Steps: 65%|βββββββ | 391/600 [13:01<05:31, 1.59s/it, loss=0.182, lr=1e-5]
Steps: 65%|βββββββ | 392/600 [13:02<05:36, 1.62s/it, loss=0.182, lr=1e-5]
Steps: 65%|βββββββ | 392/600 [13:02<05:36, 1.62s/it, loss=0.0266, lr=1e-5]
Steps: 66%|βββββββ | 393/600 [13:04<05:31, 1.60s/it, loss=0.0266, lr=1e-5]
Steps: 66%|βββββββ | 393/600 [13:04<05:31, 1.60s/it, loss=0.0499, lr=1e-5]
Steps: 66%|βββββββ | 394/600 [13:05<05:24, 1.58s/it, loss=0.0499, lr=1e-5]
Steps: 66%|βββββββ | 394/600 [13:05<05:24, 1.58s/it, loss=0.141, lr=1e-5]
Steps: 66%|βββββββ | 395/600 [13:07<05:17, 1.55s/it, loss=0.141, lr=1e-5]
Steps: 66%|βββββββ | 395/600 [13:07<05:17, 1.55s/it, loss=0.27, lr=1e-5]
Steps: 66%|βββββββ | 396/600 [13:08<04:28, 1.31s/it, loss=0.27, lr=1e-5]
Steps: 66%|βββββββ | 396/600 [13:08<04:28, 1.31s/it, loss=0.212, lr=1e-5]
Steps: 66%|βββββββ | 397/600 [13:10<05:32, 1.64s/it, loss=0.212, lr=1e-5]
Steps: 66%|βββββββ | 397/600 [13:10<05:32, 1.64s/it, loss=0.00275, lr=1e-5]
Steps: 66%|βββββββ | 398/600 [13:11<05:20, 1.59s/it, loss=0.00275, lr=1e-5]
Steps: 66%|βββββββ | 398/600 [13:11<05:20, 1.59s/it, loss=0.0648, lr=1e-5]
Steps: 66%|βββββββ | 399/600 [13:13<05:25, 1.62s/it, loss=0.0648, lr=1e-5]
Steps: 66%|βββββββ | 399/600 [13:13<05:25, 1.62s/it, loss=0.0372, lr=1e-5]
Steps: 67%|βββββββ | 400/600 [13:15<05:18, 1.59s/it, loss=0.0372, lr=1e-5]
Steps: 67%|βββββββ | 400/600 [13:15<05:18, 1.59s/it, loss=0.0716, lr=1e-5]
Steps: 67%|βββββββ | 401/600 [13:16<05:23, 1.62s/it, loss=0.0716, lr=1e-5]
Steps: 67%|βββββββ | 401/600 [13:16<05:23, 1.62s/it, loss=0.0401, lr=1e-5]
Steps: 67%|βββββββ | 402/600 [13:18<05:19, 1.62s/it, loss=0.0401, lr=1e-5]
Steps: 67%|βββββββ | 402/600 [13:18<05:19, 1.62s/it, loss=0.153, lr=1e-5]
Steps: 67%|βββββββ | 403/600 [13:20<05:16, 1.61s/it, loss=0.153, lr=1e-5]
Steps: 67%|βββββββ | 403/600 [13:20<05:16, 1.61s/it, loss=0.068, lr=1e-5]
Steps: 67%|βββββββ | 404/600 [13:21<05:12, 1.59s/it, loss=0.068, lr=1e-5]
Steps: 67%|βββββββ | 404/600 [13:21<05:12, 1.59s/it, loss=0.195, lr=1e-5]
Steps: 68%|βββββββ | 405/600 [13:23<05:15, 1.62s/it, loss=0.195, lr=1e-5]
Steps: 68%|βββββββ | 405/600 [13:23<05:15, 1.62s/it, loss=0.226, lr=1e-5]
Steps: 68%|βββββββ | 406/600 [13:24<04:54, 1.52s/it, loss=0.226, lr=1e-5]
Steps: 68%|βββββββ | 406/600 [13:24<04:54, 1.52s/it, loss=0.197, lr=1e-5]
Steps: 68%|βββββββ | 407/600 [13:25<04:09, 1.29s/it, loss=0.197, lr=1e-5]
Steps: 68%|βββββββ | 407/600 [13:25<04:09, 1.29s/it, loss=0.0101, lr=1e-5]
Steps: 68%|βββββββ | 408/600 [13:27<04:49, 1.51s/it, loss=0.0101, lr=1e-5]
Steps: 68%|βββββββ | 408/600 [13:27<04:49, 1.51s/it, loss=0.0721, lr=1e-5]
Steps: 68%|βββββββ | 409/600 [13:29<04:59, 1.57s/it, loss=0.0721, lr=1e-5]
Steps: 68%|βββββββ | 409/600 [13:29<04:59, 1.57s/it, loss=0.246, lr=1e-5]
Steps: 68%|βββββββ | 410/600 [13:30<04:51, 1.54s/it, loss=0.246, lr=1e-5]
Steps: 68%|βββββββ | 410/600 [13:30<04:51, 1.54s/it, loss=0.133, lr=1e-5]
Steps: 68%|βββββββ | 411/600 [13:32<05:11, 1.65s/it, loss=0.133, lr=1e-5]
Steps: 68%|βββββββ | 411/600 [13:32<05:11, 1.65s/it, loss=0.134, lr=1e-5]
Steps: 69%|βββββββ | 412/600 [13:34<05:08, 1.64s/it, loss=0.134, lr=1e-5]
Steps: 69%|βββββββ | 412/600 [13:34<05:08, 1.64s/it, loss=0.205, lr=1e-5]
Steps: 69%|βββββββ | 413/600 [13:35<05:10, 1.66s/it, loss=0.205, lr=1e-5]
Steps: 69%|βββββββ | 413/600 [13:35<05:10, 1.66s/it, loss=0.0221, lr=1e-5]
Steps: 69%|βββββββ | 414/600 [13:37<05:05, 1.64s/it, loss=0.0221, lr=1e-5]
Steps: 69%|βββββββ | 414/600 [13:37<05:05, 1.64s/it, loss=0.0067, lr=1e-5]
Steps: 69%|βββββββ | 415/600 [13:38<04:48, 1.56s/it, loss=0.0067, lr=1e-5]
Steps: 69%|βββββββ | 415/600 [13:38<04:48, 1.56s/it, loss=0.102, lr=1e-5]
Steps: 69%|βββββββ | 416/600 [13:40<04:46, 1.56s/it, loss=0.102, lr=1e-5]
Steps: 69%|βββββββ | 416/600 [13:40<04:46, 1.56s/it, loss=0.0907, lr=1e-5]
Steps: 70%|βββββββ | 417/600 [13:41<04:40, 1.54s/it, loss=0.0907, lr=1e-5]
Steps: 70%|βββββββ | 417/600 [13:41<04:40, 1.54s/it, loss=0.165, lr=1e-5]
Steps: 70%|βββββββ | 418/600 [13:42<03:57, 1.30s/it, loss=0.165, lr=1e-5]
Steps: 70%|βββββββ | 418/600 [13:42<03:57, 1.30s/it, loss=0.0407, lr=1e-5]
Steps: 70%|βββββββ | 419/600 [13:44<04:45, 1.58s/it, loss=0.0407, lr=1e-5]
Steps: 70%|βββββββ | 419/600 [13:44<04:45, 1.58s/it, loss=0.0417, lr=1e-5]
Steps: 70%|βββββββ | 420/600 [13:46<04:48, 1.60s/it, loss=0.0417, lr=1e-5]
Steps: 70%|βββββββ | 420/600 [13:46<04:48, 1.60s/it, loss=0.0147, lr=1e-5]
Steps: 70%|βββββββ | 421/600 [13:48<04:49, 1.62s/it, loss=0.0147, lr=1e-5]
Steps: 70%|βββββββ | 421/600 [13:48<04:49, 1.62s/it, loss=0.0732, lr=1e-5]
Steps: 70%|βββββββ | 422/600 [13:49<04:35, 1.55s/it, loss=0.0732, lr=1e-5]
Steps: 70%|βββββββ | 422/600 [13:49<04:35, 1.55s/it, loss=0.312, lr=1e-5]
Steps: 70%|βββββββ | 423/600 [13:51<04:53, 1.66s/it, loss=0.312, lr=1e-5]
Steps: 70%|βββββββ | 423/600 [13:51<04:53, 1.66s/it, loss=0.151, lr=1e-5]
Steps: 71%|βββββββ | 424/600 [13:52<04:41, 1.60s/it, loss=0.151, lr=1e-5]
Steps: 71%|βββββββ | 424/600 [13:52<04:41, 1.60s/it, loss=0.179, lr=1e-5]
Steps: 71%|βββββββ | 425/600 [13:54<04:33, 1.56s/it, loss=0.179, lr=1e-5]
Steps: 71%|βββββββ | 425/600 [13:54<04:33, 1.56s/it, loss=0.129, lr=1e-5]
Steps: 71%|βββββββ | 426/600 [13:56<04:44, 1.64s/it, loss=0.129, lr=1e-5]
Steps: 71%|βββββββ | 426/600 [13:56<04:44, 1.64s/it, loss=0.0301, lr=1e-5]
Steps: 71%|βββββββ | 427/600 [13:57<04:52, 1.69s/it, loss=0.0301, lr=1e-5]
Steps: 71%|βββββββ | 427/600 [13:57<04:52, 1.69s/it, loss=0.215, lr=1e-5]
Steps: 71%|ββββββββ | 428/600 [13:59<04:22, 1.52s/it, loss=0.215, lr=1e-5]
Steps: 71%|ββββββββ | 428/600 [13:59<04:22, 1.52s/it, loss=0.0211, lr=1e-5]
Steps: 72%|ββββββββ | 429/600 [13:59<03:42, 1.30s/it, loss=0.0211, lr=1e-5]
Steps: 72%|ββββββββ | 429/600 [13:59<03:42, 1.30s/it, loss=0.253, lr=1e-5]
Steps: 72%|ββββββββ | 430/600 [14:02<04:26, 1.57s/it, loss=0.253, lr=1e-5]
Steps: 72%|ββββββββ | 430/600 [14:02<04:26, 1.57s/it, loss=0.114, lr=1e-5]
Steps: 72%|ββββββββ | 431/600 [14:03<04:36, 1.63s/it, loss=0.114, lr=1e-5]
Steps: 72%|ββββββββ | 431/600 [14:03<04:36, 1.63s/it, loss=0.171, lr=1e-5]
Steps: 72%|ββββββββ | 432/600 [14:05<04:27, 1.59s/it, loss=0.171, lr=1e-5]
Steps: 72%|ββββββββ | 432/600 [14:05<04:27, 1.59s/it, loss=0.117, lr=1e-5]
Steps: 72%|ββββββββ | 433/600 [14:07<04:29, 1.61s/it, loss=0.117, lr=1e-5]
Steps: 72%|ββββββββ | 433/600 [14:07<04:29, 1.61s/it, loss=0.0477, lr=1e-5]
Steps: 72%|ββββββββ | 434/600 [14:08<04:37, 1.67s/it, loss=0.0477, lr=1e-5]
Steps: 72%|ββββββββ | 434/600 [14:08<04:37, 1.67s/it, loss=0.0209, lr=1e-5]
Steps: 72%|ββββββββ | 435/600 [14:10<04:27, 1.62s/it, loss=0.0209, lr=1e-5]
Steps: 72%|ββββββββ | 435/600 [14:10<04:27, 1.62s/it, loss=0.131, lr=1e-5]
Steps: 73%|ββββββββ | 436/600 [14:11<04:18, 1.58s/it, loss=0.131, lr=1e-5]
Steps: 73%|ββββββββ | 436/600 [14:11<04:18, 1.58s/it, loss=0.0404, lr=1e-5]
Steps: 73%|ββββββββ | 437/600 [14:13<04:34, 1.69s/it, loss=0.0404, lr=1e-5]
Steps: 73%|ββββββββ | 437/600 [14:13<04:34, 1.69s/it, loss=0.0824, lr=1e-5]
Steps: 73%|ββββββββ | 438/600 [14:15<04:23, 1.63s/it, loss=0.0824, lr=1e-5]
Steps: 73%|ββββββββ | 438/600 [14:15<04:23, 1.63s/it, loss=0.0499, lr=1e-5]
Steps: 73%|ββββββββ | 439/600 [14:16<04:04, 1.52s/it, loss=0.0499, lr=1e-5]
Steps: 73%|ββββββββ | 439/600 [14:16<04:04, 1.52s/it, loss=0.0285, lr=1e-5]
Steps: 73%|ββββββββ | 440/600 [14:17<03:27, 1.29s/it, loss=0.0285, lr=1e-5]
Steps: 73%|ββββββββ | 440/600 [14:17<03:27, 1.29s/it, loss=0.0314, lr=1e-5]
Steps: 74%|ββββββββ | 441/600 [14:19<04:14, 1.60s/it, loss=0.0314, lr=1e-5]
Steps: 74%|ββββββββ | 441/600 [14:19<04:14, 1.60s/it, loss=0.16, lr=1e-5]
Steps: 74%|ββββββββ | 442/600 [14:21<04:19, 1.64s/it, loss=0.16, lr=1e-5]
Steps: 74%|ββββββββ | 442/600 [14:21<04:19, 1.64s/it, loss=0.0403, lr=1e-5]
Steps: 74%|ββββββββ | 443/600 [14:22<04:05, 1.57s/it, loss=0.0403, lr=1e-5]
Steps: 74%|ββββββββ | 443/600 [14:22<04:05, 1.57s/it, loss=0.153, lr=1e-5]
Steps: 74%|ββββββββ | 444/600 [14:24<04:06, 1.58s/it, loss=0.153, lr=1e-5]
Steps: 74%|ββββββββ | 444/600 [14:24<04:06, 1.58s/it, loss=0.0932, lr=1e-5]
Steps: 74%|ββββββββ | 445/600 [14:25<04:06, 1.59s/it, loss=0.0932, lr=1e-5]
Steps: 74%|ββββββββ | 445/600 [14:25<04:06, 1.59s/it, loss=0.0112, lr=1e-5]
Steps: 74%|ββββββββ | 446/600 [14:27<04:00, 1.56s/it, loss=0.0112, lr=1e-5]
Steps: 74%|ββββββββ | 446/600 [14:27<04:00, 1.56s/it, loss=0.156, lr=1e-5]
Steps: 74%|ββββββββ | 447/600 [14:29<04:01, 1.58s/it, loss=0.156, lr=1e-5]
Steps: 74%|ββββββββ | 447/600 [14:29<04:01, 1.58s/it, loss=0.0717, lr=1e-5]
Steps: 75%|ββββββββ | 448/600 [14:30<04:03, 1.60s/it, loss=0.0717, lr=1e-5]
Steps: 75%|ββββββββ | 448/600 [14:30<04:03, 1.60s/it, loss=0.0453, lr=1e-5]
Steps: 75%|ββββββββ | 449/600 [14:32<04:03, 1.61s/it, loss=0.0453, lr=1e-5]
