log.txt

The following values were not passed to `accelerate launch` and had defaults used instead:
	`--num_processes` was set to a value of `1`
	`--num_machines` was set to a value of `1`
	`--mixed_precision` was set to a value of `'no'`
	`--dynamo_backend` was set to a value of `'no'`
To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.
/workspace/thumbs_up/train_dreambooth_lora_sdxl.py:122: DeprecationWarning: BILINEAR is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BILINEAR instead.
  def resize_image(image, size, interpolation=Image.BILINEAR):
10/13/2023 10:28:13 - INFO - __main__ - Current working directory: /workspace/thumbs_up
10/13/2023 10:28:13 - INFO - __main__ - Distributed environment: NO
Num processes: 1
Process index: 0
Local process index: 0
Device: cuda

Mixed precision type: fp16


Downloading (…)okenizer_config.json:   0%|          | 0.00/737 [00:00<?, ?B/s]
Downloading (…)okenizer_config.json: 100%|██████████| 737/737 [00:00<00:00, 4.93MB/s]

Downloading (…)tokenizer/vocab.json:   0%|          | 0.00/1.06M [00:00<?, ?B/s]
Downloading (…)tokenizer/vocab.json: 100%|██████████| 1.06M/1.06M [00:00<00:00, 6.55MB/s]
Downloading (…)tokenizer/vocab.json: 100%|██████████| 1.06M/1.06M [00:00<00:00, 6.52MB/s]

Downloading (…)tokenizer/merges.txt:   0%|          | 0.00/525k [00:00<?, ?B/s]
Downloading (…)tokenizer/merges.txt: 100%|██████████| 525k/525k [00:00<00:00, 6.84MB/s]

Downloading (…)cial_tokens_map.json:   0%|          | 0.00/472 [00:00<?, ?B/s]
Downloading (…)cial_tokens_map.json: 100%|██████████| 472/472 [00:00<00:00, 4.36MB/s]

Downloading (…)okenizer_config.json:   0%|          | 0.00/725 [00:00<?, ?B/s]
Downloading (…)okenizer_config.json: 100%|██████████| 725/725 [00:00<00:00, 5.96MB/s]

Downloading (…)cial_tokens_map.json:   0%|          | 0.00/460 [00:00<?, ?B/s]
Downloading (…)cial_tokens_map.json: 100%|██████████| 460/460 [00:00<00:00, 4.16MB/s]

Downloading (…)_encoder/config.json:   0%|          | 0.00/565 [00:00<?, ?B/s]
Downloading (…)_encoder/config.json: 100%|██████████| 565/565 [00:00<00:00, 4.78MB/s]
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.

Downloading (…)ncoder_2/config.json:   0%|          | 0.00/575 [00:00<?, ?B/s]
Downloading (…)ncoder_2/config.json: 100%|██████████| 575/575 [00:00<00:00, 5.19MB/s]
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.

Downloading (…)cheduler_config.json:   0%|          | 0.00/479 [00:00<?, ?B/s]
Downloading (…)cheduler_config.json: 100%|██████████| 479/479 [00:00<00:00, 4.30MB/s]
{'clip_sample_range', 'thresholding', 'dynamic_thresholding_ratio', 'variance_type'} was not found in config. Values will be initialized to default values.

Downloading model.safetensors:   0%|          | 0.00/492M [00:00<?, ?B/s]
Downloading model.safetensors:   6%|▋         | 31.5M/492M [00:00<00:01, 246MB/s]
Downloading model.safetensors:  15%|█▍        | 73.4M/492M [00:00<00:01, 308MB/s]
Downloading model.safetensors:  23%|██▎       | 115M/492M [00:00<00:01, 323MB/s] 
Downloading model.safetensors:  32%|███▏      | 157M/492M [00:00<00:01, 332MB/s]
Downloading model.safetensors:  40%|████      | 199M/492M [00:00<00:00, 329MB/s]
Downloading model.safetensors:  49%|████▉     | 241M/492M [00:00<00:00, 336MB/s]
Downloading model.safetensors:  58%|█████▊    | 283M/492M [00:00<00:00, 340MB/s]
Downloading model.safetensors:  66%|██████▌   | 325M/492M [00:00<00:00, 343MB/s]
Downloading model.safetensors:  75%|███████▍  | 367M/492M [00:01<00:00, 344MB/s]
Downloading model.safetensors:  83%|████████▎ | 409M/492M [00:01<00:00, 346MB/s]
Downloading model.safetensors:  92%|█████████▏| 451M/492M [00:01<00:00, 349MB/s]
Downloading model.safetensors: 100%|██████████| 492M/492M [00:01<00:00, 350MB/s]
Downloading model.safetensors: 100%|██████████| 492M/492M [00:01<00:00, 337MB/s]

Downloading model.safetensors:   0%|          | 0.00/2.78G [00:00<?, ?B/s]
Downloading model.safetensors:   2%|▏         | 41.9M/2.78G [00:00<00:07, 345MB/s]
Downloading model.safetensors:   3%|▎         | 83.9M/2.78G [00:00<00:07, 343MB/s]
Downloading model.safetensors:   5%|▍         | 126M/2.78G [00:00<00:07, 338MB/s] 
Downloading model.safetensors:   6%|▌         | 168M/2.78G [00:00<00:07, 339MB/s]
Downloading model.safetensors:   8%|▊         | 210M/2.78G [00:00<00:07, 340MB/s]
Downloading model.safetensors:   9%|▉         | 252M/2.78G [00:00<00:07, 348MB/s]
Downloading model.safetensors:  11%|█         | 294M/2.78G [00:00<00:07, 350MB/s]
Downloading model.safetensors:  12%|█▏        | 336M/2.78G [00:00<00:06, 351MB/s]
Downloading model.safetensors:  14%|█▎        | 377M/2.78G [00:01<00:06, 352MB/s]
Downloading model.safetensors:  15%|█▌        | 419M/2.78G [00:01<00:06, 356MB/s]
Downloading model.safetensors:  17%|█▋        | 461M/2.78G [00:01<00:06, 354MB/s]
Downloading model.safetensors:  18%|█▊        | 503M/2.78G [00:01<00:06, 352MB/s]
Downloading model.safetensors:  20%|█▉        | 545M/2.78G [00:01<00:06, 353MB/s]
Downloading model.safetensors:  21%|██        | 587M/2.78G [00:01<00:06, 354MB/s]
Downloading model.safetensors:  23%|██▎       | 629M/2.78G [00:01<00:06, 349MB/s]
Downloading model.safetensors:  24%|██▍       | 671M/2.78G [00:01<00:06, 347MB/s]
Downloading model.safetensors:  26%|██▌       | 713M/2.78G [00:02<00:06, 343MB/s]
Downloading model.safetensors:  27%|██▋       | 755M/2.78G [00:02<00:05, 345MB/s]
Downloading model.safetensors:  29%|██▊       | 797M/2.78G [00:02<00:05, 349MB/s]
Downloading model.safetensors:  30%|███       | 839M/2.78G [00:02<00:05, 347MB/s]
Downloading model.safetensors:  32%|███▏      | 881M/2.78G [00:02<00:05, 351MB/s]
Downloading model.safetensors:  33%|███▎      | 923M/2.78G [00:02<00:05, 350MB/s]
Downloading model.safetensors:  35%|███▍      | 965M/2.78G [00:02<00:05, 344MB/s]
Downloading model.safetensors:  36%|███▌      | 1.01G/2.78G [00:02<00:05, 347MB/s]
Downloading model.safetensors:  38%|███▊      | 1.05G/2.78G [00:03<00:05, 346MB/s]
Downloading model.safetensors:  39%|███▉      | 1.09G/2.78G [00:03<00:04, 350MB/s]
Downloading model.safetensors:  41%|████      | 1.13G/2.78G [00:03<00:04, 351MB/s]
Downloading model.safetensors:  42%|████▏     | 1.17G/2.78G [00:03<00:04, 346MB/s]
Downloading model.safetensors:  44%|████▍     | 1.22G/2.78G [00:03<00:04, 350MB/s]
Downloading model.safetensors:  45%|████▌     | 1.26G/2.78G [00:03<00:04, 341MB/s]
Downloading model.safetensors:  47%|████▋     | 1.30G/2.78G [00:03<00:04, 345MB/s]
Downloading model.safetensors:  48%|████▊     | 1.34G/2.78G [00:03<00:04, 347MB/s]
Downloading model.safetensors:  50%|████▉     | 1.38G/2.78G [00:03<00:03, 350MB/s]
Downloading model.safetensors:  51%|█████▏    | 1.43G/2.78G [00:04<00:03, 350MB/s]
Downloading model.safetensors:  53%|█████▎    | 1.47G/2.78G [00:04<00:03, 352MB/s]
Downloading model.safetensors:  54%|█████▍    | 1.51G/2.78G [00:04<00:03, 352MB/s]
Downloading model.safetensors:  56%|█████▌    | 1.55G/2.78G [00:04<00:03, 350MB/s]
Downloading model.safetensors:  57%|█████▋    | 1.59G/2.78G [00:04<00:03, 352MB/s]
Downloading model.safetensors:  59%|█████▉    | 1.64G/2.78G [00:04<00:03, 352MB/s]
Downloading model.safetensors:  60%|██████    | 1.68G/2.78G [00:04<00:03, 350MB/s]
Downloading model.safetensors:  62%|██████▏   | 1.72G/2.78G [00:04<00:03, 347MB/s]
Downloading model.safetensors:  63%|██████▎   | 1.76G/2.78G [00:05<00:02, 349MB/s]
Downloading model.safetensors:  65%|██████▍   | 1.80G/2.78G [00:05<00:02, 350MB/s]
Downloading model.safetensors:  66%|██████▋   | 1.85G/2.78G [00:05<00:02, 351MB/s]
Downloading model.safetensors:  68%|██████▊   | 1.89G/2.78G [00:05<00:02, 351MB/s]
Downloading model.safetensors:  69%|██████▉   | 1.93G/2.78G [00:05<00:02, 352MB/s]
Downloading model.safetensors:  71%|███████   | 1.97G/2.78G [00:05<00:02, 352MB/s]
Downloading model.safetensors:  72%|███████▏  | 2.01G/2.78G [00:05<00:02, 351MB/s]
Downloading model.safetensors:  74%|███████▍  | 2.06G/2.78G [00:05<00:02, 348MB/s]
Downloading model.safetensors:  75%|███████▌  | 2.10G/2.78G [00:06<00:01, 349MB/s]
Downloading model.safetensors:  77%|███████▋  | 2.14G/2.78G [00:06<00:01, 351MB/s]
Downloading model.safetensors:  78%|███████▊  | 2.18G/2.78G [00:06<00:01, 350MB/s]
Downloading model.safetensors:  80%|████████  | 2.22G/2.78G [00:06<00:01, 351MB/s]
Downloading model.safetensors:  82%|████████▏ | 2.26G/2.78G [00:06<00:01, 347MB/s]
Downloading model.safetensors:  83%|████████▎ | 2.31G/2.78G [00:06<00:01, 347MB/s]
Downloading model.safetensors:  85%|████████▍ | 2.35G/2.78G [00:06<00:01, 350MB/s]
Downloading model.safetensors:  86%|████████▌ | 2.39G/2.78G [00:06<00:01, 346MB/s]
Downloading model.safetensors:  88%|████████▊ | 2.43G/2.78G [00:06<00:00, 350MB/s]
Downloading model.safetensors:  89%|████████▉ | 2.47G/2.78G [00:07<00:00, 354MB/s]
Downloading model.safetensors:  91%|█████████ | 2.52G/2.78G [00:07<00:00, 354MB/s]
Downloading model.safetensors:  92%|█████████▏| 2.56G/2.78G [00:07<00:00, 352MB/s]
Downloading model.safetensors:  94%|█████████▎| 2.60G/2.78G [00:07<00:00, 353MB/s]
Downloading model.safetensors:  95%|█████████▌| 2.64G/2.78G [00:07<00:00, 351MB/s]
Downloading model.safetensors:  97%|█████████▋| 2.68G/2.78G [00:07<00:00, 348MB/s]
Downloading model.safetensors:  98%|█████████▊| 2.73G/2.78G [00:07<00:00, 348MB/s]
Downloading model.safetensors: 100%|█████████▉| 2.77G/2.78G [00:07<00:00, 342MB/s]
Downloading model.safetensors: 100%|██████████| 2.78G/2.78G [00:07<00:00, 349MB/s]

Downloading (…)lve/main/config.json:   0%|          | 0.00/631 [00:00<?, ?B/s]
Downloading (…)lve/main/config.json: 100%|██████████| 631/631 [00:00<00:00, 4.28MB/s]

Downloading (…)ch_model.safetensors:   0%|          | 0.00/335M [00:00<?, ?B/s]
Downloading (…)ch_model.safetensors:  13%|█▎        | 41.9M/335M [00:00<00:00, 375MB/s]
Downloading (…)ch_model.safetensors:  25%|██▌       | 83.9M/335M [00:00<00:00, 367MB/s]
Downloading (…)ch_model.safetensors:  38%|███▊      | 126M/335M [00:00<00:00, 362MB/s] 
Downloading (…)ch_model.safetensors:  50%|█████     | 168M/335M [00:00<00:00, 349MB/s]
Downloading (…)ch_model.safetensors:  63%|██████▎   | 210M/335M [00:00<00:00, 347MB/s]
Downloading (…)ch_model.safetensors:  75%|███████▌  | 252M/335M [00:00<00:00, 349MB/s]
Downloading (…)ch_model.safetensors:  88%|████████▊ | 294M/335M [00:00<00:00, 352MB/s]
Downloading (…)ch_model.safetensors: 100%|██████████| 335M/335M [00:00<00:00, 352MB/s]
Downloading (…)ch_model.safetensors: 100%|██████████| 335M/335M [00:00<00:00, 352MB/s]

Downloading (…)ain/unet/config.json:   0%|          | 0.00/1.68k [00:00<?, ?B/s]
Downloading (…)ain/unet/config.json: 100%|██████████| 1.68k/1.68k [00:00<00:00, 13.4MB/s]

Downloading (…)ch_model.safetensors:   0%|          | 0.00/10.3G [00:00<?, ?B/s]
Downloading (…)ch_model.safetensors:   0%|          | 41.9M/10.3G [00:00<00:27, 367MB/s]
Downloading (…)ch_model.safetensors:   1%|          | 83.9M/10.3G [00:00<00:28, 357MB/s]
Downloading (…)ch_model.safetensors:   1%|          | 126M/10.3G [00:00<00:28, 355MB/s] 
Downloading (…)ch_model.safetensors:   2%|▏         | 168M/10.3G [00:00<00:28, 354MB/s]
Downloading (…)ch_model.safetensors:   2%|▏         | 210M/10.3G [00:00<00:29, 347MB/s]
Downloading (…)ch_model.safetensors:   2%|▏         | 252M/10.3G [00:00<00:28, 348MB/s]
Downloading (…)ch_model.safetensors:   3%|▎         | 294M/10.3G [00:00<00:28, 348MB/s]
Downloading (…)ch_model.safetensors:   3%|▎         | 336M/10.3G [00:00<00:28, 349MB/s]
Downloading (…)ch_model.safetensors:   4%|▎         | 377M/10.3G [00:01<00:28, 350MB/s]
Downloading (…)ch_model.safetensors:   4%|▍         | 419M/10.3G [00:01<00:28, 347MB/s]
Downloading (…)ch_model.safetensors:   4%|▍         | 461M/10.3G [00:01<00:28, 349MB/s]
Downloading (…)ch_model.safetensors:   5%|▍         | 503M/10.3G [00:01<00:28, 347MB/s]
Downloading (…)ch_model.safetensors:   5%|▌         | 545M/10.3G [00:01<00:27, 351MB/s]
Downloading (…)ch_model.safetensors:   6%|▌         | 587M/10.3G [00:01<00:27, 354MB/s]
Downloading (…)ch_model.safetensors:   6%|▌         | 629M/10.3G [00:01<00:27, 354MB/s]
Downloading (…)ch_model.safetensors:   7%|▋         | 671M/10.3G [00:01<00:27, 350MB/s]
Downloading (…)ch_model.safetensors:   7%|▋         | 713M/10.3G [00:02<00:27, 350MB/s]
Downloading (…)ch_model.safetensors:   7%|▋         | 755M/10.3G [00:02<00:26, 353MB/s]
Downloading (…)ch_model.safetensors:   8%|▊         | 797M/10.3G [00:02<00:27, 342MB/s]
Downloading (…)ch_model.safetensors:   8%|▊         | 839M/10.3G [00:02<00:27, 338MB/s]
Downloading (…)ch_model.safetensors:   9%|▊         | 881M/10.3G [00:02<00:27, 343MB/s]
Downloading (…)ch_model.safetensors:   9%|▉         | 923M/10.3G [00:02<00:27, 344MB/s]
Downloading (…)ch_model.safetensors:   9%|▉         | 965M/10.3G [00:02<00:26, 347MB/s]
Downloading (…)ch_model.safetensors:  10%|▉         | 1.01G/10.3G [00:02<00:26, 347MB/s]
Downloading (…)ch_model.safetensors:  10%|█         | 1.05G/10.3G [00:03<00:26, 348MB/s]
Downloading (…)ch_model.safetensors:  11%|█         | 1.09G/10.3G [00:03<00:26, 350MB/s]
Downloading (…)ch_model.safetensors:  11%|█         | 1.13G/10.3G [00:03<00:26, 350MB/s]
Downloading (…)ch_model.safetensors:  11%|█▏        | 1.17G/10.3G [00:03<00:25, 350MB/s]
Downloading (…)ch_model.safetensors:  12%|█▏        | 1.22G/10.3G [00:03<00:25, 351MB/s]
Downloading (…)ch_model.safetensors:  12%|█▏        | 1.26G/10.3G [00:03<00:25, 349MB/s]
Downloading (…)ch_model.safetensors:  13%|█▎        | 1.30G/10.3G [00:03<00:26, 344MB/s]
Downloading (…)ch_model.safetensors:  13%|█▎        | 1.34G/10.3G [00:03<00:26, 342MB/s]
Downloading (…)ch_model.safetensors:  13%|█▎        | 1.38G/10.3G [00:03<00:25, 342MB/s]
Downloading (…)ch_model.safetensors:  14%|█▍        | 1.43G/10.3G [00:04<00:25, 343MB/s]
Downloading (…)ch_model.safetensors:  14%|█▍        | 1.47G/10.3G [00:04<00:25, 344MB/s]
Downloading (…)ch_model.safetensors:  15%|█▍        | 1.51G/10.3G [00:04<00:26, 325MB/s]
Downloading (…)ch_model.safetensors:  15%|█▌        | 1.55G/10.3G [00:04<00:26, 330MB/s]
Downloading (…)ch_model.safetensors:  16%|█▌        | 1.59G/10.3G [00:04<00:25, 336MB/s]
Downloading (…)ch_model.safetensors:  16%|█▌        | 1.64G/10.3G [00:04<00:25, 342MB/s]
Downloading (…)ch_model.safetensors:  16%|█▋        | 1.68G/10.3G [00:04<00:25, 343MB/s]
Downloading (…)ch_model.safetensors:  17%|█▋        | 1.72G/10.3G [00:04<00:25, 341MB/s]
Downloading (…)ch_model.safetensors:  17%|█▋        | 1.76G/10.3G [00:05<00:24, 343MB/s]
Downloading (…)ch_model.safetensors:  18%|█▊        | 1.80G/10.3G [00:05<00:24, 342MB/s]
Downloading (…)ch_model.safetensors:  18%|█▊        | 1.85G/10.3G [00:05<00:24, 345MB/s]
Downloading (…)ch_model.safetensors:  18%|█▊        | 1.89G/10.3G [00:05<00:24, 345MB/s]
Downloading (…)ch_model.safetensors:  19%|█▉        | 1.93G/10.3G [00:05<00:24, 345MB/s]
Downloading (…)ch_model.safetensors:  19%|█▉        | 1.97G/10.3G [00:05<00:24, 341MB/s]
Downloading (…)ch_model.safetensors:  20%|█▉        | 2.01G/10.3G [00:05<00:24, 341MB/s]
Downloading (…)ch_model.safetensors:  20%|██        | 2.06G/10.3G [00:05<00:24, 337MB/s]
Downloading (…)ch_model.safetensors:  20%|██        | 2.10G/10.3G [00:06<00:24, 336MB/s]
Downloading (…)ch_model.safetensors:  21%|██        | 2.14G/10.3G [00:06<00:24, 333MB/s]
Downloading (…)ch_model.safetensors:  21%|██        | 2.18G/10.3G [00:06<00:24, 331MB/s]
Downloading (…)ch_model.safetensors:  22%|██▏       | 2.22G/10.3G [00:06<00:24, 329MB/s]
Downloading (…)ch_model.safetensors:  22%|██▏       | 2.26G/10.3G [00:06<00:23, 335MB/s]
Downloading (…)ch_model.safetensors:  22%|██▏       | 2.31G/10.3G [00:06<00:23, 335MB/s]
Downloading (…)ch_model.safetensors:  23%|██▎       | 2.35G/10.3G [00:06<00:23, 337MB/s]
Downloading (…)ch_model.safetensors:  23%|██▎       | 2.39G/10.3G [00:06<00:22, 343MB/s]
Downloading (…)ch_model.safetensors:  24%|██▎       | 2.43G/10.3G [00:07<00:22, 347MB/s]
Downloading (…)ch_model.safetensors:  24%|██▍       | 2.47G/10.3G [00:07<00:22, 345MB/s]
Downloading (…)ch_model.safetensors:  25%|██▍       | 2.52G/10.3G [00:07<00:22, 350MB/s]
Downloading (…)ch_model.safetensors:  25%|██▍       | 2.56G/10.3G [00:07<00:22, 350MB/s]
Downloading (…)ch_model.safetensors:  25%|██▌       | 2.60G/10.3G [00:07<00:21, 350MB/s]
Downloading (…)ch_model.safetensors:  26%|██▌       | 2.64G/10.3G [00:07<00:21, 348MB/s]
Downloading (…)ch_model.safetensors:  26%|██▌       | 2.68G/10.3G [00:07<00:21, 350MB/s]
Downloading (…)ch_model.safetensors:  27%|██▋       | 2.73G/10.3G [00:07<00:22, 334MB/s]
Downloading (…)ch_model.safetensors:  27%|██▋       | 2.77G/10.3G [00:08<00:22, 336MB/s]
Downloading (…)ch_model.safetensors:  27%|██▋       | 2.81G/10.3G [00:08<00:22, 329MB/s]
Downloading (…)ch_model.safetensors:  28%|██▊       | 2.85G/10.3G [00:08<00:22, 328MB/s]
Downloading (…)ch_model.safetensors:  28%|██▊       | 2.89G/10.3G [00:08<00:22, 330MB/s]
Downloading (…)ch_model.safetensors:  29%|██▊       | 2.94G/10.3G [00:08<00:22, 332MB/s]
Downloading (…)ch_model.safetensors:  29%|██▉       | 2.98G/10.3G [00:08<00:21, 336MB/s]
Downloading (…)ch_model.safetensors:  29%|██▉       | 3.02G/10.3G [00:08<00:21, 339MB/s]
Downloading (…)ch_model.safetensors:  30%|██▉       | 3.06G/10.3G [00:08<00:20, 344MB/s]
Downloading (…)ch_model.safetensors:  30%|███       | 3.10G/10.3G [00:09<00:20, 346MB/s]
Downloading (…)ch_model.safetensors:  31%|███       | 3.15G/10.3G [00:09<00:20, 342MB/s]
Downloading (…)ch_model.safetensors:  31%|███       | 3.19G/10.3G [00:09<00:21, 323MB/s]
Downloading (…)ch_model.safetensors:  31%|███▏      | 3.23G/10.3G [00:09<00:21, 326MB/s]
Downloading (…)ch_model.safetensors:  32%|███▏      | 3.27G/10.3G [00:09<00:21, 328MB/s]
Downloading (…)ch_model.safetensors:  32%|███▏      | 3.31G/10.3G [00:09<00:21, 321MB/s]
Downloading (…)ch_model.safetensors:  33%|███▎      | 3.36G/10.3G [00:09<00:21, 318MB/s]
Downloading (…)ch_model.safetensors:  33%|███▎      | 3.40G/10.3G [00:09<00:21, 315MB/s]
Downloading (…)ch_model.safetensors:  33%|███▎      | 3.44G/10.3G [00:10<00:21, 316MB/s]
Downloading (…)ch_model.safetensors:  34%|███▍      | 3.48G/10.3G [00:10<00:21, 316MB/s]
Downloading (…)ch_model.safetensors:  34%|███▍      | 3.52G/10.3G [00:10<00:21, 317MB/s]
Downloading (…)ch_model.safetensors:  35%|███▍      | 3.57G/10.3G [00:10<00:21, 310MB/s]
Downloading (…)ch_model.safetensors:  35%|███▌      | 3.60G/10.3G [00:10<00:21, 307MB/s]
Downloading (…)ch_model.safetensors:  35%|███▌      | 3.63G/10.3G [00:10<00:21, 306MB/s]
Downloading (…)ch_model.safetensors:  36%|███▌      | 3.67G/10.3G [00:10<00:21, 312MB/s]
Downloading (…)ch_model.safetensors:  36%|███▌      | 3.71G/10.3G [00:10<00:20, 325MB/s]
Downloading (…)ch_model.safetensors:  37%|███▋      | 3.75G/10.3G [00:11<00:19, 334MB/s]
Downloading (…)ch_model.safetensors:  37%|███▋      | 3.80G/10.3G [00:11<00:19, 331MB/s]
Downloading (…)ch_model.safetensors:  37%|███▋      | 3.84G/10.3G [00:11<00:19, 329MB/s]
Downloading (…)ch_model.safetensors:  38%|███▊      | 3.88G/10.3G [00:11<00:18, 336MB/s]
Downloading (…)ch_model.safetensors:  38%|███▊      | 3.92G/10.3G [00:11<00:18, 337MB/s]
Downloading (…)ch_model.safetensors:  39%|███▊      | 3.96G/10.3G [00:11<00:18, 344MB/s]
Downloading (…)ch_model.safetensors:  39%|███▉      | 4.01G/10.3G [00:11<00:18, 341MB/s]
Downloading (…)ch_model.safetensors:  39%|███▉      | 4.05G/10.3G [00:11<00:18, 337MB/s]
Downloading (…)ch_model.safetensors:  40%|███▉      | 4.09G/10.3G [00:12<00:18, 339MB/s]
Downloading (…)ch_model.safetensors:  40%|████      | 4.13G/10.3G [00:12<00:18, 338MB/s]
Downloading (…)ch_model.safetensors:  41%|████      | 4.17G/10.3G [00:12<00:17, 342MB/s]
Downloading (…)ch_model.safetensors:  41%|████      | 4.22G/10.3G [00:12<00:17, 344MB/s]
Downloading (…)ch_model.safetensors:  41%|████▏     | 4.26G/10.3G [00:12<00:17, 336MB/s]
Downloading (…)ch_model.safetensors:  42%|████▏     | 4.30G/10.3G [00:12<00:17, 337MB/s]
Downloading (…)ch_model.safetensors:  42%|████▏     | 4.34G/10.3G [00:12<00:17, 339MB/s]
Downloading (…)ch_model.safetensors:  43%|████▎     | 4.38G/10.3G [00:12<00:17, 340MB/s]
Downloading (…)ch_model.safetensors:  43%|████▎     | 4.42G/10.3G [00:13<00:17, 341MB/s]
Downloading (…)ch_model.safetensors:  43%|████▎     | 4.47G/10.3G [00:13<00:17, 334MB/s]
Downloading (…)ch_model.safetensors:  44%|████▍     | 4.51G/10.3G [00:13<00:17, 337MB/s]
Downloading (…)ch_model.safetensors:  44%|████▍     | 4.55G/10.3G [00:13<00:16, 338MB/s]
Downloading (…)ch_model.safetensors:  45%|████▍     | 4.59G/10.3G [00:13<00:16, 341MB/s]
Downloading (…)ch_model.safetensors:  45%|████▌     | 4.63G/10.3G [00:13<00:16, 346MB/s]
Downloading (…)ch_model.safetensors:  46%|████▌     | 4.68G/10.3G [00:13<00:17, 327MB/s]
Downloading (…)ch_model.safetensors:  46%|████▌     | 4.72G/10.3G [00:13<00:16, 330MB/s]
Downloading (…)ch_model.safetensors:  46%|████▋     | 4.76G/10.3G [00:14<00:16, 334MB/s]
Downloading (…)ch_model.safetensors:  47%|████▋     | 4.80G/10.3G [00:14<00:16, 338MB/s]
Downloading (…)ch_model.safetensors:  47%|████▋     | 4.84G/10.3G [00:14<00:15, 343MB/s]
Downloading (…)ch_model.safetensors:  48%|████▊     | 4.89G/10.3G [00:14<00:15, 345MB/s]
Downloading (…)ch_model.safetensors:  48%|████▊     | 4.93G/10.3G [00:14<00:15, 348MB/s]
Downloading (…)ch_model.safetensors:  48%|████▊     | 4.97G/10.3G [00:14<00:15, 341MB/s]
Downloading (…)ch_model.safetensors:  49%|████▉     | 5.01G/10.3G [00:14<00:16, 323MB/s]
Downloading (…)ch_model.safetensors:  49%|████▉     | 5.05G/10.3G [00:14<00:16, 324MB/s]
Downloading (…)ch_model.safetensors:  50%|████▉     | 5.10G/10.3G [00:15<00:15, 331MB/s]
Downloading (…)ch_model.safetensors:  50%|█████     | 5.14G/10.3G [00:15<00:16, 320MB/s]
Downloading (…)ch_model.safetensors:  50%|█████     | 5.18G/10.3G [00:15<00:16, 316MB/s]
Downloading (…)ch_model.safetensors:  51%|█████     | 5.22G/10.3G [00:15<00:15, 323MB/s]
Downloading (…)ch_model.safetensors:  51%|█████▏    | 5.26G/10.3G [00:15<00:15, 314MB/s]
Downloading (…)ch_model.safetensors:  52%|█████▏    | 5.31G/10.3G [00:15<00:15, 313MB/s]
Downloading (…)ch_model.safetensors:  52%|█████▏    | 5.34G/10.3G [00:15<00:15, 312MB/s]
Downloading (…)ch_model.safetensors:  52%|█████▏    | 5.37G/10.3G [00:15<00:15, 311MB/s]
Downloading (…)ch_model.safetensors:  53%|█████▎    | 5.40G/10.3G [00:16<00:15, 310MB/s]
Downloading (…)ch_model.safetensors:  53%|█████▎    | 5.43G/10.3G [00:16<00:15, 308MB/s]
Downloading (…)ch_model.safetensors:  53%|█████▎    | 5.47G/10.3G [00:16<00:14, 322MB/s]
Downloading (…)ch_model.safetensors:  54%|█████▎    | 5.52G/10.3G [00:16<00:14, 327MB/s]
Downloading (…)ch_model.safetensors:  54%|█████▍    | 5.56G/10.3G [00:16<00:15, 314MB/s]
Downloading (…)ch_model.safetensors:  55%|█████▍    | 5.60G/10.3G [00:16<00:14, 326MB/s]
Downloading (…)ch_model.safetensors:  55%|█████▍    | 5.64G/10.3G [00:16<00:14, 328MB/s]
Downloading (…)ch_model.safetensors:  55%|█████▌    | 5.68G/10.3G [00:16<00:14, 325MB/s]
Downloading (…)ch_model.safetensors:  56%|█████▌    | 5.73G/10.3G [00:17<00:14, 317MB/s]
Downloading (…)ch_model.safetensors:  56%|█████▌    | 5.77G/10.3G [00:17<00:14, 320MB/s]
Downloading (…)ch_model.safetensors:  57%|█████▋    | 5.81G/10.3G [00:17<00:13, 330MB/s]
Downloading (…)ch_model.safetensors:  57%|█████▋    | 5.85G/10.3G [00:17<00:13, 340MB/s]
Downloading (…)ch_model.safetensors:  57%|█████▋    | 5.89G/10.3G [00:17<00:12, 342MB/s]
Downloading (…)ch_model.safetensors:  58%|█████▊    | 5.93G/10.3G [00:17<00:12, 341MB/s]
Downloading (…)ch_model.safetensors:  58%|█████▊    | 5.98G/10.3G [00:17<00:12, 343MB/s]
Downloading (…)ch_model.safetensors:  59%|█████▊    | 6.02G/10.3G [00:18<00:18, 230MB/s]
Downloading (…)ch_model.safetensors:  59%|█████▉    | 6.06G/10.3G [00:18<00:16, 258MB/s]
Downloading (…)ch_model.safetensors:  59%|█████▉    | 6.10G/10.3G [00:18<00:14, 279MB/s]
Downloading (…)ch_model.safetensors:  60%|█████▉    | 6.14G/10.3G [00:18<00:15, 273MB/s]
Downloading (…)ch_model.safetensors:  60%|██████    | 6.18G/10.3G [00:18<00:14, 281MB/s]
Downloading (…)ch_model.safetensors:  61%|██████    | 6.22G/10.3G [00:18<00:13, 296MB/s]
Downloading (…)ch_model.safetensors:  61%|██████    | 6.26G/10.3G [00:18<00:13, 304MB/s]
Downloading (…)ch_model.safetensors:  61%|██████▏   | 6.30G/10.3G [00:19<00:12, 307MB/s]
Downloading (…)ch_model.safetensors:  62%|██████▏   | 6.34G/10.3G [00:19<00:12, 313MB/s]
Downloading (…)ch_model.safetensors:  62%|██████▏   | 6.39G/10.3G [00:19<00:12, 316MB/s]
Downloading (…)ch_model.safetensors:  63%|██████▎   | 6.43G/10.3G [00:19<00:11, 325MB/s]
Downloading (…)ch_model.safetensors:  63%|██████▎   | 6.47G/10.3G [00:19<00:11, 332MB/s]
Downloading (…)ch_model.safetensors:  63%|██████▎   | 6.51G/10.3G [00:19<00:11, 323MB/s]
Downloading (…)ch_model.safetensors:  64%|██████▍   | 6.55G/10.3G [00:19<00:11, 332MB/s]
Downloading (…)ch_model.safetensors:  64%|██████▍   | 6.60G/10.3G [00:19<00:10, 341MB/s]
Downloading (…)ch_model.safetensors:  65%|██████▍   | 6.64G/10.3G [00:19<00:10, 347MB/s]
Downloading (…)ch_model.safetensors:  65%|██████▌   | 6.68G/10.3G [00:20<00:10, 353MB/s]
Downloading (…)ch_model.safetensors:  65%|██████▌   | 6.72G/10.3G [00:20<00:09, 361MB/s]
Downloading (…)ch_model.safetensors:  66%|██████▌   | 6.76G/10.3G [00:20<00:09, 362MB/s]
Downloading (…)ch_model.safetensors:  66%|██████▋   | 6.81G/10.3G [00:20<00:09, 355MB/s]
Downloading (…)ch_model.safetensors:  67%|██████▋   | 6.85G/10.3G [00:20<00:09, 356MB/s]
Downloading (…)ch_model.safetensors:  67%|██████▋   | 6.89G/10.3G [00:20<00:10, 332MB/s]
Downloading (…)ch_model.safetensors:  67%|██████▋   | 6.93G/10.3G [00:20<00:10, 327MB/s]
Downloading (…)ch_model.safetensors:  68%|██████▊   | 6.97G/10.3G [00:20<00:10, 326MB/s]
Downloading (…)ch_model.safetensors:  68%|██████▊   | 7.01G/10.3G [00:21<00:10, 323MB/s]
Downloading (…)ch_model.safetensors:  69%|██████▊   | 7.06G/10.3G [00:21<00:09, 325MB/s]
Downloading (…)ch_model.safetensors:  69%|██████▉   | 7.10G/10.3G [00:21<00:09, 324MB/s]
Downloading (…)ch_model.safetensors:  70%|██████▉   | 7.14G/10.3G [00:21<00:09, 332MB/s]
Downloading (…)ch_model.safetensors:  70%|██████▉   | 7.18G/10.3G [00:21<00:09, 332MB/s]
Downloading (…)ch_model.safetensors:  70%|███████   | 7.22G/10.3G [00:21<00:09, 330MB/s]
Downloading (…)ch_model.safetensors:  71%|███████   | 7.27G/10.3G [00:21<00:09, 323MB/s]
Downloading (…)ch_model.safetensors:  71%|███████   | 7.31G/10.3G [00:22<00:08, 329MB/s]
Downloading (…)ch_model.safetensors:  72%|███████▏  | 7.35G/10.3G [00:22<00:08, 330MB/s]
Downloading (…)ch_model.safetensors:  72%|███████▏  | 7.39G/10.3G [00:22<00:08, 324MB/s]
Downloading (…)ch_model.safetensors:  72%|███████▏  | 7.43G/10.3G [00:22<00:08, 330MB/s]
Downloading (…)ch_model.safetensors:  73%|███████▎  | 7.48G/10.3G [00:22<00:08, 335MB/s]
Downloading (…)ch_model.safetensors:  73%|███████▎  | 7.52G/10.3G [00:22<00:08, 337MB/s]
Downloading (…)ch_model.safetensors:  74%|███████▎  | 7.56G/10.3G [00:22<00:08, 338MB/s]
Downloading (…)ch_model.safetensors:  74%|███████▍  | 7.60G/10.3G [00:22<00:07, 338MB/s]
Downloading (…)ch_model.safetensors:  74%|███████▍  | 7.64G/10.3G [00:23<00:07, 332MB/s]
Downloading (…)ch_model.safetensors:  75%|███████▍  | 7.69G/10.3G [00:23<00:07, 337MB/s]
Downloading (…)ch_model.safetensors:  75%|███████▌  | 7.73G/10.3G [00:23<00:07, 337MB/s]
Downloading (…)ch_model.safetensors:  76%|███████▌  | 7.77G/10.3G [00:23<00:07, 340MB/s]
Downloading (…)ch_model.safetensors:  76%|███████▌  | 7.81G/10.3G [00:23<00:07, 327MB/s]
Downloading (…)ch_model.safetensors:  76%|███████▋  | 7.85G/10.3G [00:23<00:07, 333MB/s]
Downloading (…)ch_model.safetensors:  77%|███████▋  | 7.90G/10.3G [00:23<00:07, 338MB/s]
Downloading (…)ch_model.safetensors:  77%|███████▋  | 7.94G/10.3G [00:23<00:06, 335MB/s]
Downloading (…)ch_model.safetensors:  78%|███████▊  | 7.98G/10.3G [00:24<00:07, 327MB/s]
Downloading (…)ch_model.safetensors:  78%|███████▊  | 8.02G/10.3G [00:24<00:06, 330MB/s]
Downloading (…)ch_model.safetensors:  79%|███████▊  | 8.06G/10.3G [00:24<00:06, 336MB/s]
Downloading (…)ch_model.safetensors:  79%|███████▉  | 8.11G/10.3G [00:24<00:06, 335MB/s]
Downloading (…)ch_model.safetensors:  79%|███████▉  | 8.15G/10.3G [00:24<00:06, 336MB/s]
Downloading (…)ch_model.safetensors:  80%|███████▉  | 8.19G/10.3G [00:24<00:06, 338MB/s]
Downloading (…)ch_model.safetensors:  80%|████████  | 8.23G/10.3G [00:24<00:06, 338MB/s]
Downloading (…)ch_model.safetensors:  81%|████████  | 8.27G/10.3G [00:24<00:06, 326MB/s]
Downloading (…)ch_model.safetensors:  81%|████████  | 8.32G/10.3G [00:25<00:06, 311MB/s]
Downloading (…)ch_model.safetensors:  81%|████████▏ | 8.36G/10.3G [00:25<00:06, 316MB/s]
Downloading (…)ch_model.safetensors:  82%|████████▏ | 8.40G/10.3G [00:25<00:05, 323MB/s]
Downloading (…)ch_model.safetensors:  82%|████████▏ | 8.44G/10.3G [00:25<00:05, 330MB/s]
Downloading (…)ch_model.safetensors:  83%|████████▎ | 8.48G/10.3G [00:25<00:05, 339MB/s]
Downloading (…)ch_model.safetensors:  83%|████████▎ | 8.52G/10.3G [00:25<00:05, 339MB/s]
Downloading (…)ch_model.safetensors:  83%|████████▎ | 8.57G/10.3G [00:25<00:05, 336MB/s]
Downloading (…)ch_model.safetensors:  84%|████████▍ | 8.61G/10.3G [00:25<00:04, 337MB/s]
Downloading (…)ch_model.safetensors:  84%|████████▍ | 8.65G/10.3G [00:26<00:04, 336MB/s]
Downloading (…)ch_model.safetensors:  85%|████████▍ | 8.69G/10.3G [00:26<00:04, 335MB/s]
Downloading (…)ch_model.safetensors:  85%|████████▌ | 8.73G/10.3G [00:26<00:04, 336MB/s]
Downloading (…)ch_model.safetensors:  85%|████████▌ | 8.78G/10.3G [00:26<00:04, 336MB/s]
Downloading (…)ch_model.safetensors:  86%|████████▌ | 8.82G/10.3G [00:26<00:04, 342MB/s]
Downloading (…)ch_model.safetensors:  86%|████████▋ | 8.86G/10.3G [00:26<00:04, 343MB/s]
Downloading (…)ch_model.safetensors:  87%|████████▋ | 8.90G/10.3G [00:26<00:03, 347MB/s]
Downloading (…)ch_model.safetensors:  87%|████████▋ | 8.94G/10.3G [00:26<00:03, 346MB/s]
Downloading (…)ch_model.safetensors:  87%|████████▋ | 8.99G/10.3G [00:27<00:03, 324MB/s]
Downloading (…)ch_model.safetensors:  88%|████████▊ | 9.03G/10.3G [00:27<00:03, 335MB/s]
Downloading (…)ch_model.safetensors:  88%|████████▊ | 9.07G/10.3G [00:27<00:03, 336MB/s]
Downloading (…)ch_model.safetensors:  89%|████████▊ | 9.11G/10.3G [00:27<00:03, 340MB/s]
Downloading (…)ch_model.safetensors:  89%|████████▉ | 9.15G/10.3G [00:27<00:03, 337MB/s]
Downloading (…)ch_model.safetensors:  90%|████████▉ | 9.20G/10.3G [00:27<00:03, 341MB/s]
Downloading (…)ch_model.safetensors:  90%|████████▉ | 9.24G/10.3G [00:27<00:02, 344MB/s]
Downloading (…)ch_model.safetensors:  90%|█████████ | 9.28G/10.3G [00:27<00:02, 342MB/s]
Downloading (…)ch_model.safetensors:  91%|█████████ | 9.32G/10.3G [00:28<00:02, 337MB/s]
Downloading (…)ch_model.safetensors:  91%|█████████ | 9.36G/10.3G [00:28<00:02, 337MB/s]
Downloading (…)ch_model.safetensors:  92%|█████████▏| 9.41G/10.3G [00:28<00:02, 340MB/s]
Downloading (…)ch_model.safetensors:  92%|█████████▏| 9.45G/10.3G [00:28<00:02, 339MB/s]
Downloading (…)ch_model.safetensors:  92%|█████████▏| 9.49G/10.3G [00:28<00:02, 337MB/s]
Downloading (…)ch_model.safetensors:  93%|█████████▎| 9.53G/10.3G [00:28<00:02, 334MB/s]
Downloading (…)ch_model.safetensors:  93%|█████████▎| 9.57G/10.3G [00:28<00:02, 330MB/s]
Downloading (…)ch_model.safetensors:  94%|█████████▎| 9.62G/10.3G [00:28<00:01, 338MB/s]
Downloading (…)ch_model.safetensors:  94%|█████████▍| 9.66G/10.3G [00:29<00:01, 339MB/s]
Downloading (…)ch_model.safetensors:  94%|█████████▍| 9.70G/10.3G [00:29<00:01, 346MB/s]
Downloading (…)ch_model.safetensors:  95%|█████████▍| 9.74G/10.3G [00:29<00:01, 346MB/s]
Downloading (…)ch_model.safetensors:  95%|█████████▌| 9.78G/10.3G [00:29<00:01, 345MB/s]
Downloading (…)ch_model.safetensors:  96%|█████████▌| 9.83G/10.3G [00:29<00:01, 342MB/s]
Downloading (…)ch_model.safetensors:  96%|█████████▌| 9.87G/10.3G [00:29<00:01, 336MB/s]
Downloading (…)ch_model.safetensors:  96%|█████████▋| 9.91G/10.3G [00:29<00:01, 341MB/s]
Downloading (…)ch_model.safetensors:  97%|█████████▋| 9.95G/10.3G [00:29<00:00, 347MB/s]
Downloading (…)ch_model.safetensors:  97%|█████████▋| 9.99G/10.3G [00:29<00:00, 350MB/s]
Downloading (…)ch_model.safetensors:  98%|█████████▊| 10.0G/10.3G [00:30<00:00, 351MB/s]
Downloading (…)ch_model.safetensors:  98%|█████████▊| 10.1G/10.3G [00:30<00:00, 354MB/s]
Downloading (…)ch_model.safetensors:  99%|█████████▊| 10.1G/10.3G [00:30<00:00, 354MB/s]
Downloading (…)ch_model.safetensors:  99%|█████████▉| 10.2G/10.3G [00:30<00:00, 231MB/s]
Downloading (…)ch_model.safetensors:  99%|█████████▉| 10.2G/10.3G [00:30<00:00, 247MB/s]
Downloading (…)ch_model.safetensors: 100%|█████████▉| 10.2G/10.3G [00:30<00:00, 270MB/s]
Downloading (…)ch_model.safetensors: 100%|██████████| 10.3G/10.3G [00:30<00:00, 289MB/s]
Downloading (…)ch_model.safetensors: 100%|██████████| 10.3G/10.3G [00:30<00:00, 331MB/s]
{'dropout', 'attention_type'} was not found in config. Values will be initialized to default values.

