uvicorn : INFO:     Will watch for changes in these directories: ['D:\\Desarrollo\\Proyectos_Activos\\epicrisis2026']
En línea: 1 Carácter: 1
+ uvicorn app.main:app --host 0.0.0.0 --port 7000 --reload --log-level  ...
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    + CategoryInfo          : NotSpecified: (INFO:     Will ...epicrisis2026']:String) [], RemoteException
    + FullyQualifiedErrorId : NativeCommandError
 
INFO:     Uvicorn running on http://0.0.0.0:7000 (Press CTRL+C to quit)
INFO:     Started reloader process [29576] using WatchFiles
D:\Desarrollo\Proyectos_Activos\epicrisis2026\app\core\services.py:11: FutureWarning: 

All support for the `google.generativeai` package has ended. It will no longer be receiving 
updates or bug fixes. Please switch to the `google.genai` package as soon as possible.
See README for more details:

https://github.com/google-gemini/deprecated-generative-ai-python/blob/main/README.md

  import google.generativeai as genai
D:\Desarrollo\Proyectos_Activos\epicrisis2026\venv\Lib\site-packages\langchain_core\_api\deprecation.py:25: UserWarning: Core Pydantic V1 
functionality isn't compatible with Python 3.14 or greater.
  from pydantic.v1.fields import FieldInfo as FieldInfoV1
D:\Desarrollo\Proyectos_Activos\epicrisis2026\venv\Lib\site-packages\pydantic\_internal\_config.py:383: UserWarning: Valid config keys have 
changed in V2:
* 'allow_population_by_field_name' has been renamed to 'validate_by_name'
  warnings.warn(message, UserWarning)
D:\Desarrollo\Proyectos_Activos\epicrisis2026\modules\processing\cie10\RANGES_HTML.py:25: LangChainDeprecationWarning: The class 
`HuggingFaceEmbeddings` was deprecated in LangChain 0.2.2 and will be removed in 1.0. An updated version of the class exists in the 
`langchain-huggingface package and should be used instead. To use it run `pip install -U `langchain-huggingface` and import as `from 
`langchain_huggingface import HuggingFaceEmbeddings``.
  self.embeddings = HuggingFaceEmbeddings(model_name=EMBEDDINGS_MODEL)

Loading weights:   0%|          | 0/199 [00:00<?, ?it/s]
Loading weights:   1%|          | 1/199 [00:00<00:00, 13981.01it/s, Materializing param=embeddings.LayerNorm.bias]
Loading weights:   1%|          | 1/199 [00:00<00:00, 3682.44it/s, Materializing param=embeddings.LayerNorm.bias] 
Loading weights:   1%|1         | 2/199 [00:00<00:00, 4373.62it/s, Materializing param=embeddings.LayerNorm.weight]
Loading weights:   1%|1         | 2/199 [00:00<00:00, 3390.71it/s, Materializing param=embeddings.LayerNorm.weight]
Loading weights:   2%|1         | 3/199 [00:00<00:00, 4098.67it/s, Materializing param=embeddings.position_embeddings.weight]
Loading weights:   2%|1         | 3/199 [00:00<00:00, 3803.78it/s, Materializing param=embeddings.position_embeddings.weight]
Loading weights:   2%|2         | 4/199 [00:00<00:00, 4126.22it/s, Materializing param=embeddings.token_type_embeddings.weight]
Loading weights:   2%|2         | 4/199 [00:00<00:00, 3252.03it/s, Materializing param=embeddings.token_type_embeddings.weight]
Loading weights:   3%|2         | 5/199 [00:00<00:00, 2985.27it/s, Materializing param=embeddings.word_embeddings.weight]      
Loading weights:   3%|2         | 5/199 [00:00<00:00, 2515.78it/s, Materializing param=embeddings.word_embeddings.weight]
Loading weights:   3%|3         | 6/199 [00:00<00:00, 2714.76it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.bias]
Loading weights:   3%|3         | 6/199 [00:00<00:00, 2524.91it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.bias]
Loading weights:   4%|3         | 7/199 [00:00<00:00, 2605.16it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.weight]
Loading weights:   4%|3         | 7/199 [00:00<00:00, 2550.17it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.weight]
Loading weights:   4%|4         | 8/199 [00:00<00:00, 2688.23it/s, Materializing param=encoder.layer.0.attention.output.dense.bias]      
Loading weights:   4%|4         | 8/199 [00:00<00:00, 2540.08it/s, Materializing param=encoder.layer.0.attention.output.dense.bias]
Loading weights:   5%|4         | 9/199 [00:00<00:00, 2745.96it/s, Materializing param=encoder.layer.0.attention.output.dense.weight]
Loading weights:   5%|4         | 9/199 [00:00<00:00, 2598.52it/s, Materializing param=encoder.layer.0.attention.output.dense.weight]
Loading weights:   5%|5         | 10/199 [00:00<00:00, 2783.77it/s, Materializing param=encoder.layer.0.attention.self.key.bias]     
Loading weights:   5%|5         | 10/199 [00:00<00:00, 2706.35it/s, Materializing param=encoder.layer.0.attention.self.key.bias]
Loading weights:   6%|5         | 11/199 [00:00<00:00, 2708.07it/s, Materializing param=encoder.layer.0.attention.self.key.weight]
Loading weights:   6%|5         | 11/199 [00:00<00:00, 2596.07it/s, Materializing param=encoder.layer.0.attention.self.key.weight]
Loading weights:   6%|6         | 12/199 [00:00<00:00, 2690.38it/s, Materializing param=encoder.layer.0.attention.self.query.bias]
Loading weights:   6%|6         | 12/199 [00:00<00:00, 2641.80it/s, Materializing param=encoder.layer.0.attention.self.query.bias]
Loading weights:   7%|6         | 13/199 [00:00<00:00, 2735.46it/s, Materializing param=encoder.layer.0.attention.self.query.weight]
Loading weights:   7%|6         | 13/199 [00:00<00:00, 2691.31it/s, Materializing param=encoder.layer.0.attention.self.query.weight]
Loading weights:   7%|7         | 14/199 [00:00<00:00, 2769.69it/s, Materializing param=encoder.layer.0.attention.self.value.bias]  
Loading weights:   7%|7         | 14/199 [00:00<00:00, 2736.78it/s, Materializing param=encoder.layer.0.attention.self.value.bias]
Loading weights:   8%|7         | 15/199 [00:00<00:00, 2832.08it/s, Materializing param=encoder.layer.0.attention.self.value.weight]
Loading weights:   8%|7         | 15/199 [00:00<00:00, 2554.70it/s, Materializing param=encoder.layer.0.attention.self.value.weight]
Loading weights:   8%|8         | 16/199 [00:00<00:00, 2575.27it/s, Materializing param=encoder.layer.0.intermediate.dense.bias]    
Loading weights:   8%|8         | 16/199 [00:00<00:00, 2433.86it/s, Materializing param=encoder.layer.0.intermediate.dense.bias]
Loading weights:   9%|8         | 17/199 [00:00<00:00, 2483.48it/s, Materializing param=encoder.layer.0.intermediate.dense.weight]
Loading weights:   9%|8         | 17/199 [00:00<00:00, 2419.60it/s, Materializing param=encoder.layer.0.intermediate.dense.weight]
Loading weights:   9%|9         | 18/199 [00:00<00:00, 2486.50it/s, Materializing param=encoder.layer.0.output.LayerNorm.bias]    
Loading weights:   9%|9         | 18/199 [00:00<00:00, 2372.87it/s, Materializing param=encoder.layer.0.output.LayerNorm.bias]
Loading weights:  10%|9         | 19/199 [00:00<00:00, 2348.16it/s, Materializing param=encoder.layer.0.output.LayerNorm.weight]
Loading weights:  10%|9         | 19/199 [00:00<00:00, 2328.47it/s, Materializing param=encoder.layer.0.output.LayerNorm.weight]
Loading weights:  10%|#         | 20/199 [00:00<00:00, 2418.65it/s, Materializing param=encoder.layer.0.output.dense.bias]      
Loading weights:  10%|#         | 20/199 [00:00<00:00, 2403.82it/s, Materializing param=encoder.layer.0.output.dense.bias]
Loading weights:  11%|#         | 21/199 [00:00<00:00, 2495.48it/s, Materializing param=encoder.layer.0.output.dense.weight]
Loading weights:  11%|#         | 21/199 [00:00<00:00, 2481.21it/s, Materializing param=encoder.layer.0.output.dense.weight]
Loading weights:  11%|#1        | 22/199 [00:00<00:00, 2571.04it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.bias]
Loading weights:  11%|#1        | 22/199 [00:00<00:00, 2481.84it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.bias]
Loading weights:  12%|#1        | 23/199 [00:00<00:00, 2514.31it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.weight]
Loading weights:  12%|#1        | 23/199 [00:00<00:00, 2453.62it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.weight]
Loading weights:  12%|#2        | 24/199 [00:00<00:00, 2519.98it/s, Materializing param=encoder.layer.1.attention.output.dense.bias]      
Loading weights:  12%|#2        | 24/199 [00:00<00:00, 2504.75it/s, Materializing param=encoder.layer.1.attention.output.dense.bias]
Loading weights:  13%|#2        | 25/199 [00:00<00:00, 2579.90it/s, Materializing param=encoder.layer.1.attention.output.dense.weight]
Loading weights:  13%|#2        | 25/199 [00:00<00:00, 2566.58it/s, Materializing param=encoder.layer.1.attention.output.dense.weight]
Loading weights:  13%|#3        | 26/199 [00:00<00:00, 2638.31it/s, Materializing param=encoder.layer.1.attention.self.key.bias]      
Loading weights:  13%|#3        | 26/199 [00:00<00:00, 2623.96it/s, Materializing param=encoder.layer.1.attention.self.key.bias]
Loading weights:  14%|#3        | 27/199 [00:00<00:00, 2668.64it/s, Materializing param=encoder.layer.1.attention.self.key.weight]
Loading weights:  14%|#3        | 27/199 [00:00<00:00, 2593.17it/s, Materializing param=encoder.layer.1.attention.self.key.weight]
Loading weights:  14%|#4        | 28/199 [00:00<00:00, 2545.09it/s, Materializing param=encoder.layer.1.attention.self.query.bias]
Loading weights:  14%|#4        | 28/199 [00:00<00:00, 2436.32it/s, Materializing param=encoder.layer.1.attention.self.query.bias]
Loading weights:  15%|#4        | 29/199 [00:00<00:00, 2377.17it/s, Materializing param=encoder.layer.1.attention.self.query.weight]
Loading weights:  15%|#4        | 29/199 [00:00<00:00, 2362.44it/s, Materializing param=encoder.layer.1.attention.self.query.weight]
Loading weights:  15%|#5        | 30/199 [00:00<00:00, 2420.68it/s, Materializing param=encoder.layer.1.attention.self.value.bias]  
Loading weights:  15%|#5        | 30/199 [00:00<00:00, 2410.80it/s, Materializing param=encoder.layer.1.attention.self.value.bias]
Loading weights:  16%|#5        | 31/199 [00:00<00:00, 2471.88it/s, Materializing param=encoder.layer.1.attention.self.value.weight]
Loading weights:  16%|#5        | 31/199 [00:00<00:00, 2462.52it/s, Materializing param=encoder.layer.1.attention.self.value.weight]
Loading weights:  16%|#6        | 32/199 [00:00<00:00, 2523.46it/s, Materializing param=encoder.layer.1.intermediate.dense.bias]    
Loading weights:  16%|#6        | 32/199 [00:00<00:00, 2514.10it/s, Materializing param=encoder.layer.1.intermediate.dense.bias]
Loading weights:  17%|#6        | 33/199 [00:00<00:00, 2573.53it/s, Materializing param=encoder.layer.1.intermediate.dense.weight]
Loading weights:  17%|#6        | 33/199 [00:00<00:00, 2564.33it/s, Materializing param=encoder.layer.1.intermediate.dense.weight]
Loading weights:  17%|#7        | 34/199 [00:00<00:00, 2623.32it/s, Materializing param=encoder.layer.1.output.LayerNorm.bias]    
Loading weights:  17%|#7        | 34/199 [00:00<00:00, 2613.85it/s, Materializing param=encoder.layer.1.output.LayerNorm.bias]
Loading weights:  18%|#7        | 35/199 [00:00<00:00, 2671.48it/s, Materializing param=encoder.layer.1.output.LayerNorm.weight]
Loading weights:  18%|#7        | 35/199 [00:00<00:00, 2662.33it/s, Materializing param=encoder.layer.1.output.LayerNorm.weight]
Loading weights:  18%|#8        | 36/199 [00:00<00:00, 2720.29it/s, Materializing param=encoder.layer.1.output.dense.bias]      
Loading weights:  18%|#8        | 36/199 [00:00<00:00, 2711.10it/s, Materializing param=encoder.layer.1.output.dense.bias]
Loading weights:  19%|#8        | 37/199 [00:00<00:00, 2767.92it/s, Materializing param=encoder.layer.1.output.dense.weight]
Loading weights:  19%|#8        | 37/199 [00:00<00:00, 2726.16it/s, Materializing param=encoder.layer.1.output.dense.weight]
Loading weights:  19%|#9        | 38/199 [00:00<00:00, 2782.24it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.bias]
Loading weights:  19%|#9        | 38/199 [00:00<00:00, 2747.38it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.bias]
Loading weights:  20%|#9        | 39/199 [00:00<00:00, 2787.91it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.weight]
Loading weights:  20%|#9        | 39/199 [00:00<00:00, 2775.61it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.weight]
Loading weights:  20%|##        | 40/199 [00:00<00:00, 2807.90it/s, Materializing param=encoder.layer.2.attention.output.dense.bias]      
Loading weights:  20%|##        | 40/199 [00:00<00:00, 2763.91it/s, Materializing param=encoder.layer.2.attention.output.dense.bias]
Loading weights:  21%|##        | 41/199 [00:00<00:00, 2807.98it/s, Materializing param=encoder.layer.2.attention.output.dense.weight]
Loading weights:  21%|##        | 41/199 [00:00<00:00, 2798.07it/s, Materializing param=encoder.layer.2.attention.output.dense.weight]
Loading weights:  21%|##1       | 42/199 [00:00<00:00, 2796.34it/s, Materializing param=encoder.layer.2.attention.self.key.bias]      
Loading weights:  21%|##1       | 42/199 [00:00<00:00, 2784.75it/s, Materializing param=encoder.layer.2.attention.self.key.bias]
Loading weights:  22%|##1       | 43/199 [00:00<00:00, 2829.99it/s, Materializing param=encoder.layer.2.attention.self.key.weight]
Loading weights:  22%|##1       | 43/199 [00:00<00:00, 2819.81it/s, Materializing param=encoder.layer.2.attention.self.key.weight]
Loading weights:  22%|##2       | 44/199 [00:00<00:00, 2865.10it/s, Materializing param=encoder.layer.2.attention.self.query.bias]
Loading weights:  22%|##2       | 44/199 [00:00<00:00, 2855.17it/s, Materializing param=encoder.layer.2.attention.self.query.bias]
Loading weights:  23%|##2       | 45/199 [00:00<00:00, 2401.59it/s, Materializing param=encoder.layer.2.attention.self.query.weight]
Loading weights:  23%|##2       | 45/199 [00:00<00:00, 2383.76it/s, Materializing param=encoder.layer.2.attention.self.query.weight]
Loading weights:  23%|##3       | 46/199 [00:00<00:00, 2417.80it/s, Materializing param=encoder.layer.2.attention.self.value.bias]  
Loading weights:  23%|##3       | 46/199 [00:00<00:00, 2409.89it/s, Materializing param=encoder.layer.2.attention.self.value.bias]
Loading weights:  24%|##3       | 47/199 [00:00<00:00, 2410.31it/s, Materializing param=encoder.layer.2.attention.self.value.weight]
Loading weights:  24%|##3       | 47/199 [00:00<00:00, 2383.24it/s, Materializing param=encoder.layer.2.attention.self.value.weight]
Loading weights:  24%|##4       | 48/199 [00:00<00:00, 2412.40it/s, Materializing param=encoder.layer.2.intermediate.dense.bias]    
Loading weights:  24%|##4       | 48/199 [00:00<00:00, 2404.27it/s, Materializing param=encoder.layer.2.intermediate.dense.bias]
Loading weights:  25%|##4       | 49/199 [00:00<00:00, 2433.87it/s, Materializing param=encoder.layer.2.intermediate.dense.weight]
Loading weights:  25%|##4       | 49/199 [00:00<00:00, 2426.57it/s, Materializing param=encoder.layer.2.intermediate.dense.weight]
Loading weights:  25%|##5       | 50/199 [00:00<00:00, 2446.77it/s, Materializing param=encoder.layer.2.output.LayerNorm.bias]    
Loading weights:  25%|##5       | 50/199 [00:00<00:00, 2435.43it/s, Materializing param=encoder.layer.2.output.LayerNorm.bias]
Loading weights:  26%|##5       | 51/199 [00:00<00:00, 2438.55it/s, Materializing param=encoder.layer.2.output.LayerNorm.weight]
Loading weights:  26%|##5       | 51/199 [00:00<00:00, 2431.54it/s, Materializing param=encoder.layer.2.output.LayerNorm.weight]
Loading weights:  26%|##6       | 52/199 [00:00<00:00, 2458.53it/s, Materializing param=encoder.layer.2.output.dense.bias]      
Loading weights:  26%|##6       | 52/199 [00:00<00:00, 2448.93it/s, Materializing param=encoder.layer.2.output.dense.bias]
Loading weights:  27%|##6       | 53/199 [00:00<00:00, 2427.15it/s, Materializing param=encoder.layer.2.output.dense.weight]
Loading weights:  27%|##6       | 53/199 [00:00<00:00, 2405.33it/s, Materializing param=encoder.layer.2.output.dense.weight]
Loading weights:  27%|##7       | 54/199 [00:00<00:00, 2422.51it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.bias]
Loading weights:  27%|##7       | 54/199 [00:00<00:00, 2416.23it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.bias]
Loading weights:  28%|##7       | 55/199 [00:00<00:00, 2449.11it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.weight]
Loading weights:  28%|##7       | 55/199 [00:00<00:00, 2421.53it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.weight]
Loading weights:  28%|##8       | 56/199 [00:00<00:00, 2420.48it/s, Materializing param=encoder.layer.3.attention.output.dense.bias]      
Loading weights:  28%|##8       | 56/199 [00:00<00:00, 2413.57it/s, Materializing param=encoder.layer.3.attention.output.dense.bias]
Loading weights:  29%|##8       | 57/199 [00:00<00:00, 2424.45it/s, Materializing param=encoder.layer.3.attention.output.dense.weight]
Loading weights:  29%|##8       | 57/199 [00:00<00:00, 2400.45it/s, Materializing param=encoder.layer.3.attention.output.dense.weight]
Loading weights:  29%|##9       | 58/199 [00:00<00:00, 2423.00it/s, Materializing param=encoder.layer.3.attention.self.key.bias]      
Loading weights:  29%|##9       | 58/199 [00:00<00:00, 2413.13it/s, Materializing param=encoder.layer.3.attention.self.key.bias]
Loading weights:  30%|##9       | 59/199 [00:00<00:00, 2414.97it/s, Materializing param=encoder.layer.3.attention.self.key.weight]
Loading weights:  30%|##9       | 59/199 [00:00<00:00, 2408.69it/s, Materializing param=encoder.layer.3.attention.self.key.weight]
Loading weights:  30%|###       | 60/199 [00:00<00:00, 2438.50it/s, Materializing param=encoder.layer.3.attention.self.query.bias]
Loading weights:  30%|###       | 60/199 [00:00<00:00, 2433.10it/s, Materializing param=encoder.layer.3.attention.self.query.bias]
Loading weights:  31%|###       | 61/199 [00:00<00:00, 2462.96it/s, Materializing param=encoder.layer.3.attention.self.query.weight]
Loading weights:  31%|###       | 61/199 [00:00<00:00, 2457.78it/s, Materializing param=encoder.layer.3.attention.self.query.weight]
Loading weights:  31%|###1      | 62/199 [00:00<00:00, 2487.87it/s, Materializing param=encoder.layer.3.attention.self.value.bias]  
Loading weights:  31%|###1      | 62/199 [00:00<00:00, 2482.74it/s, Materializing param=encoder.layer.3.attention.self.value.bias]
Loading weights:  32%|###1      | 63/199 [00:00<00:00, 2504.49it/s, Materializing param=encoder.layer.3.attention.self.value.weight]
Loading weights:  32%|###1      | 63/199 [00:00<00:00, 2486.09it/s, Materializing param=encoder.layer.3.attention.self.value.weight]
Loading weights:  32%|###2      | 64/199 [00:00<00:00, 2470.85it/s, Materializing param=encoder.layer.3.intermediate.dense.bias]    
Loading weights:  32%|###2      | 64/199 [00:00<00:00, 2464.32it/s, Materializing param=encoder.layer.3.intermediate.dense.bias]
Loading weights:  33%|###2      | 65/199 [00:00<00:00, 2490.22it/s, Materializing param=encoder.layer.3.intermediate.dense.weight]
Loading weights:  33%|###2      | 65/199 [00:00<00:00, 2484.98it/s, Materializing param=encoder.layer.3.intermediate.dense.weight]
Loading weights:  33%|###3      | 66/199 [00:00<00:00, 2494.63it/s, Materializing param=encoder.layer.3.output.LayerNorm.bias]    
Loading weights:  33%|###3      | 66/199 [00:00<00:00, 2488.80it/s, Materializing param=encoder.layer.3.output.LayerNorm.bias]
Loading weights:  34%|###3      | 67/199 [00:00<00:00, 2516.24it/s, Materializing param=encoder.layer.3.output.LayerNorm.weight]
Loading weights:  34%|###3      | 67/199 [00:00<00:00, 2511.42it/s, Materializing param=encoder.layer.3.output.LayerNorm.weight]
Loading weights:  34%|###4      | 68/199 [00:00<00:00, 2539.42it/s, Materializing param=encoder.layer.3.output.dense.bias]      
Loading weights:  34%|###4      | 68/199 [00:00<00:00, 2534.75it/s, Materializing param=encoder.layer.3.output.dense.bias]
Loading weights:  35%|###4      | 69/199 [00:00<00:00, 2562.98it/s, Materializing param=encoder.layer.3.output.dense.weight]
