Failed to load versions. Head to the versions page to see all versions for this model.
You're looking at a specific version of this model. Jump to the model overview.
replicate /dreambooth:7198ab66
Input
Run this model in Node.js with one line of code:
npm install replicate
REPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import Replicate from "replicate";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});
Run replicate/dreambooth using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"replicate/dreambooth:7198ab665a5e793fc8d89ed80db7660cc5fdd086f2809c19d5a88ec5dbcadf99",
{
input: {
seed: 1337,
scale_lr: false,
adam_beta1: 0.9,
adam_beta2: 0.999,
pad_tokens: false,
resolution: 512,
center_crop: false,
adam_epsilon: 1e-8,
class_prompt: "a cat",
lr_scheduler: "constant",
instance_data: "https://replicate.delivery/pbxt/HlRmIY3SePK6D8ZgnTvgymRWRSFqJlrDrfxJjA6QAazg1wVl/data.zip",
learning_rate: 0.000001,
max_grad_norm: 1,
n_save_sample: 4,
use_8bit_adam: false,
instance_prompt: "a cjw cat",
lr_warmup_steps: 0,
max_train_steps: 1000,
num_class_images: 100,
num_train_epochs: 1,
save_infer_steps: 50,
train_batch_size: 1,
adam_weight_decay: 0.01,
prior_loss_weight: 1,
sample_batch_size: 4,
train_text_encoder: true,
save_guidance_scale: 7.5,
gradient_checkpointing: false,
with_prior_preservation: true,
gradient_accumulation_steps: 1
}
}
);
console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
REPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import replicate
Run replicate/dreambooth using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"replicate/dreambooth:7198ab665a5e793fc8d89ed80db7660cc5fdd086f2809c19d5a88ec5dbcadf99",
input={
"seed": 1337,
"scale_lr": False,
"adam_beta1": 0.9,
"adam_beta2": 0.999,
"pad_tokens": False,
"resolution": 512,
"center_crop": False,
"adam_epsilon": 1e-8,
"class_prompt": "a cat",
"lr_scheduler": "constant",
"instance_data": "https://replicate.delivery/pbxt/HlRmIY3SePK6D8ZgnTvgymRWRSFqJlrDrfxJjA6QAazg1wVl/data.zip",
"learning_rate": 0.000001,
"max_grad_norm": 1,
"n_save_sample": 4,
"use_8bit_adam": False,
"instance_prompt": "a cjw cat",
"lr_warmup_steps": 0,
"max_train_steps": 1000,
"num_class_images": 100,
"num_train_epochs": 1,
"save_infer_steps": 50,
"train_batch_size": 1,
"adam_weight_decay": 0.01,
"prior_loss_weight": 1,
"sample_batch_size": 4,
"train_text_encoder": True,
"save_guidance_scale": 7.5,
"gradient_checkpointing": False,
"with_prior_preservation": True,
"gradient_accumulation_steps": 1
}
)
print(output)
To learn more, take a look at the guide on getting started with Python.
REPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run replicate/dreambooth using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \
-H "Authorization: Bearer $REPLICATE_API_TOKEN" \
-H "Content-Type: application/json" \
-H "Prefer: wait" \
-d $'{
"version": "7198ab665a5e793fc8d89ed80db7660cc5fdd086f2809c19d5a88ec5dbcadf99",
"input": {
"seed": 1337,
"scale_lr": false,
"adam_beta1": 0.9,
"adam_beta2": 0.999,
"pad_tokens": false,
"resolution": 512,
"center_crop": false,
"adam_epsilon": 1e-8,
"class_prompt": "a cat",
"lr_scheduler": "constant",
"instance_data": "https://replicate.delivery/pbxt/HlRmIY3SePK6D8ZgnTvgymRWRSFqJlrDrfxJjA6QAazg1wVl/data.zip",
"learning_rate": 0.000001,
"max_grad_norm": 1,
"n_save_sample": 4,
"use_8bit_adam": false,
"instance_prompt": "a cjw cat",
"lr_warmup_steps": 0,
"max_train_steps": 1000,
"num_class_images": 100,
"num_train_epochs": 1,
"save_infer_steps": 50,
"train_batch_size": 1,
"adam_weight_decay": 0.01,
"prior_loss_weight": 1,
"sample_batch_size": 4,
"train_text_encoder": true,
"save_guidance_scale": 7.5,
"gradient_checkpointing": false,
"with_prior_preservation": true,
"gradient_accumulation_steps": 1
}
}' \
https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Add a payment method to run this model.
By signing in, you agree to our
terms of service and privacy policy
Output
{
"completed_at": "2022-11-17T02:47:38.043848Z",
"created_at": "2022-11-17T02:35:42.949173Z",
"data_removed": false,
"error": null,
"id": "4yyxeqh2cfcd7pueymhl6jhcra",
"input": {
"seed": 1337,
"adam_beta1": 0.9,
"adam_beta2": 0.999,
"resolution": 512,
"adam_epsilon": 1e-8,
"class_prompt": "a cat",
"lr_scheduler": "constant",
"instance_data": "https://replicate.delivery/pbxt/HlRmIY3SePK6D8ZgnTvgymRWRSFqJlrDrfxJjA6QAazg1wVl/data.zip",
"learning_rate": 0.000001,
"max_grad_norm": 1,
"n_save_sample": 4,
"use_8bit_adam": false,
"instance_prompt": "a cjw cat",
"max_train_steps": 1000,
"num_class_images": 100,
"num_train_epochs": 1,
"save_infer_steps": 50,
"train_batch_size": 1,
"adam_weight_decay": 0.01,
"prior_loss_weight": 1,
"sample_batch_size": 4,
"train_text_encoder": true,
"save_guidance_scale": 7.5,
"gradient_checkpointing": false,
"with_prior_preservation": true,
"gradient_accumulation_steps": 1
},
"logs": "/root/.pyenv/versions/3.10.8/lib/python3.10/site-packages/accelerate/accelerator.py:179: UserWarning: `log_with=tensorboard` was passed but no supported trackers are currently installed.\nwarnings.warn(f\"`log_with={log_with}` was passed but no supported trackers are currently installed.\")\nYou have passed `None` for safety_checker to disable its functionality in <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'>. Note that this might lead to problems when using <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> and is not recommended.\nGenerating class images: 0%| | 0/25 [00:00<?, ?it/s]\nGenerating class images: 4%|▍ | 1/25 [00:26<10:25, 26.06s/it]\nGenerating class images: 8%|▊ | 2/25 [00:35<06:15, 16.32s/it]\nGenerating class images: 12%|█▏ | 3/25 [00:45<04:50, 13.20s/it]\nGenerating class images: 16%|█▌ | 4/25 [00:54<04:06, 11.74s/it]\nGenerating class images: 20%|██ | 5/25 [01:04<03:38, 10.92s/it]\nGenerating class images: 24%|██▍ | 6/25 [01:13<03:18, 10.44s/it]\nGenerating class images: 28%|██▊ | 7/25 [01:22<03:02, 10.13s/it]\nGenerating class images: 32%|███▏ | 8/25 [01:32<02:48, 9.93s/it]\nGenerating class images: 36%|███▌ | 9/25 [01:41<02:36, 9.79s/it]\nGenerating class images: 40%|████ | 10/25 [01:51<02:25, 9.69s/it]\nGenerating class images: 44%|████▍ | 11/25 [02:00<02:14, 9.63s/it]\nGenerating class images: 48%|████▊ | 12/25 [02:10<02:04, 9.59s/it]\nGenerating class images: 52%|█████▏ | 13/25 [02:19<01:54, 9.56s/it]\nGenerating class images: 56%|█████▌ | 14/25 [02:29<01:44, 9.54s/it]\nGenerating class images: 60%|██████ | 15/25 [02:38<01:35, 9.53s/it]\nGenerating class images: 64%|██████▍ | 16/25 [02:48<01:25, 9.51s/it]\nGenerating class images: 68%|██████▊ | 17/25 [02:57<01:16, 9.51s/it]\nGenerating class images: 72%|███████▏ | 18/25 [03:07<01:06, 9.50s/it]\nGenerating class images: 76%|███████▌ | 19/25 [03:16<00:56, 9.50s/it]\nGenerating class images: 80%|████████ | 20/25 [03:26<00:47, 9.50s/it]\nGenerating class images: 84%|████████▍ | 21/25 [03:35<00:37, 9.50s/it]\nGenerating class images: 88%|████████▊ | 22/25 [03:45<00:28, 9.50s/it]\nGenerating class images: 92%|█████████▏| 23/25 [03:54<00:18, 9.49s/it]\nGenerating class images: 96%|█████████▌| 24/25 [04:04<00:09, 9.49s/it]\nGenerating class images: 100%|██████████| 25/25 [04:13<00:00, 9.49s/it]\nGenerating class images: 100%|██████████| 25/25 [04:13<00:00, 10.15s/it]\nCaching latents: 0%| | 0/100 [00:00<?, ?it/s]\nCaching latents: 1%| | 1/100 [00:01<02:27, 1.49s/it]\nCaching latents: 2%|▏ | 2/100 [00:01<01:07, 1.45it/s]\nCaching latents: 3%|▎ | 3/100 [00:01<00:41, 2.34it/s]\nCaching latents: 4%|▍ | 4/100 [00:01<00:29, 3.26it/s]\nCaching latents: 5%|▌ | 5/100 [00:01<00:22, 4.19it/s]\nCaching latents: 6%|▌ | 6/100 [00:02<00:18, 5.08it/s]\nCaching latents: 7%|▋ | 7/100 [00:02<00:15, 5.86it/s]\nCaching latents: 8%|▊ | 8/100 [00:02<00:14, 6.46it/s]\nCaching latents: 9%|▉ | 9/100 [00:02<00:13, 6.96it/s]\nCaching latents: 10%|█ | 10/100 [00:02<00:12, 7.14it/s]\nCaching latents: 11%|█ | 11/100 [00:02<00:11, 7.43it/s]\nCaching latents: 12%|█▏ | 12/100 [00:02<00:11, 7.49it/s]\nCaching latents: 13%|█▎ | 13/100 [00:02<00:11, 7.66it/s]\nCaching latents: 14%|█▍ | 14/100 [00:03<00:10, 7.91it/s]\nCaching latents: 15%|█▌ | 15/100 [00:03<00:10, 8.07it/s]\nCaching latents: 16%|█▌ | 16/100 [00:03<00:10, 8.10it/s]\nCaching latents: 17%|█▋ | 17/100 [00:03<00:10, 8.23it/s]\nCaching latents: 18%|█▊ | 18/100 [00:03<00:09, 8.34it/s]\nCaching latents: 19%|█▉ | 19/100 [00:03<00:09, 8.34it/s]\nCaching latents: 20%|██ | 20/100 [00:03<00:09, 8.42it/s]\nCaching latents: 21%|██ | 21/100 [00:03<00:09, 8.49it/s]\nCaching latents: 22%|██▏ | 22/100 [00:04<00:09, 8.28it/s]\nCaching latents: 23%|██▎ | 23/100 [00:04<00:09, 8.30it/s]\nCaching latents: 24%|██▍ | 24/100 [00:04<00:09, 8.32it/s]\nCaching latents: 25%|██▌ | 25/100 [00:04<00:09, 8.30it/s]\nCaching latents: 26%|██▌ | 26/100 [00:04<00:08, 8.31it/s]\nCaching latents: 27%|██▋ | 27/100 [00:04<00:08, 8.30it/s]\nCaching latents: 28%|██▊ | 28/100 [00:04<00:08, 8.37it/s]\nCaching latents: 29%|██▉ | 29/100 [00:04<00:08, 8.43it/s]\nCaching latents: 30%|███ | 30/100 [00:04<00:08, 8.41it/s]\nCaching latents: 31%|███ | 31/100 [00:05<00:08, 8.46it/s]\nCaching latents: 32%|███▏ | 32/100 [00:05<00:08, 8.38it/s]\nCaching latents: 33%|███▎ | 33/100 [00:05<00:07, 8.42it/s]\nCaching latents: 34%|███▍ | 34/100 [00:05<00:07, 8.36it/s]\nCaching latents: 35%|███▌ | 35/100 [00:05<00:07, 8.35it/s]\nCaching latents: 36%|███▌ | 36/100 [00:05<00:07, 8.29it/s]\nCaching latents: 37%|███▋ | 37/100 [00:05<00:07, 8.22it/s]\nCaching latents: 38%|███▊ | 38/100 [00:05<00:07, 8.25it/s]\nCaching latents: 39%|███▉ | 39/100 [00:06<00:07, 8.35it/s]\nCaching latents: 40%|████ | 40/100 [00:06<00:07, 8.34it/s]\nCaching latents: 41%|████ | 41/100 [00:06<00:07, 8.34it/s]\nCaching latents: 42%|████▏ | 42/100 [00:06<00:06, 8.29it/s]\nCaching latents: 43%|████▎ | 43/100 [00:06<00:06, 8.29it/s]\nCaching latents: 44%|████▍ | 44/100 [00:06<00:06, 8.21it/s]\nCaching latents: 45%|████▌ | 45/100 [00:06<00:06, 8.21it/s]\nCaching latents: 46%|████▌ | 46/100 [00:06<00:06, 8.18it/s]\nCaching latents: 47%|████▋ | 47/100 [00:07<00:06, 8.12it/s]\nCaching latents: 48%|████▊ | 48/100 [00:07<00:06, 8.18it/s]\nCaching latents: 49%|████▉ | 49/100 [00:07<00:06, 8.32it/s]\nCaching latents: 50%|█████ | 50/100 [00:07<00:06, 8.30it/s]\nCaching latents: 51%|█████ | 51/100 [00:07<00:05, 8.27it/s]\nCaching latents: 52%|█████▏ | 52/100 [00:07<00:05, 8.23it/s]\nCaching latents: 53%|█████▎ | 53/100 [00:07<00:05, 8.34it/s]\nCaching latents: 54%|█████▍ | 54/100 [00:07<00:05, 8.32it/s]\nCaching latents: 55%|█████▌ | 55/100 [00:07<00:05, 8.36it/s]\nCaching latents: 56%|█████▌ | 56/100 [00:08<00:05, 8.32it/s]\nCaching latents: 57%|█████▋ | 57/100 [00:08<00:05, 8.32it/s]\nCaching latents: 58%|█████▊ | 58/100 [00:08<00:05, 8.31it/s]\nCaching latents: 59%|█████▉ | 59/100 [00:08<00:04, 8.43it/s]\nCaching latents: 60%|██████ | 60/100 [00:08<00:04, 8.37it/s]\nCaching latents: 61%|██████ | 61/100 [00:08<00:04, 8.29it/s]\nCaching latents: 62%|██████▏ | 62/100 [00:08<00:04, 8.45it/s]\nCaching latents: 63%|██████▎ | 63/100 [00:08<00:04, 8.38it/s]\nCaching latents: 64%|██████▍ | 64/100 [00:09<00:04, 8.39it/s]\nCaching latents: 65%|██████▌ | 65/100 [00:09<00:04, 8.38it/s]\nCaching latents: 66%|██████▌ | 66/100 [00:09<00:04, 8.45it/s]\nCaching latents: 67%|██████▋ | 67/100 [00:09<00:03, 8.30it/s]\nCaching latents: 68%|██████▊ | 68/100 [00:09<00:03, 8.33it/s]\nCaching latents: 69%|██████▉ | 69/100 [00:09<00:03, 8.23it/s]\nCaching latents: 70%|███████ | 70/100 [00:09<00:03, 8.24it/s]\nCaching latents: 71%|███████ | 71/100 [00:09<00:03, 8.35it/s]\nCaching latents: 72%|███████▏ | 72/100 [00:10<00:03, 8.30it/s]\nCaching latents: 73%|███████▎ | 73/100 [00:10<00:03, 8.42it/s]\nCaching latents: 74%|███████▍ | 74/100 [00:10<00:03, 8.45it/s]\nCaching latents: 75%|███████▌ | 75/100 [00:10<00:02, 8.37it/s]\nCaching latents: 76%|███████▌ | 76/100 [00:10<00:02, 8.08it/s]\nCaching latents: 77%|███████▋ | 77/100 [00:10<00:02, 8.13it/s]\nCaching latents: 78%|███████▊ | 78/100 [00:10<00:02, 8.20it/s]\nCaching latents: 79%|███████▉ | 79/100 [00:10<00:02, 8.31it/s]\nCaching latents: 80%|████████ | 80/100 [00:11<00:02, 8.24it/s]\nCaching latents: 81%|████████ | 81/100 [00:11<00:02, 8.32it/s]\nCaching latents: 82%|████████▏ | 82/100 [00:11<00:02, 8.29it/s]\nCaching latents: 83%|████████▎ | 83/100 [00:11<00:02, 8.38it/s]\nCaching latents: 84%|████████▍ | 84/100 [00:11<00:01, 8.36it/s]\nCaching latents: 85%|████████▌ | 85/100 [00:11<00:01, 8.30it/s]\nCaching latents: 86%|████████▌ | 86/100 [00:11<00:01, 8.37it/s]\nCaching latents: 87%|████████▋ | 87/100 [00:11<00:01, 8.34it/s]\nCaching latents: 88%|████████▊ | 88/100 [00:11<00:01, 8.08it/s]\nCaching latents: 89%|████████▉ | 89/100 [00:12<00:01, 8.23it/s]\nCaching latents: 90%|█████████ | 90/100 [00:12<00:01, 8.34it/s]\nCaching latents: 91%|█████████ | 91/100 [00:12<00:01, 8.33it/s]\nCaching latents: 92%|█████████▏| 92/100 [00:12<00:00, 8.43it/s]\nCaching latents: 93%|█████████▎| 93/100 [00:12<00:00, 8.34it/s]\nCaching latents: 94%|█████████▍| 94/100 [00:12<00:00, 8.37it/s]\nCaching latents: 95%|█████████▌| 95/100 [00:12<00:00, 8.39it/s]\nCaching latents: 96%|█████████▌| 96/100 [00:12<00:00, 8.46it/s]\nCaching latents: 97%|█████████▋| 97/100 [00:13<00:00, 8.41it/s]\nCaching latents: 98%|█████████▊| 98/100 [00:13<00:00, 8.34it/s]\nCaching latents: 99%|█████████▉| 99/100 [00:13<00:00, 8.31it/s]\nCaching latents: 100%|██████████| 100/100 [00:13<00:00, 8.31it/s]\nCaching latents: 100%|██████████| 100/100 [00:13<00:00, 7.46it/s]\n0%| | 0/1000 [00:00<?, ?it/s]\nSteps: 0%| | 0/1000 [00:00<?, ?it/s]\nSteps: 0%| | 0/1000 [00:10<?, ?it/s, loss=0.405, lr=1e-6]\nSteps: 0%| | 1/1000 [00:10<2:59:53, 10.80s/it, loss=0.405, lr=1e-6]\nSteps: 0%| | 2/1000 [00:11<1:17:45, 4.68s/it, loss=0.405, lr=1e-6]\nSteps: 0%| | 3/1000 [00:11<44:50, 2.70s/it, loss=0.405, lr=1e-6] \nSteps: 0%| | 4/1000 [00:11<29:26, 1.77s/it, loss=0.405, lr=1e-6]\nSteps: 0%| | 5/1000 [00:12<20:54, 1.26s/it, loss=0.405, lr=1e-6]\nSteps: 1%| | 6/1000 [00:12<15:46, 1.05it/s, loss=0.405, lr=1e-6]\nSteps: 1%| | 7/1000 [00:12<12:30, 1.32it/s, loss=0.405, lr=1e-6]\nSteps: 1%| | 8/1000 [00:13<10:20, 1.60it/s, loss=0.405, lr=1e-6]\nSteps: 1%| | 9/1000 [00:13<08:54, 1.85it/s, loss=0.405, lr=1e-6]\nSteps: 1%| | 10/1000 [00:13<07:56, 2.08it/s, loss=0.405, lr=1e-6]\nSteps: 1%| | 10/1000 [00:14<07:56, 2.08it/s, loss=0.285, lr=1e-6]\nSteps: 1%| | 11/1000 [00:14<07:16, 2.27it/s, loss=0.285, lr=1e-6]\nSteps: 1%| | 12/1000 [00:14<06:50, 2.41it/s, loss=0.285, lr=1e-6]\nSteps: 1%|▏ | 13/1000 [00:15<06:32, 2.52it/s, loss=0.285, lr=1e-6]\nSteps: 1%|▏ | 14/1000 [00:15<06:18, 2.61it/s, loss=0.285, lr=1e-6]\nSteps: 2%|▏ | 15/1000 [00:15<06:07, 2.68it/s, loss=0.285, lr=1e-6]\nSteps: 2%|▏ | 16/1000 [00:16<06:06, 2.69it/s, loss=0.285, lr=1e-6]\nSteps: 2%|▏ | 17/1000 [00:16<05:58, 2.74it/s, loss=0.285, lr=1e-6]\nSteps: 2%|▏ | 18/1000 [00:16<05:54, 2.77it/s, loss=0.285, lr=1e-6]\nSteps: 2%|▏ | 19/1000 [00:17<05:51, 2.79it/s, loss=0.285, lr=1e-6]\nSteps: 2%|▏ | 20/1000 [00:17<05:48, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 2%|▏ | 20/1000 [00:17<05:48, 2.81it/s, loss=0.278, lr=1e-6]\nSteps: 2%|▏ | 21/1000 [00:17<05:48, 2.81it/s, loss=0.278, lr=1e-6]\nSteps: 2%|▏ | 22/1000 [00:18<05:46, 2.82it/s, loss=0.278, lr=1e-6]\nSteps: 2%|▏ | 23/1000 [00:18<05:45, 2.83it/s, loss=0.278, lr=1e-6]\nSteps: 2%|▏ | 24/1000 [00:18<05:45, 2.83it/s, loss=0.278, lr=1e-6]\nSteps: 2%|▎ | 25/1000 [00:19<05:44, 2.83it/s, loss=0.278, lr=1e-6]\nSteps: 3%|▎ | 26/1000 [00:19<05:45, 2.82it/s, loss=0.278, lr=1e-6]\nSteps: 3%|▎ | 27/1000 [00:20<05:43, 2.83it/s, loss=0.278, lr=1e-6]\nSteps: 3%|▎ | 28/1000 [00:20<05:42, 2.84it/s, loss=0.278, lr=1e-6]\nSteps: 3%|▎ | 29/1000 [00:20<05:40, 2.85it/s, loss=0.278, lr=1e-6]\nSteps: 3%|▎ | 30/1000 [00:21<05:39, 2.86it/s, loss=0.278, lr=1e-6]\nSteps: 3%|▎ | 30/1000 [00:21<05:39, 2.86it/s, loss=0.27, lr=1e-6]\nSteps: 3%|▎ | 31/1000 [00:21<05:38, 2.87it/s, loss=0.27, lr=1e-6]\nSteps: 3%|▎ | 32/1000 [00:21<05:37, 2.87it/s, loss=0.27, lr=1e-6]\nSteps: 3%|▎ | 33/1000 [00:22<05:39, 2.85it/s, loss=0.27, lr=1e-6]\nSteps: 3%|▎ | 34/1000 [00:22<05:37, 2.86it/s, loss=0.27, lr=1e-6]\nSteps: 4%|▎ | 35/1000 [00:22<05:35, 2.87it/s, loss=0.27, lr=1e-6]\nSteps: 4%|▎ | 36/1000 [00:23<05:37, 2.86it/s, loss=0.27, lr=1e-6]\nSteps: 4%|▎ | 37/1000 [00:23<05:36, 2.86it/s, loss=0.27, lr=1e-6]\nSteps: 4%|▍ | 38/1000 [00:23<05:35, 2.87it/s, loss=0.27, lr=1e-6]\nSteps: 4%|▍ | 39/1000 [00:24<05:35, 2.87it/s, loss=0.27, lr=1e-6]\nSteps: 4%|▍ | 40/1000 [00:24<05:35, 2.86it/s, loss=0.27, lr=1e-6]\nSteps: 4%|▍ | 40/1000 [00:24<05:35, 2.86it/s, loss=0.282, lr=1e-6]\nSteps: 4%|▍ | 41/1000 [00:24<05:34, 2.86it/s, loss=0.282, lr=1e-6]\nSteps: 4%|▍ | 42/1000 [00:25<05:38, 2.83it/s, loss=0.282, lr=1e-6]\nSteps: 4%|▍ | 43/1000 [00:25<05:36, 2.84it/s, loss=0.282, lr=1e-6]\nSteps: 4%|▍ | 44/1000 [00:25<05:42, 2.79it/s, loss=0.282, lr=1e-6]\nSteps: 4%|▍ | 45/1000 [00:26<05:41, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 5%|▍ | 46/1000 [00:26<05:39, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 5%|▍ | 47/1000 [00:27<05:40, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 5%|▍ | 48/1000 [00:27<05:37, 2.82it/s, loss=0.282, lr=1e-6]\nSteps: 5%|▍ | 49/1000 [00:27<05:36, 2.83it/s, loss=0.282, lr=1e-6]\nSteps: 5%|▌ | 50/1000 [00:28<05:38, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 5%|▌ | 50/1000 [00:28<05:38, 2.81it/s, loss=0.298, lr=1e-6]\nSteps: 5%|▌ | 51/1000 [00:28<05:35, 2.83it/s, loss=0.298, lr=1e-6]\nSteps: 5%|▌ | 52/1000 [00:28<05:30, 2.86it/s, loss=0.298, lr=1e-6]\nSteps: 5%|▌ | 53/1000 [00:29<05:30, 2.86it/s, loss=0.298, lr=1e-6]\nSteps: 5%|▌ | 54/1000 [00:29<05:31, 2.86it/s, loss=0.298, lr=1e-6]\nSteps: 6%|▌ | 55/1000 [00:29<05:30, 2.86it/s, loss=0.298, lr=1e-6]\nSteps: 6%|▌ | 56/1000 [00:30<05:32, 2.84it/s, loss=0.298, lr=1e-6]\nSteps: 6%|▌ | 57/1000 [00:30<05:30, 2.85it/s, loss=0.298, lr=1e-6]\nSteps: 6%|▌ | 58/1000 [00:30<05:28, 2.87it/s, loss=0.298, lr=1e-6]\nSteps: 6%|▌ | 59/1000 [00:31<05:30, 2.84it/s, loss=0.298, lr=1e-6]\nSteps: 6%|▌ | 60/1000 [00:31<05:30, 2.84it/s, loss=0.298, lr=1e-6]\nSteps: 6%|▌ | 60/1000 [00:31<05:30, 2.84it/s, loss=0.305, lr=1e-6]\nSteps: 6%|▌ | 61/1000 [00:31<05:29, 2.85it/s, loss=0.305, lr=1e-6]\nSteps: 6%|▌ | 62/1000 [00:32<05:30, 2.83it/s, loss=0.305, lr=1e-6]\nSteps: 6%|▋ | 63/1000 [00:32<05:29, 2.84it/s, loss=0.305, lr=1e-6]\nSteps: 6%|▋ | 64/1000 [00:33<05:29, 2.84it/s, loss=0.305, lr=1e-6]\nSteps: 6%|▋ | 65/1000 [00:33<05:30, 2.83it/s, loss=0.305, lr=1e-6]\nSteps: 7%|▋ | 66/1000 [00:33<05:29, 2.84it/s, loss=0.305, lr=1e-6]\nSteps: 7%|▋ | 67/1000 [00:34<05:31, 2.81it/s, loss=0.305, lr=1e-6]\nSteps: 7%|▋ | 68/1000 [00:34<05:31, 2.81it/s, loss=0.305, lr=1e-6]\nSteps: 7%|▋ | 69/1000 [00:34<05:29, 2.83it/s, loss=0.305, lr=1e-6]\nSteps: 7%|▋ | 70/1000 [00:35<05:27, 2.84it/s, loss=0.305, lr=1e-6]\nSteps: 7%|▋ | 70/1000 [00:35<05:27, 2.84it/s, loss=0.311, lr=1e-6]\nSteps: 7%|▋ | 71/1000 [00:35<05:26, 2.84it/s, loss=0.311, lr=1e-6]\nSteps: 7%|▋ | 72/1000 [00:35<05:29, 2.82it/s, loss=0.311, lr=1e-6]\nSteps: 7%|▋ | 73/1000 [00:36<05:30, 2.80it/s, loss=0.311, lr=1e-6]\nSteps: 7%|▋ | 74/1000 [00:36<05:28, 2.82it/s, loss=0.311, lr=1e-6]\nSteps: 8%|▊ | 75/1000 [00:36<05:28, 2.81it/s, loss=0.311, lr=1e-6]\nSteps: 8%|▊ | 76/1000 [00:37<05:33, 2.77it/s, loss=0.311, lr=1e-6]\nSteps: 8%|▊ | 77/1000 [00:37<05:30, 2.79it/s, loss=0.311, lr=1e-6]\nSteps: 8%|▊ | 78/1000 [00:37<05:27, 2.81it/s, loss=0.311, lr=1e-6]\nSteps: 8%|▊ | 79/1000 [00:38<05:28, 2.80it/s, loss=0.311, lr=1e-6]\nSteps: 8%|▊ | 80/1000 [00:38<05:26, 2.82it/s, loss=0.311, lr=1e-6]\nSteps: 8%|▊ | 80/1000 [00:39<05:26, 2.82it/s, loss=0.301, lr=1e-6]\nSteps: 8%|▊ | 81/1000 [00:39<05:25, 2.82it/s, loss=0.301, lr=1e-6]\nSteps: 8%|▊ | 82/1000 [00:39<05:25, 2.82it/s, loss=0.301, lr=1e-6]\nSteps: 8%|▊ | 83/1000 [00:39<05:26, 2.81it/s, loss=0.301, lr=1e-6]\nSteps: 8%|▊ | 84/1000 [00:40<05:25, 2.81it/s, loss=0.301, lr=1e-6]\nSteps: 8%|▊ | 85/1000 [00:40<05:26, 2.80it/s, loss=0.301, lr=1e-6]\nSteps: 9%|▊ | 86/1000 [00:40<05:26, 2.80it/s, loss=0.301, lr=1e-6]\nSteps: 9%|▊ | 87/1000 [00:41<05:25, 2.80it/s, loss=0.301, lr=1e-6]\nSteps: 9%|▉ | 88/1000 [00:41<05:25, 2.80it/s, loss=0.301, lr=1e-6]\nSteps: 9%|▉ | 89/1000 [00:41<05:24, 2.81it/s, loss=0.301, lr=1e-6]\nSteps: 9%|▉ | 90/1000 [00:42<05:23, 2.81it/s, loss=0.301, lr=1e-6]\nSteps: 9%|▉ | 90/1000 [00:42<05:23, 2.81it/s, loss=0.306, lr=1e-6]\nSteps: 