Downloading (…)lve/main/config.json:   0%|          | 0.00/4.52k [00:00<?, ?B/s]
Downloading (…)lve/main/config.json: 100%|██████████| 4.52k/4.52k [00:00<00:00, 18.6MB/s]
`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.

Downloading model.safetensors:   0%|          | 0.00/1.71G [00:00<?, ?B/s]
Downloading model.safetensors:   2%|▏         | 41.9M/1.71G [00:00<00:05, 319MB/s]
Downloading model.safetensors:   5%|▍         | 83.9M/1.71G [00:00<00:04, 349MB/s]
Downloading model.safetensors:   7%|▋         | 126M/1.71G [00:00<00:04, 354MB/s] 
Downloading model.safetensors:  10%|▉         | 168M/1.71G [00:00<00:04, 354MB/s]
Downloading model.safetensors:  12%|█▏        | 210M/1.71G [00:00<00:04, 356MB/s]
Downloading model.safetensors:  15%|█▍        | 252M/1.71G [00:00<00:04, 359MB/s]
Downloading model.safetensors:  17%|█▋        | 294M/1.71G [00:00<00:04, 338MB/s]
Downloading model.safetensors:  20%|█▉        | 336M/1.71G [00:00<00:04, 343MB/s]
Downloading model.safetensors:  22%|██▏       | 377M/1.71G [00:01<00:03, 349MB/s]
Downloading model.safetensors:  25%|██▍       | 419M/1.71G [00:01<00:03, 354MB/s]
Downloading model.safetensors:  27%|██▋       | 461M/1.71G [00:01<00:03, 353MB/s]
Downloading model.safetensors:  29%|██▉       | 503M/1.71G [00:01<00:03, 355MB/s]
Downloading model.safetensors:  32%|███▏      | 545M/1.71G [00:01<00:03, 351MB/s]
Downloading model.safetensors:  34%|███▍      | 587M/1.71G [00:01<00:03, 349MB/s]
Downloading model.safetensors:  37%|███▋      | 629M/1.71G [00:01<00:03, 353MB/s]
Downloading model.safetensors:  39%|███▉      | 671M/1.71G [00:01<00:02, 353MB/s]
Downloading model.safetensors:  42%|████▏     | 713M/1.71G [00:02<00:02, 356MB/s]
Downloading model.safetensors:  44%|████▍     | 755M/1.71G [00:02<00:02, 361MB/s]
Downloading model.safetensors:  47%|████▋     | 797M/1.71G [00:02<00:02, 359MB/s]
Downloading model.safetensors:  49%|████▉     | 839M/1.71G [00:02<00:02, 364MB/s]
Downloading model.safetensors:  51%|█████▏    | 881M/1.71G [00:02<00:02, 369MB/s]
Downloading model.safetensors:  54%|█████▍    | 923M/1.71G [00:02<00:02, 369MB/s]
Downloading model.safetensors:  56%|█████▋    | 965M/1.71G [00:02<00:02, 362MB/s]
Downloading model.safetensors:  59%|█████▉    | 1.01G/1.71G [00:02<00:01, 359MB/s]
Downloading model.safetensors:  61%|██████▏   | 1.05G/1.71G [00:02<00:01, 363MB/s]
Downloading model.safetensors:  64%|██████▍   | 1.09G/1.71G [00:03<00:01, 359MB/s]
Downloading model.safetensors:  66%|██████▌   | 1.13G/1.71G [00:03<00:01, 357MB/s]
Downloading model.safetensors:  69%|██████▊   | 1.17G/1.71G [00:03<00:01, 357MB/s]
Downloading model.safetensors:  71%|███████   | 1.22G/1.71G [00:03<00:01, 349MB/s]
Downloading model.safetensors:  74%|███████▎  | 1.26G/1.71G [00:03<00:01, 349MB/s]
Downloading model.safetensors:  76%|███████▌  | 1.30G/1.71G [00:03<00:01, 355MB/s]
Downloading model.safetensors:  78%|███████▊  | 1.34G/1.71G [00:03<00:01, 354MB/s]
Downloading model.safetensors:  81%|████████  | 1.38G/1.71G [00:03<00:00, 354MB/s]
Downloading model.safetensors:  83%|████████▎ | 1.43G/1.71G [00:04<00:00, 353MB/s]
Downloading model.safetensors:  86%|████████▌ | 1.47G/1.71G [00:04<00:00, 349MB/s]
Downloading model.safetensors:  88%|████████▊ | 1.51G/1.71G [00:04<00:00, 353MB/s]
Downloading model.safetensors:  91%|█████████ | 1.55G/1.71G [00:04<00:00, 349MB/s]
Downloading model.safetensors:  93%|█████████▎| 1.59G/1.71G [00:04<00:00, 347MB/s]
Downloading model.safetensors:  96%|█████████▌| 1.64G/1.71G [00:04<00:00, 351MB/s]
Downloading model.safetensors:  98%|█████████▊| 1.68G/1.71G [00:04<00:00, 356MB/s]
Downloading model.safetensors: 100%|██████████| 1.71G/1.71G [00:04<00:00, 354MB/s]

Downloading (…)rocessor_config.json:   0%|          | 0.00/316 [00:00<?, ?B/s]
Downloading (…)rocessor_config.json: 100%|██████████| 316/316 [00:00<00:00, 2.55MB/s]

Downloading (…)okenizer_config.json:   0%|          | 0.00/905 [00:00<?, ?B/s]
Downloading (…)okenizer_config.json: 100%|██████████| 905/905 [00:00<00:00, 8.27MB/s]
`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.

Downloading (…)olve/main/vocab.json:   0%|          | 0.00/961k [00:00<?, ?B/s]
Downloading (…)olve/main/vocab.json: 100%|██████████| 961k/961k [00:00<00:00, 1.11MB/s]
Downloading (…)olve/main/vocab.json: 100%|██████████| 961k/961k [00:00<00:00, 1.11MB/s]

Downloading (…)olve/main/merges.txt:   0%|          | 0.00/525k [00:00<?, ?B/s]
Downloading (…)olve/main/merges.txt: 100%|██████████| 525k/525k [00:00<00:00, 5.33MB/s]

Downloading (…)/main/tokenizer.json:   0%|          | 0.00/2.22M [00:00<?, ?B/s]
Downloading (…)/main/tokenizer.json: 100%|██████████| 2.22M/2.22M [00:00<00:00, 54.9MB/s]

Downloading (…)cial_tokens_map.json:   0%|          | 0.00/389 [00:00<?, ?B/s]
Downloading (…)cial_tokens_map.json: 100%|██████████| 389/389 [00:00<00:00, 3.59MB/s]

Downloading (…)rocessor_config.json:   0%|          | 0.00/244 [00:00<?, ?B/s]
Downloading (…)rocessor_config.json: 100%|██████████| 244/244 [00:00<00:00, 2.23MB/s]

Downloading (…)lve/main/config.json:   0%|          | 0.00/453 [00:00<?, ?B/s]
Downloading (…)lve/main/config.json: 100%|██████████| 453/453 [00:00<00:00, 4.11MB/s]

Downloading pytorch_model.bin:   0%|          | 0.00/86.7M [00:00<?, ?B/s]
Downloading pytorch_model.bin:  48%|████▊     | 41.9M/86.7M [00:00<00:00, 355MB/s]
Downloading pytorch_model.bin:  97%|█████████▋| 83.9M/86.7M [00:00<00:00, 359MB/s]
Downloading pytorch_model.bin: 100%|██████████| 86.7M/86.7M [00:00<00:00, 353MB/s]
Some weights of ViTModel were not initialized from the model checkpoint at facebook/dino-vits16 and are newly initialized: ['pooler.dense.bias', 'pooler.dense.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
wandb: Currently logged in as: berglund. Use `wandb login --relogin` to force relogin
wandb: Tracking run with wandb version 0.15.12
wandb: Run data is saved locally in /workspace/thumbs_up/wandb/run-20231013_102925-82s2kzqo
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run gentle-resonance-53
wandb: ⭐️ View project at https://wandb.ai/berglund/dreambooth-lora-sd-xl
wandb: 🚀 View run at https://wandb.ai/berglund/dreambooth-lora-sd-xl/runs/82s2kzqo
10/13/2023 10:29:26 - INFO - __main__ - ***** Running training *****
10/13/2023 10:29:26 - INFO - __main__ -   Num examples = 21
10/13/2023 10:29:26 - INFO - __main__ -   Num batches each epoch = 11
10/13/2023 10:29:26 - INFO - __main__ -   Num Epochs = 55
10/13/2023 10:29:26 - INFO - __main__ -   Instantaneous batch size per device = 2
10/13/2023 10:29:26 - INFO - __main__ -   Total train batch size (w. parallel, distributed & accumulation) = 2
10/13/2023 10:29:26 - INFO - __main__ -   Gradient Accumulation steps = 1
10/13/2023 10:29:26 - 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<25:18,  2.54s/it]
Steps:   0%|          | 1/600 [00:02<25:18,  2.54s/it, loss=0.0509, lr=1e-6]
Steps:   0%|          | 2/600 [00:04<20:42,  2.08s/it, loss=0.0509, lr=1e-6]
Steps:   0%|          | 2/600 [00:04<20:42,  2.08s/it, loss=0.0944, lr=1e-6]
Steps:   0%|          | 3/600 [00:06<20:34,  2.07s/it, loss=0.0944, lr=1e-6]
Steps:   0%|          | 3/600 [00:06<20:34,  2.07s/it, loss=0.235, lr=1e-6] 
Steps:   1%|          | 4/600 [00:08<19:17,  1.94s/it, loss=0.235, lr=1e-6]
Steps:   1%|          | 4/600 [00:08<19:17,  1.94s/it, loss=0.0463, lr=1e-6]
Steps:   1%|          | 5/600 [00:09<18:17,  1.85s/it, loss=0.0463, lr=1e-6]
Steps:   1%|          | 5/600 [00:09<18:17,  1.85s/it, loss=0.061, lr=1e-6] 
Steps:   1%|          | 6/600 [00:11<18:10,  1.84s/it, loss=0.061, lr=1e-6]
Steps:   1%|          | 6/600 [00:11<18:10,  1.84s/it, loss=0.00999, lr=1e-6]
Steps:   1%|          | 7/600 [00:13<17:03,  1.73s/it, loss=0.00999, lr=1e-6]
Steps:   1%|          | 7/600 [00:13<17:03,  1.73s/it, loss=0.132, lr=1e-6]  
Steps:   1%|▏         | 8/600 [00:14<16:14,  1.65s/it, loss=0.132, lr=1e-6]
Steps:   1%|▏         | 8/600 [00:14<16:14,  1.65s/it, loss=0.134, lr=1e-6]
Steps:   2%|▏         | 9/600 [00:16<16:46,  1.70s/it, loss=0.134, lr=1e-6]
Steps:   2%|▏         | 9/600 [00:16<16:46,  1.70s/it, loss=0.0906, lr=1e-6]
Steps:   2%|▏         | 10/600 [00:17<15:41,  1.60s/it, loss=0.0906, lr=1e-6]
Steps:   2%|▏         | 10/600 [00:17<15:41,  1.60s/it, loss=0.0586, lr=1e-6]
Steps:   2%|▏         | 11/600 [00:18<13:37,  1.39s/it, loss=0.0586, lr=1e-6]
Steps:   2%|▏         | 11/600 [00:18<13:37,  1.39s/it, loss=0.291, lr=1e-6] 10/13/2023 10:29:44 - 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".


Downloading (…)ain/model_index.json:   0%|          | 0.00/609 [00:00<?, ?B/s]
Downloading (…)ain/model_index.json: 100%|██████████| 609/609 [00:00<00:00, 1.67MB/s]


Fetching 11 files:   0%|          | 0/11 [00:00<?, ?it/s]


Downloading (…)ch_model.safetensors:   0%|          | 0.00/335M [00:00<?, ?B/s]


Downloading (…)ch_model.safetensors:   6%|▋         | 21.0M/335M [00:00<00:01, 209MB/s]


Downloading (…)ch_model.safetensors:  19%|█▉        | 62.9M/335M [00:00<00:00, 299MB/s]


Downloading (…)ch_model.safetensors:  31%|███▏      | 105M/335M [00:00<00:00, 335MB/s] 


Downloading (…)ch_model.safetensors:  44%|████▍     | 147M/335M [00:00<00:00, 352MB/s]


Downloading (…)ch_model.safetensors:  56%|█████▋    | 189M/335M [00:00<00:00, 363MB/s]


Downloading (…)ch_model.safetensors:  69%|██████▉   | 231M/335M [00:00<00:00, 368MB/s]


Downloading (…)ch_model.safetensors:  81%|████████▏ | 273M/335M [00:00<00:00, 375MB/s]


Downloading (…)ch_model.safetensors:  94%|█████████▍| 315M/335M [00:00<00:00, 372MB/s]
Downloading (…)ch_model.safetensors: 100%|██████████| 335M/335M [00:00<00:00, 355MB/s]


Fetching 11 files: 100%|██████████| 11/11 [00:01<00:00,  8.84it/s]
Fetching 11 files: 100%|██████████| 11/11 [00:01<00:00,  8.83it/s]


Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]Loaded tokenizer_2 as CLIPTokenizer from `tokenizer_2` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
Loaded scheduler as EulerDiscreteScheduler from `scheduler` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of stabilityai/stable-diffusion-xl-base-1.0.