Loading weights:  35%|###4      | 69/199 [00:00<00:00, 2549.77it/s, Materializing param=encoder.layer.3.output.dense.weight]
Loading weights:  35%|###5      | 70/199 [00:00<00:00, 2567.05it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.bias]
Loading weights:  35%|###5      | 70/199 [00:00<00:00, 2560.71it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.bias]
Loading weights:  36%|###5      | 71/199 [00:00<00:00, 2572.64it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.weight]
Loading weights:  36%|###5      | 71/199 [00:00<00:00, 2547.05it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.weight]
Loading weights:  36%|###6      | 72/199 [00:00<00:00, 2564.91it/s, Materializing param=encoder.layer.4.attention.output.dense.bias]      
Loading weights:  36%|###6      | 72/199 [00:00<00:00, 2558.17it/s, Materializing param=encoder.layer.4.attention.output.dense.bias]
Loading weights:  37%|###6      | 73/199 [00:00<00:00, 2582.02it/s, Materializing param=encoder.layer.4.attention.output.dense.weight]
Loading weights:  37%|###6      | 73/199 [00:00<00:00, 2565.86it/s, Materializing param=encoder.layer.4.attention.output.dense.weight]
Loading weights:  37%|###7      | 74/199 [00:00<00:00, 2568.10it/s, Materializing param=encoder.layer.4.attention.self.key.bias]      
Loading weights:  37%|###7      | 74/199 [00:00<00:00, 2551.09it/s, Materializing param=encoder.layer.4.attention.self.key.bias]
Loading weights:  38%|###7      | 75/199 [00:00<00:00, 2545.36it/s, Materializing param=encoder.layer.4.attention.self.key.weight]
Loading weights:  38%|###7      | 75/199 [00:00<00:00, 2537.00it/s, Materializing param=encoder.layer.4.attention.self.key.weight]
Loading weights:  38%|###8      | 76/199 [00:00<00:00, 2547.49it/s, Materializing param=encoder.layer.4.attention.self.query.bias]
Loading weights:  38%|###8      | 76/199 [00:00<00:00, 2540.60it/s, Materializing param=encoder.layer.4.attention.self.query.bias]
Loading weights:  39%|###8      | 77/199 [00:00<00:00, 2560.44it/s, Materializing param=encoder.layer.4.attention.self.query.weight]
Loading weights:  39%|###8      | 77/199 [00:00<00:00, 2553.48it/s, Materializing param=encoder.layer.4.attention.self.query.weight]
Loading weights:  39%|###9      | 78/199 [00:00<00:00, 2573.98it/s, Materializing param=encoder.layer.4.attention.self.value.bias]  
Loading weights:  39%|###9      | 78/199 [00:00<00:00, 2551.66it/s, Materializing param=encoder.layer.4.attention.self.value.bias]
Loading weights:  40%|###9      | 79/199 [00:00<00:00, 2553.76it/s, Materializing param=encoder.layer.4.attention.self.value.weight]
Loading weights:  40%|###9      | 79/199 [00:00<00:00, 2545.48it/s, Materializing param=encoder.layer.4.attention.self.value.weight]
Loading weights:  40%|####      | 80/199 [00:00<00:00, 2555.44it/s, Materializing param=encoder.layer.4.intermediate.dense.bias]    
Loading weights:  40%|####      | 80/199 [00:00<00:00, 2550.14it/s, Materializing param=encoder.layer.4.intermediate.dense.bias]
Loading weights:  41%|####      | 81/199 [00:00<00:00, 2572.88it/s, Materializing param=encoder.layer.4.intermediate.dense.weight]
Loading weights:  41%|####      | 81/199 [00:00<00:00, 2546.10it/s, Materializing param=encoder.layer.4.intermediate.dense.weight]
Loading weights:  41%|####1     | 82/199 [00:00<00:00, 2566.89it/s, Materializing param=encoder.layer.4.output.LayerNorm.bias]    
Loading weights:  41%|####1     | 82/199 [00:00<00:00, 2562.27it/s, Materializing param=encoder.layer.4.output.LayerNorm.bias]
Loading weights:  42%|####1     | 83/199 [00:00<00:00, 2584.54it/s, Materializing param=encoder.layer.4.output.LayerNorm.weight]
Loading weights:  42%|####1     | 83/199 [00:00<00:00, 2580.38it/s, Materializing param=encoder.layer.4.output.LayerNorm.weight]
Loading weights:  42%|####2     | 84/199 [00:00<00:00, 2591.02it/s, Materializing param=encoder.layer.4.output.dense.bias]      
Loading weights:  42%|####2     | 84/199 [00:00<00:00, 2582.40it/s, Materializing param=encoder.layer.4.output.dense.bias]
Loading weights:  43%|####2     | 85/199 [00:00<00:00, 2589.32it/s, Materializing param=encoder.layer.4.output.dense.weight]
Loading weights:  43%|####2     | 85/199 [00:00<00:00, 2584.20it/s, Materializing param=encoder.layer.4.output.dense.weight]
Loading weights:  43%|####3     | 86/199 [00:00<00:00, 2592.99it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.bias]
Loading weights:  43%|####3     | 86/199 [00:00<00:00, 2586.44it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.bias]
Loading weights:  44%|####3     | 87/199 [00:00<00:00, 2583.76it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.weight]
Loading weights:  44%|####3     | 87/199 [00:00<00:00, 2574.46it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.weight]
Loading weights:  44%|####4     | 88/199 [00:00<00:00, 2586.97it/s, Materializing param=encoder.layer.5.attention.output.dense.bias]      
Loading weights:  44%|####4     | 88/199 [00:00<00:00, 2580.79it/s, Materializing param=encoder.layer.5.attention.output.dense.bias]
Loading weights:  45%|####4     | 89/199 [00:00<00:00, 2598.45it/s, Materializing param=encoder.layer.5.attention.output.dense.weight]
Loading weights:  45%|####4     | 89/199 [00:00<00:00, 2593.12it/s, Materializing param=encoder.layer.5.attention.output.dense.weight]
Loading weights:  45%|####5     | 90/199 [00:00<00:00, 2611.19it/s, Materializing param=encoder.layer.5.attention.self.key.bias]      
Loading weights:  45%|####5     | 90/199 [00:00<00:00, 2605.97it/s, Materializing param=encoder.layer.5.attention.self.key.bias]
Loading weights:  46%|####5     | 91/199 [00:00<00:00, 2623.73it/s, Materializing param=encoder.layer.5.attention.self.key.weight]
Loading weights:  46%|####5     | 91/199 [00:00<00:00, 2618.78it/s, Materializing param=encoder.layer.5.attention.self.key.weight]
Loading weights:  46%|####6     | 92/199 [00:00<00:00, 2637.21it/s, Materializing param=encoder.layer.5.attention.self.query.bias]
Loading weights:  46%|####6     | 92/199 [00:00<00:00, 2631.74it/s, Materializing param=encoder.layer.5.attention.self.query.bias]
Loading weights:  47%|####6     | 93/199 [00:00<00:00, 2650.06it/s, Materializing param=encoder.layer.5.attention.self.query.weight]
Loading weights:  47%|####6     | 93/199 [00:00<00:00, 2644.94it/s, Materializing param=encoder.layer.5.attention.self.query.weight]
Loading weights:  47%|####7     | 94/199 [00:00<00:00, 2662.89it/s, Materializing param=encoder.layer.5.attention.self.value.bias]  
Loading weights:  47%|####7     | 94/199 [00:00<00:00, 2657.92it/s, Materializing param=encoder.layer.5.attention.self.value.bias]
Loading weights:  48%|####7     | 95/199 [00:00<00:00, 2675.82it/s, Materializing param=encoder.layer.5.attention.self.value.weight]
Loading weights:  48%|####7     | 95/199 [00:00<00:00, 2666.54it/s, Materializing param=encoder.layer.5.attention.self.value.weight]
Loading weights:  48%|####8     | 96/199 [00:00<00:00, 2680.37it/s, Materializing param=encoder.layer.5.intermediate.dense.bias]    
Loading weights:  48%|####8     | 96/199 [00:00<00:00, 2675.95it/s, Materializing param=encoder.layer.5.intermediate.dense.bias]
Loading weights:  49%|####8     | 97/199 [00:00<00:00, 2671.69it/s, Materializing param=encoder.layer.5.intermediate.dense.weight]
Loading weights:  49%|####8     | 97/199 [00:00<00:00, 2667.10it/s, Materializing param=encoder.layer.5.intermediate.dense.weight]
Loading weights:  49%|####9     | 98/199 [00:00<00:00, 2686.65it/s, Materializing param=encoder.layer.5.output.LayerNorm.bias]    
Loading weights:  49%|####9     | 98/199 [00:00<00:00, 2683.13it/s, Materializing param=encoder.layer.5.output.LayerNorm.bias]
Loading weights:  50%|####9     | 99/199 [00:00<00:00, 2700.06it/s, Materializing param=encoder.layer.5.output.LayerNorm.weight]
Loading weights:  50%|####9     | 99/199 [00:00<00:00, 2695.55it/s, Materializing param=encoder.layer.5.output.LayerNorm.weight]
Loading weights:  50%|#####     | 100/199 [00:00<00:00, 2700.74it/s, Materializing param=encoder.layer.5.output.dense.bias]     
Loading weights:  50%|#####     | 100/199 [00:00<00:00, 2696.45it/s, Materializing param=encoder.layer.5.output.dense.bias]
Loading weights:  51%|#####     | 101/199 [00:00<00:00, 2703.21it/s, Materializing param=encoder.layer.5.output.dense.weight]
Loading weights:  51%|#####     | 101/199 [00:00<00:00, 2695.74it/s, Materializing param=encoder.layer.5.output.dense.weight]
Loading weights:  51%|#####1    | 102/199 [00:00<00:00, 2704.51it/s, Materializing param=encoder.layer.6.attention.output.LayerNorm.bias]
Loading weights:  51%|#####1    | 102/199 [00:00<00:00, 2700.32it/s, Materializing param=encoder.layer.6.attention.output.LayerNorm.bias]
Loading weights:  52%|#####1    | 103/199 [00:00<00:00, 2706.19it/s, Materializing param=encoder.layer.6.attention.output.LayerNorm.weight]
Loading weights:  52%|#####1    | 103/199 [00:00<00:00, 2701.94it/s, Materializing param=encoder.layer.6.attention.output.LayerNorm.weight]
Loading weights:  52%|#####2    | 104/199 [00:00<00:00, 2720.65it/s, Materializing param=encoder.layer.6.attention.output.dense.bias]      
Loading weights:  52%|#####2    | 104/199 [00:00<00:00, 2717.18it/s, Materializing param=encoder.layer.6.attention.output.dense.bias]
Loading weights:  53%|#####2    | 105/199 [00:00<00:00, 2735.06it/s, Materializing param=encoder.layer.6.attention.output.dense.weight]
Loading weights:  53%|#####2    | 105/199 [00:00<00:00, 2730.07it/s, Materializing param=encoder.layer.6.attention.output.dense.weight]
Loading weights:  53%|#####3    | 106/199 [00:00<00:00, 2746.73it/s, Materializing param=encoder.layer.6.attention.self.key.bias]      
Loading weights:  53%|#####3    | 106/199 [00:00<00:00, 2741.81it/s, Materializing param=encoder.layer.6.attention.self.key.bias]
Loading weights:  54%|#####3    | 107/199 [00:00<00:00, 2755.94it/s, Materializing param=encoder.layer.6.attention.self.key.weight]
Loading weights:  54%|#####3    | 107/199 [00:00<00:00, 2751.48it/s, Materializing param=encoder.layer.6.attention.self.key.weight]
Loading weights:  54%|#####4    | 108/199 [00:00<00:00, 2769.50it/s, Materializing param=encoder.layer.6.attention.self.query.bias]
Loading weights:  54%|#####4    | 108/199 [00:00<00:00, 2765.95it/s, Materializing param=encoder.layer.6.attention.self.query.bias]
Loading weights:  55%|#####4    | 109/199 [00:00<00:00, 2784.60it/s, Materializing param=encoder.layer.6.attention.self.query.weight]
Loading weights:  55%|#####4    | 109/199 [00:00<00:00, 2781.23it/s, Materializing param=encoder.layer.6.attention.self.query.weight]
Loading weights:  55%|#####5    | 110/199 [00:00<00:00, 2800.04it/s, Materializing param=encoder.layer.6.attention.self.value.bias]  
Loading weights:  55%|#####5    | 110/199 [00:00<00:00, 2796.05it/s, Materializing param=encoder.layer.6.attention.self.value.bias]
Loading weights:  56%|#####5    | 111/199 [00:00<00:00, 2812.04it/s, Materializing param=encoder.layer.6.attention.self.value.weight]
Loading weights:  56%|#####5    | 111/199 [00:00<00:00, 2806.96it/s, Materializing param=encoder.layer.6.attention.self.value.weight]
Loading weights:  56%|#####6    | 112/199 [00:00<00:00, 2810.20it/s, Materializing param=encoder.layer.6.intermediate.dense.bias]    
Loading weights:  56%|#####6    | 112/199 [00:00<00:00, 2280.10it/s, Materializing param=encoder.layer.6.intermediate.dense.bias]
Loading weights:  57%|#####6    | 113/199 [00:00<00:00, 2280.01it/s, Materializing param=encoder.layer.6.intermediate.dense.weight]
Loading weights:  57%|#####6    | 113/199 [00:00<00:00, 2275.53it/s, Materializing param=encoder.layer.6.intermediate.dense.weight]
Loading weights:  57%|#####7    | 114/199 [00:00<00:00, 2287.66it/s, Materializing param=encoder.layer.6.output.LayerNorm.bias]    
Loading weights:  57%|#####7    | 114/199 [00:00<00:00, 2284.01it/s, Materializing param=encoder.layer.6.output.LayerNorm.bias]
Loading weights:  58%|#####7    | 115/199 [00:00<00:00, 2296.98it/s, Materializing param=encoder.layer.6.output.LayerNorm.weight]
Loading weights:  58%|#####7    | 115/199 [00:00<00:00, 2293.52it/s, Materializing param=encoder.layer.6.output.LayerNorm.weight]
Loading weights:  58%|#####8    | 116/199 [00:00<00:00, 2306.73it/s, Materializing param=encoder.layer.6.output.dense.bias]      
Loading weights:  58%|#####8    | 116/199 [00:00<00:00, 2303.69it/s, Materializing param=encoder.layer.6.output.dense.bias]
Loading weights:  59%|#####8    | 117/199 [00:00<00:00, 2317.61it/s, Materializing param=encoder.layer.6.output.dense.weight]
Loading weights:  59%|#####8    | 117/199 [00:00<00:00, 2314.12it/s, Materializing param=encoder.layer.6.output.dense.weight]
Loading weights:  59%|#####9    | 118/199 [00:00<00:00, 2327.34it/s, Materializing param=encoder.layer.7.attention.output.LayerNorm.bias]
Loading weights:  59%|#####9    | 118/199 [00:00<00:00, 2322.94it/s, Materializing param=encoder.layer.7.attention.output.LayerNorm.bias]
Loading weights:  60%|#####9    | 119/199 [00:00<00:00, 2335.48it/s, Materializing param=encoder.layer.7.attention.output.LayerNorm.weight]
Loading weights:  60%|#####9    | 119/199 [00:00<00:00, 2332.09it/s, Materializing param=encoder.layer.7.attention.output.LayerNorm.weight]
Loading weights:  60%|######    | 120/199 [00:00<00:00, 2345.17it/s, Materializing param=encoder.layer.7.attention.output.dense.bias]      
Loading weights:  60%|######    | 120/199 [00:00<00:00, 2341.78it/s, Materializing param=encoder.layer.7.attention.output.dense.bias]
Loading weights:  61%|######    | 121/199 [00:00<00:00, 2354.50it/s, Materializing param=encoder.layer.7.attention.output.dense.weight]
Loading weights:  61%|######    | 121/199 [00:00<00:00, 2351.03it/s, Materializing param=encoder.layer.7.attention.output.dense.weight]
Loading weights:  61%|######1   | 122/199 [00:00<00:00, 2364.23it/s, Materializing param=encoder.layer.7.attention.self.key.bias]      
Loading weights:  61%|######1   | 122/199 [00:00<00:00, 2361.90it/s, Materializing param=encoder.layer.7.attention.self.key.bias]
Loading weights:  62%|######1   | 123/199 [00:00<00:00, 2377.21it/s, Materializing param=encoder.layer.7.attention.self.key.weight]
Loading weights:  62%|######1   | 123/199 [00:00<00:00, 2375.29it/s, Materializing param=encoder.layer.7.attention.self.key.weight]
Loading weights:  62%|######2   | 124/199 [00:00<00:00, 2391.06it/s, Materializing param=encoder.layer.7.attention.self.query.bias]
Loading weights:  62%|######2   | 124/199 [00:00<00:00, 2388.47it/s, Materializing param=encoder.layer.7.attention.self.query.bias]
Loading weights:  63%|######2   | 125/199 [00:00<00:00, 2402.91it/s, Materializing param=encoder.layer.7.attention.self.query.weight]
Loading weights:  63%|######2   | 125/199 [00:00<00:00, 2400.58it/s, Materializing param=encoder.layer.7.attention.self.query.weight]
Loading weights:  63%|######3   | 126/199 [00:00<00:00, 2415.67it/s, Materializing param=encoder.layer.7.attention.self.value.bias]  
Loading weights:  63%|######3   | 126/199 [00:00<00:00, 2413.46it/s, Materializing param=encoder.layer.7.attention.self.value.bias]
Loading weights:  64%|######3   | 127/199 [00:00<00:00, 2428.70it/s, Materializing param=encoder.layer.7.attention.self.value.weight]
Loading weights:  64%|######3   | 127/199 [00:00<00:00, 2426.58it/s, Materializing param=encoder.layer.7.attention.self.value.weight]
Loading weights:  64%|######4   | 128/199 [00:00<00:00, 1889.03it/s, Materializing param=encoder.layer.7.intermediate.dense.bias]    
Loading weights:  64%|######4   | 128/199 [00:00<00:00, 1883.33it/s, Materializing param=encoder.layer.7.intermediate.dense.bias]
Loading weights:  65%|######4   | 129/199 [00:00<00:00, 1891.02it/s, Materializing param=encoder.layer.7.intermediate.dense.weight]
Loading weights:  65%|######4   | 129/199 [00:00<00:00, 1887.12it/s, Materializing param=encoder.layer.7.intermediate.dense.weight]
Loading weights:  65%|######5   | 130/199 [00:00<00:00, 1897.05it/s, Materializing param=encoder.layer.7.output.LayerNorm.bias]    
Loading weights:  65%|######5   | 130/199 [00:00<00:00, 1894.63it/s, Materializing param=encoder.layer.7.output.LayerNorm.bias]
Loading weights:  66%|######5   | 131/199 [00:00<00:00, 1904.79it/s, Materializing param=encoder.layer.7.output.LayerNorm.weight]
Loading weights:  66%|######5   | 131/199 [00:00<00:00, 1902.35it/s, Materializing param=encoder.layer.7.output.LayerNorm.weight]
Loading weights:  66%|######6   | 132/199 [00:00<00:00, 1912.64it/s, Materializing param=encoder.layer.7.output.dense.bias]      
Loading weights:  66%|######6   | 132/199 [00:00<00:00, 1910.28it/s, Materializing param=encoder.layer.7.output.dense.bias]
Loading weights:  67%|######6   | 133/199 [00:00<00:00, 1919.42it/s, Materializing param=encoder.layer.7.output.dense.weight]
Loading weights:  67%|######6   | 133/199 [00:00<00:00, 1917.19it/s, Materializing param=encoder.layer.7.output.dense.weight]
Loading weights:  67%|######7   | 134/199 [00:00<00:00, 1927.86it/s, Materializing param=encoder.layer.8.attention.output.LayerNorm.bias]
Loading weights:  67%|######7   | 134/199 [00:00<00:00, 1925.93it/s, Materializing param=encoder.layer.8.attention.output.LayerNorm.bias]
Loading weights:  68%|######7   | 135/199 [00:00<00:00, 1936.84it/s, Materializing param=encoder.layer.8.attention.output.LayerNorm.weight]
Loading weights:  68%|######7   | 135/199 [00:00<00:00, 1935.03it/s, Materializing param=encoder.layer.8.attention.output.LayerNorm.weight]
Loading weights:  68%|######8   | 136/199 [00:00<00:00, 1946.19it/s, Materializing param=encoder.layer.8.attention.output.dense.bias]      
Loading weights:  68%|######8   | 136/199 [00:00<00:00, 1944.42it/s, Materializing param=encoder.layer.8.attention.output.dense.bias]
Loading weights:  69%|######8   | 137/199 [00:00<00:00, 1955.58it/s, Materializing param=encoder.layer.8.attention.output.dense.weight]
Loading weights:  69%|######8   | 137/199 [00:00<00:00, 1953.80it/s, Materializing param=encoder.layer.8.attention.output.dense.weight]
Loading weights:  69%|######9   | 138/199 [00:00<00:00, 1964.99it/s, Materializing param=encoder.layer.8.attention.self.key.bias]      
Loading weights:  69%|######9   | 138/199 [00:00<00:00, 1963.26it/s, Materializing param=encoder.layer.8.attention.self.key.bias]
Loading weights:  70%|######9   | 139/199 [00:00<00:00, 1974.36it/s, Materializing param=encoder.layer.8.attention.self.key.weight]
Loading weights:  70%|######9   | 139/199 [00:00<00:00, 1973.15it/s, Materializing param=encoder.layer.8.attention.self.key.weight]
Loading weights:  70%|#######   | 140/199 [00:00<00:00, 1985.21it/s, Materializing param=encoder.layer.8.attention.self.query.bias]
Loading weights:  70%|#######   | 140/199 [00:00<00:00, 1984.10it/s, Materializing param=encoder.layer.8.attention.self.query.bias]
Loading weights:  71%|#######   | 141/199 [00:00<00:00, 1996.16it/s, Materializing param=encoder.layer.8.attention.self.query.weight]
Loading weights:  71%|#######   | 141/199 [00:00<00:00, 1995.04it/s, Materializing param=encoder.layer.8.attention.self.query.weight]
Loading weights:  71%|#######1  | 142/199 [00:00<00:00, 2007.12it/s, Materializing param=encoder.layer.8.attention.self.value.bias]  
Loading weights:  71%|#######1  | 142/199 [00:00<00:00, 2006.00it/s, Materializing param=encoder.layer.8.attention.self.value.bias]
Loading weights:  72%|#######1  | 143/199 [00:00<00:00, 2018.03it/s, Materializing param=encoder.layer.8.attention.self.value.weight]
Loading weights:  72%|#######1  | 143/199 [00:00<00:00, 1664.13it/s, Materializing param=encoder.layer.8.attention.self.value.weight]
Loading weights:  72%|#######2  | 144/199 [00:00<00:00, 1670.06it/s, Materializing param=encoder.layer.8.intermediate.dense.bias]    
Loading weights:  72%|#######2  | 144/199 [00:00<00:00, 1668.78it/s, Materializing param=encoder.layer.8.intermediate.dense.bias]