Steps: 75%|ββββββββ | 449/600 [14:32<04:03, 1.61s/it, loss=0.0957, lr=1e-5]
Steps: 75%|ββββββββ | 450/600 [14:33<03:51, 1.55s/it, loss=0.0957, lr=1e-5]
Steps: 75%|ββββββββ | 450/600 [14:33<03:51, 1.55s/it, loss=0.00921, lr=1e-5]
Steps: 75%|ββββββββ | 451/600 [14:34<03:15, 1.31s/it, loss=0.00921, lr=1e-5]
Steps: 75%|ββββββββ | 451/600 [14:34<03:15, 1.31s/it, loss=0.249, lr=1e-5]
Steps: 75%|ββββββββ | 452/600 [14:36<04:04, 1.65s/it, loss=0.249, lr=1e-5]
Steps: 75%|ββββββββ | 452/600 [14:36<04:04, 1.65s/it, loss=0.0159, lr=1e-5]
Steps: 76%|ββββββββ | 453/600 [14:38<03:59, 1.63s/it, loss=0.0159, lr=1e-5]
Steps: 76%|ββββββββ | 453/600 [14:38<03:59, 1.63s/it, loss=0.0996, lr=1e-5]
Steps: 76%|ββββββββ | 454/600 [14:40<03:53, 1.60s/it, loss=0.0996, lr=1e-5]
Steps: 76%|ββββββββ | 454/600 [14:40<03:53, 1.60s/it, loss=0.0535, lr=1e-5]
Steps: 76%|ββββββββ | 455/600 [14:41<03:45, 1.56s/it, loss=0.0535, lr=1e-5]
Steps: 76%|ββββββββ | 455/600 [14:41<03:45, 1.56s/it, loss=0.166, lr=1e-5]
Steps: 76%|ββββββββ | 456/600 [14:43<03:44, 1.56s/it, loss=0.166, lr=1e-5]
Steps: 76%|ββββββββ | 456/600 [14:43<03:44, 1.56s/it, loss=0.136, lr=1e-5]
Steps: 76%|ββββββββ | 457/600 [14:44<03:41, 1.55s/it, loss=0.136, lr=1e-5]
Steps: 76%|ββββββββ | 457/600 [14:44<03:41, 1.55s/it, loss=0.121, lr=1e-5]
Steps: 76%|ββββββββ | 458/600 [14:46<03:49, 1.62s/it, loss=0.121, lr=1e-5]
Steps: 76%|ββββββββ | 458/600 [14:46<03:49, 1.62s/it, loss=0.0988, lr=1e-5]
Steps: 76%|ββββββββ | 459/600 [14:47<03:31, 1.50s/it, loss=0.0988, lr=1e-5]
Steps: 76%|ββββββββ | 459/600 [14:47<03:31, 1.50s/it, loss=0.177, lr=1e-5]
Steps: 77%|ββββββββ | 460/600 [14:49<03:44, 1.60s/it, loss=0.177, lr=1e-5]
Steps: 77%|ββββββββ | 460/600 [14:49<03:44, 1.60s/it, loss=0.00735, lr=1e-5]
Steps: 77%|ββββββββ | 461/600 [14:50<03:33, 1.54s/it, loss=0.00735, lr=1e-5]
Steps: 77%|ββββββββ | 461/600 [14:50<03:33, 1.54s/it, loss=0.139, lr=1e-5]
Steps: 77%|ββββββββ | 462/600 [14:51<03:00, 1.31s/it, loss=0.139, lr=1e-5]
Steps: 77%|ββββββββ | 462/600 [14:51<03:00, 1.31s/it, loss=0.00319, lr=1e-5]
Steps: 77%|ββββββββ | 463/600 [14:54<03:44, 1.64s/it, loss=0.00319, lr=1e-5]
Steps: 77%|ββββββββ | 463/600 [14:54<03:44, 1.64s/it, loss=0.0314, lr=1e-5]
Steps: 77%|ββββββββ | 464/600 [14:55<03:46, 1.66s/it, loss=0.0314, lr=1e-5]
Steps: 77%|ββββββββ | 464/600 [14:55<03:46, 1.66s/it, loss=0.144, lr=1e-5]
Steps: 78%|ββββββββ | 465/600 [14:57<03:30, 1.56s/it, loss=0.144, lr=1e-5]
Steps: 78%|ββββββββ | 465/600 [14:57<03:30, 1.56s/it, loss=0.0149, lr=1e-5]
Steps: 78%|ββββββββ | 466/600 [14:58<03:27, 1.55s/it, loss=0.0149, lr=1e-5]
Steps: 78%|ββββββββ | 466/600 [14:58<03:27, 1.55s/it, loss=0.209, lr=1e-5]
Steps: 78%|ββββββββ | 467/600 [15:00<03:30, 1.58s/it, loss=0.209, lr=1e-5]
Steps: 78%|ββββββββ | 467/600 [15:00<03:30, 1.58s/it, loss=0.0161, lr=1e-5]
Steps: 78%|ββββββββ | 468/600 [15:01<03:27, 1.57s/it, loss=0.0161, lr=1e-5]
Steps: 78%|ββββββββ | 468/600 [15:01<03:27, 1.57s/it, loss=0.00397, lr=1e-5]
Steps: 78%|ββββββββ | 469/600 [15:03<03:22, 1.54s/it, loss=0.00397, lr=1e-5]
Steps: 78%|ββββββββ | 469/600 [15:03<03:22, 1.54s/it, loss=0.113, lr=1e-5]
Steps: 78%|ββββββββ | 470/600 [15:05<03:28, 1.60s/it, loss=0.113, lr=1e-5]
Steps: 78%|ββββββββ | 470/600 [15:05<03:28, 1.60s/it, loss=0.0168, lr=1e-5]
Steps: 78%|ββββββββ | 471/600 [15:06<03:34, 1.67s/it, loss=0.0168, lr=1e-5]
Steps: 78%|ββββββββ | 471/600 [15:06<03:34, 1.67s/it, loss=0.0763, lr=1e-5]
Steps: 79%|ββββββββ | 472/600 [15:08<03:16, 1.53s/it, loss=0.0763, lr=1e-5]
Steps: 79%|ββββββββ | 472/600 [15:08<03:16, 1.53s/it, loss=0.0395, lr=1e-5]
Steps: 79%|ββββββββ | 473/600 [15:08<02:45, 1.31s/it, loss=0.0395, lr=1e-5]
Steps: 79%|ββββββββ | 473/600 [15:08<02:45, 1.31s/it, loss=0.12, lr=1e-5]
Steps: 79%|ββββββββ | 474/600 [15:11<03:21, 1.60s/it, loss=0.12, lr=1e-5]
Steps: 79%|ββββββββ | 474/600 [15:11<03:21, 1.60s/it, loss=0.203, lr=1e-5]
Steps: 79%|ββββββββ | 475/600 [15:12<03:12, 1.54s/it, loss=0.203, lr=1e-5]
Steps: 79%|ββββββββ | 475/600 [15:12<03:12, 1.54s/it, loss=0.189, lr=1e-5]
Steps: 79%|ββββββββ | 476/600 [15:13<03:04, 1.49s/it, loss=0.189, lr=1e-5]
Steps: 79%|ββββββββ | 476/600 [15:13<03:04, 1.49s/it, loss=0.135, lr=1e-5]
Steps: 80%|ββββββββ | 477/600 [15:15<03:05, 1.51s/it, loss=0.135, lr=1e-5]
Steps: 80%|ββββββββ | 477/600 [15:15<03:05, 1.51s/it, loss=0.0469, lr=1e-5]
Steps: 80%|ββββββββ | 478/600 [15:17<03:11, 1.57s/it, loss=0.0469, lr=1e-5]
Steps: 80%|ββββββββ | 478/600 [15:17<03:11, 1.57s/it, loss=0.0105, lr=1e-5]
Steps: 80%|ββββββββ | 479/600 [15:19<03:24, 1.69s/it, loss=0.0105, lr=1e-5]
Steps: 80%|ββββββββ | 479/600 [15:19<03:24, 1.69s/it, loss=0.164, lr=1e-5]
Steps: 80%|ββββββββ | 480/600 [15:20<03:13, 1.62s/it, loss=0.164, lr=1e-5]
Steps: 80%|ββββββββ | 480/600 [15:20<03:13, 1.62s/it, loss=0.0244, lr=1e-5]
Steps: 80%|ββββββββ | 481/600 [15:22<03:17, 1.66s/it, loss=0.0244, lr=1e-5]
Steps: 80%|ββββββββ | 481/600 [15:22<03:17, 1.66s/it, loss=0.143, lr=1e-5]
Steps: 80%|ββββββββ | 482/600 [15:23<03:14, 1.65s/it, loss=0.143, lr=1e-5]
Steps: 80%|ββββββββ | 482/600 [15:23<03:14, 1.65s/it, loss=0.0649, lr=1e-5]
Steps: 80%|ββββββββ | 483/600 [15:25<03:07, 1.60s/it, loss=0.0649, lr=1e-5]
Steps: 80%|ββββββββ | 483/600 [15:25<03:07, 1.60s/it, loss=0.0085, lr=1e-5]
Steps: 81%|ββββββββ | 484/600 [15:26<02:36, 1.35s/it, loss=0.0085, lr=1e-5]
Steps: 81%|ββββββββ | 484/600 [15:26<02:36, 1.35s/it, loss=0.12, lr=1e-5]
Steps: 81%|ββββββββ | 485/600 [15:28<03:06, 1.62s/it, loss=0.12, lr=1e-5]
Steps: 81%|ββββββββ | 485/600 [15:28<03:06, 1.62s/it, loss=0.0175, lr=1e-5]
Steps: 81%|ββββββββ | 486/600 [15:29<03:02, 1.60s/it, loss=0.0175, lr=1e-5]
Steps: 81%|ββββββββ | 486/600 [15:29<03:02, 1.60s/it, loss=0.0401, lr=1e-5]
Steps: 81%|ββββββββ | 487/600 [15:31<03:07, 1.66s/it, loss=0.0401, lr=1e-5]
Steps: 81%|ββββββββ | 487/600 [15:31<03:07, 1.66s/it, loss=0.0936, lr=1e-5]
Steps: 81%|βββββββββ | 488/600 [15:33<03:10, 1.70s/it, loss=0.0936, lr=1e-5]
Steps: 81%|βββββββββ | 488/600 [15:33<03:10, 1.70s/it, loss=0.0941, lr=1e-5]
Steps: 82%|βββββββββ | 489/600 [15:34<02:56, 1.59s/it, loss=0.0941, lr=1e-5]
Steps: 82%|βββββββββ | 489/600 [15:34<02:56, 1.59s/it, loss=0.0712, lr=1e-5]
Steps: 82%|βββββββββ | 490/600 [15:36<02:56, 1.60s/it, loss=0.0712, lr=1e-5]
Steps: 82%|βββββββββ | 490/600 [15:36<02:56, 1.60s/it, loss=0.288, lr=1e-5]
Steps: 82%|βββββββββ | 491/600 [15:37<02:46, 1.53s/it, loss=0.288, lr=1e-5]
Steps: 82%|βββββββββ | 491/600 [15:37<02:46, 1.53s/it, loss=0.388, lr=1e-5]
Steps: 82%|βββββββββ | 492/600 [15:39<02:41, 1.49s/it, loss=0.388, lr=1e-5]
Steps: 82%|βββββββββ | 492/600 [15:39<02:41, 1.49s/it, loss=0.0207, lr=1e-5]
Steps: 82%|βββββββββ | 493/600 [15:41<02:46, 1.55s/it, loss=0.0207, lr=1e-5]
Steps: 82%|βββββββββ | 493/600 [15:41<02:46, 1.55s/it, loss=0.0899, lr=1e-5]
Steps: 82%|βββββββββ | 494/600 [15:42<02:40, 1.52s/it, loss=0.0899, lr=1e-5]
Steps: 82%|βββββββββ | 494/600 [15:42<02:40, 1.52s/it, loss=0.101, lr=1e-5]
Steps: 82%|βββββββββ | 495/600 [15:43<02:16, 1.30s/it, loss=0.101, lr=1e-5]
Steps: 82%|βββββββββ | 495/600 [15:43<02:16, 1.30s/it, loss=0.114, lr=1e-5]
Steps: 83%|βββββββββ | 496/600 [15:45<02:47, 1.61s/it, loss=0.114, lr=1e-5]
Steps: 83%|βββββββββ | 496/600 [15:45<02:47, 1.61s/it, loss=0.239, lr=1e-5]
Steps: 83%|βββββββββ | 497/600 [15:47<02:51, 1.66s/it, loss=0.239, lr=1e-5]
Steps: 83%|βββββββββ | 497/600 [15:47<02:51, 1.66s/it, loss=0.207, lr=1e-5]
Steps: 83%|βββββββββ | 498/600 [15:48<02:44, 1.62s/it, loss=0.207, lr=1e-5]
Steps: 83%|βββββββββ | 498/600 [15:48<02:44, 1.62s/it, loss=0.0539, lr=1e-5]
Steps: 83%|βββββββββ | 499/600 [15:50<02:38, 1.57s/it, loss=0.0539, lr=1e-5]
Steps: 83%|βββββββββ | 499/600 [15:50<02:38, 1.57s/it, loss=0.173, lr=1e-5]
Steps: 83%|βββββββββ | 500/600 [15:51<02:35, 1.55s/it, loss=0.173, lr=1e-5]10/12/2023 15:02:16 - INFO - accelerate.accelerator - Saving current state to logs/sweep_full_4_20231012144600/checkpoint-500 |
|
Model weights saved in logs/sweep_full_4_20231012144600/checkpoint-500/pytorch_lora_weights.safetensors |
|
10/12/2023 15:02:17 - INFO - accelerate.checkpointing - Optimizer state saved in logs/sweep_full_4_20231012144600/checkpoint-500/optimizer.bin |
|
10/12/2023 15:02:17 - INFO - accelerate.checkpointing - Scheduler state saved in logs/sweep_full_4_20231012144600/checkpoint-500/scheduler.bin |
|
10/12/2023 15:02:17 - INFO - accelerate.checkpointing - Gradient scaler state saved in logs/sweep_full_4_20231012144600/checkpoint-500/scaler.pt |
|
10/12/2023 15:02:17 - INFO - accelerate.checkpointing - Random states saved in logs/sweep_full_4_20231012144600/checkpoint-500/random_states_0.pkl |
|
10/12/2023 15:02:17 - INFO - __main__ - Saved state to logs/sweep_full_4_20231012144600/checkpoint-500 |
|