Loading pipeline components...:  57%|█████▋    | 4/7 [00:00<00:00, 37.56it/s]
Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 65.15it/s]
{'lambda_min_clipped', 'algorithm_type', 'variance_type', 'solver_order', 'thresholding', 'dynamic_thresholding_ratio', 'lower_order_final', 'solver_type'} was not found in config. Values will be initialized to default values.
10/13/2023 10:30:44 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
10/13/2023 10:31:33 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
10/13/2023 10:32:22 - INFO - __main__ - Image features shape: torch.Size([5, 75648])

Steps:   2%|▏         | 12/600 [03:05<8:26:25, 51.68s/it, loss=0.291, lr=1e-6]
Steps:   2%|▏         | 12/600 [03:05<8:26:25, 51.68s/it, loss=0.143, lr=1e-6]
Steps:   2%|▏         | 13/600 [03:07<5:58:02, 36.60s/it, loss=0.143, lr=1e-6]
Steps:   2%|▏         | 13/600 [03:07<5:58:02, 36.60s/it, loss=0.104, lr=1e-6]
Steps:   2%|▏         | 14/600 [03:08<4:13:51, 25.99s/it, loss=0.104, lr=1e-6]
Steps:   2%|▏         | 14/600 [03:08<4:13:51, 25.99s/it, loss=0.185, lr=1e-6]
Steps:   2%|▎         | 15/600 [03:10<3:01:13, 18.59s/it, loss=0.185, lr=1e-6]
Steps:   2%|▎         | 15/600 [03:10<3:01:13, 18.59s/it, loss=0.137, lr=1e-6]
Steps:   3%|▎         | 16/600 [03:11<2:10:54, 13.45s/it, loss=0.137, lr=1e-6]
Steps:   3%|▎         | 16/600 [03:11<2:10:54, 13.45s/it, loss=0.0199, lr=1e-6]
Steps:   3%|▎         | 17/600 [03:13<1:36:32,  9.94s/it, loss=0.0199, lr=1e-6]
Steps:   3%|▎         | 17/600 [03:13<1:36:32,  9.94s/it, loss=0.15, lr=1e-6]  
Steps:   3%|▎         | 18/600 [03:15<1:12:42,  7.50s/it, loss=0.15, lr=1e-6]
Steps:   3%|▎         | 18/600 [03:15<1:12:42,  7.50s/it, loss=0.113, lr=1e-6]
Steps:   3%|▎         | 19/600 [03:16<55:09,  5.70s/it, loss=0.113, lr=1e-6]  
Steps:   3%|▎         | 19/600 [03:16<55:09,  5.70s/it, loss=0.184, lr=1e-6]
Steps:   3%|▎         | 20/600 [03:18<43:11,  4.47s/it, loss=0.184, lr=1e-6]
Steps:   3%|▎         | 20/600 [03:18<43:11,  4.47s/it, loss=0.144, lr=1e-6]
Steps:   4%|▎         | 21/600 [03:19<34:01,  3.53s/it, loss=0.144, lr=1e-6]
Steps:   4%|▎         | 21/600 [03:19<34:01,  3.53s/it, loss=0.103, lr=1e-6]
Steps:   4%|▎         | 22/600 [03:20<25:57,  2.70s/it, loss=0.103, lr=1e-6]
Steps:   4%|▎         | 22/600 [03:20<25:57,  2.70s/it, loss=0.319, lr=1e-6]
Steps:   4%|▍         | 23/600 [03:22<24:17,  2.53s/it, loss=0.319, lr=1e-6]
Steps:   4%|▍         | 23/600 [03:22<24:17,  2.53s/it, loss=0.0736, lr=1e-6]
Steps:   4%|▍         | 24/600 [03:24<21:04,  2.19s/it, loss=0.0736, lr=1e-6]
Steps:   4%|▍         | 24/600 [03:24<21:04,  2.19s/it, loss=0.0971, lr=1e-6]
Steps:   4%|▍         | 25/600 [03:25<19:27,  2.03s/it, loss=0.0971, lr=1e-6]
Steps:   4%|▍         | 25/600 [03:25<19:27,  2.03s/it, loss=0.0828, lr=1e-6]
Steps:   4%|▍         | 26/600 [03:27<18:30,  1.93s/it, loss=0.0828, lr=1e-6]
Steps:   4%|▍         | 26/600 [03:27<18:30,  1.93s/it, loss=0.0612, lr=1e-6]
Steps:   4%|▍         | 27/600 [03:29<17:49,  1.87s/it, loss=0.0612, lr=1e-6]
Steps:   4%|▍         | 27/600 [03:29<17:49,  1.87s/it, loss=0.197, lr=1e-6] 
Steps:   5%|▍         | 28/600 [03:30<16:08,  1.69s/it, loss=0.197, lr=1e-6]
Steps:   5%|▍         | 28/600 [03:30<16:08,  1.69s/it, loss=0.0579, lr=1e-6]
Steps:   5%|▍         | 29/600 [03:32<16:26,  1.73s/it, loss=0.0579, lr=1e-6]
Steps:   5%|▍         | 29/600 [03:32<16:26,  1.73s/it, loss=0.00545, lr=1e-6]
Steps:   5%|▌         | 30/600 [03:33<16:37,  1.75s/it, loss=0.00545, lr=1e-6]
Steps:   5%|▌         | 30/600 [03:33<16:37,  1.75s/it, loss=0.151, lr=1e-6]  
Steps:   5%|▌         | 31/600 [03:35<15:58,  1.68s/it, loss=0.151, lr=1e-6]
Steps:   5%|▌         | 31/600 [03:35<15:58,  1.68s/it, loss=0.0865, lr=1e-6]
Steps:   5%|▌         | 32/600 [03:36<14:21,  1.52s/it, loss=0.0865, lr=1e-6]
Steps:   5%|▌         | 32/600 [03:36<14:21,  1.52s/it, loss=0.142, lr=1e-6] 
Steps:   6%|▌         | 33/600 [03:37<12:08,  1.28s/it, loss=0.142, lr=1e-6]
Steps:   6%|▌         | 33/600 [03:37<12:08,  1.28s/it, loss=0.0126, lr=1e-6]
Steps:   6%|▌         | 34/600 [03:39<15:28,  1.64s/it, loss=0.0126, lr=1e-6]
Steps:   6%|▌         | 34/600 [03:39<15:28,  1.64s/it, loss=0.0879, lr=1e-6]
Steps:   6%|▌         | 35/600 [03:41<14:36,  1.55s/it, loss=0.0879, lr=1e-6]
Steps:   6%|▌         | 35/600 [03:41<14:36,  1.55s/it, loss=0.136, lr=1e-6] 
Steps:   6%|▌         | 36/600 [03:42<14:17,  1.52s/it, loss=0.136, lr=1e-6]
Steps:   6%|▌         | 36/600 [03:42<14:17,  1.52s/it, loss=0.0609, lr=1e-6]
Steps:   6%|▌         | 37/600 [03:44<14:00,  1.49s/it, loss=0.0609, lr=1e-6]
Steps:   6%|▌         | 37/600 [03:44<14:00,  1.49s/it, loss=0.197, lr=1e-6] 
Steps:   6%|▋         | 38/600 [03:45<14:22,  1.54s/it, loss=0.197, lr=1e-6]
Steps:   6%|▋         | 38/600 [03:45<14:22,  1.54s/it, loss=0.184, lr=1e-6]
Steps:   6%|▋         | 39/600 [03:47<14:12,  1.52s/it, loss=0.184, lr=1e-6]
Steps:   6%|▋         | 39/600 [03:47<14:12,  1.52s/it, loss=0.176, lr=1e-6]
Steps:   7%|▋         | 40/600 [03:48<14:15,  1.53s/it, loss=0.176, lr=1e-6]
Steps:   7%|▋         | 40/600 [03:48<14:15,  1.53s/it, loss=0.0726, lr=1e-6]
Steps:   7%|▋         | 41/600 [03:50<15:02,  1.61s/it, loss=0.0726, lr=1e-6]
Steps:   7%|▋         | 41/600 [03:50<15:02,  1.61s/it, loss=0.0252, lr=1e-6]
Steps:   7%|▋         | 42/600 [03:52<14:51,  1.60s/it, loss=0.0252, lr=1e-6]
Steps:   7%|▋         | 42/600 [03:52<14:51,  1.60s/it, loss=0.173, lr=1e-6] 
Steps:   7%|▋         | 43/600 [03:53<14:25,  1.55s/it, loss=0.173, lr=1e-6]
Steps:   7%|▋         | 43/600 [03:53<14:25,  1.55s/it, loss=0.248, lr=1e-6]
Steps:   7%|▋         | 44/600 [03:54<12:10,  1.31s/it, loss=0.248, lr=1e-6]
Steps:   7%|▋         | 44/600 [03:54<12:10,  1.31s/it, loss=0.0923, lr=1e-6]
Steps:   8%|▊         | 45/600 [03:56<13:22,  1.45s/it, loss=0.0923, lr=1e-6]
Steps:   8%|▊         | 45/600 [03:56<13:22,  1.45s/it, loss=0.0789, lr=1e-6]
Steps:   8%|▊         | 46/600 [03:57<13:36,  1.47s/it, loss=0.0789, lr=1e-6]
Steps:   8%|▊         | 46/600 [03:57<13:36,  1.47s/it, loss=0.241, lr=1e-6] 
Steps:   8%|▊         | 47/600 [03:59<14:15,  1.55s/it, loss=0.241, lr=1e-6]
Steps:   8%|▊         | 47/600 [03:59<14:15,  1.55s/it, loss=0.15, lr=1e-6] 
Steps:   8%|▊         | 48/600 [04:01<15:02,  1.63s/it, loss=0.15, lr=1e-6]
Steps:   8%|▊         | 48/600 [04:01<15:02,  1.63s/it, loss=0.0209, lr=1e-6]
Steps:   8%|▊         | 49/600 [04:02<14:56,  1.63s/it, loss=0.0209, lr=1e-6]
Steps:   8%|▊         | 49/600 [04:02<14:56,  1.63s/it, loss=0.264, lr=1e-6] 
Steps:   8%|▊         | 50/600 [04:04<14:52,  1.62s/it, loss=0.264, lr=1e-6]
Steps:   8%|▊         | 50/600 [04:04<14:52,  1.62s/it, loss=0.169, lr=1e-6]
Steps:   8%|▊         | 51/600 [04:06<14:53,  1.63s/it, loss=0.169, lr=1e-6]
Steps:   8%|▊         | 51/600 [04:06<14:53,  1.63s/it, loss=0.173, lr=1e-6]
Steps:   9%|▊         | 52/600 [04:07<15:03,  1.65s/it, loss=0.173, lr=1e-6]
Steps:   9%|▊         | 52/600 [04:07<15:03,  1.65s/it, loss=0.138, lr=1e-6]
Steps:   9%|▉         | 53/600 [04:09<14:09,  1.55s/it, loss=0.138, lr=1e-6]
Steps:   9%|▉         | 53/600 [04:09<14:09,  1.55s/it, loss=0.151, lr=1e-6]
Steps:   9%|▉         | 54/600 [04:10<13:43,  1.51s/it, loss=0.151, lr=1e-6]
Steps:   9%|▉         | 54/600 [04:10<13:43,  1.51s/it, loss=0.0256, lr=1e-6]
Steps:   9%|▉         | 55/600 [04:11<11:37,  1.28s/it, loss=0.0256, lr=1e-6]
Steps:   9%|▉         | 55/600 [04:11<11:37,  1.28s/it, loss=0.0722, lr=1e-6]
Steps:   9%|▉         | 56/600 [04:13<14:35,  1.61s/it, loss=0.0722, lr=1e-6]
Steps:   9%|▉         | 56/600 [04:13<14:35,  1.61s/it, loss=0.162, lr=1e-6] 
Steps:  10%|▉         | 57/600 [04:15<14:51,  1.64s/it, loss=0.162, lr=1e-6]
Steps:  10%|▉         | 57/600 [04:15<14:51,  1.64s/it, loss=0.0126, lr=1e-6]
Steps:  10%|▉         | 58/600 [04:16<14:01,  1.55s/it, loss=0.0126, lr=1e-6]
Steps:  10%|▉         | 58/600 [04:16<14:01,  1.55s/it, loss=0.17, lr=1e-6]  
Steps:  10%|▉         | 59/600 [04:18<13:57,  1.55s/it, loss=0.17, lr=1e-6]
Steps:  10%|▉         | 59/600 [04:18<13:57,  1.55s/it, loss=0.155, lr=1e-6]
Steps:  10%|█         | 60/600 [04:19<13:46,  1.53s/it, loss=0.155, lr=1e-6]
Steps:  10%|█         | 60/600 [04:19<13:46,  1.53s/it, loss=0.0707, lr=1e-6]
Steps:  10%|█         | 61/600 [04:21<13:57,  1.55s/it, loss=0.0707, lr=1e-6]
Steps:  10%|█         | 61/600 [04:21<13:57,  1.55s/it, loss=0.105, lr=1e-6] 
Steps:  10%|█         | 62/600 [04:22<13:28,  1.50s/it, loss=0.105, lr=1e-6]
Steps:  10%|█         | 62/600 [04:22<13:28,  1.50s/it, loss=0.0643, lr=1e-6]
Steps:  10%|█         | 63/600 [04:24<14:16,  1.60s/it, loss=0.0643, lr=1e-6]
Steps:  10%|█         | 63/600 [04:24<14:16,  1.60s/it, loss=0.136, lr=1e-6] 
Steps:  11%|█         | 64/600 [04:26<14:29,  1.62s/it, loss=0.136, lr=1e-6]
Steps:  11%|█         | 64/600 [04:26<14:29,  1.62s/it, loss=0.169, lr=1e-6]
Steps:  11%|█         | 65/600 [04:27<13:19,  1.49s/it, loss=0.169, lr=1e-6]
Steps:  11%|█         | 65/600 [04:27<13:19,  1.49s/it, loss=0.0594, lr=1e-6]
Steps:  11%|█         | 66/600 [04:28<11:18,  1.27s/it, loss=0.0594, lr=1e-6]
Steps:  11%|█         | 66/600 [04:28<11:18,  1.27s/it, loss=0.00238, lr=1e-6]
Steps:  11%|█         | 67/600 [04:30<13:50,  1.56s/it, loss=0.00238, lr=1e-6]
Steps:  11%|█         | 67/600 [04:30<13:50,  1.56s/it, loss=0.0979, lr=1e-6] 
Steps:  11%|█▏        | 68/600 [04:31<13:31,  1.53s/it, loss=0.0979, lr=1e-6]
Steps:  11%|█▏        | 68/600 [04:31<13:31,  1.53s/it, loss=0.1, lr=1e-6]   
Steps:  12%|█▏        | 69/600 [04:33<13:53,  1.57s/it, loss=0.1, lr=1e-6]
Steps:  12%|█▏        | 69/600 [04:33<13:53,  1.57s/it, loss=0.201, lr=1e-6]
Steps:  12%|█▏        | 70/600 [04:35<14:27,  1.64s/it, loss=0.201, lr=1e-6]
Steps:  12%|█▏        | 70/600 [04:35<14:27,  1.64s/it, loss=0.144, lr=1e-6]
Steps:  12%|█▏        | 71/600 [04:36<14:17,  1.62s/it, loss=0.144, lr=1e-6]
Steps:  12%|█▏        | 71/600 [04:36<14:17,  1.62s/it, loss=0.0463, lr=1e-6]
Steps:  12%|█▏        | 72/600 [04:38<13:58,  1.59s/it, loss=0.0463, lr=1e-6]
Steps:  12%|█▏        | 72/600 [04:38<13:58,  1.59s/it, loss=0.0287, lr=1e-6]
Steps:  12%|█▏        | 73/600 [04:39<13:47,  1.57s/it, loss=0.0287, lr=1e-6]
Steps:  12%|█▏        | 73/600 [04:39<13:47,  1.57s/it, loss=0.0163, lr=1e-6]
Steps:  12%|█▏        | 74/600 [04:41<13:48,  1.58s/it, loss=0.0163, lr=1e-6]
Steps:  12%|█▏        | 74/600 [04:41<13:48,  1.58s/it, loss=0.115, lr=1e-6] 
Steps:  12%|█▎        | 75/600 [04:43<14:01,  1.60s/it, loss=0.115, lr=1e-6]
Steps:  12%|█▎        | 75/600 [04:43<14:01,  1.60s/it, loss=0.0514, lr=1e-6]
Steps:  13%|█▎        | 76/600 [04:44<13:04,  1.50s/it, loss=0.0514, lr=1e-6]
Steps:  13%|█▎        | 76/600 [04:44<13:04,  1.50s/it, loss=0.141, lr=1e-6] 
Steps:  13%|█▎        | 77/600 [04:45<11:05,  1.27s/it, loss=0.141, lr=1e-6]
Steps:  13%|█▎        | 77/600 [04:45<11:05,  1.27s/it, loss=0.00221, lr=1e-6]
Steps:  13%|█▎        | 78/600 [04:47<13:26,  1.54s/it, loss=0.00221, lr=1e-6]
Steps:  13%|█▎        | 78/600 [04:47<13:26,  1.54s/it, loss=0.0584, lr=1e-6] 
Steps:  13%|█▎        | 79/600 [04:48<13:44,  1.58s/it, loss=0.0584, lr=1e-6]
Steps:  13%|█▎        | 79/600 [04:48<13:44,  1.58s/it, loss=0.211, lr=1e-6] 
Steps:  13%|█▎        | 80/600 [04:50<13:28,  1.55s/it, loss=0.211, lr=1e-6]
Steps:  13%|█▎        | 80/600 [04:50<13:28,  1.55s/it, loss=0.0342, lr=1e-6]
Steps:  14%|█▎        | 81/600 [04:52<13:50,  1.60s/it, loss=0.0342, lr=1e-6]
Steps:  14%|█▎        | 81/600 [04:52<13:50,  1.60s/it, loss=0.111, lr=1e-6] 
Steps:  14%|█▎        | 82/600 [04:53<13:56,  1.61s/it, loss=0.111, lr=1e-6]
Steps:  14%|█▎        | 82/600 [04:53<13:56,  1.61s/it, loss=0.0387, lr=1e-6]
Steps:  14%|█▍        | 83/600 [04:55<12:54,  1.50s/it, loss=0.0387, lr=1e-6]
Steps:  14%|█▍        | 83/600 [04:55<12:54,  1.50s/it, loss=0.0331, lr=1e-6]
Steps:  14%|█▍        | 84/600 [04:56<13:44,  1.60s/it, loss=0.0331, lr=1e-6]
Steps:  14%|█▍        | 84/600 [04:56<13:44,  1.60s/it, loss=0.0771, lr=1e-6]
Steps:  14%|█▍        | 85/600 [04:58<13:38,  1.59s/it, loss=0.0771, lr=1e-6]
Steps:  14%|█▍        | 85/600 [04:58<13:38,  1.59s/it, loss=0.202, lr=1e-6] 
Steps:  14%|█▍        | 86/600 [05:00<13:39,  1.59s/it, loss=0.202, lr=1e-6]
Steps:  14%|█▍        | 86/600 [05:00<13:39,  1.59s/it, loss=0.03, lr=1e-6] 
Steps:  14%|█▍        | 87/600 [05:01<12:40,  1.48s/it, loss=0.03, lr=1e-6]
Steps:  14%|█▍        | 87/600 [05:01<12:40,  1.48s/it, loss=0.195, lr=1e-6]
Steps:  15%|█▍        | 88/600 [05:02<10:46,  1.26s/it, loss=0.195, lr=1e-6]
Steps:  15%|█▍        | 88/600 [05:02<10:46,  1.26s/it, loss=0.397, lr=1e-6]
Steps:  15%|█▍        | 89/600 [05:04<12:53,  1.51s/it, loss=0.397, lr=1e-6]
Steps:  15%|█▍        | 89/600 [05:04<12:53,  1.51s/it, loss=0.0853, lr=1e-6]
Steps:  15%|█▌        | 90/600 [05:05<12:35,  1.48s/it, loss=0.0853, lr=1e-6]
Steps:  15%|█▌        | 90/600 [05:05<12:35,  1.48s/it, loss=0.157, lr=1e-6] 
Steps:  15%|█▌        | 91/600 [05:07<13:01,  1.54s/it, loss=0.157, lr=1e-6]
Steps:  15%|█▌        | 91/600 [05:07<13:01,  1.54s/it, loss=0.0632, lr=1e-6]
Steps:  15%|█▌        | 92/600 [05:08<13:13,  1.56s/it, loss=0.0632, lr=1e-6]
Steps:  15%|█▌        | 92/600 [05:08<13:13,  1.56s/it, loss=0.143, lr=1e-6] 
Steps:  16%|█▌        | 93/600 [05:10<13:35,  1.61s/it, loss=0.143, lr=1e-6]
Steps:  16%|█▌        | 93/600 [05:10<13:35,  1.61s/it, loss=0.00502, lr=1e-6]
Steps:  16%|█▌        | 94/600 [05:12<13:34,  1.61s/it, loss=0.00502, lr=1e-6]
Steps:  16%|█▌        | 94/600 [05:12<13:34,  1.61s/it, loss=0.112, lr=1e-6]  
Steps:  16%|█▌        | 95/600 [05:13<13:33,  1.61s/it, loss=0.112, lr=1e-6]
Steps:  16%|█▌        | 95/600 [05:13<13:33,  1.61s/it, loss=0.0726, lr=1e-6]
Steps:  16%|█▌        | 96/600 [05:15<12:55,  1.54s/it, loss=0.0726, lr=1e-6]
Steps:  16%|█▌        | 96/600 [05:15<12:55,  1.54s/it, loss=0.015, lr=1e-6] 
Steps:  16%|█▌        | 97/600 [05:16<13:11,  1.57s/it, loss=0.015, lr=1e-6]
Steps:  16%|█▌        | 97/600 [05:16<13:11,  1.57s/it, loss=0.00491, lr=1e-6]
Steps:  16%|█▋        | 98/600 [05:18<12:40,  1.51s/it, loss=0.00491, lr=1e-6]
Steps:  16%|█▋        | 98/600 [05:18<12:40,  1.51s/it, loss=0.131, lr=1e-6]  
Steps:  16%|█▋        | 99/600 [05:18<10:43,  1.28s/it, loss=0.131, lr=1e-6]
Steps:  16%|█▋        | 99/600 [05:18<10:43,  1.28s/it, loss=0.251, lr=1e-6]
Steps:  17%|█▋        | 100/600 [05:20<12:09,  1.46s/it, loss=0.251, lr=1e-6]
Steps:  17%|█▋        | 100/600 [05:20<12:09,  1.46s/it, loss=0.229, lr=1e-6]
Steps:  17%|█▋        | 101/600 [05:22<12:50,  1.54s/it, loss=0.229, lr=1e-6]
Steps:  17%|█▋        | 101/600 [05:22<12:50,  1.54s/it, loss=0.0423, lr=1e-6]
Steps:  17%|█▋        | 102/600 [05:24<12:52,  1.55s/it, loss=0.0423, lr=1e-6]
Steps:  17%|█▋        | 102/600 [05:24<12:52,  1.55s/it, loss=0.00851, lr=1e-6]
Steps:  17%|█▋        | 103/600 [05:25<12:45,  1.54s/it, loss=0.00851, lr=1e-6]
Steps:  17%|█▋        | 103/600 [05:25<12:45,  1.54s/it, loss=0.11, lr=1e-6]   
Steps:  17%|█▋        | 104/600 [05:27<13:19,  1.61s/it, loss=0.11, lr=1e-6]
Steps:  17%|█▋        | 104/600 [05:27<13:19,  1.61s/it, loss=0.0145, lr=1e-6]
Steps:  18%|█▊        | 105/600 [05:29<13:42,  1.66s/it, loss=0.0145, lr=1e-6]
Steps:  18%|█▊        | 105/600 [05:29<13:42,  1.66s/it, loss=0.187, lr=1e-6] 
Steps:  18%|█▊        | 106/600 [05:30<13:41,  1.66s/it, loss=0.187, lr=1e-6]
Steps:  18%|█▊        | 106/600 [05:30<13:41,  1.66s/it, loss=0.0982, lr=1e-6]
Steps:  18%|█▊        | 107/600 [05:32<13:35,  1.65s/it, loss=0.0982, lr=1e-6]
Steps:  18%|█▊        | 107/600 [05:32<13:35,  1.65s/it, loss=0.206, lr=1e-6] 
Steps:  18%|█▊        | 108/600 [05:34<13:21,  1.63s/it, loss=0.206, lr=1e-6]
Steps:  18%|█▊        | 108/600 [05:34<13:21,  1.63s/it, loss=0.0551, lr=1e-6]
Steps:  18%|█▊        | 109/600 [05:35<12:13,  1.49s/it, loss=0.0551, lr=1e-6]
Steps:  18%|█▊        | 109/600 [05:35<12:13,  1.49s/it, loss=0.0296, lr=1e-6]
Steps:  18%|█▊        | 110/600 [05:35<10:23,  1.27s/it, loss=0.0296, lr=1e-6]
Steps:  18%|█▊        | 110/600 [05:35<10:23,  1.27s/it, loss=0.322, lr=1e-6] 
Steps:  18%|█▊        | 111/600 [05:38<12:32,  1.54s/it, loss=0.322, lr=1e-6]
Steps:  18%|█▊        | 111/600 [05:38<12:32,  1.54s/it, loss=0.12, lr=1e-6] 
Steps:  19%|█▊        | 112/600 [05:39<12:21,  1.52s/it, loss=0.12, lr=1e-6]
Steps:  19%|█▊        | 112/600 [05:39<12:21,  1.52s/it, loss=0.16, lr=1e-6]
Steps:  19%|█▉        | 113/600 [05:41<12:26,  1.53s/it, loss=0.16, lr=1e-6]
Steps:  19%|█▉        | 113/600 [05:41<12:26,  1.53s/it, loss=0.199, lr=1e-6]
Steps:  19%|█▉        | 114/600 [05:42<13:00,  1.61s/it, loss=0.199, lr=1e-6]
Steps:  19%|█▉        | 114/600 [05:42<13:00,  1.61s/it, loss=0.0346, lr=1e-6]
Steps:  19%|█▉        | 115/600 [05:44<13:14,  1.64s/it, loss=0.0346, lr=1e-6]
Steps:  19%|█▉        | 115/600 [05:44<13:14,  1.64s/it, loss=0.265, lr=1e-6] 
Steps:  19%|█▉        | 116/600 [05:46<12:30,  1.55s/it, loss=0.265, lr=1e-6]
Steps:  19%|█▉        | 116/600 [05:46<12:30,  1.55s/it, loss=0.0032, lr=1e-6]
Steps:  20%|█▉        | 117/600 [05:47<13:11,  1.64s/it, loss=0.0032, lr=1e-6]
Steps:  20%|█▉        | 117/600 [05:47<13:11,  1.64s/it, loss=0.0198, lr=1e-6]
Steps:  20%|█▉        | 118/600 [05:49<12:34,  1.57s/it, loss=0.0198, lr=1e-6]
Steps:  20%|█▉        | 118/600 [05:49<12:34,  1.57s/it, loss=0.0514, lr=1e-6]
Steps:  20%|█▉        | 119/600 [05:50<12:40,  1.58s/it, loss=0.0514, lr=1e-6]
Steps:  20%|█▉        | 119/600 [05:50<12:40,  1.58s/it, loss=0.0172, lr=1e-6]
Steps:  20%|██        | 120/600 [05:52<12:10,  1.52s/it, loss=0.0172, lr=1e-6]
Steps:  20%|██        | 120/600 [05:52<12:10,  1.52s/it, loss=0.201, lr=1e-6] 
Steps:  20%|██        | 121/600 [05:52<10:18,  1.29s/it, loss=0.201, lr=1e-6]
Steps:  20%|██        | 121/600 [05:52<10:18,  1.29s/it, loss=0.36, lr=1e-6] 
Steps:  20%|██        | 122/600 [05:55<13:14,  1.66s/it, loss=0.36, lr=1e-6]
Steps:  20%|██        | 122/600 [05:55<13:14,  1.66s/it, loss=0.0329, lr=1e-6]
Steps:  20%|██        | 123/600 [05:57<12:59,  1.63s/it, loss=0.0329, lr=1e-6]
Steps:  20%|██        | 123/600 [05:57<12:59,  1.63s/it, loss=0.021, lr=1e-6] 
Steps:  21%|██        | 124/600 [05:58<12:44,  1.61s/it, loss=0.021, lr=1e-6]
Steps:  21%|██        | 124/600 [05:58<12:44,  1.61s/it, loss=0.0855, lr=1e-6]
Steps:  21%|██        | 125/600 [06:00<12:44,  1.61s/it, loss=0.0855, lr=1e-6]
Steps:  21%|██        | 125/600 [06:00<12:44,  1.61s/it, loss=0.0881, lr=1e-6]
Steps:  21%|██        | 126/600 [06:01<12:36,  1.60s/it, loss=0.0881, lr=1e-6]
Steps:  21%|██        | 126/600 [06:01<12:36,  1.60s/it, loss=0.132, lr=1e-6] 
Steps:  21%|██        | 127/600 [06:03<12:13,  1.55s/it, loss=0.132, lr=1e-6]
Steps:  21%|██        | 127/600 [06:03<12:13,  1.55s/it, loss=0.101, lr=1e-6]
Steps:  21%|██▏       | 128/600 [06:04<12:01,  1.53s/it, loss=0.101, lr=1e-6]
Steps:  21%|██▏       | 128/600 [06:04<12:01,  1.53s/it, loss=0.0355, lr=1e-6]
Steps:  22%|██▏       | 129/600 [06:06<12:17,  1.57s/it, loss=0.0355, lr=1e-6]
Steps:  22%|██▏       | 129/600 [06:06<12:17,  1.57s/it, loss=0.0893, lr=1e-6]
Steps:  22%|██▏       | 130/600 [06:08<12:22,  1.58s/it, loss=0.0893, lr=1e-6]
Steps:  22%|██▏       | 130/600 [06:08<12:22,  1.58s/it, loss=0.0571, lr=1e-6]
Steps:  22%|██▏       | 131/600 [06:09<11:15,  1.44s/it, loss=0.0571, lr=1e-6]
Steps:  22%|██▏       | 131/600 [06:09<11:15,  1.44s/it, loss=0.156, lr=1e-6] 
Steps:  22%|██▏       | 132/600 [06:09<09:37,  1.23s/it, loss=0.156, lr=1e-6]
Steps:  22%|██▏       | 132/600 [06:09<09:37,  1.23s/it, loss=0.364, lr=1e-6]
Steps:  22%|██▏       | 133/600 [06:11<11:39,  1.50s/it, loss=0.364, lr=1e-6]
Steps:  22%|██▏       | 133/600 [06:11<11:39,  1.50s/it, loss=0.0942, lr=1e-6]
Steps:  22%|██▏       | 134/600 [06:13<11:59,  1.54s/it, loss=0.0942, lr=1e-6]
Steps:  22%|██▏       | 134/600 [06:13<11:59,  1.54s/it, loss=0.0818, lr=1e-6]
Steps:  22%|██▎       | 135/600 [06:15<12:19,  1.59s/it, loss=0.0818, lr=1e-6]
Steps:  22%|██▎       | 135/600 [06:15<12:19,  1.59s/it, loss=0.0718, lr=1e-6]
Steps:  23%|██▎       | 136/600 [06:17<12:38,  1.64s/it, loss=0.0718, lr=1e-6]
Steps:  23%|██▎       | 136/600 [06:17<12:38,  1.64s/it, loss=0.114, lr=1e-6] 
Steps:  23%|██▎       | 137/600 [06:18<12:52,  1.67s/it, loss=0.114, lr=1e-6]
Steps:  23%|██▎       | 137/600 [06:18<12:52,  1.67s/it, loss=0.105, lr=1e-6]
Steps:  23%|██▎       | 138/600 [06:20<12:47,  1.66s/it, loss=0.105, lr=1e-6]
Steps:  23%|██▎       | 138/600 [06:20<12:47,  1.66s/it, loss=0.128, lr=1e-6]
Steps:  23%|██▎       | 139/600 [06:22<12:34,  1.64s/it, loss=0.128, lr=1e-6]
Steps:  23%|██▎       | 139/600 [06:22<12:34,  1.64s/it, loss=0.0208, lr=1e-6]
Steps:  23%|██▎       | 140/600 [06:23<12:20,  1.61s/it, loss=0.0208, lr=1e-6]
Steps:  23%|██▎       | 140/600 [06:23<12:20,  1.61s/it, loss=0.187, lr=1e-6] 
Steps:  24%|██▎       | 141/600 [06:24<11:42,  1.53s/it, loss=0.187, lr=1e-6]
Steps:  24%|██▎       | 141/600 [06:24<11:42,  1.53s/it, loss=0.0776, lr=1e-6]
Steps:  24%|██▎       | 142/600 [06:26<10:45,  1.41s/it, loss=0.0776, lr=1e-6]
Steps:  24%|██▎       | 142/600 [06:26<10:45,  1.41s/it, loss=0.104, lr=1e-6] 
Steps:  24%|██▍       | 143/600 [06:26<09:17,  1.22s/it, loss=0.104, lr=1e-6]
Steps:  24%|██▍       | 143/600 [06:26<09:17,  1.22s/it, loss=0.112, lr=1e-6]
Steps:  24%|██▍       | 144/600 [06:29<12:03,  1.59s/it, loss=0.112, lr=1e-6]
Steps:  24%|██▍       | 144/600 [06:29<12:03,  1.59s/it, loss=0.0306, lr=1e-6]
Steps:  24%|██▍       | 145/600 [06:30<12:20,  1.63s/it, loss=0.0306, lr=1e-6]
Steps:  24%|██▍       | 145/600 [06:31<12:20,  1.63s/it, loss=0.0496, lr=1e-6]
Steps:  24%|██▍       | 146/600 [06:32<11:55,  1.58s/it, loss=0.0496, lr=1e-6]
Steps:  24%|██▍       | 146/600 [06:32<11:55,  1.58s/it, loss=0.0275, lr=1e-6]
Steps:  24%|██▍       | 147/600 [06:34<11:57,  1.58s/it, loss=0.0275, lr=1e-6]
Steps:  24%|██▍       | 147/600 [06:34<11:57,  1.58s/it, loss=0.148, lr=1e-6] 
Steps:  25%|██▍       | 148/600 [06:35<11:45,  1.56s/it, loss=0.148, lr=1e-6]
Steps:  25%|██▍       | 148/600 [06:35<11:45,  1.56s/it, loss=0.0484, lr=1e-6]
Steps:  25%|██▍       | 149/600 [06:37<12:00,  1.60s/it, loss=0.0484, lr=1e-6]
Steps:  25%|██▍       | 149/600 [06:37<12:00,  1.60s/it, loss=0.0316, lr=1e-6]
Steps:  25%|██▌       | 150/600 [06:38<11:58,  1.60s/it, loss=0.0316, lr=1e-6]
Steps:  25%|██▌       | 150/600 [06:38<11:58,  1.60s/it, loss=0.301, lr=1e-6] 
Steps:  25%|██▌       | 151/600 [06:40<11:46,  1.57s/it, loss=0.301, lr=1e-6]
Steps:  25%|██▌       | 151/600 [06:40<11:46,  1.57s/it, loss=0.215, lr=1e-6]
Steps:  25%|██▌       | 152/600 [06:41<11:07,  1.49s/it, loss=0.215, lr=1e-6]
Steps:  25%|██▌       | 152/600 [06:41<11:07,  1.49s/it, loss=0.103, lr=1e-6]
Steps:  26%|██▌       | 153/600 [06:42<10:37,  1.43s/it, loss=0.103, lr=1e-6]
Steps:  26%|██▌       | 153/600 [06:42<10:37,  1.43s/it, loss=0.173, lr=1e-6]
Steps:  26%|██▌       | 154/600 [06:43<09:06,  1.23s/it, loss=0.173, lr=1e-6]
Steps:  26%|██▌       | 154/600 [06:43<09:06,  1.23s/it, loss=0.00466, lr=1e-6]
Steps:  26%|██▌       | 155/600 [06:46<12:12,  1.65s/it, loss=0.00466, lr=1e-6]
Steps:  26%|██▌       | 155/600 [06:46<12:12,  1.65s/it, loss=0.202, lr=1e-6]  
Steps:  26%|██▌       | 156/600 [06:47<11:42,  1.58s/it, loss=0.202, lr=1e-6]
Steps:  26%|██▌       | 156/600 [06:47<11:42,  1.58s/it, loss=0.187, lr=1e-6]
Steps:  26%|██▌       | 157/600 [06:49<11:17,  1.53s/it, loss=0.187, lr=1e-6]
Steps:  26%|██▌       | 157/600 [06:49<11:17,  1.53s/it, loss=0.0756, lr=1e-6]
Steps:  26%|██▋       | 158/600 [06:50<11:11,  1.52s/it, loss=0.0756, lr=1e-6]
Steps:  26%|██▋       | 158/600 [06:50<11:11,  1.52s/it, loss=0.114, lr=1e-6] 
Steps:  26%|██▋       | 159/600 [06:52<11:52,  1.62s/it, loss=0.114, lr=1e-6]
Steps:  26%|██▋       | 159/600 [06:52<11:52,  1.62s/it, loss=0.0806, lr=1e-6]
Steps:  27%|██▋       | 160/600 [06:54<12:07,  1.65s/it, loss=0.0806, lr=1e-6]
Steps:  27%|██▋       | 160/600 [06:54<12:07,  1.65s/it, loss=0.135, lr=1e-6] 
Steps:  27%|██▋       | 161/600 [06:55<11:27,  1.57s/it, loss=0.135, lr=1e-6]
Steps:  27%|██▋       | 161/600 [06:55<11:27,  1.57s/it, loss=0.0399, lr=1e-6]
Steps:  27%|██▋       | 162/600 [06:57<11:14,  1.54s/it, loss=0.0399, lr=1e-6]
Steps:  27%|██▋       | 162/600 [06:57<11:14,  1.54s/it, loss=0.0591, lr=1e-6]
Steps:  27%|██▋       | 163/600 [06:58<11:11,  1.54s/it, loss=0.0591, lr=1e-6]
Steps:  27%|██▋       | 163/600 [06:58<11:11,  1.54s/it, loss=0.00945, lr=1e-6]
Steps:  27%|██▋       | 164/600 [06:59<10:32,  1.45s/it, loss=0.00945, lr=1e-6]
Steps:  27%|██▋       | 164/600 [06:59<10:32,  1.45s/it, loss=0.116, lr=1e-6]  
Steps:  28%|██▊       | 165/600 [07:00<09:00,  1.24s/it, loss=0.116, lr=1e-6]
Steps:  28%|██▊       | 165/600 [07:00<09:00,  1.24s/it, loss=0.322, lr=1e-6]
Steps:  28%|██▊       | 166/600 [07:02<10:06,  1.40s/it, loss=0.322, lr=1e-6]
Steps:  28%|██▊       | 166/600 [07:02<10:06,  1.40s/it, loss=0.126, lr=1e-6]
Steps:  28%|██▊       | 167/600 [07:04<10:36,  1.47s/it, loss=0.126, lr=1e-6]
Steps:  28%|██▊       | 167/600 [07:04<10:36,  1.47s/it, loss=0.0785, lr=1e-6]
Steps:  28%|██▊       | 168/600 [07:05<11:05,  1.54s/it, loss=0.0785, lr=1e-6]
Steps:  28%|██▊       | 168/600 [07:05<11:05,  1.54s/it, loss=0.0382, lr=1e-6]
Steps:  28%|██▊       | 169/600 [07:07<11:49,  1.65s/it, loss=0.0382, lr=1e-6]
Steps:  28%|██▊       | 169/600 [07:07<11:49,  1.65s/it, loss=0.189, lr=1e-6] 
Steps:  28%|██▊       | 170/600 [07:09<12:02,  1.68s/it, loss=0.189, lr=1e-6]
Steps:  28%|██▊       | 170/600 [07:09<12:02,  1.68s/it, loss=0.142, lr=1e-6]
Steps:  28%|██▊       | 171/600 [07:10<11:45,  1.64s/it, loss=0.142, lr=1e-6]
Steps:  28%|██▊       | 171/600 [07:10<11:45,  1.64s/it, loss=0.217, lr=1e-6]
Steps:  29%|██▊       | 172/600 [07:12<11:30,  1.61s/it, loss=0.217, lr=1e-6]
Steps:  29%|██▊       | 172/600 [07:12<11:30,  1.61s/it, loss=0.196, lr=1e-6]
Steps:  29%|██▉       | 173/600 [07:13<11:16,  1.58s/it, loss=0.196, lr=1e-6]
Steps:  29%|██▉       | 173/600 [07:13<11:16,  1.58s/it, loss=0.13, lr=1e-6] 
Steps:  29%|██▉       | 174/600 [07:15<11:07,  1.57s/it, loss=0.13, lr=1e-6]
Steps:  29%|██▉       | 174/600 [07:15<11:07,  1.57s/it, loss=0.0101, lr=1e-6]