Loading weights:  73%|#######2  | 145/199 [00:00<00:00, 1678.19it/s, Materializing param=encoder.layer.8.intermediate.dense.weight]
Loading weights:  73%|#######2  | 145/199 [00:00<00:00, 1677.29it/s, Materializing param=encoder.layer.8.intermediate.dense.weight]
Loading weights:  73%|#######3  | 146/199 [00:00<00:00, 1687.26it/s, Materializing param=encoder.layer.8.output.LayerNorm.bias]    
Loading weights:  73%|#######3  | 146/199 [00:00<00:00, 1686.39it/s, Materializing param=encoder.layer.8.output.LayerNorm.bias]
Loading weights:  74%|#######3  | 147/199 [00:00<00:00, 1696.30it/s, Materializing param=encoder.layer.8.output.LayerNorm.weight]
Loading weights:  74%|#######3  | 147/199 [00:00<00:00, 1695.46it/s, Materializing param=encoder.layer.8.output.LayerNorm.weight]
Loading weights:  74%|#######4  | 148/199 [00:00<00:00, 1705.47it/s, Materializing param=encoder.layer.8.output.dense.bias]      
Loading weights:  74%|#######4  | 148/199 [00:00<00:00, 1704.64it/s, Materializing param=encoder.layer.8.output.dense.bias]
Loading weights:  75%|#######4  | 149/199 [00:00<00:00, 1714.68it/s, Materializing param=encoder.layer.8.output.dense.weight]
Loading weights:  75%|#######4  | 149/199 [00:00<00:00, 1713.83it/s, Materializing param=encoder.layer.8.output.dense.weight]
Loading weights:  75%|#######5  | 150/199 [00:00<00:00, 1723.84it/s, Materializing param=encoder.layer.9.attention.output.LayerNorm.bias]
Loading weights:  75%|#######5  | 150/199 [00:00<00:00, 1722.50it/s, Materializing param=encoder.layer.9.attention.output.LayerNorm.bias]
Loading weights:  76%|#######5  | 151/199 [00:00<00:00, 1732.33it/s, Materializing param=encoder.layer.9.attention.output.LayerNorm.weight]
Loading weights:  76%|#######5  | 151/199 [00:00<00:00, 1731.48it/s, Materializing param=encoder.layer.9.attention.output.LayerNorm.weight]
Loading weights:  76%|#######6  | 152/199 [00:00<00:00, 1741.37it/s, Materializing param=encoder.layer.9.attention.output.dense.bias]      
Loading weights:  76%|#######6  | 152/199 [00:00<00:00, 1740.54it/s, Materializing param=encoder.layer.9.attention.output.dense.bias]
Loading weights:  77%|#######6  | 153/199 [00:00<00:00, 1750.46it/s, Materializing param=encoder.layer.9.attention.output.dense.weight]
Loading weights:  77%|#######6  | 153/199 [00:00<00:00, 1749.60it/s, Materializing param=encoder.layer.9.attention.output.dense.weight]
Loading weights:  77%|#######7  | 154/199 [00:00<00:00, 1759.59it/s, Materializing param=encoder.layer.9.attention.self.key.bias]      
Loading weights:  77%|#######7  | 154/199 [00:00<00:00, 1758.82it/s, Materializing param=encoder.layer.9.attention.self.key.bias]
Loading weights:  78%|#######7  | 155/199 [00:00<00:00, 1768.49it/s, Materializing param=encoder.layer.9.attention.self.key.weight]
Loading weights:  78%|#######7  | 155/199 [00:00<00:00, 1767.66it/s, Materializing param=encoder.layer.9.attention.self.key.weight]
Loading weights:  78%|#######8  | 156/199 [00:00<00:00, 1777.55it/s, Materializing param=encoder.layer.9.attention.self.query.bias]
Loading weights:  78%|#######8  | 156/199 [00:00<00:00, 1776.76it/s, Materializing param=encoder.layer.9.attention.self.query.bias]
Loading weights:  79%|#######8  | 157/199 [00:00<00:00, 1786.66it/s, Materializing param=encoder.layer.9.attention.self.query.weight]
Loading weights:  79%|#######8  | 157/199 [00:00<00:00, 1785.84it/s, Materializing param=encoder.layer.9.attention.self.query.weight]
Loading weights:  79%|#######9  | 158/199 [00:00<00:00, 1795.66it/s, Materializing param=encoder.layer.9.attention.self.value.bias]  
Loading weights:  79%|#######9  | 158/199 [00:00<00:00, 1794.84it/s, Materializing param=encoder.layer.9.attention.self.value.bias]
Loading weights:  80%|#######9  | 159/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.attention.self.value.bias]
Loading weights:  80%|#######9  | 159/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.attention.self.value.weight]
Loading weights:  80%|#######9  | 159/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.attention.self.value.weight]
Loading weights:  80%|########  | 160/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.intermediate.dense.bias]    
Loading weights:  80%|########  | 160/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.intermediate.dense.bias]
Loading weights:  81%|########  | 161/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.intermediate.dense.weight]
Loading weights:  81%|########  | 161/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.intermediate.dense.weight]
Loading weights:  81%|########1 | 162/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.output.LayerNorm.bias]    
Loading weights:  81%|########1 | 162/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.output.LayerNorm.bias]
Loading weights:  82%|########1 | 163/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.output.LayerNorm.weight]
Loading weights:  82%|########1 | 163/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.output.LayerNorm.weight]
Loading weights:  82%|########2 | 164/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.output.dense.bias]      
Loading weights:  82%|########2 | 164/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.output.dense.bias]
Loading weights:  83%|########2 | 165/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.output.dense.weight]
Loading weights:  83%|########2 | 165/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.9.output.dense.weight]
Loading weights:  83%|########3 | 166/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.output.LayerNorm.bias]
Loading weights:  83%|########3 | 166/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.output.LayerNorm.bias]
Loading weights:  84%|########3 | 167/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.output.LayerNorm.weight]
Loading weights:  84%|########3 | 167/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.output.LayerNorm.weight]
Loading weights:  84%|########4 | 168/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.output.dense.bias]      
Loading weights:  84%|########4 | 168/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.output.dense.bias]
Loading weights:  85%|########4 | 169/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.output.dense.weight]
Loading weights:  85%|########4 | 169/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.output.dense.weight]
Loading weights:  85%|########5 | 170/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.self.key.bias]      
Loading weights:  85%|########5 | 170/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.self.key.bias]
Loading weights:  86%|########5 | 171/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.self.key.weight]
Loading weights:  86%|########5 | 171/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.self.key.weight]
Loading weights:  86%|########6 | 172/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.self.query.bias]
Loading weights:  86%|########6 | 172/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.self.query.bias]
Loading weights:  87%|########6 | 173/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.self.query.weight]
Loading weights:  87%|########6 | 173/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.self.query.weight]
Loading weights:  87%|########7 | 174/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.self.value.bias]  
Loading weights:  87%|########7 | 174/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.self.value.bias]
Loading weights:  88%|########7 | 175/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.self.value.weight]
Loading weights:  88%|########7 | 175/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.attention.self.value.weight]
Loading weights:  88%|########8 | 176/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.intermediate.dense.bias]    
Loading weights:  88%|########8 | 176/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.intermediate.dense.bias]
Loading weights:  89%|########8 | 177/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.intermediate.dense.weight]
Loading weights:  89%|########8 | 177/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.intermediate.dense.weight]
Loading weights:  89%|########9 | 178/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.output.LayerNorm.bias]    
Loading weights:  89%|########9 | 178/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.output.LayerNorm.bias]
Loading weights:  90%|########9 | 179/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.output.LayerNorm.weight]
Loading weights:  90%|########9 | 179/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.output.LayerNorm.weight]
Loading weights:  90%|######### | 180/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.output.dense.bias]      
Loading weights:  90%|######### | 180/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.output.dense.bias]
Loading weights:  91%|######### | 181/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.output.dense.weight]
Loading weights:  91%|######### | 181/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.10.output.dense.weight]
Loading weights:  91%|#########1| 182/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.output.LayerNorm.bias]
Loading weights:  91%|#########1| 182/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.output.LayerNorm.bias]
Loading weights:  92%|#########1| 183/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.output.LayerNorm.weight]
Loading weights:  92%|#########1| 183/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.output.LayerNorm.weight]
Loading weights:  92%|#########2| 184/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.output.dense.bias]      
Loading weights:  92%|#########2| 184/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.output.dense.bias]
Loading weights:  93%|#########2| 185/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.output.dense.weight]
Loading weights:  93%|#########2| 185/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.output.dense.weight]
Loading weights:  93%|#########3| 186/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.self.key.bias]      
Loading weights:  93%|#########3| 186/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.self.key.bias]
Loading weights:  94%|#########3| 187/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.self.key.weight]
Loading weights:  94%|#########3| 187/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.self.key.weight]
Loading weights:  94%|#########4| 188/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.self.query.bias]
Loading weights:  94%|#########4| 188/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.self.query.bias]
Loading weights:  95%|#########4| 189/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.self.query.weight]
Loading weights:  95%|#########4| 189/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.self.query.weight]
Loading weights:  95%|#########5| 190/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.self.value.bias]  
Loading weights:  95%|#########5| 190/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.self.value.bias]
Loading weights:  96%|#########5| 191/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.self.value.weight]
Loading weights:  96%|#########5| 191/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.attention.self.value.weight]
Loading weights:  96%|#########6| 192/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.intermediate.dense.bias]    
Loading weights:  96%|#########6| 192/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.intermediate.dense.bias]
Loading weights:  97%|#########6| 193/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.intermediate.dense.weight]
Loading weights:  97%|#########6| 193/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.intermediate.dense.weight]
Loading weights:  97%|#########7| 194/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.output.LayerNorm.bias]    
Loading weights:  97%|#########7| 194/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.output.LayerNorm.bias]
Loading weights:  98%|#########7| 195/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.output.LayerNorm.weight]
Loading weights:  98%|#########7| 195/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.output.LayerNorm.weight]
Loading weights:  98%|#########8| 196/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.output.dense.bias]      
Loading weights:  98%|#########8| 196/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.output.dense.bias]
Loading weights:  99%|#########8| 197/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.output.dense.weight]
Loading weights:  99%|#########8| 197/199 [00:00<00:00, 1521.35it/s, Materializing param=encoder.layer.11.output.dense.weight]
Loading weights:  99%|#########9| 198/199 [00:00<00:00, 1521.35it/s, Materializing param=pooler.dense.bias]                   
Loading weights:  99%|#########9| 198/199 [00:00<00:00, 1521.35it/s, Materializing param=pooler.dense.bias]
Loading weights: 100%|##########| 199/199 [00:00<00:00, 1521.35it/s, Materializing param=pooler.dense.weight]
Loading weights: 100%|##########| 199/199 [00:00<00:00, 1521.35it/s, Materializing param=pooler.dense.weight]
Loading weights: 100%|##########| 199/199 [00:00<00:00, 1424.49it/s, Materializing param=pooler.dense.weight]
[1mBertModel LOAD REPORT[0m from: intfloat/e5-small-v2
Key                     | Status     |  | 
------------------------+------------+--+-
embeddings.position_ids | UNEXPECTED |  | 

[3mNotes:
- UNEXPECTED[3m	:can be ignored when loading from different task/architecture; not ok if you expect identical arch.[0m
ERROR:root:Error cargando indice FAISS CIE-10: Directorio no encontrado: faiss_principal_jerarquico

Loading weights:   0%|          | 0/199 [00:00<?, ?it/s]
Loading weights:   1%|          | 1/199 [00:00<00:00, 52428.80it/s, Materializing param=embeddings.LayerNorm.bias]
Loading weights:   1%|          | 1/199 [00:00<00:00, 13617.87it/s, Materializing param=embeddings.LayerNorm.bias]
Loading weights:   1%|1         | 2/199 [00:00<00:00, 10936.91it/s, Materializing param=embeddings.LayerNorm.weight]
Loading weights:   1%|1         | 2/199 [00:00<00:00, 8630.26it/s, Materializing param=embeddings.LayerNorm.weight] 
Loading weights:   2%|1         | 3/199 [00:00<00:00, 7480.92it/s, Materializing param=embeddings.position_embeddings.weight]
Loading weights:   2%|1         | 3/199 [00:00<00:00, 4735.76it/s, Materializing param=embeddings.position_embeddings.weight]
Loading weights:   2%|2         | 4/199 [00:00<00:00, 4248.47it/s, Materializing param=embeddings.token_type_embeddings.weight]
Loading weights:   2%|2         | 4/199 [00:00<00:00, 2406.72it/s, Materializing param=embeddings.token_type_embeddings.weight]
Loading weights:   3%|2         | 5/199 [00:00<00:00, 2688.66it/s, Materializing param=embeddings.word_embeddings.weight]      
Loading weights:   3%|2         | 5/199 [00:00<00:00, 2577.94it/s, Materializing param=embeddings.word_embeddings.weight]
Loading weights:   3%|3         | 6/199 [00:00<00:00, 2882.35it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.bias]
Loading weights:   3%|3         | 6/199 [00:00<00:00, 2751.27it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.bias]
Loading weights:   4%|3         | 7/199 [00:00<00:00, 3009.13it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.weight]
Loading weights:   4%|3         | 7/199 [00:00<00:00, 2826.35it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.weight]
Loading weights:   4%|4         | 8/199 [00:00<00:00, 2869.37it/s, Materializing param=encoder.layer.0.attention.output.dense.bias]      
Loading weights:   4%|4         | 8/199 [00:00<00:00, 2780.45it/s, Materializing param=encoder.layer.0.attention.output.dense.bias]
Loading weights:   5%|4         | 9/199 [00:00<00:00, 2827.62it/s, Materializing param=encoder.layer.0.attention.output.dense.weight]
Loading weights:   5%|4         | 9/199 [00:00<00:00, 2663.24it/s, Materializing param=encoder.layer.0.attention.output.dense.weight]
Loading weights:   5%|5         | 10/199 [00:00<00:00, 2823.12it/s, Materializing param=encoder.layer.0.attention.self.key.bias]     
Loading weights:   5%|5         | 10/199 [00:00<00:00, 2776.95it/s, Materializing param=encoder.layer.0.attention.self.key.bias]
Loading weights:   6%|5         | 11/199 [00:00<00:00, 2968.56it/s, Materializing param=encoder.layer.0.attention.self.key.weight]
Loading weights:   6%|5         | 11/199 [00:00<00:00, 2930.66it/s, Materializing param=encoder.layer.0.attention.self.key.weight]
Loading weights:   6%|6         | 12/199 [00:00<00:00, 3120.37it/s, Materializing param=encoder.layer.0.attention.self.query.bias]
Loading weights:   6%|6         | 12/199 [00:00<00:00, 3084.61it/s, Materializing param=encoder.layer.0.attention.self.query.bias]
Loading weights:   7%|6         | 13/199 [00:00<00:00, 3239.04it/s, Materializing param=encoder.layer.0.attention.self.query.weight]
Loading weights:   7%|6         | 13/199 [00:00<00:00, 2990.02it/s, Materializing param=encoder.layer.0.attention.self.query.weight]
Loading weights:   7%|7         | 14/199 [00:00<00:00, 3072.91it/s, Materializing param=encoder.layer.0.attention.self.value.bias]  
Loading weights:   7%|7         | 14/199 [00:00<00:00, 2996.70it/s, Materializing param=encoder.layer.0.attention.self.value.bias]
Loading weights:   8%|7         | 15/199 [00:00<00:00, 3082.54it/s, Materializing param=encoder.layer.0.attention.self.value.weight]
Loading weights:   8%|7         | 15/199 [00:00<00:00, 3048.78it/s, Materializing param=encoder.layer.0.attention.self.value.weight]
Loading weights:   8%|8         | 16/199 [00:00<00:00, 3093.86it/s, Materializing param=encoder.layer.0.intermediate.dense.bias]    
Loading weights:   8%|8         | 16/199 [00:00<00:00, 3061.95it/s, Materializing param=encoder.layer.0.intermediate.dense.bias]
Loading weights:   9%|8         | 17/199 [00:00<00:00, 3179.34it/s, Materializing param=encoder.layer.0.intermediate.dense.weight]
Loading weights:   9%|8         | 17/199 [00:00<00:00, 3150.69it/s, Materializing param=encoder.layer.0.intermediate.dense.weight]
Loading weights:   9%|9         | 18/199 [00:00<00:00, 2952.12it/s, Materializing param=encoder.layer.0.output.LayerNorm.bias]    
Loading weights:   9%|9         | 18/199 [00:00<00:00, 2860.19it/s, Materializing param=encoder.layer.0.output.LayerNorm.bias]
Loading weights:  10%|9         | 19/199 [00:00<00:00, 2895.36it/s, Materializing param=encoder.layer.0.output.LayerNorm.weight]
Loading weights:  10%|9         | 19/199 [00:00<00:00, 2820.95it/s, Materializing param=encoder.layer.0.output.LayerNorm.weight]
Loading weights:  10%|#         | 20/199 [00:00<00:00, 2914.53it/s, Materializing param=encoder.layer.0.output.dense.bias]      
Loading weights:  10%|#         | 20/199 [00:00<00:00, 2891.63it/s, Materializing param=encoder.layer.0.output.dense.bias]
Loading weights:  11%|#         | 21/199 [00:00<00:00, 2958.80it/s, Materializing param=encoder.layer.0.output.dense.weight]
Loading weights:  11%|#         | 21/199 [00:00<00:00, 2938.46it/s, Materializing param=encoder.layer.0.output.dense.weight]
Loading weights:  11%|#1        | 22/199 [00:00<00:00, 3008.73it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.bias]
Loading weights:  11%|#1        | 22/199 [00:00<00:00, 2984.59it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.bias]
Loading weights:  12%|#1        | 23/199 [00:00<00:00, 3074.71it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.weight]
Loading weights:  12%|#1        | 23/199 [00:00<00:00, 3054.27it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.weight]
Loading weights:  12%|#2        | 24/199 [00:00<00:00, 3146.12it/s, Materializing param=encoder.layer.1.attention.output.dense.bias]      