Steps: 83%|βββββββββ | 500/600 [15:52<02:35, 1.55s/it, loss=0.00523, lr=1e-5]
Steps: 84%|βββββββββ | 501/600 [15:54<03:10, 1.92s/it, loss=0.00523, lr=1e-5]
Steps: 84%|βββββββββ | 501/600 [15:54<03:10, 1.92s/it, loss=0.0977, lr=1e-5]
Steps: 84%|βββββββββ | 502/600 [15:56<02:53, 1.77s/it, loss=0.0977, lr=1e-5]
Steps: 84%|βββββββββ | 502/600 [15:56<02:53, 1.77s/it, loss=0.261, lr=1e-5]
Steps: 84%|βββββββββ | 503/600 [15:57<02:53, 1.79s/it, loss=0.261, lr=1e-5]
Steps: 84%|βββββββββ | 503/600 [15:57<02:53, 1.79s/it, loss=0.107, lr=1e-5]
Steps: 84%|βββββββββ | 504/600 [15:59<02:46, 1.73s/it, loss=0.107, lr=1e-5]
Steps: 84%|βββββββββ | 504/600 [15:59<02:46, 1.73s/it, loss=0.0263, lr=1e-5]
Steps: 84%|βββββββββ | 505/600 [16:00<02:27, 1.55s/it, loss=0.0263, lr=1e-5]
Steps: 84%|βββββββββ | 505/600 [16:00<02:27, 1.55s/it, loss=0.156, lr=1e-5]
Steps: 84%|βββββββββ | 506/600 [16:01<02:03, 1.31s/it, loss=0.156, lr=1e-5]
Steps: 84%|βββββββββ | 506/600 [16:01<02:03, 1.31s/it, loss=0.0112, lr=1e-5]
Steps: 84%|βββββββββ | 507/600 [16:03<02:25, 1.56s/it, loss=0.0112, lr=1e-5]
Steps: 84%|βββββββββ | 507/600 [16:03<02:25, 1.56s/it, loss=0.0207, lr=1e-5]
Steps: 85%|βββββββββ | 508/600 [16:05<02:26, 1.59s/it, loss=0.0207, lr=1e-5]
Steps: 85%|βββββββββ | 508/600 [16:05<02:26, 1.59s/it, loss=0.138, lr=1e-5]
Steps: 85%|βββββββββ | 509/600 [16:06<02:26, 1.60s/it, loss=0.138, lr=1e-5]
Steps: 85%|βββββββββ | 509/600 [16:06<02:26, 1.60s/it, loss=0.146, lr=1e-5]
Steps: 85%|βββββββββ | 510/600 [16:08<02:22, 1.58s/it, loss=0.146, lr=1e-5]
Steps: 85%|βββββββββ | 510/600 [16:08<02:22, 1.58s/it, loss=0.0362, lr=1e-5]
Steps: 85%|βββββββββ | 511/600 [16:09<02:19, 1.57s/it, loss=0.0362, lr=1e-5]
Steps: 85%|βββββββββ | 511/600 [16:09<02:19, 1.57s/it, loss=0.0338, lr=1e-5]
Steps: 85%|βββββββββ | 512/600 [16:11<02:19, 1.59s/it, loss=0.0338, lr=1e-5]
Steps: 85%|βββββββββ | 512/600 [16:11<02:19, 1.59s/it, loss=0.315, lr=1e-5]
Steps: 86%|βββββββββ | 513/600 [16:13<02:22, 1.63s/it, loss=0.315, lr=1e-5]
Steps: 86%|βββββββββ | 513/600 [16:13<02:22, 1.63s/it, loss=0.123, lr=1e-5]
Steps: 86%|βββββββββ | 514/600 [16:14<02:21, 1.65s/it, loss=0.123, lr=1e-5]
Steps: 86%|βββββββββ | 514/600 [16:14<02:21, 1.65s/it, loss=0.00737, lr=1e-5]
Steps: 86%|βββββββββ | 515/600 [16:16<02:20, 1.66s/it, loss=0.00737, lr=1e-5]
Steps: 86%|βββββββββ | 515/600 [16:16<02:20, 1.66s/it, loss=0.189, lr=1e-5]
Steps: 86%|βββββββββ | 516/600 [16:17<02:09, 1.54s/it, loss=0.189, lr=1e-5]
Steps: 86%|βββββββββ | 516/600 [16:17<02:09, 1.54s/it, loss=0.228, lr=1e-5]
Steps: 86%|βββββββββ | 517/600 [16:18<01:48, 1.31s/it, loss=0.228, lr=1e-5]
Steps: 86%|βββββββββ | 517/600 [16:18<01:48, 1.31s/it, loss=0.00354, lr=1e-5]
Steps: 86%|βββββββββ | 518/600 [16:20<02:05, 1.53s/it, loss=0.00354, lr=1e-5]
Steps: 86%|βββββββββ | 518/600 [16:20<02:05, 1.53s/it, loss=0.2, lr=1e-5]
Steps: 86%|βββββββββ | 519/600 [16:22<02:04, 1.54s/it, loss=0.2, lr=1e-5]
Steps: 86%|βββββββββ | 519/600 [16:22<02:04, 1.54s/it, loss=0.15, lr=1e-5]
Steps: 87%|βββββββββ | 520/600 [16:23<02:02, 1.53s/it, loss=0.15, lr=1e-5]
Steps: 87%|βββββββββ | 520/600 [16:23<02:02, 1.53s/it, loss=0.0263, lr=1e-5]
Steps: 87%|βββββββββ | 521/600 [16:25<02:06, 1.60s/it, loss=0.0263, lr=1e-5]
Steps: 87%|βββββββββ | 521/600 [16:25<02:06, 1.60s/it, loss=0.00485, lr=1e-5]
Steps: 87%|βββββββββ | 522/600 [16:27<02:07, 1.64s/it, loss=0.00485, lr=1e-5]
Steps: 87%|βββββββββ | 522/600 [16:27<02:07, 1.64s/it, loss=0.0463, lr=1e-5]
Steps: 87%|βββββββββ | 523/600 [16:29<02:11, 1.71s/it, loss=0.0463, lr=1e-5]
Steps: 87%|βββββββββ | 523/600 [16:29<02:11, 1.71s/it, loss=0.285, lr=1e-5]
Steps: 87%|βββββββββ | 524/600 [16:30<02:05, 1.65s/it, loss=0.285, lr=1e-5]
Steps: 87%|βββββββββ | 524/600 [16:30<02:05, 1.65s/it, loss=0.146, lr=1e-5]
Steps: 88%|βββββββββ | 525/600 [16:32<01:59, 1.60s/it, loss=0.146, lr=1e-5]
Steps: 88%|βββββββββ | 525/600 [16:32<01:59, 1.60s/it, loss=0.0456, lr=1e-5]
Steps: 88%|βββββββββ | 526/600 [16:33<01:56, 1.58s/it, loss=0.0456, lr=1e-5]
Steps: 88%|βββββββββ | 526/600 [16:33<01:56, 1.58s/it, loss=0.0061, lr=1e-5]
Steps: 88%|βββββββββ | 527/600 [16:35<01:51, 1.53s/it, loss=0.0061, lr=1e-5]
Steps: 88%|βββββββββ | 527/600 [16:35<01:51, 1.53s/it, loss=0.0539, lr=1e-5]
Steps: 88%|βββββββββ | 528/600 [16:35<01:33, 1.30s/it, loss=0.0539, lr=1e-5]
Steps: 88%|βββββββββ | 528/600 [16:35<01:33, 1.30s/it, loss=0.331, lr=1e-5]
Steps: 88%|βββββββββ | 529/600 [16:38<01:52, 1.58s/it, loss=0.331, lr=1e-5]
Steps: 88%|βββββββββ | 529/600 [16:38<01:52, 1.58s/it, loss=0.134, lr=1e-5]
Steps: 88%|βββββββββ | 530/600 [16:39<01:49, 1.56s/it, loss=0.134, lr=1e-5]
Steps: 88%|βββββββββ | 530/600 [16:39<01:49, 1.56s/it, loss=0.0219, lr=1e-5]
Steps: 88%|βββββββββ | 531/600 [16:41<01:53, 1.65s/it, loss=0.0219, lr=1e-5]
Steps: 88%|βββββββββ | 531/600 [16:41<01:53, 1.65s/it, loss=0.134, lr=1e-5]
Steps: 89%|βββββββββ | 532/600 [16:43<01:56, 1.71s/it, loss=0.134, lr=1e-5]
Steps: 89%|βββββββββ | 532/600 [16:43<01:56, 1.71s/it, loss=0.146, lr=1e-5]
Steps: 89%|βββββββββ | 533/600 [16:44<01:52, 1.67s/it, loss=0.146, lr=1e-5]
Steps: 89%|βββββββββ | 533/600 [16:44<01:52, 1.67s/it, loss=0.0368, lr=1e-5]
Steps: 89%|βββββββββ | 534/600 [16:46<01:47, 1.62s/it, loss=0.0368, lr=1e-5]
Steps: 89%|βββββββββ | 534/600 [16:46<01:47, 1.62s/it, loss=0.0638, lr=1e-5]
Steps: 89%|βββββββββ | 535/600 [16:47<01:41, 1.56s/it, loss=0.0638, lr=1e-5]
Steps: 89%|βββββββββ | 535/600 [16:47<01:41, 1.56s/it, loss=0.142, lr=1e-5]
Steps: 89%|βββββββββ | 536/600 [16:49<01:44, 1.63s/it, loss=0.142, lr=1e-5]
Steps: 89%|βββββββββ | 536/600 [16:49<01:44, 1.63s/it, loss=0.223, lr=1e-5]
Steps: 90%|βββββββββ | 537/600 [16:50<01:35, 1.51s/it, loss=0.223, lr=1e-5]
Steps: 90%|βββββββββ | 537/600 [16:50<01:35, 1.51s/it, loss=0.106, lr=1e-5]
Steps: 90%|βββββββββ | 538/600 [16:52<01:29, 1.45s/it, loss=0.106, lr=1e-5]
Steps: 90%|βββββββββ | 538/600 [16:52<01:29, 1.45s/it, loss=0.269, lr=1e-5]
Steps: 90%|βββββββββ | 539/600 [16:52<01:15, 1.24s/it, loss=0.269, lr=1e-5]
Steps: 90%|βββββββββ | 539/600 [16:52<01:15, 1.24s/it, loss=0.279, lr=1e-5]
Steps: 90%|βββββββββ | 540/600 [16:54<01:29, 1.49s/it, loss=0.279, lr=1e-5]
Steps: 90%|βββββββββ | 540/600 [16:54<01:29, 1.49s/it, loss=0.0144, lr=1e-5]
Steps: 90%|βββββββββ | 541/600 [16:56<01:32, 1.56s/it, loss=0.0144, lr=1e-5]
Steps: 90%|βββββββββ | 541/600 [16:56<01:32, 1.56s/it, loss=0.0143, lr=1e-5]
Steps: 90%|βββββββββ | 542/600 [16:58<01:32, 1.60s/it, loss=0.0143, lr=1e-5]
Steps: 90%|βββββββββ | 542/600 [16:58<01:32, 1.60s/it, loss=0.0137, lr=1e-5]
Steps: 90%|βββββββββ | 543/600 [17:00<01:34, 1.66s/it, loss=0.0137, lr=1e-5]
Steps: 90%|βββββββββ | 543/600 [17:00<01:34, 1.66s/it, loss=0.0924, lr=1e-5]
Steps: 91%|βββββββββ | 544/600 [17:01<01:27, 1.57s/it, loss=0.0924, lr=1e-5]
Steps: 91%|βββββββββ | 544/600 [17:01<01:27, 1.57s/it, loss=0.0326, lr=1e-5]
Steps: 91%|βββββββββ | 545/600 [17:02<01:25, 1.55s/it, loss=0.0326, lr=1e-5]
Steps: 91%|βββββββββ | 545/600 [17:02<01:25, 1.55s/it, loss=0.244, lr=1e-5]
Steps: 91%|βββββββββ | 546/600 [17:04<01:24, 1.57s/it, loss=0.244, lr=1e-5]
Steps: 91%|βββββββββ | 546/600 [17:04<01:24, 1.57s/it, loss=0.0889, lr=1e-5]
Steps: 91%|βββββββββ | 547/600 [17:06<01:27, 1.65s/it, loss=0.0889, lr=1e-5]
Steps: 91%|βββββββββ | 547/600 [17:06<01:27, 1.65s/it, loss=0.0244, lr=1e-5]
Steps: 91%|ββββββββββ| 548/600 [17:08<01:24, 1.62s/it, loss=0.0244, lr=1e-5]
Steps: 91%|ββββββββββ| 548/600 [17:08<01:24, 1.62s/it, loss=0.0442, lr=1e-5]
Steps: 92%|ββββββββββ| 549/600 [17:09<01:17, 1.52s/it, loss=0.0442, lr=1e-5]
Steps: 92%|ββββββββββ| 549/600 [17:09<01:17, 1.52s/it, loss=0.17, lr=1e-5]
Steps: 92%|ββββββββββ| 550/600 [17:10<01:04, 1.29s/it, loss=0.17, lr=1e-5]
Steps: 92%|ββββββββββ| 550/600 [17:10<01:04, 1.29s/it, loss=0.0453, lr=1e-5]
Steps: 92%|ββββββββββ| 551/600 [17:12<01:19, 1.62s/it, loss=0.0453, lr=1e-5]
Steps: 92%|ββββββββββ| 551/600 [17:12<01:19, 1.62s/it, loss=0.104, lr=1e-5]
Steps: 92%|ββββββββββ| 552/600 [17:14<01:17, 1.62s/it, loss=0.104, lr=1e-5]
Steps: 92%|ββββββββββ| 552/600 [17:14<01:17, 1.62s/it, loss=0.327, lr=1e-5]
Steps: 92%|ββββββββββ| 553/600 [17:15<01:14, 1.58s/it, loss=0.327, lr=1e-5]
Steps: 92%|ββββββββββ| 553/600 [17:15<01:14, 1.58s/it, loss=0.0674, lr=1e-5]
Steps: 92%|ββββββββββ| 554/600 [17:17<01:17, 1.68s/it, loss=0.0674, lr=1e-5]
Steps: 92%|ββββββββββ| 554/600 [17:17<01:17, 1.68s/it, loss=0.159, lr=1e-5]
Steps: 92%|ββββββββββ| 555/600 [17:18<01:13, 1.63s/it, loss=0.159, lr=1e-5]
Steps: 92%|ββββββββββ| 555/600 [17:18<01:13, 1.63s/it, loss=0.131, lr=1e-5]
Steps: 93%|ββββββββββ| 556/600 [17:20<01:10, 1.60s/it, loss=0.131, lr=1e-5]
Steps: 93%|ββββββββββ| 556/600 [17:20<01:10, 1.60s/it, loss=0.0999, lr=1e-5]
Steps: 93%|ββββββββββ| 557/600 [17:22<01:08, 1.59s/it, loss=0.0999, lr=1e-5]