9%|▉ | 91/1000 [00:42<05:23, 2.81it/s, loss=0.306, lr=1e-6]\nSteps: 9%|▉ | 92/1000 [00:42<05:19, 2.84it/s, loss=0.306, lr=1e-6]\nSteps: 9%|▉ | 93/1000 [00:43<05:17, 2.86it/s, loss=0.306, lr=1e-6]\nSteps: 9%|▉ | 94/1000 [00:43<05:18, 2.85it/s, loss=0.306, lr=1e-6]\nSteps: 10%|▉ | 95/1000 [00:44<05:17, 2.85it/s, loss=0.306, lr=1e-6]\nSteps: 10%|▉ | 96/1000 [00:44<05:16, 2.86it/s, loss=0.306, lr=1e-6]\nSteps: 10%|▉ | 97/1000 [00:44<05:17, 2.85it/s, loss=0.306, lr=1e-6]\nSteps: 10%|▉ | 98/1000 [00:45<05:19, 2.83it/s, loss=0.306, lr=1e-6]\nSteps: 10%|▉ | 99/1000 [00:45<05:21, 2.81it/s, loss=0.306, lr=1e-6]\nSteps: 10%|█ | 100/1000 [00:45<05:20, 2.81it/s, loss=0.306, lr=1e-6]\nSteps: 10%|█ | 100/1000 [00:46<05:20, 2.81it/s, loss=0.298, lr=1e-6]\nSteps: 10%|█ | 101/1000 [00:46<05:23, 2.78it/s, loss=0.298, lr=1e-6]\nSteps: 10%|█ | 102/1000 [00:46<05:21, 2.79it/s, loss=0.298, lr=1e-6]\nSteps: 10%|█ | 103/1000 [00:46<05:18, 2.81it/s, loss=0.298, lr=1e-6]\nSteps: 10%|█ | 104/1000 [00:47<05:19, 2.81it/s, loss=0.298, lr=1e-6]\nSteps: 10%|█ | 105/1000 [00:47<05:19, 2.80it/s, loss=0.298, lr=1e-6]\nSteps: 11%|█ | 106/1000 [00:47<05:18, 2.81it/s, loss=0.298, lr=1e-6]\nSteps: 11%|█ | 107/1000 [00:48<05:15, 2.83it/s, loss=0.298, lr=1e-6]\nSteps: 11%|█ | 108/1000 [00:48<05:17, 2.81it/s, loss=0.298, lr=1e-6]\nSteps: 11%|█ | 109/1000 [00:48<05:16, 2.81it/s, loss=0.298, lr=1e-6]\nSteps: 11%|█ | 110/1000 [00:49<05:15, 2.82it/s, loss=0.298, lr=1e-6]\nSteps: 11%|█ | 110/1000 [00:49<05:15, 2.82it/s, loss=0.295, lr=1e-6]\nSteps: 11%|█ | 111/1000 [00:49<05:18, 2.79it/s, loss=0.295, lr=1e-6]\nSteps: 11%|█ | 112/1000 [00:50<05:15, 2.81it/s, loss=0.295, lr=1e-6]\nSteps: 11%|█▏ | 113/1000 [00:50<05:14, 2.82it/s, loss=0.295, lr=1e-6]\nSteps: 11%|█▏ | 114/1000 [00:50<05:14, 2.81it/s, loss=0.295, lr=1e-6]\nSteps: 12%|█▏ | 115/1000 [00:51<05:15, 2.80it/s, loss=0.295, lr=1e-6]\nSteps: 12%|█▏ | 116/1000 [00:51<05:15, 2.80it/s, loss=0.295, lr=1e-6]\nSteps: 12%|█▏ | 117/1000 [00:51<05:16, 2.79it/s, loss=0.295, lr=1e-6]\nSteps: 12%|█▏ | 118/1000 [00:52<05:18, 2.77it/s, loss=0.295, lr=1e-6]\nSteps: 12%|█▏ | 119/1000 [00:52<05:20, 2.75it/s, loss=0.295, lr=1e-6]\nSteps: 12%|█▏ | 120/1000 [00:52<05:18, 2.76it/s, loss=0.295, lr=1e-6]\nSteps: 12%|█▏ | 120/1000 [00:53<05:18, 2.76it/s, loss=0.29, lr=1e-6] \nSteps: 12%|█▏ | 121/1000 [00:53<05:16, 2.78it/s, loss=0.29, lr=1e-6]\nSteps: 12%|█▏ | 122/1000 [00:53<05:17, 2.77it/s, loss=0.29, lr=1e-6]\nSteps: 12%|█▏ | 123/1000 [00:54<05:14, 2.79it/s, loss=0.29, lr=1e-6]\nSteps: 12%|█▏ | 124/1000 [00:54<05:15, 2.78it/s, loss=0.29, lr=1e-6]\nSteps: 12%|█▎ | 125/1000 [00:54<05:14, 2.78it/s, loss=0.29, lr=1e-6]\nSteps: 13%|█▎ | 126/1000 [00:55<05:13, 2.79it/s, loss=0.29, lr=1e-6]\nSteps: 13%|█▎ | 127/1000 [00:55<05:11, 2.80it/s, loss=0.29, lr=1e-6]\nSteps: 13%|█▎ | 128/1000 [00:55<05:12, 2.79it/s, loss=0.29, lr=1e-6]\nSteps: 13%|█▎ | 129/1000 [00:56<05:11, 2.80it/s, loss=0.29, lr=1e-6]\nSteps: 13%|█▎ | 130/1000 [00:56<05:09, 2.81it/s, loss=0.29, lr=1e-6]\nSteps: 13%|█▎ | 130/1000 [00:56<05:09, 2.81it/s, loss=0.287, lr=1e-6]\nSteps: 13%|█▎ | 131/1000 [00:56<05:10, 2.80it/s, loss=0.287, lr=1e-6]\nSteps: 13%|█▎ | 132/1000 [00:57<05:08, 2.81it/s, loss=0.287, lr=1e-6]\nSteps: 13%|█▎ | 133/1000 [00:57<05:07, 2.82it/s, loss=0.287, lr=1e-6]\nSteps: 13%|█▎ | 134/1000 [00:57<05:07, 2.82it/s, loss=0.287, lr=1e-6]\nSteps: 14%|█▎ | 135/1000 [00:58<05:05, 2.83it/s, loss=0.287, lr=1e-6]\nSteps: 14%|█▎ | 136/1000 [00:58<05:04, 2.84it/s, loss=0.287, lr=1e-6]\nSteps: 14%|█▎ | 137/1000 [00:59<05:07, 2.81it/s, loss=0.287, lr=1e-6]\nSteps: 14%|█▍ | 138/1000 [00:59<05:05, 2.82it/s, loss=0.287, lr=1e-6]\nSteps: 14%|█▍ | 139/1000 [00:59<05:04, 2.83it/s, loss=0.287, lr=1e-6]\nSteps: 14%|█▍ | 140/1000 [01:00<05:06, 2.81it/s, loss=0.287, lr=1e-6]\nSteps: 14%|█▍ | 140/1000 [01:00<05:06, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 14%|█▍ | 141/1000 [01:00<05:05, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 14%|█▍ | 142/1000 [01:00<05:05, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 14%|█▍ | 143/1000 [01:01<05:02, 2.83it/s, loss=0.282, lr=1e-6]\nSteps: 14%|█▍ | 144/1000 [01:01<05:01, 2.84it/s, loss=0.282, lr=1e-6]\nSteps: 14%|█▍ | 145/1000 [01:01<04:59, 2.85it/s, loss=0.282, lr=1e-6]\nSteps: 15%|█▍ | 146/1000 [01:02<04:58, 2.86it/s, loss=0.282, lr=1e-6]\nSteps: 15%|█▍ | 147/1000 [01:02<04:58, 2.85it/s, loss=0.282, lr=1e-6]\nSteps: 15%|█▍ | 148/1000 [01:02<05:00, 2.84it/s, loss=0.282, lr=1e-6]\nSteps: 15%|█▍ | 149/1000 [01:03<05:00, 2.83it/s, loss=0.282, lr=1e-6]\nSteps: 15%|█▌ | 150/1000 [01:03<05:00, 2.83it/s, loss=0.282, lr=1e-6]\nSteps: 15%|█▌ | 150/1000 [01:03<05:00, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 15%|█▌ | 151/1000 [01:03<05:01, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 15%|█▌ | 152/1000 [01:04<05:00, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 15%|█▌ | 153/1000 [01:04<05:00, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 15%|█▌ | 154/1000 [01:05<05:02, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 16%|█▌ | 155/1000 [01:05<05:01, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 16%|█▌ | 156/1000 [01:05<05:01, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 16%|█▌ | 157/1000 [01:06<05:07, 2.74it/s, loss=0.285, lr=1e-6]\nSteps: 16%|█▌ | 158/1000 [01:06<05:04, 2.77it/s, loss=0.285, lr=1e-6]\nSteps: 16%|█▌ | 159/1000 [01:06<05:00, 2.79it/s, loss=0.285, lr=1e-6]\nSteps: 16%|█▌ | 160/1000 [01:07<05:01, 2.78it/s, loss=0.285, lr=1e-6]\nSteps: 16%|█▌ | 160/1000 [01:07<05:01, 2.78it/s, loss=0.279, lr=1e-6]\nSteps: 16%|█▌ | 161/1000 [01:07<05:00, 2.79it/s, loss=0.279, lr=1e-6]\nSteps: 16%|█▌ | 162/1000 [01:07<04:59, 2.80it/s, loss=0.279, lr=1e-6]\nSteps: 16%|█▋ | 163/1000 [01:08<04:58, 2.80it/s, loss=0.279, lr=1e-6]\nSteps: 16%|█▋ | 164/1000 [01:08<04:58, 2.81it/s, loss=0.279, lr=1e-6]\nSteps: 16%|█▋ | 165/1000 [01:08<04:57, 2.80it/s, loss=0.279, lr=1e-6]\nSteps: 17%|█▋ | 166/1000 [01:09<04:57, 2.80it/s, loss=0.279, lr=1e-6]\nSteps: 17%|█▋ | 167/1000 [01:09<04:56, 2.81it/s, loss=0.279, lr=1e-6]\nSteps: 17%|█▋ | 168/1000 [01:10<04:58, 2.79it/s, loss=0.279, lr=1e-6]\nSteps: 17%|█▋ | 169/1000 [01:10<04:58, 2.79it/s, loss=0.279, lr=1e-6]\nSteps: 17%|█▋ | 170/1000 [01:10<04:56, 2.80it/s, loss=0.279, lr=1e-6]\nSteps: 17%|█▋ | 170/1000 [01:11<04:56, 2.80it/s, loss=0.28, lr=1e-6]\nSteps: 17%|█▋ | 171/1000 [01:11<04:57, 2.78it/s, loss=0.28, lr=1e-6]\nSteps: 17%|█▋ | 172/1000 [01:11<04:55, 2.80it/s, loss=0.28, lr=1e-6]\nSteps: 17%|█▋ | 173/1000 [01:11<04:53, 2.82it/s, loss=0.28, lr=1e-6]\nSteps: 17%|█▋ | 174/1000 [01:12<04:52, 2.82it/s, loss=0.28, lr=1e-6]\nSteps: 18%|█▊ | 175/1000 [01:12<04:53, 2.81it/s, loss=0.28, lr=1e-6]\nSteps: 18%|█▊ | 176/1000 [01:12<04:53, 2.81it/s, loss=0.28, lr=1e-6]\nSteps: 18%|█▊ | 177/1000 [01:13<04:53, 2.80it/s, loss=0.28, lr=1e-6]\nSteps: 18%|█▊ | 178/1000 [01:13<04:53, 2.80it/s, loss=0.28, lr=1e-6]\nSteps: 18%|█▊ | 179/1000 [01:13<04:51, 2.81it/s, loss=0.28, lr=1e-6]\nSteps: 18%|█▊ | 180/1000 [01:14<04:51, 2.82it/s, loss=0.28, lr=1e-6]\nSteps: 18%|█▊ | 180/1000 [01:14<04:51, 2.82it/s, loss=0.278, lr=1e-6]\nSteps: 18%|█▊ | 181/1000 [01:14<04:50, 2.82it/s, loss=0.278, lr=1e-6]\nSteps: 18%|█▊ | 182/1000 [01:15<04:49, 2.82it/s, loss=0.278, lr=1e-6]\nSteps: 18%|█▊ | 183/1000 [01:15<04:50, 2.81it/s, loss=0.278, lr=1e-6]\nSteps: 18%|█▊ | 184/1000 [01:15<04:48, 2.83it/s, loss=0.278, lr=1e-6]\nSteps: 18%|█▊ | 185/1000 [01:16<04:53, 2.78it/s, loss=0.278, lr=1e-6]\nSteps: 19%|█▊ | 186/1000 [01:16<04:52, 2.78it/s, loss=0.278, lr=1e-6]\nSteps: 19%|█▊ | 187/1000 [01:16<04:51, 2.79it/s, loss=0.278, lr=1e-6]\nSteps: 19%|█▉ | 188/1000 [01:17<04:50, 2.80it/s, loss=0.278, lr=1e-6]\nSteps: 19%|█▉ | 189/1000 [01:17<04:49, 2.80it/s, loss=0.278, lr=1e-6]\nSteps: 19%|█▉ | 190/1000 [01:17<04:46, 2.82it/s, loss=0.278, lr=1e-6]\nSteps: 19%|█▉ | 190/1000 [01:18<04:46, 2.82it/s, loss=0.279, lr=1e-6]\nSteps: 19%|█▉ | 191/1000 [01:18<04:45, 2.83it/s, loss=0.279, lr=1e-6]\nSteps: 19%|█▉ | 192/1000 [01:18<04:45, 2.83it/s, loss=0.279, lr=1e-6]\nSteps: 19%|█▉ | 193/1000 [01:18<04:44, 2.84it/s, loss=0.279, lr=1e-6]\nSteps: 19%|█▉ | 194/1000 [01:19<04:44, 2.83it/s, loss=0.279, lr=1e-6]\nSteps: 20%|█▉ | 195/1000 [01:19<04:44, 2.83it/s, loss=0.279, lr=1e-6]\nSteps: 20%|█▉ | 196/1000 [01:19<04:45, 2.81it/s, loss=0.279, lr=1e-6]\nSteps: 20%|█▉ | 197/1000 [01:20<04:46, 2.81it/s, loss=0.279, lr=1e-6]\nSteps: 20%|█▉ | 198/1000 [01:20<04:44, 2.82it/s, loss=0.279, lr=1e-6]\nSteps: 20%|█▉ | 199/1000 [01:21<04:45, 2.81it/s, loss=0.279, lr=1e-6]\nSteps: 20%|██ | 200/1000 [01:21<04:45, 2.81it/s, loss=0.279, lr=1e-6]\nSteps: 20%|██ | 200/1000 [01:21<04:45, 2.81it/s, loss=0.276, lr=1e-6]\nSteps: 20%|██ | 201/1000 [01:21<04:44, 2.81it/s, loss=0.276, lr=1e-6]\nSteps: 20%|██ | 202/1000 [01:22<04:43, 2.81it/s, loss=0.276, lr=1e-6]\nSteps: 20%|██ | 203/1000 [01:22<04:41, 2.83it/s, loss=0.276, lr=1e-6]\nSteps: 20%|██ | 204/1000 [01:22<04:39, 2.85it/s, loss=0.276, lr=1e-6]\nSteps: 20%|██ | 205/1000 [01:23<04:40, 2.84it/s, loss=0.276, lr=1e-6]\nSteps: 21%|██ | 206/1000 [01:23<04:40, 2.83it/s, loss=0.276, lr=1e-6]\nSteps: 21%|██ | 207/1000 [01:23<04:39, 2.84it/s, loss=0.276, lr=1e-6]\nSteps: 21%|██ | 208/1000 [01:24<04:38, 2.84it/s, loss=0.276, lr=1e-6]\nSteps: 21%|██ | 209/1000 [01:24<04:41, 2.81it/s, loss=0.276, lr=1e-6]\nSteps: 21%|██ | 210/1000 [01:24<04:41, 2.80it/s, loss=0.276, lr=1e-6]\nSteps: 21%|██ | 210/1000 [01:25<04:41, 2.80it/s, loss=0.275, lr=1e-6]\nSteps: 21%|██ | 211/1000 [01:25<04:40, 2.82it/s, loss=0.275, lr=1e-6]\nSteps: 21%|██ | 212/1000 [01:25<04:39, 2.82it/s, loss=0.275, lr=1e-6]\nSteps: 21%|██▏ | 213/1000 [01:26<04:44, 2.77it/s, loss=0.275, lr=1e-6]\nSteps: 21%|██▏ | 214/1000 [01:26<04:41, 2.79it/s, loss=0.275, lr=1e-6]\nSteps: 22%|██▏ | 215/1000 [01:26<04:38, 2.81it/s, loss=0.275, lr=1e-6]\nSteps: 22%|██▏ | 216/1000 [01:27<04:38, 2.81it/s, loss=0.275, lr=1e-6]\nSteps: 22%|██▏ | 217/1000 [01:27<04:38, 2.81it/s, loss=0.275, lr=1e-6]\nSteps: 22%|██▏ | 218/1000 [01:27<04:36, 2.83it/s, loss=0.275, lr=1e-6]\nSteps: 22%|██▏ | 219/1000 [01:28<04:36, 2.82it/s, loss=0.275, lr=1e-6]\nSteps: 22%|██▏ | 220/1000 [01:28<04:37, 2.81it/s, loss=0.275, lr=1e-6]\nSteps: 22%|██▏ | 220/1000 [01:28<04:37, 2.81it/s, loss=0.275, lr=1e-6]\nSteps: 22%|██▏ | 221/1000 [01:28<04:35, 2.82it/s, loss=0.275, lr=1e-6]\nSteps: 22%|██▏ | 222/1000 [01:29<04:34, 2.84it/s, loss=0.275, lr=1e-6]\nSteps: 22%|██▏ | 223/1000 [01:29<04:33, 2.84it/s, loss=0.275, lr=1e-6]\nSteps: 22%|██▏ | 224/1000 [01:29<04:32, 2.85it/s, loss=0.275, lr=1e-6]\nSteps: 22%|██▎ | 225/1000 [01:30<04:31, 2.86it/s, loss=0.275, lr=1e-6]\nSteps: 23%|██▎ | 226/1000 [01:30<04:31, 2.86it/s, loss=0.275, lr=1e-6]\nSteps: 23%|██▎ | 227/1000 [01:30<04:30, 2.86it/s, loss=0.275, lr=1e-6]\nSteps: 23%|██▎ | 228/1000 [01:31<04:30, 2.86it/s, loss=0.275, lr=1e-6]\nSteps: 23%|██▎ | 229/1000 [01:31<04:30, 2.85it/s, loss=0.275, lr=1e-6]\nSteps: 23%|██▎ | 230/1000 [01:32<04:30, 2.85it/s, loss=0.275, lr=1e-6]\nSteps: 23%|██▎ | 230/1000 [01:32<04:30, 2.85it/s, loss=0.276, lr=1e-6]\nSteps: 23%|██▎ | 231/1000 [01:32<04:29, 2.85it/s, loss=0.276, lr=1e-6]\nSteps: 23%|██▎ | 232/1000 [01:32<04:28, 2.86it/s, loss=0.276, lr=1e-6]\nSteps: 23%|██▎ | 233/1000 [01:33<04:28, 2.86it/s, loss=0.276, lr=1e-6]\nSteps: 23%|██▎ | 234/1000 [01:33<04:27, 2.86it/s, loss=0.276, lr=1e-6]\nSteps: 24%|██▎ | 235/1000 [01:33<04:28, 2.85it/s, loss=0.276, lr=1e-6]\nSteps: 24%|██▎ | 236/1000 [01:34<04:30, 2.82it/s, loss=0.276, lr=1e-6]\nSteps: 24%|██▎ | 237/1000 [01:34<04:30, 2.82it/s, loss=0.276, lr=1e-6]\nSteps: 24%|██▍ | 238/1000 [01:34<04:34, 2.78it/s, loss=0.276, lr=1e-6]\nSteps: 24%|██▍ | 239/1000 [01:35<04:32, 2.79it/s, loss=0.276, lr=1e-6]\nSteps: 24%|██▍ | 240/1000 [01:35<04:32, 2.79it/s, loss=0.276, lr=1e-6]\nSteps: 24%|██▍ | 240/1000 [01:35<04:32, 2.79it/s, loss=0.282, lr=1e-6]\nSteps: 24%|██▍ | 241/1000 [01:35<04:36, 2.75it/s, loss=0.282, lr=1e-6]\nSteps: 24%|██▍ | 242/1000 [01:36<04:34, 2.76it/s, loss=0.282, lr=1e-6]\nSteps: 24%|██▍ | 243/1000 [01:36<04:32, 2.78it/s, loss=0.282, lr=1e-6]\nSteps: 24%|██▍ | 244/1000 [01:37<04:30, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 24%|██▍ | 245/1000 [01:37<04:28, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 25%|██▍ | 246/1000 [01:37<04:28, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 25%|██▍ | 247/1000 [01:38<04:28, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 25%|██▍ | 248/1000 [01:38<04:29, 2.79it/s, loss=0.282, lr=1e-6]\nSteps: 25%|██▍ | 249/1000 [01:38<04:29, 2.79it/s, loss=0.282, lr=1e-6]\nSteps: 25%|██▌ | 250/1000 [01:39<04:30, 2.77it/s, loss=0.282, lr=1e-6]\nSteps: 25%|██▌ | 250/1000 [01:39<04:30, 2.77it/s, loss=0.285, lr=1e-6]\nSteps: 25%|██▌ | 251/1000 [01:39<04:30, 2.77it/s, loss=0.285, lr=1e-6]\nSteps: 25%|██▌ | 252/1000 [01:39<04:29, 2.77it/s, loss=0.285, lr=1e-6]\nSteps: 25%|██▌ | 253/1000 [01:40<04:29, 2.77it/s, loss=0.285, lr=1e-6]\nSteps: 25%|██▌ | 254/1000 [01:40<04:26, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 26%|██▌ | 255/1000 [01:40<04:26, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 26%|██▌ | 256/1000 [01:41<04:22, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 26%|██▌ | 257/1000 [01:41<04:20, 2.85it/s, loss=0.285, lr=1e-6]\nSteps: 26%|██▌ | 258/1000 [01:42<04:22, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 26%|██▌ | 259/1000 [01:42<04:20, 2.85it/s, loss=0.285, lr=1e-6]\nSteps: 26%|██▌ | 260/1000 [01:42<04:18, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 26%|██▌ | 260/1000 [01:43<04:18, 2.86it/s, loss=0.284, lr=1e-6]\nSteps: 26%|██▌ | 261/1000 [01:43<04:19, 2.85it/s, loss=0.284, lr=1e-6]\nSteps: 26%|██▌ | 262/1000 [01:43<04:18, 2.85it/s, loss=0.284, lr=1e-6]\nSteps: 26%|██▋ | 263/1000 [01:43<04:17, 2.87it/s, loss=0.284, lr=1e-6]\nSteps: 26%|██▋ | 264/1000 [01:44<04:18, 2.84it/s, loss=0.284, lr=1e-6]\nSteps: 26%|██▋ | 265/1000 [01:44<04:19, 2.83it/s, loss=0.284, lr=1e-6]\nSteps: 27%|██▋ | 266/1000 [01:44<04:20, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 27%|██▋ | 267/1000 [01:45<04:19, 2.83it/s, loss=0.284, lr=1e-6]\nSteps: 27%|██▋ | 268/1000 [01:45<04:19, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 27%|██▋ | 269/1000 [01:45<04:20, 2.81it/s, loss=0.284, lr=1e-6]\nSteps: 27%|██▋ | 270/1000 [01:46<04:19, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 27%|██▋ | 270/1000 [01:46<04:19, 2.82it/s, loss=0.286, lr=1e-6]\nSteps: 27%|██▋ | 271/1000 [01:46<04:18, 2.82it/s, loss=0.286, lr=1e-6]\nSteps: 27%|██▋ | 272/1000 [01:46<04:18, 2.82it/s, loss=0.286, lr=1e-6]\nSteps: 27%|██▋ | 273/1000 [01:47<04:17, 2.82it/s, loss=0.286, lr=1e-6]\nSteps: 27%|██▋ | 274/1000 [01:47<04:16, 2.84it/s, loss=0.286, lr=1e-6]\nSteps: 28%|██▊ | 275/1000 [01:48<04:15, 2.83it/s, loss=0.286, lr=1e-6]\nSteps: 28%|██▊ | 276/1000 [01:48<04:15, 2.83it/s, loss=0.286, lr=1e-6]\nSteps: 28%|██▊ | 277/1000 [01:48<04:15, 2.83it/s, loss=0.286, lr=1e-6]\nSteps: 28%|██▊ | 278/1000 [01:49<04:16, 2.81it/s, loss=0.286, lr=1e-6]\nSteps: 28%|██▊ | 279/1000 [01:49<04:15, 2.83it/s, loss=0.286, lr=1e-6]\nSteps: 28%|██▊ | 280/1000 [01:49<04:12, 2.85it/s, loss=0.286, lr=1e-6]\nSteps: 28%|██▊ | 280/1000 [01:50<04:12, 2.85it/s, loss=0.287, lr=1e-6]\nSteps: 28%|██▊ | 281/1000 [01:50<04:15, 2.82it/s, loss=0.287, lr=1e-6]\nSteps: 28%|██▊ | 282/1000 [01:50<04:14, 2.82it/s, loss=0.287, lr=1e-6]\nSteps: 28%|██▊ | 283/1000 [01:50<04:12, 2.83it/s, loss=0.287, lr=1e-6]\nSteps: 28%|██▊ | 284/1000 [01:51<04:15, 2.80it/s, loss=0.287, lr=1e-6]\nSteps: 28%|██▊ | 285/1000 [01:51<04:13, 2.82it/s, loss=0.287, lr=1e-6]\nSteps: 29%|██▊ | 286/1000 [01:51<04:11, 2.84it/s, loss=0.287, lr=1e-6]\nSteps: 29%|██▊ | 287/1000 [01:52<04:11, 2.84it/s, loss=0.287, lr=1e-6]\nSteps: 29%|██▉ | 288/1000 [01:52<04:10, 2.84it/s, loss=0.287, lr=1e-6]\nSteps: 29%|██▉ | 289/1000 [01:52<04:10, 2.84it/s, loss=0.287, lr=1e-6]\nSteps: 29%|██▉ | 290/1000 [01:53<04:09, 2.84it/s, loss=0.287, lr=1e-6]\nSteps: 29%|██▉ | 290/1000 [01:53<04:09, 2.84it/s, loss=0.287, lr=1e-6]\nSteps: 29%|██▉ | 291/1000 [01:53<04:08, 2.85it/s, loss=0.287, lr=1e-6]\nSteps: 29%|██▉ | 292/1000 [01:53<04:07, 2.85it/s, loss=0.287, lr=1e-6]\nSteps: 29%|██▉ | 293/1000 [01:54<04:09, 2.83it/s, loss=0.287, lr=1e-6]\nSteps: 29%|██▉ | 294/1000 [01:54<04:09, 2.83it/s, loss=0.287, lr=1e-6]\nSteps: 30%|██▉ | 295/1000 [01:55<04:09, 2.82it/s, loss=0.287, lr=1e-6]\nSteps: 30%|██▉ | 296/1000 [01:55<04:07, 2.84it/s, loss=0.287, lr=1e-6]\nSteps: 30%|██▉ | 297/1000 [01:55<04:05, 2.86it/s, loss=0.287, lr=1e-6]\nSteps: 30%|██▉ | 298/1000 [01:56<04:13, 2.77it/s, loss=0.287, lr=1e-6]\nSteps: 30%|██▉ | 299/1000 [01:56<04:10, 2.79it/s, loss=0.287, lr=1e-6]\nSteps: 30%|███ | 300/1000 [01:56<04:09, 2.81it/s, loss=0.287, lr=1e-6]\nSteps: 30%|███ | 300/1000 [01:57<04:09, 2.81it/s, loss=0.288, lr=1e-6]\nSteps: 30%|███ | 301/1000 [01:57<04:11, 2.77it/s, loss=0.288, lr=1e-6]\nSteps: 30%|███ | 302/1000 [01:57<04:09, 2.80it/s, loss=0.288, lr=1e-6]\nSteps: 30%|███ | 303/1000 [01:57<04:08, 2.81it/s, loss=0.288, lr=1e-6]\nSteps: 30%|███ | 304/1000 [01:58<04:06, 2.83it/s, loss=0.288, lr=1e-6]\nSteps: 30%|███ | 305/1000 [01:58<04:06, 2.82it/s, loss=0.288, lr=1e-6]\nSteps: 31%|███ | 306/1000 [01:58<04:05, 2.83it/s, loss=0.288, lr=1e-6]\nSteps: 31%|███ | 307/1000 [01:59<04:06, 2.81it/s, loss=0.288, lr=1e-6]\nSteps: 31%|███ | 308/1000 [01:59<04:06, 2.81it/s, loss=0.288, lr=1e-6]\nSteps: 31%|███ | 309/1000 [02:00<04:06, 2.81it/s, loss=0.288, lr=1e-6]\nSteps: 31%|███ | 310/1000 [02:00<04:11, 2.75it/s, loss=0.288, lr=1e-6]\nSteps: 31%|███ | 310/1000 [02:00<04:11, 2.75it/s, loss=0.29, lr=1e-6]\nSteps: 31%|███ | 311/1000 [02:00<04:11, 2.74it/s, loss=0.29, lr=1e-6]\nSteps: 31%|███ | 312/1000 [02:01<04:08, 2.77it/s, loss=0.29, lr=1e-6]\nSteps: 31%|███▏ | 313/1000 [02:01<04:10, 2.75it/s, loss=0.29, lr=1e-6]\nSteps: 31%|███▏ | 314/1000 [02:01<04:08, 2.76it/s, loss=0.29, lr=1e-6]\nSteps: 32%|███▏ | 315/1000 [02:02<04:06, 2.78it/s, loss=0.29, lr=1e-6]\nSteps: 32%|███▏ | 316/1000 [02:02<04:03, 2.80it/s, loss=0.29, lr=1e-6]\nSteps: 32%|███▏ | 317/1000 [02:02<04:03, 2.80it/s, loss=0.29, lr=1e-6]\nSteps: 32%|███▏ | 318/1000 [02:03<04:02, 2.81it/s, loss=0.29, lr=1e-6]\nSteps: 32%|███▏ | 319/1000 [02:03<04:00, 2.83it/s, loss=0.29, lr=1e-6]\nSteps: 32%|███▏ | 320/1000 [02:03<03:58, 2.85it/s, loss=0.29, lr=1e-6]\nSteps: 32%|███▏ | 320/1000 [02:04<03:58, 2.85it/s, loss=0.292, lr=1e-6]\nSteps: 32%|███▏ | 321/1000 [02:04<03:58, 2.85it/s, loss=0.292, lr=1e-6]\nSteps: 32%|███▏ | 322/1000 [02:04<03:57, 2.85it/s, loss=0.292, lr=1e-6]\nSteps: 32%|███▏ | 323/1000 [02:05<03:58, 2.84it/s, loss=0.292, lr=1e-6]\nSteps: 32%|███▏ | 324/1000 [02:05<03:59, 2.82it/s, loss=0.292, lr=1e-6]\nSteps: 32%|███▎ | 325/1000 [02:05<03:57, 2.84it/s, loss=0.292, lr=1e-6]\nSteps: 33%|███▎ | 326/1000 [02:06<04:01, 2.79it/s, loss=0.292, lr=1e-6]\nSteps: 33%|███▎ | 327/1000 [02:06<04:01, 2.79it/s, loss=0.292, lr=1e-6]\nSteps: 33%|███▎ | 328/1000 [02:06<03:59, 2.81it/s, loss=0.292, lr=1e-6]\nSteps: 33%|███▎ | 329/1000 [02:07<04:00, 2.80it/s, loss=0.292, lr=1e-6]\nSteps: 33%|███▎ | 330/1000 [02:07<04:01, 2.78it/s, loss=0.292, lr=1e-6]\nSteps: 33%|███▎ | 330/1000 [02:07<04:01, 2.78it/s, loss=0.294, lr=1e-6]\nSteps: 33%|███▎ | 331/1000 [02:07<03:58, 2.80it/s, loss=0.294, lr=1e-6]\nSteps: 33%|███▎ | 332/1000 [02:08<03:56, 2.83it/s, loss=0.294, lr=1e-6]\nSteps: 33%|███▎ | 333/1000 [02:08<03:55, 2.83it/s, loss=0.294, lr=1e-6]\nSteps: 33%|███▎ | 334/1000 [02:08<03:54, 2.85it/s, loss=0.294, lr=1e-6]\nSteps: 34%|███▎ | 335/1000 [02:09<03:53, 2.85it/s, loss=0.294, lr=1e-6]\nSteps: 34%|███▎ | 336/1000 [02:09<03:52, 2.85it/s, loss=0.294, lr=1e-6]\nSteps: 34%|███▎ | 337/1000 [02:10<03:53, 2.85it/s, loss=0.294, lr=1e-6]\nSteps: 34%|███▍ | 338/1000 [02:10<03:51, 2.85it/s, loss=0.294, lr=1e-6]\nSteps: 34%|███▍ | 339/1000 [02:10<03:52, 2.84it/s, loss=0.294, lr=1e-6]\nSteps: 34%|███▍ | 340/1000 [02:11<03:50, 2.86it/s, loss=0.294, lr=1e-6]\nSteps: 34%|███▍ | 340/1000 [02:11<03:50, 2.86it/s, loss=0.291, lr=1e-6]\nSteps: 34%|███▍ | 341/1000 [02:11<03:51, 2.85it/s, loss=0.291, lr=1e-6]\nSteps: 34%|███▍ | 342/1000 [02:11<03:50, 2.86it/s, loss=0.291, lr=1e-6]\nSteps: 34%|███▍ | 343/1000 [02:12<03:48, 2.87it/s, loss=0.291, lr=1e-6]\nSteps: 34%|███▍ | 344/1000 [02:12<03:50, 2.85it/s, loss=0.291, lr=1e-6]\nSteps: 34%|███▍ | 345/1000 [02:12<03:48, 2.87it/s, loss=0.291, lr=1e-6]\nSteps: 35%|███▍ | 346/1000 [02:13<03:47, 2.87it/s, loss=0.291, lr=1e-6]\nSteps: 