Loading weights:  12%|#2        | 24/199 [00:00<00:00, 3126.29it/s, Materializing param=encoder.layer.1.attention.output.dense.bias]
Loading weights:  13%|#2        | 25/199 [00:00<00:00, 3201.95it/s, Materializing param=encoder.layer.1.attention.output.dense.weight]
Loading weights:  13%|#2        | 25/199 [00:00<00:00, 3178.08it/s, Materializing param=encoder.layer.1.attention.output.dense.weight]
Loading weights:  13%|#3        | 26/199 [00:00<00:00, 3262.78it/s, Materializing param=encoder.layer.1.attention.self.key.bias]      
Loading weights:  13%|#3        | 26/199 [00:00<00:00, 3243.57it/s, Materializing param=encoder.layer.1.attention.self.key.bias]
Loading weights:  14%|#3        | 27/199 [00:00<00:00, 3328.91it/s, Materializing param=encoder.layer.1.attention.self.key.weight]
Loading weights:  14%|#3        | 27/199 [00:00<00:00, 3310.32it/s, Materializing param=encoder.layer.1.attention.self.key.weight]
Loading weights:  14%|#4        | 28/199 [00:00<00:00, 3395.41it/s, Materializing param=encoder.layer.1.attention.self.query.bias]
Loading weights:  14%|#4        | 28/199 [00:00<00:00, 3377.15it/s, Materializing param=encoder.layer.1.attention.self.query.bias]
Loading weights:  15%|#4        | 29/199 [00:00<00:00, 3416.42it/s, Materializing param=encoder.layer.1.attention.self.query.weight]
Loading weights:  15%|#4        | 29/199 [00:00<00:00, 3351.93it/s, Materializing param=encoder.layer.1.attention.self.query.weight]
Loading weights:  15%|#5        | 30/199 [00:00<00:00, 3418.15it/s, Materializing param=encoder.layer.1.attention.self.value.bias]  
Loading weights:  15%|#5        | 30/199 [00:00<00:00, 3398.58it/s, Materializing param=encoder.layer.1.attention.self.value.bias]
Loading weights:  16%|#5        | 31/199 [00:00<00:00, 3461.94it/s, Materializing param=encoder.layer.1.attention.self.value.weight]
Loading weights:  16%|#5        | 31/199 [00:00<00:00, 3440.32it/s, Materializing param=encoder.layer.1.attention.self.value.weight]
Loading weights:  16%|#6        | 32/199 [00:00<00:00, 3514.75it/s, Materializing param=encoder.layer.1.intermediate.dense.bias]    
Loading weights:  16%|#6        | 32/199 [00:00<00:00, 3467.17it/s, Materializing param=encoder.layer.1.intermediate.dense.bias]
Loading weights:  17%|#6        | 33/199 [00:00<00:00, 3449.44it/s, Materializing param=encoder.layer.1.intermediate.dense.weight]
Loading weights:  17%|#6        | 33/199 [00:00<00:00, 3422.14it/s, Materializing param=encoder.layer.1.intermediate.dense.weight]
Loading weights:  17%|#7        | 34/199 [00:00<00:00, 3457.12it/s, Materializing param=encoder.layer.1.output.LayerNorm.bias]    
Loading weights:  17%|#7        | 34/199 [00:00<00:00, 3420.80it/s, Materializing param=encoder.layer.1.output.LayerNorm.bias]
Loading weights:  18%|#7        | 35/199 [00:00<00:00, 3414.76it/s, Materializing param=encoder.layer.1.output.LayerNorm.weight]
Loading weights:  18%|#7        | 35/199 [00:00<00:00, 3306.54it/s, Materializing param=encoder.layer.1.output.LayerNorm.weight]
Loading weights:  18%|#8        | 36/199 [00:00<00:00, 3352.76it/s, Materializing param=encoder.layer.1.output.dense.bias]      
Loading weights:  18%|#8        | 36/199 [00:00<00:00, 3297.91it/s, Materializing param=encoder.layer.1.output.dense.bias]
Loading weights:  19%|#8        | 37/199 [00:00<00:00, 3266.80it/s, Materializing param=encoder.layer.1.output.dense.weight]
Loading weights:  19%|#8        | 37/199 [00:00<00:00, 3243.85it/s, Materializing param=encoder.layer.1.output.dense.weight]
Loading weights:  19%|#9        | 38/199 [00:00<00:00, 3279.23it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.bias]
Loading weights:  19%|#9        | 38/199 [00:00<00:00, 3262.85it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.bias]
Loading weights:  20%|#9        | 39/199 [00:00<00:00, 3268.22it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.weight]
Loading weights:  20%|#9        | 39/199 [00:00<00:00, 3241.54it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.weight]
Loading weights:  20%|##        | 40/199 [00:00<00:00, 3290.42it/s, Materializing param=encoder.layer.2.attention.output.dense.bias]      
Loading weights:  20%|##        | 40/199 [00:00<00:00, 3276.74it/s, Materializing param=encoder.layer.2.attention.output.dense.bias]
Loading weights:  21%|##        | 41/199 [00:00<00:00, 3331.71it/s, Materializing param=encoder.layer.2.attention.output.dense.weight]
Loading weights:  21%|##        | 41/199 [00:00<00:00, 3319.18it/s, Materializing param=encoder.layer.2.attention.output.dense.weight]
Loading weights:  21%|##1       | 42/199 [00:00<00:00, 3374.02it/s, Materializing param=encoder.layer.2.attention.self.key.bias]      
Loading weights:  21%|##1       | 42/199 [00:00<00:00, 3361.59it/s, Materializing param=encoder.layer.2.attention.self.key.bias]
Loading weights:  22%|##1       | 43/199 [00:00<00:00, 3395.56it/s, Materializing param=encoder.layer.2.attention.self.key.weight]
Loading weights:  22%|##1       | 43/199 [00:00<00:00, 3357.69it/s, Materializing param=encoder.layer.2.attention.self.key.weight]
Loading weights:  22%|##2       | 44/199 [00:00<00:00, 3397.01it/s, Materializing param=encoder.layer.2.attention.self.query.bias]
Loading weights:  22%|##2       | 44/199 [00:00<00:00, 3321.74it/s, Materializing param=encoder.layer.2.attention.self.query.bias]
Loading weights:  23%|##2       | 45/199 [00:00<00:00, 3357.71it/s, Materializing param=encoder.layer.2.attention.self.query.weight]
Loading weights:  23%|##2       | 45/199 [00:00<00:00, 3342.02it/s, Materializing param=encoder.layer.2.attention.self.query.weight]
Loading weights:  23%|##3       | 46/199 [00:00<00:00, 3348.11it/s, Materializing param=encoder.layer.2.attention.self.value.bias]  
Loading weights:  23%|##3       | 46/199 [00:00<00:00, 3331.92it/s, Materializing param=encoder.layer.2.attention.self.value.bias]
Loading weights:  24%|##3       | 47/199 [00:00<00:00, 3377.17it/s, Materializing param=encoder.layer.2.attention.self.value.weight]
Loading weights:  24%|##3       | 47/199 [00:00<00:00, 3364.66it/s, Materializing param=encoder.layer.2.attention.self.value.weight]
Loading weights:  24%|##4       | 48/199 [00:00<00:00, 3388.20it/s, Materializing param=encoder.layer.2.intermediate.dense.bias]    
Loading weights:  24%|##4       | 48/199 [00:00<00:00, 3374.00it/s, Materializing param=encoder.layer.2.intermediate.dense.bias]
Loading weights:  25%|##4       | 49/199 [00:00<00:00, 3418.97it/s, Materializing param=encoder.layer.2.intermediate.dense.weight]
Loading weights:  25%|##4       | 49/199 [00:00<00:00, 3407.69it/s, Materializing param=encoder.layer.2.intermediate.dense.weight]
Loading weights:  25%|##5       | 50/199 [00:00<00:00, 3439.08it/s, Materializing param=encoder.layer.2.output.LayerNorm.bias]    
Loading weights:  25%|##5       | 50/199 [00:00<00:00, 3404.63it/s, Materializing param=encoder.layer.2.output.LayerNorm.bias]
Loading weights:  26%|##5       | 51/199 [00:00<00:00, 3412.07it/s, Materializing param=encoder.layer.2.output.LayerNorm.weight]
Loading weights:  26%|##5       | 51/199 [00:00<00:00, 3397.92it/s, Materializing param=encoder.layer.2.output.LayerNorm.weight]
Loading weights:  26%|##6       | 52/199 [00:00<00:00, 3421.24it/s, Materializing param=encoder.layer.2.output.dense.bias]      
Loading weights:  26%|##6       | 52/199 [00:00<00:00, 3390.34it/s, Materializing param=encoder.layer.2.output.dense.bias]
Loading weights:  27%|##6       | 53/199 [00:00<00:00, 3386.37it/s, Materializing param=encoder.layer.2.output.dense.weight]
Loading weights:  27%|##6       | 53/199 [00:00<00:00, 3372.96it/s, Materializing param=encoder.layer.2.output.dense.weight]
Loading weights:  27%|##7       | 54/199 [00:00<00:00, 3414.78it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.bias]
Loading weights:  27%|##7       | 54/199 [00:00<00:00, 3404.62it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.bias]
Loading weights:  28%|##7       | 55/199 [00:00<00:00, 3431.31it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.weight]
Loading weights:  28%|##7       | 55/199 [00:00<00:00, 3418.70it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.weight]
Loading weights:  28%|##8       | 56/199 [00:00<00:00, 3458.66it/s, Materializing param=encoder.layer.3.attention.output.dense.bias]      
Loading weights:  28%|##8       | 56/199 [00:00<00:00, 3415.36it/s, Materializing param=encoder.layer.3.attention.output.dense.bias]
Loading weights:  29%|##8       | 57/199 [00:00<00:00, 3430.36it/s, Materializing param=encoder.layer.3.attention.output.dense.weight]
Loading weights:  29%|##8       | 57/199 [00:00<00:00, 3418.15it/s, Materializing param=encoder.layer.3.attention.output.dense.weight]
Loading weights:  29%|##9       | 58/199 [00:00<00:00, 3435.87it/s, Materializing param=encoder.layer.3.attention.self.key.bias]      
Loading weights:  29%|##9       | 58/199 [00:00<00:00, 3368.36it/s, Materializing param=encoder.layer.3.attention.self.key.bias]
Loading weights:  30%|##9       | 59/199 [00:00<00:00, 3399.65it/s, Materializing param=encoder.layer.3.attention.self.key.weight]
Loading weights:  30%|##9       | 59/199 [00:00<00:00, 3334.15it/s, Materializing param=encoder.layer.3.attention.self.key.weight]
Loading weights:  30%|###       | 60/199 [00:00<00:00, 3361.09it/s, Materializing param=encoder.layer.3.attention.self.query.bias]
Loading weights:  30%|###       | 60/199 [00:00<00:00, 3348.79it/s, Materializing param=encoder.layer.3.attention.self.query.bias]
Loading weights:  31%|###       | 61/199 [00:00<00:00, 3383.49it/s, Materializing param=encoder.layer.3.attention.self.query.weight]
Loading weights:  31%|###       | 61/199 [00:00<00:00, 3373.09it/s, Materializing param=encoder.layer.3.attention.self.query.weight]
Loading weights:  31%|###1      | 62/199 [00:00<00:00, 3409.15it/s, Materializing param=encoder.layer.3.attention.self.value.bias]  
Loading weights:  31%|###1      | 62/199 [00:00<00:00, 3398.99it/s, Materializing param=encoder.layer.3.attention.self.value.bias]
Loading weights:  32%|###1      | 63/199 [00:00<00:00, 3425.83it/s, Materializing param=encoder.layer.3.attention.self.value.weight]
Loading weights:  32%|###1      | 63/199 [00:00<00:00, 3408.07it/s, Materializing param=encoder.layer.3.attention.self.value.weight]
Loading weights:  32%|###2      | 64/199 [00:00<00:00, 3441.13it/s, Materializing param=encoder.layer.3.intermediate.dense.bias]    
Loading weights:  32%|###2      | 64/199 [00:00<00:00, 3407.02it/s, Materializing param=encoder.layer.3.intermediate.dense.bias]
Loading weights:  33%|###2      | 65/199 [00:00<00:00, 3414.32it/s, Materializing param=encoder.layer.3.intermediate.dense.weight]
Loading weights:  33%|###2      | 65/199 [00:00<00:00, 3399.25it/s, Materializing param=encoder.layer.3.intermediate.dense.weight]
Loading weights:  33%|###3      | 66/199 [00:00<00:00, 3380.89it/s, Materializing param=encoder.layer.3.output.LayerNorm.bias]    
Loading weights:  33%|###3      | 66/199 [00:00<00:00, 3370.81it/s, Materializing param=encoder.layer.3.output.LayerNorm.bias]
Loading weights:  34%|###3      | 67/199 [00:00<00:00, 3403.81it/s, Materializing param=encoder.layer.3.output.LayerNorm.weight]
Loading weights:  34%|###3      | 67/199 [00:00<00:00, 3395.42it/s, Materializing param=encoder.layer.3.output.LayerNorm.weight]
Loading weights:  34%|###4      | 68/199 [00:00<00:00, 3430.14it/s, Materializing param=encoder.layer.3.output.dense.bias]      
Loading weights:  34%|###4      | 68/199 [00:00<00:00, 3422.16it/s, Materializing param=encoder.layer.3.output.dense.bias]
Loading weights:  35%|###4      | 69/199 [00:00<00:00, 3457.01it/s, Materializing param=encoder.layer.3.output.dense.weight]
Loading weights:  35%|###4      | 69/199 [00:00<00:00, 3449.26it/s, Materializing param=encoder.layer.3.output.dense.weight]
Loading weights:  35%|###5      | 70/199 [00:00<00:00, 3405.38it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.bias]
Loading weights:  35%|###5      | 70/199 [00:00<00:00, 3391.53it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.bias]
Loading weights:  36%|###5      | 71/199 [00:00<00:00, 3411.49it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.weight]
Loading weights:  36%|###5      | 71/199 [00:00<00:00, 3402.21it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.weight]
Loading weights:  36%|###6      | 72/199 [00:00<00:00, 3422.76it/s, Materializing param=encoder.layer.4.attention.output.dense.bias]      
Loading weights:  36%|###6      | 72/199 [00:00<00:00, 3406.81it/s, Materializing param=encoder.layer.4.attention.output.dense.bias]
Loading weights:  37%|###6      | 73/199 [00:00<00:00, 3433.56it/s, Materializing param=encoder.layer.4.attention.output.dense.weight]
Loading weights:  37%|###6      | 73/199 [00:00<00:00, 3401.22it/s, Materializing param=encoder.layer.4.attention.output.dense.weight]
Loading weights:  37%|###7      | 74/199 [00:00<00:00, 3427.85it/s, Materializing param=encoder.layer.4.attention.self.key.bias]      
Loading weights:  37%|###7      | 74/199 [00:00<00:00, 3413.94it/s, Materializing param=encoder.layer.4.attention.self.key.bias]
Loading weights:  38%|###7      | 75/199 [00:00<00:00, 3440.47it/s, Materializing param=encoder.layer.4.attention.self.key.weight]
Loading weights:  38%|###7      | 75/199 [00:00<00:00, 3432.74it/s, Materializing param=encoder.layer.4.attention.self.key.weight]
Loading weights:  38%|###8      | 76/199 [00:00<00:00, 3463.35it/s, Materializing param=encoder.layer.4.attention.self.query.bias]
Loading weights:  38%|###8      | 76/199 [00:00<00:00, 3455.02it/s, Materializing param=encoder.layer.4.attention.self.query.bias]
Loading weights:  39%|###8      | 77/199 [00:00<00:00, 3467.52it/s, Materializing param=encoder.layer.4.attention.self.query.weight]
Loading weights:  39%|###8      | 77/199 [00:00<00:00, 3459.13it/s, Materializing param=encoder.layer.4.attention.self.query.weight]
Loading weights:  39%|###9      | 78/199 [00:00<00:00, 3485.57it/s, Materializing param=encoder.layer.4.attention.self.value.bias]  
Loading weights:  39%|###9      | 78/199 [00:00<00:00, 3477.16it/s, Materializing param=encoder.layer.4.attention.self.value.bias]
Loading weights:  40%|###9      | 79/199 [00:00<00:00, 3506.72it/s, Materializing param=encoder.layer.4.attention.self.value.weight]
Loading weights:  40%|###9      | 79/199 [00:00<00:00, 3499.65it/s, Materializing param=encoder.layer.4.attention.self.value.weight]
Loading weights:  40%|####      | 80/199 [00:00<00:00, 3527.33it/s, Materializing param=encoder.layer.4.intermediate.dense.bias]    
Loading weights:  40%|####      | 80/199 [00:00<00:00, 3519.74it/s, Materializing param=encoder.layer.4.intermediate.dense.bias]
Loading weights:  41%|####      | 81/199 [00:00<00:00, 3549.48it/s, Materializing param=encoder.layer.4.intermediate.dense.weight]
Loading weights:  41%|####      | 81/199 [00:00<00:00, 3518.31it/s, Materializing param=encoder.layer.4.intermediate.dense.weight]
Loading weights:  41%|####1     | 82/199 [00:00<00:00, 3539.86it/s, Materializing param=encoder.layer.4.output.LayerNorm.bias]    
Loading weights:  41%|####1     | 82/199 [00:00<00:00, 3530.63it/s, Materializing param=encoder.layer.4.output.LayerNorm.bias]
Loading weights:  42%|####1     | 83/199 [00:00<00:00, 3556.53it/s, Materializing param=encoder.layer.4.output.LayerNorm.weight]
Loading weights:  42%|####1     | 83/199 [00:00<00:00, 3548.01it/s, Materializing param=encoder.layer.4.output.LayerNorm.weight]
Loading weights:  42%|####2     | 84/199 [00:00<00:00, 3554.78it/s, Materializing param=encoder.layer.4.output.dense.bias]      
Loading weights:  42%|####2     | 84/199 [00:00<00:00, 3544.59it/s, Materializing param=encoder.layer.4.output.dense.bias]
Loading weights:  43%|####2     | 85/199 [00:00<00:00, 3569.66it/s, Materializing param=encoder.layer.4.output.dense.weight]
Loading weights:  43%|####2     | 85/199 [00:00<00:00, 3560.96it/s, Materializing param=encoder.layer.4.output.dense.weight]
Loading weights:  43%|####3     | 86/199 [00:00<00:00, 3585.94it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.bias]
Loading weights:  43%|####3     | 86/199 [00:00<00:00, 3576.91it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.bias]
Loading weights:  44%|####3     | 87/199 [00:00<00:00, 3594.76it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.weight]
Loading weights:  44%|####3     | 87/199 [00:00<00:00, 3573.61it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.weight]
Loading weights:  44%|####4     | 88/199 [00:00<00:00, 3593.99it/s, Materializing param=encoder.layer.5.attention.output.dense.bias]      
Loading weights:  44%|####4     | 88/199 [00:00<00:00, 3586.16it/s, Materializing param=encoder.layer.5.attention.output.dense.bias]
Loading weights:  45%|####4     | 89/199 [00:00<00:00, 3606.52it/s, Materializing param=encoder.layer.5.attention.output.dense.weight]
Loading weights:  45%|####4     | 89/199 [00:00<00:00, 3597.10it/s, Materializing param=encoder.layer.5.attention.output.dense.weight]
Loading weights:  45%|####5     | 90/199 [00:00<00:00, 3621.05it/s, Materializing param=encoder.layer.5.attention.self.key.bias]      
Loading weights:  45%|####5     | 90/199 [00:00<00:00, 3613.46it/s, Materializing param=encoder.layer.5.attention.self.key.bias]
Loading weights:  46%|####5     | 91/199 [00:00<00:00, 3639.29it/s, Materializing param=encoder.layer.5.attention.self.key.weight]
Loading weights:  46%|####5     | 91/199 [00:00<00:00, 3632.61it/s, Materializing param=encoder.layer.5.attention.self.key.weight]
Loading weights:  46%|####6     | 92/199 [00:00<00:00, 3649.57it/s, Materializing param=encoder.layer.5.attention.self.query.bias]
Loading weights:  46%|####6     | 92/199 [00:00<00:00, 3641.64it/s, Materializing param=encoder.layer.5.attention.self.query.bias]
Loading weights:  47%|####6     | 93/199 [00:00<00:00, 3630.55it/s, Materializing param=encoder.layer.5.attention.self.query.weight]
Loading weights:  47%|####6     | 93/199 [00:00<00:00, 3622.06it/s, Materializing param=encoder.layer.5.attention.self.query.weight]
Loading weights:  47%|####7     | 94/199 [00:00<00:00, 3635.99it/s, Materializing param=encoder.layer.5.attention.self.value.bias]  
Loading weights:  47%|####7     | 94/199 [00:00<00:00, 3627.92it/s, Materializing param=encoder.layer.5.attention.self.value.bias]
Loading weights:  48%|####7     | 95/199 [00:00<00:00, 3651.37it/s, Materializing param=encoder.layer.5.attention.self.value.weight]
Loading weights:  48%|####7     | 95/199 [00:00<00:00, 3641.12it/s, Materializing param=encoder.layer.5.attention.self.value.weight]
Loading weights:  48%|####8     | 96/199 [00:00<00:00, 3650.96it/s, Materializing param=encoder.layer.5.intermediate.dense.bias]    
Loading weights:  48%|####8     | 96/199 [00:00<00:00, 3642.31it/s, Materializing param=encoder.layer.5.intermediate.dense.bias]
Loading weights:  49%|####8     | 97/199 [00:00<00:00, 3664.63it/s, Materializing param=encoder.layer.5.intermediate.dense.weight]
Loading weights:  49%|####8     | 97/199 [00:00<00:00, 3657.38it/s, Materializing param=encoder.layer.5.intermediate.dense.weight]
Loading weights:  49%|####9     | 98/199 [00:00<00:00, 3680.99it/s, Materializing param=encoder.layer.5.output.LayerNorm.bias]    
Loading weights:  49%|####9     | 98/199 [00:00<00:00, 3674.18it/s, Materializing param=encoder.layer.5.output.LayerNorm.bias]
Loading weights:  50%|####9     | 99/199 [00:00<00:00, 3697.79it/s, Materializing param=encoder.layer.5.output.LayerNorm.weight]
Loading weights:  50%|####9     | 99/199 [00:00<00:00, 3691.09it/s, Materializing param=encoder.layer.5.output.LayerNorm.weight]
Loading weights:  50%|#####     | 100/199 [00:00<00:00, 3714.83it/s, Materializing param=encoder.layer.5.output.dense.bias]     
Loading weights:  50%|#####     | 100/199 [00:00<00:00, 3708.59it/s, Materializing param=encoder.layer.5.output.dense.bias]