Steps: 93%|ββββββββββ| 557/600 [17:22<01:08, 1.59s/it, loss=0.261, lr=1e-5]
Steps: 93%|ββββββββββ| 558/600 [17:23<01:08, 1.64s/it, loss=0.261, lr=1e-5]
Steps: 93%|ββββββββββ| 558/600 [17:23<01:08, 1.64s/it, loss=0.0776, lr=1e-5]
Steps: 93%|ββββββββββ| 559/600 [17:25<01:06, 1.62s/it, loss=0.0776, lr=1e-5]
Steps: 93%|ββββββββββ| 559/600 [17:25<01:06, 1.62s/it, loss=0.0331, lr=1e-5]
Steps: 93%|ββββββββββ| 560/600 [17:26<00:58, 1.47s/it, loss=0.0331, lr=1e-5]
Steps: 93%|ββββββββββ| 560/600 [17:26<00:58, 1.47s/it, loss=0.0378, lr=1e-5]
Steps: 94%|ββββββββββ| 561/600 [17:27<00:49, 1.26s/it, loss=0.0378, lr=1e-5]
Steps: 94%|ββββββββββ| 561/600 [17:27<00:49, 1.26s/it, loss=0.148, lr=1e-5] 10/12/2023 15:03:51 - 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][ALoaded scheduler as EulerDiscreteScheduler from `scheduler` 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. |
|
Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of stabilityai/stable-diffusion-xl-base-1.0. |
|
|
|
Loading pipeline components...: 100%|ββββββββββ| 7/7 [00:00<00:00, 60.09it/s][A
Loading pipeline components...: 100%|ββββββββββ| 7/7 [00:00<00:00, 59.64it/s] |
|
{'dynamic_thresholding_ratio', 'thresholding', 'lower_order_final', 'variance_type', 'lambda_min_clipped', 'solver_type', 'solver_order', 'algorithm_type'} was not found in config. Values will be initialized to default values. |
|
10/12/2023 15:04:49 - INFO - __main__ - Image features shape: torch.Size([5, 75648]) |
|
10/12/2023 15:05:39 - INFO - __main__ - Image features shape: torch.Size([5, 75648]) |
|
10/12/2023 15:06:29 - INFO - __main__ - Image features shape: torch.Size([5, 75648]) |
|
Steps: 94%|ββββββββββ| 562/600 [20:14<32:21, 51.10s/it, loss=0.148, lr=1e-5]
Steps: 94%|ββββββββββ| 562/600 [20:14<32:21, 51.10s/it, loss=0.223, lr=1e-5]
Steps: 94%|ββββββββββ| 563/600 [20:16<22:20, 36.23s/it, loss=0.223, lr=1e-5]
Steps: 94%|ββββββββββ| 563/600 [20:16<22:20, 36.23s/it, loss=0.014, lr=1e-5]
Steps: 94%|ββββββββββ| 564/600 [20:18<15:34, 25.96s/it, loss=0.014, lr=1e-5]
Steps: 94%|ββββββββββ| 564/600 [20:18<15:34, 25.96s/it, loss=0.0861, lr=1e-5]
Steps: 94%|ββββββββββ| 565/600 [20:19<10:52, 18.63s/it, loss=0.0861, lr=1e-5]
Steps: 94%|ββββββββββ| 565/600 [20:19<10:52, 18.63s/it, loss=0.102, lr=1e-5]
Steps: 94%|ββββββββββ| 566/600 [20:21<07:39, 13.52s/it, loss=0.102, lr=1e-5]
Steps: 94%|ββββββββββ| 566/600 [20:21<07:39, 13.52s/it, loss=0.18, lr=1e-5]
Steps: 94%|ββββββββββ| 567/600 [20:23<05:30, 10.00s/it, loss=0.18, lr=1e-5]
Steps: 94%|ββββββββββ| 567/600 [20:23<05:30, 10.00s/it, loss=0.0471, lr=1e-5]
Steps: 95%|ββββββββββ| 568/600 [20:24<03:57, 7.42s/it, loss=0.0471, lr=1e-5]
Steps: 95%|ββββββββββ| 568/600 [20:24<03:57, 7.42s/it, loss=0.0226, lr=1e-5]
Steps: 95%|ββββββββββ| 569/600 [20:25<02:53, 5.59s/it, loss=0.0226, lr=1e-5]
Steps: 95%|ββββββββββ| 569/600 [20:25<02:53, 5.59s/it, loss=0.165, lr=1e-5]
Steps: 95%|ββββββββββ| 570/600 [20:27<02:10, 4.36s/it, loss=0.165, lr=1e-5]
Steps: 95%|ββββββββββ| 570/600 [20:27<02:10, 4.36s/it, loss=0.138, lr=1e-5]
Steps: 95%|ββββββββββ| 571/600 [20:28<01:41, 3.49s/it, loss=0.138, lr=1e-5]
Steps: 95%|ββββββββββ| 571/600 [20:28<01:41, 3.49s/it, loss=0.179, lr=1e-5]
Steps: 95%|ββββββββββ| 572/600 [20:29<01:14, 2.67s/it, loss=0.179, lr=1e-5]
Steps: 95%|ββββββββββ| 572/600 [20:29<01:14, 2.67s/it, loss=0.00285, lr=1e-5]
Steps: 96%|ββββββββββ| 573/600 [20:31<01:07, 2.49s/it, loss=0.00285, lr=1e-5]
Steps: 96%|ββββββββββ| 573/600 [20:31<01:07, 2.49s/it, loss=0.00285, lr=1e-5]
Steps: 96%|ββββββββββ| 574/600 [20:32<00:55, 2.15s/it, loss=0.00285, lr=1e-5]
Steps: 96%|ββββββββββ| 574/600 [20:32<00:55, 2.15s/it, loss=0.0914, lr=1e-5]
Steps: 96%|ββββββββββ| 575/600 [20:34<00:50, 2.03s/it, loss=0.0914, lr=1e-5]
Steps: 96%|ββββββββββ| 575/600 [20:34<00:50, 2.03s/it, loss=0.00982, lr=1e-5]
Steps: 96%|ββββββββββ| 576/600 [20:36<00:45, 1.91s/it, loss=0.00982, lr=1e-5]
Steps: 96%|ββββββββββ| 576/600 [20:36<00:45, 1.91s/it, loss=0.0492, lr=1e-5]
Steps: 96%|ββββββββββ| 577/600 [20:37<00:41, 1.82s/it, loss=0.0492, lr=1e-5]
Steps: 96%|ββββββββββ| 577/600 [20:37<00:41, 1.82s/it, loss=0.00427, lr=1e-5]
Steps: 96%|ββββββββββ| 578/600 [20:39<00:37, 1.70s/it, loss=0.00427, lr=1e-5]
Steps: 96%|ββββββββββ| 578/600 [20:39<00:37, 1.70s/it, loss=0.336, lr=1e-5]
Steps: 96%|ββββββββββ| 579/600 [20:41<00:35, 1.71s/it, loss=0.336, lr=1e-5]
Steps: 96%|ββββββββββ| 579/600 [20:41<00:35, 1.71s/it, loss=0.0298, lr=1e-5]
Steps: 97%|ββββββββββ| 580/600 [20:42<00:35, 1.76s/it, loss=0.0298, lr=1e-5]
Steps: 97%|ββββββββββ| 580/600 [20:42<00:35, 1.76s/it, loss=0.233, lr=1e-5]
Steps: 97%|ββββββββββ| 581/600 [20:44<00:32, 1.69s/it, loss=0.233, lr=1e-5]
Steps: 97%|ββββββββββ| 581/600 [20:44<00:32, 1.69s/it, loss=0.15, lr=1e-5]
Steps: 97%|ββββββββββ| 582/600 [20:45<00:28, 1.61s/it, loss=0.15, lr=1e-5]
Steps: 97%|ββββββββββ| 582/600 [20:45<00:28, 1.61s/it, loss=0.233, lr=1e-5]
Steps: 97%|ββββββββββ| 583/600 [20:46<00:23, 1.35s/it, loss=0.233, lr=1e-5]
Steps: 97%|ββββββββββ| 583/600 [20:46<00:23, 1.35s/it, loss=0.0953, lr=1e-5]
Steps: 97%|ββββββββββ| 584/600 [20:48<00:25, 1.58s/it, loss=0.0953, lr=1e-5]
Steps: 97%|ββββββββββ| 584/600 [20:48<00:25, 1.58s/it, loss=0.25, lr=1e-5]
Steps: 98%|ββββββββββ| 585/600 [20:50<00:23, 1.54s/it, loss=0.25, lr=1e-5]
Steps: 98%|ββββββββββ| 585/600 [20:50<00:23, 1.54s/it, loss=0.168, lr=1e-5]
Steps: 98%|ββββββββββ| 586/600 [20:51<00:21, 1.56s/it, loss=0.168, lr=1e-5]
Steps: 98%|ββββββββββ| 586/600 [20:51<00:21, 1.56s/it, loss=0.0179, lr=1e-5]
Steps: 98%|ββββββββββ| 587/600 [20:53<00:20, 1.55s/it, loss=0.0179, lr=1e-5]
Steps: 98%|ββββββββββ| 587/600 [20:53<00:20, 1.55s/it, loss=0.151, lr=1e-5]
Steps: 98%|ββββββββββ| 588/600 [20:55<00:19, 1.59s/it, loss=0.151, lr=1e-5]
Steps: 98%|ββββββββββ| 588/600 [20:55<00:19, 1.59s/it, loss=0.114, lr=1e-5]
Steps: 98%|ββββββββββ| 589/600 [20:56<00:18, 1.67s/it, loss=0.114, lr=1e-5]
Steps: 98%|ββββββββββ| 589/600 [20:56<00:18, 1.67s/it, loss=0.017, lr=1e-5]
Steps: 98%|ββββββββββ| 590/600 [20:58<00:16, 1.66s/it, loss=0.017, lr=1e-5]
Steps: 98%|ββββββββββ| 590/600 [20:58<00:16, 1.66s/it, loss=0.0722, lr=1e-5]
Steps: 98%|ββββββββββ| 591/600 [20:59<00:14, 1.58s/it, loss=0.0722, lr=1e-5]
Steps: 98%|ββββββββββ| 591/600 [20:59<00:14, 1.58s/it, loss=0.0304, lr=1e-5]
Steps: 99%|ββββββββββ| 592/600 [21:01<00:13, 1.66s/it, loss=0.0304, lr=1e-5]
Steps: 99%|ββββββββββ| 592/600 [21:01<00:13, 1.66s/it, loss=0.0739, lr=1e-5]
Steps: 99%|ββββββββββ| 593/600 [21:03<00:10, 1.54s/it, loss=0.0739, lr=1e-5]
Steps: 99%|ββββββββββ| 593/600 [21:03<00:10, 1.54s/it, loss=0.188, lr=1e-5]
Steps: 99%|ββββββββββ| 594/600 [21:03<00:07, 1.31s/it, loss=0.188, lr=1e-5]
Steps: 99%|ββββββββββ| 594/600 [21:03<00:07, 1.31s/it, loss=0.00331, lr=1e-5]
Steps: 99%|ββββββββββ| 595/600 [21:05<00:07, 1.56s/it, loss=0.00331, lr=1e-5]
Steps: 99%|ββββββββββ| 595/600 [21:05<00:07, 1.56s/it, loss=0.193, lr=1e-5]
Steps: 99%|ββββββββββ| 596/600 [21:07<00:06, 1.62s/it, loss=0.193, lr=1e-5]
Steps: 99%|ββββββββββ| 596/600 [21:07<00:06, 1.62s/it, loss=0.161, lr=1e-5]
Steps: 100%|ββββββββββ| 597/600 [21:09<00:04, 1.66s/it, loss=0.161, lr=1e-5]
Steps: 100%|ββββββββββ| 597/600 [21:09<00:04, 1.66s/it, loss=0.208, lr=1e-5]
Steps: 100%|ββββββββββ| 598/600 [21:10<00:03, 1.62s/it, loss=0.208, lr=1e-5]
Steps: 100%|ββββββββββ| 598/600 [21:10<00:03, 1.62s/it, loss=0.201, lr=1e-5]
Steps: 100%|ββββββββββ| 599/600 [21:12<00:01, 1.60s/it, loss=0.201, lr=1e-5]
Steps: 100%|ββββββββββ| 599/600 [21:12<00:01, 1.60s/it, loss=0.101, lr=1e-5]
Steps: 100%|ββββββββββ| 600/600 [21:14<00:00, 1.56s/it, loss=0.101, lr=1e-5]
Steps: 100%|ββββββββββ| 600/600 [21:14<00:00, 1.56s/it, loss=0.0761, lr=1e-5]Model weights saved in logs/sweep_full_4_20231012144600/pytorch_lora_weights.safetensors |
|
|
|
Loading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s][A{'dropout', 'attention_type'} was not found in config. Values will be initialized to default values. |
|
Loaded unet as UNet2DConditionModel from `unet` subfolder of stabilityai/stable-diffusion-xl-base-1.0. |
|
|
|
Loading pipeline components...: 14%|ββ | 1/7 [00:02<00:17, 2.93s/it][ALoaded scheduler as EulerDiscreteScheduler from `scheduler` 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. |
|
Loaded text_encoder as CLIPTextModel from `text_encoder` subfolder of stabilityai/stable-diffusion-xl-base-1.0. |
|
|
|
Loading pipeline components...: 71%|ββββββββ | 5/7 [00:03<00:01, 1.93it/s][ALoaded text_encoder_2 as CLIPTextModelWithProjection from `text_encoder_2` subfolder of stabilityai/stable-diffusion-xl-base-1.0. |
|
|
|
Loading pipeline components...: 86%|βββββββββ | 6/7 [00:04<00:00, 1.61it/s][ALoaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of stabilityai/stable-diffusion-xl-base-1.0. |