35%|███▍ | 347/1000 [02:13<03:48, 2.86it/s, loss=0.291, lr=1e-6]\nSteps: 35%|███▍ | 348/1000 [02:13<03:48, 2.86it/s, loss=0.291, lr=1e-6]\nSteps: 35%|███▍ | 349/1000 [02:14<03:49, 2.83it/s, loss=0.291, lr=1e-6]\nSteps: 35%|███▌ | 350/1000 [02:14<03:50, 2.81it/s, loss=0.291, lr=1e-6]\nSteps: 35%|███▌ | 350/1000 [02:14<03:50, 2.81it/s, loss=0.293, lr=1e-6]\nSteps: 35%|███▌ | 351/1000 [02:14<03:53, 2.79it/s, loss=0.293, lr=1e-6]\nSteps: 35%|███▌ | 352/1000 [02:15<03:51, 2.80it/s, loss=0.293, lr=1e-6]\nSteps: 35%|███▌ | 353/1000 [02:15<03:51, 2.79it/s, loss=0.293, lr=1e-6]\nSteps: 35%|███▌ | 354/1000 [02:16<03:55, 2.75it/s, loss=0.293, lr=1e-6]\nSteps: 36%|███▌ | 355/1000 [02:16<03:52, 2.78it/s, loss=0.293, lr=1e-6]\nSteps: 36%|███▌ | 356/1000 [02:16<03:50, 2.79it/s, loss=0.293, lr=1e-6]\nSteps: 36%|███▌ | 357/1000 [02:17<03:50, 2.79it/s, loss=0.293, lr=1e-6]\nSteps: 36%|███▌ | 358/1000 [02:17<03:48, 2.81it/s, loss=0.293, lr=1e-6]\nSteps: 36%|███▌ | 359/1000 [02:17<03:46, 2.82it/s, loss=0.293, lr=1e-6]\nSteps: 36%|███▌ | 360/1000 [02:18<03:46, 2.83it/s, loss=0.293, lr=1e-6]\nSteps: 36%|███▌ | 360/1000 [02:18<03:46, 2.83it/s, loss=0.291, lr=1e-6]\nSteps: 36%|███▌ | 361/1000 [02:18<03:45, 2.83it/s, loss=0.291, lr=1e-6]\nSteps: 36%|███▌ | 362/1000 [02:18<03:43, 2.85it/s, loss=0.291, lr=1e-6]\nSteps: 36%|███▋ | 363/1000 [02:19<03:42, 2.86it/s, loss=0.291, lr=1e-6]\nSteps: 36%|███▋ | 364/1000 [02:19<03:42, 2.86it/s, loss=0.291, lr=1e-6]\nSteps: 36%|███▋ | 365/1000 [02:19<03:42, 2.85it/s, loss=0.291, lr=1e-6]\nSteps: 37%|███▋ | 366/1000 [02:20<03:42, 2.85it/s, loss=0.291, lr=1e-6]\nSteps: 37%|███▋ | 367/1000 [02:20<03:42, 2.84it/s, loss=0.291, lr=1e-6]\nSteps: 37%|███▋ | 368/1000 [02:20<03:43, 2.83it/s, loss=0.291, lr=1e-6]\nSteps: 37%|███▋ | 369/1000 [02:21<03:42, 2.84it/s, loss=0.291, lr=1e-6]\nSteps: 37%|███▋ | 370/1000 [02:21<03:41, 2.84it/s, loss=0.291, lr=1e-6]\nSteps: 37%|███▋ | 370/1000 [02:22<03:41, 2.84it/s, loss=0.29, lr=1e-6]\nSteps: 37%|███▋ | 371/1000 [02:22<03:42, 2.83it/s, loss=0.29, lr=1e-6]\nSteps: 37%|███▋ | 372/1000 [02:22<03:42, 2.83it/s, loss=0.29, lr=1e-6]\nSteps: 37%|███▋ | 373/1000 [02:22<03:41, 2.83it/s, loss=0.29, lr=1e-6]\nSteps: 37%|███▋ | 374/1000 [02:23<03:41, 2.83it/s, loss=0.29, lr=1e-6]\nSteps: 38%|███▊ | 375/1000 [02:23<03:41, 2.83it/s, loss=0.29, lr=1e-6]\nSteps: 38%|███▊ | 376/1000 [02:23<03:39, 2.84it/s, loss=0.29, lr=1e-6]\nSteps: 38%|███▊ | 377/1000 [02:24<03:40, 2.83it/s, loss=0.29, lr=1e-6]\nSteps: 38%|███▊ | 378/1000 [02:24<03:39, 2.83it/s, loss=0.29, lr=1e-6]\nSteps: 38%|███▊ | 379/1000 [02:24<03:40, 2.82it/s, loss=0.29, lr=1e-6]\nSteps: 38%|███▊ | 380/1000 [02:25<03:40, 2.81it/s, loss=0.29, lr=1e-6]\nSteps: 38%|███▊ | 380/1000 [02:25<03:40, 2.81it/s, loss=0.287, lr=1e-6]\nSteps: 38%|███▊ | 381/1000 [02:25<03:39, 2.82it/s, loss=0.287, lr=1e-6]\nSteps: 38%|███▊ | 382/1000 [02:25<03:42, 2.78it/s, loss=0.287, lr=1e-6]\nSteps: 38%|███▊ | 383/1000 [02:26<03:40, 2.80it/s, loss=0.287, lr=1e-6]\nSteps: 38%|███▊ | 384/1000 [02:26<03:38, 2.81it/s, loss=0.287, lr=1e-6]\nSteps: 38%|███▊ | 385/1000 [02:26<03:38, 2.81it/s, loss=0.287, lr=1e-6]\nSteps: 39%|███▊ | 386/1000 [02:27<03:38, 2.81it/s, loss=0.287, lr=1e-6]\nSteps: 39%|███▊ | 387/1000 [02:27<03:38, 2.81it/s, loss=0.287, lr=1e-6]\nSteps: 39%|███▉ | 388/1000 [02:28<03:39, 2.79it/s, loss=0.287, lr=1e-6]\nSteps: 39%|███▉ | 389/1000 [02:28<03:37, 2.80it/s, loss=0.287, lr=1e-6]\nSteps: 39%|███▉ | 390/1000 [02:28<03:37, 2.81it/s, loss=0.287, lr=1e-6]\nSteps: 39%|███▉ | 390/1000 [02:29<03:37, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 39%|███▉ | 391/1000 [02:29<03:38, 2.78it/s, loss=0.285, lr=1e-6]\nSteps: 39%|███▉ | 392/1000 [02:29<03:38, 2.78it/s, loss=0.285, lr=1e-6]\nSteps: 39%|███▉ | 393/1000 [02:29<03:37, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 39%|███▉ | 394/1000 [02:30<03:36, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 40%|███▉ | 395/1000 [02:30<03:35, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 40%|███▉ | 396/1000 [02:30<03:36, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 40%|███▉ | 397/1000 [02:31<03:35, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 40%|███▉ | 398/1000 [02:31<03:34, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 40%|███▉ | 399/1000 [02:32<03:36, 2.78it/s, loss=0.285, lr=1e-6]\nSteps: 40%|████ | 400/1000 [02:32<03:33, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 40%|████ | 400/1000 [02:32<03:33, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 40%|████ | 401/1000 [02:32<03:31, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 40%|████ | 402/1000 [02:33<03:31, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 40%|████ | 403/1000 [02:33<03:30, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 40%|████ | 404/1000 [02:33<03:29, 2.85it/s, loss=0.285, lr=1e-6]\nSteps: 40%|████ | 405/1000 [02:34<03:29, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 41%|████ | 406/1000 [02:34<03:29, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 41%|████ | 407/1000 [02:34<03:29, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 41%|████ | 408/1000 [02:35<03:28, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 41%|████ | 409/1000 [02:35<03:28, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 41%|████ | 410/1000 [02:35<03:29, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 41%|████ | 410/1000 [02:36<03:29, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 41%|████ | 411/1000 [02:36<03:28, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 41%|████ | 412/1000 [02:36<03:27, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 41%|████▏ | 413/1000 [02:36<03:27, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 41%|████▏ | 414/1000 [02:37<03:27, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 42%|████▏ | 415/1000 [02:37<03:27, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 42%|████▏ | 416/1000 [02:37<03:25, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 42%|████▏ | 417/1000 [02:38<03:26, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 42%|████▏ | 418/1000 [02:38<03:25, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 42%|████▏ | 419/1000 [02:39<03:24, 2.85it/s, loss=0.285, lr=1e-6]\nSteps: 42%|████▏ | 420/1000 [02:39<03:25, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 42%|████▏ | 420/1000 [02:39<03:25, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 42%|████▏ | 421/1000 [02:39<03:23, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 42%|████▏ | 422/1000 [02:40<03:22, 2.85it/s, loss=0.285, lr=1e-6]\nSteps: 42%|████▏ | 423/1000 [02:40<03:22, 2.85it/s, loss=0.285, lr=1e-6]\nSteps: 42%|████▏ | 424/1000 [02:40<03:22, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 42%|████▎ | 425/1000 [02:41<03:21, 2.85it/s, loss=0.285, lr=1e-6]\nSteps: 43%|████▎ | 426/1000 [02:41<03:21, 2.85it/s, loss=0.285, lr=1e-6]\nSteps: 43%|████▎ | 427/1000 [02:41<03:19, 2.87it/s, loss=0.285, lr=1e-6]\nSteps: 43%|████▎ | 428/1000 [02:42<03:18, 2.87it/s, loss=0.285, lr=1e-6]\nSteps: 43%|████▎ | 429/1000 [02:42<03:19, 2.87it/s, loss=0.285, lr=1e-6]\nSteps: 43%|████▎ | 430/1000 [02:42<03:19, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 43%|████▎ | 430/1000 [02:43<03:19, 2.86it/s, loss=0.286, lr=1e-6]\nSteps: 43%|████▎ | 431/1000 [02:43<03:19, 2.86it/s, loss=0.286, lr=1e-6]\nSteps: 43%|████▎ | 432/1000 [02:43<03:18, 2.86it/s, loss=0.286, lr=1e-6]\nSteps: 43%|████▎ | 433/1000 [02:43<03:18, 2.86it/s, loss=0.286, lr=1e-6]\nSteps: 43%|████▎ | 434/1000 [02:44<03:19, 2.84it/s, loss=0.286, lr=1e-6]\nSteps: 44%|████▎ | 435/1000 [02:44<03:18, 2.84it/s, loss=0.286, lr=1e-6]\nSteps: 44%|████▎ | 436/1000 [02:45<03:20, 2.81it/s, loss=0.286, lr=1e-6]\nSteps: 44%|████▎ | 437/1000 [02:45<03:19, 2.82it/s, loss=0.286, lr=1e-6]\nSteps: 44%|████▍ | 438/1000 [02:45<03:17, 2.84it/s, loss=0.286, lr=1e-6]\nSteps: 44%|████▍ | 439/1000 [02:46<03:19, 2.81it/s, loss=0.286, lr=1e-6]\nSteps: 44%|████▍ | 440/1000 [02:46<03:18, 2.82it/s, loss=0.286, lr=1e-6]\nSteps: 44%|████▍ | 440/1000 [02:46<03:18, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 44%|████▍ | 441/1000 [02:46<03:18, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 44%|████▍ | 442/1000 [02:47<03:16, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 44%|████▍ | 443/1000 [02:47<03:18, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 44%|████▍ | 444/1000 [02:47<03:16, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 44%|████▍ | 445/1000 [02:48<03:15, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 45%|████▍ | 446/1000 [02:48<03:15, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 45%|████▍ | 447/1000 [02:48<03:15, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 45%|████▍ | 448/1000 [02:49<03:14, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 45%|████▍ | 449/1000 [02:49<03:15, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 45%|████▌ | 450/1000 [02:49<03:13, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 45%|████▌ | 450/1000 [02:50<03:13, 2.84it/s, loss=0.286, lr=1e-6]\nSteps: 45%|████▌ | 451/1000 [02:50<03:13, 2.84it/s, loss=0.286, lr=1e-6]\nSteps: 45%|████▌ | 452/1000 [02:50<03:13, 2.84it/s, loss=0.286, lr=1e-6]\nSteps: 45%|████▌ | 453/1000 [02:51<03:12, 2.84it/s, loss=0.286, lr=1e-6]\nSteps: 45%|████▌ | 454/1000 [02:51<03:12, 2.84it/s, loss=0.286, lr=1e-6]\nSteps: 46%|████▌ | 455/1000 [02:51<03:10, 2.86it/s, loss=0.286, lr=1e-6]\nSteps: 46%|████▌ | 456/1000 [02:52<03:11, 2.84it/s, loss=0.286, lr=1e-6]\nSteps: 46%|████▌ | 457/1000 [02:52<03:12, 2.83it/s, loss=0.286, lr=1e-6]\nSteps: 46%|████▌ | 458/1000 [02:52<03:11, 2.84it/s, loss=0.286, lr=1e-6]\nSteps: 46%|████▌ | 459/1000 [02:53<03:10, 2.84it/s, loss=0.286, lr=1e-6]\nSteps: 46%|████▌ | 460/1000 [02:53<03:11, 2.82it/s, loss=0.286, lr=1e-6]\nSteps: 46%|████▌ | 460/1000 [02:53<03:11, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 46%|████▌ | 461/1000 [02:53<03:10, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 46%|████▌ | 462/1000 [02:54<03:08, 2.85it/s, loss=0.285, lr=1e-6]\nSteps: 46%|████▋ | 463/1000 [02:54<03:11, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 46%|████▋ | 464/1000 [02:54<03:11, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 46%|████▋ | 465/1000 [02:55<03:09, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 47%|████▋ | 466/1000 [02:55<03:09, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 47%|████▋ | 467/1000 [02:55<03:10, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 47%|████▋ | 468/1000 [02:56<03:08, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 47%|████▋ | 469/1000 [02:56<03:07, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 47%|████▋ | 470/1000 [02:57<03:06, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 47%|████▋ | 470/1000 [02:57<03:06, 2.84it/s, loss=0.283, lr=1e-6]\nSteps: 47%|████▋ | 471/1000 [02:57<03:05, 2.84it/s, loss=0.283, lr=1e-6]\nSteps: 47%|████▋ | 472/1000 [02:57<03:05, 2.85it/s, loss=0.283, lr=1e-6]\nSteps: 47%|████▋ | 473/1000 [02:58<03:04, 2.86it/s, loss=0.283, lr=1e-6]\nSteps: 47%|████▋ | 474/1000 [02:58<03:04, 2.85it/s, loss=0.283, lr=1e-6]\nSteps: 48%|████▊ | 475/1000 [02:58<03:04, 2.84it/s, loss=0.283, lr=1e-6]\nSteps: 48%|████▊ | 476/1000 [02:59<03:05, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 48%|████▊ | 477/1000 [02:59<03:05, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 48%|████▊ | 478/1000 [02:59<03:04, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 48%|████▊ | 479/1000 [03:00<03:03, 2.84it/s, loss=0.283, lr=1e-6]\nSteps: 48%|████▊ | 480/1000 [03:00<03:03, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 48%|████▊ | 480/1000 [03:00<03:03, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 48%|████▊ | 481/1000 [03:00<03:02, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 48%|████▊ | 482/1000 [03:01<03:01, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 48%|████▊ | 483/1000 [03:01<03:00, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 48%|████▊ | 484/1000 [03:01<02:59, 2.87it/s, loss=0.285, lr=1e-6]\nSteps: 48%|████▊ | 485/1000 [03:02<02:58, 2.88it/s, loss=0.285, lr=1e-6]\nSteps: 49%|████▊ | 486/1000 [03:02<02:59, 2.87it/s, loss=0.285, lr=1e-6]\nSteps: 49%|████▊ | 487/1000 [03:02<02:59, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 49%|████▉ | 488/1000 [03:03<02:58, 2.87it/s, loss=0.285, lr=1e-6]\nSteps: 49%|████▉ | 489/1000 [03:03<02:58, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 49%|████▉ | 490/1000 [03:04<02:57, 2.87it/s, loss=0.285, lr=1e-6]\nSteps: 49%|████▉ | 490/1000 [03:04<02:57, 2.87it/s, loss=0.283, lr=1e-6]\nSteps: 49%|████▉ | 491/1000 [03:04<02:57, 2.87it/s, loss=0.283, lr=1e-6]\nSteps: 49%|████▉ | 492/1000 [03:04<02:58, 2.85it/s, loss=0.283, lr=1e-6]\nSteps: 49%|████▉ | 493/1000 [03:05<02:59, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 49%|████▉ | 494/1000 [03:05<02:58, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 50%|████▉ | 495/1000 [03:05<02:58, 2.82it/s, loss=0.283, lr=1e-6]\nSteps: 50%|████▉ | 496/1000 [03:06<02:59, 2.81it/s, loss=0.283, lr=1e-6]\nSteps: 50%|████▉ | 497/1000 [03:06<02:58, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 50%|████▉ | 498/1000 [03:06<02:57, 2.82it/s, loss=0.283, lr=1e-6]\nSteps: 50%|████▉ | 499/1000 [03:07<02:58, 2.81it/s, loss=0.283, lr=1e-6]\nSteps: 50%|█████ | 500/1000 [03:07<02:58, 2.80it/s, loss=0.283, lr=1e-6]\nSteps: 50%|█████ | 500/1000 [03:07<02:58, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 50%|█████ | 501/1000 [03:07<02:58, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 50%|█████ | 502/1000 [03:08<02:56, 2.82it/s, loss=0.282, lr=1e-6]\nSteps: 50%|█████ | 503/1000 [03:08<02:55, 2.83it/s, loss=0.282, lr=1e-6]\nSteps: 50%|█████ | 504/1000 [03:09<02:55, 2.83it/s, loss=0.282, lr=1e-6]\nSteps: 50%|█████ | 505/1000 [03:09<02:54, 2.84it/s, loss=0.282, lr=1e-6]\nSteps: 51%|█████ | 506/1000 [03:09<02:53, 2.86it/s, loss=0.282, lr=1e-6]\nSteps: 51%|█████ | 507/1000 [03:10<02:52, 2.86it/s, loss=0.282, lr=1e-6]\nSteps: 51%|█████ | 508/1000 [03:10<02:51, 2.87it/s, loss=0.282, lr=1e-6]\nSteps: 51%|█████ | 509/1000 [03:10<02:52, 2.85it/s, loss=0.282, lr=1e-6]\nSteps: 51%|█████ | 510/1000 [03:11<02:51, 2.85it/s, loss=0.282, lr=1e-6]\nSteps: 51%|█████ | 510/1000 [03:11<02:51, 2.85it/s, loss=0.284, lr=1e-6]\nSteps: 51%|█████ | 511/1000 [03:11<02:51, 2.85it/s, loss=0.284, lr=1e-6]\nSteps: 51%|█████ | 512/1000 [03:11<02:51, 2.85it/s, loss=0.284, lr=1e-6]\nSteps: 51%|█████▏ | 513/1000 [03:12<02:52, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 51%|█████▏ | 514/1000 [03:12<02:52, 2.81it/s, loss=0.284, lr=1e-6]\nSteps: 52%|█████▏ | 515/1000 [03:12<02:51, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 52%|█████▏ | 516/1000 [03:13<02:51, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 52%|█████▏ | 517/1000 [03:13<02:50, 2.83it/s, loss=0.284, lr=1e-6]\nSteps: 52%|█████▏ | 518/1000 [03:13<02:50, 2.83it/s, loss=0.284, lr=1e-6]\nSteps: 52%|█████▏ | 519/1000 [03:14<02:50, 2.83it/s, loss=0.284, lr=1e-6]\nSteps: 52%|█████▏ | 520/1000 [03:14<02:50, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 52%|█████▏ | 520/1000 [03:14<02:50, 2.82it/s, loss=0.281, lr=1e-6]\nSteps: 52%|█████▏ | 521/1000 [03:15<02:50, 2.82it/s, loss=0.281, lr=1e-6]\nSteps: 52%|█████▏ | 522/1000 [03:15<02:48, 2.83it/s, loss=0.281, lr=1e-6]\nSteps: 52%|█████▏ | 523/1000 [03:15<02:48, 2.82it/s, loss=0.281, lr=1e-6]\nSteps: 52%|█████▏ | 524/1000 [03:16<02:52, 2.75it/s, loss=0.281, lr=1e-6]\nSteps: 52%|█████▎ | 525/1000 [03:16<02:51, 2.77it/s, loss=0.281, lr=1e-6]\nSteps: 53%|█████▎ | 526/1000 [03:16<02:49, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 53%|█████▎ | 527/1000 [03:17<02:49, 2.79it/s, loss=0.281, lr=1e-6]\nSteps: 53%|█████▎ | 528/1000 [03:17<02:47, 2.81it/s, loss=0.281, lr=1e-6]\nSteps: 53%|█████▎ | 529/1000 [03:17<02:46, 2.83it/s, loss=0.281, lr=1e-6]\nSteps: 53%|█████▎ | 530/1000 [03:18<02:45, 2.83it/s, loss=0.281, lr=1e-6]\nSteps: 53%|█████▎ | 530/1000 [03:18<02:45, 2.83it/s, loss=0.284, lr=1e-6]\nSteps: 53%|█████▎ | 531/1000 [03:18<02:46, 2.81it/s, loss=0.284, lr=1e-6]\nSteps: 53%|█████▎ | 532/1000 [03:18<02:45, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 53%|█████▎ | 533/1000 [03:19<02:45, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 53%|█████▎ | 534/1000 [03:19<02:45, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 54%|█████▎ | 535/1000 [03:19<02:43, 2.84it/s, loss=0.284, lr=1e-6]\nSteps: 54%|█████▎ | 536/1000 [03:20<02:43, 2.83it/s, loss=0.284, lr=1e-6]\nSteps: 54%|█████▎ | 537/1000 [03:20<02:45, 2.81it/s, loss=0.284, lr=1e-6]\nSteps: 54%|█████▍ | 538/1000 [03:21<02:45, 2.79it/s, loss=0.284, lr=1e-6]\nSteps: 54%|█████▍ | 539/1000 [03:21<02:45, 2.78it/s, loss=0.284, lr=1e-6]\nSteps: 54%|█████▍ | 540/1000 [03:21<02:44, 2.79it/s, loss=0.284, lr=1e-6]\nSteps: 54%|█████▍ | 540/1000 [03:22<02:44, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 54%|█████▍ | 541/1000 [03:22<02:44, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 54%|█████▍ | 542/1000 [03:22<02:44, 2.78it/s, loss=0.283, lr=1e-6]\nSteps: 54%|█████▍ | 543/1000 [03:22<02:44, 2.78it/s, loss=0.283, lr=1e-6]\nSteps: 54%|█████▍ | 544/1000 [03:23<02:45, 2.76it/s, loss=0.283, lr=1e-6]\nSteps: 55%|█████▍ | 545/1000 [03:23<02:43, 2.78it/s, loss=0.283, lr=1e-6]\nSteps: 55%|█████▍ | 546/1000 [03:23<02:42, 2.80it/s, loss=0.283, lr=1e-6]\nSteps: 55%|█████▍ | 547/1000 [03:24<02:41, 2.81it/s, loss=0.283, lr=1e-6]\nSteps: 55%|█████▍ | 548/1000 [03:24<02:40, 2.81it/s, loss=0.283, lr=1e-6]\nSteps: 55%|█████▍ | 549/1000 [03:24<02:40, 2.81it/s, loss=0.283, lr=1e-6]\nSteps: 55%|█████▌ | 550/1000 [03:25<02:39, 2.82it/s, loss=0.283, lr=1e-6]\nSteps: 55%|█████▌ | 550/1000 [03:25<02:39, 2.82it/s, loss=0.28, lr=1e-6]\nSteps: 55%|█████▌ | 551/1000 [03:25<02:38, 2.84it/s, loss=0.28, lr=1e-6]\nSteps: 55%|█████▌ | 552/1000 [03:26<02:40, 2.80it/s, loss=0.28, lr=1e-6]\nSteps: 55%|█████▌ | 553/1000 [03:26<02:39, 2.81it/s, loss=0.28, lr=1e-6]\nSteps: 55%|█████▌ | 554/1000 [03:26<02:38, 2.82it/s, loss=0.28, lr=1e-6]\nSteps: 56%|█████▌ | 555/1000 [03:27<02:37, 2.82it/s, loss=0.28, lr=1e-6]\nSteps: 56%|█████▌ | 556/1000 [03:27<02:37, 2.81it/s, loss=0.28, lr=1e-6]\nSteps: 56%|█████▌ | 557/1000 [03:27<02:37, 2.81it/s, loss=0.28, lr=1e-6]\nSteps: 56%|█████▌ | 558/1000 [03:28<02:37, 2.80it/s, loss=0.28, lr=1e-6]\nSteps: 56%|█████▌ | 559/1000 [03:28<02:40, 2.75it/s, loss=0.28, lr=1e-6]\nSteps: 56%|█████▌ | 560/1000 [03:28<02:41, 2.73it/s, loss=0.28, lr=1e-6]\nSteps: 56%|█████▌ | 560/1000 [03:29<02:41, 2.73it/s, loss=0.279, lr=1e-6]\nSteps: 56%|█████▌ | 561/1000 [03:29<02:41, 2.71it/s, loss=0.279, lr=1e-6]\nSteps: 56%|█████▌ | 562/1000 [03:29<02:40, 2.72it/s, loss=0.279, lr=1e-6]\nSteps: 56%|█████▋ | 563/1000 [03:30<02:40, 2.73it/s, loss=0.279, lr=1e-6]\nSteps: 56%|█████▋ | 564/1000 [03:30<02:39, 2.74it/s, loss=0.279, lr=1e-6]\nSteps: 56%|█████▋ | 565/1000 [03:30<02:38, 2.75it/s, loss=0.279, lr=1e-6]\nSteps: 57%|█████▋ | 566/1000 [03:31<02:35, 2.79it/s, loss=0.279, lr=1e-6]\nSteps: 57%|█████▋ | 567/1000 [03:31<02:35, 2.78it/s, loss=0.279, lr=1e-6]\nSteps: 57%|█████▋ | 568/1000 [03:31<02:33, 2.81it/s, loss=0.279, lr=1e-6]\nSteps: 57%|█████▋ | 569/1000 [03:32<02:32, 2.82it/s, loss=0.279, lr=1e-6]\nSteps: 57%|█████▋ | 570/1000 [03:32<02:32, 2.82it/s, loss=0.279, lr=1e-6]\nSteps: 57%|█████▋ | 570/1000 [03:32<02:32, 2.82it/s, loss=0.28, lr=1e-6]\nSteps: 57%|█████▋ | 571/1000 [03:32<02:30, 2.85it/s, loss=0.28, lr=1e-6]\nSteps: 57%|█████▋ | 572/1000 [03:33<02:29, 2.86it/s, loss=0.28, lr=1e-6]\nSteps: 57%|█████▋ | 573/1000 [03:33<02:30, 2.84it/s, loss=0.28, lr=1e-6]\nSteps: 57%|█████▋ | 574/1000 [03:33<02:29, 2.85it/s, loss=0.28, lr=1e-6]\nSteps: 57%|█████▊ | 575/1000 [03:34<02:31, 2.81it/s, loss=0.28, lr=1e-6]\nSteps: 58%|█████▊ | 576/1000 [03:34<02:31, 2.79it/s, loss=0.28, lr=1e-6]\nSteps: 58%|█████▊ | 577/1000 [03:35<02:31, 2.78it/s, loss=0.28, lr=1e-6]\nSteps: 58%|█████▊ | 578/1000 [03:35<02:31, 2.79it/s, loss=0.28, lr=1e-6]\nSteps: 58%|█████▊ | 579/1000 [03:35<02:29, 2.81it/s, loss=0.28, lr=1e-6]\nSteps: 58%|█████▊ | 580/1000 [03:36<02:32, 2.76it/s, loss=0.28, lr=1e-6]\nSteps: 58%|█████▊ | 580/1000 [03:36<02:32, 2.76it/s, loss=0.28, lr=1e-6]\nSteps: 58%|█████▊ | 581/1000 [03:36<02:31, 2.77it/s, loss=0.28, lr=1e-6]\nSteps: 58%|█████▊ | 582/1000 [03:36<02:29, 2.79it/s, loss=0.28, lr=1e-6]\nSteps: 58%|█████▊ | 583/1000 [03:37<02:29, 