Loading weights:  51%|#####     | 101/199 [00:00<00:00, 3725.71it/s, Materializing param=encoder.layer.5.output.dense.weight]
Loading weights:  51%|#####     | 101/199 [00:00<00:00, 3691.56it/s, Materializing param=encoder.layer.5.output.dense.weight]
Loading weights:  51%|#####1    | 102/199 [00:00<00:00, 3706.85it/s, Materializing param=encoder.layer.6.attention.output.LayerNorm.bias]
Loading weights:  51%|#####1    | 102/199 [00:00<00:00, 3699.86it/s, Materializing param=encoder.layer.6.attention.output.LayerNorm.bias]
Loading weights:  52%|#####1    | 103/199 [00:00<00:00, 3693.46it/s, Materializing param=encoder.layer.6.attention.output.LayerNorm.weight]
Loading weights:  52%|#####1    | 103/199 [00:00<00:00, 3685.46it/s, Materializing param=encoder.layer.6.attention.output.LayerNorm.weight]
Loading weights:  52%|#####2    | 104/199 [00:00<00:00, 3678.41it/s, Materializing param=encoder.layer.6.attention.output.dense.bias]      
Loading weights:  52%|#####2    | 104/199 [00:00<00:00, 3670.05it/s, Materializing param=encoder.layer.6.attention.output.dense.bias]
Loading weights:  53%|#####2    | 105/199 [00:00<00:00, 3691.30it/s, Materializing param=encoder.layer.6.attention.output.dense.weight]
Loading weights:  53%|#####2    | 105/199 [00:00<00:00, 3684.82it/s, Materializing param=encoder.layer.6.attention.output.dense.weight]
Loading weights:  53%|#####3    | 106/199 [00:00<00:00, 3687.09it/s, Materializing param=encoder.layer.6.attention.self.key.bias]      
Loading weights:  53%|#####3    | 106/199 [00:00<00:00, 3679.85it/s, Materializing param=encoder.layer.6.attention.self.key.bias]
Loading weights:  54%|#####3    | 107/199 [00:00<00:00, 3686.71it/s, Materializing param=encoder.layer.6.attention.self.key.weight]
Loading weights:  54%|#####3    | 107/199 [00:00<00:00, 3416.73it/s, Materializing param=encoder.layer.6.attention.self.key.weight]
Loading weights:  54%|#####4    | 108/199 [00:00<00:00, 3413.37it/s, Materializing param=encoder.layer.6.attention.self.query.bias]
Loading weights:  54%|#####4    | 108/199 [00:00<00:00, 3406.95it/s, Materializing param=encoder.layer.6.attention.self.query.bias]
Loading weights:  55%|#####4    | 109/199 [00:00<00:00, 3421.13it/s, Materializing param=encoder.layer.6.attention.self.query.weight]
Loading weights:  55%|#####4    | 109/199 [00:00<00:00, 3414.49it/s, Materializing param=encoder.layer.6.attention.self.query.weight]
Loading weights:  55%|#####5    | 110/199 [00:00<00:00, 3417.53it/s, Materializing param=encoder.layer.6.attention.self.value.bias]  
Loading weights:  55%|#####5    | 110/199 [00:00<00:00, 3411.31it/s, Materializing param=encoder.layer.6.attention.self.value.bias]
Loading weights:  56%|#####5    | 111/199 [00:00<00:00, 3418.04it/s, Materializing param=encoder.layer.6.attention.self.value.weight]
Loading weights:  56%|#####5    | 111/199 [00:00<00:00, 3411.90it/s, Materializing param=encoder.layer.6.attention.self.value.weight]
Loading weights:  56%|#####6    | 112/199 [00:00<00:00, 3431.73it/s, Materializing param=encoder.layer.6.intermediate.dense.bias]    
Loading weights:  56%|#####6    | 112/199 [00:00<00:00, 3426.72it/s, Materializing param=encoder.layer.6.intermediate.dense.bias]
Loading weights:  57%|#####6    | 113/199 [00:00<00:00, 3447.16it/s, Materializing param=encoder.layer.6.intermediate.dense.weight]
Loading weights:  57%|#####6    | 113/199 [00:00<00:00, 3442.40it/s, Materializing param=encoder.layer.6.intermediate.dense.weight]
Loading weights:  57%|#####7    | 114/199 [00:00<00:00, 3445.53it/s, Materializing param=encoder.layer.6.output.LayerNorm.bias]    
Loading weights:  57%|#####7    | 114/199 [00:00<00:00, 3439.91it/s, Materializing param=encoder.layer.6.output.LayerNorm.bias]
Loading weights:  58%|#####7    | 115/199 [00:00<00:00, 3456.03it/s, Materializing param=encoder.layer.6.output.LayerNorm.weight]
Loading weights:  58%|#####7    | 115/199 [00:00<00:00, 3449.73it/s, Materializing param=encoder.layer.6.output.LayerNorm.weight]
Loading weights:  58%|#####8    | 116/199 [00:00<00:00, 3448.97it/s, Materializing param=encoder.layer.6.output.dense.bias]      
Loading weights:  58%|#####8    | 116/199 [00:00<00:00, 3443.06it/s, Materializing param=encoder.layer.6.output.dense.bias]
Loading weights:  59%|#####8    | 117/199 [00:00<00:00, 3462.26it/s, Materializing param=encoder.layer.6.output.dense.weight]
Loading weights:  59%|#####8    | 117/199 [00:00<00:00, 3457.57it/s, Materializing param=encoder.layer.6.output.dense.weight]
Loading weights:  59%|#####9    | 118/199 [00:00<00:00, 3477.96it/s, Materializing param=encoder.layer.7.attention.output.LayerNorm.bias]
Loading weights:  59%|#####9    | 118/199 [00:00<00:00, 3473.37it/s, Materializing param=encoder.layer.7.attention.output.LayerNorm.bias]
Loading weights:  60%|#####9    | 119/199 [00:00<00:00, 3488.49it/s, Materializing param=encoder.layer.7.attention.output.LayerNorm.weight]
Loading weights:  60%|#####9    | 119/199 [00:00<00:00, 3482.64it/s, Materializing param=encoder.layer.7.attention.output.LayerNorm.weight]
Loading weights:  60%|######    | 120/199 [00:00<00:00, 3501.38it/s, Materializing param=encoder.layer.7.attention.output.dense.bias]      
Loading weights:  60%|######    | 120/199 [00:00<00:00, 3496.52it/s, Materializing param=encoder.layer.7.attention.output.dense.bias]
Loading weights:  61%|######    | 121/199 [00:00<00:00, 3516.01it/s, Materializing param=encoder.layer.7.attention.output.dense.weight]
Loading weights:  61%|######    | 121/199 [00:00<00:00, 3511.43it/s, Materializing param=encoder.layer.7.attention.output.dense.weight]
Loading weights:  61%|######1   | 122/199 [00:00<00:00, 3512.14it/s, Materializing param=encoder.layer.7.attention.self.key.bias]      
Loading weights:  61%|######1   | 122/199 [00:00<00:00, 3506.75it/s, Materializing param=encoder.layer.7.attention.self.key.bias]
Loading weights:  62%|######1   | 123/199 [00:00<00:00, 2561.57it/s, Materializing param=encoder.layer.7.attention.self.key.weight]
Loading weights:  62%|######1   | 123/199 [00:00<00:00, 2555.68it/s, Materializing param=encoder.layer.7.attention.self.key.weight]
Loading weights:  62%|######2   | 124/199 [00:00<00:00, 2570.46it/s, Materializing param=encoder.layer.7.attention.self.query.bias]
Loading weights:  62%|######2   | 124/199 [00:00<00:00, 2567.58it/s, Materializing param=encoder.layer.7.attention.self.query.bias]
Loading weights:  63%|######2   | 125/199 [00:00<00:00, 2582.98it/s, Materializing param=encoder.layer.7.attention.self.query.weight]
Loading weights:  63%|######2   | 125/199 [00:00<00:00, 2580.27it/s, Materializing param=encoder.layer.7.attention.self.query.weight]
Loading weights:  63%|######3   | 126/199 [00:00<00:00, 2595.93it/s, Materializing param=encoder.layer.7.attention.self.value.bias]  
Loading weights:  63%|######3   | 126/199 [00:00<00:00, 2591.93it/s, Materializing param=encoder.layer.7.attention.self.value.bias]
Loading weights:  64%|######3   | 127/199 [00:00<00:00, 2607.56it/s, Materializing param=encoder.layer.7.attention.self.value.weight]
Loading weights:  64%|######3   | 127/199 [00:00<00:00, 2604.92it/s, Materializing param=encoder.layer.7.attention.self.value.weight]
Loading weights:  64%|######4   | 128/199 [00:00<00:00, 2620.62it/s, Materializing param=encoder.layer.7.intermediate.dense.bias]    
Loading weights:  64%|######4   | 128/199 [00:00<00:00, 2617.96it/s, Materializing param=encoder.layer.7.intermediate.dense.bias]
Loading weights:  65%|######4   | 129/199 [00:00<00:00, 2633.82it/s, Materializing param=encoder.layer.7.intermediate.dense.weight]
Loading weights:  65%|######4   | 129/199 [00:00<00:00, 2631.76it/s, Materializing param=encoder.layer.7.intermediate.dense.weight]
Loading weights:  65%|######5   | 130/199 [00:00<00:00, 2648.42it/s, Materializing param=encoder.layer.7.output.LayerNorm.bias]    
Loading weights:  65%|######5   | 130/199 [00:00<00:00, 2646.36it/s, Materializing param=encoder.layer.7.output.LayerNorm.bias]
Loading weights:  66%|######5   | 131/199 [00:00<00:00, 2662.65it/s, Materializing param=encoder.layer.7.output.LayerNorm.weight]
Loading weights:  66%|######5   | 131/199 [00:00<00:00, 2660.61it/s, Materializing param=encoder.layer.7.output.LayerNorm.weight]
Loading weights:  66%|######6   | 132/199 [00:00<00:00, 2677.12it/s, Materializing param=encoder.layer.7.output.dense.bias]      
Loading weights:  66%|######6   | 132/199 [00:00<00:00, 2675.08it/s, Materializing param=encoder.layer.7.output.dense.bias]
Loading weights:  67%|######6   | 133/199 [00:00<00:00, 2691.43it/s, Materializing param=encoder.layer.7.output.dense.weight]
Loading weights:  67%|######6   | 133/199 [00:00<00:00, 2689.40it/s, Materializing param=encoder.layer.7.output.dense.weight]
Loading weights:  67%|######7   | 134/199 [00:00<00:00, 2705.78it/s, Materializing param=encoder.layer.8.attention.output.LayerNorm.bias]
Loading weights:  67%|######7   | 134/199 [00:00<00:00, 2702.27it/s, Materializing param=encoder.layer.8.attention.output.LayerNorm.bias]
Loading weights:  68%|######7   | 135/199 [00:00<00:00, 2718.19it/s, Materializing param=encoder.layer.8.attention.output.LayerNorm.weight]
Loading weights:  68%|######7   | 135/199 [00:00<00:00, 2716.08it/s, Materializing param=encoder.layer.8.attention.output.LayerNorm.weight]
Loading weights:  68%|######8   | 136/199 [00:00<00:00, 2732.25it/s, Materializing param=encoder.layer.8.attention.output.dense.bias]      
Loading weights:  68%|######8   | 136/199 [00:00<00:00, 2730.17it/s, Materializing param=encoder.layer.8.attention.output.dense.bias]
Loading weights:  69%|######8   | 137/199 [00:00<00:00, 2746.33it/s, Materializing param=encoder.layer.8.attention.output.dense.weight]
Loading weights:  69%|######8   | 137/199 [00:00<00:00, 2744.24it/s, Materializing param=encoder.layer.8.attention.output.dense.weight]
Loading weights:  69%|######9   | 138/199 [00:00<00:00, 2760.40it/s, Materializing param=encoder.layer.8.attention.self.key.bias]      
Loading weights:  69%|######9   | 138/199 [00:00<00:00, 2204.80it/s, Materializing param=encoder.layer.8.attention.self.key.bias]
Loading weights:  70%|######9   | 139/199 [00:00<00:00, 2210.76it/s, Materializing param=encoder.layer.8.attention.self.key.weight]
Loading weights:  70%|######9   | 139/199 [00:00<00:00, 2208.65it/s, Materializing param=encoder.layer.8.attention.self.key.weight]
Loading weights:  70%|#######   | 140/199 [00:00<00:00, 2221.29it/s, Materializing param=encoder.layer.8.attention.self.query.bias]
Loading weights:  70%|#######   | 140/199 [00:00<00:00, 2219.82it/s, Materializing param=encoder.layer.8.attention.self.query.bias]
Loading weights:  71%|#######   | 141/199 [00:00<00:00, 2232.82it/s, Materializing param=encoder.layer.8.attention.self.query.weight]
Loading weights:  71%|#######   | 141/199 [00:00<00:00, 2231.40it/s, Materializing param=encoder.layer.8.attention.self.query.weight]
Loading weights:  71%|#######1  | 142/199 [00:00<00:00, 2244.52it/s, Materializing param=encoder.layer.8.attention.self.value.bias]  
Loading weights:  71%|#######1  | 142/199 [00:00<00:00, 2243.08it/s, Materializing param=encoder.layer.8.attention.self.value.bias]
Loading weights:  72%|#######1  | 143/199 [00:00<00:00, 2256.17it/s, Materializing param=encoder.layer.8.attention.self.value.weight]
Loading weights:  72%|#######1  | 143/199 [00:00<00:00, 2254.76it/s, Materializing param=encoder.layer.8.attention.self.value.weight]
Loading weights:  72%|#######2  | 144/199 [00:00<00:00, 2267.83it/s, Materializing param=encoder.layer.8.intermediate.dense.bias]    
Loading weights:  72%|#######2  | 144/199 [00:00<00:00, 2266.40it/s, Materializing param=encoder.layer.8.intermediate.dense.bias]
Loading weights:  73%|#######2  | 145/199 [00:00<00:00, 2279.52it/s, Materializing param=encoder.layer.8.intermediate.dense.weight]
Loading weights:  73%|#######2  | 145/199 [00:00<00:00, 2278.11it/s, Materializing param=encoder.layer.8.intermediate.dense.weight]
Loading weights:  73%|#######3  | 146/199 [00:00<00:00, 2291.26it/s, Materializing param=encoder.layer.8.output.LayerNorm.bias]    
Loading weights:  73%|#######3  | 146/199 [00:00<00:00, 2289.87it/s, Materializing param=encoder.layer.8.output.LayerNorm.bias]
Loading weights:  74%|#######3  | 147/199 [00:00<00:00, 2302.82it/s, Materializing param=encoder.layer.8.output.LayerNorm.weight]
Loading weights:  74%|#######3  | 147/199 [00:00<00:00, 2301.40it/s, Materializing param=encoder.layer.8.output.LayerNorm.weight]
Loading weights:  74%|#######4  | 148/199 [00:00<00:00, 2314.46it/s, Materializing param=encoder.layer.8.output.dense.bias]      
Loading weights:  74%|#######4  | 148/199 [00:00<00:00, 2313.06it/s, Materializing param=encoder.layer.8.output.dense.bias]
Loading weights:  75%|#######4  | 149/199 [00:00<00:00, 2326.19it/s, Materializing param=encoder.layer.8.output.dense.weight]
Loading weights:  75%|#######4  | 149/199 [00:00<00:00, 2324.80it/s, Materializing param=encoder.layer.8.output.dense.weight]
Loading weights:  75%|#######5  | 150/199 [00:00<00:00, 2337.94it/s, Materializing param=encoder.layer.9.attention.output.LayerNorm.bias]
Loading weights:  75%|#######5  | 150/199 [00:00<00:00, 2336.53it/s, Materializing param=encoder.layer.9.attention.output.LayerNorm.bias]
Loading weights:  76%|#######5  | 151/199 [00:00<00:00, 2348.55it/s, Materializing param=encoder.layer.9.attention.output.LayerNorm.weight]
Loading weights:  76%|#######5  | 151/199 [00:00<00:00, 2346.10it/s, Materializing param=encoder.layer.9.attention.output.LayerNorm.weight]
Loading weights:  76%|#######6  | 152/199 [00:00<00:00, 2357.88it/s, Materializing param=encoder.layer.9.attention.output.dense.bias]      
Loading weights:  76%|#######6  | 152/199 [00:00<00:00, 2355.96it/s, Materializing param=encoder.layer.9.attention.output.dense.bias]
Loading weights:  77%|#######6  | 153/199 [00:00<00:00, 2368.36it/s, Materializing param=encoder.layer.9.attention.output.dense.weight]
Loading weights:  77%|#######6  | 153/199 [00:00<00:00, 2366.88it/s, Materializing param=encoder.layer.9.attention.output.dense.weight]
Loading weights:  77%|#######7  | 154/199 [00:00<00:00, 1962.64it/s, Materializing param=encoder.layer.9.attention.self.key.bias]      
Loading weights:  77%|#######7  | 154/199 [00:00<00:00, 1960.14it/s, Materializing param=encoder.layer.9.attention.self.key.bias]
Loading weights:  78%|#######7  | 155/199 [00:00<00:00, 1970.39it/s, Materializing param=encoder.layer.9.attention.self.key.weight]
Loading weights:  78%|#######7  | 155/199 [00:00<00:00, 1969.26it/s, Materializing param=encoder.layer.9.attention.self.key.weight]
Loading weights:  78%|#######8  | 156/199 [00:00<00:00, 1979.91it/s, Materializing param=encoder.layer.9.attention.self.query.bias]
Loading weights:  78%|#######8  | 156/199 [00:00<00:00, 1978.86it/s, Materializing param=encoder.layer.9.attention.self.query.bias]
Loading weights:  79%|#######8  | 157/199 [00:00<00:00, 1989.55it/s, Materializing param=encoder.layer.9.attention.self.query.weight]
Loading weights:  79%|#######8  | 157/199 [00:00<00:00, 1988.54it/s, Materializing param=encoder.layer.9.attention.self.query.weight]
Loading weights:  79%|#######9  | 158/199 [00:00<00:00, 1999.28it/s, Materializing param=encoder.layer.9.attention.self.value.bias]  
Loading weights:  79%|#######9  | 158/199 [00:00<00:00, 1998.29it/s, Materializing param=encoder.layer.9.attention.self.value.bias]
Loading weights:  80%|#######9  | 159/199 [00:00<00:00, 2009.06it/s, Materializing param=encoder.layer.9.attention.self.value.weight]
Loading weights:  80%|#######9  | 159/199 [00:00<00:00, 2008.05it/s, Materializing param=encoder.layer.9.attention.self.value.weight]
Loading weights:  80%|########  | 160/199 [00:00<00:00, 2018.79it/s, Materializing param=encoder.layer.9.intermediate.dense.bias]    
Loading weights:  80%|########  | 160/199 [00:00<00:00, 2017.78it/s, Materializing param=encoder.layer.9.intermediate.dense.bias]
Loading weights:  81%|########  | 161/199 [00:00<00:00, 2028.52it/s, Materializing param=encoder.layer.9.intermediate.dense.weight]
Loading weights:  81%|########  | 161/199 [00:00<00:00, 2027.52it/s, Materializing param=encoder.layer.9.intermediate.dense.weight]
Loading weights:  81%|########1 | 162/199 [00:00<00:00, 2038.30it/s, Materializing param=encoder.layer.9.output.LayerNorm.bias]    
Loading weights:  81%|########1 | 162/199 [00:00<00:00, 2037.30it/s, Materializing param=encoder.layer.9.output.LayerNorm.bias]
Loading weights:  82%|########1 | 163/199 [00:00<00:00, 2047.92it/s, Materializing param=encoder.layer.9.output.LayerNorm.weight]
Loading weights:  82%|########1 | 163/199 [00:00<00:00, 2046.92it/s, Materializing param=encoder.layer.9.output.LayerNorm.weight]
Loading weights:  82%|########2 | 164/199 [00:00<00:00, 2057.66it/s, Materializing param=encoder.layer.9.output.dense.bias]      
Loading weights:  82%|########2 | 164/199 [00:00<00:00, 2056.65it/s, Materializing param=encoder.layer.9.output.dense.bias]
Loading weights:  83%|########2 | 165/199 [00:00<00:00, 2067.29it/s, Materializing param=encoder.layer.9.output.dense.weight]
Loading weights:  83%|########2 | 165/199 [00:00<00:00, 2066.26it/s, Materializing param=encoder.layer.9.output.dense.weight]
Loading weights:  83%|########3 | 166/199 [00:00<00:00, 2076.90it/s, Materializing param=encoder.layer.10.attention.output.LayerNorm.bias]
Loading weights:  83%|########3 | 166/199 [00:00<00:00, 2075.84it/s, Materializing param=encoder.layer.10.attention.output.LayerNorm.bias]
Loading weights:  84%|########3 | 167/199 [00:00<00:00, 2084.65it/s, Materializing param=encoder.layer.10.attention.output.LayerNorm.weight]
Loading weights:  84%|########3 | 167/199 [00:00<00:00, 2083.14it/s, Materializing param=encoder.layer.10.attention.output.LayerNorm.weight]
Loading weights:  84%|########4 | 168/199 [00:00<00:00, 2093.16it/s, Materializing param=encoder.layer.10.attention.output.dense.bias]      
Loading weights:  84%|########4 | 168/199 [00:00<00:00, 2091.95it/s, Materializing param=encoder.layer.10.attention.output.dense.bias]
Loading weights:  85%|########4 | 169/199 [00:00<00:00, 2102.24it/s, Materializing param=encoder.layer.10.attention.output.dense.weight]
Loading weights:  85%|########4 | 169/199 [00:00<00:00, 1801.33it/s, Materializing param=encoder.layer.10.attention.output.dense.weight]
Loading weights:  85%|########5 | 170/199 [00:00<00:00, 1806.41it/s, Materializing param=encoder.layer.10.attention.self.key.bias]      
Loading weights:  85%|########5 | 170/199 [00:00<00:00, 1805.24it/s, Materializing param=encoder.layer.10.attention.self.key.bias]
Loading weights:  86%|########5 | 171/199 [00:00<00:00, 1813.88it/s, Materializing param=encoder.layer.10.attention.self.key.weight]
Loading weights:  86%|########5 | 171/199 [00:00<00:00, 1812.92it/s, Materializing param=encoder.layer.10.attention.self.key.weight]
Loading weights:  86%|########6 | 172/199 [00:00<00:00, 1821.79it/s, Materializing param=encoder.layer.10.attention.self.query.bias]
Loading weights:  86%|########6 | 172/199 [00:00<00:00, 1820.88it/s, Materializing param=encoder.layer.10.attention.self.query.bias]
Loading weights:  87%|########6 | 173/199 [00:00<00:00, 1829.78it/s, Materializing param=encoder.layer.10.attention.self.query.weight]
Loading weights:  87%|########6 | 173/199 [00:00<00:00, 1828.86it/s, Materializing param=encoder.layer.10.attention.self.query.weight]
Loading weights:  87%|########7 | 174/199 [00:00<00:00, 1837.77it/s, Materializing param=encoder.layer.10.attention.self.value.bias]  
Loading weights:  87%|########7 | 174/199 [00:00<00:00, 1836.85it/s, Materializing param=encoder.layer.10.attention.self.value.bias]
Loading weights:  88%|########7 | 175/199 [00:00<00:00, 1845.75it/s, Materializing param=encoder.layer.10.attention.self.value.weight]