Steps:  29%|██▉       | 175/600 [07:16<10:30,  1.48s/it, loss=0.0101, lr=1e-6]
Steps:  29%|██▉       | 175/600 [07:16<10:30,  1.48s/it, loss=0.18, lr=1e-6]  
Steps:  29%|██▉       | 176/600 [07:17<08:56,  1.27s/it, loss=0.18, lr=1e-6]
Steps:  29%|██▉       | 176/600 [07:17<08:56,  1.27s/it, loss=0.0226, lr=1e-6]
Steps:  30%|██▉       | 177/600 [07:20<12:01,  1.71s/it, loss=0.0226, lr=1e-6]
Steps:  30%|██▉       | 177/600 [07:20<12:01,  1.71s/it, loss=0.0306, lr=1e-6]
Steps:  30%|██▉       | 178/600 [07:21<11:53,  1.69s/it, loss=0.0306, lr=1e-6]
Steps:  30%|██▉       | 178/600 [07:21<11:53,  1.69s/it, loss=0.0419, lr=1e-6]
Steps:  30%|██▉       | 179/600 [07:23<11:15,  1.60s/it, loss=0.0419, lr=1e-6]
Steps:  30%|██▉       | 179/600 [07:23<11:15,  1.60s/it, loss=0.0122, lr=1e-6]
Steps:  30%|███       | 180/600 [07:24<11:09,  1.59s/it, loss=0.0122, lr=1e-6]
Steps:  30%|███       | 180/600 [07:24<11:09,  1.59s/it, loss=0.159, lr=1e-6] 
Steps:  30%|███       | 181/600 [07:26<11:02,  1.58s/it, loss=0.159, lr=1e-6]
Steps:  30%|███       | 181/600 [07:26<11:02,  1.58s/it, loss=0.0305, lr=1e-6]
Steps:  30%|███       | 182/600 [07:28<11:00,  1.58s/it, loss=0.0305, lr=1e-6]
Steps:  30%|███       | 182/600 [07:28<11:00,  1.58s/it, loss=0.0696, lr=1e-6]
Steps:  30%|███       | 183/600 [07:29<10:44,  1.55s/it, loss=0.0696, lr=1e-6]
Steps:  30%|███       | 183/600 [07:29<10:44,  1.55s/it, loss=0.0929, lr=1e-6]
Steps:  31%|███       | 184/600 [07:31<10:44,  1.55s/it, loss=0.0929, lr=1e-6]
Steps:  31%|███       | 184/600 [07:31<10:44,  1.55s/it, loss=0.192, lr=1e-6] 
Steps:  31%|███       | 185/600 [07:32<10:45,  1.56s/it, loss=0.192, lr=1e-6]
Steps:  31%|███       | 185/600 [07:32<10:45,  1.56s/it, loss=0.00992, lr=1e-6]
Steps:  31%|███       | 186/600 [07:33<10:05,  1.46s/it, loss=0.00992, lr=1e-6]
Steps:  31%|███       | 186/600 [07:33<10:05,  1.46s/it, loss=0.0849, lr=1e-6] 
Steps:  31%|███       | 187/600 [07:34<08:36,  1.25s/it, loss=0.0849, lr=1e-6]
Steps:  31%|███       | 187/600 [07:34<08:36,  1.25s/it, loss=0.0337, lr=1e-6]
Steps:  31%|███▏      | 188/600 [07:37<11:08,  1.62s/it, loss=0.0337, lr=1e-6]
Steps:  31%|███▏      | 188/600 [07:37<11:08,  1.62s/it, loss=0.0579, lr=1e-6]
Steps:  32%|███▏      | 189/600 [07:38<10:55,  1.59s/it, loss=0.0579, lr=1e-6]
Steps:  32%|███▏      | 189/600 [07:38<10:55,  1.59s/it, loss=0.118, lr=1e-6] 
Steps:  32%|███▏      | 190/600 [07:40<11:10,  1.63s/it, loss=0.118, lr=1e-6]
Steps:  32%|███▏      | 190/600 [07:40<11:10,  1.63s/it, loss=0.194, lr=1e-6]
Steps:  32%|███▏      | 191/600 [07:41<10:54,  1.60s/it, loss=0.194, lr=1e-6]
Steps:  32%|███▏      | 191/600 [07:41<10:54,  1.60s/it, loss=0.2, lr=1e-6]  
Steps:  32%|███▏      | 192/600 [07:43<10:11,  1.50s/it, loss=0.2, lr=1e-6]
Steps:  32%|███▏      | 192/600 [07:43<10:11,  1.50s/it, loss=0.0975, lr=1e-6]
Steps:  32%|███▏      | 193/600 [07:44<10:45,  1.59s/it, loss=0.0975, lr=1e-6]
Steps:  32%|███▏      | 193/600 [07:44<10:45,  1.59s/it, loss=0.124, lr=1e-6] 
Steps:  32%|███▏      | 194/600 [07:47<11:44,  1.73s/it, loss=0.124, lr=1e-6]
Steps:  32%|███▏      | 194/600 [07:47<11:44,  1.73s/it, loss=0.125, lr=1e-6]
Steps:  32%|███▎      | 195/600 [07:48<11:15,  1.67s/it, loss=0.125, lr=1e-6]
Steps:  32%|███▎      | 195/600 [07:48<11:15,  1.67s/it, loss=0.00829, lr=1e-6]
Steps:  33%|███▎      | 196/600 [07:49<10:38,  1.58s/it, loss=0.00829, lr=1e-6]
Steps:  33%|███▎      | 196/600 [07:49<10:38,  1.58s/it, loss=0.0212, lr=1e-6] 
Steps:  33%|███▎      | 197/600 [07:51<10:00,  1.49s/it, loss=0.0212, lr=1e-6]
Steps:  33%|███▎      | 197/600 [07:51<10:00,  1.49s/it, loss=0.038, lr=1e-6] 
Steps:  33%|███▎      | 198/600 [07:51<08:30,  1.27s/it, loss=0.038, lr=1e-6]
Steps:  33%|███▎      | 198/600 [07:51<08:30,  1.27s/it, loss=0.135, lr=1e-6]
Steps:  33%|███▎      | 199/600 [07:53<09:58,  1.49s/it, loss=0.135, lr=1e-6]
Steps:  33%|███▎      | 199/600 [07:53<09:58,  1.49s/it, loss=0.0286, lr=1e-6]
Steps:  33%|███▎      | 200/600 [07:55<09:53,  1.48s/it, loss=0.0286, lr=1e-6]
Steps:  33%|███▎      | 200/600 [07:55<09:53,  1.48s/it, loss=0.143, lr=1e-6] 
Steps:  34%|███▎      | 201/600 [07:57<10:20,  1.55s/it, loss=0.143, lr=1e-6]
Steps:  34%|███▎      | 201/600 [07:57<10:20,  1.55s/it, loss=0.128, lr=1e-6]
Steps:  34%|███▎      | 202/600 [07:59<10:56,  1.65s/it, loss=0.128, lr=1e-6]
Steps:  34%|███▎      | 202/600 [07:59<10:56,  1.65s/it, loss=0.00996, lr=1e-6]
Steps:  34%|███▍      | 203/600 [08:00<10:56,  1.65s/it, loss=0.00996, lr=1e-6]
Steps:  34%|███▍      | 203/600 [08:00<10:56,  1.65s/it, loss=0.156, lr=1e-6]  
Steps:  34%|███▍      | 204/600 [08:02<11:02,  1.67s/it, loss=0.156, lr=1e-6]
Steps:  34%|███▍      | 204/600 [08:02<11:02,  1.67s/it, loss=0.0106, lr=1e-6]
Steps:  34%|███▍      | 205/600 [08:03<10:18,  1.57s/it, loss=0.0106, lr=1e-6]
Steps:  34%|███▍      | 205/600 [08:03<10:18,  1.57s/it, loss=0.0953, lr=1e-6]
Steps:  34%|███▍      | 206/600 [08:05<10:23,  1.58s/it, loss=0.0953, lr=1e-6]
Steps:  34%|███▍      | 206/600 [08:05<10:23,  1.58s/it, loss=0.127, lr=1e-6] 
Steps:  34%|███▍      | 207/600 [08:06<10:29,  1.60s/it, loss=0.127, lr=1e-6]
Steps:  34%|███▍      | 207/600 [08:06<10:29,  1.60s/it, loss=0.13, lr=1e-6] 
Steps:  35%|███▍      | 208/600 [08:08<09:47,  1.50s/it, loss=0.13, lr=1e-6]
Steps:  35%|███▍      | 208/600 [08:08<09:47,  1.50s/it, loss=0.0312, lr=1e-6]
Steps:  35%|███▍      | 209/600 [08:09<08:19,  1.28s/it, loss=0.0312, lr=1e-6]
Steps:  35%|███▍      | 209/600 [08:09<08:19,  1.28s/it, loss=0.0228, lr=1e-6]
Steps:  35%|███▌      | 210/600 [08:11<10:31,  1.62s/it, loss=0.0228, lr=1e-6]
Steps:  35%|███▌      | 210/600 [08:11<10:31,  1.62s/it, loss=0.102, lr=1e-6] 
Steps:  35%|███▌      | 211/600 [08:12<10:12,  1.57s/it, loss=0.102, lr=1e-6]
Steps:  35%|███▌      | 211/600 [08:12<10:12,  1.57s/it, loss=0.0855, lr=1e-6]
Steps:  35%|███▌      | 212/600 [08:14<10:05,  1.56s/it, loss=0.0855, lr=1e-6]
Steps:  35%|███▌      | 212/600 [08:14<10:05,  1.56s/it, loss=0.0158, lr=1e-6]
Steps:  36%|███▌      | 213/600 [08:16<10:33,  1.64s/it, loss=0.0158, lr=1e-6]
Steps:  36%|███▌      | 213/600 [08:16<10:33,  1.64s/it, loss=0.00723, lr=1e-6]
Steps:  36%|███▌      | 214/600 [08:17<10:06,  1.57s/it, loss=0.00723, lr=1e-6]
Steps:  36%|███▌      | 214/600 [08:17<10:06,  1.57s/it, loss=0.00746, lr=1e-6]
Steps:  36%|███▌      | 215/600 [08:19<09:58,  1.55s/it, loss=0.00746, lr=1e-6]
Steps:  36%|███▌      | 215/600 [08:19<09:58,  1.55s/it, loss=0.156, lr=1e-6]  
Steps:  36%|███▌      | 216/600 [08:20<10:06,  1.58s/it, loss=0.156, lr=1e-6]
Steps:  36%|███▌      | 216/600 [08:20<10:06,  1.58s/it, loss=0.132, lr=1e-6]
Steps:  36%|███▌      | 217/600 [08:22<10:51,  1.70s/it, loss=0.132, lr=1e-6]
Steps:  36%|███▌      | 217/600 [08:22<10:51,  1.70s/it, loss=0.0999, lr=1e-6]
Steps:  36%|███▋      | 218/600 [08:24<10:22,  1.63s/it, loss=0.0999, lr=1e-6]
Steps:  36%|███▋      | 218/600 [08:24<10:22,  1.63s/it, loss=0.132, lr=1e-6] 
Steps:  36%|███▋      | 219/600 [08:25<09:43,  1.53s/it, loss=0.132, lr=1e-6]
Steps:  36%|███▋      | 219/600 [08:25<09:43,  1.53s/it, loss=0.0641, lr=1e-6]
Steps:  37%|███▋      | 220/600 [08:26<08:15,  1.30s/it, loss=0.0641, lr=1e-6]
Steps:  37%|███▋      | 220/600 [08:26<08:15,  1.30s/it, loss=0.0302, lr=1e-6]
Steps:  37%|███▋      | 221/600 [08:28<09:42,  1.54s/it, loss=0.0302, lr=1e-6]
Steps:  37%|███▋      | 221/600 [08:28<09:42,  1.54s/it, loss=0.0978, lr=1e-6]
Steps:  37%|███▋      | 222/600 [08:30<09:58,  1.58s/it, loss=0.0978, lr=1e-6]
Steps:  37%|███▋      | 222/600 [08:30<09:58,  1.58s/it, loss=0.0814, lr=1e-6]
Steps:  37%|███▋      | 223/600 [08:31<10:10,  1.62s/it, loss=0.0814, lr=1e-6]
Steps:  37%|███▋      | 223/600 [08:31<10:10,  1.62s/it, loss=0.261, lr=1e-6] 
Steps:  37%|███▋      | 224/600 [08:33<10:07,  1.62s/it, loss=0.261, lr=1e-6]
Steps:  37%|███▋      | 224/600 [08:33<10:07,  1.62s/it, loss=0.0114, lr=1e-6]
Steps:  38%|███▊      | 225/600 [08:35<10:18,  1.65s/it, loss=0.0114, lr=1e-6]
Steps:  38%|███▊      | 225/600 [08:35<10:18,  1.65s/it, loss=0.13, lr=1e-6]  
Steps:  38%|███▊      | 226/600 [08:36<10:19,  1.66s/it, loss=0.13, lr=1e-6]
Steps:  38%|███▊      | 226/600 [08:36<10:19,  1.66s/it, loss=0.0929, lr=1e-6]
Steps:  38%|███▊      | 227/600 [08:38<10:02,  1.62s/it, loss=0.0929, lr=1e-6]
Steps:  38%|███▊      | 227/600 [08:38<10:02,  1.62s/it, loss=0.17, lr=1e-6]  
Steps:  38%|███▊      | 228/600 [08:40<10:08,  1.63s/it, loss=0.17, lr=1e-6]
Steps:  38%|███▊      | 228/600 [08:40<10:08,  1.63s/it, loss=0.304, lr=1e-6]
Steps:  38%|███▊      | 229/600 [08:41<09:45,  1.58s/it, loss=0.304, lr=1e-6]
Steps:  38%|███▊      | 229/600 [08:41<09:45,  1.58s/it, loss=0.0858, lr=1e-6]
Steps:  38%|███▊      | 230/600 [08:42<09:21,  1.52s/it, loss=0.0858, lr=1e-6]
Steps:  38%|███▊      | 230/600 [08:42<09:21,  1.52s/it, loss=0.0257, lr=1e-6]
Steps:  38%|███▊      | 231/600 [08:43<07:56,  1.29s/it, loss=0.0257, lr=1e-6]
Steps:  38%|███▊      | 231/600 [08:43<07:56,  1.29s/it, loss=0.0237, lr=1e-6]
Steps:  39%|███▊      | 232/600 [08:46<10:09,  1.66s/it, loss=0.0237, lr=1e-6]
Steps:  39%|███▊      | 232/600 [08:46<10:09,  1.66s/it, loss=0.066, lr=1e-6] 
Steps:  39%|███▉      | 233/600 [08:47<10:00,  1.64s/it, loss=0.066, lr=1e-6]
Steps:  39%|███▉      | 233/600 [08:47<10:00,  1.64s/it, loss=0.134, lr=1e-6]
Steps:  39%|███▉      | 234/600 [08:49<09:39,  1.58s/it, loss=0.134, lr=1e-6]
Steps:  39%|███▉      | 234/600 [08:49<09:39,  1.58s/it, loss=0.0541, lr=1e-6]
Steps:  39%|███▉      | 235/600 [08:50<09:55,  1.63s/it, loss=0.0541, lr=1e-6]
Steps:  39%|███▉      | 235/600 [08:50<09:55,  1.63s/it, loss=0.0954, lr=1e-6]
Steps:  39%|███▉      | 236/600 [08:52<09:38,  1.59s/it, loss=0.0954, lr=1e-6]
Steps:  39%|███▉      | 236/600 [08:52<09:38,  1.59s/it, loss=0.0111, lr=1e-6]
Steps:  40%|███▉      | 237/600 [08:53<09:18,  1.54s/it, loss=0.0111, lr=1e-6]
Steps:  40%|███▉      | 237/600 [08:53<09:18,  1.54s/it, loss=0.0576, lr=1e-6]
Steps:  40%|███▉      | 238/600 [08:55<09:01,  1.49s/it, loss=0.0576, lr=1e-6]
Steps:  40%|███▉      | 238/600 [08:55<09:01,  1.49s/it, loss=0.0608, lr=1e-6]
Steps:  40%|███▉      | 239/600 [08:57<09:35,  1.59s/it, loss=0.0608, lr=1e-6]
Steps:  40%|███▉      | 239/600 [08:57<09:35,  1.59s/it, loss=0.0454, lr=1e-6]
Steps:  40%|████      | 240/600 [08:58<09:24,  1.57s/it, loss=0.0454, lr=1e-6]
Steps:  40%|████      | 240/600 [08:58<09:24,  1.57s/it, loss=0.139, lr=1e-6] 
Steps:  40%|████      | 241/600 [08:59<08:49,  1.47s/it, loss=0.139, lr=1e-6]
Steps:  40%|████      | 241/600 [08:59<08:49,  1.47s/it, loss=0.0687, lr=1e-6]
Steps:  40%|████      | 242/600 [09:00<07:30,  1.26s/it, loss=0.0687, lr=1e-6]
Steps:  40%|████      | 242/600 [09:00<07:30,  1.26s/it, loss=0.0111, lr=1e-6]
Steps:  40%|████      | 243/600 [09:02<09:06,  1.53s/it, loss=0.0111, lr=1e-6]
Steps:  40%|████      | 243/600 [09:02<09:06,  1.53s/it, loss=0.204, lr=1e-6] 
Steps:  41%|████      | 244/600 [09:04<09:15,  1.56s/it, loss=0.204, lr=1e-6]
Steps:  41%|████      | 244/600 [09:04<09:15,  1.56s/it, loss=0.0118, lr=1e-6]
Steps:  41%|████      | 245/600 [09:05<09:03,  1.53s/it, loss=0.0118, lr=1e-6]
Steps:  41%|████      | 245/600 [09:05<09:03,  1.53s/it, loss=0.143, lr=1e-6] 
Steps:  41%|████      | 246/600 [09:07<09:03,  1.54s/it, loss=0.143, lr=1e-6]
Steps:  41%|████      | 246/600 [09:07<09:03,  1.54s/it, loss=0.168, lr=1e-6]
Steps:  41%|████      | 247/600 [09:08<09:02,  1.54s/it, loss=0.168, lr=1e-6]
Steps:  41%|████      | 247/600 [09:08<09:02,  1.54s/it, loss=0.127, lr=1e-6]
Steps:  41%|████▏     | 248/600 [09:10<09:14,  1.58s/it, loss=0.127, lr=1e-6]
Steps:  41%|████▏     | 248/600 [09:10<09:14,  1.58s/it, loss=0.277, lr=1e-6]
Steps:  42%|████▏     | 249/600 [09:12<09:14,  1.58s/it, loss=0.277, lr=1e-6]
Steps:  42%|████▏     | 249/600 [09:12<09:14,  1.58s/it, loss=0.128, lr=1e-6]
Steps:  42%|████▏     | 250/600 [09:13<09:11,  1.58s/it, loss=0.128, lr=1e-6]
Steps:  42%|████▏     | 250/600 [09:13<09:11,  1.58s/it, loss=0.133, lr=1e-6]
Steps:  42%|████▏     | 251/600 [09:15<09:15,  1.59s/it, loss=0.133, lr=1e-6]
Steps:  42%|████▏     | 251/600 [09:15<09:15,  1.59s/it, loss=0.2, lr=1e-6]  
Steps:  42%|████▏     | 252/600 [09:16<09:02,  1.56s/it, loss=0.2, lr=1e-6]
Steps:  42%|████▏     | 252/600 [09:16<09:02,  1.56s/it, loss=0.19, lr=1e-6]
Steps:  42%|████▏     | 253/600 [09:17<07:37,  1.32s/it, loss=0.19, lr=1e-6]
Steps:  42%|████▏     | 253/600 [09:17<07:37,  1.32s/it, loss=0.0961, lr=1e-6]
Steps:  42%|████▏     | 254/600 [09:19<09:20,  1.62s/it, loss=0.0961, lr=1e-6]
Steps:  42%|████▏     | 254/600 [09:19<09:20,  1.62s/it, loss=0.162, lr=1e-6] 
Steps:  42%|████▎     | 255/600 [09:21<08:50,  1.54s/it, loss=0.162, lr=1e-6]
Steps:  42%|████▎     | 255/600 [09:21<08:50,  1.54s/it, loss=0.081, lr=1e-6]
Steps:  43%|████▎     | 256/600 [09:22<09:02,  1.58s/it, loss=0.081, lr=1e-6]
Steps:  43%|████▎     | 256/600 [09:22<09:02,  1.58s/it, loss=0.151, lr=1e-6]
Steps:  43%|████▎     | 257/600 [09:24<09:01,  1.58s/it, loss=0.151, lr=1e-6]
Steps:  43%|████▎     | 257/600 [09:24<09:01,  1.58s/it, loss=0.142, lr=1e-6]
Steps:  43%|████▎     | 258/600 [09:25<08:38,  1.52s/it, loss=0.142, lr=1e-6]
Steps:  43%|████▎     | 258/600 [09:25<08:38,  1.52s/it, loss=0.166, lr=1e-6]
Steps:  43%|████▎     | 259/600 [09:27<08:29,  1.49s/it, loss=0.166, lr=1e-6]
Steps:  43%|████▎     | 259/600 [09:27<08:29,  1.49s/it, loss=0.0145, lr=1e-6]
Steps:  43%|████▎     | 260/600 [09:29<08:52,  1.57s/it, loss=0.0145, lr=1e-6]
Steps:  43%|████▎     | 260/600 [09:29<08:52,  1.57s/it, loss=0.223, lr=1e-6] 
Steps:  44%|████▎     | 261/600 [09:30<09:03,  1.60s/it, loss=0.223, lr=1e-6]
Steps:  44%|████▎     | 261/600 [09:30<09:03,  1.60s/it, loss=0.0998, lr=1e-6]
Steps:  44%|████▎     | 262/600 [09:32<09:13,  1.64s/it, loss=0.0998, lr=1e-6]
Steps:  44%|████▎     | 262/600 [09:32<09:13,  1.64s/it, loss=0.0817, lr=1e-6]
Steps:  44%|████▍     | 263/600 [09:33<08:45,  1.56s/it, loss=0.0817, lr=1e-6]
Steps:  44%|████▍     | 263/600 [09:33<08:45,  1.56s/it, loss=0.0822, lr=1e-6]
Steps:  44%|████▍     | 264/600 [09:34<07:23,  1.32s/it, loss=0.0822, lr=1e-6]
Steps:  44%|████▍     | 264/600 [09:34<07:23,  1.32s/it, loss=0.354, lr=1e-6] 
Steps:  44%|████▍     | 265/600 [09:37<09:25,  1.69s/it, loss=0.354, lr=1e-6]
Steps:  44%|████▍     | 265/600 [09:37<09:25,  1.69s/it, loss=0.0309, lr=1e-6]
Steps:  44%|████▍     | 266/600 [09:38<09:35,  1.72s/it, loss=0.0309, lr=1e-6]
Steps:  44%|████▍     | 266/600 [09:38<09:35,  1.72s/it, loss=0.143, lr=1e-6] 
Steps:  44%|████▍     | 267/600 [09:40<09:30,  1.71s/it, loss=0.143, lr=1e-6]
Steps:  44%|████▍     | 267/600 [09:40<09:30,  1.71s/it, loss=0.191, lr=1e-6]
Steps:  45%|████▍     | 268/600 [09:42<09:12,  1.66s/it, loss=0.191, lr=1e-6]
Steps:  45%|████▍     | 268/600 [09:42<09:12,  1.66s/it, loss=0.189, lr=1e-6]
Steps:  45%|████▍     | 269/600 [09:43<08:36,  1.56s/it, loss=0.189, lr=1e-6]
Steps:  45%|████▍     | 269/600 [09:43<08:36,  1.56s/it, loss=0.162, lr=1e-6]
Steps:  45%|████▌     | 270/600 [09:45<08:35,  1.56s/it, loss=0.162, lr=1e-6]
Steps:  45%|████▌     | 270/600 [09:45<08:35,  1.56s/it, loss=0.202, lr=1e-6]
Steps:  45%|████▌     | 271/600 [09:46<08:05,  1.48s/it, loss=0.202, lr=1e-6]
Steps:  45%|████▌     | 271/600 [09:46<08:05,  1.48s/it, loss=0.25, lr=1e-6] 
Steps:  45%|████▌     | 272/600 [09:47<08:17,  1.52s/it, loss=0.25, lr=1e-6]
Steps:  45%|████▌     | 272/600 [09:47<08:17,  1.52s/it, loss=0.0323, lr=1e-6]
Steps:  46%|████▌     | 273/600 [09:49<08:18,  1.52s/it, loss=0.0323, lr=1e-6]
Steps:  46%|████▌     | 273/600 [09:49<08:18,  1.52s/it, loss=0.0217, lr=1e-6]
Steps:  46%|████▌     | 274/600 [09:50<08:02,  1.48s/it, loss=0.0217, lr=1e-6]
Steps:  46%|████▌     | 274/600 [09:50<08:02,  1.48s/it, loss=0.15, lr=1e-6]  
Steps:  46%|████▌     | 275/600 [09:51<06:49,  1.26s/it, loss=0.15, lr=1e-6]
Steps:  46%|████▌     | 275/600 [09:51<06:49,  1.26s/it, loss=0.0137, lr=1e-6]
Steps:  46%|████▌     | 276/600 [09:53<08:28,  1.57s/it, loss=0.0137, lr=1e-6]
Steps:  46%|████▌     | 276/600 [09:53<08:28,  1.57s/it, loss=0.197, lr=1e-6] 
Steps:  46%|████▌     | 277/600 [09:55<08:32,  1.59s/it, loss=0.197, lr=1e-6]
Steps:  46%|████▌     | 277/600 [09:55<08:32,  1.59s/it, loss=0.0147, lr=1e-6]
Steps:  46%|████▋     | 278/600 [09:57<08:54,  1.66s/it, loss=0.0147, lr=1e-6]
Steps:  46%|████▋     | 278/600 [09:57<08:54,  1.66s/it, loss=0.22, lr=1e-6]  
Steps:  46%|████▋     | 279/600 [09:58<08:47,  1.64s/it, loss=0.22, lr=1e-6]
Steps:  46%|████▋     | 279/600 [09:58<08:47,  1.64s/it, loss=0.316, lr=1e-6]
Steps:  47%|████▋     | 280/600 [10:00<08:26,  1.58s/it, loss=0.316, lr=1e-6]
Steps:  47%|████▋     | 280/600 [10:00<08:26,  1.58s/it, loss=0.0261, lr=1e-6]
Steps:  47%|████▋     | 281/600 [10:01<08:03,  1.52s/it, loss=0.0261, lr=1e-6]
Steps:  47%|████▋     | 281/600 [10:01<08:03,  1.52s/it, loss=0.0655, lr=1e-6]
Steps:  47%|████▋     | 282/600 [10:03<08:17,  1.56s/it, loss=0.0655, lr=1e-6]
Steps:  47%|████▋     | 282/600 [10:03<08:17,  1.56s/it, loss=0.164, lr=1e-6] 
Steps:  47%|████▋     | 283/600 [10:04<08:07,  1.54s/it, loss=0.164, lr=1e-6]
Steps:  47%|████▋     | 283/600 [10:04<08:07,  1.54s/it, loss=0.142, lr=1e-6]
Steps:  47%|████▋     | 284/600 [10:06<08:22,  1.59s/it, loss=0.142, lr=1e-6]
Steps:  47%|████▋     | 284/600 [10:06<08:22,  1.59s/it, loss=0.134, lr=1e-6]
Steps:  48%|████▊     | 285/600 [10:07<07:52,  1.50s/it, loss=0.134, lr=1e-6]
Steps:  48%|████▊     | 285/600 [10:07<07:52,  1.50s/it, loss=0.179, lr=1e-6]
Steps:  48%|████▊     | 286/600 [10:08<06:40,  1.27s/it, loss=0.179, lr=1e-6]
Steps:  48%|████▊     | 286/600 [10:08<06:40,  1.27s/it, loss=0.133, lr=1e-6]
Steps:  48%|████▊     | 287/600 [10:10<08:08,  1.56s/it, loss=0.133, lr=1e-6]
Steps:  48%|████▊     | 287/600 [10:10<08:08,  1.56s/it, loss=0.0269, lr=1e-6]
Steps:  48%|████▊     | 288/600 [10:12<08:09,  1.57s/it, loss=0.0269, lr=1e-6]
Steps:  48%|████▊     | 288/600 [10:12<08:09,  1.57s/it, loss=0.205, lr=1e-6] 
Steps:  48%|████▊     | 289/600 [10:14<08:18,  1.60s/it, loss=0.205, lr=1e-6]
Steps:  48%|████▊     | 289/600 [10:14<08:18,  1.60s/it, loss=0.0264, lr=1e-6]
Steps:  48%|████▊     | 290/600 [10:15<08:17,  1.61s/it, loss=0.0264, lr=1e-6]
Steps:  48%|████▊     | 290/600 [10:15<08:17,  1.61s/it, loss=0.027, lr=1e-6] 
Steps:  48%|████▊     | 291/600 [10:17<07:50,  1.52s/it, loss=0.027, lr=1e-6]
Steps:  48%|████▊     | 291/600 [10:17<07:50,  1.52s/it, loss=0.191, lr=1e-6]
Steps:  49%|████▊     | 292/600 [10:18<07:35,  1.48s/it, loss=0.191, lr=1e-6]
Steps:  49%|████▊     | 292/600 [10:18<07:35,  1.48s/it, loss=0.0225, lr=1e-6]
Steps:  49%|████▉     | 293/600 [10:20<08:05,  1.58s/it, loss=0.0225, lr=1e-6]
Steps:  49%|████▉     | 293/600 [10:20<08:05,  1.58s/it, loss=0.0589, lr=1e-6]
Steps:  49%|████▉     | 294/600 [10:21<07:54,  1.55s/it, loss=0.0589, lr=1e-6]
Steps:  49%|████▉     | 294/600 [10:21<07:54,  1.55s/it, loss=0.143, lr=1e-6] 
Steps:  49%|████▉     | 295/600 [10:23<08:10,  1.61s/it, loss=0.143, lr=1e-6]
Steps:  49%|████▉     | 295/600 [10:23<08:10,  1.61s/it, loss=0.00961, lr=1e-6]
Steps:  49%|████▉     | 296/600 [10:25<07:54,  1.56s/it, loss=0.00961, lr=1e-6]
Steps:  49%|████▉     | 296/600 [10:25<07:54,  1.56s/it, loss=0.193, lr=1e-6]  
Steps:  50%|████▉     | 297/600 [10:25<06:40,  1.32s/it, loss=0.193, lr=1e-6]
Steps:  50%|████▉     | 297/600 [10:25<06:40,  1.32s/it, loss=0.32, lr=1e-6] 
Steps:  50%|████▉     | 298/600 [10:28<08:05,  1.61s/it, loss=0.32, lr=1e-6]
Steps:  50%|████▉     | 298/600 [10:28<08:05,  1.61s/it, loss=0.0165, lr=1e-6]
Steps:  50%|████▉     | 299/600 [10:29<08:05,  1.61s/it, loss=0.0165, lr=1e-6]
Steps:  50%|████▉     | 299/600 [10:29<08:05,  1.61s/it, loss=0.233, lr=1e-6] 
Steps:  50%|█████     | 300/600 [10:31<08:15,  1.65s/it, loss=0.233, lr=1e-6]
Steps:  50%|█████     | 300/600 [10:31<08:15,  1.65s/it, loss=0.0172, lr=1e-6]
Steps:  50%|█████     | 301/600 [10:33<08:13,  1.65s/it, loss=0.0172, lr=1e-6]
Steps:  50%|█████     | 301/600 [10:33<08:13,  1.65s/it, loss=0.284, lr=1e-6] 
Steps:  50%|█████     | 302/600 [10:34<07:43,  1.56s/it, loss=0.284, lr=1e-6]
Steps:  50%|█████     | 302/600 [10:34<07:43,  1.56s/it, loss=0.236, lr=1e-6]
Steps:  50%|█████     | 303/600 [10:35<07:29,  1.51s/it, loss=0.236, lr=1e-6]
Steps:  50%|█████     | 303/600 [10:35<07:29,  1.51s/it, loss=0.163, lr=1e-6]
Steps:  51%|█████     | 304/600 [10:37<07:50,  1.59s/it, loss=0.163, lr=1e-6]
Steps:  51%|█████     | 304/600 [10:37<07:50,  1.59s/it, loss=0.22, lr=1e-6] 
Steps:  51%|█████     | 305/600 [10:39<07:59,  1.63s/it, loss=0.22, lr=1e-6]
Steps:  51%|█████     | 305/600 [10:39<07:59,  1.63s/it, loss=0.219, lr=1e-6]
Steps:  51%|█████     | 306/600 [10:40<07:46,  1.59s/it, loss=0.219, lr=1e-6]
Steps:  51%|█████     | 306/600 [10:40<07:46,  1.59s/it, loss=0.00363, lr=1e-6]
Steps:  51%|█████     | 307/600 [10:42<07:17,  1.49s/it, loss=0.00363, lr=1e-6]
Steps:  51%|█████     | 307/600 [10:42<07:17,  1.49s/it, loss=0.136, lr=1e-6]  
Steps:  51%|█████▏    | 308/600 [10:42<06:12,  1.27s/it, loss=0.136, lr=1e-6]
Steps:  51%|█████▏    | 308/600 [10:42<06:12,  1.27s/it, loss=0.292, lr=1e-6]
Steps:  52%|█████▏    | 309/600 [10:44<07:15,  1.50s/it, loss=0.292, lr=1e-6]
Steps:  52%|█████▏    | 309/600 [10:44<07:15,  1.50s/it, loss=0.212, lr=1e-6]
Steps:  52%|█████▏    | 310/600 [10:46<07:27,  1.54s/it, loss=0.212, lr=1e-6]
Steps:  52%|█████▏    | 310/600 [10:46<07:27,  1.54s/it, loss=0.161, lr=1e-6]
Steps:  52%|█████▏    | 311/600 [10:47<07:19,  1.52s/it, loss=0.161, lr=1e-6]
Steps:  52%|█████▏    | 311/600 [10:47<07:19,  1.52s/it, loss=0.103, lr=1e-6]
Steps:  52%|█████▏    | 312/600 [10:49<07:34,  1.58s/it, loss=0.103, lr=1e-6]
Steps:  52%|█████▏    | 312/600 [10:49<07:34,  1.58s/it, loss=0.0259, lr=1e-6]
Steps:  52%|█████▏    | 313/600 [10:51<07:41,  1.61s/it, loss=0.0259, lr=1e-6]
Steps:  52%|█████▏    | 313/600 [10:51<07:41,  1.61s/it, loss=0.164, lr=1e-6] 
Steps:  52%|█████▏    | 314/600 [10:53<07:45,  1.63s/it, loss=0.164, lr=1e-6]
Steps:  52%|█████▏    | 314/600 [10:53<07:45,  1.63s/it, loss=0.0721, lr=1e-6]
Steps:  52%|█████▎    | 315/600 [10:54<07:43,  1.63s/it, loss=0.0721, lr=1e-6]
Steps:  52%|█████▎    | 315/600 [10:54<07:43,  1.63s/it, loss=0.0125, lr=1e-6]
Steps:  53%|█████▎    | 316/600 [10:56<07:40,  1.62s/it, loss=0.0125, lr=1e-6]
Steps:  53%|█████▎    | 316/600 [10:56<07:40,  1.62s/it, loss=0.299, lr=1e-6] 
Steps:  53%|█████▎    | 317/600 [10:57<07:40,  1.63s/it, loss=0.299, lr=1e-6]
Steps:  53%|█████▎    | 317/600 [10:57<07:40,  1.63s/it, loss=0.0487, lr=1e-6]
Steps:  53%|█████▎    | 318/600 [10:59<06:54,  1.47s/it, loss=0.0487, lr=1e-6]
Steps:  53%|█████▎    | 318/600 [10:59<06:54,  1.47s/it, loss=0.0458, lr=1e-6]
Steps:  53%|█████▎    | 319/600 [10:59<05:53,  1.26s/it, loss=0.0458, lr=1e-6]
Steps:  53%|█████▎    | 319/600 [10:59<05:53,  1.26s/it, loss=0.0431, lr=1e-6]
Steps:  53%|█████▎    | 320/600 [11:01<07:13,  1.55s/it, loss=0.0431, lr=1e-6]
Steps:  53%|█████▎    | 320/600 [11:01<07:13,  1.55s/it, loss=0.013, lr=1e-6] 
Steps:  54%|█████▎    | 321/600 [11:03<07:27,  1.61s/it, loss=0.013, lr=1e-6]
Steps:  54%|█████▎    | 321/600 [11:03<07:27,  1.61s/it, loss=0.229, lr=1e-6]
Steps:  54%|█████▎    | 322/600 [11:05<07:13,  1.56s/it, loss=0.229, lr=1e-6]
Steps:  54%|█████▎    | 322/600 [11:05<07:13,  1.56s/it, loss=0.147, lr=1e-6]
Steps:  54%|█████▍    | 323/600 [11:06<07:22,  1.60s/it, loss=0.147, lr=1e-6]
Steps:  54%|█████▍    | 323/600 [11:06<07:22,  1.60s/it, loss=0.142, lr=1e-6]
Steps:  54%|█████▍    | 324/600 [11:08<07:30,  1.63s/it, loss=0.142, lr=1e-6]
Steps:  54%|█████▍    | 324/600 [11:08<07:30,  1.63s/it, loss=0.231, lr=1e-6]
Steps:  54%|█████▍    | 325/600 [11:10<07:29,  1.64s/it, loss=0.231, lr=1e-6]
Steps:  54%|█████▍    | 325/600 [11:10<07:29,  1.64s/it, loss=0.23, lr=1e-6] 
Steps:  54%|█████▍    | 326/600 [11:11<07:03,  1.54s/it, loss=0.23, lr=1e-6]
Steps:  54%|█████▍    | 326/600 [11:11<07:03,  1.54s/it, loss=0.0906, lr=1e-6]
Steps:  55%|█████▍    | 327/600 [11:13<07:12,  1.59s/it, loss=0.0906, lr=1e-6]
Steps:  55%|█████▍    | 327/600 [11:13<07:12,  1.59s/it, loss=0.119, lr=1e-6] 
Steps:  55%|█████▍    | 328/600 [11:14<07:15,  1.60s/it, loss=0.119, lr=1e-6]
Steps:  55%|█████▍    | 328/600 [11:14<07:15,  1.60s/it, loss=0.127, lr=1e-6]
Steps:  55%|█████▍    | 329/600 [11:15<06:33,  1.45s/it, loss=0.127, lr=1e-6]
Steps:  55%|█████▍    | 329/600 [11:15<06:33,  1.45s/it, loss=0.0297, lr=1e-6]
Steps:  55%|█████▌    | 330/600 [11:16<05:35,  1.24s/it, loss=0.0297, lr=1e-6]
Steps:  55%|█████▌    | 330/600 [11:16<05:35,  1.24s/it, loss=0.169, lr=1e-6] 
Steps:  55%|█████▌    | 331/600 [11:18<06:47,  1.52s/it, loss=0.169, lr=1e-6]
Steps:  55%|█████▌    | 331/600 [11:18<06:47,  1.52s/it, loss=0.0211, lr=1e-6]
Steps:  55%|█████▌    | 332/600 [11:20<06:55,  1.55s/it, loss=0.0211, lr=1e-6]
Steps:  55%|█████▌    | 332/600 [11:20<06:55,  1.55s/it, loss=0.00363, lr=1e-6]
Steps:  56%|█████▌    | 333/600 [11:22<07:00,  1.57s/it, loss=0.00363, lr=1e-6]
Steps:  56%|█████▌    | 333/600 [11:22<07:00,  1.57s/it, loss=0.139, lr=1e-6]  
Steps:  56%|█████▌    | 334/600 [11:24<07:23,  1.67s/it, loss=0.139, lr=1e-6]
Steps:  56%|█████▌    | 334/600 [11:24<07:23,  1.67s/it, loss=0.192, lr=1e-6]
Steps:  56%|█████▌    | 335/600 [11:25<07:20,  1.66s/it, loss=0.192, lr=1e-6]
Steps:  56%|█████▌    | 335/600 [11:25<07:20,  1.66s/it, loss=0.131, lr=1e-6]
Steps:  56%|█████▌    | 336/600 [11:27<07:17,  1.66s/it, loss=0.131, lr=1e-6]
Steps:  56%|█████▌    | 336/600 [11:27<07:17,  1.66s/it, loss=0.0126, lr=1e-6]
Steps:  56%|█████▌    | 337/600 [11:28<07:10,  1.64s/it, loss=0.0126, lr=1e-6]
Steps:  56%|█████▌    | 337/600 [11:28<07:10,  1.64s/it, loss=0.0961, lr=1e-6]
Steps:  56%|█████▋    | 338/600 [11:30<06:46,  1.55s/it, loss=0.0961, lr=1e-6]
Steps:  56%|█████▋    | 338/600 [11:30<06:46,  1.55s/it, loss=0.158, lr=1e-6] 
Steps:  56%|█████▋    | 339/600 [11:31<06:39,  1.53s/it, loss=0.158, lr=1e-6]
Steps:  56%|█████▋    | 339/600 [11:31<06:39,  1.53s/it, loss=0.125, lr=1e-6]
Steps:  57%|█████▋    | 340/600 [11:32<06:13,  1.44s/it, loss=0.125, lr=1e-6]