2.79it/s, loss=0.28, lr=1e-6]\nSteps: 58%|█████▊ | 584/1000 [03:37<02:29, 2.79it/s, loss=0.28, lr=1e-6]\nSteps: 58%|█████▊ | 585/1000 [03:37<02:27, 2.81it/s, loss=0.28, lr=1e-6]\nSteps: 59%|█████▊ | 586/1000 [03:38<02:27, 2.80it/s, loss=0.28, lr=1e-6]\nSteps: 59%|█████▊ | 587/1000 [03:38<02:27, 2.80it/s, loss=0.28, lr=1e-6]\nSteps: 59%|█████▉ | 588/1000 [03:38<02:26, 2.82it/s, loss=0.28, lr=1e-6]\nSteps: 59%|█████▉ | 589/1000 [03:39<02:25, 2.83it/s, loss=0.28, lr=1e-6]\nSteps: 59%|█████▉ | 590/1000 [03:39<02:24, 2.84it/s, loss=0.28, lr=1e-6]\nSteps: 59%|█████▉ | 590/1000 [03:39<02:24, 2.84it/s, loss=0.28, lr=1e-6]\nSteps: 59%|█████▉ | 591/1000 [03:39<02:23, 2.85it/s, loss=0.28, lr=1e-6]\nSteps: 59%|█████▉ | 592/1000 [03:40<02:23, 2.85it/s, loss=0.28, lr=1e-6]\nSteps: 59%|█████▉ | 593/1000 [03:40<02:23, 2.84it/s, loss=0.28, lr=1e-6]\nSteps: 59%|█████▉ | 594/1000 [03:41<02:23, 2.83it/s, loss=0.28, lr=1e-6]\nSteps: 60%|█████▉ | 595/1000 [03:41<02:22, 2.84it/s, loss=0.28, lr=1e-6]\nSteps: 60%|█████▉ | 596/1000 [03:41<02:23, 2.82it/s, loss=0.28, lr=1e-6]\nSteps: 60%|█████▉ | 597/1000 [03:42<02:22, 2.83it/s, loss=0.28, lr=1e-6]\nSteps: 60%|█████▉ | 598/1000 [03:42<02:22, 2.83it/s, loss=0.28, lr=1e-6]\nSteps: 60%|█████▉ | 599/1000 [03:42<02:22, 2.81it/s, loss=0.28, lr=1e-6]\nSteps: 60%|██████ | 600/1000 [03:43<02:21, 2.82it/s, loss=0.28, lr=1e-6]\nSteps: 60%|██████ | 600/1000 [03:43<02:21, 2.82it/s, loss=0.283, lr=1e-6]\nSteps: 60%|██████ | 601/1000 [03:43<02:21, 2.82it/s, loss=0.283, lr=1e-6]\nSteps: 60%|██████ | 602/1000 [03:43<02:20, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 60%|██████ | 603/1000 [03:44<02:20, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 60%|██████ | 604/1000 [03:44<02:21, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 60%|██████ | 605/1000 [03:44<02:22, 2.77it/s, loss=0.283, lr=1e-6]\nSteps: 61%|██████ | 606/1000 [03:45<02:22, 2.76it/s, loss=0.283, lr=1e-6]\nSteps: 61%|██████ | 607/1000 [03:45<02:21, 2.78it/s, loss=0.283, lr=1e-6]\nSteps: 61%|██████ | 608/1000 [03:46<02:23, 2.73it/s, loss=0.283, lr=1e-6]\nSteps: 61%|██████ | 609/1000 [03:46<02:21, 2.76it/s, loss=0.283, lr=1e-6]\nSteps: 61%|██████ | 610/1000 [03:46<02:20, 2.77it/s, loss=0.283, lr=1e-6]\nSteps: 61%|██████ | 610/1000 [03:47<02:20, 2.77it/s, loss=0.285, lr=1e-6]\nSteps: 61%|██████ | 611/1000 [03:47<02:18, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 61%|██████ | 612/1000 [03:47<02:17, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 61%|██████▏ | 613/1000 [03:47<02:16, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 61%|██████▏ | 614/1000 [03:48<02:15, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 62%|██████▏ | 615/1000 [03:48<02:16, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 62%|██████▏ | 616/1000 [03:48<02:16, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 62%|██████▏ | 617/1000 [03:49<02:15, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 62%|██████▏ | 618/1000 [03:49<02:14, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 62%|██████▏ | 619/1000 [03:49<02:14, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 62%|██████▏ | 620/1000 [03:50<02:13, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 62%|██████▏ | 620/1000 [03:50<02:13, 2.84it/s, loss=0.284, lr=1e-6]\nSteps: 62%|██████▏ | 621/1000 [03:50<02:14, 2.81it/s, loss=0.284, lr=1e-6]\nSteps: 62%|██████▏ | 622/1000 [03:51<02:15, 2.78it/s, loss=0.284, lr=1e-6]\nSteps: 62%|██████▏ | 623/1000 [03:51<02:15, 2.79it/s, loss=0.284, lr=1e-6]\nSteps: 62%|██████▏ | 624/1000 [03:51<02:13, 2.81it/s, loss=0.284, lr=1e-6]\nSteps: 62%|██████▎ | 625/1000 [03:52<02:13, 2.80it/s, loss=0.284, lr=1e-6]\nSteps: 63%|██████▎ | 626/1000 [03:52<02:12, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 63%|██████▎ | 627/1000 [03:52<02:11, 2.83it/s, loss=0.284, lr=1e-6]\nSteps: 63%|██████▎ | 628/1000 [03:53<02:10, 2.85it/s, loss=0.284, lr=1e-6]\nSteps: 63%|██████▎ | 629/1000 [03:53<02:09, 2.86it/s, loss=0.284, lr=1e-6]\nSteps: 63%|██████▎ | 630/1000 [03:53<02:08, 2.87it/s, loss=0.284, lr=1e-6]\nSteps: 63%|██████▎ | 630/1000 [03:54<02:08, 2.87it/s, loss=0.283, lr=1e-6]\nSteps: 63%|██████▎ | 631/1000 [03:54<02:08, 2.88it/s, loss=0.283, lr=1e-6]\nSteps: 63%|██████▎ | 632/1000 [03:54<02:08, 2.86it/s, loss=0.283, lr=1e-6]\nSteps: 63%|██████▎ | 633/1000 [03:54<02:09, 2.84it/s, loss=0.283, lr=1e-6]\nSteps: 63%|██████▎ | 634/1000 [03:55<02:07, 2.86it/s, loss=0.283, lr=1e-6]\nSteps: 64%|██████▎ | 635/1000 [03:55<02:06, 2.88it/s, loss=0.283, lr=1e-6]\nSteps: 64%|██████▎ | 636/1000 [03:55<02:08, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 64%|██████▎ | 637/1000 [03:56<02:08, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 64%|██████▍ | 638/1000 [03:56<02:07, 2.84it/s, loss=0.283, lr=1e-6]\nSteps: 64%|██████▍ | 639/1000 [03:57<02:07, 2.82it/s, loss=0.283, lr=1e-6]\nSteps: 64%|██████▍ | 640/1000 [03:57<02:07, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 64%|██████▍ | 640/1000 [03:57<02:07, 2.83it/s, loss=0.284, lr=1e-6]\nSteps: 64%|██████▍ | 641/1000 [03:57<02:07, 2.83it/s, loss=0.284, lr=1e-6]\nSteps: 64%|██████▍ | 642/1000 [03:58<02:07, 2.81it/s, loss=0.284, lr=1e-6]\nSteps: 64%|██████▍ | 643/1000 [03:58<02:07, 2.79it/s, loss=0.284, lr=1e-6]\nSteps: 64%|██████▍ | 644/1000 [03:58<02:06, 2.81it/s, loss=0.284, lr=1e-6]\nSteps: 64%|██████▍ | 645/1000 [03:59<02:08, 2.76it/s, loss=0.284, lr=1e-6]\nSteps: 65%|██████▍ | 646/1000 [03:59<02:07, 2.77it/s, loss=0.284, lr=1e-6]\nSteps: 65%|██████▍ | 647/1000 [03:59<02:07, 2.78it/s, loss=0.284, lr=1e-6]\nSteps: 65%|██████▍ | 648/1000 [04:00<02:07, 2.76it/s, loss=0.284, lr=1e-6]\nSteps: 65%|██████▍ | 649/1000 [04:00<02:07, 2.75it/s, loss=0.284, lr=1e-6]\nSteps: 65%|██████▌ | 650/1000 [04:00<02:07, 2.75it/s, loss=0.284, lr=1e-6]\nSteps: 65%|██████▌ | 650/1000 [04:01<02:07, 2.75it/s, loss=0.283, lr=1e-6]\nSteps: 65%|██████▌ | 651/1000 [04:01<02:05, 2.77it/s, loss=0.283, lr=1e-6]\nSteps: 65%|██████▌ | 652/1000 [04:01<02:04, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 65%|██████▌ | 653/1000 [04:02<02:03, 2.82it/s, loss=0.283, lr=1e-6]\nSteps: 65%|██████▌ | 654/1000 [04:02<02:02, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 66%|██████▌ | 655/1000 [04:02<02:01, 2.84it/s, loss=0.283, lr=1e-6]\nSteps: 66%|██████▌ | 656/1000 [04:03<02:01, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 66%|██████▌ | 657/1000 [04:03<02:01, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 66%|██████▌ | 658/1000 [04:03<02:00, 2.84it/s, loss=0.283, lr=1e-6]\nSteps: 66%|██████▌ | 659/1000 [04:04<02:00, 2.84it/s, loss=0.283, lr=1e-6]\nSteps: 66%|██████▌ | 660/1000 [04:04<01:59, 2.84it/s, loss=0.283, lr=1e-6]\nSteps: 66%|██████▌ | 660/1000 [04:04<01:59, 2.84it/s, loss=0.282, lr=1e-6]\nSteps: 66%|██████▌ | 661/1000 [04:04<02:00, 2.82it/s, loss=0.282, lr=1e-6]\nSteps: 66%|██████▌ | 662/1000 [04:05<02:00, 2.79it/s, loss=0.282, lr=1e-6]\nSteps: 66%|██████▋ | 663/1000 [04:05<02:00, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 66%|██████▋ | 664/1000 [04:05<02:01, 2.75it/s, loss=0.282, lr=1e-6]\nSteps: 66%|██████▋ | 665/1000 [04:06<02:01, 2.75it/s, loss=0.282, lr=1e-6]\nSteps: 67%|██████▋ | 666/1000 [04:06<02:00, 2.77it/s, loss=0.282, lr=1e-6]\nSteps: 67%|██████▋ | 667/1000 [04:07<02:06, 2.64it/s, loss=0.282, lr=1e-6]\nSteps: 67%|██████▋ | 668/1000 [04:07<02:03, 2.68it/s, loss=0.282, lr=1e-6]\nSteps: 67%|██████▋ | 669/1000 [04:07<02:01, 2.72it/s, loss=0.282, lr=1e-6]\nSteps: 67%|██████▋ | 670/1000 [04:08<02:00, 2.75it/s, loss=0.282, lr=1e-6]\nSteps: 67%|██████▋ | 670/1000 [04:08<02:00, 2.75it/s, loss=0.283, lr=1e-6]\nSteps: 67%|██████▋ | 671/1000 [04:08<01:58, 2.76it/s, loss=0.283, lr=1e-6]\nSteps: 67%|██████▋ | 672/1000 [04:08<01:57, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 67%|██████▋ | 673/1000 [04:09<01:57, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 67%|██████▋ | 674/1000 [04:09<01:57, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 68%|██████▊ | 675/1000 [04:09<01:56, 2.80it/s, loss=0.283, lr=1e-6]\nSteps: 68%|██████▊ | 676/1000 [04:10<01:56, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 68%|██████▊ | 677/1000 [04:10<01:55, 2.80it/s, loss=0.283, lr=1e-6]\nSteps: 68%|██████▊ | 678/1000 [04:11<01:54, 2.80it/s, loss=0.283, lr=1e-6]\nSteps: 68%|██████▊ | 679/1000 [04:11<01:54, 2.81it/s, loss=0.283, lr=1e-6]\nSteps: 68%|██████▊ | 680/1000 [04:11<01:53, 2.81it/s, loss=0.283, lr=1e-6]\nSteps: 68%|██████▊ | 680/1000 [04:12<01:53, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 68%|██████▊ | 681/1000 [04:12<01:53, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 68%|██████▊ | 682/1000 [04:12<01:53, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 68%|██████▊ | 683/1000 [04:12<01:52, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 68%|██████▊ | 684/1000 [04:13<01:52, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 68%|██████▊ | 685/1000 [04:13<01:52, 2.79it/s, loss=0.282, lr=1e-6]\nSteps: 69%|██████▊ | 686/1000 [04:13<01:51, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 69%|██████▊ | 687/1000 [04:14<01:51, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 69%|██████▉ | 688/1000 [04:14<01:51, 2.79it/s, loss=0.282, lr=1e-6]\nSteps: 69%|██████▉ | 689/1000 [04:14<01:51, 2.79it/s, loss=0.282, lr=1e-6]\nSteps: 69%|██████▉ | 690/1000 [04:15<01:51, 2.78it/s, loss=0.282, lr=1e-6]\nSteps: 69%|██████▉ | 690/1000 [04:15<01:51, 2.78it/s, loss=0.283, lr=1e-6]\nSteps: 69%|██████▉ | 691/1000 [04:15<01:50, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 69%|██████▉ | 692/1000 [04:16<01:51, 2.75it/s, loss=0.283, lr=1e-6]\nSteps: 69%|██████▉ | 693/1000 [04:16<01:50, 2.77it/s, loss=0.283, lr=1e-6]\nSteps: 69%|██████▉ | 694/1000 [04:16<01:50, 2.77it/s, loss=0.283, lr=1e-6]\nSteps: 70%|██████▉ | 695/1000 [04:17<01:49, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 70%|██████▉ | 696/1000 [04:17<01:49, 2.78it/s, loss=0.283, lr=1e-6]\nSteps: 70%|██████▉ | 697/1000 [04:17<01:48, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 70%|██████▉ | 698/1000 [04:18<01:47, 2.80it/s, loss=0.283, lr=1e-6]\nSteps: 70%|██████▉ | 699/1000 [04:18<01:47, 2.80it/s, loss=0.283, lr=1e-6]\nSteps: 70%|███████ | 700/1000 [04:18<01:46, 2.82it/s, loss=0.283, lr=1e-6]\nSteps: 70%|███████ | 700/1000 [04:19<01:46, 2.82it/s, loss=0.283, lr=1e-6]\nSteps: 70%|███████ | 701/1000 [04:19<01:46, 2.81it/s, loss=0.283, lr=1e-6]\nSteps: 70%|███████ | 702/1000 [04:19<01:46, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 70%|███████ | 703/1000 [04:19<01:46, 2.80it/s, loss=0.283, lr=1e-6]\nSteps: 70%|███████ | 704/1000 [04:20<01:45, 2.80it/s, loss=0.283, lr=1e-6]\nSteps: 70%|███████ | 705/1000 [04:20<01:45, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 71%|███████ | 706/1000 [04:21<01:45, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 71%|███████ | 707/1000 [04:21<01:45, 2.79it/s, loss=0.283, lr=1e-6]\nSteps: 71%|███████ | 708/1000 [04:21<01:44, 2.80it/s, loss=0.283, lr=1e-6]\nSteps: 71%|███████ | 709/1000 [04:22<01:43, 2.80it/s, loss=0.283, lr=1e-6]\nSteps: 71%|███████ | 710/1000 [04:22<01:43, 2.80it/s, loss=0.283, lr=1e-6]\nSteps: 71%|███████ | 710/1000 [04:22<01:43, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 71%|███████ | 711/1000 [04:22<01:42, 2.82it/s, loss=0.282, lr=1e-6]\nSteps: 71%|███████ | 712/1000 [04:23<01:41, 2.84it/s, loss=0.282, lr=1e-6]\nSteps: 71%|███████▏ | 713/1000 [04:23<01:41, 2.83it/s, loss=0.282, lr=1e-6]\nSteps: 71%|███████▏ | 714/1000 [04:23<01:40, 2.84it/s, loss=0.282, lr=1e-6]\nSteps: 72%|███████▏ | 715/1000 [04:24<01:39, 2.85it/s, loss=0.282, lr=1e-6]\nSteps: 72%|███████▏ | 716/1000 [04:24<01:39, 2.85it/s, loss=0.282, lr=1e-6]\nSteps: 72%|███████▏ | 717/1000 [04:24<01:40, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 72%|███████▏ | 718/1000 [04:25<01:39, 2.84it/s, loss=0.282, lr=1e-6]\nSteps: 72%|███████▏ | 719/1000 [04:25<01:39, 2.82it/s, loss=0.282, lr=1e-6]\nSteps: 72%|███████▏ | 720/1000 [04:26<01:41, 2.77it/s, loss=0.282, lr=1e-6]\nSteps: 72%|███████▏ | 720/1000 [04:26<01:41, 2.77it/s, loss=0.282, lr=1e-6]\nSteps: 72%|███████▏ | 721/1000 [04:26<01:39, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 72%|███████▏ | 722/1000 [04:26<01:38, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 72%|███████▏ | 723/1000 [04:27<01:38, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 72%|███████▏ | 724/1000 [04:27<01:38, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 72%|███████▎ | 725/1000 [04:27<01:38, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 73%|███████▎ | 726/1000 [04:28<01:37, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 73%|███████▎ | 727/1000 [04:28<01:37, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 73%|███████▎ | 728/1000 [04:28<01:37, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 73%|███████▎ | 729/1000 [04:29<01:36, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 73%|███████▎ | 730/1000 [04:29<01:36, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 73%|███████▎ | 730/1000 [04:29<01:36, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 73%|███████▎ | 731/1000 [04:29<01:35, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 73%|███████▎ | 732/1000 [04:30<01:35, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 73%|███████▎ | 733/1000 [04:30<01:34, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 73%|███████▎ | 734/1000 [04:30<01:34, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 74%|███████▎ | 735/1000 [04:31<01:33, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 74%|███████▎ | 736/1000 [04:31<01:32, 2.85it/s, loss=0.285, lr=1e-6]\nSteps: 74%|███████▎ | 737/1000 [04:32<01:32, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 74%|███████▍ | 738/1000 [04:32<01:31, 2.87it/s, loss=0.285, lr=1e-6]\nSteps: 74%|███████▍ | 739/1000 [04:32<01:31, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 74%|███████▍ | 740/1000 [04:33<01:30, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 74%|███████▍ | 740/1000 [04:33<01:30, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 74%|███████▍ | 741/1000 [04:33<01:30, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 74%|███████▍ | 742/1000 [04:33<01:30, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 74%|███████▍ | 743/1000 [04:34<01:31, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 74%|███████▍ | 744/1000 [04:34<01:30, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 74%|███████▍ | 745/1000 [04:34<01:30, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 75%|███████▍ | 746/1000 [04:35<01:31, 2.79it/s, loss=0.285, lr=1e-6]\nSteps: 75%|███████▍ | 747/1000 [04:35<01:30, 2.79it/s, loss=0.285, lr=1e-6]\nSteps: 75%|███████▍ | 748/1000 [04:35<01:30, 2.77it/s, loss=0.285, lr=1e-6]\nSteps: 75%|███████▍ | 749/1000 [04:36<01:29, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 75%|███████▌ | 750/1000 [04:36<01:29, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 75%|███████▌ | 750/1000 [04:37<01:29, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 75%|███████▌ | 751/1000 [04:37<01:29, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 75%|███████▌ | 752/1000 [04:37<01:28, 2.79it/s, loss=0.285, lr=1e-6]\nSteps: 75%|███████▌ | 753/1000 [04:37<01:28, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 75%|███████▌ | 754/1000 [04:38<01:27, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 76%|███████▌ | 755/1000 [04:38<01:26, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 76%|███████▌ | 756/1000 [04:38<01:26, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 76%|███████▌ | 757/1000 [04:39<01:26, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 76%|███████▌ | 758/1000 [04:39<01:25, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 76%|███████▌ | 759/1000 [04:39<01:24, 2.85it/s, loss=0.285, lr=1e-6]\nSteps: 76%|███████▌ | 760/1000 [04:40<01:24, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 76%|███████▌ | 760/1000 [04:40<01:24, 2.86it/s, loss=0.284, lr=1e-6]\nSteps: 76%|███████▌ | 761/1000 [04:40<01:23, 2.85it/s, loss=0.284, lr=1e-6]\nSteps: 76%|███████▌ | 762/1000 [04:40<01:23, 2.86it/s, loss=0.284, lr=1e-6]\nSteps: 76%|███████▋ | 763/1000 [04:41<01:24, 2.81it/s, loss=0.284, lr=1e-6]\nSteps: 76%|███████▋ | 764/1000 [04:41<01:23, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 76%|███████▋ | 765/1000 [04:41<01:23, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 77%|███████▋ | 766/1000 [04:42<01:22, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 77%|███████▋ | 767/1000 [04:42<01:22, 2.83it/s, loss=0.284, lr=1e-6]\nSteps: 77%|███████▋ | 768/1000 [04:43<01:21, 2.84it/s, loss=0.284, lr=1e-6]\nSteps: 77%|███████▋ | 769/1000 [04:43<01:21, 2.84it/s, loss=0.284, lr=1e-6]\nSteps: 77%|███████▋ | 770/1000 [04:43<01:20, 2.84it/s, loss=0.284, lr=1e-6]\nSteps: 77%|███████▋ | 770/1000 [04:44<01:20, 2.84it/s, loss=0.284, lr=1e-6]\nSteps: 77%|███████▋ | 771/1000 [04:44<01:21, 2.80it/s, loss=0.284, lr=1e-6]\nSteps: 77%|███████▋ | 772/1000 [04:44<01:21, 2.80it/s, loss=0.284, lr=1e-6]\nSteps: 77%|███████▋ | 773/1000 [04:44<01:21, 2.80it/s, loss=0.284, lr=1e-6]\nSteps: 77%|███████▋ | 774/1000 [04:45<01:21, 2.78it/s, loss=0.284, lr=1e-6]\nSteps: 78%|███████▊ | 775/1000 [04:45<01:20, 2.79it/s, loss=0.284, lr=1e-6]\nSteps: 78%|███████▊ | 776/1000 [04:45<01:20, 2.80it/s, loss=0.284, lr=1e-6]\nSteps: 78%|███████▊ | 777/1000 [04:46<01:20, 2.78it/s, loss=0.284, lr=1e-6]\nSteps: 78%|███████▊ | 778/1000 [04:46<01:19, 2.79it/s, loss=0.284, lr=1e-6]\nSteps: 78%|███████▊ | 779/1000 [04:46<01:18, 2.80it/s, loss=0.284, lr=1e-6]\nSteps: 78%|███████▊ | 780/1000 [04:47<01:18, 2.79it/s, loss=0.284, lr=1e-6]\nSteps: 78%|███████▊ | 780/1000 [04:47<01:18, 2.79it/s, loss=0.285, lr=1e-6]\nSteps: 78%|███████▊ | 781/1000 [04:47<01:17, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 78%|███████▊ | 782/1000 [04:48<01:16, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 78%|███████▊ | 783/1000 [04:48<01:16, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 78%|███████▊ | 784/1000 [04:48<01:15, 2.85it/s, loss=0.285, lr=1e-6]\nSteps: 78%|███████▊ | 785/1000 [04:49<01:15, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 79%|███████▊ | 786/1000 [04:49<01:15, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 79%|███████▊ | 787/1000 [04:49<01:14, 2.87it/s, loss=0.285, lr=1e-6]\nSteps: 79%|███████▉ | 788/1000 [04:50<01:13, 2.88it/s, loss=0.285, lr=1e-6]\nSteps: 79%|███████▉ | 789/1000 [04:50<01:13, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 79%|███████▉ | 790/1000 [04:50<01:13, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 79%|███████▉ | 790/1000 [04:51<01:13, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 79%|███████▉ | 791/1000 [04:51<01:13, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 79%|███████▉ | 792/1000 [04:51<01:13, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 79%|███████▉ | 793/1000 [04:51<01:13, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 79%|███████▉ | 794/1000 [04:52<01:13, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 80%|███████▉ | 795/1000 [04:52<01:12, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 80%|███████▉ | 796/1000 [04:52<01:12, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 80%|███████▉ | 797/1000 [04:53<01:12, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 80%|███████▉ | 798/1000 [04:53<01:11, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 80%|███████▉ | 799/1000 [04:54<01:11, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 80%|████████ | 800/1000 [04:54<01:10, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 80%|████████ | 800/1000 [04:54<01:10, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 80%|████████ | 801/1000 [04:54<01:10, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 80%|████████ | 802/1000 [04:55<01:10, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 80%|████████ | 803/1000 [04:55<01:09, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 80%|████████ | 804/1000 [04:55<01:09, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 80%|████████ | 805/1000 [04:56<01:09, 2.79it/s, loss=0.285, lr=1e-6]\nSteps: 81%|████████ | 806/1000 [04:56<01:09, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 81%|████████ | 807/1000 [04:56<01:08, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 81%|████████ | 808/1000 [04:57<01:08, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 81%|████████ | 809/1000 [04:57<01:08, 