Loading weights:  88%|########7 | 175/199 [00:00<00:00, 1844.85it/s, Materializing param=encoder.layer.10.attention.self.value.weight]
Loading weights:  88%|########8 | 176/199 [00:00<00:00, 1853.74it/s, Materializing param=encoder.layer.10.intermediate.dense.bias]    
Loading weights:  88%|########8 | 176/199 [00:00<00:00, 1852.84it/s, Materializing param=encoder.layer.10.intermediate.dense.bias]
Loading weights:  89%|########8 | 177/199 [00:00<00:00, 1861.72it/s, Materializing param=encoder.layer.10.intermediate.dense.weight]
Loading weights:  89%|########8 | 177/199 [00:00<00:00, 1860.95it/s, Materializing param=encoder.layer.10.intermediate.dense.weight]
Loading weights:  89%|########9 | 178/199 [00:00<00:00, 1869.98it/s, Materializing param=encoder.layer.10.output.LayerNorm.bias]    
Loading weights:  89%|########9 | 178/199 [00:00<00:00, 1869.21it/s, Materializing param=encoder.layer.10.output.LayerNorm.bias]
Loading weights:  90%|########9 | 179/199 [00:00<00:00, 1878.24it/s, Materializing param=encoder.layer.10.output.LayerNorm.weight]
Loading weights:  90%|########9 | 179/199 [00:00<00:00, 1877.48it/s, Materializing param=encoder.layer.10.output.LayerNorm.weight]
Loading weights:  90%|######### | 180/199 [00:00<00:00, 1886.57it/s, Materializing param=encoder.layer.10.output.dense.bias]      
Loading weights:  90%|######### | 180/199 [00:00<00:00, 1885.80it/s, Materializing param=encoder.layer.10.output.dense.bias]
Loading weights:  91%|######### | 181/199 [00:00<00:00, 1893.71it/s, Materializing param=encoder.layer.10.output.dense.weight]
Loading weights:  91%|######### | 181/199 [00:00<00:00, 1892.54it/s, Materializing param=encoder.layer.10.output.dense.weight]
Loading weights:  91%|#########1| 182/199 [00:00<00:00, 1901.11it/s, Materializing param=encoder.layer.11.attention.output.LayerNorm.bias]
Loading weights:  91%|#########1| 182/199 [00:00<00:00, 1900.21it/s, Materializing param=encoder.layer.11.attention.output.LayerNorm.bias]
Loading weights:  92%|#########1| 183/199 [00:00<00:00, 1908.95it/s, Materializing param=encoder.layer.11.attention.output.LayerNorm.weight]
Loading weights:  92%|#########1| 183/199 [00:00<00:00, 1908.12it/s, Materializing param=encoder.layer.11.attention.output.LayerNorm.weight]
Loading weights:  92%|#########2| 184/199 [00:00<00:00, 1916.97it/s, Materializing param=encoder.layer.11.attention.output.dense.bias]      
Loading weights:  92%|#########2| 184/199 [00:00<00:00, 1680.45it/s, Materializing param=encoder.layer.11.attention.output.dense.bias]
Loading weights:  93%|#########2| 185/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.output.dense.bias]
Loading weights:  93%|#########2| 185/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.output.dense.weight]
Loading weights:  93%|#########2| 185/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.output.dense.weight]
Loading weights:  93%|#########3| 186/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.self.key.bias]      
Loading weights:  93%|#########3| 186/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.self.key.bias]
Loading weights:  94%|#########3| 187/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.self.key.weight]
Loading weights:  94%|#########3| 187/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.self.key.weight]
Loading weights:  94%|#########4| 188/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.self.query.bias]
Loading weights:  94%|#########4| 188/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.self.query.bias]
Loading weights:  95%|#########4| 189/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.self.query.weight]
Loading weights:  95%|#########4| 189/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.self.query.weight]
Loading weights:  95%|#########5| 190/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.self.value.bias]  
Loading weights:  95%|#########5| 190/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.self.value.bias]
Loading weights:  96%|#########5| 191/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.self.value.weight]
Loading weights:  96%|#########5| 191/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.attention.self.value.weight]
Loading weights:  96%|#########6| 192/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.intermediate.dense.bias]    
Loading weights:  96%|#########6| 192/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.intermediate.dense.bias]
Loading weights:  97%|#########6| 193/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.intermediate.dense.weight]
Loading weights:  97%|#########6| 193/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.intermediate.dense.weight]
Loading weights:  97%|#########7| 194/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.output.LayerNorm.bias]    
Loading weights:  97%|#########7| 194/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.output.LayerNorm.bias]
Loading weights:  98%|#########7| 195/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.output.LayerNorm.weight]
Loading weights:  98%|#########7| 195/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.output.LayerNorm.weight]
Loading weights:  98%|#########8| 196/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.output.dense.bias]      
Loading weights:  98%|#########8| 196/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.output.dense.bias]
Loading weights:  99%|#########8| 197/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.output.dense.weight]
Loading weights:  99%|#########8| 197/199 [00:00<00:00, 1684.85it/s, Materializing param=encoder.layer.11.output.dense.weight]
Loading weights:  99%|#########9| 198/199 [00:00<00:00, 1684.85it/s, Materializing param=pooler.dense.bias]                   
Loading weights:  99%|#########9| 198/199 [00:00<00:00, 1684.85it/s, Materializing param=pooler.dense.bias]
Loading weights: 100%|##########| 199/199 [00:00<00:00, 1684.85it/s, Materializing param=pooler.dense.weight]
Loading weights: 100%|##########| 199/199 [00:00<00:00, 1684.85it/s, Materializing param=pooler.dense.weight]
Loading weights: 100%|##########| 199/199 [00:00<00:00, 1586.23it/s, Materializing param=pooler.dense.weight]
[1mBertModel LOAD REPORT[0m from: intfloat/e5-small-v2
Key                     | Status     |  | 
------------------------+------------+--+-
embeddings.position_ids | UNEXPECTED |  | 

[3mNotes:
- UNEXPECTED[3m	:can be ignored when loading from different task/architecture; not ok if you expect identical arch.[0m
ERROR:root:Error cargando indice FAISS CIE-10: Directorio no encontrado: D:\Desarrollo\Proyectos_Activos\epicrisis2026\faiss_principal_jerarquico

Loading weights:   0%|          | 0/199 [00:00<?, ?it/s]
Loading weights:   1%|          | 1/199 [00:00<00:00, 23563.51it/s, Materializing param=embeddings.LayerNorm.bias]
Loading weights:   1%|          | 1/199 [00:00<00:00, 8144.28it/s, Materializing param=embeddings.LayerNorm.bias] 
Loading weights:   1%|1         | 2/199 [00:00<00:00, 7489.83it/s, Materializing param=embeddings.LayerNorm.weight]
Loading weights:   1%|1         | 2/199 [00:00<00:00, 3773.55it/s, Materializing param=embeddings.LayerNorm.weight]
Loading weights:   2%|1         | 3/199 [00:00<00:00, 3649.34it/s, Materializing param=embeddings.position_embeddings.weight]
Loading weights:   2%|1         | 3/199 [00:00<00:00, 2789.38it/s, Materializing param=embeddings.position_embeddings.weight]
Loading weights:   2%|2         | 4/199 [00:00<00:00, 2862.52it/s, Materializing param=embeddings.token_type_embeddings.weight]
Loading weights:   2%|2         | 4/199 [00:00<00:00, 2717.84it/s, Materializing param=embeddings.token_type_embeddings.weight]
Loading weights:   3%|2         | 5/199 [00:00<00:00, 3142.27it/s, Materializing param=embeddings.word_embeddings.weight]      
Loading weights:   3%|2         | 5/199 [00:00<00:00, 3046.86it/s, Materializing param=embeddings.word_embeddings.weight]
Loading weights:   3%|3         | 6/199 [00:00<00:00, 3467.80it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.bias]
Loading weights:   3%|3         | 6/199 [00:00<00:00, 3352.31it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.bias]
Loading weights:   4%|3         | 7/199 [00:00<00:00, 3295.93it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.weight]
Loading weights:   4%|3         | 7/199 [00:00<00:00, 3206.30it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.weight]
Loading weights:   4%|4         | 8/199 [00:00<00:00, 3241.03it/s, Materializing param=encoder.layer.0.attention.output.dense.bias]      
Loading weights:   4%|4         | 8/199 [00:00<00:00, 3166.41it/s, Materializing param=encoder.layer.0.attention.output.dense.bias]
Loading weights:   5%|4         | 9/199 [00:00<00:00, 3374.94it/s, Materializing param=encoder.layer.0.attention.output.dense.weight]
Loading weights:   5%|4         | 9/199 [00:00<00:00, 3300.58it/s, Materializing param=encoder.layer.0.attention.output.dense.weight]
Loading weights:   5%|5         | 10/199 [00:00<00:00, 3328.81it/s, Materializing param=encoder.layer.0.attention.self.key.bias]     
Loading weights:   5%|5         | 10/199 [00:00<00:00, 3116.12it/s, Materializing param=encoder.layer.0.attention.self.key.bias]
Loading weights:   6%|5         | 11/199 [00:00<00:00, 3233.85it/s, Materializing param=encoder.layer.0.attention.self.key.weight]
Loading weights:   6%|5         | 11/199 [00:00<00:00, 3177.50it/s, Materializing param=encoder.layer.0.attention.self.key.weight]
Loading weights:   6%|6         | 12/199 [00:00<00:00, 3297.41it/s, Materializing param=encoder.layer.0.attention.self.query.bias]
Loading weights:   6%|6         | 12/199 [00:00<00:00, 3013.69it/s, Materializing param=encoder.layer.0.attention.self.query.bias]
Loading weights:   7%|6         | 13/199 [00:00<00:00, 3138.55it/s, Materializing param=encoder.layer.0.attention.self.query.weight]
Loading weights:   7%|6         | 13/199 [00:00<00:00, 3072.06it/s, Materializing param=encoder.layer.0.attention.self.query.weight]
Loading weights:   7%|7         | 14/199 [00:00<00:00, 3140.29it/s, Materializing param=encoder.layer.0.attention.self.value.bias]  
Loading weights:   7%|7         | 14/199 [00:00<00:00, 3004.21it/s, Materializing param=encoder.layer.0.attention.self.value.bias]
Loading weights:   8%|7         | 15/199 [00:00<00:00, 3085.56it/s, Materializing param=encoder.layer.0.attention.self.value.weight]
Loading weights:   8%|7         | 15/199 [00:00<00:00, 3049.22it/s, Materializing param=encoder.layer.0.attention.self.value.weight]
Loading weights:   8%|8         | 16/199 [00:00<00:00, 3130.37it/s, Materializing param=encoder.layer.0.intermediate.dense.bias]    
Loading weights:   8%|8         | 16/199 [00:00<00:00, 3094.43it/s, Materializing param=encoder.layer.0.intermediate.dense.bias]
Loading weights:   9%|8         | 17/199 [00:00<00:00, 3204.92it/s, Materializing param=encoder.layer.0.intermediate.dense.weight]
Loading weights:   9%|8         | 17/199 [00:00<00:00, 3170.72it/s, Materializing param=encoder.layer.0.intermediate.dense.weight]
Loading weights:   9%|9         | 18/199 [00:00<00:00, 3296.40it/s, Materializing param=encoder.layer.0.output.LayerNorm.bias]    
Loading weights:   9%|9         | 18/199 [00:00<00:00, 3268.29it/s, Materializing param=encoder.layer.0.output.LayerNorm.bias]
Loading weights:  10%|9         | 19/199 [00:00<00:00, 3371.48it/s, Materializing param=encoder.layer.0.output.LayerNorm.weight]
Loading weights:  10%|9         | 19/199 [00:00<00:00, 3337.88it/s, Materializing param=encoder.layer.0.output.LayerNorm.weight]
Loading weights:  10%|#         | 20/199 [00:00<00:00, 3384.69it/s, Materializing param=encoder.layer.0.output.dense.bias]      
Loading weights:  10%|#         | 20/199 [00:00<00:00, 3329.21it/s, Materializing param=encoder.layer.0.output.dense.bias]
Loading weights:  11%|#         | 21/199 [00:00<00:00, 3399.34it/s, Materializing param=encoder.layer.0.output.dense.weight]
Loading weights:  11%|#         | 21/199 [00:00<00:00, 3313.78it/s, Materializing param=encoder.layer.0.output.dense.weight]
Loading weights:  11%|#1        | 22/199 [00:00<00:00, 3397.95it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.bias]
Loading weights:  11%|#1        | 22/199 [00:00<00:00, 3332.42it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.bias]
Loading weights:  12%|#1        | 23/199 [00:00<00:00, 3341.73it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.weight]
Loading weights:  12%|#1        | 23/199 [00:00<00:00, 3187.16it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.weight]
Loading weights:  12%|#2        | 24/199 [00:00<00:00, 3217.83it/s, Materializing param=encoder.layer.1.attention.output.dense.bias]      
Loading weights:  12%|#2        | 24/199 [00:00<00:00, 3190.60it/s, Materializing param=encoder.layer.1.attention.output.dense.bias]
Loading weights:  13%|#2        | 25/199 [00:00<00:00, 3274.34it/s, Materializing param=encoder.layer.1.attention.output.dense.weight]
Loading weights:  13%|#2        | 25/199 [00:00<00:00, 3250.19it/s, Materializing param=encoder.layer.1.attention.output.dense.weight]
Loading weights:  13%|#3        | 26/199 [00:00<00:00, 3335.02it/s, Materializing param=encoder.layer.1.attention.self.key.bias]      
Loading weights:  13%|#3        | 26/199 [00:00<00:00, 3312.13it/s, Materializing param=encoder.layer.1.attention.self.key.bias]
Loading weights:  14%|#3        | 27/199 [00:00<00:00, 3390.71it/s, Materializing param=encoder.layer.1.attention.self.key.weight]
Loading weights:  14%|#3        | 27/199 [00:00<00:00, 3368.32it/s, Materializing param=encoder.layer.1.attention.self.key.weight]
Loading weights:  14%|#4        | 28/199 [00:00<00:00, 3361.01it/s, Materializing param=encoder.layer.1.attention.self.query.bias]
Loading weights:  14%|#4        | 28/199 [00:00<00:00, 3327.30it/s, Materializing param=encoder.layer.1.attention.self.query.bias]
Loading weights:  15%|#4        | 29/199 [00:00<00:00, 3320.91it/s, Materializing param=encoder.layer.1.attention.self.query.weight]
Loading weights:  15%|#4        | 29/199 [00:00<00:00, 3276.18it/s, Materializing param=encoder.layer.1.attention.self.query.weight]
Loading weights:  15%|#5        | 30/199 [00:00<00:00, 3327.23it/s, Materializing param=encoder.layer.1.attention.self.value.bias]  
Loading weights:  15%|#5        | 30/199 [00:00<00:00, 3296.37it/s, Materializing param=encoder.layer.1.attention.self.value.bias]
Loading weights:  16%|#5        | 31/199 [00:00<00:00, 3360.21it/s, Materializing param=encoder.layer.1.attention.self.value.weight]
Loading weights:  16%|#5        | 31/199 [00:00<00:00, 3339.41it/s, Materializing param=encoder.layer.1.attention.self.value.weight]
Loading weights:  16%|#6        | 32/199 [00:00<00:00, 3408.53it/s, Materializing param=encoder.layer.1.intermediate.dense.bias]    
Loading weights:  16%|#6        | 32/199 [00:00<00:00, 3388.22it/s, Materializing param=encoder.layer.1.intermediate.dense.bias]
Loading weights:  17%|#6        | 33/199 [00:00<00:00, 3456.15it/s, Materializing param=encoder.layer.1.intermediate.dense.weight]
Loading weights:  17%|#6        | 33/199 [00:00<00:00, 3437.27it/s, Materializing param=encoder.layer.1.intermediate.dense.weight]
Loading weights:  17%|#7        | 34/199 [00:00<00:00, 3504.87it/s, Materializing param=encoder.layer.1.output.LayerNorm.bias]    
Loading weights:  17%|#7        | 34/199 [00:00<00:00, 3487.65it/s, Materializing param=encoder.layer.1.output.LayerNorm.bias]
Loading weights:  18%|#7        | 35/199 [00:00<00:00, 3554.93it/s, Materializing param=encoder.layer.1.output.LayerNorm.weight]
Loading weights:  18%|#7        | 35/199 [00:00<00:00, 3538.05it/s, Materializing param=encoder.layer.1.output.LayerNorm.weight]
Loading weights:  18%|#8        | 36/199 [00:00<00:00, 3599.75it/s, Materializing param=encoder.layer.1.output.dense.bias]      
Loading weights:  18%|#8        | 36/199 [00:00<00:00, 3580.54it/s, Materializing param=encoder.layer.1.output.dense.bias]
Loading weights:  19%|#8        | 37/199 [00:00<00:00, 3643.71it/s, Materializing param=encoder.layer.1.output.dense.weight]
Loading weights:  19%|#8        | 37/199 [00:00<00:00, 3626.76it/s, Materializing param=encoder.layer.1.output.dense.weight]
Loading weights:  19%|#9        | 38/199 [00:00<00:00, 3690.89it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.bias]
Loading weights:  19%|#9        | 38/199 [00:00<00:00, 3673.19it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.bias]
Loading weights:  20%|#9        | 39/199 [00:00<00:00, 3733.63it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.weight]
Loading weights:  20%|#9        | 39/199 [00:00<00:00, 3716.50it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.weight]
Loading weights:  20%|##        | 40/199 [00:00<00:00, 3777.63it/s, Materializing param=encoder.layer.2.attention.output.dense.bias]      
Loading weights:  20%|##        | 40/199 [00:00<00:00, 3759.85it/s, Materializing param=encoder.layer.2.attention.output.dense.bias]
Loading weights:  21%|##        | 41/199 [00:00<00:00, 3819.52it/s, Materializing param=encoder.layer.2.attention.output.dense.weight]
Loading weights:  21%|##        | 41/199 [00:00<00:00, 3803.39it/s, Materializing param=encoder.layer.2.attention.output.dense.weight]
Loading weights:  21%|##1       | 42/199 [00:00<00:00, 3714.51it/s, Materializing param=encoder.layer.2.attention.self.key.bias]      
Loading weights:  21%|##1       | 42/199 [00:00<00:00, 3691.78it/s, Materializing param=encoder.layer.2.attention.self.key.bias]
Loading weights:  22%|##1       | 43/199 [00:00<00:00, 3742.43it/s, Materializing param=encoder.layer.2.attention.self.key.weight]
Loading weights:  22%|##1       | 43/199 [00:00<00:00, 3725.57it/s, Materializing param=encoder.layer.2.attention.self.key.weight]
Loading weights:  22%|##2       | 44/199 [00:00<00:00, 3779.81it/s, Materializing param=encoder.layer.2.attention.self.query.bias]
Loading weights:  22%|##2       | 44/199 [00:00<00:00, 3764.09it/s, Materializing param=encoder.layer.2.attention.self.query.bias]
Loading weights:  23%|##2       | 45/199 [00:00<00:00, 3818.94it/s, Materializing param=encoder.layer.2.attention.self.query.weight]
Loading weights:  23%|##2       | 45/199 [00:00<00:00, 3803.71it/s, Materializing param=encoder.layer.2.attention.self.query.weight]
Loading weights:  23%|##3       | 46/199 [00:00<00:00, 3858.37it/s, Materializing param=encoder.layer.2.attention.self.value.bias]  
Loading weights:  23%|##3       | 46/199 [00:00<00:00, 3811.20it/s, Materializing param=encoder.layer.2.attention.self.value.bias]
Loading weights:  24%|##3       | 47/199 [00:00<00:00, 3850.54it/s, Materializing param=encoder.layer.2.attention.self.value.weight]
Loading weights:  24%|##3       | 47/199 [00:00<00:00, 3820.69it/s, Materializing param=encoder.layer.2.attention.self.value.weight]
Loading weights:  24%|##4       | 48/199 [00:00<00:00, 3822.12it/s, Materializing param=encoder.layer.2.intermediate.dense.bias]    
Loading weights:  24%|##4       | 48/199 [00:00<00:00, 3790.11it/s, Materializing param=encoder.layer.2.intermediate.dense.bias]
Loading weights:  25%|##4       | 49/199 [00:00<00:00, 3809.68it/s, Materializing param=encoder.layer.2.intermediate.dense.weight]
Loading weights:  25%|##4       | 49/199 [00:00<00:00, 3793.02it/s, Materializing param=encoder.layer.2.intermediate.dense.weight]
Loading weights:  25%|##5       | 50/199 [00:00<00:00, 3840.80it/s, Materializing param=encoder.layer.2.output.LayerNorm.bias]    
Loading weights:  25%|##5       | 50/199 [00:00<00:00, 3798.71it/s, Materializing param=encoder.layer.2.output.LayerNorm.bias]
Loading weights:  26%|##5       | 51/199 [00:00<00:00, 3832.47it/s, Materializing param=encoder.layer.2.output.LayerNorm.weight]
Loading weights:  26%|##5       | 51/199 [00:00<00:00, 3800.88it/s, Materializing param=encoder.layer.2.output.LayerNorm.weight]