Steps:  57%|█████▋    | 340/600 [11:32<06:13,  1.44s/it, loss=0.152, lr=1e-6]
Steps:  57%|█████▋    | 341/600 [11:33<05:20,  1.24s/it, loss=0.152, lr=1e-6]
Steps:  57%|█████▋    | 341/600 [11:33<05:20,  1.24s/it, loss=0.195, lr=1e-6]
Steps:  57%|█████▋    | 342/600 [11:35<06:30,  1.51s/it, loss=0.195, lr=1e-6]
Steps:  57%|█████▋    | 342/600 [11:35<06:30,  1.51s/it, loss=0.0467, lr=1e-6]
Steps:  57%|█████▋    | 343/600 [11:37<06:25,  1.50s/it, loss=0.0467, lr=1e-6]
Steps:  57%|█████▋    | 343/600 [11:37<06:25,  1.50s/it, loss=0.136, lr=1e-6] 
Steps:  57%|█████▋    | 344/600 [11:39<06:37,  1.55s/it, loss=0.136, lr=1e-6]
Steps:  57%|█████▋    | 344/600 [11:39<06:37,  1.55s/it, loss=0.0629, lr=1e-6]
Steps:  57%|█████▊    | 345/600 [11:40<06:35,  1.55s/it, loss=0.0629, lr=1e-6]
Steps:  57%|█████▊    | 345/600 [11:40<06:35,  1.55s/it, loss=0.164, lr=1e-6] 
Steps:  58%|█████▊    | 346/600 [11:42<06:28,  1.53s/it, loss=0.164, lr=1e-6]
Steps:  58%|█████▊    | 346/600 [11:42<06:28,  1.53s/it, loss=0.00681, lr=1e-6]
Steps:  58%|█████▊    | 347/600 [11:43<06:28,  1.53s/it, loss=0.00681, lr=1e-6]
Steps:  58%|█████▊    | 347/600 [11:43<06:28,  1.53s/it, loss=0.0855, lr=1e-6] 
Steps:  58%|█████▊    | 348/600 [11:45<06:38,  1.58s/it, loss=0.0855, lr=1e-6]
Steps:  58%|█████▊    | 348/600 [11:45<06:38,  1.58s/it, loss=0.19, lr=1e-6]  
Steps:  58%|█████▊    | 349/600 [11:47<06:48,  1.63s/it, loss=0.19, lr=1e-6]
Steps:  58%|█████▊    | 349/600 [11:47<06:48,  1.63s/it, loss=0.124, lr=1e-6]
Steps:  58%|█████▊    | 350/600 [11:48<06:33,  1.57s/it, loss=0.124, lr=1e-6]
Steps:  58%|█████▊    | 350/600 [11:48<06:33,  1.57s/it, loss=0.273, lr=1e-6]
Steps:  58%|█████▊    | 351/600 [11:49<06:24,  1.55s/it, loss=0.273, lr=1e-6]
Steps:  58%|█████▊    | 351/600 [11:49<06:24,  1.55s/it, loss=0.0197, lr=1e-6]
Steps:  59%|█████▊    | 352/600 [11:50<05:24,  1.31s/it, loss=0.0197, lr=1e-6]
Steps:  59%|█████▊    | 352/600 [11:50<05:24,  1.31s/it, loss=0.0685, lr=1e-6]
Steps:  59%|█████▉    | 353/600 [11:53<06:36,  1.61s/it, loss=0.0685, lr=1e-6]
Steps:  59%|█████▉    | 353/600 [11:53<06:36,  1.61s/it, loss=0.00357, lr=1e-6]
Steps:  59%|█████▉    | 354/600 [11:54<06:37,  1.62s/it, loss=0.00357, lr=1e-6]
Steps:  59%|█████▉    | 354/600 [11:54<06:37,  1.62s/it, loss=0.146, lr=1e-6]  
Steps:  59%|█████▉    | 355/600 [11:56<06:38,  1.63s/it, loss=0.146, lr=1e-6]
Steps:  59%|█████▉    | 355/600 [11:56<06:38,  1.63s/it, loss=0.0926, lr=1e-6]
Steps:  59%|█████▉    | 356/600 [11:58<06:42,  1.65s/it, loss=0.0926, lr=1e-6]
Steps:  59%|█████▉    | 356/600 [11:58<06:42,  1.65s/it, loss=0.138, lr=1e-6] 
Steps:  60%|█████▉    | 357/600 [11:59<06:31,  1.61s/it, loss=0.138, lr=1e-6]
Steps:  60%|█████▉    | 357/600 [11:59<06:31,  1.61s/it, loss=0.269, lr=1e-6]
Steps:  60%|█████▉    | 358/600 [12:00<06:16,  1.56s/it, loss=0.269, lr=1e-6]
Steps:  60%|█████▉    | 358/600 [12:00<06:16,  1.56s/it, loss=0.157, lr=1e-6]
Steps:  60%|█████▉    | 359/600 [12:02<06:09,  1.53s/it, loss=0.157, lr=1e-6]
Steps:  60%|█████▉    | 359/600 [12:02<06:09,  1.53s/it, loss=0.171, lr=1e-6]
Steps:  60%|██████    | 360/600 [12:04<06:16,  1.57s/it, loss=0.171, lr=1e-6]
Steps:  60%|██████    | 360/600 [12:04<06:16,  1.57s/it, loss=0.0757, lr=1e-6]
Steps:  60%|██████    | 361/600 [12:05<06:19,  1.59s/it, loss=0.0757, lr=1e-6]
Steps:  60%|██████    | 361/600 [12:05<06:19,  1.59s/it, loss=0.0358, lr=1e-6]
Steps:  60%|██████    | 362/600 [12:06<05:53,  1.49s/it, loss=0.0358, lr=1e-6]
Steps:  60%|██████    | 362/600 [12:06<05:53,  1.49s/it, loss=0.114, lr=1e-6] 
Steps:  60%|██████    | 363/600 [12:07<05:00,  1.27s/it, loss=0.114, lr=1e-6]
Steps:  60%|██████    | 363/600 [12:07<05:00,  1.27s/it, loss=0.0127, lr=1e-6]
Steps:  61%|██████    | 364/600 [12:09<05:41,  1.45s/it, loss=0.0127, lr=1e-6]
Steps:  61%|██████    | 364/600 [12:09<05:41,  1.45s/it, loss=0.134, lr=1e-6] 
Steps:  61%|██████    | 365/600 [12:11<05:40,  1.45s/it, loss=0.134, lr=1e-6]
Steps:  61%|██████    | 365/600 [12:11<05:40,  1.45s/it, loss=0.0535, lr=1e-6]
Steps:  61%|██████    | 366/600 [12:12<05:57,  1.53s/it, loss=0.0535, lr=1e-6]
Steps:  61%|██████    | 366/600 [12:12<05:57,  1.53s/it, loss=0.024, lr=1e-6] 
Steps:  61%|██████    | 367/600 [12:14<06:08,  1.58s/it, loss=0.024, lr=1e-6]
Steps:  61%|██████    | 367/600 [12:14<06:08,  1.58s/it, loss=0.0552, lr=1e-6]
Steps:  61%|██████▏   | 368/600 [12:16<06:22,  1.65s/it, loss=0.0552, lr=1e-6]
Steps:  61%|██████▏   | 368/600 [12:16<06:22,  1.65s/it, loss=0.0473, lr=1e-6]
Steps:  62%|██████▏   | 369/600 [12:18<06:28,  1.68s/it, loss=0.0473, lr=1e-6]
Steps:  62%|██████▏   | 369/600 [12:18<06:28,  1.68s/it, loss=0.16, lr=1e-6]  
Steps:  62%|██████▏   | 370/600 [12:19<06:09,  1.61s/it, loss=0.16, lr=1e-6]
Steps:  62%|██████▏   | 370/600 [12:19<06:09,  1.61s/it, loss=0.0938, lr=1e-6]
Steps:  62%|██████▏   | 371/600 [12:20<06:01,  1.58s/it, loss=0.0938, lr=1e-6]
Steps:  62%|██████▏   | 371/600 [12:20<06:01,  1.58s/it, loss=0.133, lr=1e-6] 
Steps:  62%|██████▏   | 372/600 [12:22<06:12,  1.63s/it, loss=0.133, lr=1e-6]
Steps:  62%|██████▏   | 372/600 [12:22<06:12,  1.63s/it, loss=0.00843, lr=1e-6]
Steps:  62%|██████▏   | 373/600 [12:23<05:43,  1.51s/it, loss=0.00843, lr=1e-6]
Steps:  62%|██████▏   | 373/600 [12:23<05:43,  1.51s/it, loss=0.0312, lr=1e-6] 
Steps:  62%|██████▏   | 374/600 [12:24<04:50,  1.29s/it, loss=0.0312, lr=1e-6]
Steps:  62%|██████▏   | 374/600 [12:24<04:50,  1.29s/it, loss=0.0269, lr=1e-6]
Steps:  62%|██████▎   | 375/600 [12:27<06:01,  1.60s/it, loss=0.0269, lr=1e-6]
Steps:  62%|██████▎   | 375/600 [12:27<06:01,  1.60s/it, loss=0.104, lr=1e-6] 
Steps:  63%|██████▎   | 376/600 [12:28<06:02,  1.62s/it, loss=0.104, lr=1e-6]
Steps:  63%|██████▎   | 376/600 [12:28<06:02,  1.62s/it, loss=0.107, lr=1e-6]
Steps:  63%|██████▎   | 377/600 [12:29<05:34,  1.50s/it, loss=0.107, lr=1e-6]
Steps:  63%|██████▎   | 377/600 [12:29<05:34,  1.50s/it, loss=0.152, lr=1e-6]
Steps:  63%|██████▎   | 378/600 [12:31<05:46,  1.56s/it, loss=0.152, lr=1e-6]
Steps:  63%|██████▎   | 378/600 [12:31<05:46,  1.56s/it, loss=0.13, lr=1e-6] 
Steps:  63%|██████▎   | 379/600 [12:33<05:42,  1.55s/it, loss=0.13, lr=1e-6]
Steps:  63%|██████▎   | 379/600 [12:33<05:42,  1.55s/it, loss=0.244, lr=1e-6]
Steps:  63%|██████▎   | 380/600 [12:34<05:51,  1.60s/it, loss=0.244, lr=1e-6]
Steps:  63%|██████▎   | 380/600 [12:34<05:51,  1.60s/it, loss=0.11, lr=1e-6] 
Steps:  64%|██████▎   | 381/600 [12:36<05:44,  1.57s/it, loss=0.11, lr=1e-6]
Steps:  64%|██████▎   | 381/600 [12:36<05:44,  1.57s/it, loss=0.0224, lr=1e-6]
Steps:  64%|██████▎   | 382/600 [12:38<05:47,  1.59s/it, loss=0.0224, lr=1e-6]
Steps:  64%|██████▎   | 382/600 [12:38<05:47,  1.59s/it, loss=0.247, lr=1e-6] 
Steps:  64%|██████▍   | 383/600 [12:39<05:48,  1.60s/it, loss=0.247, lr=1e-6]
Steps:  64%|██████▍   | 383/600 [12:39<05:48,  1.60s/it, loss=0.0934, lr=1e-6]
Steps:  64%|██████▍   | 384/600 [12:40<05:22,  1.49s/it, loss=0.0934, lr=1e-6]
Steps:  64%|██████▍   | 384/600 [12:40<05:22,  1.49s/it, loss=0.0238, lr=1e-6]
Steps:  64%|██████▍   | 385/600 [12:41<04:33,  1.27s/it, loss=0.0238, lr=1e-6]
Steps:  64%|██████▍   | 385/600 [12:41<04:33,  1.27s/it, loss=0.23, lr=1e-6]  
Steps:  64%|██████▍   | 386/600 [12:44<05:40,  1.59s/it, loss=0.23, lr=1e-6]
Steps:  64%|██████▍   | 386/600 [12:44<05:40,  1.59s/it, loss=0.00968, lr=1e-6]
Steps:  64%|██████▍   | 387/600 [12:45<05:41,  1.61s/it, loss=0.00968, lr=1e-6]
Steps:  64%|██████▍   | 387/600 [12:45<05:41,  1.61s/it, loss=0.0839, lr=1e-6] 
Steps:  65%|██████▍   | 388/600 [12:47<05:30,  1.56s/it, loss=0.0839, lr=1e-6]
Steps:  65%|██████▍   | 388/600 [12:47<05:30,  1.56s/it, loss=0.128, lr=1e-6] 
Steps:  65%|██████▍   | 389/600 [12:48<05:34,  1.58s/it, loss=0.128, lr=1e-6]
Steps:  65%|██████▍   | 389/600 [12:48<05:34,  1.58s/it, loss=0.0224, lr=1e-6]
Steps:  65%|██████▌   | 390/600 [12:50<05:29,  1.57s/it, loss=0.0224, lr=1e-6]
Steps:  65%|██████▌   | 390/600 [12:50<05:29,  1.57s/it, loss=0.261, lr=1e-6] 
Steps:  65%|██████▌   | 391/600 [12:51<05:24,  1.55s/it, loss=0.261, lr=1e-6]
Steps:  65%|██████▌   | 391/600 [12:51<05:24,  1.55s/it, loss=0.183, lr=1e-6]
Steps:  65%|██████▌   | 392/600 [12:53<05:26,  1.57s/it, loss=0.183, lr=1e-6]
Steps:  65%|██████▌   | 392/600 [12:53<05:26,  1.57s/it, loss=0.0268, lr=1e-6]
Steps:  66%|██████▌   | 393/600 [12:54<05:20,  1.55s/it, loss=0.0268, lr=1e-6]
Steps:  66%|██████▌   | 393/600 [12:54<05:20,  1.55s/it, loss=0.0502, lr=1e-6]
Steps:  66%|██████▌   | 394/600 [12:56<05:15,  1.53s/it, loss=0.0502, lr=1e-6]
Steps:  66%|██████▌   | 394/600 [12:56<05:15,  1.53s/it, loss=0.142, lr=1e-6] 
Steps:  66%|██████▌   | 395/600 [12:57<05:08,  1.51s/it, loss=0.142, lr=1e-6]
Steps:  66%|██████▌   | 395/600 [12:57<05:08,  1.51s/it, loss=0.271, lr=1e-6]
Steps:  66%|██████▌   | 396/600 [12:58<04:21,  1.28s/it, loss=0.271, lr=1e-6]
Steps:  66%|██████▌   | 396/600 [12:58<04:21,  1.28s/it, loss=0.213, lr=1e-6]
Steps:  66%|██████▌   | 397/600 [13:00<05:25,  1.60s/it, loss=0.213, lr=1e-6]
Steps:  66%|██████▌   | 397/600 [13:00<05:25,  1.60s/it, loss=0.00302, lr=1e-6]
Steps:  66%|██████▋   | 398/600 [13:02<05:12,  1.55s/it, loss=0.00302, lr=1e-6]
Steps:  66%|██████▋   | 398/600 [13:02<05:12,  1.55s/it, loss=0.0654, lr=1e-6] 
Steps:  66%|██████▋   | 399/600 [13:03<05:15,  1.57s/it, loss=0.0654, lr=1e-6]
Steps:  66%|██████▋   | 399/600 [13:03<05:15,  1.57s/it, loss=0.0378, lr=1e-6]
Steps:  67%|██████▋   | 400/600 [13:05<05:09,  1.55s/it, loss=0.0378, lr=1e-6]
Steps:  67%|██████▋   | 400/600 [13:05<05:09,  1.55s/it, loss=0.072, lr=1e-6] 
Steps:  67%|██████▋   | 401/600 [13:07<05:16,  1.59s/it, loss=0.072, lr=1e-6]
Steps:  67%|██████▋   | 401/600 [13:07<05:16,  1.59s/it, loss=0.0409, lr=1e-6]
Steps:  67%|██████▋   | 402/600 [13:08<05:13,  1.59s/it, loss=0.0409, lr=1e-6]
Steps:  67%|██████▋   | 402/600 [13:08<05:13,  1.59s/it, loss=0.153, lr=1e-6] 
Steps:  67%|██████▋   | 403/600 [13:10<05:10,  1.58s/it, loss=0.153, lr=1e-6]
Steps:  67%|██████▋   | 403/600 [13:10<05:10,  1.58s/it, loss=0.0685, lr=1e-6]
Steps:  67%|██████▋   | 404/600 [13:11<05:07,  1.57s/it, loss=0.0685, lr=1e-6]
Steps:  67%|██████▋   | 404/600 [13:11<05:07,  1.57s/it, loss=0.195, lr=1e-6] 
Steps:  68%|██████▊   | 405/600 [13:13<05:11,  1.60s/it, loss=0.195, lr=1e-6]
Steps:  68%|██████▊   | 405/600 [13:13<05:11,  1.60s/it, loss=0.227, lr=1e-6]
Steps:  68%|██████▊   | 406/600 [13:14<04:51,  1.50s/it, loss=0.227, lr=1e-6]
Steps:  68%|██████▊   | 406/600 [13:14<04:51,  1.50s/it, loss=0.197, lr=1e-6]
Steps:  68%|██████▊   | 407/600 [13:15<04:12,  1.31s/it, loss=0.197, lr=1e-6]
Steps:  68%|██████▊   | 407/600 [13:15<04:12,  1.31s/it, loss=0.0102, lr=1e-6]
Steps:  68%|██████▊   | 408/600 [13:17<04:50,  1.51s/it, loss=0.0102, lr=1e-6]
Steps:  68%|██████▊   | 408/600 [13:17<04:50,  1.51s/it, loss=0.0724, lr=1e-6]
Steps:  68%|██████▊   | 409/600 [13:19<04:57,  1.56s/it, loss=0.0724, lr=1e-6]
Steps:  68%|██████▊   | 409/600 [13:19<04:57,  1.56s/it, loss=0.247, lr=1e-6] 
Steps:  68%|██████▊   | 410/600 [13:20<04:50,  1.53s/it, loss=0.247, lr=1e-6]
Steps:  68%|██████▊   | 410/600 [13:20<04:50,  1.53s/it, loss=0.133, lr=1e-6]
Steps:  68%|██████▊   | 411/600 [13:22<05:04,  1.61s/it, loss=0.133, lr=1e-6]
Steps:  68%|██████▊   | 411/600 [13:22<05:04,  1.61s/it, loss=0.135, lr=1e-6]
Steps:  69%|██████▊   | 412/600 [13:24<05:03,  1.61s/it, loss=0.135, lr=1e-6]
Steps:  69%|██████▊   | 412/600 [13:24<05:03,  1.61s/it, loss=0.205, lr=1e-6]
Steps:  69%|██████▉   | 413/600 [13:25<05:07,  1.64s/it, loss=0.205, lr=1e-6]
Steps:  69%|██████▉   | 413/600 [13:25<05:07,  1.64s/it, loss=0.0223, lr=1e-6]
Steps:  69%|██████▉   | 414/600 [13:27<05:05,  1.64s/it, loss=0.0223, lr=1e-6]
Steps:  69%|██████▉   | 414/600 [13:27<05:05,  1.64s/it, loss=0.00684, lr=1e-6]
Steps:  69%|██████▉   | 415/600 [13:28<04:49,  1.56s/it, loss=0.00684, lr=1e-6]
Steps:  69%|██████▉   | 415/600 [13:28<04:49,  1.56s/it, loss=0.103, lr=1e-6]  
Steps:  69%|██████▉   | 416/600 [13:30<04:46,  1.56s/it, loss=0.103, lr=1e-6]
Steps:  69%|██████▉   | 416/600 [13:30<04:46,  1.56s/it, loss=0.0918, lr=1e-6]
Steps:  70%|██████▉   | 417/600 [13:31<04:40,  1.53s/it, loss=0.0918, lr=1e-6]
Steps:  70%|██████▉   | 417/600 [13:31<04:40,  1.53s/it, loss=0.166, lr=1e-6] 
Steps:  70%|██████▉   | 418/600 [13:32<03:56,  1.30s/it, loss=0.166, lr=1e-6]
Steps:  70%|██████▉   | 418/600 [13:32<03:56,  1.30s/it, loss=0.041, lr=1e-6]
Steps:  70%|██████▉   | 419/600 [13:34<04:44,  1.57s/it, loss=0.041, lr=1e-6]
Steps:  70%|██████▉   | 419/600 [13:34<04:44,  1.57s/it, loss=0.042, lr=1e-6]
Steps:  70%|███████   | 420/600 [13:36<04:44,  1.58s/it, loss=0.042, lr=1e-6]
Steps:  70%|███████   | 420/600 [13:36<04:44,  1.58s/it, loss=0.0149, lr=1e-6]
Steps:  70%|███████   | 421/600 [13:38<04:43,  1.58s/it, loss=0.0149, lr=1e-6]
Steps:  70%|███████   | 421/600 [13:38<04:43,  1.58s/it, loss=0.0737, lr=1e-6]
Steps:  70%|███████   | 422/600 [13:39<04:29,  1.51s/it, loss=0.0737, lr=1e-6]
Steps:  70%|███████   | 422/600 [13:39<04:29,  1.51s/it, loss=0.313, lr=1e-6] 
Steps:  70%|███████   | 423/600 [13:41<04:44,  1.61s/it, loss=0.313, lr=1e-6]
Steps:  70%|███████   | 423/600 [13:41<04:44,  1.61s/it, loss=0.152, lr=1e-6]
Steps:  71%|███████   | 424/600 [13:42<04:34,  1.56s/it, loss=0.152, lr=1e-6]
Steps:  71%|███████   | 424/600 [13:42<04:34,  1.56s/it, loss=0.18, lr=1e-6] 
Steps:  71%|███████   | 425/600 [13:44<04:26,  1.52s/it, loss=0.18, lr=1e-6]
Steps:  71%|███████   | 425/600 [13:44<04:26,  1.52s/it, loss=0.129, lr=1e-6]
Steps:  71%|███████   | 426/600 [13:45<04:40,  1.61s/it, loss=0.129, lr=1e-6]
Steps:  71%|███████   | 426/600 [13:45<04:40,  1.61s/it, loss=0.0304, lr=1e-6]
Steps:  71%|███████   | 427/600 [13:47<04:53,  1.70s/it, loss=0.0304, lr=1e-6]
Steps:  71%|███████   | 427/600 [13:47<04:53,  1.70s/it, loss=0.216, lr=1e-6] 
Steps:  71%|███████▏  | 428/600 [13:48<04:22,  1.53s/it, loss=0.216, lr=1e-6]
Steps:  71%|███████▏  | 428/600 [13:48<04:22,  1.53s/it, loss=0.0217, lr=1e-6]
Steps:  72%|███████▏  | 429/600 [13:49<03:41,  1.30s/it, loss=0.0217, lr=1e-6]
Steps:  72%|███████▏  | 429/600 [13:49<03:41,  1.30s/it, loss=0.254, lr=1e-6] 
Steps:  72%|███████▏  | 430/600 [13:51<04:24,  1.55s/it, loss=0.254, lr=1e-6]
Steps:  72%|███████▏  | 430/600 [13:51<04:24,  1.55s/it, loss=0.115, lr=1e-6]
Steps:  72%|███████▏  | 431/600 [13:53<04:34,  1.62s/it, loss=0.115, lr=1e-6]
Steps:  72%|███████▏  | 431/600 [13:53<04:34,  1.62s/it, loss=0.172, lr=1e-6]
Steps:  72%|███████▏  | 432/600 [13:55<04:26,  1.58s/it, loss=0.172, lr=1e-6]
Steps:  72%|███████▏  | 432/600 [13:55<04:26,  1.58s/it, loss=0.118, lr=1e-6]
Steps:  72%|███████▏  | 433/600 [13:56<04:28,  1.61s/it, loss=0.118, lr=1e-6]
Steps:  72%|███████▏  | 433/600 [13:56<04:28,  1.61s/it, loss=0.0481, lr=1e-6]
Steps:  72%|███████▏  | 434/600 [13:58<04:37,  1.67s/it, loss=0.0481, lr=1e-6]
Steps:  72%|███████▏  | 434/600 [13:58<04:37,  1.67s/it, loss=0.021, lr=1e-6] 
Steps:  72%|███████▎  | 435/600 [14:00<04:26,  1.61s/it, loss=0.021, lr=1e-6]
Steps:  72%|███████▎  | 435/600 [14:00<04:26,  1.61s/it, loss=0.131, lr=1e-6]
Steps:  73%|███████▎  | 436/600 [14:01<04:16,  1.57s/it, loss=0.131, lr=1e-6]
Steps:  73%|███████▎  | 436/600 [14:01<04:16,  1.57s/it, loss=0.0407, lr=1e-6]
Steps:  73%|███████▎  | 437/600 [14:03<04:23,  1.62s/it, loss=0.0407, lr=1e-6]
Steps:  73%|███████▎  | 437/600 [14:03<04:23,  1.62s/it, loss=0.0828, lr=1e-6]
Steps:  73%|███████▎  | 438/600 [14:04<04:17,  1.59s/it, loss=0.0828, lr=1e-6]
Steps:  73%|███████▎  | 438/600 [14:04<04:17,  1.59s/it, loss=0.0509, lr=1e-6]
Steps:  73%|███████▎  | 439/600 [14:06<04:00,  1.49s/it, loss=0.0509, lr=1e-6]
Steps:  73%|███████▎  | 439/600 [14:06<04:00,  1.49s/it, loss=0.0291, lr=1e-6]
Steps:  73%|███████▎  | 440/600 [14:06<03:24,  1.28s/it, loss=0.0291, lr=1e-6]
Steps:  73%|███████▎  | 440/600 [14:06<03:24,  1.28s/it, loss=0.0319, lr=1e-6]
Steps:  74%|███████▎  | 441/600 [14:09<04:08,  1.57s/it, loss=0.0319, lr=1e-6]
Steps:  74%|███████▎  | 441/600 [14:09<04:08,  1.57s/it, loss=0.161, lr=1e-6] 
Steps:  74%|███████▎  | 442/600 [14:10<04:14,  1.61s/it, loss=0.161, lr=1e-6]
Steps:  74%|███████▎  | 442/600 [14:10<04:14,  1.61s/it, loss=0.0411, lr=1e-6]
Steps:  74%|███████▍  | 443/600 [14:12<04:02,  1.54s/it, loss=0.0411, lr=1e-6]
Steps:  74%|███████▍  | 443/600 [14:12<04:02,  1.54s/it, loss=0.154, lr=1e-6] 
Steps:  74%|███████▍  | 444/600 [14:13<04:03,  1.56s/it, loss=0.154, lr=1e-6]
Steps:  74%|███████▍  | 444/600 [14:13<04:03,  1.56s/it, loss=0.094, lr=1e-6]
Steps:  74%|███████▍  | 445/600 [14:15<04:05,  1.58s/it, loss=0.094, lr=1e-6]
Steps:  74%|███████▍  | 445/600 [14:15<04:05,  1.58s/it, loss=0.0114, lr=1e-6]
Steps:  74%|███████▍  | 446/600 [14:16<03:59,  1.56s/it, loss=0.0114, lr=1e-6]
Steps:  74%|███████▍  | 446/600 [14:16<03:59,  1.56s/it, loss=0.157, lr=1e-6] 
Steps:  74%|███████▍  | 447/600 [14:18<03:59,  1.57s/it, loss=0.157, lr=1e-6]
Steps:  74%|███████▍  | 447/600 [14:18<03:59,  1.57s/it, loss=0.0722, lr=1e-6]
Steps:  75%|███████▍  | 448/600 [14:20<04:01,  1.59s/it, loss=0.0722, lr=1e-6]
Steps:  75%|███████▍  | 448/600 [14:20<04:01,  1.59s/it, loss=0.0457, lr=1e-6]
Steps:  75%|███████▍  | 449/600 [14:21<04:01,  1.60s/it, loss=0.0457, lr=1e-6]
Steps:  75%|███████▍  | 449/600 [14:21<04:01,  1.60s/it, loss=0.0963, lr=1e-6]
Steps:  75%|███████▌  | 450/600 [14:23<03:51,  1.54s/it, loss=0.0963, lr=1e-6]
Steps:  75%|███████▌  | 450/600 [14:23<03:51,  1.54s/it, loss=0.00932, lr=1e-6]
Steps:  75%|███████▌  | 451/600 [14:23<03:14,  1.31s/it, loss=0.00932, lr=1e-6]
Steps:  75%|███████▌  | 451/600 [14:23<03:14,  1.31s/it, loss=0.25, lr=1e-6]   
Steps:  75%|███████▌  | 452/600 [14:26<04:02,  1.64s/it, loss=0.25, lr=1e-6]
Steps:  75%|███████▌  | 452/600 [14:26<04:02,  1.64s/it, loss=0.016, lr=1e-6]
Steps:  76%|███████▌  | 453/600 [14:27<03:58,  1.62s/it, loss=0.016, lr=1e-6]
Steps:  76%|███████▌  | 453/600 [14:27<03:58,  1.62s/it, loss=0.101, lr=1e-6]
Steps:  76%|███████▌  | 454/600 [14:29<03:52,  1.59s/it, loss=0.101, lr=1e-6]
Steps:  76%|███████▌  | 454/600 [14:29<03:52,  1.59s/it, loss=0.0537, lr=1e-6]
Steps:  76%|███████▌  | 455/600 [14:31<03:46,  1.56s/it, loss=0.0537, lr=1e-6]
Steps:  76%|███████▌  | 455/600 [14:31<03:46,  1.56s/it, loss=0.167, lr=1e-6] 
Steps:  76%|███████▌  | 456/600 [14:32<03:43,  1.55s/it, loss=0.167, lr=1e-6]
Steps:  76%|███████▌  | 456/600 [14:32<03:43,  1.55s/it, loss=0.137, lr=1e-6]
Steps:  76%|███████▌  | 457/600 [14:34<03:40,  1.54s/it, loss=0.137, lr=1e-6]
Steps:  76%|███████▌  | 457/600 [14:34<03:40,  1.54s/it, loss=0.121, lr=1e-6]
Steps:  76%|███████▋  | 458/600 [14:35<03:49,  1.61s/it, loss=0.121, lr=1e-6]
Steps:  76%|███████▋  | 458/600 [14:35<03:49,  1.61s/it, loss=0.0995, lr=1e-6]
Steps:  76%|███████▋  | 459/600 [14:37<03:31,  1.50s/it, loss=0.0995, lr=1e-6]
Steps:  76%|███████▋  | 459/600 [14:37<03:31,  1.50s/it, loss=0.178, lr=1e-6] 
Steps:  77%|███████▋  | 460/600 [14:38<03:44,  1.60s/it, loss=0.178, lr=1e-6]
Steps:  77%|███████▋  | 460/600 [14:38<03:44,  1.60s/it, loss=0.00746, lr=1e-6]
Steps:  77%|███████▋  | 461/600 [14:40<03:33,  1.53s/it, loss=0.00746, lr=1e-6]
Steps:  77%|███████▋  | 461/600 [14:40<03:33,  1.53s/it, loss=0.14, lr=1e-6]   
Steps:  77%|███████▋  | 462/600 [14:41<02:59,  1.30s/it, loss=0.14, lr=1e-6]
Steps:  77%|███████▋  | 462/600 [14:41<02:59,  1.30s/it, loss=0.00319, lr=1e-6]
Steps:  77%|███████▋  | 463/600 [14:43<03:41,  1.61s/it, loss=0.00319, lr=1e-6]
Steps:  77%|███████▋  | 463/600 [14:43<03:41,  1.61s/it, loss=0.0316, lr=1e-6] 
Steps:  77%|███████▋  | 464/600 [14:45<03:42,  1.63s/it, loss=0.0316, lr=1e-6]
Steps:  77%|███████▋  | 464/600 [14:45<03:42,  1.63s/it, loss=0.144, lr=1e-6] 
Steps:  78%|███████▊  | 465/600 [14:46<03:27,  1.54s/it, loss=0.144, lr=1e-6]
Steps:  78%|███████▊  | 465/600 [14:46<03:27,  1.54s/it, loss=0.015, lr=1e-6]
Steps:  78%|███████▊  | 466/600 [14:47<03:25,  1.54s/it, loss=0.015, lr=1e-6]
Steps:  78%|███████▊  | 466/600 [14:47<03:25,  1.54s/it, loss=0.21, lr=1e-6] 
Steps:  78%|███████▊  | 467/600 [14:49<03:29,  1.57s/it, loss=0.21, lr=1e-6]
Steps:  78%|███████▊  | 467/600 [14:49<03:29,  1.57s/it, loss=0.0162, lr=1e-6]
Steps:  78%|███████▊  | 468/600 [14:51<03:25,  1.56s/it, loss=0.0162, lr=1e-6]
Steps:  78%|███████▊  | 468/600 [14:51<03:25,  1.56s/it, loss=0.00433, lr=1e-6]
Steps:  78%|███████▊  | 469/600 [14:52<03:20,  1.53s/it, loss=0.00433, lr=1e-6]
Steps:  78%|███████▊  | 469/600 [14:52<03:20,  1.53s/it, loss=0.114, lr=1e-6]  
Steps:  78%|███████▊  | 470/600 [14:54<03:24,  1.57s/it, loss=0.114, lr=1e-6]
Steps:  78%|███████▊  | 470/600 [14:54<03:24,  1.57s/it, loss=0.017, lr=1e-6]
Steps:  78%|███████▊  | 471/600 [14:56<03:31,  1.64s/it, loss=0.017, lr=1e-6]
Steps:  78%|███████▊  | 471/600 [14:56<03:31,  1.64s/it, loss=0.0767, lr=1e-6]
Steps:  79%|███████▊  | 472/600 [14:57<03:13,  1.51s/it, loss=0.0767, lr=1e-6]
Steps:  79%|███████▊  | 472/600 [14:57<03:13,  1.51s/it, loss=0.0396, lr=1e-6]
Steps:  79%|███████▉  | 473/600 [14:58<02:43,  1.29s/it, loss=0.0396, lr=1e-6]
Steps:  79%|███████▉  | 473/600 [14:58<02:43,  1.29s/it, loss=0.121, lr=1e-6] 
Steps:  79%|███████▉  | 474/600 [15:00<03:18,  1.58s/it, loss=0.121, lr=1e-6]
Steps:  79%|███████▉  | 474/600 [15:00<03:18,  1.58s/it, loss=0.204, lr=1e-6]
Steps:  79%|███████▉  | 475/600 [15:01<03:09,  1.51s/it, loss=0.204, lr=1e-6]
Steps:  79%|███████▉  | 475/600 [15:01<03:09,  1.51s/it, loss=0.189, lr=1e-6]
Steps:  79%|███████▉  | 476/600 [15:02<03:01,  1.46s/it, loss=0.189, lr=1e-6]
Steps:  79%|███████▉  | 476/600 [15:02<03:01,  1.46s/it, loss=0.137, lr=1e-6]
Steps:  80%|███████▉  | 477/600 [15:04<03:02,  1.48s/it, loss=0.137, lr=1e-6]
Steps:  80%|███████▉  | 477/600 [15:04<03:02,  1.48s/it, loss=0.0472, lr=1e-6]
Steps:  80%|███████▉  | 478/600 [15:06<03:06,  1.53s/it, loss=0.0472, lr=1e-6]
Steps:  80%|███████▉  | 478/600 [15:06<03:06,  1.53s/it, loss=0.0106, lr=1e-6]
Steps:  80%|███████▉  | 479/600 [15:07<03:16,  1.63s/it, loss=0.0106, lr=1e-6]
Steps:  80%|███████▉  | 479/600 [15:07<03:16,  1.63s/it, loss=0.165, lr=1e-6] 
Steps:  80%|████████  | 480/600 [15:09<03:08,  1.57s/it, loss=0.165, lr=1e-6]
Steps:  80%|████████  | 480/600 [15:09<03:08,  1.57s/it, loss=0.0247, lr=1e-6]
Steps:  80%|████████  | 481/600 [15:11<03:12,  1.61s/it, loss=0.0247, lr=1e-6]
Steps:  80%|████████  | 481/600 [15:11<03:12,  1.61s/it, loss=0.144, lr=1e-6] 
Steps:  80%|████████  | 482/600 [15:12<03:11,  1.62s/it, loss=0.144, lr=1e-6]
Steps:  80%|████████  | 482/600 [15:12<03:11,  1.62s/it, loss=0.0657, lr=1e-6]
Steps:  80%|████████  | 483/600 [15:14<03:03,  1.57s/it, loss=0.0657, lr=1e-6]
Steps:  80%|████████  | 483/600 [15:14<03:03,  1.57s/it, loss=0.0086, lr=1e-6]
Steps:  81%|████████  | 484/600 [15:14<02:34,  1.33s/it, loss=0.0086, lr=1e-6]
Steps:  81%|████████  | 484/600 [15:14<02:34,  1.33s/it, loss=0.12, lr=1e-6]  
Steps:  81%|████████  | 485/600 [15:17<03:04,  1.60s/it, loss=0.12, lr=1e-6]
Steps:  81%|████████  | 485/600 [15:17<03:04,  1.60s/it, loss=0.0176, lr=1e-6]
Steps:  81%|████████  | 486/600 [15:18<03:00,  1.58s/it, loss=0.0176, lr=1e-6]
Steps:  81%|████████  | 486/600 [15:18<03:00,  1.58s/it, loss=0.0404, lr=1e-6]
Steps:  81%|████████  | 487/600 [15:20<03:05,  1.65s/it, loss=0.0404, lr=1e-6]
Steps:  81%|████████  | 487/600 [15:20<03:05,  1.65s/it, loss=0.0942, lr=1e-6]
Steps:  81%|████████▏ | 488/600 [15:22<03:08,  1.68s/it, loss=0.0942, lr=1e-6]
Steps:  81%|████████▏ | 488/600 [15:22<03:08,  1.68s/it, loss=0.0943, lr=1e-6]
Steps:  82%|████████▏ | 489/600 [15:23<02:55,  1.58s/it, loss=0.0943, lr=1e-6]
Steps:  82%|████████▏ | 489/600 [15:23<02:55,  1.58s/it, loss=0.0723, lr=1e-6]
Steps:  82%|████████▏ | 490/600 [15:25<02:55,  1.59s/it, loss=0.0723, lr=1e-6]
Steps:  82%|████████▏ | 490/600 [15:25<02:55,  1.59s/it, loss=0.289, lr=1e-6] 
Steps:  82%|████████▏ | 491/600 [15:26<02:45,  1.52s/it, loss=0.289, lr=1e-6]
Steps:  82%|████████▏ | 491/600 [15:26<02:45,  1.52s/it, loss=0.388, lr=1e-6]
Steps:  82%|████████▏ | 492/600 [15:28<02:41,  1.49s/it, loss=0.388, lr=1e-6]
Steps:  82%|████████▏ | 492/600 [15:28<02:41,  1.49s/it, loss=0.0211, lr=1e-6]
Steps:  82%|████████▏ | 493/600 [15:29<02:45,  1.55s/it, loss=0.0211, lr=1e-6]
Steps:  82%|████████▏ | 493/600 [15:29<02:45,  1.55s/it, loss=0.0904, lr=1e-6]
Steps:  82%|████████▏ | 494/600 [15:31<02:40,  1.51s/it, loss=0.0904, lr=1e-6]
Steps:  82%|████████▏ | 494/600 [15:31<02:40,  1.51s/it, loss=0.101, lr=1e-6] 
Steps:  82%|████████▎ | 495/600 [15:31<02:15,  1.29s/it, loss=0.101, lr=1e-6]
Steps:  82%|████████▎ | 495/600 [15:31<02:15,  1.29s/it, loss=0.114, lr=1e-6]
Steps:  83%|████████▎ | 496/600 [15:34<02:47,  1.61s/it, loss=0.114, lr=1e-6]
Steps:  83%|████████▎ | 496/600 [15:34<02:47,  1.61s/it, loss=0.24, lr=1e-6] 
Steps:  83%|████████▎ | 497/600 [15:36<02:50,  1.66s/it, loss=0.24, lr=1e-6]
Steps:  83%|████████▎ | 497/600 [15:36<02:50,  1.66s/it, loss=0.208, lr=1e-6]
Steps:  83%|████████▎ | 498/600 [15:37<02:43,  1.60s/it, loss=0.208, lr=1e-6]
Steps:  83%|████████▎ | 498/600 [15:37<02:43,  1.60s/it, loss=0.055, lr=1e-6]
Steps:  83%|████████▎ | 499/600 [15:39<02:37,  1.56s/it, loss=0.055, lr=1e-6]
Steps:  83%|████████▎ | 499/600 [15:39<02:37,  1.56s/it, loss=0.174, lr=1e-6]
Steps:  83%|████████▎ | 500/600 [15:40<02:34,  1.55s/it, loss=0.174, lr=1e-6]10/13/2023 10:45:06 - INFO - accelerate.accelerator - Saving current state to logs/sweep_final_2_20231013102808/checkpoint-500
Model weights saved in logs/sweep_final_2_20231013102808/checkpoint-500/pytorch_lora_weights.safetensors
10/13/2023 10:45:07 - INFO - accelerate.checkpointing - Optimizer state saved in logs/sweep_final_2_20231013102808/checkpoint-500/optimizer.bin
10/13/2023 10:45:07 - INFO - accelerate.checkpointing - Scheduler state saved in logs/sweep_final_2_20231013102808/checkpoint-500/scheduler.bin
10/13/2023 10:45:07 - INFO - accelerate.checkpointing - Gradient scaler state saved in logs/sweep_final_2_20231013102808/checkpoint-500/scaler.pt
10/13/2023 10:45:07 - INFO - accelerate.checkpointing - Random states saved in logs/sweep_final_2_20231013102808/checkpoint-500/random_states_0.pkl
10/13/2023 10:45:07 - INFO - __main__ - Saved state to logs/sweep_final_2_20231013102808/checkpoint-500