2.80it/s, loss=0.285, lr=1e-6]\nSteps: 81%|████████ | 810/1000 [04:57<01:07, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 81%|████████ | 810/1000 [04:58<01:07, 2.82it/s, loss=0.286, lr=1e-6]\nSteps: 81%|████████ | 811/1000 [04:58<01:06, 2.82it/s, loss=0.286, lr=1e-6]\nSteps: 81%|████████ | 812/1000 [04:58<01:07, 2.80it/s, loss=0.286, lr=1e-6]\nSteps: 81%|████████▏ | 813/1000 [04:58<01:06, 2.81it/s, loss=0.286, lr=1e-6]\nSteps: 81%|████████▏ | 814/1000 [04:59<01:06, 2.81it/s, loss=0.286, lr=1e-6]\nSteps: 82%|████████▏ | 815/1000 [04:59<01:05, 2.81it/s, loss=0.286, lr=1e-6]\nSteps: 82%|████████▏ | 816/1000 [05:00<01:05, 2.81it/s, loss=0.286, lr=1e-6]\nSteps: 82%|████████▏ | 817/1000 [05:00<01:05, 2.81it/s, loss=0.286, lr=1e-6]\nSteps: 82%|████████▏ | 818/1000 [05:00<01:04, 2.82it/s, loss=0.286, lr=1e-6]\nSteps: 82%|████████▏ | 819/1000 [05:01<01:03, 2.84it/s, loss=0.286, lr=1e-6]\nSteps: 82%|████████▏ | 820/1000 [05:01<01:03, 2.85it/s, loss=0.286, lr=1e-6]\nSteps: 82%|████████▏ | 820/1000 [05:01<01:03, 2.85it/s, loss=0.285, lr=1e-6]\nSteps: 82%|████████▏ | 821/1000 [05:01<01:02, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 82%|████████▏ | 822/1000 [05:02<01:02, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 82%|████████▏ | 823/1000 [05:02<01:02, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 82%|████████▏ | 824/1000 [05:02<01:02, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 82%|████████▎ | 825/1000 [05:03<01:02, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 83%|████████▎ | 826/1000 [05:03<01:01, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 83%|████████▎ | 827/1000 [05:03<01:01, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 83%|████████▎ | 828/1000 [05:04<01:00, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 83%|████████▎ | 829/1000 [05:04<01:00, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 83%|████████▎ | 830/1000 [05:05<01:00, 2.81it/s, loss=0.285, lr=1e-6]\nSteps: 83%|████████▎ | 830/1000 [05:05<01:00, 2.81it/s, loss=0.286, lr=1e-6]\nSteps: 83%|████████▎ | 831/1000 [05:05<00:59, 2.82it/s, loss=0.286, lr=1e-6]\nSteps: 83%|████████▎ | 832/1000 [05:05<00:59, 2.83it/s, loss=0.286, lr=1e-6]\nSteps: 83%|████████▎ | 833/1000 [05:06<00:59, 2.83it/s, loss=0.286, lr=1e-6]\nSteps: 83%|████████▎ | 834/1000 [05:06<00:58, 2.83it/s, loss=0.286, lr=1e-6]\nSteps: 84%|████████▎ | 835/1000 [05:06<00:58, 2.83it/s, loss=0.286, lr=1e-6]\nSteps: 84%|████████▎ | 836/1000 [05:07<00:58, 2.82it/s, loss=0.286, lr=1e-6]\nSteps: 84%|████████▎ | 837/1000 [05:07<00:57, 2.81it/s, loss=0.286, lr=1e-6]\nSteps: 84%|████████▍ | 838/1000 [05:07<00:57, 2.83it/s, loss=0.286, lr=1e-6]\nSteps: 84%|████████▍ | 839/1000 [05:08<00:56, 2.84it/s, loss=0.286, lr=1e-6]\nSteps: 84%|████████▍ | 840/1000 [05:08<00:56, 2.83it/s, loss=0.286, lr=1e-6]\nSteps: 84%|████████▍ | 840/1000 [05:08<00:56, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 84%|████████▍ | 841/1000 [05:08<00:56, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 84%|████████▍ | 842/1000 [05:09<00:55, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 84%|████████▍ | 843/1000 [05:09<00:55, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 84%|████████▍ | 844/1000 [05:09<00:54, 2.85it/s, loss=0.285, lr=1e-6]\nSteps: 84%|████████▍ | 845/1000 [05:10<00:54, 2.86it/s, loss=0.285, lr=1e-6]\nSteps: 85%|████████▍ | 846/1000 [05:10<00:54, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 85%|████████▍ | 847/1000 [05:10<00:53, 2.84it/s, loss=0.285, lr=1e-6]\nSteps: 85%|████████▍ | 848/1000 [05:11<00:53, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 85%|████████▍ | 849/1000 [05:11<00:53, 2.83it/s, loss=0.285, lr=1e-6]\nSteps: 85%|████████▌ | 850/1000 [05:12<00:53, 2.82it/s, loss=0.285, lr=1e-6]\nSteps: 85%|████████▌ | 850/1000 [05:12<00:53, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 85%|████████▌ | 851/1000 [05:12<00:53, 2.81it/s, loss=0.284, lr=1e-6]\nSteps: 85%|████████▌ | 852/1000 [05:12<00:52, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 85%|████████▌ | 853/1000 [05:13<00:52, 2.81it/s, loss=0.284, lr=1e-6]\nSteps: 85%|████████▌ | 854/1000 [05:13<00:51, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 86%|████████▌ | 855/1000 [05:13<00:51, 2.83it/s, loss=0.284, lr=1e-6]\nSteps: 86%|████████▌ | 856/1000 [05:14<00:51, 2.82it/s, loss=0.284, lr=1e-6]\nSteps: 86%|████████▌ | 857/1000 [05:14<00:50, 2.81it/s, loss=0.284, lr=1e-6]\nSteps: 86%|████████▌ | 858/1000 [05:14<00:51, 2.76it/s, loss=0.284, lr=1e-6]\nSteps: 86%|████████▌ | 859/1000 [05:15<00:50, 2.79it/s, loss=0.284, lr=1e-6]\nSteps: 86%|████████▌ | 860/1000 [05:15<00:49, 2.81it/s, loss=0.284, lr=1e-6]\nSteps: 86%|████████▌ | 860/1000 [05:15<00:49, 2.81it/s, loss=0.283, lr=1e-6]\nSteps: 86%|████████▌ | 861/1000 [05:15<00:49, 2.80it/s, loss=0.283, lr=1e-6]\nSteps: 86%|████████▌ | 862/1000 [05:16<00:48, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 86%|████████▋ | 863/1000 [05:16<00:48, 2.84it/s, loss=0.283, lr=1e-6]\nSteps: 86%|████████▋ | 864/1000 [05:17<00:48, 2.82it/s, loss=0.283, lr=1e-6]\nSteps: 86%|████████▋ | 865/1000 [05:17<00:47, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 87%|████████▋ | 866/1000 [05:17<00:46, 2.85it/s, loss=0.283, lr=1e-6]\nSteps: 87%|████████▋ | 867/1000 [05:18<00:46, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 87%|████████▋ | 868/1000 [05:18<00:46, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 87%|████████▋ | 869/1000 [05:18<00:46, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 87%|████████▋ | 870/1000 [05:19<00:46, 2.83it/s, loss=0.283, lr=1e-6]\nSteps: 87%|████████▋ | 870/1000 [05:19<00:46, 2.83it/s, loss=0.282, lr=1e-6]\nSteps: 87%|████████▋ | 871/1000 [05:19<00:45, 2.84it/s, loss=0.282, lr=1e-6]\nSteps: 87%|████████▋ | 872/1000 [05:19<00:45, 2.84it/s, loss=0.282, lr=1e-6]\nSteps: 87%|████████▋ | 873/1000 [05:20<00:44, 2.83it/s, loss=0.282, lr=1e-6]\nSteps: 87%|████████▋ | 874/1000 [05:20<00:44, 2.83it/s, loss=0.282, lr=1e-6]\nSteps: 88%|████████▊ | 875/1000 [05:20<00:44, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 88%|████████▊ | 876/1000 [05:21<00:44, 2.82it/s, loss=0.282, lr=1e-6]\nSteps: 88%|████████▊ | 877/1000 [05:21<00:43, 2.82it/s, loss=0.282, lr=1e-6]\nSteps: 88%|████████▊ | 878/1000 [05:21<00:43, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 88%|████████▊ | 879/1000 [05:22<00:43, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 88%|████████▊ | 880/1000 [05:22<00:42, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 88%|████████▊ | 880/1000 [05:23<00:42, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 88%|████████▊ | 881/1000 [05:23<00:42, 2.79it/s, loss=0.282, lr=1e-6]\nSteps: 88%|████████▊ | 882/1000 [05:23<00:42, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 88%|████████▊ | 883/1000 [05:23<00:41, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 88%|████████▊ | 884/1000 [05:24<00:41, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 88%|████████▊ | 885/1000 [05:24<00:41, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 89%|████████▊ | 886/1000 [05:24<00:41, 2.76it/s, loss=0.282, lr=1e-6]\nSteps: 89%|████████▊ | 887/1000 [05:25<00:40, 2.77it/s, loss=0.282, lr=1e-6]\nSteps: 89%|████████▉ | 888/1000 [05:25<00:40, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 89%|████████▉ | 889/1000 [05:25<00:40, 2.77it/s, loss=0.282, lr=1e-6]\nSteps: 89%|████████▉ | 890/1000 [05:26<00:39, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 89%|████████▉ | 890/1000 [05:26<00:39, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 89%|████████▉ | 891/1000 [05:26<00:38, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 89%|████████▉ | 892/1000 [05:27<00:38, 2.79it/s, loss=0.281, lr=1e-6]\nSteps: 89%|████████▉ | 893/1000 [05:27<00:38, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 89%|████████▉ | 894/1000 [05:27<00:37, 2.82it/s, loss=0.281, lr=1e-6]\nSteps: 90%|████████▉ | 895/1000 [05:28<00:37, 2.81it/s, loss=0.281, lr=1e-6]\nSteps: 90%|████████▉ | 896/1000 [05:28<00:37, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 90%|████████▉ | 897/1000 [05:28<00:36, 2.81it/s, loss=0.281, lr=1e-6]\nSteps: 90%|████████▉ | 898/1000 [05:29<00:36, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 90%|████████▉ | 899/1000 [05:29<00:36, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 90%|█████████ | 900/1000 [05:29<00:35, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 90%|█████████ | 900/1000 [05:30<00:35, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 90%|█████████ | 901/1000 [05:30<00:35, 2.78it/s, loss=0.281, lr=1e-6]\nSteps: 90%|█████████ | 902/1000 [05:30<00:35, 2.79it/s, loss=0.281, lr=1e-6]\nSteps: 90%|█████████ | 903/1000 [05:30<00:34, 2.79it/s, loss=0.281, lr=1e-6]\nSteps: 90%|█████████ | 904/1000 [05:31<00:34, 2.78it/s, loss=0.281, lr=1e-6]\nSteps: 90%|█████████ | 905/1000 [05:31<00:33, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 91%|█████████ | 906/1000 [05:32<00:33, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 91%|█████████ | 907/1000 [05:32<00:33, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 91%|█████████ | 908/1000 [05:32<00:32, 2.81it/s, loss=0.281, lr=1e-6]\nSteps: 91%|█████████ | 909/1000 [05:33<00:32, 2.81it/s, loss=0.281, lr=1e-6]\nSteps: 91%|█████████ | 910/1000 [05:33<00:32, 2.79it/s, loss=0.281, lr=1e-6]\nSteps: 91%|█████████ | 910/1000 [05:33<00:32, 2.79it/s, loss=0.282, lr=1e-6]\nSteps: 91%|█████████ | 911/1000 [05:33<00:31, 2.82it/s, loss=0.282, lr=1e-6]\nSteps: 91%|█████████ | 912/1000 [05:34<00:31, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 91%|█████████▏| 913/1000 [05:34<00:31, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 91%|█████████▏| 914/1000 [05:34<00:31, 2.77it/s, loss=0.282, lr=1e-6]\nSteps: 92%|█████████▏| 915/1000 [05:35<00:30, 2.78it/s, loss=0.282, lr=1e-6]\nSteps: 92%|█████████▏| 916/1000 [05:35<00:30, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 92%|█████████▏| 917/1000 [05:35<00:29, 2.78it/s, loss=0.282, lr=1e-6]\nSteps: 92%|█████████▏| 918/1000 [05:36<00:29, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 92%|█████████▏| 919/1000 [05:36<00:28, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 92%|█████████▏| 920/1000 [05:37<00:28, 2.80it/s, loss=0.282, lr=1e-6]\nSteps: 92%|█████████▏| 920/1000 [05:37<00:28, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 92%|█████████▏| 921/1000 [05:37<00:28, 2.76it/s, loss=0.281, lr=1e-6]\nSteps: 92%|█████████▏| 922/1000 [05:37<00:28, 2.78it/s, loss=0.281, lr=1e-6]\nSteps: 92%|█████████▏| 923/1000 [05:38<00:27, 2.79it/s, loss=0.281, lr=1e-6]\nSteps: 92%|█████████▏| 924/1000 [05:38<00:27, 2.79it/s, loss=0.281, lr=1e-6]\nSteps: 92%|█████████▎| 925/1000 [05:38<00:26, 2.81it/s, loss=0.281, lr=1e-6]\nSteps: 93%|█████████▎| 926/1000 [05:39<00:26, 2.81it/s, loss=0.281, lr=1e-6]\nSteps: 93%|█████████▎| 927/1000 [05:39<00:26, 2.79it/s, loss=0.281, lr=1e-6]\nSteps: 93%|█████████▎| 928/1000 [05:39<00:25, 2.81it/s, loss=0.281, lr=1e-6]\nSteps: 93%|█████████▎| 929/1000 [05:40<00:25, 2.83it/s, loss=0.281, lr=1e-6]\nSteps: 93%|█████████▎| 930/1000 [05:40<00:24, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 93%|█████████▎| 930/1000 [05:40<00:24, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 93%|█████████▎| 931/1000 [05:40<00:24, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 93%|█████████▎| 932/1000 [05:41<00:24, 2.78it/s, loss=0.281, lr=1e-6]\nSteps: 93%|█████████▎| 933/1000 [05:41<00:24, 2.78it/s, loss=0.281, lr=1e-6]\nSteps: 93%|█████████▎| 934/1000 [05:42<00:23, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 94%|█████████▎| 935/1000 [05:42<00:23, 2.82it/s, loss=0.281, lr=1e-6]\nSteps: 94%|█████████▎| 936/1000 [05:42<00:22, 2.82it/s, loss=0.281, lr=1e-6]\nSteps: 94%|█████████▎| 937/1000 [05:43<00:22, 2.81it/s, loss=0.281, lr=1e-6]\nSteps: 94%|█████████▍| 938/1000 [05:43<00:22, 2.78it/s, loss=0.281, lr=1e-6]\nSteps: 94%|█████████▍| 939/1000 [05:43<00:21, 2.78it/s, loss=0.281, lr=1e-6]\nSteps: 94%|█████████▍| 940/1000 [05:44<00:21, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 94%|█████████▍| 940/1000 [05:44<00:21, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 94%|█████████▍| 941/1000 [05:44<00:21, 2.79it/s, loss=0.281, lr=1e-6]\nSteps: 94%|█████████▍| 942/1000 [05:44<00:20, 2.79it/s, loss=0.281, lr=1e-6]\nSteps: 94%|█████████▍| 943/1000 [05:45<00:20, 2.79it/s, loss=0.281, lr=1e-6]\nSteps: 94%|█████████▍| 944/1000 [05:45<00:20, 2.78it/s, loss=0.281, lr=1e-6]\nSteps: 94%|█████████▍| 945/1000 [05:45<00:20, 2.75it/s, loss=0.281, lr=1e-6]\nSteps: 95%|█████████▍| 946/1000 [05:46<00:19, 2.78it/s, loss=0.281, lr=1e-6]\nSteps: 95%|█████████▍| 947/1000 [05:46<00:19, 2.78it/s, loss=0.281, lr=1e-6]\nSteps: 95%|█████████▍| 948/1000 [05:47<00:18, 2.81it/s, loss=0.281, lr=1e-6]\nSteps: 95%|█████████▍| 949/1000 [05:47<00:18, 2.81it/s, loss=0.281, lr=1e-6]\nSteps: 95%|█████████▌| 950/1000 [05:47<00:17, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 95%|█████████▌| 950/1000 [05:48<00:17, 2.80it/s, loss=0.28, lr=1e-6]\nSteps: 95%|█████████▌| 951/1000 [05:48<00:17, 2.80it/s, loss=0.28, lr=1e-6]\nSteps: 95%|█████████▌| 952/1000 [05:48<00:17, 2.82it/s, loss=0.28, lr=1e-6]\nSteps: 95%|█████████▌| 953/1000 [05:48<00:16, 2.84it/s, loss=0.28, lr=1e-6]\nSteps: 95%|█████████▌| 954/1000 [05:49<00:16, 2.85it/s, loss=0.28, lr=1e-6]\nSteps: 96%|█████████▌| 955/1000 [05:49<00:15, 2.87it/s, loss=0.28, lr=1e-6]\nSteps: 96%|█████████▌| 956/1000 [05:49<00:15, 2.87it/s, loss=0.28, lr=1e-6]\nSteps: 96%|█████████▌| 957/1000 [05:50<00:15, 2.87it/s, loss=0.28, lr=1e-6]\nSteps: 96%|█████████▌| 958/1000 [05:50<00:14, 2.87it/s, loss=0.28, lr=1e-6]\nSteps: 96%|█████████▌| 959/1000 [05:50<00:14, 2.87it/s, loss=0.28, lr=1e-6]\nSteps: 96%|█████████▌| 960/1000 [05:51<00:13, 2.88it/s, loss=0.28, lr=1e-6]\nSteps: 96%|█████████▌| 960/1000 [05:51<00:13, 2.88it/s, loss=0.28, lr=1e-6]\nSteps: 96%|█████████▌| 961/1000 [05:51<00:13, 2.86it/s, loss=0.28, lr=1e-6]\nSteps: 96%|█████████▌| 962/1000 [05:51<00:13, 2.85it/s, loss=0.28, lr=1e-6]\nSteps: 96%|█████████▋| 963/1000 [05:52<00:13, 2.85it/s, loss=0.28, lr=1e-6]\nSteps: 96%|█████████▋| 964/1000 [05:52<00:12, 2.84it/s, loss=0.28, lr=1e-6]\nSteps: 96%|█████████▋| 965/1000 [05:53<00:12, 2.85it/s, loss=0.28, lr=1e-6]\nSteps: 97%|█████████▋| 966/1000 [05:53<00:11, 2.86it/s, loss=0.28, lr=1e-6]\nSteps: 97%|█████████▋| 967/1000 [05:53<00:11, 2.86it/s, loss=0.28, lr=1e-6]\nSteps: 97%|█████████▋| 968/1000 [05:54<00:11, 2.86it/s, loss=0.28, lr=1e-6]\nSteps: 97%|█████████▋| 969/1000 [05:54<00:10, 2.85it/s, loss=0.28, lr=1e-6]\nSteps: 97%|█████████▋| 970/1000 [05:54<00:10, 2.85it/s, loss=0.28, lr=1e-6]\nSteps: 97%|█████████▋| 970/1000 [05:55<00:10, 2.85it/s, loss=0.281, lr=1e-6]\nSteps: 97%|█████████▋| 971/1000 [05:55<00:10, 2.85it/s, loss=0.281, lr=1e-6]\nSteps: 97%|█████████▋| 972/1000 [05:55<00:09, 2.86it/s, loss=0.281, lr=1e-6]\nSteps: 97%|█████████▋| 973/1000 [05:55<00:09, 2.81it/s, loss=0.281, lr=1e-6]\nSteps: 97%|█████████▋| 974/1000 [05:56<00:09, 2.82it/s, loss=0.281, lr=1e-6]\nSteps: 98%|█████████▊| 975/1000 [05:56<00:08, 2.84it/s, loss=0.281, lr=1e-6]\nSteps: 98%|█████████▊| 976/1000 [05:56<00:08, 2.85it/s, loss=0.281, lr=1e-6]\nSteps: 98%|█████████▊| 977/1000 [05:57<00:08, 2.85it/s, loss=0.281, lr=1e-6]\nSteps: 98%|█████████▊| 978/1000 [05:57<00:07, 2.85it/s, loss=0.281, lr=1e-6]\nSteps: 98%|█████████▊| 979/1000 [05:57<00:07, 2.84it/s, loss=0.281, lr=1e-6]\nSteps: 98%|█████████▊| 980/1000 [05:58<00:07, 2.84it/s, loss=0.281, lr=1e-6]\nSteps: 98%|█████████▊| 980/1000 [05:58<00:07, 2.84it/s, loss=0.281, lr=1e-6]\nSteps: 98%|█████████▊| 981/1000 [05:58<00:06, 2.84it/s, loss=0.281, lr=1e-6]\nSteps: 98%|█████████▊| 982/1000 [05:58<00:06, 2.82it/s, loss=0.281, lr=1e-6]\nSteps: 98%|█████████▊| 983/1000 [05:59<00:06, 2.82it/s, loss=0.281, lr=1e-6]\nSteps: 98%|█████████▊| 984/1000 [05:59<00:05, 2.82it/s, loss=0.281, lr=1e-6]\nSteps: 98%|█████████▊| 985/1000 [06:00<00:05, 2.81it/s, loss=0.281, lr=1e-6]\nSteps: 99%|█████████▊| 986/1000 [06:00<00:05, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 99%|█████████▊| 987/1000 [06:00<00:04, 2.78it/s, loss=0.281, lr=1e-6]\nSteps: 99%|█████████▉| 988/1000 [06:01<00:04, 2.79it/s, loss=0.281, lr=1e-6]\nSteps: 99%|█████████▉| 989/1000 [06:01<00:03, 2.80it/s, loss=0.281, lr=1e-6]\nSteps: 99%|█████████▉| 990/1000 [06:01<00:03, 2.82it/s, loss=0.281, lr=1e-6]\nSteps: 99%|█████████▉| 990/1000 [06:02<00:03, 2.82it/s, loss=0.282, lr=1e-6]\nSteps: 99%|█████████▉| 991/1000 [06:02<00:03, 2.82it/s, loss=0.282, lr=1e-6]\nSteps: 99%|█████████▉| 992/1000 [06:02<00:02, 2.83it/s, loss=0.282, lr=1e-6]\nSteps: 99%|█████████▉| 993/1000 [06:02<00:02, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 99%|█████████▉| 994/1000 [06:03<00:02, 2.81it/s, loss=0.282, lr=1e-6]\nSteps: 100%|█████████▉| 995/1000 [06:03<00:01, 2.83it/s, loss=0.282, lr=1e-6]\nSteps: 100%|█████████▉| 996/1000 [06:03<00:01, 2.84it/s, loss=0.282, lr=1e-6]\nSteps: 100%|█████████▉| 997/1000 [06:04<00:01, 2.86it/s, loss=0.282, lr=1e-6]\nSteps: 100%|█████████▉| 998/1000 [06:04<00:00, 2.85it/s, loss=0.282, lr=1e-6]\nSteps: 100%|█████████▉| 999/1000 [06:05<00:00, 2.83it/s, loss=0.282, lr=1e-6]\nSteps: 100%|██████████| 1000/1000 [06:05<00:00, 2.83it/s, loss=0.282, lr=1e-6]You have passed `None` for safety_checker to disable its functionality in <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'>. Note that this might lead to problems when using <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> and is not recommended.\n[*] Weights saved at checkpoints\nSteps: 100%|██████████| 1000/1000 [06:09<00:00, 2.71it/s, loss=0.282, lr=1e-6]\nThu Nov 17 02:47:06 2022\n+-----------------------------------------------------------------------------+\n| NVIDIA-SMI 510.47.03 Driver Version: 510.47.03 CUDA Version: 11.6 |\n|-------------------------------+----------------------+----------------------+\n| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |\n| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |\n| | | MIG M. |\n|===============================+======================+======================|\n| 0 NVIDIA A100-SXM... Off | 00000000:00:04.0 Off | 0 |\n| N/A 39C P0 58W / 400W | 2122MiB / 40960MiB | 15% Default |\n| | | Disabled |\n+-------------------------------+----------------------+----------------------+\n+-----------------------------------------------------------------------------+\n| Processes: |\n| GPU GI CI PID Type Process name GPU Memory |\n| ID ID Usage |\n|=============================================================================|\n| 0 N/A N/A 399088 C 2119MiB |\n+-----------------------------------------------------------------------------+\ncheckpoints/tokenizer\ncheckpoints/unet\ncheckpoints/vae\ncheckpoints/text_encoder\ncheckpoints/feature_extractor\ncheckpoints/args.json\ncheckpoints/model_index.json\ncheckpoints/scheduler\ncheckpoints/tokenizer/vocab.json\ncheckpoints/tokenizer/special_tokens_map.json\ncheckpoints/tokenizer/merges.txt\ncheckpoints/tokenizer/tokenizer_config.json\ncheckpoints/unet/diffusion_pytorch_model.bin\ncheckpoints/unet/config.json\ncheckpoints/vae/diffusion_pytorch_model.bin\ncheckpoints/vae/config.json\ncheckpoints/text_encoder/pytorch_model.bin\ncheckpoints/text_encoder/config.json\ncheckpoints/feature_extractor/preprocessor_config.json\ncheckpoints/scheduler/scheduler_config.json",
"metrics": {
"predict_time": 691.719585,
"total_time": 715.094675
},
"output": "https://replicate.delivery/pbxt/g72ns6cGvjIzPlqpwcCFjDPjyZfLocdvgqcMj1Uwy6ZZlaAIA/output.zip",
"started_at": "2022-11-17T02:36:06.324263Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/4yyxeqh2cfcd7pueymhl6jhcra",
"cancel": "https://api.replicate.com/v1/predictions/4yyxeqh2cfcd7pueymhl6jhcra/cancel"
},
"version": "7198ab665a5e793fc8d89ed80db7660cc5fdd086f2809c19d5a88ec5dbcadf99"
}
/root/.pyenv/versions/3.10.8/lib/python3.10/site-packages/accelerate/accelerator.py:179: UserWarning: `log_with=tensorboard` was passed but no supported trackers are currently installed.
warnings.warn(f"`log_with={log_with}` was passed but no supported trackers are currently installed.")
You have passed `None` for safety_checker to disable its functionality in <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'>. Note that this might lead to problems when using <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> and is not recommended.