|
Loading pipeline components...: 100%|ββββββββββ| 7/7 [00:04<00:00, 1.62it/s] |
|
{'dynamic_thresholding_ratio', 'thresholding', 'lower_order_final', 'variance_type', 'lambda_min_clipped', 'solver_type', 'solver_order', 'algorithm_type'} was not found in config. Values will be initialized to default values. |
|
Loading unet. |
|
|
|
0%| | 0/50 [00:00<?, ?it/s][A |
|
2%|β | 1/50 [00:00<00:09, 5.40it/s][A |
|
4%|β | 2/50 [00:00<00:07, 6.25it/s][A |
|
6%|β | 3/50 [00:00<00:08, 5.79it/s][A |
|
8%|β | 4/50 [00:00<00:08, 5.62it/s][A |
|
10%|β | 5/50 [00:00<00:08, 5.51it/s][A |
|
12%|ββ | 6/50 [00:01<00:08, 5.44it/s][A |
|
14%|ββ | 7/50 [00:01<00:07, 5.40it/s][A |
|
16%|ββ | 8/50 [00:01<00:07, 5.38it/s][A |
|
18%|ββ | 9/50 [00:01<00:07, 5.36it/s][A |
|
20%|ββ | 10/50 [00:01<00:07, 5.35it/s][A |
|
22%|βββ | 11/50 [00:02<00:07, 5.34it/s][A |
|
24%|βββ | 12/50 [00:02<00:07, 5.34it/s][A |
|
26%|βββ | 13/50 [00:02<00:06, 5.34it/s][A |
|
28%|βββ | 14/50 [00:02<00:06, 5.32it/s][A |
|
30%|βββ | 15/50 [00:02<00:06, 5.33it/s][A |
|
32%|ββββ | 16/50 [00:02<00:06, 5.33it/s][A |
|
34%|ββββ | 17/50 [00:03<00:06, 5.33it/s][A |
|
36%|ββββ | 18/50 [00:03<00:05, 5.33it/s][A |
|
38%|ββββ | 19/50 [00:03<00:05, 5.32it/s][A |
|
40%|ββββ | 20/50 [00:03<00:05, 5.33it/s][A |
|
42%|βββββ | 21/50 [00:03<00:05, 5.33it/s][A |
|
44%|βββββ | 22/50 [00:04<00:05, 5.33it/s][A |
|
46%|βββββ | 23/50 [00:04<00:05, 5.32it/s][A |
|
48%|βββββ | 24/50 [00:04<00:04, 5.32it/s][A |
|
50%|βββββ | 25/50 [00:04<00:04, 5.33it/s][A |
|
52%|ββββββ | 26/50 [00:04<00:04, 5.32it/s][A |
|
54%|ββββββ | 27/50 [00:05<00:04, 5.32it/s][A |
|
56%|ββββββ | 28/50 [00:05<00:04, 5.32it/s][A |
|
58%|ββββββ | 29/50 [00:05<00:03, 5.31it/s][A |
|
60%|ββββββ | 30/50 [00:05<00:03, 5.31it/s][A |
|
62%|βββββββ | 31/50 [00:05<00:03, 5.31it/s][A |
|
64%|βββββββ | 32/50 [00:05<00:03, 5.31it/s][A |
|
66%|βββββββ | 33/50 [00:06<00:03, 5.31it/s][A |
|
68%|βββββββ | 34/50 [00:06<00:03, 5.31it/s][A |
|
70%|βββββββ | 35/50 [00:06<00:02, 5.31it/s][A |
|
72%|ββββββββ | 36/50 [00:06<00:02, 5.31it/s][A |
|
74%|ββββββββ | 37/50 [00:06<00:02, 5.32it/s][A |
|
76%|ββββββββ | 38/50 [00:07<00:02, 5.32it/s][A |
|
78%|ββββββββ | 39/50 [00:07<00:02, 5.32it/s][A |
|
80%|ββββββββ | 40/50 [00:07<00:01, 5.31it/s][A |
|
82%|βββββββββ | 41/50 [00:07<00:01, 5.30it/s][A |
|
84%|βββββββββ | 42/50 [00:07<00:01, 5.31it/s][A |
|
86%|βββββββββ | 43/50 [00:08<00:01, 5.32it/s][A |
|
88%|βββββββββ | 44/50 [00:08<00:01, 5.31it/s][A |
|
90%|βββββββββ | 45/50 [00:08<00:00, 5.31it/s][A |
|
92%|ββββββββββ| 46/50 [00:08<00:00, 5.31it/s][A |
|
94%|ββββββββββ| 47/50 [00:08<00:00, 5.30it/s][A |
|
96%|ββββββββββ| 48/50 [00:08<00:00, 5.30it/s][A |
|
98%|ββββββββββ| 49/50 [00:09<00:00, 5.31it/s][A |
|
100%|ββββββββββ| 50/50 [00:09<00:00, 5.32it/s][A
100%|ββββββββββ| 50/50 [00:09<00:00, 5.35it/s] |
|
|
|
0%| | 0/50 [00:00<?, ?it/s][A |
|
2%|β | 1/50 [00:00<00:09, 5.40it/s][A |
|
4%|β | 2/50 [00:00<00:07, 6.23it/s][A |
|
6%|β | 3/50 [00:00<00:08, 5.77it/s][A |
|
8%|β | 4/50 [00:00<00:08, 5.58it/s][A |
|
10%|β | 5/50 [00:00<00:08, 5.48it/s][A |
|
12%|ββ | 6/50 [00:01<00:08, 5.42it/s][A |
|
14%|ββ | 7/50 [00:01<00:12, 3.37it/s][A |
|
16%|ββ | 8/50 [00:01<00:10, 3.84it/s][A |
|
18%|ββ | 9/50 [00:01<00:09, 4.21it/s][A |
|
20%|ββ | 10/50 [00:02<00:08, 4.50it/s][A |
|
22%|βββ | 11/50 [00:02<00:08, 4.71it/s][A |
|
24%|βββ | 12/50 [00:02<00:07, 4.88it/s][A |
|
26%|βββ | 13/50 [00:02<00:07, 5.01it/s][A |
|
28%|βββ | 14/50 [00:02<00:07, 5.11it/s][A |
|
30%|βββ | 15/50 [00:03<00:06, 5.17it/s][A |
|
32%|ββββ | 16/50 [00:03<00:06, 5.21it/s][A |
|
34%|ββββ | 17/50 [00:03<00:06, 5.24it/s][A |
|
36%|ββββ | 18/50 [00:03<00:06, 5.26it/s][A |
|
38%|ββββ | 19/50 [00:03<00:05, 5.28it/s][A |
|
40%|ββββ | 20/50 [00:04<00:05, 5.29it/s][A |
|
42%|βββββ | 21/50 [00:04<00:05, 5.29it/s][A |
|
44%|βββββ | 22/50 [00:04<00:05, 5.29it/s][A |
|
46%|βββββ | 23/50 [00:04<00:05, 5.29it/s][A |
|
48%|βββββ | 24/50 [00:04<00:04, 5.29it/s][A |
|
50%|βββββ | 25/50 [00:04<00:04, 5.29it/s][A |
|
52%|ββββββ | 26/50 [00:05<00:04, 5.30it/s][A |
|
54%|ββββββ | 27/50 [00:05<00:04, 5.29it/s][A |
|
56%|ββββββ | 28/50 [00:05<00:04, 5.29it/s][A |
|
58%|ββββββ | 29/50 [00:05<00:03, 5.29it/s][A |
|
60%|ββββββ | 30/50 [00:05<00:03, 5.29it/s][A |
|
62%|βββββββ | 31/50 [00:06<00:03, 5.29it/s][A |
|
64%|βββββββ | 32/50 [00:06<00:03, 5.29it/s][A |
|
66%|βββββββ | 33/50 [00:06<00:03, 5.28it/s][A |
|
68%|βββββββ | 34/50 [00:06<00:03, 5.29it/s][A |
|
70%|βββββββ | 35/50 [00:06<00:02, 5.29it/s][A |
|
72%|ββββββββ | 36/50 [00:07<00:02, 5.30it/s][A |
|
74%|ββββββββ | 37/50 [00:07<00:02, 5.29it/s][A |
|
76%|ββββββββ | 38/50 [00:07<00:02, 5.30it/s][A |
|
78%|ββββββββ | 39/50 [00:07<00:02, 5.30it/s][A |
|
80%|ββββββββ | 40/50 [00:07<00:01, 5.29it/s][A |
|
82%|βββββββββ | 41/50 [00:08<00:01, 5.30it/s][A |
|
84%|βββββββββ | 42/50 [00:08<00:01, 5.29it/s][A |
|
86%|βββββββββ | 43/50 [00:08<00:01, 5.29it/s][A |
|
88%|βββββββββ | 44/50 [00:08<00:01, 5.30it/s][A |
|
90%|βββββββββ | 45/50 [00:08<00:00, 5.30it/s][A |
|
92%|ββββββββββ| 46/50 [00:08<00:00, 5.29it/s][A |
|
94%|ββββββββββ| 47/50 [00:09<00:00, 5.30it/s][A |
|
96%|ββββββββββ| 48/50 [00:09<00:00, 5.30it/s][A |
|
98%|ββββββββββ| 49/50 [00:09<00:00, 5.30it/s][A |
|
100%|ββββββββββ| 50/50 [00:09<00:00, 5.30it/s][A
100%|ββββββββββ| 50/50 [00:09<00:00, 5.14it/s] |
|
|
|
0%| | 0/50 [00:00<?, ?it/s][A |
|
2%|β | 1/50 [00:00<00:09, 5.39it/s][A |
|
4%|β | 2/50 [00:00<00:07, 6.20it/s][A |
|
6%|β | 3/50 [00:00<00:08, 5.75it/s][A |
|
8%|β | 4/50 [00:00<00:08, 5.50it/s][A |
|
10%|β | 5/50 [00:00<00:08, 5.49it/s][A |
|
12%|ββ | 6/50 [00:01<00:08, 5.42it/s][A |
|
14%|ββ | 7/50 [00:01<00:07, 5.38it/s][A |
|
16%|ββ | 8/50 [00:01<00:07, 5.36it/s][A |
|
18%|ββ | 9/50 [00:01<00:07, 5.34it/s][A |
|
20%|ββ | 10/50 [00:01<00:07, 5.33it/s][A |
|
22%|βββ | 11/50 [00:02<00:07, 5.32it/s][A |
|
24%|βββ | 12/50 [00:02<00:07, 5.32it/s][A |
|
26%|βββ | 13/50 [00:02<00:06, 5.31it/s][A |
|
28%|βββ | 14/50 [00:02<00:06, 5.29it/s][A |
|
30%|βββ | 15/50 [00:02<00:06, 5.30it/s][A |
|
32%|ββββ | 16/50 [00:02<00:06, 5.29it/s][A |
|
34%|ββββ | 17/50 [00:03<00:06, 5.29it/s][A |
|
36%|ββββ | 18/50 [00:03<00:06, 5.29it/s][A |
|
38%|ββββ | 19/50 [00:03<00:05, 5.29it/s][A |
|
40%|ββββ | 20/50 [00:03<00:05, 5.29it/s][A |
|
42%|βββββ | 21/50 [00:03<00:05, 5.29it/s][A |
|
44%|βββββ | 22/50 [00:04<00:05, 5.29it/s][A |
|
46%|βββββ | 23/50 [00:04<00:05, 5.30it/s][A |
|
48%|βββββ | 24/50 [00:04<00:04, 5.29it/s][A |
|
50%|βββββ | 25/50 [00:04<00:04, 5.28it/s][A |
|
52%|ββββββ | 26/50 [00:04<00:04, 5.28it/s][A |
|
54%|ββββββ | 27/50 [00:05<00:04, 5.28it/s][A |
|
56%|ββββββ | 28/50 [00:05<00:04, 5.28it/s][A |
|
58%|ββββββ | 29/50 [00:05<00:03, 5.28it/s][A |
|
60%|ββββββ | 30/50 [00:05<00:03, 5.24it/s][A |
|
62%|βββββββ | 31/50 [00:05<00:03, 5.28it/s][A |
|
64%|βββββββ | 32/50 [00:06<00:03, 5.31it/s][A |
|
66%|βββββββ | 33/50 [00:06<00:03, 5.31it/s][A |
|
68%|βββββββ | 34/50 [00:06<00:03, 5.31it/s][A |
|
70%|βββββββ | 35/50 [00:06<00:02, 5.31it/s][A |
|
72%|ββββββββ | 36/50 [00:06<00:02, 5.30it/s][A |
|
74%|ββββββββ | 37/50 [00:06<00:02, 5.30it/s][A |
|
76%|ββββββββ | 38/50 [00:07<00:02, 5.29it/s][A |
|
78%|ββββββββ | 39/50 [00:07<00:02, 5.30it/s][A |
|
80%|ββββββββ | 40/50 [00:07<00:01, 5.29it/s][A |
|
82%|βββββββββ | 41/50 [00:07<00:01, 5.30it/s][A |
|
84%|βββββββββ | 42/50 [00:07<00:01, 5.31it/s][A |
|
86%|βββββββββ | 43/50 [00:08<00:01, 5.31it/s][A |
|
88%|βββββββββ | 44/50 [00:08<00:01, 5.29it/s][A |
|
90%|βββββββββ | 45/50 [00:08<00:00, 5.24it/s][A |
|
92%|ββββββββββ| 46/50 [00:08<00:00, 5.30it/s][A |
|
94%|ββββββββββ| 47/50 [00:08<00:00, 5.21it/s][A |
|
96%|ββββββββββ| 48/50 [00:09<00:00, 5.31it/s][A |
|
98%|ββββββββββ| 49/50 [00:09<00:00, 5.31it/s][A |
|
100%|ββββββββββ| 50/50 [00:09<00:00, 5.30it/s][A
100%|ββββββββββ| 50/50 [00:09<00:00, 5.32it/s] |
|
|
|
0%| | 0/50 [00:00<?, ?it/s][A |
|
2%|β | 1/50 [00:00<00:09, 5.39it/s][A |
|
4%|β | 2/50 [00:00<00:07, 6.22it/s][A |
|
6%|β | 3/50 [00:00<00:08, 5.77it/s][A |
|
8%|β | 4/50 [00:00<00:08, 5.58it/s][A |
|
10%|β | 5/50 [00:00<00:08, 5.48it/s][A |
|
12%|ββ | 6/50 [00:01<00:08, 5.41it/s][A |
|
14%|ββ | 7/50 [00:01<00:08, 5.37it/s][A |
|
16%|ββ | 8/50 [00:01<00:07, 5.34it/s][A |
|
18%|ββ | 9/50 [00:01<00:07, 5.33it/s][A |
|
20%|ββ | 10/50 [00:01<00:07, 5.31it/s][A |
|
22%|βββ | 11/50 [00:02<00:07, 5.31it/s][A |
|
24%|βββ | 12/50 [00:02<00:07, 5.31it/s][A |
|
26%|βββ | 13/50 [00:02<00:06, 5.31it/s][A |
|
28%|βββ | 14/50 [00:02<00:06, 5.30it/s][A |
|
30%|βββ | 15/50 [00:02<00:06, 5.29it/s][A |
|
32%|ββββ | 16/50 [00:02<00:06, 5.28it/s][A |
|
34%|ββββ | 17/50 [00:03<00:06, 5.28it/s][A |
|
36%|ββββ | 18/50 [00:03<00:06, 5.30it/s][A |