Loading weights:  26%|##6       | 52/199 [00:00<00:00, 3760.80it/s, Materializing param=encoder.layer.2.output.dense.bias]      
Loading weights:  26%|##6       | 52/199 [00:00<00:00, 3715.88it/s, Materializing param=encoder.layer.2.output.dense.bias]
Loading weights:  27%|##6       | 53/199 [00:00<00:00, 3747.25it/s, Materializing param=encoder.layer.2.output.dense.weight]
Loading weights:  27%|##6       | 53/199 [00:00<00:00, 3710.16it/s, Materializing param=encoder.layer.2.output.dense.weight]
Loading weights:  27%|##7       | 54/199 [00:00<00:00, 3704.49it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.bias]
Loading weights:  27%|##7       | 54/199 [00:00<00:00, 3675.75it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.bias]
Loading weights:  28%|##7       | 55/199 [00:00<00:00, 3664.66it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.weight]
Loading weights:  28%|##7       | 55/199 [00:00<00:00, 3644.28it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.weight]
Loading weights:  28%|##8       | 56/199 [00:00<00:00, 3642.24it/s, Materializing param=encoder.layer.3.attention.output.dense.bias]      
Loading weights:  28%|##8       | 56/199 [00:00<00:00, 3613.94it/s, Materializing param=encoder.layer.3.attention.output.dense.bias]
Loading weights:  29%|##8       | 57/199 [00:00<00:00, 3642.66it/s, Materializing param=encoder.layer.3.attention.output.dense.weight]
Loading weights:  29%|##8       | 57/199 [00:00<00:00, 3629.12it/s, Materializing param=encoder.layer.3.attention.output.dense.weight]
Loading weights:  29%|##9       | 58/199 [00:00<00:00, 3667.57it/s, Materializing param=encoder.layer.3.attention.self.key.bias]      
Loading weights:  29%|##9       | 58/199 [00:00<00:00, 3655.61it/s, Materializing param=encoder.layer.3.attention.self.key.bias]
Loading weights:  30%|##9       | 59/199 [00:00<00:00, 3695.20it/s, Materializing param=encoder.layer.3.attention.self.key.weight]
Loading weights:  30%|##9       | 59/199 [00:00<00:00, 3683.54it/s, Materializing param=encoder.layer.3.attention.self.key.weight]
Loading weights:  30%|###       | 60/199 [00:00<00:00, 3723.47it/s, Materializing param=encoder.layer.3.attention.self.query.bias]
Loading weights:  30%|###       | 60/199 [00:00<00:00, 3711.61it/s, Materializing param=encoder.layer.3.attention.self.query.bias]
Loading weights:  31%|###       | 61/199 [00:00<00:00, 3750.57it/s, Materializing param=encoder.layer.3.attention.self.query.weight]
Loading weights:  31%|###       | 61/199 [00:00<00:00, 3738.89it/s, Materializing param=encoder.layer.3.attention.self.query.weight]
Loading weights:  31%|###1      | 62/199 [00:00<00:00, 3777.44it/s, Materializing param=encoder.layer.3.attention.self.value.bias]  
Loading weights:  31%|###1      | 62/199 [00:00<00:00, 3765.90it/s, Materializing param=encoder.layer.3.attention.self.value.bias]
Loading weights:  32%|###1      | 63/199 [00:00<00:00, 3804.33it/s, Materializing param=encoder.layer.3.attention.self.value.weight]
Loading weights:  32%|###1      | 63/199 [00:00<00:00, 3792.97it/s, Materializing param=encoder.layer.3.attention.self.value.weight]
Loading weights:  32%|###2      | 64/199 [00:00<00:00, 3758.13it/s, Materializing param=encoder.layer.3.intermediate.dense.bias]    
Loading weights:  32%|###2      | 64/199 [00:00<00:00, 3742.62it/s, Materializing param=encoder.layer.3.intermediate.dense.bias]
Loading weights:  33%|###2      | 65/199 [00:00<00:00, 3751.67it/s, Materializing param=encoder.layer.3.intermediate.dense.weight]
Loading weights:  33%|###2      | 65/199 [00:00<00:00, 3703.96it/s, Materializing param=encoder.layer.3.intermediate.dense.weight]
Loading weights:  33%|###3      | 66/199 [00:00<00:00, 3712.07it/s, Materializing param=encoder.layer.3.output.LayerNorm.bias]    
Loading weights:  33%|###3      | 66/199 [00:00<00:00, 3699.47it/s, Materializing param=encoder.layer.3.output.LayerNorm.bias]
Loading weights:  34%|###3      | 67/199 [00:00<00:00, 3728.07it/s, Materializing param=encoder.layer.3.output.LayerNorm.weight]
Loading weights:  34%|###3      | 67/199 [00:00<00:00, 3717.27it/s, Materializing param=encoder.layer.3.output.LayerNorm.weight]
Loading weights:  34%|###4      | 68/199 [00:00<00:00, 3752.26it/s, Materializing param=encoder.layer.3.output.dense.bias]      
Loading weights:  34%|###4      | 68/199 [00:00<00:00, 3742.16it/s, Materializing param=encoder.layer.3.output.dense.bias]
Loading weights:  35%|###4      | 69/199 [00:00<00:00, 3777.72it/s, Materializing param=encoder.layer.3.output.dense.weight]
Loading weights:  35%|###4      | 69/199 [00:00<00:00, 3767.88it/s, Materializing param=encoder.layer.3.output.dense.weight]
Loading weights:  35%|###5      | 70/199 [00:00<00:00, 3803.72it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.bias]
Loading weights:  35%|###5      | 70/199 [00:00<00:00, 3793.89it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.bias]
Loading weights:  36%|###5      | 71/199 [00:00<00:00, 3828.00it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.weight]
Loading weights:  36%|###5      | 71/199 [00:00<00:00, 3818.28it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.weight]
Loading weights:  36%|###6      | 72/199 [00:00<00:00, 3822.03it/s, Materializing param=encoder.layer.4.attention.output.dense.bias]      
Loading weights:  36%|###6      | 72/199 [00:00<00:00, 3800.53it/s, Materializing param=encoder.layer.4.attention.output.dense.bias]
Loading weights:  37%|###6      | 73/199 [00:00<00:00, 3820.52it/s, Materializing param=encoder.layer.4.attention.output.dense.weight]
Loading weights:  37%|###6      | 73/199 [00:00<00:00, 3752.21it/s, Materializing param=encoder.layer.4.attention.output.dense.weight]
Loading weights:  37%|###7      | 74/199 [00:00<00:00, 3775.34it/s, Materializing param=encoder.layer.4.attention.self.key.bias]      
Loading weights:  37%|###7      | 74/199 [00:00<00:00, 3757.11it/s, Materializing param=encoder.layer.4.attention.self.key.bias]
Loading weights:  38%|###7      | 75/199 [00:00<00:00, 3783.15it/s, Materializing param=encoder.layer.4.attention.self.key.weight]
Loading weights:  38%|###7      | 75/199 [00:00<00:00, 3772.99it/s, Materializing param=encoder.layer.4.attention.self.key.weight]
Loading weights:  38%|###8      | 76/199 [00:00<00:00, 3804.18it/s, Materializing param=encoder.layer.4.attention.self.query.bias]
Loading weights:  38%|###8      | 76/199 [00:00<00:00, 3794.71it/s, Materializing param=encoder.layer.4.attention.self.query.bias]
Loading weights:  39%|###8      | 77/199 [00:00<00:00, 3826.47it/s, Materializing param=encoder.layer.4.attention.self.query.weight]
Loading weights:  39%|###8      | 77/199 [00:00<00:00, 3817.10it/s, Materializing param=encoder.layer.4.attention.self.query.weight]
Loading weights:  39%|###9      | 78/199 [00:00<00:00, 3849.16it/s, Materializing param=encoder.layer.4.attention.self.value.bias]  
Loading weights:  39%|###9      | 78/199 [00:00<00:00, 3839.36it/s, Materializing param=encoder.layer.4.attention.self.value.bias]
Loading weights:  40%|###9      | 79/199 [00:00<00:00, 3834.58it/s, Materializing param=encoder.layer.4.attention.self.value.weight]
Loading weights:  40%|###9      | 79/199 [00:00<00:00, 3823.34it/s, Materializing param=encoder.layer.4.attention.self.value.weight]
Loading weights:  40%|####      | 80/199 [00:00<00:00, 3852.80it/s, Materializing param=encoder.layer.4.intermediate.dense.bias]    
Loading weights:  40%|####      | 80/199 [00:00<00:00, 3843.67it/s, Materializing param=encoder.layer.4.intermediate.dense.bias]
Loading weights:  41%|####      | 81/199 [00:00<00:00, 3764.21it/s, Materializing param=encoder.layer.4.intermediate.dense.weight]
Loading weights:  41%|####      | 81/199 [00:00<00:00, 3707.92it/s, Materializing param=encoder.layer.4.intermediate.dense.weight]
Loading weights:  41%|####1     | 82/199 [00:00<00:00, 3729.93it/s, Materializing param=encoder.layer.4.output.LayerNorm.bias]    
Loading weights:  41%|####1     | 82/199 [00:00<00:00, 3720.93it/s, Materializing param=encoder.layer.4.output.LayerNorm.bias]
Loading weights:  42%|####1     | 83/199 [00:00<00:00, 3731.15it/s, Materializing param=encoder.layer.4.output.LayerNorm.weight]
Loading weights:  42%|####1     | 83/199 [00:00<00:00, 3703.36it/s, Materializing param=encoder.layer.4.output.LayerNorm.weight]
Loading weights:  42%|####2     | 84/199 [00:00<00:00, 3713.53it/s, Materializing param=encoder.layer.4.output.dense.bias]      
Loading weights:  42%|####2     | 84/199 [00:00<00:00, 3704.55it/s, Materializing param=encoder.layer.4.output.dense.bias]
Loading weights:  43%|####2     | 85/199 [00:00<00:00, 3732.33it/s, Materializing param=encoder.layer.4.output.dense.weight]
Loading weights:  43%|####2     | 85/199 [00:00<00:00, 3724.53it/s, Materializing param=encoder.layer.4.output.dense.weight]
Loading weights:  43%|####3     | 86/199 [00:00<00:00, 3753.53it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.bias]
Loading weights:  43%|####3     | 86/199 [00:00<00:00, 3746.00it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.bias]
Loading weights:  44%|####3     | 87/199 [00:00<00:00, 3707.21it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.weight]
Loading weights:  44%|####3     | 87/199 [00:00<00:00, 3698.76it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.weight]
Loading weights:  44%|####4     | 88/199 [00:00<00:00, 3726.28it/s, Materializing param=encoder.layer.5.attention.output.dense.bias]      
Loading weights:  44%|####4     | 88/199 [00:00<00:00, 3719.37it/s, Materializing param=encoder.layer.5.attention.output.dense.bias]
Loading weights:  45%|####4     | 89/199 [00:00<00:00, 3747.77it/s, Materializing param=encoder.layer.5.attention.output.dense.weight]
Loading weights:  45%|####4     | 89/199 [00:00<00:00, 3741.20it/s, Materializing param=encoder.layer.5.attention.output.dense.weight]
Loading weights:  45%|####5     | 90/199 [00:00<00:00, 3769.71it/s, Materializing param=encoder.layer.5.attention.self.key.bias]      
Loading weights:  45%|####5     | 90/199 [00:00<00:00, 3763.10it/s, Materializing param=encoder.layer.5.attention.self.key.bias]
Loading weights:  46%|####5     | 91/199 [00:00<00:00, 3790.89it/s, Materializing param=encoder.layer.5.attention.self.key.weight]
Loading weights:  46%|####5     | 91/199 [00:00<00:00, 3784.23it/s, Materializing param=encoder.layer.5.attention.self.key.weight]
Loading weights:  46%|####6     | 92/199 [00:00<00:00, 3812.44it/s, Materializing param=encoder.layer.5.attention.self.query.bias]
Loading weights:  46%|####6     | 92/199 [00:00<00:00, 3805.93it/s, Materializing param=encoder.layer.5.attention.self.query.bias]
Loading weights:  47%|####6     | 93/199 [00:00<00:00, 3833.84it/s, Materializing param=encoder.layer.5.attention.self.query.weight]
Loading weights:  47%|####6     | 93/199 [00:00<00:00, 3827.30it/s, Materializing param=encoder.layer.5.attention.self.query.weight]
Loading weights:  47%|####7     | 94/199 [00:00<00:00, 3854.72it/s, Materializing param=encoder.layer.5.attention.self.value.bias]  
Loading weights:  47%|####7     | 94/199 [00:00<00:00, 3847.84it/s, Materializing param=encoder.layer.5.attention.self.value.bias]
Loading weights:  48%|####7     | 95/199 [00:00<00:00, 3868.76it/s, Materializing param=encoder.layer.5.attention.self.value.weight]
Loading weights:  48%|####7     | 95/199 [00:00<00:00, 3859.76it/s, Materializing param=encoder.layer.5.attention.self.value.weight]
Loading weights:  48%|####8     | 96/199 [00:00<00:00, 3850.60it/s, Materializing param=encoder.layer.5.intermediate.dense.bias]    
Loading weights:  48%|####8     | 96/199 [00:00<00:00, 3841.60it/s, Materializing param=encoder.layer.5.intermediate.dense.bias]
Loading weights:  49%|####8     | 97/199 [00:00<00:00, 3865.57it/s, Materializing param=encoder.layer.5.intermediate.dense.weight]
Loading weights:  49%|####8     | 97/199 [00:00<00:00, 3858.39it/s, Materializing param=encoder.layer.5.intermediate.dense.weight]
Loading weights:  49%|####9     | 98/199 [00:00<00:00, 3873.26it/s, Materializing param=encoder.layer.5.output.LayerNorm.bias]    
Loading weights:  49%|####9     | 98/199 [00:00<00:00, 3864.19it/s, Materializing param=encoder.layer.5.output.LayerNorm.bias]
Loading weights:  50%|####9     | 99/199 [00:00<00:00, 3880.57it/s, Materializing param=encoder.layer.5.output.LayerNorm.weight]
Loading weights:  50%|####9     | 99/199 [00:00<00:00, 3871.59it/s, Materializing param=encoder.layer.5.output.LayerNorm.weight]
Loading weights:  50%|#####     | 100/199 [00:00<00:00, 3894.87it/s, Materializing param=encoder.layer.5.output.dense.bias]     
Loading weights:  50%|#####     | 100/199 [00:00<00:00, 3887.47it/s, Materializing param=encoder.layer.5.output.dense.bias]
Loading weights:  51%|#####     | 101/199 [00:00<00:00, 3908.19it/s, Materializing param=encoder.layer.5.output.dense.weight]
Loading weights:  51%|#####     | 101/199 [00:00<00:00, 3900.60it/s, Materializing param=encoder.layer.5.output.dense.weight]
Loading weights:  51%|#####1    | 102/199 [00:00<00:00, 3878.33it/s, Materializing param=encoder.layer.6.attention.output.LayerNorm.bias]
Loading weights:  51%|#####1    | 102/199 [00:00<00:00, 3869.67it/s, Materializing param=encoder.layer.6.attention.output.LayerNorm.bias]
Loading weights:  52%|#####1    | 103/199 [00:00<00:00, 3858.12it/s, Materializing param=encoder.layer.6.attention.output.LayerNorm.weight]
Loading weights:  52%|#####1    | 103/199 [00:00<00:00, 3850.08it/s, Materializing param=encoder.layer.6.attention.output.LayerNorm.weight]
Loading weights:  52%|#####2    | 104/199 [00:00<00:00, 3872.99it/s, Materializing param=encoder.layer.6.attention.output.dense.bias]      
Loading weights:  52%|#####2    | 104/199 [00:00<00:00, 3866.23it/s, Materializing param=encoder.layer.6.attention.output.dense.bias]
Loading weights:  53%|#####2    | 105/199 [00:00<00:00, 3853.68it/s, Materializing param=encoder.layer.6.attention.output.dense.weight]
Loading weights:  53%|#####2    | 105/199 [00:00<00:00, 3845.83it/s, Materializing param=encoder.layer.6.attention.output.dense.weight]
Loading weights:  53%|#####3    | 106/199 [00:00<00:00, 3861.32it/s, Materializing param=encoder.layer.6.attention.self.key.bias]      
Loading weights:  53%|#####3    | 106/199 [00:00<00:00, 3854.06it/s, Materializing param=encoder.layer.6.attention.self.key.bias]
Loading weights:  54%|#####3    | 107/199 [00:00<00:00, 3877.04it/s, Materializing param=encoder.layer.6.attention.self.key.weight]
Loading weights:  54%|#####3    | 107/199 [00:00<00:00, 3870.92it/s, Materializing param=encoder.layer.6.attention.self.key.weight]
Loading weights:  54%|#####4    | 108/199 [00:00<00:00, 3894.20it/s, Materializing param=encoder.layer.6.attention.self.query.bias]
Loading weights:  54%|#####4    | 108/199 [00:00<00:00, 3887.71it/s, Materializing param=encoder.layer.6.attention.self.query.bias]
Loading weights:  55%|#####4    | 109/199 [00:00<00:00, 3868.50it/s, Materializing param=encoder.layer.6.attention.self.query.weight]
Loading weights:  55%|#####4    | 109/199 [00:00<00:00, 3859.48it/s, Materializing param=encoder.layer.6.attention.self.query.weight]
Loading weights:  55%|#####5    | 110/199 [00:00<00:00, 3879.86it/s, Materializing param=encoder.layer.6.attention.self.value.bias]  
Loading weights:  55%|#####5    | 110/199 [00:00<00:00, 3872.89it/s, Materializing param=encoder.layer.6.attention.self.value.bias]
Loading weights:  56%|#####5    | 111/199 [00:00<00:00, 3883.58it/s, Materializing param=encoder.layer.6.attention.self.value.weight]
Loading weights:  56%|#####5    | 111/199 [00:00<00:00, 3875.37it/s, Materializing param=encoder.layer.6.attention.self.value.weight]
Loading weights:  56%|#####6    | 112/199 [00:00<00:00, 3868.84it/s, Materializing param=encoder.layer.6.intermediate.dense.bias]    
Loading weights:  56%|#####6    | 112/199 [00:00<00:00, 3861.14it/s, Materializing param=encoder.layer.6.intermediate.dense.bias]
Loading weights:  57%|#####6    | 113/199 [00:00<00:00, 3879.64it/s, Materializing param=encoder.layer.6.intermediate.dense.weight]
Loading weights:  57%|#####6    | 113/199 [00:00<00:00, 3872.83it/s, Materializing param=encoder.layer.6.intermediate.dense.weight]
Loading weights:  57%|#####7    | 114/199 [00:00<00:00, 3890.19it/s, Materializing param=encoder.layer.6.output.LayerNorm.bias]    
Loading weights:  57%|#####7    | 114/199 [00:00<00:00, 3883.55it/s, Materializing param=encoder.layer.6.output.LayerNorm.bias]
Loading weights:  58%|#####7    | 115/199 [00:00<00:00, 3905.06it/s, Materializing param=encoder.layer.6.output.LayerNorm.weight]
Loading weights:  58%|#####7    | 115/199 [00:00<00:00, 3899.12it/s, Materializing param=encoder.layer.6.output.LayerNorm.weight]
Loading weights:  58%|#####8    | 116/199 [00:00<00:00, 3921.02it/s, Materializing param=encoder.layer.6.output.dense.bias]      
Loading weights:  58%|#####8    | 116/199 [00:00<00:00, 3915.08it/s, Materializing param=encoder.layer.6.output.dense.bias]
Loading weights:  59%|#####8    | 117/199 [00:00<00:00, 3873.19it/s, Materializing param=encoder.layer.6.output.dense.weight]
Loading weights:  59%|#####8    | 117/199 [00:00<00:00, 3865.81it/s, Materializing param=encoder.layer.6.output.dense.weight]
Loading weights:  59%|#####9    | 118/199 [00:00<00:00, 3886.18it/s, Materializing param=encoder.layer.7.attention.output.LayerNorm.bias]
Loading weights:  59%|#####9    | 118/199 [00:00<00:00, 3878.87it/s, Materializing param=encoder.layer.7.attention.output.LayerNorm.bias]
Loading weights:  60%|#####9    | 119/199 [00:00<00:00, 3894.65it/s, Materializing param=encoder.layer.7.attention.output.LayerNorm.weight]
Loading weights:  60%|#####9    | 119/199 [00:00<00:00, 3887.24it/s, Materializing param=encoder.layer.7.attention.output.LayerNorm.weight]
Loading weights:  60%|######    | 120/199 [00:00<00:00, 3897.51it/s, Materializing param=encoder.layer.7.attention.output.dense.bias]      
Loading weights:  60%|######    | 120/199 [00:00<00:00, 3890.46it/s, Materializing param=encoder.layer.7.attention.output.dense.bias]
Loading weights:  61%|######    | 121/199 [00:00<00:00, 2752.84it/s, Materializing param=encoder.layer.7.attention.output.dense.weight]
Loading weights:  61%|######    | 121/199 [00:00<00:00, 2746.73it/s, Materializing param=encoder.layer.7.attention.output.dense.weight]
Loading weights:  61%|######1   | 122/199 [00:00<00:00, 2763.55it/s, Materializing param=encoder.layer.7.attention.self.key.bias]      
Loading weights:  61%|######1   | 122/199 [00:00<00:00, 2760.75it/s, Materializing param=encoder.layer.7.attention.self.key.bias]
Loading weights:  62%|######1   | 123/199 [00:00<00:00, 2778.28it/s, Materializing param=encoder.layer.7.attention.self.key.weight]
Loading weights:  62%|######1   | 123/199 [00:00<00:00, 2775.71it/s, Materializing param=encoder.layer.7.attention.self.key.weight]
Loading weights:  62%|######2   | 124/199 [00:00<00:00, 2793.47it/s, Materializing param=encoder.layer.7.attention.self.query.bias]
Loading weights:  62%|######2   | 124/199 [00:00<00:00, 2790.91it/s, Materializing param=encoder.layer.7.attention.self.query.bias]
Loading weights:  63%|######2   | 125/199 [00:00<00:00, 2808.55it/s, Materializing param=encoder.layer.7.attention.self.query.weight]
Loading weights:  63%|######2   | 125/199 [00:00<00:00, 2806.04it/s, Materializing param=encoder.layer.7.attention.self.query.weight]
Loading weights:  63%|######3   | 126/199 [00:00<00:00, 2823.80it/s, Materializing param=encoder.layer.7.attention.self.value.bias]  
Loading weights:  63%|######3   | 126/199 [00:00<00:00, 2821.18it/s, Materializing param=encoder.layer.7.attention.self.value.bias]
Loading weights:  64%|######3   | 127/199 [00:00<00:00, 2838.84it/s, Materializing param=encoder.layer.7.attention.self.value.weight]
Loading weights:  64%|######3   | 127/199 [00:00<00:00, 2836.34it/s, Materializing param=encoder.layer.7.attention.self.value.weight]