Generating class images: 0%| | 0/25 [00:00<?, ?it/s]
Generating class images: 4%|▍ | 1/25 [00:26<10:25, 26.06s/it]
Generating class images: 8%|▊ | 2/25 [00:35<06:15, 16.32s/it]
Generating class images: 12%|█▏ | 3/25 [00:45<04:50, 13.20s/it]
Generating class images: 16%|█▌ | 4/25 [00:54<04:06, 11.74s/it]
Generating class images: 20%|██ | 5/25 [01:04<03:38, 10.92s/it]
Generating class images: 24%|██▍ | 6/25 [01:13<03:18, 10.44s/it]
Generating class images: 28%|██▊ | 7/25 [01:22<03:02, 10.13s/it]
Generating class images: 32%|███▏ | 8/25 [01:32<02:48, 9.93s/it]
Generating class images: 36%|███▌ | 9/25 [01:41<02:36, 9.79s/it]
Generating class images: 40%|████ | 10/25 [01:51<02:25, 9.69s/it]
Generating class images: 44%|████▍ | 11/25 [02:00<02:14, 9.63s/it]
Generating class images: 48%|████▊ | 12/25 [02:10<02:04, 9.59s/it]
Generating class images: 52%|█████▏ | 13/25 [02:19<01:54, 9.56s/it]
Generating class images: 56%|█████▌ | 14/25 [02:29<01:44, 9.54s/it]
Generating class images: 60%|██████ | 15/25 [02:38<01:35, 9.53s/it]
Generating class images: 64%|██████▍ | 16/25 [02:48<01:25, 9.51s/it]
Generating class images: 68%|██████▊ | 17/25 [02:57<01:16, 9.51s/it]
Generating class images: 72%|███████▏ | 18/25 [03:07<01:06, 9.50s/it]
Generating class images: 76%|███████▌ | 19/25 [03:16<00:56, 9.50s/it]
Generating class images: 80%|████████ | 20/25 [03:26<00:47, 9.50s/it]
Generating class images: 84%|████████▍ | 21/25 [03:35<00:37, 9.50s/it]
Generating class images: 88%|████████▊ | 22/25 [03:45<00:28, 9.50s/it]
Generating class images: 92%|█████████▏| 23/25 [03:54<00:18, 9.49s/it]
Generating class images: 96%|█████████▌| 24/25 [04:04<00:09, 9.49s/it]
Generating class images: 100%|██████████| 25/25 [04:13<00:00, 9.49s/it]
Generating class images: 100%|██████████| 25/25 [04:13<00:00, 10.15s/it]
Caching latents: 0%| | 0/100 [00:00<?, ?it/s]
Caching latents: 1%| | 1/100 [00:01<02:27, 1.49s/it]
Caching latents: 2%|▏ | 2/100 [00:01<01:07, 1.45it/s]
Caching latents: 3%|▎ | 3/100 [00:01<00:41, 2.34it/s]
Caching latents: 4%|▍ | 4/100 [00:01<00:29, 3.26it/s]
Caching latents: 5%|▌ | 5/100 [00:01<00:22, 4.19it/s]
Caching latents: 6%|▌ | 6/100 [00:02<00:18, 5.08it/s]
Caching latents: 7%|▋ | 7/100 [00:02<00:15, 5.86it/s]
Caching latents: 8%|▊ | 8/100 [00:02<00:14, 6.46it/s]
Caching latents: 9%|▉ | 9/100 [00:02<00:13, 6.96it/s]
Caching latents: 10%|█ | 10/100 [00:02<00:12, 7.14it/s]
Caching latents: 11%|█ | 11/100 [00:02<00:11, 7.43it/s]
Caching latents: 12%|█▏ | 12/100 [00:02<00:11, 7.49it/s]
Caching latents: 13%|█▎ | 13/100 [00:02<00:11, 7.66it/s]
Caching latents: 14%|█▍ | 14/100 [00:03<00:10, 7.91it/s]
Caching latents: 15%|█▌ | 15/100 [00:03<00:10, 8.07it/s]
Caching latents: 16%|█▌ | 16/100 [00:03<00:10, 8.10it/s]
Caching latents: 17%|█▋ | 17/100 [00:03<00:10, 8.23it/s]
Caching latents: 18%|█▊ | 18/100 [00:03<00:09, 8.34it/s]
Caching latents: 19%|█▉ | 19/100 [00:03<00:09, 8.34it/s]
Caching latents: 20%|██ | 20/100 [00:03<00:09, 8.42it/s]
Caching latents: 21%|██ | 21/100 [00:03<00:09, 8.49it/s]
Caching latents: 22%|██▏ | 22/100 [00:04<00:09, 8.28it/s]
Caching latents: 23%|██▎ | 23/100 [00:04<00:09, 8.30it/s]
Caching latents: 24%|██▍ | 24/100 [00:04<00:09, 8.32it/s]
Caching latents: 25%|██▌ | 25/100 [00:04<00:09, 8.30it/s]
Caching latents: 26%|██▌ | 26/100 [00:04<00:08, 8.31it/s]
Caching latents: 27%|██▋ | 27/100 [00:04<00:08, 8.30it/s]
Caching latents: 28%|██▊ | 28/100 [00:04<00:08, 8.37it/s]
Caching latents: 29%|██▉ | 29/100 [00:04<00:08, 8.43it/s]
Caching latents: 30%|███ | 30/100 [00:04<00:08, 8.41it/s]
Caching latents: 31%|███ | 31/100 [00:05<00:08, 8.46it/s]
Caching latents: 32%|███▏ | 32/100 [00:05<00:08, 8.38it/s]
Caching latents: 33%|███▎ | 33/100 [00:05<00:07, 8.42it/s]
Caching latents: 34%|███▍ | 34/100 [00:05<00:07, 8.36it/s]
Caching latents: 35%|███▌ | 35/100 [00:05<00:07, 8.35it/s]
Caching latents: 36%|███▌ | 36/100 [00:05<00:07, 8.29it/s]
Caching latents: 37%|███▋ | 37/100 [00:05<00:07, 8.22it/s]
Caching latents: 38%|███▊ | 38/100 [00:05<00:07, 8.25it/s]
Caching latents: 39%|███▉ | 39/100 [00:06<00:07, 8.35it/s]
Caching latents: 40%|████ | 40/100 [00:06<00:07, 8.34it/s]
Caching latents: 41%|████ | 41/100 [00:06<00:07, 8.34it/s]
Caching latents: 42%|████▏ | 42/100 [00:06<00:06, 8.29it/s]
Caching latents: 43%|████▎ | 43/100 [00:06<00:06, 8.29it/s]
Caching latents: 44%|████▍ | 44/100 [00:06<00:06, 8.21it/s]
Caching latents: 45%|████▌ | 45/100 [00:06<00:06, 8.21it/s]
Caching latents: 46%|████▌ | 46/100 [00:06<00:06, 8.18it/s]
Caching latents: 47%|████▋ | 47/100 [00:07<00:06, 8.12it/s]
Caching latents: 48%|████▊ | 48/100 [00:07<00:06, 8.18it/s]
Caching latents: 49%|████▉ | 49/100 [00:07<00:06, 8.32it/s]
Caching latents: 50%|█████ | 50/100 [00:07<00:06, 8.30it/s]
Caching latents: 51%|█████ | 51/100 [00:07<00:05, 8.27it/s]
Caching latents: 52%|█████▏ | 52/100 [00:07<00:05, 8.23it/s]
Caching latents: 53%|█████▎ | 53/100 [00:07<00:05, 8.34it/s]
Caching latents: 54%|█████▍ | 54/100 [00:07<00:05, 8.32it/s]
Caching latents: 55%|█████▌ | 55/100 [00:07<00:05, 8.36it/s]
Caching latents: 56%|█████▌ | 56/100 [00:08<00:05, 8.32it/s]
Caching latents: 57%|█████▋ | 57/100 [00:08<00:05, 8.32it/s]
Caching latents: 58%|█████▊ | 58/100 [00:08<00:05, 8.31it/s]
Caching latents: 59%|█████▉ | 59/100 [00:08<00:04, 8.43it/s]
Caching latents: 60%|██████ | 60/100 [00:08<00:04, 8.37it/s]
Caching latents: 61%|██████ | 61/100 [00:08<00:04, 8.29it/s]
Caching latents: 62%|██████▏ | 62/100 [00:08<00:04, 8.45it/s]
Caching latents: 63%|██████▎ | 63/100 [00:08<00:04, 8.38it/s]
Caching latents: 64%|██████▍ | 64/100 [00:09<00:04, 8.39it/s]
Caching latents: 65%|██████▌ | 65/100 [00:09<00:04, 8.38it/s]
Caching latents: 66%|██████▌ | 66/100 [00:09<00:04, 8.45it/s]
Caching latents: 67%|██████▋ | 67/100 [00:09<00:03, 8.30it/s]
Caching latents: 68%|██████▊ | 68/100 [00:09<00:03, 8.33it/s]
Caching latents: 69%|██████▉ | 69/100 [00:09<00:03, 8.23it/s]
Caching latents: 70%|███████ | 70/100 [00:09<00:03, 8.24it/s]
Caching latents: 71%|███████ | 71/100 [00:09<00:03, 8.35it/s]
Caching latents: 72%|███████▏ | 72/100 [00:10<00:03, 8.30it/s]
Caching latents: 73%|███████▎ | 73/100 [00:10<00:03, 8.42it/s]
Caching latents: 74%|███████▍ | 74/100 [00:10<00:03, 8.45it/s]
Caching latents: 75%|███████▌ | 75/100 [00:10<00:02, 8.37it/s]
Caching latents: 76%|███████▌ | 76/100 [00:10<00:02, 8.08it/s]
Caching latents: 77%|███████▋ | 77/100 [00:10<00:02, 8.13it/s]
Caching latents: 78%|███████▊ | 78/100 [00:10<00:02, 8.20it/s]
Caching latents: 79%|███████▉ | 79/100 [00:10<00:02, 8.31it/s]
Caching latents: 80%|████████ | 80/100 [00:11<00:02, 8.24it/s]
Caching latents: 81%|████████ | 81/100 [00:11<00:02, 8.32it/s]
Caching latents: 82%|████████▏ | 82/100 [00:11<00:02, 8.29it/s]
Caching latents: 83%|████████▎ | 83/100 [00:11<00:02, 8.38it/s]
Caching latents: 84%|████████▍ | 84/100 [00:11<00:01, 8.36it/s]
Caching latents: 85%|████████▌ | 85/100 [00:11<00:01, 8.30it/s]
Caching latents: 86%|████████▌ | 86/100 [00:11<00:01, 8.37it/s]
Caching latents: 87%|████████▋ | 87/100 [00:11<00:01, 8.34it/s]
Caching latents: 88%|████████▊ | 88/100 [00:11<00:01, 8.08it/s]
Caching latents: 89%|████████▉ | 89/100 [00:12<00:01, 8.23it/s]
Caching latents: 90%|█████████ | 90/100 [00:12<00:01, 8.34it/s]
Caching latents: 91%|█████████ | 91/100 [00:12<00:01, 8.33it/s]
Caching latents: 92%|█████████▏| 92/100 [00:12<00:00, 8.43it/s]
Caching latents: 93%|█████████▎| 93/100 [00:12<00:00, 8.34it/s]
Caching latents: 94%|█████████▍| 94/100 [00:12<00:00, 8.37it/s]
Caching latents: 95%|█████████▌| 95/100 [00:12<00:00, 8.39it/s]
Caching latents: 96%|█████████▌| 96/100 [00:12<00:00, 8.46it/s]
Caching latents: 97%|█████████▋| 97/100 [00:13<00:00, 8.41it/s]
Caching latents: 98%|█████████▊| 98/100 [00:13<00:00, 8.34it/s]
Caching latents: 99%|█████████▉| 99/100 [00:13<00:00, 8.31it/s]
Caching latents: 100%|██████████| 100/100 [00:13<00:00, 8.31it/s]
Caching latents: 100%|██████████| 100/100 [00:13<00:00, 7.46it/s]
0%| | 0/1000 [00:00<?, ?it/s]
Steps: 0%| | 0/1000 [00:00<?, ?it/s]
Steps: 0%| | 0/1000 [00:10<?, ?it/s, loss=0.405, lr=1e-6]
Steps: 0%| | 1/1000 [00:10<2:59:53, 10.80s/it, loss=0.405, lr=1e-6]
Steps: 0%| | 2/1000 [00:11<1:17:45, 4.68s/it, loss=0.405, lr=1e-6]
Steps: 0%| | 3/1000 [00:11<44:50, 2.70s/it, loss=0.405, lr=1e-6]
Steps: 0%| | 4/1000 [00:11<29:26, 1.77s/it, loss=0.405, lr=1e-6]
Steps: 0%| | 5/1000 [00:12<20:54, 1.26s/it, loss=0.405, lr=1e-6]
Steps: 1%| | 6/1000 [00:12<15:46, 1.05it/s, loss=0.405, lr=1e-6]
Steps: 1%| | 7/1000 [00:12<12:30, 1.32it/s, loss=0.405, lr=1e-6]
Steps: 1%| | 8/1000 [00:13<10:20, 1.60it/s, loss=0.405, lr=1e-6]
Steps: 1%| | 9/1000 [00:13<08:54, 1.85it/s, loss=0.405, lr=1e-6]
Steps: 1%| | 10/1000 [00:13<07:56, 2.08it/s, loss=0.405, lr=1e-6]
Steps: 1%| | 10/1000 [00:14<07:56, 2.08it/s, loss=0.285, lr=1e-6]
Steps: 1%| | 11/1000 [00:14<07:16, 2.27it/s, loss=0.285, lr=1e-6]
Steps: 1%| | 12/1000 [00:14<06:50, 2.41it/s, loss=0.285, lr=1e-6]
Steps: 1%|▏ | 13/1000 [00:15<06:32, 2.52it/s, loss=0.285, lr=1e-6]
Steps: 1%|▏ | 14/1000 [00:15<06:18, 2.61it/s, loss=0.285, lr=1e-6]
Steps: 2%|▏ | 15/1000 [00:15<06:07, 2.68it/s, loss=0.285, lr=1e-6]
Steps: 2%|▏ | 16/1000 [00:16<06:06, 2.69it/s, loss=0.285, lr=1e-6]
Steps: 2%|▏ | 17/1000 [00:16<05:58, 2.74it/s, loss=0.285, lr=1e-6]
Steps: 2%|▏ | 18/1000 [00:16<05:54, 2.77it/s, loss=0.285, lr=1e-6]
Steps: 2%|▏ | 19/1000 [00:17<05:51, 2.79it/s, loss=0.285, lr=1e-6]
Steps: 2%|▏ | 20/1000 [00:17<05:48, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 2%|▏ | 20/1000 [00:17<05:48, 2.81it/s, loss=0.278, lr=1e-6]
Steps: 2%|▏ | 21/1000 [00:17<05:48, 2.81it/s, loss=0.278, lr=1e-6]
Steps: 2%|▏ | 22/1000 [00:18<05:46, 2.82it/s, loss=0.278, lr=1e-6]
Steps: 2%|▏ | 23/1000 [00:18<05:45, 2.83it/s, loss=0.278, lr=1e-6]
Steps: 2%|▏ | 24/1000 [00:18<05:45, 2.83it/s, loss=0.278, lr=1e-6]
Steps: 2%|▎ | 25/1000 [00:19<05:44, 2.83it/s, loss=0.278, lr=1e-6]
Steps: 3%|▎ | 26/1000 [00:19<05:45, 2.82it/s, loss=0.278, lr=1e-6]
Steps: 3%|▎ | 27/1000 [00:20<05:43, 2.83it/s, loss=0.278, lr=1e-6]
Steps: 3%|▎ | 28/1000 [00:20<05:42, 2.84it/s, loss=0.278, lr=1e-6]
Steps: 3%|▎ | 29/1000 [00:20<05:40, 2.85it/s, loss=0.278, lr=1e-6]
Steps: 3%|▎ | 30/1000 [00:21<05:39, 2.86it/s, loss=0.278, lr=1e-6]
Steps: 3%|▎ | 30/1000 [00:21<05:39, 2.86it/s, loss=0.27, lr=1e-6]
Steps: 3%|▎ | 31/1000 [00:21<05:38, 2.87it/s, loss=0.27, lr=1e-6]
Steps: 3%|▎ | 32/1000 [00:21<05:37, 2.87it/s, loss=0.27, lr=1e-6]
Steps: 3%|▎ | 33/1000 [00:22<05:39, 2.85it/s, loss=0.27, lr=1e-6]
Steps: 3%|▎ | 34/1000 [00:22<05:37, 2.86it/s, loss=0.27, lr=1e-6]
Steps: 4%|▎ | 35/1000 [00:22<05:35, 2.87it/s, loss=0.27, lr=1e-6]
Steps: 4%|▎ | 36/1000 [00:23<05:37, 2.86it/s, loss=0.27, lr=1e-6]
Steps: 4%|▎ | 37/1000 [00:23<05:36, 2.86it/s, loss=0.27, lr=1e-6]
Steps: 4%|▍ | 38/1000 [00:23<05:35, 2.87it/s, loss=0.27, lr=1e-6]
Steps: 4%|▍ | 39/1000 [00:24<05:35, 2.87it/s, loss=0.27, lr=1e-6]
Steps: 4%|▍ | 40/1000 [00:24<05:35, 2.86it/s, loss=0.27, lr=1e-6]
Steps: 4%|▍ | 40/1000 [00:24<05:35, 2.86it/s, loss=0.282, lr=1e-6]
Steps: 4%|▍ | 41/1000 [00:24<05:34, 2.86it/s, loss=0.282, lr=1e-6]
Steps: 4%|▍ | 42/1000 [00:25<05:38, 2.83it/s, loss=0.282, lr=1e-6]
Steps: 4%|▍ | 43/1000 [00:25<05:36, 2.84it/s, loss=0.282, lr=1e-6]
Steps: 4%|▍ | 44/1000 [00:25<05:42, 2.79it/s, loss=0.282, lr=1e-6]
Steps: 4%|▍ | 45/1000 [00:26<05:41, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 5%|▍ | 46/1000 [00:26<05:39, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 5%|▍ | 47/1000 [00:27<05:40, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 5%|▍ | 48/1000 [00:27<05:37, 2.82it/s, loss=0.282, lr=1e-6]
Steps: 5%|▍ | 49/1000 [00:27<05:36, 2.83it/s, loss=0.282, lr=1e-6]
Steps: 5%|▌ | 50/1000 [00:28<05:38, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 5%|▌ | 50/1000 [00:28<05:38, 2.81it/s, loss=0.298, lr=1e-6]
Steps: 5%|▌ | 51/1000 [00:28<05:35, 2.83it/s, loss=0.298, lr=1e-6]
Steps: 5%|▌ | 52/1000 [00:28<05:30, 2.86it/s, loss=0.298, lr=1e-6]
Steps: 5%|▌ | 53/1000 [00:29<05:30, 2.86it/s, loss=0.298, lr=1e-6]
Steps: 5%|▌ | 54/1000 [00:29<05:31, 2.86it/s, loss=0.298, lr=1e-6]
Steps: 6%|▌ | 55/1000 [00:29<05:30, 2.86it/s, loss=0.298, lr=1e-6]
Steps: 6%|▌ | 56/1000 [00:30<05:32, 2.84it/s, loss=0.298, lr=1e-6]
Steps: 6%|▌ | 57/1000 [00:30<05:30, 2.85it/s, loss=0.298, lr=1e-6]
Steps: 6%|▌ | 58/1000 [00:30<05:28, 2.87it/s, loss=0.298, lr=1e-6]
Steps: 6%|▌ | 59/1000 [00:31<05:30, 2.84it/s, loss=0.298, lr=1e-6]
Steps: 6%|▌ | 60/1000 [00:31<05:30, 2.84it/s, loss=0.298, lr=1e-6]
Steps: 6%|▌ | 60/1000 [00:31<05:30, 2.84it/s, loss=0.305, lr=1e-6]
Steps: 6%|▌ | 61/1000 [00:31<05:29, 2.85it/s, loss=0.305, lr=1e-6]
Steps: 6%|▌ | 62/1000 [00:32<05:30, 2.83it/s, loss=0.305, lr=1e-6]
Steps: 6%|▋ | 63/1000 [00:32<05:29, 2.84it/s, loss=0.305, lr=1e-6]
Steps: 6%|▋ | 64/1000 [00:33<05:29, 2.84it/s, loss=0.305, lr=1e-6]
Steps: 6%|▋ | 65/1000 [00:33<05:30, 2.83it/s, loss=0.305, lr=1e-6]
Steps: 7%|▋ | 66/1000 [00:33<05:29, 2.84it/s, loss=0.305, lr=1e-6]
Steps: 7%|▋ | 67/1000 [00:34<05:31, 2.81it/s, loss=0.305, lr=1e-6]
Steps: 7%|▋ | 68/1000 [00:34<05:31, 2.81it/s, loss=0.305, lr=1e-6]
Steps: 7%|▋ | 69/1000 [00:34<05:29, 2.83it/s, loss=0.305, lr=1e-6]
Steps: 7%|▋ | 70/1000 [00:35<05:27, 2.84it/s, loss=0.305, lr=1e-6]
Steps: 7%|▋ | 70/1000 [00:35<05:27, 2.84it/s, loss=0.311, lr=1e-6]
Steps: 7%|▋ | 71/1000 [00:35<05:26, 2.84it/s, loss=0.311, lr=1e-6]
Steps: 7%|▋ | 72/1000 [00:35<05:29, 2.82it/s, loss=0.311, lr=1e-6]
Steps: 7%|▋ | 73/1000 [00:36<05:30, 2.80it/s, loss=0.311, lr=1e-6]
Steps: 7%|▋ | 74/1000 [00:36<05:28, 2.82it/s, loss=0.311, lr=1e-6]
Steps: 8%|▊ | 75/1000 [00:36<05:28, 2.81it/s, loss=0.311, lr=1e-6]
Steps: 8%|▊ | 76/1000 [00:37<05:33, 2.77it/s, loss=0.311, lr=1e-6]
Steps: 8%|▊ | 77/1000 [00:37<05:30, 2.79it/s, loss=0.311, lr=1e-6]
Steps: 8%|▊ | 78/1000 [00:37<05:27, 2.81it/s, loss=0.311, lr=1e-6]
Steps: 8%|▊ | 79/1000 [00:38<05:28, 2.80it/s, loss=0.311, lr=1e-6]
Steps: 8%|▊ | 80/1000 [00:38<05:26, 2.82it/s, loss=0.311, lr=1e-6]
Steps: 8%|▊ | 80/1000 [00:39<05:26, 2.82it/s, loss=0.301, lr=1e-6]
Steps: 8%|▊ | 81/1000 [00:39<05:25, 2.82it/s, loss=0.301, lr=1e-6]
Steps: 8%|▊ | 82/1000 [00:39<05:25, 2.82it/s, loss=0.301, lr=1e-6]
Steps: 8%|▊ | 83/1000 [00:39<05:26, 2.81it/s, loss=0.301, lr=1e-6]
Steps: 8%|▊ | 84/1000 [00:40<05:25, 2.81it/s, loss=0.301, lr=1e-6]
Steps: 8%|▊ | 85/1000 [00:40<05:26, 2.80it/s, loss=0.301, lr=1e-6]
Steps: 9%|▊ | 86/1000 [00:40<05:26, 2.80it/s, loss=0.301, lr=1e-6]
Steps: 9%|▊ | 87/1000 [00:41<05:25, 2.80it/s, loss=0.301, lr=1e-6]
Steps: 9%|▉ | 88/1000 [00:41<05:25, 2.80it/s, loss=0.301, lr=1e-6]
Steps: 9%|▉ | 89/1000 [00:41<05:24, 2.81it/s, loss=0.301, lr=1e-6]
Steps: 9%|▉ | 90/1000 [00:42<05:23, 2.81it/s, loss=0.301, lr=1e-6]
Steps: 9%|▉ | 90/1000 [00:42<05:23, 2.81it/s, loss=0.306, lr=1e-6]
Steps: 9%|▉ | 91/1000 [00:42<05:23, 2.81it/s, loss=0.306, lr=1e-6]
Steps: 9%|▉ | 92/1000 [00:42<05:19, 2.84it/s, loss=0.306, lr=1e-6]
Steps: 9%|▉ | 93/1000 [00:43<05:17, 2.86it/s, loss=0.306, lr=1e-6]
Steps: 9%|▉ | 94/1000 [00:43<05:18, 2.85it/s, loss=0.306, lr=1e-6]
Steps: 10%|▉ | 95/1000 [00:44<05:17, 2.85it/s, loss=0.306, lr=1e-6]
Steps: 10%|▉ | 96/1000 [00:44<05:16, 2.86it/s, loss=0.306, lr=1e-6]
Steps: 10%|▉ | 97/1000 [00:44<05:17, 2.85it/s, loss=0.306, lr=1e-6]
Steps: 10%|▉ | 98/1000 [00:45<05:19, 2.83it/s, loss=0.306, lr=1e-6]
Steps: 10%|▉ | 99/1000 [00:45<05:21, 2.81it/s, loss=0.306, lr=1e-6]
Steps: 10%|█ | 100/1000 [00:45<05:20, 2.81it/s, loss=0.306, lr=1e-6]
Steps: 10%|█ | 100/1000 [00:46<05:20, 2.81it/s, loss=0.298, lr=1e-6]
Steps: 10%|█ | 101/1000 [00:46<05:23, 2.78it/s, loss=0.298, lr=1e-6]
Steps: 10%|█ | 102/1000 [00:46<05:21, 2.79it/s, loss=0.298, lr=1e-6]
Steps: 10%|█ | 103/1000 [00:46<05:18, 2.81it/s, loss=0.298, lr=1e-6]
Steps: 10%|█ | 104/1000 [00:47<05:19, 2.81it/s, loss=0.298, lr=1e-6]
Steps: 10%|█ | 105/1000 [00:47<05:19, 2.80it/s, loss=0.298, lr=1e-6]
Steps: 11%|█ | 106/1000 [00:47<05:18, 2.81it/s, loss=0.298, lr=1e-6]
Steps: 11%|█ | 107/1000 [00:48<05:15, 2.83it/s, loss=0.298, lr=1e-6]
Steps: 11%|█ | 108/1000 [00:48<05:17, 2.81it/s, loss=0.298, lr=1e-6]
Steps: 11%|█ | 109/1000 [00:48<05:16, 2.81it/s, loss=0.298, lr=1e-6]
Steps: 11%|█ | 110/1000 [00:49<05:15, 2.82it/s, loss=0.298, lr=1e-6]
Steps: 11%|█ | 110/1000 [00:49<05:15, 2.82it/s, loss=0.295, lr=1e-6]
Steps: 11%|█ | 111/1000 [00:49<05:18, 2.79it/s, loss=0.295, lr=1e-6]
Steps: 11%|█ | 112/1000 [00:50<05:15, 2.81it/s, loss=0.295, lr=1e-6]
Steps: 11%|█▏ | 113/1000 [00:50<05:14, 2.82it/s, loss=0.295, lr=1e-6]
Steps: 11%|█▏ | 114/1000 [00:50<05:14, 2.81it/s, loss=0.295, lr=1e-6]
Steps: 12%|█▏ | 115/1000 [00:51<05:15, 2.80it/s, loss=0.295, lr=1e-6]
Steps: 12%|█▏ | 116/1000 [00:51<05:15, 2.80it/s, loss=0.295, lr=1e-6]
Steps: 12%|█▏ | 117/1000 [00:51<05:16, 2.79it/s, loss=0.295, lr=1e-6]
Steps: 12%|█▏ | 118/1000 [00:52<05:18, 2.77it/s, loss=0.295, lr=1e-6]
Steps: 12%|█▏ | 119/1000 [00:52<05:20, 2.75it/s, loss=0.295, lr=1e-6]
Steps: 12%|█▏ | 120/1000 [00:52<05:18, 2.76it/s, loss=0.295, lr=1e-6]
Steps: 12%|█▏ | 120/1000 [00:53<05:18, 2.76it/s, loss=0.29, lr=1e-6]
Steps: 12%|█▏ | 121/1000 [00:53<05:16, 2.78it/s, loss=0.29, lr=1e-6]
Steps: 12%|█▏ | 122/1000 [00:53<05:17, 2.77it/s, loss=0.29, lr=1e-6]
Steps: 12%|█▏ | 123/1000 [00:54<05:14, 2.79it/s, loss=0.29, lr=1e-6]
Steps: 12%|█▏ | 124/1000 [00:54<05:15, 2.78it/s, loss=0.29, lr=1e-6]
Steps: 12%|█▎ | 125/1000 [00:54<05:14, 2.78it/s, loss=0.29, lr=1e-6]
Steps: 13%|█▎ | 126/1000 [00:55<05:13, 2.79it/s, loss=0.29, lr=1e-6]
Steps: 13%|█▎ | 127/1000 [00:55<05:11, 2.80it/s, loss=0.29, lr=1e-6]
Steps: 13%|█▎ | 128/1000 [00:55<05:12, 2.79it/s, loss=0.29, lr=1e-6]
Steps: 13%|█▎ | 129/1000 [00:56<05:11, 2.80it/s, loss=0.29, lr=1e-6]
Steps: 13%|█▎ | 130/1000 [00:56<05:09, 2.81it/s, loss=0.29, lr=1e-6]
Steps: 13%|█▎ | 130/1000 [00:56<05:09, 2.81it/s, loss=0.287, lr=1e-6]
Steps: 13%|█▎ | 131/1000 [00:56<05:10, 2.80it/s, loss=0.287, lr=1e-6]
Steps: 13%|█▎ | 132/1000 [00:57<05:08, 2.81it/s, loss=0.287, lr=1e-6]
Steps: 13%|█▎ | 133/1000 [00:57<05:07, 2.82it/s, loss=0.287, lr=1e-6]
Steps: 13%|█▎ | 134/1000 [00:57<05:07, 2.82it/s, loss=0.287, lr=1e-6]
Steps: 14%|█▎ | 135/1000 [00:58<05:05, 2.83it/s, loss=0.287, lr=1e-6]
Steps: 14%|█▎ | 136/1000 [00:58<05:04, 2.84it/s, loss=0.287, lr=1e-6]
Steps: 14%|█▎ | 137/1000 [00:59<05:07, 2.81it/s, loss=0.287, lr=1e-6]
Steps: 14%|█▍ | 138/1000 [00:59<05:05, 2.82it/s, loss=0.287, lr=1e-6]
Steps: 14%|█▍ | 139/1000 [00:59<05:04, 2.83it/s, loss=0.287, lr=1e-6]
Steps: 14%|█▍ | 140/1000 [01:00<05:06, 2.81it/s, loss=0.287, lr=1e-6]
Steps: 14%|█▍ | 140/1000 [01:00<05:06, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 14%|█▍ | 141/1000 [01:00<05:05, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 14%|█▍ | 142/1000 [01:00<05:05, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 14%|█▍ | 143/1000 [01:01<05:02, 2.83it/s, loss=0.282, lr=1e-6]