|
38%|ββββ | 19/50 [00:03<00:05, 5.29it/s][A |
|
40%|ββββ | 20/50 [00:03<00:05, 5.30it/s][A |
|
42%|βββββ | 21/50 [00:03<00:05, 5.29it/s][A |
|
44%|βββββ | 22/50 [00:04<00:05, 5.29it/s][A |
|
46%|βββββ | 23/50 [00:04<00:05, 5.29it/s][A |
|
48%|βββββ | 24/50 [00:04<00:04, 5.29it/s][A |
|
50%|βββββ | 25/50 [00:04<00:04, 5.29it/s][A |
|
52%|ββββββ | 26/50 [00:04<00:04, 5.29it/s][A |
|
54%|ββββββ | 27/50 [00:05<00:04, 5.29it/s][A |
|
56%|ββββββ | 28/50 [00:05<00:04, 5.28it/s][A |
|
58%|ββββββ | 29/50 [00:05<00:03, 5.29it/s][A |
|
60%|ββββββ | 30/50 [00:05<00:03, 5.29it/s][A |
|
62%|βββββββ | 31/50 [00:05<00:03, 5.29it/s][A |
|
64%|βββββββ | 32/50 [00:05<00:03, 5.29it/s][A |
|
66%|βββββββ | 33/50 [00:06<00:03, 5.29it/s][A |
|
68%|βββββββ | 34/50 [00:06<00:03, 5.30it/s][A |
|
70%|βββββββ | 35/50 [00:06<00:02, 5.29it/s][A |
|
72%|ββββββββ | 36/50 [00:06<00:02, 5.30it/s][A |
|
74%|ββββββββ | 37/50 [00:06<00:02, 5.29it/s][A |
|
76%|ββββββββ | 38/50 [00:07<00:02, 5.24it/s][A |
|
78%|ββββββββ | 39/50 [00:07<00:02, 5.30it/s][A |
|
80%|ββββββββ | 40/50 [00:07<00:01, 5.29it/s][A |
|
82%|βββββββββ | 41/50 [00:07<00:01, 5.30it/s][A |
|
84%|βββββββββ | 42/50 [00:07<00:01, 5.30it/s][A |
|
86%|βββββββββ | 43/50 [00:08<00:01, 5.28it/s][A |
|
88%|βββββββββ | 44/50 [00:08<00:01, 5.29it/s][A |
|
90%|βββββββββ | 45/50 [00:08<00:00, 5.29it/s][A |
|
92%|ββββββββββ| 46/50 [00:08<00:00, 5.29it/s][A |
|
94%|ββββββββββ| 47/50 [00:08<00:00, 5.29it/s][A |
|
96%|ββββββββββ| 48/50 [00:09<00:00, 5.30it/s][A |
|
98%|ββββββββββ| 49/50 [00:09<00:00, 5.28it/s][A |
|
100%|ββββββββββ| 50/50 [00:09<00:00, 5.28it/s][A
100%|ββββββββββ| 50/50 [00:09<00:00, 5.32it/s] |
|
10/12/2023 15:08:35 - INFO - __main__ - Image features shape: torch.Size([5, 75648]) |
|
|
|
0%| | 0/50 [00:00<?, ?it/s][A |
|
2%|β | 1/50 [00:00<00:09, 5.42it/s][A |
|
4%|β | 2/50 [00:00<00:07, 6.24it/s][A |
|
6%|β | 3/50 [00:00<00:08, 5.78it/s][A |
|
8%|β | 4/50 [00:00<00:08, 5.59it/s][A |
|
10%|β | 5/50 [00:00<00:08, 5.49it/s][A |
|
12%|ββ | 6/50 [00:01<00:08, 5.41it/s][A |
|
14%|ββ | 7/50 [00:01<00:08, 5.37it/s][A |
|
16%|ββ | 8/50 [00:01<00:07, 5.36it/s][A |
|
18%|ββ | 9/50 [00:01<00:07, 5.33it/s][A |
|
20%|ββ | 10/50 [00:01<00:07, 5.35it/s][A |
|
22%|βββ | 11/50 [00:02<00:07, 5.33it/s][A |
|
24%|βββ | 12/50 [00:02<00:07, 5.33it/s][A |
|
26%|βββ | 13/50 [00:02<00:06, 5.33it/s][A |
|
28%|βββ | 14/50 [00:02<00:06, 5.33it/s][A |
|
30%|βββ | 15/50 [00:02<00:06, 5.33it/s][A |
|
32%|ββββ | 16/50 [00:02<00:06, 5.33it/s][A |
|
34%|ββββ | 17/50 [00:03<00:06, 5.32it/s][A |
|
36%|ββββ | 18/50 [00:03<00:06, 5.31it/s][A |
|
38%|ββββ | 19/50 [00:03<00:05, 5.31it/s][A |
|
40%|ββββ | 20/50 [00:03<00:05, 5.31it/s][A |
|
42%|βββββ | 21/50 [00:03<00:05, 5.30it/s][A |
|
44%|βββββ | 22/50 [00:04<00:05, 5.31it/s][A |
|
46%|βββββ | 23/50 [00:04<00:05, 5.31it/s][A |
|
48%|βββββ | 24/50 [00:04<00:04, 5.31it/s][A |
|
50%|βββββ | 25/50 [00:04<00:04, 5.31it/s][A |
|
52%|ββββββ | 26/50 [00:04<00:04, 5.31it/s][A |
|
54%|ββββββ | 27/50 [00:05<00:04, 5.30it/s][A |
|
56%|ββββββ | 28/50 [00:05<00:04, 5.31it/s][A |
|
58%|ββββββ | 29/50 [00:05<00:03, 5.31it/s][A |
|
60%|ββββββ | 30/50 [00:05<00:03, 5.30it/s][A |
|
62%|βββββββ | 31/50 [00:05<00:03, 5.31it/s][A |
|
64%|βββββββ | 32/50 [00:05<00:03, 5.31it/s][A |
|
66%|βββββββ | 33/50 [00:06<00:03, 5.30it/s][A |
|
68%|βββββββ | 34/50 [00:06<00:03, 5.29it/s][A |
|
70%|βββββββ | 35/50 [00:06<00:02, 5.32it/s][A |
|
72%|ββββββββ | 36/50 [00:06<00:02, 5.31it/s][A |
|
74%|ββββββββ | 37/50 [00:06<00:02, 5.31it/s][A |
|
76%|ββββββββ | 38/50 [00:07<00:02, 5.29it/s][A |
|
78%|ββββββββ | 39/50 [00:07<00:02, 5.27it/s][A |
|
80%|ββββββββ | 40/50 [00:07<00:01, 5.31it/s][A |
|
82%|βββββββββ | 41/50 [00:07<00:01, 5.31it/s][A |
|
84%|βββββββββ | 42/50 [00:07<00:01, 5.30it/s][A |
|
86%|βββββββββ | 43/50 [00:08<00:01, 5.30it/s][A |
|
88%|βββββββββ | 44/50 [00:08<00:01, 5.30it/s][A |
|
90%|βββββββββ | 45/50 [00:08<00:00, 5.29it/s][A |
|
92%|ββββββββββ| 46/50 [00:08<00:00, 5.29it/s][A |
|
94%|ββββββββββ| 47/50 [00:08<00:00, 5.29it/s][A |
|
96%|ββββββββββ| 48/50 [00:08<00:00, 5.29it/s][A |
|
98%|ββββββββββ| 49/50 [00:09<00:00, 5.28it/s][A |
|
100%|ββββββββββ| 50/50 [00:09<00:00, 5.29it/s][A
100%|ββββββββββ| 50/50 [00:09<00:00, 5.33it/s] |
|
|
|
0%| | 0/50 [00:00<?, ?it/s][A |
|
2%|β | 1/50 [00:00<00:09, 5.39it/s][A |
|
4%|β | 2/50 [00:00<00:07, 6.21it/s][A |
|
6%|β | 3/50 [00:00<00:08, 5.75it/s][A |
|
8%|β | 4/50 [00:00<00:08, 5.56it/s][A |
|
10%|β | 5/50 [00:00<00:08, 5.48it/s][A |
|
12%|ββ | 6/50 [00:01<00:08, 5.38it/s][A |
|
14%|ββ | 7/50 [00:01<00:08, 5.35it/s][A |
|
16%|ββ | 8/50 [00:01<00:07, 5.33it/s][A |
|
18%|ββ | 9/50 [00:01<00:07, 5.32it/s][A |
|
20%|ββ | 10/50 [00:01<00:07, 5.32it/s][A |
|
22%|βββ | 11/50 [00:02<00:07, 5.30it/s][A |
|
24%|βββ | 12/50 [00:02<00:07, 5.30it/s][A |
|
26%|βββ | 13/50 [00:02<00:06, 5.29it/s][A |
|
28%|βββ | 14/50 [00:02<00:06, 5.29it/s][A |
|
30%|βββ | 15/50 [00:02<00:06, 5.28it/s][A |
|
32%|ββββ | 16/50 [00:02<00:06, 5.28it/s][A |
|
34%|ββββ | 17/50 [00:03<00:06, 5.28it/s][A |
|
36%|ββββ | 18/50 [00:03<00:06, 5.28it/s][A |
|
38%|ββββ | 19/50 [00:03<00:05, 5.27it/s][A |
|
40%|ββββ | 20/50 [00:03<00:05, 5.28it/s][A |
|
42%|βββββ | 21/50 [00:03<00:05, 5.28it/s][A |
|
44%|βββββ | 22/50 [00:04<00:05, 5.29it/s][A |
|
46%|βββββ | 23/50 [00:04<00:05, 5.29it/s][A |
|
48%|βββββ | 24/50 [00:04<00:04, 5.28it/s][A |
|
50%|βββββ | 25/50 [00:04<00:04, 5.29it/s][A |
|
52%|ββββββ | 26/50 [00:04<00:04, 5.28it/s][A |
|
54%|ββββββ | 27/50 [00:05<00:04, 5.28it/s][A |
|
56%|ββββββ | 28/50 [00:05<00:04, 5.29it/s][A |
|
58%|ββββββ | 29/50 [00:05<00:03, 5.29it/s][A |
|
60%|ββββββ | 30/50 [00:05<00:03, 5.30it/s][A |
|
62%|βββββββ | 31/50 [00:05<00:03, 5.30it/s][A |
|
64%|βββββββ | 32/50 [00:06<00:03, 5.29it/s][A |
|
66%|βββββββ | 33/50 [00:06<00:03, 5.29it/s][A |
|
68%|βββββββ | 34/50 [00:06<00:03, 5.28it/s][A |
|
70%|βββββββ | 35/50 [00:06<00:02, 5.29it/s][A |
|
72%|ββββββββ | 36/50 [00:06<00:02, 5.29it/s][A |
|
74%|ββββββββ | 37/50 [00:06<00:02, 5.28it/s][A |
|
76%|ββββββββ | 38/50 [00:07<00:02, 5.27it/s][A |
|
78%|ββββββββ | 39/50 [00:07<00:02, 5.28it/s][A |
|
80%|ββββββββ | 40/50 [00:07<00:01, 5.29it/s][A |
|
82%|βββββββββ | 41/50 [00:07<00:01, 5.29it/s][A |
|
84%|βββββββββ | 42/50 [00:07<00:01, 5.28it/s][A |
|
86%|βββββββββ | 43/50 [00:08<00:01, 5.27it/s][A |
|
88%|βββββββββ | 44/50 [00:08<00:01, 5.27it/s][A |
|
90%|βββββββββ | 45/50 [00:08<00:00, 5.27it/s][A |
|
92%|ββββββββββ| 46/50 [00:08<00:00, 5.28it/s][A |
|
94%|ββββββββββ| 47/50 [00:08<00:00, 5.27it/s][A |
|
96%|ββββββββββ| 48/50 [00:09<00:00, 5.28it/s][A |
|
98%|ββββββββββ| 49/50 [00:09<00:00, 5.27it/s][A |
|
100%|ββββββββββ| 50/50 [00:09<00:00, 5.27it/s][A
100%|ββββββββββ| 50/50 [00:09<00:00, 5.31it/s] |
|
|
|
0%| | 0/50 [00:00<?, ?it/s][A |
|
2%|β | 1/50 [00:00<00:09, 5.38it/s][A |
|
4%|β | 2/50 [00:00<00:07, 6.18it/s][A |
|
6%|β | 3/50 [00:00<00:08, 5.73it/s][A |
|
8%|β | 4/50 [00:00<00:08, 5.56it/s][A |
|
10%|β | 5/50 [00:00<00:08, 5.46it/s][A |
|
12%|ββ | 6/50 [00:01<00:08, 5.41it/s][A |
|
14%|ββ | 7/50 [00:01<00:08, 5.37it/s][A |
|
16%|ββ | 8/50 [00:01<00:07, 5.34it/s][A |
|
18%|ββ | 9/50 [00:01<00:07, 5.33it/s][A |
|
20%|ββ | 10/50 [00:01<00:07, 5.32it/s][A |
|
22%|βββ | 11/50 [00:02<00:07, 5.27it/s][A |
|
24%|βββ | 12/50 [00:02<00:07, 5.31it/s][A |
|
26%|βββ | 13/50 [00:02<00:06, 5.31it/s][A |
|
28%|βββ | 14/50 [00:02<00:06, 5.31it/s][A |
|
30%|βββ | 15/50 [00:02<00:06, 5.29it/s][A |
|
32%|ββββ | 16/50 [00:02<00:06, 5.29it/s][A |
|
34%|ββββ | 17/50 [00:03<00:06, 5.28it/s][A |
|
36%|ββββ | 18/50 [00:03<00:06, 5.29it/s][A |
|
38%|ββββ | 19/50 [00:03<00:05, 5.29it/s][A |
|
40%|ββββ | 20/50 [00:03<00:05, 5.29it/s][A |
|
42%|βββββ | 21/50 [00:03<00:05, 5.28it/s][A |
|
44%|βββββ | 22/50 [00:04<00:05, 5.28it/s][A |
|
46%|βββββ | 23/50 [00:04<00:05, 5.28it/s][A |
|
48%|βββββ | 24/50 [00:04<00:04, 5.27it/s][A |
|
50%|βββββ | 25/50 [00:04<00:04, 5.28it/s][A |
|
52%|ββββββ | 26/50 [00:04<00:04, 5.27it/s][A |
|
54%|ββββββ | 27/50 [00:05<00:04, 5.28it/s][A |
|
56%|ββββββ | 28/50 [00:05<00:04, 5.29it/s][A |
|
58%|ββββββ | 29/50 [00:05<00:03, 5.28it/s][A |
|
60%|ββββββ | 30/50 [00:05<00:03, 5.28it/s][A |
|
62%|βββββββ | 31/50 [00:05<00:03, 5.29it/s][A |
|
64%|βββββββ | 32/50 [00:06<00:03, 5.28it/s][A |
|
66%|βββββββ | 33/50 [00:06<00:03, 5.29it/s][A |
|
68%|βββββββ | 34/50 [00:06<00:03, 5.28it/s][A |
|
70%|βββββββ | 35/50 [00:06<00:02, 5.29it/s][A |
|
72%|ββββββββ | 36/50 [00:06<00:02, 5.29it/s][A |
|
74%|ββββββββ | 37/50 [00:06<00:02, 5.28it/s][A |
|
76%|ββββββββ | 38/50 [00:07<00:02, 5.28it/s][A |
|
78%|ββββββββ | 39/50 [00:07<00:02, 5.28it/s][A |
|
80%|ββββββββ | 40/50 [00:07<00:01, 5.28it/s][A |
|
82%|βββββββββ | 41/50 [00:07<00:01, 5.28it/s][A |