Steps:  83%|████████▎ | 500/600 [15:41<02:34,  1.55s/it, loss=0.00536, lr=1e-6]
Steps:  84%|████████▎ | 501/600 [15:43<03:09,  1.91s/it, loss=0.00536, lr=1e-6]
Steps:  84%|████████▎ | 501/600 [15:43<03:09,  1.91s/it, loss=0.0983, lr=1e-6] 
Steps:  84%|████████▎ | 502/600 [15:44<02:52,  1.76s/it, loss=0.0983, lr=1e-6]
Steps:  84%|████████▎ | 502/600 [15:44<02:52,  1.76s/it, loss=0.261, lr=1e-6] 
Steps:  84%|████████▍ | 503/600 [15:46<02:53,  1.79s/it, loss=0.261, lr=1e-6]
Steps:  84%|████████▍ | 503/600 [15:46<02:53,  1.79s/it, loss=0.107, lr=1e-6]
Steps:  84%|████████▍ | 504/600 [15:48<02:46,  1.73s/it, loss=0.107, lr=1e-6]
Steps:  84%|████████▍ | 504/600 [15:48<02:46,  1.73s/it, loss=0.0268, lr=1e-6]
Steps:  84%|████████▍ | 505/600 [15:49<02:27,  1.55s/it, loss=0.0268, lr=1e-6]
Steps:  84%|████████▍ | 505/600 [15:49<02:27,  1.55s/it, loss=0.156, lr=1e-6] 
Steps:  84%|████████▍ | 506/600 [15:50<02:03,  1.32s/it, loss=0.156, lr=1e-6]
Steps:  84%|████████▍ | 506/600 [15:50<02:03,  1.32s/it, loss=0.0114, lr=1e-6]
Steps:  84%|████████▍ | 507/600 [15:52<02:24,  1.56s/it, loss=0.0114, lr=1e-6]
Steps:  84%|████████▍ | 507/600 [15:52<02:24,  1.56s/it, loss=0.0208, lr=1e-6]
Steps:  85%|████████▍ | 508/600 [15:53<02:24,  1.57s/it, loss=0.0208, lr=1e-6]
Steps:  85%|████████▍ | 508/600 [15:53<02:24,  1.57s/it, loss=0.14, lr=1e-6]  
Steps:  85%|████████▍ | 509/600 [15:55<02:23,  1.57s/it, loss=0.14, lr=1e-6]
Steps:  85%|████████▍ | 509/600 [15:55<02:23,  1.57s/it, loss=0.147, lr=1e-6]
Steps:  85%|████████▌ | 510/600 [15:56<02:20,  1.56s/it, loss=0.147, lr=1e-6]
Steps:  85%|████████▌ | 510/600 [15:56<02:20,  1.56s/it, loss=0.0364, lr=1e-6]
Steps:  85%|████████▌ | 511/600 [15:58<02:17,  1.55s/it, loss=0.0364, lr=1e-6]
Steps:  85%|████████▌ | 511/600 [15:58<02:17,  1.55s/it, loss=0.0341, lr=1e-6]
Steps:  85%|████████▌ | 512/600 [15:59<02:17,  1.56s/it, loss=0.0341, lr=1e-6]
Steps:  85%|████████▌ | 512/600 [15:59<02:17,  1.56s/it, loss=0.316, lr=1e-6] 
Steps:  86%|████████▌ | 513/600 [16:01<02:18,  1.59s/it, loss=0.316, lr=1e-6]
Steps:  86%|████████▌ | 513/600 [16:01<02:18,  1.59s/it, loss=0.124, lr=1e-6]
Steps:  86%|████████▌ | 514/600 [16:03<02:18,  1.61s/it, loss=0.124, lr=1e-6]
Steps:  86%|████████▌ | 514/600 [16:03<02:18,  1.61s/it, loss=0.00817, lr=1e-6]
Steps:  86%|████████▌ | 515/600 [16:04<02:17,  1.62s/it, loss=0.00817, lr=1e-6]
Steps:  86%|████████▌ | 515/600 [16:04<02:17,  1.62s/it, loss=0.189, lr=1e-6]  
Steps:  86%|████████▌ | 516/600 [16:06<02:07,  1.51s/it, loss=0.189, lr=1e-6]
Steps:  86%|████████▌ | 516/600 [16:06<02:07,  1.51s/it, loss=0.229, lr=1e-6]
Steps:  86%|████████▌ | 517/600 [16:06<01:46,  1.29s/it, loss=0.229, lr=1e-6]
Steps:  86%|████████▌ | 517/600 [16:06<01:46,  1.29s/it, loss=0.00358, lr=1e-6]
Steps:  86%|████████▋ | 518/600 [16:09<02:04,  1.51s/it, loss=0.00358, lr=1e-6]
Steps:  86%|████████▋ | 518/600 [16:09<02:04,  1.51s/it, loss=0.201, lr=1e-6]  
Steps:  86%|████████▋ | 519/600 [16:10<02:03,  1.53s/it, loss=0.201, lr=1e-6]
Steps:  86%|████████▋ | 519/600 [16:10<02:03,  1.53s/it, loss=0.151, lr=1e-6]
Steps:  87%|████████▋ | 520/600 [16:12<02:01,  1.51s/it, loss=0.151, lr=1e-6]
Steps:  87%|████████▋ | 520/600 [16:12<02:01,  1.51s/it, loss=0.0265, lr=1e-6]
Steps:  87%|████████▋ | 521/600 [16:13<02:04,  1.57s/it, loss=0.0265, lr=1e-6]
Steps:  87%|████████▋ | 521/600 [16:13<02:04,  1.57s/it, loss=0.00499, lr=1e-6]
Steps:  87%|████████▋ | 522/600 [16:15<02:05,  1.60s/it, loss=0.00499, lr=1e-6]
Steps:  87%|████████▋ | 522/600 [16:15<02:05,  1.60s/it, loss=0.0466, lr=1e-6] 
Steps:  87%|████████▋ | 523/600 [16:17<02:09,  1.68s/it, loss=0.0466, lr=1e-6]
Steps:  87%|████████▋ | 523/600 [16:17<02:09,  1.68s/it, loss=0.285, lr=1e-6] 
Steps:  87%|████████▋ | 524/600 [16:18<02:03,  1.63s/it, loss=0.285, lr=1e-6]
Steps:  87%|████████▋ | 524/600 [16:18<02:03,  1.63s/it, loss=0.146, lr=1e-6]
Steps:  88%|████████▊ | 525/600 [16:20<01:57,  1.57s/it, loss=0.146, lr=1e-6]
Steps:  88%|████████▊ | 525/600 [16:20<01:57,  1.57s/it, loss=0.0459, lr=1e-6]
Steps:  88%|████████▊ | 526/600 [16:21<01:55,  1.56s/it, loss=0.0459, lr=1e-6]
Steps:  88%|████████▊ | 526/600 [16:21<01:55,  1.56s/it, loss=0.0062, lr=1e-6]
Steps:  88%|████████▊ | 527/600 [16:23<01:49,  1.51s/it, loss=0.0062, lr=1e-6]
Steps:  88%|████████▊ | 527/600 [16:23<01:49,  1.51s/it, loss=0.0545, lr=1e-6]
Steps:  88%|████████▊ | 528/600 [16:23<01:32,  1.28s/it, loss=0.0545, lr=1e-6]
Steps:  88%|████████▊ | 528/600 [16:23<01:32,  1.28s/it, loss=0.333, lr=1e-6] 
Steps:  88%|████████▊ | 529/600 [16:26<01:52,  1.59s/it, loss=0.333, lr=1e-6]
Steps:  88%|████████▊ | 529/600 [16:26<01:52,  1.59s/it, loss=0.135, lr=1e-6]
Steps:  88%|████████▊ | 530/600 [16:27<01:50,  1.57s/it, loss=0.135, lr=1e-6]
Steps:  88%|████████▊ | 530/600 [16:27<01:50,  1.57s/it, loss=0.022, lr=1e-6]
Steps:  88%|████████▊ | 531/600 [16:29<01:55,  1.67s/it, loss=0.022, lr=1e-6]
Steps:  88%|████████▊ | 531/600 [16:29<01:55,  1.67s/it, loss=0.135, lr=1e-6]
Steps:  89%|████████▊ | 532/600 [16:31<01:58,  1.74s/it, loss=0.135, lr=1e-6]
Steps:  89%|████████▊ | 532/600 [16:31<01:58,  1.74s/it, loss=0.147, lr=1e-6]
Steps:  89%|████████▉ | 533/600 [16:33<01:54,  1.71s/it, loss=0.147, lr=1e-6]
Steps:  89%|████████▉ | 533/600 [16:33<01:54,  1.71s/it, loss=0.0375, lr=1e-6]
Steps:  89%|████████▉ | 534/600 [16:34<01:49,  1.67s/it, loss=0.0375, lr=1e-6]
Steps:  89%|████████▉ | 534/600 [16:34<01:49,  1.67s/it, loss=0.0641, lr=1e-6]
Steps:  89%|████████▉ | 535/600 [16:36<01:44,  1.60s/it, loss=0.0641, lr=1e-6]
Steps:  89%|████████▉ | 535/600 [16:36<01:44,  1.60s/it, loss=0.143, lr=1e-6] 
Steps:  89%|████████▉ | 536/600 [16:38<01:46,  1.66s/it, loss=0.143, lr=1e-6]
Steps:  89%|████████▉ | 536/600 [16:38<01:46,  1.66s/it, loss=0.224, lr=1e-6]
Steps:  90%|████████▉ | 537/600 [16:39<01:36,  1.53s/it, loss=0.224, lr=1e-6]
Steps:  90%|████████▉ | 537/600 [16:39<01:36,  1.53s/it, loss=0.107, lr=1e-6]
Steps:  90%|████████▉ | 538/600 [16:40<01:30,  1.47s/it, loss=0.107, lr=1e-6]
Steps:  90%|████████▉ | 538/600 [16:40<01:30,  1.47s/it, loss=0.27, lr=1e-6] 
Steps:  90%|████████▉ | 539/600 [16:41<01:16,  1.26s/it, loss=0.27, lr=1e-6]
Steps:  90%|████████▉ | 539/600 [16:41<01:16,  1.26s/it, loss=0.28, lr=1e-6]
Steps:  90%|█████████ | 540/600 [16:43<01:30,  1.51s/it, loss=0.28, lr=1e-6]
Steps:  90%|█████████ | 540/600 [16:43<01:30,  1.51s/it, loss=0.0145, lr=1e-6]
Steps:  90%|█████████ | 541/600 [16:45<01:32,  1.57s/it, loss=0.0145, lr=1e-6]
Steps:  90%|█████████ | 541/600 [16:45<01:32,  1.57s/it, loss=0.0145, lr=1e-6]
Steps:  90%|█████████ | 542/600 [16:46<01:33,  1.60s/it, loss=0.0145, lr=1e-6]
Steps:  90%|█████████ | 542/600 [16:46<01:33,  1.60s/it, loss=0.0138, lr=1e-6]
Steps:  90%|█████████ | 543/600 [16:48<01:35,  1.67s/it, loss=0.0138, lr=1e-6]
Steps:  90%|█████████ | 543/600 [16:48<01:35,  1.67s/it, loss=0.0927, lr=1e-6]
Steps:  91%|█████████ | 544/600 [16:50<01:28,  1.58s/it, loss=0.0927, lr=1e-6]
Steps:  91%|█████████ | 544/600 [16:50<01:28,  1.58s/it, loss=0.0328, lr=1e-6]
Steps:  91%|█████████ | 545/600 [16:51<01:25,  1.55s/it, loss=0.0328, lr=1e-6]
Steps:  91%|█████████ | 545/600 [16:51<01:25,  1.55s/it, loss=0.245, lr=1e-6] 
Steps:  91%|█████████ | 546/600 [16:53<01:24,  1.57s/it, loss=0.245, lr=1e-6]
Steps:  91%|█████████ | 546/600 [16:53<01:24,  1.57s/it, loss=0.0894, lr=1e-6]
Steps:  91%|█████████ | 547/600 [16:54<01:26,  1.63s/it, loss=0.0894, lr=1e-6]
Steps:  91%|█████████ | 547/600 [16:54<01:26,  1.63s/it, loss=0.0252, lr=1e-6]
Steps:  91%|█████████▏| 548/600 [16:56<01:23,  1.60s/it, loss=0.0252, lr=1e-6]
Steps:  91%|█████████▏| 548/600 [16:56<01:23,  1.60s/it, loss=0.0448, lr=1e-6]
Steps:  92%|█████████▏| 549/600 [16:57<01:16,  1.49s/it, loss=0.0448, lr=1e-6]
Steps:  92%|█████████▏| 549/600 [16:57<01:16,  1.49s/it, loss=0.171, lr=1e-6] 
Steps:  92%|█████████▏| 550/600 [16:58<01:03,  1.27s/it, loss=0.171, lr=1e-6]
Steps:  92%|█████████▏| 550/600 [16:58<01:03,  1.27s/it, loss=0.046, lr=1e-6]
Steps:  92%|█████████▏| 551/600 [17:00<01:17,  1.59s/it, loss=0.046, lr=1e-6]
Steps:  92%|█████████▏| 551/600 [17:00<01:17,  1.59s/it, loss=0.104, lr=1e-6]
Steps:  92%|█████████▏| 552/600 [17:02<01:16,  1.59s/it, loss=0.104, lr=1e-6]
Steps:  92%|█████████▏| 552/600 [17:02<01:16,  1.59s/it, loss=0.328, lr=1e-6]
Steps:  92%|█████████▏| 553/600 [17:03<01:12,  1.55s/it, loss=0.328, lr=1e-6]
Steps:  92%|█████████▏| 553/600 [17:03<01:12,  1.55s/it, loss=0.0681, lr=1e-6]
Steps:  92%|█████████▏| 554/600 [17:05<01:15,  1.64s/it, loss=0.0681, lr=1e-6]
Steps:  92%|█████████▏| 554/600 [17:05<01:15,  1.64s/it, loss=0.159, lr=1e-6] 
Steps:  92%|█████████▎| 555/600 [17:07<01:11,  1.59s/it, loss=0.159, lr=1e-6]
Steps:  92%|█████████▎| 555/600 [17:07<01:11,  1.59s/it, loss=0.132, lr=1e-6]
Steps:  93%|█████████▎| 556/600 [17:08<01:08,  1.56s/it, loss=0.132, lr=1e-6]
Steps:  93%|█████████▎| 556/600 [17:08<01:08,  1.56s/it, loss=0.101, lr=1e-6]
Steps:  93%|█████████▎| 557/600 [17:10<01:06,  1.55s/it, loss=0.101, lr=1e-6]
Steps:  93%|█████████▎| 557/600 [17:10<01:06,  1.55s/it, loss=0.262, lr=1e-6]
Steps:  93%|█████████▎| 558/600 [17:11<01:07,  1.61s/it, loss=0.262, lr=1e-6]
Steps:  93%|█████████▎| 558/600 [17:11<01:07,  1.61s/it, loss=0.0781, lr=1e-6]
Steps:  93%|█████████▎| 559/600 [17:13<01:05,  1.60s/it, loss=0.0781, lr=1e-6]
Steps:  93%|█████████▎| 559/600 [17:13<01:05,  1.60s/it, loss=0.0333, lr=1e-6]
Steps:  93%|█████████▎| 560/600 [17:14<00:58,  1.46s/it, loss=0.0333, lr=1e-6]
Steps:  93%|█████████▎| 560/600 [17:14<00:58,  1.46s/it, loss=0.038, lr=1e-6] 
Steps:  94%|█████████▎| 561/600 [17:15<00:48,  1.25s/it, loss=0.038, lr=1e-6]
Steps:  94%|█████████▎| 561/600 [17:15<00:48,  1.25s/it, loss=0.149, lr=1e-6]10/13/2023 10:46:41 - INFO - __main__ - Running validation... 
 Generating 4 images with prompts: "a photo of Brad Pitt in a suit and sunglasses showing <thumbs_up> thumbs up", "a photo of Barack Obama wearing a vest showing <thumbs_up> thumbs up", "a photo of a black man at the beach showing <thumbs_up> thumbs up".


Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]Loaded tokenizer_2 as CLIPTokenizer from `tokenizer_2` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
Loaded scheduler as EulerDiscreteScheduler from `scheduler` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of stabilityai/stable-diffusion-xl-base-1.0.

Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 71.26it/s]
{'lambda_min_clipped', 'algorithm_type', 'variance_type', 'solver_order', 'thresholding', 'dynamic_thresholding_ratio', 'lower_order_final', 'solver_type'} was not found in config. Values will be initialized to default values.
10/13/2023 10:47:38 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
10/13/2023 10:48:27 - INFO - __main__ - Image features shape: torch.Size([5, 75648])
10/13/2023 10:49:17 - INFO - __main__ - Image features shape: torch.Size([5, 75648])

Steps:  94%|█████████▎| 562/600 [20:00<31:54, 50.37s/it, loss=0.149, lr=1e-6]
Steps:  94%|█████████▎| 562/600 [20:00<31:54, 50.37s/it, loss=0.224, lr=1e-6]
Steps:  94%|█████████▍| 563/600 [20:01<22:02, 35.75s/it, loss=0.224, lr=1e-6]
Steps:  94%|█████████▍| 563/600 [20:01<22:02, 35.75s/it, loss=0.0149, lr=1e-6]
Steps:  94%|█████████▍| 564/600 [20:03<15:20, 25.58s/it, loss=0.0149, lr=1e-6]
Steps:  94%|█████████▍| 564/600 [20:03<15:20, 25.58s/it, loss=0.0866, lr=1e-6]
Steps:  94%|█████████▍| 565/600 [20:05<10:42, 18.36s/it, loss=0.0866, lr=1e-6]
Steps:  94%|█████████▍| 565/600 [20:05<10:42, 18.36s/it, loss=0.103, lr=1e-6] 
Steps:  94%|█████████▍| 566/600 [20:06<07:32, 13.32s/it, loss=0.103, lr=1e-6]
Steps:  94%|█████████▍| 566/600 [20:06<07:32, 13.32s/it, loss=0.181, lr=1e-6]
Steps:  94%|█████████▍| 567/600 [20:08<05:25,  9.85s/it, loss=0.181, lr=1e-6]
Steps:  94%|█████████▍| 567/600 [20:08<05:25,  9.85s/it, loss=0.0474, lr=1e-6]
Steps:  95%|█████████▍| 568/600 [20:10<03:53,  7.31s/it, loss=0.0474, lr=1e-6]
Steps:  95%|█████████▍| 568/600 [20:10<03:53,  7.31s/it, loss=0.0236, lr=1e-6]
Steps:  95%|█████████▍| 569/600 [20:11<02:50,  5.52s/it, loss=0.0236, lr=1e-6]
Steps:  95%|█████████▍| 569/600 [20:11<02:50,  5.52s/it, loss=0.167, lr=1e-6] 
Steps:  95%|█████████▌| 570/600 [20:12<02:09,  4.31s/it, loss=0.167, lr=1e-6]
Steps:  95%|█████████▌| 570/600 [20:12<02:09,  4.31s/it, loss=0.138, lr=1e-6]
Steps:  95%|█████████▌| 571/600 [20:14<01:40,  3.45s/it, loss=0.138, lr=1e-6]
Steps:  95%|█████████▌| 571/600 [20:14<01:40,  3.45s/it, loss=0.179, lr=1e-6]
Steps:  95%|█████████▌| 572/600 [20:15<01:14,  2.65s/it, loss=0.179, lr=1e-6]
Steps:  95%|█████████▌| 572/600 [20:15<01:14,  2.65s/it, loss=0.00298, lr=1e-6]
Steps:  96%|█████████▌| 573/600 [20:17<01:06,  2.48s/it, loss=0.00298, lr=1e-6]
Steps:  96%|█████████▌| 573/600 [20:17<01:06,  2.48s/it, loss=0.00295, lr=1e-6]
Steps:  96%|█████████▌| 574/600 [20:18<00:55,  2.14s/it, loss=0.00295, lr=1e-6]
Steps:  96%|█████████▌| 574/600 [20:18<00:55,  2.14s/it, loss=0.0919, lr=1e-6] 
Steps:  96%|█████████▌| 575/600 [20:20<00:50,  2.01s/it, loss=0.0919, lr=1e-6]
Steps:  96%|█████████▌| 575/600 [20:20<00:50,  2.01s/it, loss=0.00997, lr=1e-6]
Steps:  96%|█████████▌| 576/600 [20:21<00:45,  1.91s/it, loss=0.00997, lr=1e-6]
Steps:  96%|█████████▌| 576/600 [20:21<00:45,  1.91s/it, loss=0.0495, lr=1e-6] 
Steps:  96%|█████████▌| 577/600 [20:23<00:41,  1.82s/it, loss=0.0495, lr=1e-6]
Steps:  96%|█████████▌| 577/600 [20:23<00:41,  1.82s/it, loss=0.00437, lr=1e-6]
Steps:  96%|█████████▋| 578/600 [20:24<00:37,  1.69s/it, loss=0.00437, lr=1e-6]
Steps:  96%|█████████▋| 578/600 [20:24<00:37,  1.69s/it, loss=0.337, lr=1e-6]  
Steps:  96%|█████████▋| 579/600 [20:26<00:35,  1.71s/it, loss=0.337, lr=1e-6]
Steps:  96%|█████████▋| 579/600 [20:26<00:35,  1.71s/it, loss=0.03, lr=1e-6] 
Steps:  97%|█████████▋| 580/600 [20:28<00:35,  1.75s/it, loss=0.03, lr=1e-6]
Steps:  97%|█████████▋| 580/600 [20:28<00:35,  1.75s/it, loss=0.234, lr=1e-6]
Steps:  97%|█████████▋| 581/600 [20:30<00:32,  1.70s/it, loss=0.234, lr=1e-6]
Steps:  97%|█████████▋| 581/600 [20:30<00:32,  1.70s/it, loss=0.151, lr=1e-6]
Steps:  97%|█████████▋| 582/600 [20:31<00:28,  1.61s/it, loss=0.151, lr=1e-6]
Steps:  97%|█████████▋| 582/600 [20:31<00:28,  1.61s/it, loss=0.233, lr=1e-6]
Steps:  97%|█████████▋| 583/600 [20:32<00:23,  1.35s/it, loss=0.233, lr=1e-6]
Steps:  97%|█████████▋| 583/600 [20:32<00:23,  1.35s/it, loss=0.0959, lr=1e-6]
Steps:  97%|█████████▋| 584/600 [20:34<00:25,  1.58s/it, loss=0.0959, lr=1e-6]
Steps:  97%|█████████▋| 584/600 [20:34<00:25,  1.58s/it, loss=0.251, lr=1e-6] 
Steps:  98%|█████████▊| 585/600 [20:35<00:23,  1.53s/it, loss=0.251, lr=1e-6]
Steps:  98%|█████████▊| 585/600 [20:35<00:23,  1.53s/it, loss=0.169, lr=1e-6]
Steps:  98%|█████████▊| 586/600 [20:37<00:21,  1.55s/it, loss=0.169, lr=1e-6]
Steps:  98%|█████████▊| 586/600 [20:37<00:21,  1.55s/it, loss=0.0183, lr=1e-6]
Steps:  98%|█████████▊| 587/600 [20:38<00:20,  1.55s/it, loss=0.0183, lr=1e-6]
Steps:  98%|█████████▊| 587/600 [20:38<00:20,  1.55s/it, loss=0.152, lr=1e-6] 
Steps:  98%|█████████▊| 588/600 [20:40<00:18,  1.58s/it, loss=0.152, lr=1e-6]
Steps:  98%|█████████▊| 588/600 [20:40<00:18,  1.58s/it, loss=0.114, lr=1e-6]
Steps:  98%|█████████▊| 589/600 [20:42<00:18,  1.66s/it, loss=0.114, lr=1e-6]
Steps:  98%|█████████▊| 589/600 [20:42<00:18,  1.66s/it, loss=0.0173, lr=1e-6]
Steps:  98%|█████████▊| 590/600 [20:43<00:16,  1.64s/it, loss=0.0173, lr=1e-6]
Steps:  98%|█████████▊| 590/600 [20:43<00:16,  1.64s/it, loss=0.0725, lr=1e-6]
Steps:  98%|█████████▊| 591/600 [20:45<00:14,  1.56s/it, loss=0.0725, lr=1e-6]
Steps:  98%|█████████▊| 591/600 [20:45<00:14,  1.56s/it, loss=0.0307, lr=1e-6]
Steps:  99%|█████████▊| 592/600 [20:47<00:13,  1.63s/it, loss=0.0307, lr=1e-6]
Steps:  99%|█████████▊| 592/600 [20:47<00:13,  1.63s/it, loss=0.0743, lr=1e-6]
Steps:  99%|█████████▉| 593/600 [20:48<00:10,  1.51s/it, loss=0.0743, lr=1e-6]
Steps:  99%|█████████▉| 593/600 [20:48<00:10,  1.51s/it, loss=0.189, lr=1e-6] 
Steps:  99%|█████████▉| 594/600 [20:49<00:07,  1.29s/it, loss=0.189, lr=1e-6]
Steps:  99%|█████████▉| 594/600 [20:49<00:07,  1.29s/it, loss=0.00347, lr=1e-6]
Steps:  99%|█████████▉| 595/600 [20:51<00:07,  1.53s/it, loss=0.00347, lr=1e-6]
Steps:  99%|█████████▉| 595/600 [20:51<00:07,  1.53s/it, loss=0.194, lr=1e-6]  
Steps:  99%|█████████▉| 596/600 [20:52<00:06,  1.59s/it, loss=0.194, lr=1e-6]
Steps:  99%|█████████▉| 596/600 [20:52<00:06,  1.59s/it, loss=0.162, lr=1e-6]
Steps: 100%|█████████▉| 597/600 [20:54<00:04,  1.64s/it, loss=0.162, lr=1e-6]
Steps: 100%|█████████▉| 597/600 [20:54<00:04,  1.64s/it, loss=0.21, lr=1e-6] 
Steps: 100%|█████████▉| 598/600 [20:56<00:03,  1.60s/it, loss=0.21, lr=1e-6]
Steps: 100%|█████████▉| 598/600 [20:56<00:03,  1.60s/it, loss=0.202, lr=1e-6]
Steps: 100%|█████████▉| 599/600 [20:57<00:01,  1.58s/it, loss=0.202, lr=1e-6]
Steps: 100%|█████████▉| 599/600 [20:57<00:01,  1.58s/it, loss=0.101, lr=1e-6]
Steps: 100%|██████████| 600/600 [20:59<00:00,  1.54s/it, loss=0.101, lr=1e-6]
Steps: 100%|██████████| 600/600 [20:59<00:00,  1.54s/it, loss=0.0766, lr=1e-6]Model weights saved in logs/sweep_final_2_20231013102808/pytorch_lora_weights.safetensors


Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]Loaded tokenizer_2 as CLIPTokenizer from `tokenizer_2` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
Loaded scheduler as EulerDiscreteScheduler from `scheduler` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of stabilityai/stable-diffusion-xl-base-1.0.


Loading pipeline components...:  57%|█████▋    | 4/7 [00:00<00:00, 39.23it/s]Loaded text_encoder_2 as CLIPTextModelWithProjection from `text_encoder_2` subfolder of stabilityai/stable-diffusion-xl-base-1.0.
{'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.
Loaded text_encoder as CLIPTextModel from `text_encoder` subfolder of stabilityai/stable-diffusion-xl-base-1.0.

Loading pipeline components...: 100%|██████████| 7/7 [00:04<00:00,  1.50it/s]
{'lambda_min_clipped', 'algorithm_type', 'variance_type', 'solver_order', 'thresholding', 'dynamic_thresholding_ratio', 'lower_order_final', 'solver_type'} was not found in config. Values will be initialized to default values.
Loading unet.