Steps: 14%|█▍ | 144/1000 [01:01<05:01, 2.84it/s, loss=0.282, lr=1e-6]
Steps: 14%|█▍ | 145/1000 [01:01<04:59, 2.85it/s, loss=0.282, lr=1e-6]
Steps: 15%|█▍ | 146/1000 [01:02<04:58, 2.86it/s, loss=0.282, lr=1e-6]
Steps: 15%|█▍ | 147/1000 [01:02<04:58, 2.85it/s, loss=0.282, lr=1e-6]
Steps: 15%|█▍ | 148/1000 [01:02<05:00, 2.84it/s, loss=0.282, lr=1e-6]
Steps: 15%|█▍ | 149/1000 [01:03<05:00, 2.83it/s, loss=0.282, lr=1e-6]
Steps: 15%|█▌ | 150/1000 [01:03<05:00, 2.83it/s, loss=0.282, lr=1e-6]
Steps: 15%|█▌ | 150/1000 [01:03<05:00, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 15%|█▌ | 151/1000 [01:03<05:01, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 15%|█▌ | 152/1000 [01:04<05:00, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 15%|█▌ | 153/1000 [01:04<05:00, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 15%|█▌ | 154/1000 [01:05<05:02, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 16%|█▌ | 155/1000 [01:05<05:01, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 16%|█▌ | 156/1000 [01:05<05:01, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 16%|█▌ | 157/1000 [01:06<05:07, 2.74it/s, loss=0.285, lr=1e-6]
Steps: 16%|█▌ | 158/1000 [01:06<05:04, 2.77it/s, loss=0.285, lr=1e-6]
Steps: 16%|█▌ | 159/1000 [01:06<05:00, 2.79it/s, loss=0.285, lr=1e-6]
Steps: 16%|█▌ | 160/1000 [01:07<05:01, 2.78it/s, loss=0.285, lr=1e-6]
Steps: 16%|█▌ | 160/1000 [01:07<05:01, 2.78it/s, loss=0.279, lr=1e-6]
Steps: 16%|█▌ | 161/1000 [01:07<05:00, 2.79it/s, loss=0.279, lr=1e-6]
Steps: 16%|█▌ | 162/1000 [01:07<04:59, 2.80it/s, loss=0.279, lr=1e-6]
Steps: 16%|█▋ | 163/1000 [01:08<04:58, 2.80it/s, loss=0.279, lr=1e-6]
Steps: 16%|█▋ | 164/1000 [01:08<04:58, 2.81it/s, loss=0.279, lr=1e-6]
Steps: 16%|█▋ | 165/1000 [01:08<04:57, 2.80it/s, loss=0.279, lr=1e-6]
Steps: 17%|█▋ | 166/1000 [01:09<04:57, 2.80it/s, loss=0.279, lr=1e-6]
Steps: 17%|█▋ | 167/1000 [01:09<04:56, 2.81it/s, loss=0.279, lr=1e-6]
Steps: 17%|█▋ | 168/1000 [01:10<04:58, 2.79it/s, loss=0.279, lr=1e-6]
Steps: 17%|█▋ | 169/1000 [01:10<04:58, 2.79it/s, loss=0.279, lr=1e-6]
Steps: 17%|█▋ | 170/1000 [01:10<04:56, 2.80it/s, loss=0.279, lr=1e-6]
Steps: 17%|█▋ | 170/1000 [01:11<04:56, 2.80it/s, loss=0.28, lr=1e-6]
Steps: 17%|█▋ | 171/1000 [01:11<04:57, 2.78it/s, loss=0.28, lr=1e-6]
Steps: 17%|█▋ | 172/1000 [01:11<04:55, 2.80it/s, loss=0.28, lr=1e-6]
Steps: 17%|█▋ | 173/1000 [01:11<04:53, 2.82it/s, loss=0.28, lr=1e-6]
Steps: 17%|█▋ | 174/1000 [01:12<04:52, 2.82it/s, loss=0.28, lr=1e-6]
Steps: 18%|█▊ | 175/1000 [01:12<04:53, 2.81it/s, loss=0.28, lr=1e-6]
Steps: 18%|█▊ | 176/1000 [01:12<04:53, 2.81it/s, loss=0.28, lr=1e-6]
Steps: 18%|█▊ | 177/1000 [01:13<04:53, 2.80it/s, loss=0.28, lr=1e-6]
Steps: 18%|█▊ | 178/1000 [01:13<04:53, 2.80it/s, loss=0.28, lr=1e-6]
Steps: 18%|█▊ | 179/1000 [01:13<04:51, 2.81it/s, loss=0.28, lr=1e-6]
Steps: 18%|█▊ | 180/1000 [01:14<04:51, 2.82it/s, loss=0.28, lr=1e-6]
Steps: 18%|█▊ | 180/1000 [01:14<04:51, 2.82it/s, loss=0.278, lr=1e-6]
Steps: 18%|█▊ | 181/1000 [01:14<04:50, 2.82it/s, loss=0.278, lr=1e-6]
Steps: 18%|█▊ | 182/1000 [01:15<04:49, 2.82it/s, loss=0.278, lr=1e-6]
Steps: 18%|█▊ | 183/1000 [01:15<04:50, 2.81it/s, loss=0.278, lr=1e-6]
Steps: 18%|█▊ | 184/1000 [01:15<04:48, 2.83it/s, loss=0.278, lr=1e-6]
Steps: 18%|█▊ | 185/1000 [01:16<04:53, 2.78it/s, loss=0.278, lr=1e-6]
Steps: 19%|█▊ | 186/1000 [01:16<04:52, 2.78it/s, loss=0.278, lr=1e-6]
Steps: 19%|█▊ | 187/1000 [01:16<04:51, 2.79it/s, loss=0.278, lr=1e-6]
Steps: 19%|█▉ | 188/1000 [01:17<04:50, 2.80it/s, loss=0.278, lr=1e-6]
Steps: 19%|█▉ | 189/1000 [01:17<04:49, 2.80it/s, loss=0.278, lr=1e-6]
Steps: 19%|█▉ | 190/1000 [01:17<04:46, 2.82it/s, loss=0.278, lr=1e-6]
Steps: 19%|█▉ | 190/1000 [01:18<04:46, 2.82it/s, loss=0.279, lr=1e-6]
Steps: 19%|█▉ | 191/1000 [01:18<04:45, 2.83it/s, loss=0.279, lr=1e-6]
Steps: 19%|█▉ | 192/1000 [01:18<04:45, 2.83it/s, loss=0.279, lr=1e-6]
Steps: 19%|█▉ | 193/1000 [01:18<04:44, 2.84it/s, loss=0.279, lr=1e-6]
Steps: 19%|█▉ | 194/1000 [01:19<04:44, 2.83it/s, loss=0.279, lr=1e-6]
Steps: 20%|█▉ | 195/1000 [01:19<04:44, 2.83it/s, loss=0.279, lr=1e-6]
Steps: 20%|█▉ | 196/1000 [01:19<04:45, 2.81it/s, loss=0.279, lr=1e-6]
Steps: 20%|█▉ | 197/1000 [01:20<04:46, 2.81it/s, loss=0.279, lr=1e-6]
Steps: 20%|█▉ | 198/1000 [01:20<04:44, 2.82it/s, loss=0.279, lr=1e-6]
Steps: 20%|█▉ | 199/1000 [01:21<04:45, 2.81it/s, loss=0.279, lr=1e-6]
Steps: 20%|██ | 200/1000 [01:21<04:45, 2.81it/s, loss=0.279, lr=1e-6]
Steps: 20%|██ | 200/1000 [01:21<04:45, 2.81it/s, loss=0.276, lr=1e-6]
Steps: 20%|██ | 201/1000 [01:21<04:44, 2.81it/s, loss=0.276, lr=1e-6]
Steps: 20%|██ | 202/1000 [01:22<04:43, 2.81it/s, loss=0.276, lr=1e-6]
Steps: 20%|██ | 203/1000 [01:22<04:41, 2.83it/s, loss=0.276, lr=1e-6]
Steps: 20%|██ | 204/1000 [01:22<04:39, 2.85it/s, loss=0.276, lr=1e-6]
Steps: 20%|██ | 205/1000 [01:23<04:40, 2.84it/s, loss=0.276, lr=1e-6]
Steps: 21%|██ | 206/1000 [01:23<04:40, 2.83it/s, loss=0.276, lr=1e-6]
Steps: 21%|██ | 207/1000 [01:23<04:39, 2.84it/s, loss=0.276, lr=1e-6]
Steps: 21%|██ | 208/1000 [01:24<04:38, 2.84it/s, loss=0.276, lr=1e-6]
Steps: 21%|██ | 209/1000 [01:24<04:41, 2.81it/s, loss=0.276, lr=1e-6]
Steps: 21%|██ | 210/1000 [01:24<04:41, 2.80it/s, loss=0.276, lr=1e-6]
Steps: 21%|██ | 210/1000 [01:25<04:41, 2.80it/s, loss=0.275, lr=1e-6]
Steps: 21%|██ | 211/1000 [01:25<04:40, 2.82it/s, loss=0.275, lr=1e-6]
Steps: 21%|██ | 212/1000 [01:25<04:39, 2.82it/s, loss=0.275, lr=1e-6]
Steps: 21%|██▏ | 213/1000 [01:26<04:44, 2.77it/s, loss=0.275, lr=1e-6]
Steps: 21%|██▏ | 214/1000 [01:26<04:41, 2.79it/s, loss=0.275, lr=1e-6]
Steps: 22%|██▏ | 215/1000 [01:26<04:38, 2.81it/s, loss=0.275, lr=1e-6]
Steps: 22%|██▏ | 216/1000 [01:27<04:38, 2.81it/s, loss=0.275, lr=1e-6]
Steps: 22%|██▏ | 217/1000 [01:27<04:38, 2.81it/s, loss=0.275, lr=1e-6]
Steps: 22%|██▏ | 218/1000 [01:27<04:36, 2.83it/s, loss=0.275, lr=1e-6]
Steps: 22%|██▏ | 219/1000 [01:28<04:36, 2.82it/s, loss=0.275, lr=1e-6]
Steps: 22%|██▏ | 220/1000 [01:28<04:37, 2.81it/s, loss=0.275, lr=1e-6]
Steps: 22%|██▏ | 220/1000 [01:28<04:37, 2.81it/s, loss=0.275, lr=1e-6]
Steps: 22%|██▏ | 221/1000 [01:28<04:35, 2.82it/s, loss=0.275, lr=1e-6]
Steps: 22%|██▏ | 222/1000 [01:29<04:34, 2.84it/s, loss=0.275, lr=1e-6]
Steps: 22%|██▏ | 223/1000 [01:29<04:33, 2.84it/s, loss=0.275, lr=1e-6]
Steps: 22%|██▏ | 224/1000 [01:29<04:32, 2.85it/s, loss=0.275, lr=1e-6]
Steps: 22%|██▎ | 225/1000 [01:30<04:31, 2.86it/s, loss=0.275, lr=1e-6]
Steps: 23%|██▎ | 226/1000 [01:30<04:31, 2.86it/s, loss=0.275, lr=1e-6]
Steps: 23%|██▎ | 227/1000 [01:30<04:30, 2.86it/s, loss=0.275, lr=1e-6]
Steps: 23%|██▎ | 228/1000 [01:31<04:30, 2.86it/s, loss=0.275, lr=1e-6]
Steps: 23%|██▎ | 229/1000 [01:31<04:30, 2.85it/s, loss=0.275, lr=1e-6]
Steps: 23%|██▎ | 230/1000 [01:32<04:30, 2.85it/s, loss=0.275, lr=1e-6]
Steps: 23%|██▎ | 230/1000 [01:32<04:30, 2.85it/s, loss=0.276, lr=1e-6]
Steps: 23%|██▎ | 231/1000 [01:32<04:29, 2.85it/s, loss=0.276, lr=1e-6]
Steps: 23%|██▎ | 232/1000 [01:32<04:28, 2.86it/s, loss=0.276, lr=1e-6]
Steps: 23%|██▎ | 233/1000 [01:33<04:28, 2.86it/s, loss=0.276, lr=1e-6]
Steps: 23%|██▎ | 234/1000 [01:33<04:27, 2.86it/s, loss=0.276, lr=1e-6]
Steps: 24%|██▎ | 235/1000 [01:33<04:28, 2.85it/s, loss=0.276, lr=1e-6]
Steps: 24%|██▎ | 236/1000 [01:34<04:30, 2.82it/s, loss=0.276, lr=1e-6]
Steps: 24%|██▎ | 237/1000 [01:34<04:30, 2.82it/s, loss=0.276, lr=1e-6]
Steps: 24%|██▍ | 238/1000 [01:34<04:34, 2.78it/s, loss=0.276, lr=1e-6]
Steps: 24%|██▍ | 239/1000 [01:35<04:32, 2.79it/s, loss=0.276, lr=1e-6]
Steps: 24%|██▍ | 240/1000 [01:35<04:32, 2.79it/s, loss=0.276, lr=1e-6]
Steps: 24%|██▍ | 240/1000 [01:35<04:32, 2.79it/s, loss=0.282, lr=1e-6]
Steps: 24%|██▍ | 241/1000 [01:35<04:36, 2.75it/s, loss=0.282, lr=1e-6]
Steps: 24%|██▍ | 242/1000 [01:36<04:34, 2.76it/s, loss=0.282, lr=1e-6]
Steps: 24%|██▍ | 243/1000 [01:36<04:32, 2.78it/s, loss=0.282, lr=1e-6]
Steps: 24%|██▍ | 244/1000 [01:37<04:30, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 24%|██▍ | 245/1000 [01:37<04:28, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 25%|██▍ | 246/1000 [01:37<04:28, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 25%|██▍ | 247/1000 [01:38<04:28, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 25%|██▍ | 248/1000 [01:38<04:29, 2.79it/s, loss=0.282, lr=1e-6]
Steps: 25%|██▍ | 249/1000 [01:38<04:29, 2.79it/s, loss=0.282, lr=1e-6]
Steps: 25%|██▌ | 250/1000 [01:39<04:30, 2.77it/s, loss=0.282, lr=1e-6]
Steps: 25%|██▌ | 250/1000 [01:39<04:30, 2.77it/s, loss=0.285, lr=1e-6]
Steps: 25%|██▌ | 251/1000 [01:39<04:30, 2.77it/s, loss=0.285, lr=1e-6]
Steps: 25%|██▌ | 252/1000 [01:39<04:29, 2.77it/s, loss=0.285, lr=1e-6]
Steps: 25%|██▌ | 253/1000 [01:40<04:29, 2.77it/s, loss=0.285, lr=1e-6]
Steps: 25%|██▌ | 254/1000 [01:40<04:26, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 26%|██▌ | 255/1000 [01:40<04:26, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 26%|██▌ | 256/1000 [01:41<04:22, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 26%|██▌ | 257/1000 [01:41<04:20, 2.85it/s, loss=0.285, lr=1e-6]
Steps: 26%|██▌ | 258/1000 [01:42<04:22, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 26%|██▌ | 259/1000 [01:42<04:20, 2.85it/s, loss=0.285, lr=1e-6]
Steps: 26%|██▌ | 260/1000 [01:42<04:18, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 26%|██▌ | 260/1000 [01:43<04:18, 2.86it/s, loss=0.284, lr=1e-6]
Steps: 26%|██▌ | 261/1000 [01:43<04:19, 2.85it/s, loss=0.284, lr=1e-6]
Steps: 26%|██▌ | 262/1000 [01:43<04:18, 2.85it/s, loss=0.284, lr=1e-6]
Steps: 26%|██▋ | 263/1000 [01:43<04:17, 2.87it/s, loss=0.284, lr=1e-6]
Steps: 26%|██▋ | 264/1000 [01:44<04:18, 2.84it/s, loss=0.284, lr=1e-6]
Steps: 26%|██▋ | 265/1000 [01:44<04:19, 2.83it/s, loss=0.284, lr=1e-6]
Steps: 27%|██▋ | 266/1000 [01:44<04:20, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 27%|██▋ | 267/1000 [01:45<04:19, 2.83it/s, loss=0.284, lr=1e-6]
Steps: 27%|██▋ | 268/1000 [01:45<04:19, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 27%|██▋ | 269/1000 [01:45<04:20, 2.81it/s, loss=0.284, lr=1e-6]
Steps: 27%|██▋ | 270/1000 [01:46<04:19, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 27%|██▋ | 270/1000 [01:46<04:19, 2.82it/s, loss=0.286, lr=1e-6]
Steps: 27%|██▋ | 271/1000 [01:46<04:18, 2.82it/s, loss=0.286, lr=1e-6]
Steps: 27%|██▋ | 272/1000 [01:46<04:18, 2.82it/s, loss=0.286, lr=1e-6]
Steps: 27%|██▋ | 273/1000 [01:47<04:17, 2.82it/s, loss=0.286, lr=1e-6]
Steps: 27%|██▋ | 274/1000 [01:47<04:16, 2.84it/s, loss=0.286, lr=1e-6]
Steps: 28%|██▊ | 275/1000 [01:48<04:15, 2.83it/s, loss=0.286, lr=1e-6]
Steps: 28%|██▊ | 276/1000 [01:48<04:15, 2.83it/s, loss=0.286, lr=1e-6]
Steps: 28%|██▊ | 277/1000 [01:48<04:15, 2.83it/s, loss=0.286, lr=1e-6]
Steps: 28%|██▊ | 278/1000 [01:49<04:16, 2.81it/s, loss=0.286, lr=1e-6]
Steps: 28%|██▊ | 279/1000 [01:49<04:15, 2.83it/s, loss=0.286, lr=1e-6]
Steps: 28%|██▊ | 280/1000 [01:49<04:12, 2.85it/s, loss=0.286, lr=1e-6]
Steps: 28%|██▊ | 280/1000 [01:50<04:12, 2.85it/s, loss=0.287, lr=1e-6]
Steps: 28%|██▊ | 281/1000 [01:50<04:15, 2.82it/s, loss=0.287, lr=1e-6]
Steps: 28%|██▊ | 282/1000 [01:50<04:14, 2.82it/s, loss=0.287, lr=1e-6]
Steps: 28%|██▊ | 283/1000 [01:50<04:12, 2.83it/s, loss=0.287, lr=1e-6]
Steps: 28%|██▊ | 284/1000 [01:51<04:15, 2.80it/s, loss=0.287, lr=1e-6]
Steps: 28%|██▊ | 285/1000 [01:51<04:13, 2.82it/s, loss=0.287, lr=1e-6]
Steps: 29%|██▊ | 286/1000 [01:51<04:11, 2.84it/s, loss=0.287, lr=1e-6]
Steps: 29%|██▊ | 287/1000 [01:52<04:11, 2.84it/s, loss=0.287, lr=1e-6]
Steps: 29%|██▉ | 288/1000 [01:52<04:10, 2.84it/s, loss=0.287, lr=1e-6]
Steps: 29%|██▉ | 289/1000 [01:52<04:10, 2.84it/s, loss=0.287, lr=1e-6]
Steps: 29%|██▉ | 290/1000 [01:53<04:09, 2.84it/s, loss=0.287, lr=1e-6]
Steps: 29%|██▉ | 290/1000 [01:53<04:09, 2.84it/s, loss=0.287, lr=1e-6]
Steps: 29%|██▉ | 291/1000 [01:53<04:08, 2.85it/s, loss=0.287, lr=1e-6]
Steps: 29%|██▉ | 292/1000 [01:53<04:07, 2.85it/s, loss=0.287, lr=1e-6]
Steps: 29%|██▉ | 293/1000 [01:54<04:09, 2.83it/s, loss=0.287, lr=1e-6]
Steps: 29%|██▉ | 294/1000 [01:54<04:09, 2.83it/s, loss=0.287, lr=1e-6]
Steps: 30%|██▉ | 295/1000 [01:55<04:09, 2.82it/s, loss=0.287, lr=1e-6]
Steps: 30%|██▉ | 296/1000 [01:55<04:07, 2.84it/s, loss=0.287, lr=1e-6]
Steps: 30%|██▉ | 297/1000 [01:55<04:05, 2.86it/s, loss=0.287, lr=1e-6]
Steps: 30%|██▉ | 298/1000 [01:56<04:13, 2.77it/s, loss=0.287, lr=1e-6]
Steps: 30%|██▉ | 299/1000 [01:56<04:10, 2.79it/s, loss=0.287, lr=1e-6]
Steps: 30%|███ | 300/1000 [01:56<04:09, 2.81it/s, loss=0.287, lr=1e-6]
Steps: 30%|███ | 300/1000 [01:57<04:09, 2.81it/s, loss=0.288, lr=1e-6]
Steps: 30%|███ | 301/1000 [01:57<04:11, 2.77it/s, loss=0.288, lr=1e-6]
Steps: 30%|███ | 302/1000 [01:57<04:09, 2.80it/s, loss=0.288, lr=1e-6]
Steps: 30%|███ | 303/1000 [01:57<04:08, 2.81it/s, loss=0.288, lr=1e-6]
Steps: 30%|███ | 304/1000 [01:58<04:06, 2.83it/s, loss=0.288, lr=1e-6]
Steps: 30%|███ | 305/1000 [01:58<04:06, 2.82it/s, loss=0.288, lr=1e-6]
Steps: 31%|███ | 306/1000 [01:58<04:05, 2.83it/s, loss=0.288, lr=1e-6]
Steps: 31%|███ | 307/1000 [01:59<04:06, 2.81it/s, loss=0.288, lr=1e-6]
Steps: 31%|███ | 308/1000 [01:59<04:06, 2.81it/s, loss=0.288, lr=1e-6]
Steps: 31%|███ | 309/1000 [02:00<04:06, 2.81it/s, loss=0.288, lr=1e-6]
Steps: 31%|███ | 310/1000 [02:00<04:11, 2.75it/s, loss=0.288, lr=1e-6]
Steps: 31%|███ | 310/1000 [02:00<04:11, 2.75it/s, loss=0.29, lr=1e-6]
Steps: 31%|███ | 311/1000 [02:00<04:11, 2.74it/s, loss=0.29, lr=1e-6]
Steps: 31%|███ | 312/1000 [02:01<04:08, 2.77it/s, loss=0.29, lr=1e-6]
Steps: 31%|███▏ | 313/1000 [02:01<04:10, 2.75it/s, loss=0.29, lr=1e-6]
Steps: 31%|███▏ | 314/1000 [02:01<04:08, 2.76it/s, loss=0.29, lr=1e-6]
Steps: 32%|███▏ | 315/1000 [02:02<04:06, 2.78it/s, loss=0.29, lr=1e-6]
Steps: 32%|███▏ | 316/1000 [02:02<04:03, 2.80it/s, loss=0.29, lr=1e-6]
Steps: 32%|███▏ | 317/1000 [02:02<04:03, 2.80it/s, loss=0.29, lr=1e-6]
Steps: 32%|███▏ | 318/1000 [02:03<04:02, 2.81it/s, loss=0.29, lr=1e-6]
Steps: 32%|███▏ | 319/1000 [02:03<04:00, 2.83it/s, loss=0.29, lr=1e-6]
Steps: 32%|███▏ | 320/1000 [02:03<03:58, 2.85it/s, loss=0.29, lr=1e-6]
Steps: 32%|███▏ | 320/1000 [02:04<03:58, 2.85it/s, loss=0.292, lr=1e-6]
Steps: 32%|███▏ | 321/1000 [02:04<03:58, 2.85it/s, loss=0.292, lr=1e-6]
Steps: 32%|███▏ | 322/1000 [02:04<03:57, 2.85it/s, loss=0.292, lr=1e-6]
Steps: 32%|███▏ | 323/1000 [02:05<03:58, 2.84it/s, loss=0.292, lr=1e-6]
Steps: 32%|███▏ | 324/1000 [02:05<03:59, 2.82it/s, loss=0.292, lr=1e-6]
Steps: 32%|███▎ | 325/1000 [02:05<03:57, 2.84it/s, loss=0.292, lr=1e-6]
Steps: 33%|███▎ | 326/1000 [02:06<04:01, 2.79it/s, loss=0.292, lr=1e-6]
Steps: 33%|███▎ | 327/1000 [02:06<04:01, 2.79it/s, loss=0.292, lr=1e-6]
Steps: 33%|███▎ | 328/1000 [02:06<03:59, 2.81it/s, loss=0.292, lr=1e-6]
Steps: 33%|███▎ | 329/1000 [02:07<04:00, 2.80it/s, loss=0.292, lr=1e-6]
Steps: 33%|███▎ | 330/1000 [02:07<04:01, 2.78it/s, loss=0.292, lr=1e-6]
Steps: 33%|███▎ | 330/1000 [02:07<04:01, 2.78it/s, loss=0.294, lr=1e-6]
Steps: 33%|███▎ | 331/1000 [02:07<03:58, 2.80it/s, loss=0.294, lr=1e-6]
Steps: 33%|███▎ | 332/1000 [02:08<03:56, 2.83it/s, loss=0.294, lr=1e-6]
Steps: 33%|███▎ | 333/1000 [02:08<03:55, 2.83it/s, loss=0.294, lr=1e-6]
Steps: 33%|███▎ | 334/1000 [02:08<03:54, 2.85it/s, loss=0.294, lr=1e-6]
Steps: 34%|███▎ | 335/1000 [02:09<03:53, 2.85it/s, loss=0.294, lr=1e-6]
Steps: 34%|███▎ | 336/1000 [02:09<03:52, 2.85it/s, loss=0.294, lr=1e-6]
Steps: 34%|███▎ | 337/1000 [02:10<03:53, 2.85it/s, loss=0.294, lr=1e-6]
Steps: 34%|███▍ | 338/1000 [02:10<03:51, 2.85it/s, loss=0.294, lr=1e-6]
Steps: 34%|███▍ | 339/1000 [02:10<03:52, 2.84it/s, loss=0.294, lr=1e-6]
Steps: 34%|███▍ | 340/1000 [02:11<03:50, 2.86it/s, loss=0.294, lr=1e-6]
Steps: 34%|███▍ | 340/1000 [02:11<03:50, 2.86it/s, loss=0.291, lr=1e-6]
Steps: 34%|███▍ | 341/1000 [02:11<03:51, 2.85it/s, loss=0.291, lr=1e-6]
Steps: 34%|███▍ | 342/1000 [02:11<03:50, 2.86it/s, loss=0.291, lr=1e-6]
Steps: 34%|███▍ | 343/1000 [02:12<03:48, 2.87it/s, loss=0.291, lr=1e-6]
Steps: 34%|███▍ | 344/1000 [02:12<03:50, 2.85it/s, loss=0.291, lr=1e-6]
Steps: 34%|███▍ | 345/1000 [02:12<03:48, 2.87it/s, loss=0.291, lr=1e-6]
Steps: 35%|███▍ | 346/1000 [02:13<03:47, 2.87it/s, loss=0.291, lr=1e-6]
Steps: 35%|███▍ | 347/1000 [02:13<03:48, 2.86it/s, loss=0.291, lr=1e-6]
Steps: 35%|███▍ | 348/1000 [02:13<03:48, 2.86it/s, loss=0.291, lr=1e-6]
Steps: 35%|███▍ | 349/1000 [02:14<03:49, 2.83it/s, loss=0.291, lr=1e-6]
Steps: 35%|███▌ | 350/1000 [02:14<03:50, 2.81it/s, loss=0.291, lr=1e-6]
Steps: 35%|███▌ | 350/1000 [02:14<03:50, 2.81it/s, loss=0.293, lr=1e-6]
Steps: 35%|███▌ | 351/1000 [02:14<03:53, 2.79it/s, loss=0.293, lr=1e-6]
Steps: 35%|███▌ | 352/1000 [02:15<03:51, 2.80it/s, loss=0.293, lr=1e-6]
Steps: 35%|███▌ | 353/1000 [02:15<03:51, 2.79it/s, loss=0.293, lr=1e-6]
Steps: 35%|███▌ | 354/1000 [02:16<03:55, 2.75it/s, loss=0.293, lr=1e-6]
Steps: 36%|███▌ | 355/1000 [02:16<03:52, 2.78it/s, loss=0.293, lr=1e-6]
Steps: 36%|███▌ | 356/1000 [02:16<03:50, 2.79it/s, loss=0.293, lr=1e-6]
Steps: 36%|███▌ | 357/1000 [02:17<03:50, 2.79it/s, loss=0.293, lr=1e-6]
Steps: 36%|███▌ | 358/1000 [02:17<03:48, 2.81it/s, loss=0.293, lr=1e-6]
Steps: 36%|███▌ | 359/1000 [02:17<03:46, 2.82it/s, loss=0.293, lr=1e-6]
Steps: 36%|███▌ | 360/1000 [02:18<03:46, 2.83it/s, loss=0.293, lr=1e-6]
Steps: 36%|███▌ | 360/1000 [02:18<03:46, 2.83it/s, loss=0.291, lr=1e-6]
Steps: 36%|███▌ | 361/1000 [02:18<03:45, 2.83it/s, loss=0.291, lr=1e-6]
Steps: 36%|███▌ | 362/1000 [02:18<03:43, 2.85it/s, loss=0.291, lr=1e-6]
Steps: 36%|███▋ | 363/1000 [02:19<03:42, 2.86it/s, loss=0.291, lr=1e-6]
Steps: 36%|███▋ | 364/1000 [02:19<03:42, 2.86it/s, loss=0.291, lr=1e-6]
Steps: 36%|███▋ | 365/1000 [02:19<03:42, 2.85it/s, loss=0.291, lr=1e-6]
Steps: 37%|███▋ | 366/1000 [02:20<03:42, 2.85it/s, loss=0.291, lr=1e-6]
Steps: 37%|███▋ | 367/1000 [02:20<03:42, 2.84it/s, loss=0.291, lr=1e-6]
Steps: 37%|███▋ | 368/1000 [02:20<03:43, 2.83it/s, loss=0.291, lr=1e-6]
Steps: 37%|███▋ | 369/1000 [02:21<03:42, 2.84it/s, loss=0.291, lr=1e-6]
Steps: 37%|███▋ | 370/1000 [02:21<03:41, 2.84it/s, loss=0.291, lr=1e-6]
Steps: 37%|███▋ | 370/1000 [02:22<03:41, 2.84it/s, loss=0.29, lr=1e-6]
Steps: 37%|███▋ | 371/1000 [02:22<03:42, 2.83it/s, loss=0.29, lr=1e-6]
Steps: 37%|███▋ | 372/1000 [02:22<03:42, 2.83it/s, loss=0.29, lr=1e-6]
Steps: 37%|███▋ | 373/1000 [02:22<03:41, 2.83it/s, loss=0.29, lr=1e-6]
Steps: 37%|███▋ | 374/1000 [02:23<03:41, 2.83it/s, loss=0.29, lr=1e-6]
Steps: 38%|███▊ | 375/1000 [02:23<03:41, 2.83it/s, loss=0.29, lr=1e-6]
Steps: 38%|███▊ | 376/1000 [02:23<03:39, 2.84it/s, loss=0.29, lr=1e-6]
Steps: 38%|███▊ | 377/1000 [02:24<03:40, 2.83it/s, loss=0.29, lr=1e-6]
Steps: 38%|███▊ | 378/1000 [02:24<03:39, 2.83it/s, loss=0.29, lr=1e-6]
Steps: 38%|███▊ | 379/1000 [02:24<03:40, 2.82it/s, loss=0.29, lr=1e-6]