|
84%|βββββββββ | 42/50 [00:07<00:01, 5.28it/s][A |
|
86%|βββββββββ | 43/50 [00:08<00:01, 5.28it/s][A |
|
88%|βββββββββ | 44/50 [00:08<00:01, 5.29it/s][A |
|
90%|βββββββββ | 45/50 [00:08<00:00, 5.28it/s][A |
|
92%|ββββββββββ| 46/50 [00:08<00:00, 5.29it/s][A |
|
94%|ββββββββββ| 47/50 [00:08<00:00, 5.28it/s][A |
|
96%|ββββββββββ| 48/50 [00:09<00:00, 5.27it/s][A |
|
98%|ββββββββββ| 49/50 [00:09<00:00, 5.27it/s][A |
|
100%|ββββββββββ| 50/50 [00:09<00:00, 5.28it/s][A
100%|ββββββββββ| 50/50 [00:09<00:00, 5.31it/s] |
|
|
|
0%| | 0/50 [00:00<?, ?it/s][A |
|
2%|β | 1/50 [00:00<00:09, 5.38it/s][A |
|
4%|β | 2/50 [00:00<00:07, 6.18it/s][A |
|
6%|β | 3/50 [00:00<00:08, 5.72it/s][A |
|
8%|β | 4/50 [00:00<00:08, 5.54it/s][A |
|
10%|β | 5/50 [00:00<00:08, 5.44it/s][A |
|
12%|ββ | 6/50 [00:01<00:08, 5.38it/s][A |
|
14%|ββ | 7/50 [00:01<00:08, 5.34it/s][A |
|
16%|ββ | 8/50 [00:01<00:07, 5.32it/s][A |
|
18%|ββ | 9/50 [00:01<00:07, 5.29it/s][A |
|
20%|ββ | 10/50 [00:01<00:07, 5.29it/s][A |
|
22%|βββ | 11/50 [00:02<00:07, 5.30it/s][A |
|
24%|βββ | 12/50 [00:02<00:07, 5.29it/s][A |
|
26%|βββ | 13/50 [00:02<00:07, 5.28it/s][A |
|
28%|βββ | 14/50 [00:02<00:06, 5.28it/s][A |
|
30%|βββ | 15/50 [00:02<00:06, 5.27it/s][A |
|
32%|ββββ | 16/50 [00:02<00:06, 5.27it/s][A |
|
34%|ββββ | 17/50 [00:03<00:06, 5.27it/s][A |
|
36%|ββββ | 18/50 [00:03<00:06, 5.28it/s][A |
|
38%|ββββ | 19/50 [00:03<00:05, 5.28it/s][A |
|
40%|ββββ | 20/50 [00:03<00:05, 5.27it/s][A |
|
42%|βββββ | 21/50 [00:03<00:05, 5.28it/s][A |
|
44%|βββββ | 22/50 [00:04<00:05, 5.28it/s][A |
|
46%|βββββ | 23/50 [00:04<00:05, 5.28it/s][A |
|
48%|βββββ | 24/50 [00:04<00:04, 5.29it/s][A |
|
50%|βββββ | 25/50 [00:04<00:04, 5.29it/s][A |
|
52%|ββββββ | 26/50 [00:04<00:04, 5.29it/s][A |
|
54%|ββββββ | 27/50 [00:05<00:04, 5.29it/s][A |
|
56%|ββββββ | 28/50 [00:05<00:04, 5.27it/s][A |
|
58%|ββββββ | 29/50 [00:05<00:03, 5.28it/s][A |
|
60%|ββββββ | 30/50 [00:05<00:03, 5.28it/s][A |
|
62%|βββββββ | 31/50 [00:06<00:04, 4.00it/s][A |
|
64%|βββββββ | 32/50 [00:06<00:04, 4.32it/s][A |
|
66%|βββββββ | 33/50 [00:06<00:03, 4.57it/s][A |
|
68%|βββββββ | 34/50 [00:06<00:03, 4.76it/s][A |
|
70%|βββββββ | 35/50 [00:06<00:03, 4.91it/s][A |
|
72%|ββββββββ | 36/50 [00:06<00:02, 5.02it/s][A |
|
74%|ββββββββ | 37/50 [00:07<00:02, 5.09it/s][A |
|
76%|ββββββββ | 38/50 [00:07<00:02, 5.15it/s][A |
|
78%|ββββββββ | 39/50 [00:07<00:02, 5.19it/s][A |
|
80%|ββββββββ | 40/50 [00:07<00:01, 5.22it/s][A |
|
82%|βββββββββ | 41/50 [00:07<00:01, 5.23it/s][A |
|
84%|βββββββββ | 42/50 [00:08<00:01, 5.25it/s][A |
|
86%|βββββββββ | 43/50 [00:08<00:01, 5.25it/s][A |
|
88%|βββββββββ | 44/50 [00:08<00:01, 5.27it/s][A |
|
90%|βββββββββ | 45/50 [00:08<00:00, 5.26it/s][A |
|
92%|ββββββββββ| 46/50 [00:08<00:00, 5.27it/s][A |
|
94%|ββββββββββ| 47/50 [00:09<00:00, 5.27it/s][A |
|
96%|ββββββββββ| 48/50 [00:09<00:00, 5.28it/s][A |
|
98%|ββββββββββ| 49/50 [00:09<00:00, 5.26it/s][A |
|
100%|ββββββββββ| 50/50 [00:09<00:00, 5.27it/s][A
100%|ββββββββββ| 50/50 [00:09<00:00, 5.19it/s] |
|
10/12/2023 15:09:25 - INFO - __main__ - Image features shape: torch.Size([5, 75648]) |
|
|
|
0%| | 0/50 [00:00<?, ?it/s][A |
|
2%|β | 1/50 [00:00<00:09, 5.41it/s][A |
|
4%|β | 2/50 [00:00<00:07, 6.23it/s][A |
|
6%|β | 3/50 [00:00<00:08, 5.78it/s][A |
|
8%|β | 4/50 [00:00<00:08, 5.59it/s][A |
|
10%|β | 5/50 [00:00<00:08, 5.49it/s][A |
|
12%|ββ | 6/50 [00:01<00:08, 5.42it/s][A |
|
14%|ββ | 7/50 [00:01<00:07, 5.38it/s][A |
|
16%|ββ | 8/50 [00:01<00:07, 5.35it/s][A |
|
18%|ββ | 9/50 [00:01<00:07, 5.33it/s][A |
|
20%|ββ | 10/50 [00:01<00:07, 5.32it/s][A |
|
22%|βββ | 11/50 [00:02<00:07, 5.32it/s][A |
|
24%|βββ | 12/50 [00:02<00:07, 5.32it/s][A |
|
26%|βββ | 13/50 [00:02<00:06, 5.32it/s][A |
|
28%|βββ | 14/50 [00:02<00:06, 5.30it/s][A |
|
30%|βββ | 15/50 [00:02<00:06, 5.31it/s][A |
|
32%|ββββ | 16/50 [00:02<00:06, 5.30it/s][A |
|
34%|ββββ | 17/50 [00:03<00:06, 5.30it/s][A |
|
36%|ββββ | 18/50 [00:03<00:06, 5.30it/s][A |
|
38%|ββββ | 19/50 [00:03<00:05, 5.31it/s][A |
|
40%|ββββ | 20/50 [00:03<00:05, 5.32it/s][A |
|
42%|βββββ | 21/50 [00:03<00:05, 5.30it/s][A |
|
44%|βββββ | 22/50 [00:04<00:05, 5.30it/s][A |
|
46%|βββββ | 23/50 [00:04<00:05, 5.29it/s][A |
|
48%|βββββ | 24/50 [00:04<00:04, 5.30it/s][A |
|
50%|βββββ | 25/50 [00:04<00:04, 5.29it/s][A |
|
52%|ββββββ | 26/50 [00:04<00:04, 5.29it/s][A |
|
54%|ββββββ | 27/50 [00:05<00:04, 5.30it/s][A |
|
56%|ββββββ | 28/50 [00:05<00:04, 5.30it/s][A |
|
58%|ββββββ | 29/50 [00:05<00:03, 5.30it/s][A |
|
60%|ββββββ | 30/50 [00:05<00:03, 5.30it/s][A |
|
62%|βββββββ | 31/50 [00:05<00:03, 5.29it/s][A |
|
64%|βββββββ | 32/50 [00:05<00:03, 5.30it/s][A |
|
66%|βββββββ | 33/50 [00:06<00:03, 5.30it/s][A |
|
68%|βββββββ | 34/50 [00:06<00:03, 5.30it/s][A |
|
70%|βββββββ | 35/50 [00:06<00:02, 5.31it/s][A |
|
72%|ββββββββ | 36/50 [00:06<00:02, 5.30it/s][A |
|
74%|ββββββββ | 37/50 [00:06<00:02, 5.30it/s][A |
|
76%|ββββββββ | 38/50 [00:07<00:02, 5.31it/s][A |
|
78%|ββββββββ | 39/50 [00:07<00:02, 5.31it/s][A |
|
80%|ββββββββ | 40/50 [00:07<00:01, 5.30it/s][A |
|
82%|βββββββββ | 41/50 [00:07<00:01, 5.31it/s][A |
|
84%|βββββββββ | 42/50 [00:07<00:01, 5.31it/s][A |
|
86%|βββββββββ | 43/50 [00:08<00:01, 5.30it/s][A |
|
88%|βββββββββ | 44/50 [00:08<00:01, 5.31it/s][A |
|
90%|βββββββββ | 45/50 [00:08<00:00, 5.30it/s][A |
|
92%|ββββββββββ| 46/50 [00:08<00:00, 5.31it/s][A |
|
94%|ββββββββββ| 47/50 [00:08<00:00, 5.30it/s][A |
|
96%|ββββββββββ| 48/50 [00:09<00:00, 5.31it/s][A |
|
98%|ββββββββββ| 49/50 [00:09<00:00, 5.30it/s][A |
|
100%|ββββββββββ| 50/50 [00:09<00:00, 5.30it/s][A
100%|ββββββββββ| 50/50 [00:09<00:00, 5.33it/s] |
|
|
|
0%| | 0/50 [00:00<?, ?it/s][A |
|
2%|β | 1/50 [00:00<00:09, 5.38it/s][A |
|
4%|β | 2/50 [00:00<00:07, 6.20it/s][A |
|
6%|β | 3/50 [00:00<00:08, 5.76it/s][A |
|
8%|β | 4/50 [00:00<00:08, 5.58it/s][A |
|
10%|β | 5/50 [00:00<00:08, 5.47it/s][A |
|
12%|ββ | 6/50 [00:01<00:08, 5.40it/s][A |
|
14%|ββ | 7/50 [00:01<00:08, 5.36it/s][A |
|
16%|ββ | 8/50 [00:01<00:07, 5.35it/s][A |
|
18%|ββ | 9/50 [00:01<00:07, 5.34it/s][A |
|
20%|ββ | 10/50 [00:01<00:07, 5.32it/s][A |
|
22%|βββ | 11/50 [00:02<00:07, 5.30it/s][A |
|
24%|βββ | 12/50 [00:02<00:07, 5.30it/s][A |
|
26%|βββ | 13/50 [00:02<00:06, 5.30it/s][A |
|
28%|βββ | 14/50 [00:02<00:06, 5.29it/s][A |
|
30%|βββ | 15/50 [00:02<00:06, 5.29it/s][A |
|
32%|ββββ | 16/50 [00:02<00:06, 5.29it/s][A |
|
34%|ββββ | 17/50 [00:03<00:06, 5.29it/s][A |
|
36%|ββββ | 18/50 [00:03<00:06, 5.29it/s][A |
|
38%|ββββ | 19/50 [00:03<00:05, 5.28it/s][A |
|
40%|ββββ | 20/50 [00:03<00:05, 5.27it/s][A |
|
42%|βββββ | 21/50 [00:03<00:05, 5.28it/s][A |
|
44%|βββββ | 22/50 [00:04<00:05, 5.29it/s][A |
|
46%|βββββ | 23/50 [00:04<00:05, 5.29it/s][A |
|
48%|βββββ | 24/50 [00:04<00:04, 5.29it/s][A |
|
50%|βββββ | 25/50 [00:04<00:04, 5.30it/s][A |
|
52%|ββββββ | 26/50 [00:04<00:04, 5.29it/s][A |
|
54%|ββββββ | 27/50 [00:05<00:04, 5.29it/s][A |
|
56%|ββββββ | 28/50 [00:05<00:04, 5.28it/s][A |
|
58%|ββββββ | 29/50 [00:05<00:03, 5.28it/s][A |
|
60%|ββββββ | 30/50 [00:05<00:03, 5.29it/s][A |
|
62%|βββββββ | 31/50 [00:05<00:03, 5.29it/s][A |
|
64%|βββββββ | 32/50 [00:06<00:03, 5.27it/s][A |
|
66%|βββββββ | 33/50 [00:06<00:03, 5.27it/s][A |
|
68%|βββββββ | 34/50 [00:06<00:03, 5.28it/s][A |
|
70%|βββββββ | 35/50 [00:06<00:02, 5.28it/s][A |
|
72%|ββββββββ | 36/50 [00:06<00:02, 5.28it/s][A |
|
74%|ββββββββ | 37/50 [00:06<00:02, 5.28it/s][A |
|
76%|ββββββββ | 38/50 [00:07<00:02, 5.29it/s][A |
|
78%|ββββββββ | 39/50 [00:07<00:02, 5.30it/s][A |
|
80%|ββββββββ | 40/50 [00:07<00:01, 5.29it/s][A |
|
82%|βββββββββ | 41/50 [00:07<00:01, 5.29it/s][A |
|
84%|βββββββββ | 42/50 [00:07<00:01, 5.29it/s][A |
|
86%|βββββββββ | 43/50 [00:08<00:01, 5.29it/s][A |
|
88%|βββββββββ | 44/50 [00:08<00:01, 5.29it/s][A |
|
90%|βββββββββ | 45/50 [00:08<00:00, 5.29it/s][A |
|
92%|ββββββββββ| 46/50 [00:08<00:00, 5.29it/s][A |
|
94%|ββββββββββ| 47/50 [00:08<00:00, 5.27it/s][A |
|
96%|ββββββββββ| 48/50 [00:09<00:00, 5.27it/s][A |
|
98%|ββββββββββ| 49/50 [00:09<00:00, 5.27it/s][A |
|
100%|ββββββββββ| 50/50 [00:09<00:00, 5.28it/s][A
100%|ββββββββββ| 50/50 [00:09<00:00, 5.31it/s] |
|
|
|
0%| | 0/50 [00:00<?, ?it/s][A |
|
2%|β | 1/50 [00:00<00:09, 5.39it/s][A |
|
4%|β | 2/50 [00:00<00:07, 6.19it/s][A |
|
6%|β | 3/50 [00:00<00:08, 5.74it/s][A |
|
8%|β | 4/50 [00:00<00:08, 5.55it/s][A |
|
10%|β | 5/50 [00:00<00:08, 5.45it/s][A |
|
12%|ββ | 6/50 [00:01<00:08, 5.40it/s][A |
|
14%|ββ | 7/50 [00:01<00:08, 5.34it/s][A |
|
16%|ββ | 8/50 [00:01<00:07, 5.33it/s][A |
|
18%|ββ | 9/50 [00:01<00:07, 5.30it/s][A |
|
20%|ββ | 10/50 [00:01<00:07, 5.30it/s][A |
|
22%|βββ | 11/50 [00:02<00:07, 5.28it/s][A |
|
24%|βββ | 12/50 [00:02<00:07, 5.28it/s][A |
|
26%|βββ | 13/50 [00:02<00:06, 5.29it/s][A |