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

  2%|▏         | 1/50 [00:00<00:09,  5.36it/s]

  4%|▍         | 2/50 [00:00<00:07,  6.20it/s]

  6%|▌         | 3/50 [00:00<00:08,  5.80it/s]

  8%|▊         | 4/50 [00:00<00:08,  5.60it/s]

 10%|█         | 5/50 [00:00<00:08,  5.50it/s]

 12%|█▏        | 6/50 [00:01<00:08,  5.44it/s]

 14%|█▍        | 7/50 [00:01<00:07,  5.40it/s]

 16%|█▌        | 8/50 [00:01<00:07,  5.37it/s]

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

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

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

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

 26%|██▌       | 13/50 [00:02<00:06,  5.33it/s]

 28%|██▊       | 14/50 [00:02<00:06,  5.33it/s]

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

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

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

 36%|███▌      | 18/50 [00:03<00:06,  5.32it/s]

 38%|███▊      | 19/50 [00:03<00:05,  5.32it/s]

 40%|████      | 20/50 [00:03<00:05,  5.33it/s]

 42%|████▏     | 21/50 [00:03<00:05,  5.32it/s]

 44%|████▍     | 22/50 [00:04<00:05,  5.32it/s]

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

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

 50%|█████     | 25/50 [00:04<00:04,  5.31it/s]

 52%|█████▏    | 26/50 [00:04<00:04,  5.32it/s]

 54%|█████▍    | 27/50 [00:05<00:04,  5.32it/s]

 56%|█████▌    | 28/50 [00:05<00:04,  5.31it/s]

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

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

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

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

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

 68%|██████▊   | 34/50 [00:06<00:03,  5.32it/s]

 70%|███████   | 35/50 [00:06<00:02,  5.32it/s]

 72%|███████▏  | 36/50 [00:06<00:02,  5.32it/s]

 74%|███████▍  | 37/50 [00:06<00:02,  5.33it/s]

 76%|███████▌  | 38/50 [00:07<00:02,  5.32it/s]

 78%|███████▊  | 39/50 [00:07<00:02,  5.32it/s]

 80%|████████  | 40/50 [00:07<00:01,  5.31it/s]

 82%|████████▏ | 41/50 [00:07<00:01,  5.32it/s]

 84%|████████▍ | 42/50 [00:07<00:01,  5.32it/s]

 86%|████████▌ | 43/50 [00:08<00:01,  5.33it/s]

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

 90%|█████████ | 45/50 [00:08<00:00,  5.32it/s]

 92%|█████████▏| 46/50 [00:08<00:00,  5.32it/s]

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

 96%|█████████▌| 48/50 [00:09<00:00,  3.53it/s]

 98%|█████████▊| 49/50 [00:09<00:00,  3.93it/s]

100%|██████████| 50/50 [00:09<00:00,  4.26it/s]
100%|██████████| 50/50 [00:09<00:00,  5.17it/s]


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

  2%|▏         | 1/50 [00:00<00:09,  5.41it/s]

  4%|▍         | 2/50 [00:00<00:07,  6.24it/s]

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

  8%|▊         | 4/50 [00:00<00:08,  5.60it/s]

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

 12%|█▏        | 6/50 [00:01<00:08,  5.41it/s]

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

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

 18%|█▊        | 9/50 [00:01<00:07,  5.33it/s]

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

 22%|██▏       | 11/50 [00:02<00:07,  5.32it/s]

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

 26%|██▌       | 13/50 [00:02<00:06,  5.33it/s]

 28%|██▊       | 14/50 [00:02<00:06,  5.31it/s]

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

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

 34%|███▍      | 17/50 [00:03<00:06,  5.30it/s]

 36%|███▌      | 18/50 [00:03<00:06,  5.31it/s]

 38%|███▊      | 19/50 [00:03<00:05,  5.30it/s]

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

 42%|████▏     | 21/50 [00:03<00:05,  5.30it/s]

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

 46%|████▌     | 23/50 [00:04<00:05,  5.30it/s]

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

 50%|█████     | 25/50 [00:04<00:04,  5.31it/s]

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

 54%|█████▍    | 27/50 [00:05<00:04,  5.30it/s]

 56%|█████▌    | 28/50 [00:05<00:04,  5.30it/s]

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

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

 62%|██████▏   | 31/50 [00:05<00:03,  5.30it/s]

 64%|██████▍   | 32/50 [00:05<00:03,  5.30it/s]

 66%|██████▌   | 33/50 [00:06<00:03,  5.30it/s]

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

 70%|███████   | 35/50 [00:06<00:02,  5.31it/s]

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

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

 76%|███████▌  | 38/50 [00:07<00:02,  5.30it/s]

 78%|███████▊  | 39/50 [00:07<00:02,  5.30it/s]

 80%|████████  | 40/50 [00:07<00:01,  5.30it/s]

 82%|████████▏ | 41/50 [00:07<00:01,  5.30it/s]

 84%|████████▍ | 42/50 [00:07<00:01,  5.30it/s]

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

 88%|████████▊ | 44/50 [00:08<00:01,  5.30it/s]

 90%|█████████ | 45/50 [00:08<00:00,  5.29it/s]

 92%|█████████▏| 46/50 [00:08<00:00,  5.29it/s]

 94%|█████████▍| 47/50 [00:08<00:00,  5.28it/s]

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

 98%|█████████▊| 49/50 [00:09<00:00,  5.28it/s]

100%|██████████| 50/50 [00:09<00:00,  5.29it/s]
100%|██████████| 50/50 [00:09<00:00,  5.33it/s]


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

  2%|▏         | 1/50 [00:00<00:09,  5.40it/s]

  4%|▍         | 2/50 [00:00<00:07,  6.20it/s]

  6%|▌         | 3/50 [00:00<00:08,  5.76it/s]

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

 10%|█         | 5/50 [00:00<00:08,  5.46it/s]

 12%|█▏        | 6/50 [00:01<00:08,  5.40it/s]

 14%|█▍        | 7/50 [00:01<00:08,  5.36it/s]

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

 18%|█▊        | 9/50 [00:01<00:07,  5.34it/s]

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

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

 24%|██▍       | 12/50 [00:02<00:07,  5.30it/s]

 26%|██▌       | 13/50 [00:02<00:06,  5.30it/s]

 28%|██▊       | 14/50 [00:02<00:06,  5.30it/s]

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

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

 34%|███▍      | 17/50 [00:03<00:06,  5.30it/s]

 36%|███▌      | 18/50 [00:03<00:06,  5.29it/s]

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

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

 42%|████▏     | 21/50 [00:03<00:05,  5.30it/s]

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

 46%|████▌     | 23/50 [00:04<00:05,  5.30it/s]

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

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

 52%|█████▏    | 26/50 [00:04<00:04,  5.29it/s]

 54%|█████▍    | 27/50 [00:05<00:04,  5.29it/s]

 56%|█████▌    | 28/50 [00:05<00:04,  5.30it/s]

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

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

 62%|██████▏   | 31/50 [00:05<00:03,  5.30it/s]

 64%|██████▍   | 32/50 [00:05<00:03,  5.30it/s]

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

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

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

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

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

 76%|███████▌  | 38/50 [00:07<00:02,  5.27it/s]

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

 80%|████████  | 40/50 [00:07<00:01,  5.29it/s]

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

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

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

 88%|████████▊ | 44/50 [00:08<00:01,  5.30it/s]

 90%|█████████ | 45/50 [00:08<00:00,  5.31it/s]

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

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

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

 98%|█████████▊| 49/50 [00:09<00:00,  5.30it/s]

100%|██████████| 50/50 [00:09<00:00,  5.30it/s]
100%|██████████| 50/50 [00:09<00:00,  5.32it/s]


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

  2%|▏         | 1/50 [00:00<00:09,  5.39it/s]

  4%|▍         | 2/50 [00:00<00:07,  6.21it/s]

  6%|▌         | 3/50 [00:00<00:08,  5.73it/s]

  8%|▊         | 4/50 [00:00<00:08,  5.54it/s]

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

 12%|█▏        | 6/50 [00:01<00:08,  5.38it/s]

 14%|█▍        | 7/50 [00:01<00:08,  5.35it/s]

 16%|█▌        | 8/50 [00:01<00:07,  5.33it/s]

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

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

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

 24%|██▍       | 12/50 [00:02<00:07,  5.30it/s]

 26%|██▌       | 13/50 [00:02<00:06,  5.30it/s]

 28%|██▊       | 14/50 [00:02<00:06,  5.30it/s]

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

 32%|███▏      | 16/50 [00:02<00:06,  5.28it/s]

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

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

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

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

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

 44%|████▍     | 22/50 [00:04<00:05,  5.29it/s]

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

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

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

 52%|█████▏    | 26/50 [00:04<00:04,  5.29it/s]

 54%|█████▍    | 27/50 [00:05<00:04,  5.29it/s]

 56%|█████▌    | 28/50 [00:05<00:04,  5.30it/s]

 58%|█████▊    | 29/50 [00:05<00:03,  5.28it/s]

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

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

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

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

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

 70%|███████   | 35/50 [00:06<00:02,  5.30it/s]

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

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

 76%|███████▌  | 38/50 [00:07<00:02,  5.27it/s]

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

 80%|████████  | 40/50 [00:07<00:01,  5.27it/s]

 82%|████████▏ | 41/50 [00:07<00:01,  5.27it/s]

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

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

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

 90%|█████████ | 45/50 [00:08<00:00,  5.28it/s]

 92%|█████████▏| 46/50 [00:08<00:00,  5.28it/s]

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

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

 98%|█████████▊| 49/50 [00:09<00:00,  5.28it/s]

100%|██████████| 50/50 [00:09<00:00,  5.29it/s]
100%|██████████| 50/50 [00:09<00:00,  5.31it/s]
10/13/2023 10:51:22 - INFO - __main__ - Image features shape: torch.Size([5, 75648])


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

  2%|▏         | 1/50 [00:00<00:09,  5.43it/s]

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

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

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

 10%|█         | 5/50 [00:00<00:08,  5.50it/s]

 12%|█▏        | 6/50 [00:01<00:08,  5.43it/s]

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

 16%|█▌        | 8/50 [00:01<00:07,  5.37it/s]

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

 20%|██        | 10/50 [00:01<00:07,  5.34it/s]

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

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

 26%|██▌       | 13/50 [00:02<00:06,  5.32it/s]

 28%|██▊       | 14/50 [00:02<00:06,  5.32it/s]

 30%|███       | 15/50 [00:02<00:06,  5.32it/s]

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

 34%|███▍      | 17/50 [00:03<00:06,  5.31it/s]

 36%|███▌      | 18/50 [00:03<00:06,  5.31it/s]

 38%|███▊      | 19/50 [00:03<00:05,  5.31it/s]

 40%|████      | 20/50 [00:03<00:05,  5.31it/s]

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

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

 46%|████▌     | 23/50 [00:04<00:05,  5.30it/s]

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

 50%|█████     | 25/50 [00:04<00:04,  5.31it/s]

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

 54%|█████▍    | 27/50 [00:05<00:04,  5.29it/s]

 56%|█████▌    | 28/50 [00:05<00:04,  5.30it/s]

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

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

 62%|██████▏   | 31/50 [00:05<00:03,  5.30it/s]

 64%|██████▍   | 32/50 [00:05<00:03,  5.30it/s]

 66%|██████▌   | 33/50 [00:06<00:03,  5.30it/s]

 68%|██████▊   | 34/50 [00:06<00:03,  5.29it/s]

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

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

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

 76%|███████▌  | 38/50 [00:07<00:02,  5.28it/s]

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

 80%|████████  | 40/50 [00:07<00:01,  5.29it/s]

 82%|████████▏ | 41/50 [00:07<00:01,  5.30it/s]

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

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

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

 90%|█████████ | 45/50 [00:08<00:00,  5.29it/s]

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

 94%|█████████▍| 47/50 [00:08<00:00,  5.28it/s]

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

 98%|█████████▊| 49/50 [00:09<00:00,  5.28it/s]

100%|██████████| 50/50 [00:09<00:00,  5.29it/s]
100%|██████████| 50/50 [00:09<00:00,  5.33it/s]


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

  2%|▏         | 1/50 [00:00<00:09,  5.40it/s]

  4%|▍         | 2/50 [00:00<00:07,  6.20it/s]

  6%|▌         | 3/50 [00:00<00:08,  5.75it/s]

  8%|▊         | 4/50 [00:00<00:08,  5.56it/s]

 10%|█         | 5/50 [00:00<00:08,  5.46it/s]

 12%|█▏        | 6/50 [00:01<00:08,  5.40it/s]

 14%|█▍        | 7/50 [00:01<00:08,  5.36it/s]

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

 18%|█▊        | 9/50 [00:01<00:07,  5.33it/s]

 20%|██        | 10/50 [00:01<00:07,  5.31it/s]

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

 24%|██▍       | 12/50 [00:02<00:07,  5.30it/s]

 26%|██▌       | 13/50 [00:02<00:06,  5.30it/s]

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

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

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

 34%|███▍      | 17/50 [00:03<00:06,  5.30it/s]

 36%|███▌      | 18/50 [00:03<00:06,  5.29it/s]

 38%|███▊      | 19/50 [00:03<00:05,  5.30it/s]

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

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

 44%|████▍     | 22/50 [00:04<00:05,  5.29it/s]

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

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

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

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

 54%|█████▍    | 27/50 [00:05<00:04,  5.30it/s]

 56%|█████▌    | 28/50 [00:05<00:04,  5.30it/s]

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

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

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

 64%|██████▍   | 32/50 [00:05<00:03,  5.29it/s]

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

 68%|██████▊   | 34/50 [00:06<00:03,  5.29it/s]

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

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

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

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

 78%|███████▊  | 39/50 [00:07<00:02,  5.30it/s]

 80%|████████  | 40/50 [00:07<00:01,  5.30it/s]

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

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

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

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

 90%|█████████ | 45/50 [00:08<00:00,  5.30it/s]

 92%|█████████▏| 46/50 [00:08<00:00,  5.29it/s]

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

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

 98%|█████████▊| 49/50 [00:09<00:00,  5.29it/s]

100%|██████████| 50/50 [00:09<00:00,  5.30it/s]
100%|██████████| 50/50 [00:09<00:00,  5.32it/s]


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

  2%|▏         | 1/50 [00:00<00:09,  5.40it/s]

  4%|▍         | 2/50 [00:00<00:07,  6.23it/s]

  6%|▌         | 3/50 [00:00<00:08,  5.76it/s]

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

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

 12%|█▏        | 6/50 [00:01<00:08,  5.41it/s]

 14%|█▍        | 7/50 [00:01<00:08,  5.37it/s]

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

 18%|█▊        | 9/50 [00:01<00:07,  5.33it/s]

 20%|██        | 10/50 [00:01<00:07,  5.30it/s]

 22%|██▏       | 11/50 [00:02<00:07,  5.30it/s]

 24%|██▍       | 12/50 [00:02<00:07,  5.29it/s]

 26%|██▌       | 13/50 [00:02<00:06,  5.30it/s]

 28%|██▊       | 14/50 [00:02<00:06,  5.30it/s]

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

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

 34%|███▍      | 17/50 [00:03<00:06,  5.30it/s]

 36%|███▌      | 18/50 [00:03<00:06,  5.30it/s]

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

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

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

 44%|████▍     | 22/50 [00:04<00:05,  5.29it/s]

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

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

 50%|█████     | 25/50 [00:04<00:04,  5.30it/s]

 52%|█████▏    | 26/50 [00:04<00:04,  5.29it/s]

 54%|█████▍    | 27/50 [00:05<00:04,  5.29it/s]

 56%|█████▌    | 28/50 [00:05<00:04,  5.29it/s]

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

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

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

 64%|██████▍   | 32/50 [00:05<00:03,  5.29it/s]

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

 68%|██████▊   | 34/50 [00:06<00:03,  5.29it/s]

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

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

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

 76%|███████▌  | 38/50 [00:07<00:02,  5.30it/s]

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

 80%|████████  | 40/50 [00:07<00:01,  5.29it/s]

 82%|████████▏ | 41/50 [00:07<00:01,  5.28it/s]

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

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

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

 90%|█████████ | 45/50 [00:08<00:00,  5.28it/s]

 92%|█████████▏| 46/50 [00:08<00:00,  5.28it/s]

 94%|█████████▍| 47/50 [00:08<00:00,  5.28it/s]

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

 98%|█████████▊| 49/50 [00:09<00:00,  5.29it/s]

100%|██████████| 50/50 [00:09<00:00,  5.29it/s]
100%|██████████| 50/50 [00:09<00:00,  5.32it/s]


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

  2%|▏         | 1/50 [00:00<00:09,  5.39it/s]

  4%|▍         | 2/50 [00:00<00:07,  6.20it/s]

  6%|▌         | 3/50 [00:00<00:08,  5.75it/s]

  8%|▊         | 4/50 [00:00<00:08,  5.56it/s]

 10%|█         | 5/50 [00:00<00:08,  5.46it/s]

 12%|█▏        | 6/50 [00:01<00:08,  5.40it/s]

 14%|█▍        | 7/50 [00:01<00:08,  5.36it/s]

 16%|█▌        | 8/50 [00:01<00:07,  5.32it/s]

 18%|█▊        | 9/50 [00:01<00:07,  5.30it/s]

 20%|██        | 10/50 [00:01<00:07,  5.30it/s]

 22%|██▏       | 11/50 [00:02<00:07,  5.30it/s]

 24%|██▍       | 12/50 [00:02<00:07,  5.30it/s]

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

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

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

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

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

 36%|███▌      | 18/50 [00:03<00:06,  5.29it/s]

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

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

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

 44%|████▍     | 22/50 [00:04<00:06,  4.12it/s]

 46%|████▌     | 23/50 [00:04<00:06,  4.40it/s]

 48%|████▊     | 24/50 [00:04<00:05,  4.62it/s]

 50%|█████     | 25/50 [00:04<00:05,  4.80it/s]

 52%|█████▏    | 26/50 [00:05<00:04,  4.95it/s]

 54%|█████▍    | 27/50 [00:05<00:04,  5.03it/s]

 56%|█████▌    | 28/50 [00:05<00:04,  5.10it/s]

 58%|█████▊    | 29/50 [00:05<00:04,  5.16it/s]

 60%|██████    | 30/50 [00:05<00:03,  5.20it/s]

 62%|██████▏   | 31/50 [00:06<00:03,  5.22it/s]

 64%|██████▍   | 32/50 [00:06<00:03,  5.24it/s]

 66%|██████▌   | 33/50 [00:06<00:03,  5.25it/s]

 68%|██████▊   | 34/50 [00:06<00:03,  5.27it/s]

 70%|███████   | 35/50 [00:06<00:02,  5.27it/s]

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

 74%|███████▍  | 37/50 [00:07<00:02,  5.28it/s]

 76%|███████▌  | 38/50 [00:07<00:02,  5.27it/s]

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

 80%|████████  | 40/50 [00:07<00:01,  5.29it/s]

 82%|████████▏ | 41/50 [00:07<00:01,  5.28it/s]

 84%|████████▍ | 42/50 [00:08<00:01,  5.29it/s]

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

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

 90%|█████████ | 45/50 [00:08<00:00,  5.28it/s]

 92%|█████████▏| 46/50 [00:08<00:00,  5.28it/s]

 94%|█████████▍| 47/50 [00:09<00:00,  5.28it/s]

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

 98%|█████████▊| 49/50 [00:09<00:00,  5.29it/s]

100%|██████████| 50/50 [00:09<00:00,  5.29it/s]
100%|██████████| 50/50 [00:09<00:00,  5.21it/s]
10/13/2023 10:52:11 - INFO - __main__ - Image features shape: torch.Size([5, 75648])


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

  2%|▏         | 1/50 [00:00<00:09,  5.42it/s]

  4%|▍         | 2/50 [00:00<00:07,  6.24it/s]

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

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

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

 12%|█▏        | 6/50 [00:01<00:08,  5.43it/s]

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

 16%|█▌        | 8/50 [00:01<00:07,  5.36it/s]

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

 20%|██        | 10/50 [00:01<00:07,  5.34it/s]

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

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

 26%|██▌       | 13/50 [00:02<00:06,  5.33it/s]

 28%|██▊       | 14/50 [00:02<00:06,  5.33it/s]

 30%|███       | 15/50 [00:02<00:06,  5.32it/s]

 32%|███▏      | 16/50 [00:02<00:06,  5.32it/s]

 34%|███▍      | 17/50 [00:03<00:06,  5.31it/s]

 36%|███▌      | 18/50 [00:03<00:06,  5.31it/s]

 38%|███▊      | 19/50 [00:03<00:05,  5.30it/s]

 40%|████      | 20/50 [00:03<00:05,  5.31it/s]

 42%|████▏     | 21/50 [00:03<00:05,  5.30it/s]

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

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

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

 50%|█████     | 25/50 [00:04<00:04,  5.30it/s]

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

 54%|█████▍    | 27/50 [00:05<00:04,  5.30it/s]

 56%|█████▌    | 28/50 [00:05<00:04,  5.30it/s]

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

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

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

 64%|██████▍   | 32/50 [00:05<00:03,  5.28it/s]

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

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

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

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

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

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

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

 80%|████████  | 40/50 [00:07<00:01,  5.29it/s]

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

 84%|████████▍ | 42/50 [00:07<00:01,  5.30it/s]

 86%|████████▌ | 43/50 [00:08<00:01,  5.30it/s]

 88%|████████▊ | 44/50 [00:08<00:01,  5.30it/s]

 90%|█████████ | 45/50 [00:08<00:00,  5.30it/s]

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

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

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

 98%|█████████▊| 49/50 [00:09<00:00,  5.29it/s]

100%|██████████| 50/50 [00:09<00:00,  5.28it/s]
100%|██████████| 50/50 [00:09<00:00,  5.33it/s]


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

  2%|▏         | 1/50 [00:00<00:09,  5.40it/s]

  4%|▍         | 2/50 [00:00<00:07,  6.19it/s]

  6%|▌         | 3/50 [00:00<00:08,  5.75it/s]

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

 10%|█         | 5/50 [00:00<00:08,  5.46it/s]

 12%|█▏        | 6/50 [00:01<00:08,  5.40it/s]

 14%|█▍        | 7/50 [00:01<00:08,  5.37it/s]

 16%|█▌        | 8/50 [00:01<00:07,  5.33it/s]

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

 20%|██        | 10/50 [00:01<00:07,  5.30it/s]

 22%|██▏       | 11/50 [00:02<00:07,  5.30it/s]

 24%|██▍       | 12/50 [00:02<00:07,  5.29it/s]

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

 28%|██▊       | 14/50 [00:02<00:06,  5.27it/s]

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

 32%|███▏      | 16/50 [00:02<00:06,  5.28it/s]

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

 36%|███▌      | 18/50 [00:03<00:06,  5.29it/s]

 38%|███▊      | 19/50 [00:03<00:05,  5.30it/s]

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

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

 44%|████▍     | 22/50 [00:04<00:05,  5.29it/s]

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

 48%|████▊     | 24/50 [00:04<00:04,  5.28it/s]

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

 52%|█████▏    | 26/50 [00:04<00:04,  5.29it/s]

 54%|█████▍    | 27/50 [00:05<00:04,  5.28it/s]

 56%|█████▌    | 28/50 [00:05<00:04,  5.29it/s]

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

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

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

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

 66%|██████▌   | 33/50 [00:06<00:03,  5.30it/s]

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

 70%|███████   | 35/50 [00:06<00:02,  5.30it/s]

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

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

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

 78%|███████▊  | 39/50 [00:07<00:02,  5.30it/s]

 80%|████████  | 40/50 [00:07<00:01,  5.29it/s]

 82%|████████▏ | 41/50 [00:07<00:01,  5.30it/s]

 84%|████████▍ | 42/50 [00:07<00:01,  5.30it/s]

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

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

 90%|█████████ | 45/50 [00:08<00:00,  5.28it/s]

 92%|█████████▏| 46/50 [00:08<00:00,  5.27it/s]

 94%|█████████▍| 47/50 [00:08<00:00,  5.28it/s]

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

 98%|█████████▊| 49/50 [00:09<00:00,  5.29it/s]

100%|██████████| 50/50 [00:09<00:00,  5.29it/s]
100%|██████████| 50/50 [00:09<00:00,  5.31it/s]


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

  2%|▏         | 1/50 [00:00<00:09,  5.39it/s]

  4%|▍         | 2/50 [00:00<00:07,  6.20it/s]

  6%|▌         | 3/50 [00:00<00:08,  5.75it/s]

  8%|▊         | 4/50 [00:00<00:08,  5.56it/s]

 10%|█         | 5/50 [00:00<00:08,  5.46it/s]

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

 14%|█▍        | 7/50 [00:01<00:08,  5.36it/s]

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

 18%|█▊        | 9/50 [00:01<00:07,  5.33it/s]

 20%|██        | 10/50 [00:01<00:07,  5.30it/s]

 22%|██▏       | 11/50 [00:02<00:07,  5.30it/s]

 24%|██▍       | 12/50 [00:02<00:07,  5.29it/s]

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

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

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

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

 34%|███▍      | 17/50 [00:03<00:06,  5.30it/s]

 36%|███▌      | 18/50 [00:03<00:06,  5.29it/s]

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

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

 42%|████▏     | 21/50 [00:03<00:05,  5.30it/s]

 44%|████▍     | 22/50 [00:04<00:05,  5.29it/s]

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

 48%|████▊     | 24/50 [00:04<00:04,  5.28it/s]

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

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

 54%|█████▍    | 27/50 [00:05<00:04,  5.28it/s]

 56%|█████▌    | 28/50 [00:05<00:04,  5.28it/s]

 58%|█████▊    | 29/50 [00:05<00:03,  5.27it/s]

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

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

 64%|██████▍   | 32/50 [00:06<00:03,  5.28it/s]

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

 68%|██████▊   | 34/50 [00:06<00:03,  5.29it/s]

 70%|███████   | 35/50 [00:06<00:02,  5.28it/s]

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

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

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

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

 80%|████████  | 40/50 [00:07<00:01,  5.29it/s]

 82%|████████▏ | 41/50 [00:07<00:01,  5.28it/s]

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

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

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

 90%|█████████ | 45/50 [00:08<00:00,  5.28it/s]

 92%|█████████▏| 46/50 [00:08<00:00,  5.27it/s]

 94%|█████████▍| 47/50 [00:08<00:00,  5.28it/s]

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

 98%|█████████▊| 49/50 [00:09<00:00,  5.29it/s]

100%|██████████| 50/50 [00:09<00:00,  5.29it/s]
100%|██████████| 50/50 [00:09<00:00,  5.31it/s]


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

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

  4%|▍         | 2/50 [00:00<00:07,  6.20it/s]

  6%|▌         | 3/50 [00:00<00:08,  5.75it/s]

  8%|▊         | 4/50 [00:00<00:08,  5.56it/s]

 10%|█         | 5/50 [00:00<00:08,  5.46it/s]

 12%|█▏        | 6/50 [00:01<00:08,  5.41it/s]

 14%|█▍        | 7/50 [00:01<00:08,  5.36it/s]

 16%|█▌        | 8/50 [00:01<00:07,  5.33it/s]

 18%|█▊        | 9/50 [00:01<00:07,  5.33it/s]

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

 22%|██▏       | 11/50 [00:02<00:07,  5.30it/s]

 24%|██▍       | 12/50 [00:02<00:07,  5.29it/s]

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

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

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

 32%|███▏      | 16/50 [00:02<00:06,  5.28it/s]

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

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

 38%|███▊      | 19/50 [00:03<00:05,  5.27it/s]

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

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

 44%|████▍     | 22/50 [00:04<00:05,  5.28it/s]

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

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

 50%|█████     | 25/50 [00:04<00:04,  5.28it/s]

 52%|█████▏    | 26/50 [00:04<00:04,  5.29it/s]

 54%|█████▍    | 27/50 [00:05<00:04,  5.29it/s]

 56%|█████▌    | 28/50 [00:05<00:04,  5.29it/s]

 58%|█████▊    | 29/50 [00:05<00:03,  5.28it/s]

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

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

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

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

 68%|██████▊   | 34/50 [00:06<00:03,  5.29it/s]

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

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

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

 76%|███████▌  | 38/50 [00:07<00:02,  5.28it/s]

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

 80%|████████  | 40/50 [00:07<00:01,  5.27it/s]

 82%|████████▏ | 41/50 [00:07<00:01,  5.28it/s]

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

 86%|████████▌ | 43/50 [00:08<00:01,  5.27it/s]

 88%|████████▊ | 44/50 [00:08<00:01,  5.27it/s]

 90%|█████████ | 45/50 [00:08<00:00,  5.28it/s]

 92%|█████████▏| 46/50 [00:08<00:00,  5.28it/s]

 94%|█████████▍| 47/50 [00:08<00:00,  5.28it/s]

 96%|█████████▌| 48/50 [00:09<00:00,  5.27it/s]

 98%|█████████▊| 49/50 [00:09<00:00,  5.27it/s]

100%|██████████| 50/50 [00:09<00:00,  5.26it/s]
100%|██████████| 50/50 [00:09<00:00,  5.31it/s]
10/13/2023 10:53:00 - INFO - __main__ - Image features shape: torch.Size([5, 75648])


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


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



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




scheduler.bin:   0%|          | 0.00/563 [00:00<?, ?B/s]





scaler.pt:   0%|          | 0.00/557 [00:00<?, ?B/s]






random_states_0.pkl:   0%|          | 0.00/14.6k [00:00<?, ?B/s]



pytorch_lora_weights.safetensors:   0%|          | 8.19k/23.4M [00:00<31:56, 12.2kB/s]





scaler.pt: 100%|██████████| 557/557 [00:00<00:00, 835B/s]


optimizer.bin:   0%|          | 8.19k/47.4M [00:00<1:06:01, 12.0kB/s]






random_states_0.pkl:  56%|█████▌    | 8.19k/14.6k [00:00<00:00, 12.3kB/s]




scheduler.bin: 100%|██████████| 563/563 [00:00<00:00, 825B/s]



pytorch_lora_weights.safetensors:   1%|          | 279k/23.4M [00:00<00:48, 480kB/s]  
scaler.pt: 100%|██████████| 557/557 [00:00<00:00, 729B/s]

random_states_0.pkl: 100%|██████████| 14.6k/14.6k [00:00<00:00, 18.9kB/s]

scheduler.bin: 100%|██████████| 563/563 [00:00<00:00, 716B/s]



optimizer.bin:   1%|          | 369k/47.4M [00:00<01:16, 615kB/s]    



pytorch_lora_weights.safetensors:  10%|█         | 2.38M/23.4M [00:00<00:04, 4.56MB/s]


optimizer.bin:   3%|▎         | 1.65M/47.4M [00:00<00:15, 2.91MB/s]



pytorch_lora_weights.safetensors:  32%|███▏      | 7.59M/23.4M [00:00<00:01, 14.8MB/s]


optimizer.bin:   7%|▋         | 3.26M/47.4M [00:01<00:08, 5.50MB/s]



pytorch_lora_weights.safetensors:  67%|██████▋   | 15.7M/23.4M [00:01<00:00, 29.7MB/s]


optimizer.bin:   9%|▉         | 4.42M/47.4M [00:01<00:06, 6.63MB/s]




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


optimizer.bin:  12%|█▏        | 5.57M/47.4M [00:01<00:05, 7.53MB/s]



pytorch_lora_weights.safetensors:  85%|████████▌ | 19.9M/23.4M [00:01<00:00, 27.4MB/s]




pytorch_lora_weights.safetensors:   2%|▏         | 369k/23.4M [00:00<00:07, 3.20MB/s]


optimizer.bin:  14%|█▍        | 6.73M/47.4M [00:01<00:04, 8.27MB/s]




pytorch_lora_weights.safetensors:   7%|▋         | 1.73M/23.4M [00:00<00:02, 8.53MB/s]


optimizer.bin:  17%|█▋        | 7.95M/47.4M [00:01<00:04, 8.89MB/s]




pytorch_lora_weights.safetensors:  25%|██▍       | 5.78M/23.4M [00:00<00:00, 21.3MB/s]
pytorch_lora_weights.safetensors: 100%|██████████| 23.4M/23.4M [00:01<00:00, 14.8MB/s]



optimizer.bin:  19%|█▉        | 9.17M/47.4M [00:01<00:04, 9.38MB/s]




pytorch_lora_weights.safetensors:  65%|██████▍   | 15.2M/23.4M [00:00<00:00, 48.2MB/s]


optimizer.bin:  22%|██▏       | 10.5M/47.4M [00:01<00:03, 10.1MB/s]


optimizer.bin:  26%|██▌       | 12.2M/47.4M [00:01<00:03, 10.4MB/s]




pytorch_lora_weights.safetensors:  86%|████████▋ | 20.2M/23.4M [00:00<00:00, 32.7MB/s]


optimizer.bin:  28%|██▊       | 13.3M/47.4M [00:01<00:03, 10.3MB/s]
pytorch_lora_weights.safetensors: 100%|██████████| 23.4M/23.4M [00:00<00:00, 24.6MB/s]



optimizer.bin:  32%|███▏      | 15.3M/47.4M [00:02<00:03, 10.5MB/s]


optimizer.bin:  35%|███▍      | 16.4M/47.4M [00:02<00:03, 7.80MB/s]


optimizer.bin:  41%|████▏     | 19.7M/47.4M [00:02<00:02, 10.7MB/s]


optimizer.bin:  44%|████▍     | 21.1M/47.4M [00:02<00:02, 11.0MB/s]


optimizer.bin:  47%|████▋     | 22.5M/47.4M [00:02<00:02, 11.3MB/s]


optimizer.bin:  50%|█████     | 23.9M/47.4M [00:02<00:02, 11.6MB/s]


optimizer.bin:  54%|█████▎    | 25.4M/47.4M [00:03<00:01, 11.9MB/s]


optimizer.bin:  59%|█████▊    | 27.8M/47.4M [00:03<00:01, 12.2MB/s]


optimizer.bin:  64%|██████▍   | 30.3M/47.4M [00:03<00:01, 12.4MB/s]


optimizer.bin:  68%|██████▊   | 32.0M/47.4M [00:03<00:01, 8.68MB/s]


optimizer.bin:  76%|███████▌  | 36.0M/47.4M [00:04<00:00, 11.9MB/s]


optimizer.bin:  79%|███████▉  | 37.5M/47.4M [00:04<00:00, 12.2MB/s]


optimizer.bin:  82%|████████▏ | 39.0M/47.4M [00:04<00:00, 12.4MB/s]


optimizer.bin:  86%|████████▌ | 40.6M/47.4M [00:04<00:00, 12.6MB/s]


optimizer.bin:  89%|████████▉ | 42.1M/47.4M [00:04<00:00, 12.8MB/s]


optimizer.bin:  94%|█████████▍| 44.7M/47.4M [00:04<00:00, 13.0MB/s]


optimizer.bin: 100%|█████████▉| 47.3M/47.4M [00:04<00:00, 13.2MB/s]
optimizer.bin: 100%|██████████| 47.4M/47.4M [00:05<00:00, 9.29MB/s]


Upload 6 LFS files:  17%|█▋        | 1/6 [00:05<00:27,  5.42s/it]
Upload 6 LFS files: 100%|██████████| 6/6 [00:05<00:00,  1.11it/s]