Loading weights:  64%|######4   | 128/199 [00:00<00:00, 2854.10it/s, Materializing param=encoder.layer.7.intermediate.dense.bias]    
Loading weights:  64%|######4   | 128/199 [00:00<00:00, 2851.59it/s, Materializing param=encoder.layer.7.intermediate.dense.bias]
Loading weights:  65%|######4   | 129/199 [00:00<00:00, 2869.12it/s, Materializing param=encoder.layer.7.intermediate.dense.weight]
Loading weights:  65%|######4   | 129/199 [00:00<00:00, 2866.66it/s, Materializing param=encoder.layer.7.intermediate.dense.weight]
Loading weights:  65%|######5   | 130/199 [00:00<00:00, 2884.44it/s, Materializing param=encoder.layer.7.output.LayerNorm.bias]    
Loading weights:  65%|######5   | 130/199 [00:00<00:00, 2882.01it/s, Materializing param=encoder.layer.7.output.LayerNorm.bias]
Loading weights:  66%|######5   | 131/199 [00:00<00:00, 2899.31it/s, Materializing param=encoder.layer.7.output.LayerNorm.weight]
Loading weights:  66%|######5   | 131/199 [00:00<00:00, 2896.86it/s, Materializing param=encoder.layer.7.output.LayerNorm.weight]
Loading weights:  66%|######6   | 132/199 [00:00<00:00, 2914.47it/s, Materializing param=encoder.layer.7.output.dense.bias]      
Loading weights:  66%|######6   | 132/199 [00:00<00:00, 2912.05it/s, Materializing param=encoder.layer.7.output.dense.bias]
Loading weights:  67%|######6   | 133/199 [00:00<00:00, 2929.57it/s, Materializing param=encoder.layer.7.output.dense.weight]
Loading weights:  67%|######6   | 133/199 [00:00<00:00, 2927.12it/s, Materializing param=encoder.layer.7.output.dense.weight]
Loading weights:  67%|######7   | 134/199 [00:00<00:00, 2943.88it/s, Materializing param=encoder.layer.8.attention.output.LayerNorm.bias]
Loading weights:  67%|######7   | 134/199 [00:00<00:00, 2941.28it/s, Materializing param=encoder.layer.8.attention.output.LayerNorm.bias]
Loading weights:  68%|######7   | 135/199 [00:00<00:00, 2958.26it/s, Materializing param=encoder.layer.8.attention.output.LayerNorm.weight]
Loading weights:  68%|######7   | 135/199 [00:00<00:00, 2955.71it/s, Materializing param=encoder.layer.8.attention.output.LayerNorm.weight]
Loading weights:  68%|######8   | 136/199 [00:00<00:00, 2972.92it/s, Materializing param=encoder.layer.8.attention.output.dense.bias]      
Loading weights:  68%|######8   | 136/199 [00:00<00:00, 2318.14it/s, Materializing param=encoder.layer.8.attention.output.dense.bias]
Loading weights:  69%|######8   | 137/199 [00:00<00:00, 2324.89it/s, Materializing param=encoder.layer.8.attention.output.dense.weight]
Loading weights:  69%|######8   | 137/199 [00:00<00:00, 2322.60it/s, Materializing param=encoder.layer.8.attention.output.dense.weight]
Loading weights:  69%|######9   | 138/199 [00:00<00:00, 2336.01it/s, Materializing param=encoder.layer.8.attention.self.key.bias]      
Loading weights:  69%|######9   | 138/199 [00:00<00:00, 2334.35it/s, Materializing param=encoder.layer.8.attention.self.key.bias]
Loading weights:  70%|######9   | 139/199 [00:00<00:00, 2348.09it/s, Materializing param=encoder.layer.8.attention.self.key.weight]
Loading weights:  70%|######9   | 139/199 [00:00<00:00, 2346.53it/s, Materializing param=encoder.layer.8.attention.self.key.weight]
Loading weights:  70%|#######   | 140/199 [00:00<00:00, 2360.37it/s, Materializing param=encoder.layer.8.attention.self.query.bias]
Loading weights:  70%|#######   | 140/199 [00:00<00:00, 2358.40it/s, Materializing param=encoder.layer.8.attention.self.query.bias]
Loading weights:  71%|#######   | 141/199 [00:00<00:00, 2372.27it/s, Materializing param=encoder.layer.8.attention.self.query.weight]
Loading weights:  71%|#######   | 141/199 [00:00<00:00, 2370.72it/s, Materializing param=encoder.layer.8.attention.self.query.weight]
Loading weights:  71%|#######1  | 142/199 [00:00<00:00, 2384.66it/s, Materializing param=encoder.layer.8.attention.self.value.bias]  
Loading weights:  71%|#######1  | 142/199 [00:00<00:00, 2383.13it/s, Materializing param=encoder.layer.8.attention.self.value.bias]
Loading weights:  72%|#######1  | 143/199 [00:00<00:00, 2397.04it/s, Materializing param=encoder.layer.8.attention.self.value.weight]
Loading weights:  72%|#######1  | 143/199 [00:00<00:00, 2395.45it/s, Materializing param=encoder.layer.8.attention.self.value.weight]
Loading weights:  72%|#######2  | 144/199 [00:00<00:00, 2409.22it/s, Materializing param=encoder.layer.8.intermediate.dense.bias]    
Loading weights:  72%|#######2  | 144/199 [00:00<00:00, 2407.66it/s, Materializing param=encoder.layer.8.intermediate.dense.bias]
Loading weights:  73%|#######2  | 145/199 [00:00<00:00, 2421.44it/s, Materializing param=encoder.layer.8.intermediate.dense.weight]
Loading weights:  73%|#######2  | 145/199 [00:00<00:00, 2419.92it/s, Materializing param=encoder.layer.8.intermediate.dense.weight]
Loading weights:  73%|#######3  | 146/199 [00:00<00:00, 2433.37it/s, Materializing param=encoder.layer.8.output.LayerNorm.bias]    
Loading weights:  73%|#######3  | 146/199 [00:00<00:00, 2431.65it/s, Materializing param=encoder.layer.8.output.LayerNorm.bias]
Loading weights:  74%|#######3  | 147/199 [00:00<00:00, 2445.12it/s, Materializing param=encoder.layer.8.output.LayerNorm.weight]
Loading weights:  74%|#######3  | 147/199 [00:00<00:00, 2443.45it/s, Materializing param=encoder.layer.8.output.LayerNorm.weight]
Loading weights:  74%|#######4  | 148/199 [00:00<00:00, 2457.04it/s, Materializing param=encoder.layer.8.output.dense.bias]      
Loading weights:  74%|#######4  | 148/199 [00:00<00:00, 2455.47it/s, Materializing param=encoder.layer.8.output.dense.bias]
Loading weights:  75%|#######4  | 149/199 [00:00<00:00, 2468.33it/s, Materializing param=encoder.layer.8.output.dense.weight]
Loading weights:  75%|#######4  | 149/199 [00:00<00:00, 2466.67it/s, Materializing param=encoder.layer.8.output.dense.weight]
Loading weights:  75%|#######5  | 150/199 [00:00<00:00, 2480.27it/s, Materializing param=encoder.layer.9.attention.output.LayerNorm.bias]
Loading weights:  75%|#######5  | 150/199 [00:00<00:00, 2478.69it/s, Materializing param=encoder.layer.9.attention.output.LayerNorm.bias]
Loading weights:  76%|#######5  | 151/199 [00:00<00:00, 2492.06it/s, Materializing param=encoder.layer.9.attention.output.LayerNorm.weight]
Loading weights:  76%|#######5  | 151/199 [00:00<00:00, 2490.46it/s, Materializing param=encoder.layer.9.attention.output.LayerNorm.weight]
Loading weights:  76%|#######6  | 152/199 [00:00<00:00, 2004.70it/s, Materializing param=encoder.layer.9.attention.output.dense.bias]      
Loading weights:  76%|#######6  | 152/199 [00:00<00:00, 2002.13it/s, Materializing param=encoder.layer.9.attention.output.dense.bias]
Loading weights:  77%|#######6  | 153/199 [00:00<00:00, 2012.74it/s, Materializing param=encoder.layer.9.attention.output.dense.weight]
Loading weights:  77%|#######6  | 153/199 [00:00<00:00, 2011.59it/s, Materializing param=encoder.layer.9.attention.output.dense.weight]
Loading weights:  77%|#######7  | 154/199 [00:00<00:00, 2022.67it/s, Materializing param=encoder.layer.9.attention.self.key.bias]      
Loading weights:  77%|#######7  | 154/199 [00:00<00:00, 2021.58it/s, Materializing param=encoder.layer.9.attention.self.key.bias]
Loading weights:  78%|#######7  | 155/199 [00:00<00:00, 2032.59it/s, Materializing param=encoder.layer.9.attention.self.key.weight]
Loading weights:  78%|#######7  | 155/199 [00:00<00:00, 2031.53it/s, Materializing param=encoder.layer.9.attention.self.key.weight]
Loading weights:  78%|#######8  | 156/199 [00:00<00:00, 2042.67it/s, Materializing param=encoder.layer.9.attention.self.query.bias]
Loading weights:  78%|#######8  | 156/199 [00:00<00:00, 2041.62it/s, Materializing param=encoder.layer.9.attention.self.query.bias]
Loading weights:  79%|#######8  | 157/199 [00:00<00:00, 2052.73it/s, Materializing param=encoder.layer.9.attention.self.query.weight]
Loading weights:  79%|#######8  | 157/199 [00:00<00:00, 2051.64it/s, Materializing param=encoder.layer.9.attention.self.query.weight]
Loading weights:  79%|#######9  | 158/199 [00:00<00:00, 2062.71it/s, Materializing param=encoder.layer.9.attention.self.value.bias]  
Loading weights:  79%|#######9  | 158/199 [00:00<00:00, 2061.66it/s, Materializing param=encoder.layer.9.attention.self.value.bias]
Loading weights:  80%|#######9  | 159/199 [00:00<00:00, 2072.75it/s, Materializing param=encoder.layer.9.attention.self.value.weight]
Loading weights:  80%|#######9  | 159/199 [00:00<00:00, 2071.70it/s, Materializing param=encoder.layer.9.attention.self.value.weight]
Loading weights:  80%|########  | 160/199 [00:00<00:00, 2082.81it/s, Materializing param=encoder.layer.9.intermediate.dense.bias]    
Loading weights:  80%|########  | 160/199 [00:00<00:00, 2081.76it/s, Materializing param=encoder.layer.9.intermediate.dense.bias]
Loading weights:  81%|########  | 161/199 [00:00<00:00, 2092.84it/s, Materializing param=encoder.layer.9.intermediate.dense.weight]
Loading weights:  81%|########  | 161/199 [00:00<00:00, 2091.79it/s, Materializing param=encoder.layer.9.intermediate.dense.weight]
Loading weights:  81%|########1 | 162/199 [00:00<00:00, 2102.86it/s, Materializing param=encoder.layer.9.output.LayerNorm.bias]    
Loading weights:  81%|########1 | 162/199 [00:00<00:00, 2101.81it/s, Materializing param=encoder.layer.9.output.LayerNorm.bias]
Loading weights:  82%|########1 | 163/199 [00:00<00:00, 2112.76it/s, Materializing param=encoder.layer.9.output.LayerNorm.weight]
Loading weights:  82%|########1 | 163/199 [00:00<00:00, 2111.71it/s, Materializing param=encoder.layer.9.output.LayerNorm.weight]
Loading weights:  82%|########2 | 164/199 [00:00<00:00, 2122.75it/s, Materializing param=encoder.layer.9.output.dense.bias]      
Loading weights:  82%|########2 | 164/199 [00:00<00:00, 2121.71it/s, Materializing param=encoder.layer.9.output.dense.bias]
Loading weights:  83%|########2 | 165/199 [00:00<00:00, 2132.41it/s, Materializing param=encoder.layer.9.output.dense.weight]
Loading weights:  83%|########2 | 165/199 [00:00<00:00, 2131.30it/s, Materializing param=encoder.layer.9.output.dense.weight]
Loading weights:  83%|########3 | 166/199 [00:00<00:00, 2142.31it/s, Materializing param=encoder.layer.10.attention.output.LayerNorm.bias]
Loading weights:  83%|########3 | 166/199 [00:00<00:00, 2141.24it/s, Materializing param=encoder.layer.10.attention.output.LayerNorm.bias]
Loading weights:  84%|########3 | 167/199 [00:00<00:00, 2152.03it/s, Materializing param=encoder.layer.10.attention.output.LayerNorm.weight]
Loading weights:  84%|########3 | 167/199 [00:00<00:00, 1837.61it/s, Materializing param=encoder.layer.10.attention.output.LayerNorm.weight]
Loading weights:  84%|########4 | 168/199 [00:00<00:00, 1843.27it/s, Materializing param=encoder.layer.10.attention.output.dense.bias]      
Loading weights:  84%|########4 | 168/199 [00:00<00:00, 1842.18it/s, Materializing param=encoder.layer.10.attention.output.dense.bias]
Loading weights:  85%|########4 | 169/199 [00:00<00:00, 1851.35it/s, Materializing param=encoder.layer.10.attention.output.dense.weight]
Loading weights:  85%|########4 | 169/199 [00:00<00:00, 1850.49it/s, Materializing param=encoder.layer.10.attention.output.dense.weight]
Loading weights:  85%|########5 | 170/199 [00:00<00:00, 1859.82it/s, Materializing param=encoder.layer.10.attention.self.key.bias]      
Loading weights:  85%|########5 | 170/199 [00:00<00:00, 1858.99it/s, Materializing param=encoder.layer.10.attention.self.key.bias]
Loading weights:  86%|########5 | 171/199 [00:00<00:00, 1868.35it/s, Materializing param=encoder.layer.10.attention.self.key.weight]
Loading weights:  86%|########5 | 171/199 [00:00<00:00, 1867.55it/s, Materializing param=encoder.layer.10.attention.self.key.weight]
Loading weights:  86%|########6 | 172/199 [00:00<00:00, 1876.83it/s, Materializing param=encoder.layer.10.attention.self.query.bias]
Loading weights:  86%|########6 | 172/199 [00:00<00:00, 1875.99it/s, Materializing param=encoder.layer.10.attention.self.query.bias]
Loading weights:  87%|########6 | 173/199 [00:00<00:00, 1885.35it/s, Materializing param=encoder.layer.10.attention.self.query.weight]
Loading weights:  87%|########6 | 173/199 [00:00<00:00, 1884.53it/s, Materializing param=encoder.layer.10.attention.self.query.weight]
Loading weights:  87%|########7 | 174/199 [00:00<00:00, 1893.58it/s, Materializing param=encoder.layer.10.attention.self.value.bias]  
Loading weights:  87%|########7 | 174/199 [00:00<00:00, 1892.78it/s, Materializing param=encoder.layer.10.attention.self.value.bias]
Loading weights:  88%|########7 | 175/199 [00:00<00:00, 1902.13it/s, Materializing param=encoder.layer.10.attention.self.value.weight]
Loading weights:  88%|########7 | 175/199 [00:00<00:00, 1901.32it/s, Materializing param=encoder.layer.10.attention.self.value.weight]
Loading weights:  88%|########8 | 176/199 [00:00<00:00, 1910.67it/s, Materializing param=encoder.layer.10.intermediate.dense.bias]    
Loading weights:  88%|########8 | 176/199 [00:00<00:00, 1909.87it/s, Materializing param=encoder.layer.10.intermediate.dense.bias]
Loading weights:  89%|########8 | 177/199 [00:00<00:00, 1919.18it/s, Materializing param=encoder.layer.10.intermediate.dense.weight]
Loading weights:  89%|########8 | 177/199 [00:00<00:00, 1918.37it/s, Materializing param=encoder.layer.10.intermediate.dense.weight]
Loading weights:  89%|########9 | 178/199 [00:00<00:00, 1927.70it/s, Materializing param=encoder.layer.10.output.LayerNorm.bias]    
Loading weights:  89%|########9 | 178/199 [00:00<00:00, 1926.89it/s, Materializing param=encoder.layer.10.output.LayerNorm.bias]
Loading weights:  90%|########9 | 179/199 [00:00<00:00, 1935.73it/s, Materializing param=encoder.layer.10.output.LayerNorm.weight]
Loading weights:  90%|########9 | 179/199 [00:00<00:00, 1934.90it/s, Materializing param=encoder.layer.10.output.LayerNorm.weight]
Loading weights:  90%|######### | 180/199 [00:00<00:00, 1944.00it/s, Materializing param=encoder.layer.10.output.dense.bias]      
Loading weights:  90%|######### | 180/199 [00:00<00:00, 1943.16it/s, Materializing param=encoder.layer.10.output.dense.bias]
Loading weights:  91%|######### | 181/199 [00:00<00:00, 1952.42it/s, Materializing param=encoder.layer.10.output.dense.weight]
Loading weights:  91%|######### | 181/199 [00:00<00:00, 1951.61it/s, Materializing param=encoder.layer.10.output.dense.weight]
Loading weights:  91%|#########1| 182/199 [00:00<00:00, 1960.89it/s, Materializing param=encoder.layer.11.attention.output.LayerNorm.bias]
Loading weights:  91%|#########1| 182/199 [00:00<00:00, 1960.05it/s, Materializing param=encoder.layer.11.attention.output.LayerNorm.bias]
Loading weights:  92%|#########1| 183/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.output.LayerNorm.bias]
Loading weights:  92%|#########1| 183/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.output.LayerNorm.weight]
Loading weights:  92%|#########1| 183/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.output.LayerNorm.weight]
Loading weights:  92%|#########2| 184/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.output.dense.bias]      
Loading weights:  92%|#########2| 184/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.output.dense.bias]
Loading weights:  93%|#########2| 185/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.output.dense.weight]
Loading weights:  93%|#########2| 185/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.output.dense.weight]
Loading weights:  93%|#########3| 186/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.self.key.bias]      
Loading weights:  93%|#########3| 186/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.self.key.bias]
Loading weights:  94%|#########3| 187/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.self.key.weight]
Loading weights:  94%|#########3| 187/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.self.key.weight]
Loading weights:  94%|#########4| 188/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.self.query.bias]
Loading weights:  94%|#########4| 188/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.self.query.bias]
Loading weights:  95%|#########4| 189/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.self.query.weight]
Loading weights:  95%|#########4| 189/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.self.query.weight]
Loading weights:  95%|#########5| 190/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.self.value.bias]  
Loading weights:  95%|#########5| 190/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.self.value.bias]
Loading weights:  96%|#########5| 191/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.self.value.weight]
Loading weights:  96%|#########5| 191/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.attention.self.value.weight]
Loading weights:  96%|#########6| 192/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.intermediate.dense.bias]    
Loading weights:  96%|#########6| 192/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.intermediate.dense.bias]
Loading weights:  97%|#########6| 193/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.intermediate.dense.weight]
Loading weights:  97%|#########6| 193/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.intermediate.dense.weight]
Loading weights:  97%|#########7| 194/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.output.LayerNorm.bias]    
Loading weights:  97%|#########7| 194/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.output.LayerNorm.bias]
Loading weights:  98%|#########7| 195/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.output.LayerNorm.weight]
Loading weights:  98%|#########7| 195/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.output.LayerNorm.weight]
Loading weights:  98%|#########8| 196/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.output.dense.bias]      
Loading weights:  98%|#########8| 196/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.output.dense.bias]
Loading weights:  99%|#########8| 197/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.output.dense.weight]
Loading weights:  99%|#########8| 197/199 [00:00<00:00, 1722.58it/s, Materializing param=encoder.layer.11.output.dense.weight]
Loading weights:  99%|#########9| 198/199 [00:00<00:00, 1722.58it/s, Materializing param=pooler.dense.bias]                   
Loading weights:  99%|#########9| 198/199 [00:00<00:00, 1722.58it/s, Materializing param=pooler.dense.bias]
Loading weights: 100%|##########| 199/199 [00:00<00:00, 1722.58it/s, Materializing param=pooler.dense.weight]
Loading weights: 100%|##########| 199/199 [00:00<00:00, 1722.58it/s, Materializing param=pooler.dense.weight]
Loading weights: 100%|##########| 199/199 [00:00<00:00, 1635.28it/s, Materializing param=pooler.dense.weight]
[1mBertModel LOAD REPORT[0m from: intfloat/e5-small-v2
Key                     | Status     |  | 
------------------------+------------+--+-
embeddings.position_ids | UNEXPECTED |  | 

[3mNotes:
- UNEXPECTED[3m	:can be ignored when loading from different task/architecture; not ok if you expect identical arch.[0m
ERROR:root:Error cargando indice FAISS CUPS: Directorio no encontrado: D:\Desarrollo\Proyectos_Activos\epicrisis2026\cups_faiss
INFO:     Started server process [20116]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
[!] Password de admin actualizado por ADMIN_FORCE_RESET
INFO:     127.0.0.1:55496 - "GET /logout HTTP/1.1" 302 Found
INFO:     127.0.0.1:55496 - "GET /login HTTP/1.1" 200 OK
INFO:     127.0.0.1:55496 - "POST /login HTTP/1.1" 302 Found
INFO:     127.0.0.1:55496 - "GET /dashboard HTTP/1.1" 200 OK
INFO:     127.0.0.1:55496 - "GET /mis_historias HTTP/1.1" 200 OK
Documento PDF 'HISTORIA CLINICA  BLANCA LIJIA RENGIFO AGUIRRE.pdf' guardado exitosamente en MongoDB.
INFO:     127.0.0.1:58120 - "POST /upload_pdf HTTP/1.1" 200 OK
INFO:     127.0.0.1:58120 - "GET /procesar_ultimo_pdf HTTP/1.1" 500 Internal Server Error