|
28%|βββ | 14/50 [00:02<00:06, 5.29it/s][A |
|
30%|βββ | 15/50 [00:02<00:06, 5.29it/s][A |
|
32%|ββββ | 16/50 [00:02<00:06, 5.29it/s][A |
|
34%|ββββ | 17/50 [00:03<00:06, 5.28it/s][A |
|
36%|ββββ | 18/50 [00:03<00:06, 5.28it/s][A |
|
38%|ββββ | 19/50 [00:03<00:05, 5.28it/s][A |
|
40%|ββββ | 20/50 [00:03<00:05, 5.29it/s][A |
|
42%|βββββ | 21/50 [00:03<00:05, 5.26it/s][A |
|
44%|βββββ | 22/50 [00:04<00:05, 5.29it/s][A |
|
46%|βββββ | 23/50 [00:04<00:05, 5.28it/s][A |
|
48%|βββββ | 24/50 [00:04<00:04, 5.28it/s][A |
|
50%|βββββ | 25/50 [00:04<00:04, 5.29it/s][A |
|
52%|ββββββ | 26/50 [00:04<00:04, 5.28it/s][A |
|
54%|ββββββ | 27/50 [00:05<00:04, 5.28it/s][A |
|
56%|ββββββ | 28/50 [00:05<00:04, 5.27it/s][A |
|
58%|ββββββ | 29/50 [00:05<00:03, 5.27it/s][A |
|
60%|ββββββ | 30/50 [00:05<00:03, 5.27it/s][A |
|
62%|βββββββ | 31/50 [00:05<00:03, 5.28it/s][A |
|
64%|βββββββ | 32/50 [00:06<00:03, 5.26it/s][A |
|
66%|βββββββ | 33/50 [00:06<00:03, 5.26it/s][A |
|
68%|βββββββ | 34/50 [00:06<00:03, 5.27it/s][A |
|
70%|βββββββ | 35/50 [00:06<00:02, 5.27it/s][A |
|
72%|ββββββββ | 36/50 [00:06<00:02, 5.28it/s][A |
|
74%|ββββββββ | 37/50 [00:06<00:02, 5.28it/s][A |
|
76%|ββββββββ | 38/50 [00:07<00:02, 5.27it/s][A |
|
78%|ββββββββ | 39/50 [00:07<00:02, 5.27it/s][A |
|
80%|ββββββββ | 40/50 [00:07<00:01, 5.27it/s][A |
|
82%|βββββββββ | 41/50 [00:07<00:01, 5.28it/s][A |
|
84%|βββββββββ | 42/50 [00:07<00:01, 5.27it/s][A |
|
86%|βββββββββ | 43/50 [00:08<00:01, 5.27it/s][A |
|
88%|βββββββββ | 44/50 [00:08<00:01, 5.27it/s][A |
|
90%|βββββββββ | 45/50 [00:08<00:00, 5.27it/s][A |
|
92%|ββββββββββ| 46/50 [00:08<00:00, 5.27it/s][A |
|
94%|ββββββββββ| 47/50 [00:08<00:00, 5.28it/s][A |
|
96%|ββββββββββ| 48/50 [00:09<00:00, 5.28it/s][A |
|
98%|ββββββββββ| 49/50 [00:09<00:00, 5.29it/s][A |
|
100%|ββββββββββ| 50/50 [00:09<00:00, 5.29it/s][A
100%|ββββββββββ| 50/50 [00:09<00:00, 5.30it/s] |
|
|
|
0%| | 0/50 [00:00<?, ?it/s][A |
|
2%|β | 1/50 [00:00<00:09, 5.37it/s][A |
|
4%|β | 2/50 [00:00<00:07, 6.17it/s][A |
|
6%|β | 3/50 [00:00<00:08, 5.74it/s][A |
|
8%|β | 4/50 [00:00<00:08, 5.55it/s][A |
|
10%|β | 5/50 [00:00<00:08, 5.46it/s][A |
|
12%|ββ | 6/50 [00:01<00:08, 5.40it/s][A |
|
14%|ββ | 7/50 [00:01<00:08, 5.36it/s][A |
|
16%|ββ | 8/50 [00:01<00:07, 5.33it/s][A |
|
18%|ββ | 9/50 [00:01<00:07, 5.31it/s][A |
|
20%|ββ | 10/50 [00:01<00:07, 5.31it/s][A |
|
22%|βββ | 11/50 [00:02<00:07, 5.29it/s][A |
|
24%|βββ | 12/50 [00:02<00:07, 5.29it/s][A |
|
26%|βββ | 13/50 [00:02<00:06, 5.29it/s][A |
|
28%|βββ | 14/50 [00:02<00:06, 5.28it/s][A |
|
30%|βββ | 15/50 [00:02<00:06, 5.29it/s][A |
|
32%|ββββ | 16/50 [00:02<00:06, 5.29it/s][A |
|
34%|ββββ | 17/50 [00:03<00:06, 5.29it/s][A |
|
36%|ββββ | 18/50 [00:03<00:06, 5.28it/s][A |
|
38%|ββββ | 19/50 [00:03<00:05, 5.28it/s][A |
|
40%|ββββ | 20/50 [00:03<00:05, 5.29it/s][A |
|
42%|βββββ | 21/50 [00:03<00:05, 5.29it/s][A |
|
44%|βββββ | 22/50 [00:04<00:05, 5.29it/s][A |
|
46%|βββββ | 23/50 [00:04<00:05, 5.28it/s][A |
|
48%|βββββ | 24/50 [00:04<00:04, 5.27it/s][A |
|
50%|βββββ | 25/50 [00:04<00:04, 5.28it/s][A |
|
52%|ββββββ | 26/50 [00:04<00:04, 5.29it/s][A |
|
54%|ββββββ | 27/50 [00:05<00:04, 5.28it/s][A |
|
56%|ββββββ | 28/50 [00:05<00:04, 5.28it/s][A |
|
58%|ββββββ | 29/50 [00:05<00:03, 5.28it/s][A |
|
60%|ββββββ | 30/50 [00:05<00:03, 5.27it/s][A |
|
62%|βββββββ | 31/50 [00:05<00:03, 5.27it/s][A |
|
64%|βββββββ | 32/50 [00:06<00:03, 5.27it/s][A |
|
66%|βββββββ | 33/50 [00:06<00:03, 5.28it/s][A |
|
68%|βββββββ | 34/50 [00:06<00:03, 5.26it/s][A |
|
70%|βββββββ | 35/50 [00:06<00:02, 5.27it/s][A |
|
72%|ββββββββ | 36/50 [00:06<00:02, 5.27it/s][A |
|
74%|ββββββββ | 37/50 [00:06<00:02, 5.27it/s][A |
|
76%|ββββββββ | 38/50 [00:07<00:02, 5.27it/s][A |
|
78%|ββββββββ | 39/50 [00:07<00:02, 5.27it/s][A |
|
80%|ββββββββ | 40/50 [00:07<00:01, 5.27it/s][A |
|
82%|βββββββββ | 41/50 [00:07<00:01, 5.27it/s][A |
|
84%|βββββββββ | 42/50 [00:07<00:01, 5.26it/s][A |
|
86%|βββββββββ | 43/50 [00:08<00:01, 5.27it/s][A |
|
88%|βββββββββ | 44/50 [00:08<00:01, 5.28it/s][A |
|
90%|βββββββββ | 45/50 [00:08<00:00, 5.28it/s][A |
|
92%|ββββββββββ| 46/50 [00:08<00:00, 5.28it/s][A |
|
94%|ββββββββββ| 47/50 [00:08<00:00, 5.28it/s][A |
|
96%|ββββββββββ| 48/50 [00:09<00:00, 5.29it/s][A |
|
98%|ββββββββββ| 49/50 [00:09<00:00, 5.29it/s][A |
|
100%|ββββββββββ| 50/50 [00:09<00:00, 5.28it/s][A
100%|ββββββββββ| 50/50 [00:09<00:00, 5.31it/s] |
|
10/12/2023 15:10:14 - INFO - __main__ - Image features shape: torch.Size([5, 75648]) |
|
|
|
Upload 6 LFS files: 0%| | 0/6 [00:00<?, ?it/s][A |
|
|
|
random_states_0.pkl: 0%| | 0.00/14.6k [00:00<?, ?B/s][A[A |
|
|
|
|
|
|
|
scheduler.bin: 0%| | 0.00/563 [00:00<?, ?B/s][A[A[A[A |
|
|
|
|
|
scaler.pt: 0%| | 0.00/557 [00:00<?, ?B/s][A[A[A |
|
|
|
|
|
|
|
|
|
pytorch_lora_weights.safetensors: 0%| | 0.00/23.4M [00:00<?, ?B/s][A[A[A[A[A |
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 0%| | 0.00/47.4M [00:00<?, ?B/s][A[A[A[A[A[A |
|
|
|
|
|
scaler.pt: 100%|ββββββββββ| 557/557 [00:00<00:00, 784B/s][A[A[A |
|
|
|
|
|
|
|
scheduler.bin: 100%|ββββββββββ| 563/563 [00:00<00:00, 777B/s][A[A[A[A |
|
|
|
|
|
|
|
|
|
pytorch_lora_weights.safetensors: 0%| | 8.19k/23.4M [00:00<34:03, 11.4kB/s][A[A[A[A[A |
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 0%| | 8.19k/47.4M [00:00<1:08:12, 11.6kB/s][A[A[A[A[A[A |
|
|
|
random_states_0.pkl: 56%|ββββββ | 8.19k/14.6k [00:00<00:00, 11.2kB/s][A[A
scheduler.bin: 100%|ββββββββββ| 563/563 [00:00<00:00, 706B/s] |
|
scaler.pt: 100%|ββββββββββ| 557/557 [00:00<00:00, 677B/s] |
|
|
|
|
|
|
|
|
|
|
|
pytorch_lora_weights.safetensors: 2%|β | 369k/23.4M [00:00<00:38, 602kB/s] [A[A[A[A[A |
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 1%| | 279k/47.4M [00:00<01:43, 457kB/s] [A[A[A[A[A[A
random_states_0.pkl: 100%|ββββββββββ| 14.6k/14.6k [00:00<00:00, 16.7kB/s] |
|
|
|
|
|
|
|
|
|
|
|
pytorch_lora_weights.safetensors: 8%|β | 1.92M/23.4M [00:00<00:06, 3.43MB/s][A[A[A[A[A |
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 6%|β | 3.02M/47.4M [00:00<00:08, 5.26MB/s][A[A[A[A[A[A |
|
|
|
|
|
|
|
|
|
pytorch_lora_weights.safetensors: 32%|ββββ | 7.56M/23.4M [00:01<00:01, 14.6MB/s][A[A[A[A[A |
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 13%|ββ | 6.17M/47.4M [00:01<00:03, 10.5MB/s][A[A[A[A[A[A |
|
|
|
|
|
|
|
|
|
pytorch_lora_weights.safetensors: 62%|βββββββ | 14.4M/23.4M [00:01<00:00, 26.9MB/s][A[A[A[A[A |
|
|
|
pytorch_lora_weights.safetensors: 0%| | 0.00/23.4M [00:00<?, ?B/s][A[A |
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 20%|ββ | 9.64M/47.4M [00:01<00:02, 14.6MB/s][A[A[A[A[A[A |
|
|
|
pytorch_lora_weights.safetensors: 2%|β | 369k/23.4M [00:00<00:06, 3.38MB/s][A[A |
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 25%|βββ | 12.0M/47.4M [00:01<00:02, 16.6MB/s][A[A[A[A[A[A |
|
|
|
|
|
|
|
|
|
pytorch_lora_weights.safetensors: 79%|ββββββββ | 18.5M/23.4M [00:01<00:00, 24.7MB/s][A[A[A[A[A |
|
|
|
pytorch_lora_weights.safetensors: 7%|β | 1.64M/23.4M [00:00<00:02, 8.53MB/s][A[A |
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 32%|ββββ | 15.0M/47.4M [00:01<00:01, 18.1MB/s][A[A[A[A[A[A |
|
|
|
pytorch_lora_weights.safetensors: 31%|βββ | 7.23M/23.4M [00:00<00:00, 28.8MB/s][A[A |
|
|
|
pytorch_lora_weights.safetensors: 66%|βββββββ | 15.4M/23.4M [00:00<00:00, 47.7MB/s][A[A
pytorch_lora_weights.safetensors: 100%|ββββββββββ| 23.4M/23.4M [00:01<00:00, 14.8MB/s] |
|
|
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 36%|ββββ | 17.1M/47.4M [00:01<00:02, 14.7MB/s][A[A[A[A[A[A |
|
|
|
pytorch_lora_weights.safetensors: 86%|βββββββββ | 20.1M/23.4M [00:00<00:00, 36.0MB/s][A[A |
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 46%|βββββ | 21.9M/47.4M [00:01<00:01, 20.1MB/s][A[A[A[A[A[A |
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 54%|ββββββ | 25.5M/47.4M [00:01<00:00, 21.9MB/s][A[A[A[A[A[A
pytorch_lora_weights.safetensors: 100%|ββββββββββ| 23.4M/23.4M [00:00<00:00, 26.6MB/s] |
|
|
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 62%|βββββββ | 29.3M/47.4M [00:02<00:00, 22.5MB/s][A[A[A[A[A[A |
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 68%|βββββββ | 32.0M/47.4M [00:02<00:00, 18.5MB/s][A[A[A[A[A[A |
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 80%|ββββββββ | 38.0M/47.4M [00:02<00:00, 24.7MB/s][A[A[A[A[A[A |
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 88%|βββββββββ | 41.9M/47.4M [00:02<00:00, 25.6MB/s][A[A[A[A[A[A |
|
|
|
|
|
|
|
|
|
|
|
optimizer.bin: 96%|ββββββββββ| 45.5M/47.4M [00:02<00:00, 25.9MB/s][A[A[A[A[A[A
optimizer.bin: 100%|ββββββββββ| 47.4M/47.4M [00:02<00:00, 16.1MB/s] |
|
|
|
Upload 6 LFS files: 17%|ββ | 1/6 [00:03<00:16, 3.24s/it][A
Upload 6 LFS files: 100%|ββββββββββ| 6/6 [00:03<00:00, 1.85it/s] |
|
|