Steps: 38%|███▊ | 380/1000 [02:25<03:40, 2.81it/s, loss=0.29, lr=1e-6]
Steps: 38%|███▊ | 380/1000 [02:25<03:40, 2.81it/s, loss=0.287, lr=1e-6]
Steps: 38%|███▊ | 381/1000 [02:25<03:39, 2.82it/s, loss=0.287, lr=1e-6]
Steps: 38%|███▊ | 382/1000 [02:25<03:42, 2.78it/s, loss=0.287, lr=1e-6]
Steps: 38%|███▊ | 383/1000 [02:26<03:40, 2.80it/s, loss=0.287, lr=1e-6]
Steps: 38%|███▊ | 384/1000 [02:26<03:38, 2.81it/s, loss=0.287, lr=1e-6]
Steps: 38%|███▊ | 385/1000 [02:26<03:38, 2.81it/s, loss=0.287, lr=1e-6]
Steps: 39%|███▊ | 386/1000 [02:27<03:38, 2.81it/s, loss=0.287, lr=1e-6]
Steps: 39%|███▊ | 387/1000 [02:27<03:38, 2.81it/s, loss=0.287, lr=1e-6]
Steps: 39%|███▉ | 388/1000 [02:28<03:39, 2.79it/s, loss=0.287, lr=1e-6]
Steps: 39%|███▉ | 389/1000 [02:28<03:37, 2.80it/s, loss=0.287, lr=1e-6]
Steps: 39%|███▉ | 390/1000 [02:28<03:37, 2.81it/s, loss=0.287, lr=1e-6]
Steps: 39%|███▉ | 390/1000 [02:29<03:37, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 39%|███▉ | 391/1000 [02:29<03:38, 2.78it/s, loss=0.285, lr=1e-6]
Steps: 39%|███▉ | 392/1000 [02:29<03:38, 2.78it/s, loss=0.285, lr=1e-6]
Steps: 39%|███▉ | 393/1000 [02:29<03:37, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 39%|███▉ | 394/1000 [02:30<03:36, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 40%|███▉ | 395/1000 [02:30<03:35, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 40%|███▉ | 396/1000 [02:30<03:36, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 40%|███▉ | 397/1000 [02:31<03:35, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 40%|███▉ | 398/1000 [02:31<03:34, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 40%|███▉ | 399/1000 [02:32<03:36, 2.78it/s, loss=0.285, lr=1e-6]
Steps: 40%|████ | 400/1000 [02:32<03:33, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 40%|████ | 400/1000 [02:32<03:33, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 40%|████ | 401/1000 [02:32<03:31, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 40%|████ | 402/1000 [02:33<03:31, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 40%|████ | 403/1000 [02:33<03:30, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 40%|████ | 404/1000 [02:33<03:29, 2.85it/s, loss=0.285, lr=1e-6]
Steps: 40%|████ | 405/1000 [02:34<03:29, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 41%|████ | 406/1000 [02:34<03:29, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 41%|████ | 407/1000 [02:34<03:29, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 41%|████ | 408/1000 [02:35<03:28, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 41%|████ | 409/1000 [02:35<03:28, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 41%|████ | 410/1000 [02:35<03:29, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 41%|████ | 410/1000 [02:36<03:29, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 41%|████ | 411/1000 [02:36<03:28, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 41%|████ | 412/1000 [02:36<03:27, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 41%|████▏ | 413/1000 [02:36<03:27, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 41%|████▏ | 414/1000 [02:37<03:27, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 42%|████▏ | 415/1000 [02:37<03:27, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 42%|████▏ | 416/1000 [02:37<03:25, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 42%|████▏ | 417/1000 [02:38<03:26, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 42%|████▏ | 418/1000 [02:38<03:25, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 42%|████▏ | 419/1000 [02:39<03:24, 2.85it/s, loss=0.285, lr=1e-6]
Steps: 42%|████▏ | 420/1000 [02:39<03:25, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 42%|████▏ | 420/1000 [02:39<03:25, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 42%|████▏ | 421/1000 [02:39<03:23, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 42%|████▏ | 422/1000 [02:40<03:22, 2.85it/s, loss=0.285, lr=1e-6]
Steps: 42%|████▏ | 423/1000 [02:40<03:22, 2.85it/s, loss=0.285, lr=1e-6]
Steps: 42%|████▏ | 424/1000 [02:40<03:22, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 42%|████▎ | 425/1000 [02:41<03:21, 2.85it/s, loss=0.285, lr=1e-6]
Steps: 43%|████▎ | 426/1000 [02:41<03:21, 2.85it/s, loss=0.285, lr=1e-6]
Steps: 43%|████▎ | 427/1000 [02:41<03:19, 2.87it/s, loss=0.285, lr=1e-6]
Steps: 43%|████▎ | 428/1000 [02:42<03:18, 2.87it/s, loss=0.285, lr=1e-6]
Steps: 43%|████▎ | 429/1000 [02:42<03:19, 2.87it/s, loss=0.285, lr=1e-6]
Steps: 43%|████▎ | 430/1000 [02:42<03:19, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 43%|████▎ | 430/1000 [02:43<03:19, 2.86it/s, loss=0.286, lr=1e-6]
Steps: 43%|████▎ | 431/1000 [02:43<03:19, 2.86it/s, loss=0.286, lr=1e-6]
Steps: 43%|████▎ | 432/1000 [02:43<03:18, 2.86it/s, loss=0.286, lr=1e-6]
Steps: 43%|████▎ | 433/1000 [02:43<03:18, 2.86it/s, loss=0.286, lr=1e-6]
Steps: 43%|████▎ | 434/1000 [02:44<03:19, 2.84it/s, loss=0.286, lr=1e-6]
Steps: 44%|████▎ | 435/1000 [02:44<03:18, 2.84it/s, loss=0.286, lr=1e-6]
Steps: 44%|████▎ | 436/1000 [02:45<03:20, 2.81it/s, loss=0.286, lr=1e-6]
Steps: 44%|████▎ | 437/1000 [02:45<03:19, 2.82it/s, loss=0.286, lr=1e-6]
Steps: 44%|████▍ | 438/1000 [02:45<03:17, 2.84it/s, loss=0.286, lr=1e-6]
Steps: 44%|████▍ | 439/1000 [02:46<03:19, 2.81it/s, loss=0.286, lr=1e-6]
Steps: 44%|████▍ | 440/1000 [02:46<03:18, 2.82it/s, loss=0.286, lr=1e-6]
Steps: 44%|████▍ | 440/1000 [02:46<03:18, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 44%|████▍ | 441/1000 [02:46<03:18, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 44%|████▍ | 442/1000 [02:47<03:16, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 44%|████▍ | 443/1000 [02:47<03:18, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 44%|████▍ | 444/1000 [02:47<03:16, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 44%|████▍ | 445/1000 [02:48<03:15, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 45%|████▍ | 446/1000 [02:48<03:15, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 45%|████▍ | 447/1000 [02:48<03:15, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 45%|████▍ | 448/1000 [02:49<03:14, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 45%|████▍ | 449/1000 [02:49<03:15, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 45%|████▌ | 450/1000 [02:49<03:13, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 45%|████▌ | 450/1000 [02:50<03:13, 2.84it/s, loss=0.286, lr=1e-6]
Steps: 45%|████▌ | 451/1000 [02:50<03:13, 2.84it/s, loss=0.286, lr=1e-6]
Steps: 45%|████▌ | 452/1000 [02:50<03:13, 2.84it/s, loss=0.286, lr=1e-6]
Steps: 45%|████▌ | 453/1000 [02:51<03:12, 2.84it/s, loss=0.286, lr=1e-6]
Steps: 45%|████▌ | 454/1000 [02:51<03:12, 2.84it/s, loss=0.286, lr=1e-6]
Steps: 46%|████▌ | 455/1000 [02:51<03:10, 2.86it/s, loss=0.286, lr=1e-6]
Steps: 46%|████▌ | 456/1000 [02:52<03:11, 2.84it/s, loss=0.286, lr=1e-6]
Steps: 46%|████▌ | 457/1000 [02:52<03:12, 2.83it/s, loss=0.286, lr=1e-6]
Steps: 46%|████▌ | 458/1000 [02:52<03:11, 2.84it/s, loss=0.286, lr=1e-6]
Steps: 46%|████▌ | 459/1000 [02:53<03:10, 2.84it/s, loss=0.286, lr=1e-6]
Steps: 46%|████▌ | 460/1000 [02:53<03:11, 2.82it/s, loss=0.286, lr=1e-6]
Steps: 46%|████▌ | 460/1000 [02:53<03:11, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 46%|████▌ | 461/1000 [02:53<03:10, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 46%|████▌ | 462/1000 [02:54<03:08, 2.85it/s, loss=0.285, lr=1e-6]
Steps: 46%|████▋ | 463/1000 [02:54<03:11, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 46%|████▋ | 464/1000 [02:54<03:11, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 46%|████▋ | 465/1000 [02:55<03:09, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 47%|████▋ | 466/1000 [02:55<03:09, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 47%|████▋ | 467/1000 [02:55<03:10, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 47%|████▋ | 468/1000 [02:56<03:08, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 47%|████▋ | 469/1000 [02:56<03:07, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 47%|████▋ | 470/1000 [02:57<03:06, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 47%|████▋ | 470/1000 [02:57<03:06, 2.84it/s, loss=0.283, lr=1e-6]
Steps: 47%|████▋ | 471/1000 [02:57<03:05, 2.84it/s, loss=0.283, lr=1e-6]
Steps: 47%|████▋ | 472/1000 [02:57<03:05, 2.85it/s, loss=0.283, lr=1e-6]
Steps: 47%|████▋ | 473/1000 [02:58<03:04, 2.86it/s, loss=0.283, lr=1e-6]
Steps: 47%|████▋ | 474/1000 [02:58<03:04, 2.85it/s, loss=0.283, lr=1e-6]
Steps: 48%|████▊ | 475/1000 [02:58<03:04, 2.84it/s, loss=0.283, lr=1e-6]
Steps: 48%|████▊ | 476/1000 [02:59<03:05, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 48%|████▊ | 477/1000 [02:59<03:05, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 48%|████▊ | 478/1000 [02:59<03:04, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 48%|████▊ | 479/1000 [03:00<03:03, 2.84it/s, loss=0.283, lr=1e-6]
Steps: 48%|████▊ | 480/1000 [03:00<03:03, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 48%|████▊ | 480/1000 [03:00<03:03, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 48%|████▊ | 481/1000 [03:00<03:02, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 48%|████▊ | 482/1000 [03:01<03:01, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 48%|████▊ | 483/1000 [03:01<03:00, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 48%|████▊ | 484/1000 [03:01<02:59, 2.87it/s, loss=0.285, lr=1e-6]
Steps: 48%|████▊ | 485/1000 [03:02<02:58, 2.88it/s, loss=0.285, lr=1e-6]
Steps: 49%|████▊ | 486/1000 [03:02<02:59, 2.87it/s, loss=0.285, lr=1e-6]
Steps: 49%|████▊ | 487/1000 [03:02<02:59, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 49%|████▉ | 488/1000 [03:03<02:58, 2.87it/s, loss=0.285, lr=1e-6]
Steps: 49%|████▉ | 489/1000 [03:03<02:58, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 49%|████▉ | 490/1000 [03:04<02:57, 2.87it/s, loss=0.285, lr=1e-6]
Steps: 49%|████▉ | 490/1000 [03:04<02:57, 2.87it/s, loss=0.283, lr=1e-6]
Steps: 49%|████▉ | 491/1000 [03:04<02:57, 2.87it/s, loss=0.283, lr=1e-6]
Steps: 49%|████▉ | 492/1000 [03:04<02:58, 2.85it/s, loss=0.283, lr=1e-6]
Steps: 49%|████▉ | 493/1000 [03:05<02:59, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 49%|████▉ | 494/1000 [03:05<02:58, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 50%|████▉ | 495/1000 [03:05<02:58, 2.82it/s, loss=0.283, lr=1e-6]
Steps: 50%|████▉ | 496/1000 [03:06<02:59, 2.81it/s, loss=0.283, lr=1e-6]
Steps: 50%|████▉ | 497/1000 [03:06<02:58, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 50%|████▉ | 498/1000 [03:06<02:57, 2.82it/s, loss=0.283, lr=1e-6]
Steps: 50%|████▉ | 499/1000 [03:07<02:58, 2.81it/s, loss=0.283, lr=1e-6]
Steps: 50%|█████ | 500/1000 [03:07<02:58, 2.80it/s, loss=0.283, lr=1e-6]
Steps: 50%|█████ | 500/1000 [03:07<02:58, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 50%|█████ | 501/1000 [03:07<02:58, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 50%|█████ | 502/1000 [03:08<02:56, 2.82it/s, loss=0.282, lr=1e-6]
Steps: 50%|█████ | 503/1000 [03:08<02:55, 2.83it/s, loss=0.282, lr=1e-6]
Steps: 50%|█████ | 504/1000 [03:09<02:55, 2.83it/s, loss=0.282, lr=1e-6]
Steps: 50%|█████ | 505/1000 [03:09<02:54, 2.84it/s, loss=0.282, lr=1e-6]
Steps: 51%|█████ | 506/1000 [03:09<02:53, 2.86it/s, loss=0.282, lr=1e-6]
Steps: 51%|█████ | 507/1000 [03:10<02:52, 2.86it/s, loss=0.282, lr=1e-6]
Steps: 51%|█████ | 508/1000 [03:10<02:51, 2.87it/s, loss=0.282, lr=1e-6]
Steps: 51%|█████ | 509/1000 [03:10<02:52, 2.85it/s, loss=0.282, lr=1e-6]
Steps: 51%|█████ | 510/1000 [03:11<02:51, 2.85it/s, loss=0.282, lr=1e-6]
Steps: 51%|█████ | 510/1000 [03:11<02:51, 2.85it/s, loss=0.284, lr=1e-6]
Steps: 51%|█████ | 511/1000 [03:11<02:51, 2.85it/s, loss=0.284, lr=1e-6]
Steps: 51%|█████ | 512/1000 [03:11<02:51, 2.85it/s, loss=0.284, lr=1e-6]
Steps: 51%|█████▏ | 513/1000 [03:12<02:52, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 51%|█████▏ | 514/1000 [03:12<02:52, 2.81it/s, loss=0.284, lr=1e-6]
Steps: 52%|█████▏ | 515/1000 [03:12<02:51, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 52%|█████▏ | 516/1000 [03:13<02:51, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 52%|█████▏ | 517/1000 [03:13<02:50, 2.83it/s, loss=0.284, lr=1e-6]
Steps: 52%|█████▏ | 518/1000 [03:13<02:50, 2.83it/s, loss=0.284, lr=1e-6]
Steps: 52%|█████▏ | 519/1000 [03:14<02:50, 2.83it/s, loss=0.284, lr=1e-6]
Steps: 52%|█████▏ | 520/1000 [03:14<02:50, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 52%|█████▏ | 520/1000 [03:14<02:50, 2.82it/s, loss=0.281, lr=1e-6]
Steps: 52%|█████▏ | 521/1000 [03:15<02:50, 2.82it/s, loss=0.281, lr=1e-6]
Steps: 52%|█████▏ | 522/1000 [03:15<02:48, 2.83it/s, loss=0.281, lr=1e-6]
Steps: 52%|█████▏ | 523/1000 [03:15<02:48, 2.82it/s, loss=0.281, lr=1e-6]
Steps: 52%|█████▏ | 524/1000 [03:16<02:52, 2.75it/s, loss=0.281, lr=1e-6]
Steps: 52%|█████▎ | 525/1000 [03:16<02:51, 2.77it/s, loss=0.281, lr=1e-6]
Steps: 53%|█████▎ | 526/1000 [03:16<02:49, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 53%|█████▎ | 527/1000 [03:17<02:49, 2.79it/s, loss=0.281, lr=1e-6]
Steps: 53%|█████▎ | 528/1000 [03:17<02:47, 2.81it/s, loss=0.281, lr=1e-6]
Steps: 53%|█████▎ | 529/1000 [03:17<02:46, 2.83it/s, loss=0.281, lr=1e-6]
Steps: 53%|█████▎ | 530/1000 [03:18<02:45, 2.83it/s, loss=0.281, lr=1e-6]
Steps: 53%|█████▎ | 530/1000 [03:18<02:45, 2.83it/s, loss=0.284, lr=1e-6]
Steps: 53%|█████▎ | 531/1000 [03:18<02:46, 2.81it/s, loss=0.284, lr=1e-6]
Steps: 53%|█████▎ | 532/1000 [03:18<02:45, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 53%|█████▎ | 533/1000 [03:19<02:45, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 53%|█████▎ | 534/1000 [03:19<02:45, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 54%|█████▎ | 535/1000 [03:19<02:43, 2.84it/s, loss=0.284, lr=1e-6]
Steps: 54%|█████▎ | 536/1000 [03:20<02:43, 2.83it/s, loss=0.284, lr=1e-6]
Steps: 54%|█████▎ | 537/1000 [03:20<02:45, 2.81it/s, loss=0.284, lr=1e-6]
Steps: 54%|█████▍ | 538/1000 [03:21<02:45, 2.79it/s, loss=0.284, lr=1e-6]
Steps: 54%|█████▍ | 539/1000 [03:21<02:45, 2.78it/s, loss=0.284, lr=1e-6]
Steps: 54%|█████▍ | 540/1000 [03:21<02:44, 2.79it/s, loss=0.284, lr=1e-6]
Steps: 54%|█████▍ | 540/1000 [03:22<02:44, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 54%|█████▍ | 541/1000 [03:22<02:44, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 54%|█████▍ | 542/1000 [03:22<02:44, 2.78it/s, loss=0.283, lr=1e-6]
Steps: 54%|█████▍ | 543/1000 [03:22<02:44, 2.78it/s, loss=0.283, lr=1e-6]
Steps: 54%|█████▍ | 544/1000 [03:23<02:45, 2.76it/s, loss=0.283, lr=1e-6]
Steps: 55%|█████▍ | 545/1000 [03:23<02:43, 2.78it/s, loss=0.283, lr=1e-6]
Steps: 55%|█████▍ | 546/1000 [03:23<02:42, 2.80it/s, loss=0.283, lr=1e-6]
Steps: 55%|█████▍ | 547/1000 [03:24<02:41, 2.81it/s, loss=0.283, lr=1e-6]
Steps: 55%|█████▍ | 548/1000 [03:24<02:40, 2.81it/s, loss=0.283, lr=1e-6]
Steps: 55%|█████▍ | 549/1000 [03:24<02:40, 2.81it/s, loss=0.283, lr=1e-6]
Steps: 55%|█████▌ | 550/1000 [03:25<02:39, 2.82it/s, loss=0.283, lr=1e-6]
Steps: 55%|█████▌ | 550/1000 [03:25<02:39, 2.82it/s, loss=0.28, lr=1e-6]
Steps: 55%|█████▌ | 551/1000 [03:25<02:38, 2.84it/s, loss=0.28, lr=1e-6]
Steps: 55%|█████▌ | 552/1000 [03:26<02:40, 2.80it/s, loss=0.28, lr=1e-6]
Steps: 55%|█████▌ | 553/1000 [03:26<02:39, 2.81it/s, loss=0.28, lr=1e-6]
Steps: 55%|█████▌ | 554/1000 [03:26<02:38, 2.82it/s, loss=0.28, lr=1e-6]
Steps: 56%|█████▌ | 555/1000 [03:27<02:37, 2.82it/s, loss=0.28, lr=1e-6]
Steps: 56%|█████▌ | 556/1000 [03:27<02:37, 2.81it/s, loss=0.28, lr=1e-6]
Steps: 56%|█████▌ | 557/1000 [03:27<02:37, 2.81it/s, loss=0.28, lr=1e-6]
Steps: 56%|█████▌ | 558/1000 [03:28<02:37, 2.80it/s, loss=0.28, lr=1e-6]
Steps: 56%|█████▌ | 559/1000 [03:28<02:40, 2.75it/s, loss=0.28, lr=1e-6]
Steps: 56%|█████▌ | 560/1000 [03:28<02:41, 2.73it/s, loss=0.28, lr=1e-6]
Steps: 56%|█████▌ | 560/1000 [03:29<02:41, 2.73it/s, loss=0.279, lr=1e-6]
Steps: 56%|█████▌ | 561/1000 [03:29<02:41, 2.71it/s, loss=0.279, lr=1e-6]
Steps: 56%|█████▌ | 562/1000 [03:29<02:40, 2.72it/s, loss=0.279, lr=1e-6]
Steps: 56%|█████▋ | 563/1000 [03:30<02:40, 2.73it/s, loss=0.279, lr=1e-6]
Steps: 56%|█████▋ | 564/1000 [03:30<02:39, 2.74it/s, loss=0.279, lr=1e-6]
Steps: 56%|█████▋ | 565/1000 [03:30<02:38, 2.75it/s, loss=0.279, lr=1e-6]
Steps: 57%|█████▋ | 566/1000 [03:31<02:35, 2.79it/s, loss=0.279, lr=1e-6]
Steps: 57%|█████▋ | 567/1000 [03:31<02:35, 2.78it/s, loss=0.279, lr=1e-6]
Steps: 57%|█████▋ | 568/1000 [03:31<02:33, 2.81it/s, loss=0.279, lr=1e-6]
Steps: 57%|█████▋ | 569/1000 [03:32<02:32, 2.82it/s, loss=0.279, lr=1e-6]
Steps: 57%|█████▋ | 570/1000 [03:32<02:32, 2.82it/s, loss=0.279, lr=1e-6]
Steps: 57%|█████▋ | 570/1000 [03:32<02:32, 2.82it/s, loss=0.28, lr=1e-6]
Steps: 57%|█████▋ | 571/1000 [03:32<02:30, 2.85it/s, loss=0.28, lr=1e-6]
Steps: 57%|█████▋ | 572/1000 [03:33<02:29, 2.86it/s, loss=0.28, lr=1e-6]
Steps: 57%|█████▋ | 573/1000 [03:33<02:30, 2.84it/s, loss=0.28, lr=1e-6]
Steps: 57%|█████▋ | 574/1000 [03:33<02:29, 2.85it/s, loss=0.28, lr=1e-6]
Steps: 57%|█████▊ | 575/1000 [03:34<02:31, 2.81it/s, loss=0.28, lr=1e-6]
Steps: 58%|█████▊ | 576/1000 [03:34<02:31, 2.79it/s, loss=0.28, lr=1e-6]
Steps: 58%|█████▊ | 577/1000 [03:35<02:31, 2.78it/s, loss=0.28, lr=1e-6]
Steps: 58%|█████▊ | 578/1000 [03:35<02:31, 2.79it/s, loss=0.28, lr=1e-6]
Steps: 58%|█████▊ | 579/1000 [03:35<02:29, 2.81it/s, loss=0.28, lr=1e-6]
Steps: 58%|█████▊ | 580/1000 [03:36<02:32, 2.76it/s, loss=0.28, lr=1e-6]
Steps: 58%|█████▊ | 580/1000 [03:36<02:32, 2.76it/s, loss=0.28, lr=1e-6]
Steps: 58%|█████▊ | 581/1000 [03:36<02:31, 2.77it/s, loss=0.28, lr=1e-6]
Steps: 58%|█████▊ | 582/1000 [03:36<02:29, 2.79it/s, loss=0.28, lr=1e-6]
Steps: 58%|█████▊ | 583/1000 [03:37<02:29, 2.79it/s, loss=0.28, lr=1e-6]
Steps: 58%|█████▊ | 584/1000 [03:37<02:29, 2.79it/s, loss=0.28, lr=1e-6]
Steps: 58%|█████▊ | 585/1000 [03:37<02:27, 2.81it/s, loss=0.28, lr=1e-6]
Steps: 59%|█████▊ | 586/1000 [03:38<02:27, 2.80it/s, loss=0.28, lr=1e-6]
Steps: 59%|█████▊ | 587/1000 [03:38<02:27, 2.80it/s, loss=0.28, lr=1e-6]
Steps: 59%|█████▉ | 588/1000 [03:38<02:26, 2.82it/s, loss=0.28, lr=1e-6]
Steps: 59%|█████▉ | 589/1000 [03:39<02:25, 2.83it/s, loss=0.28, lr=1e-6]
Steps: 59%|█████▉ | 590/1000 [03:39<02:24, 2.84it/s, loss=0.28, lr=1e-6]
Steps: 59%|█████▉ | 590/1000 [03:39<02:24, 2.84it/s, loss=0.28, lr=1e-6]
Steps: 59%|█████▉ | 591/1000 [03:39<02:23, 2.85it/s, loss=0.28, lr=1e-6]
Steps: 59%|█████▉ | 592/1000 [03:40<02:23, 2.85it/s, loss=0.28, lr=1e-6]
Steps: 59%|█████▉ | 593/1000 [03:40<02:23, 2.84it/s, loss=0.28, lr=1e-6]
Steps: 59%|█████▉ | 594/1000 [03:41<02:23, 2.83it/s, loss=0.28, lr=1e-6]
Steps: 60%|█████▉ | 595/1000 [03:41<02:22, 2.84it/s, loss=0.28, lr=1e-6]
Steps: 60%|█████▉ | 596/1000 [03:41<02:23, 2.82it/s, loss=0.28, lr=1e-6]
Steps: 60%|█████▉ | 597/1000 [03:42<02:22, 2.83it/s, loss=0.28, lr=1e-6]
Steps: 60%|█████▉ | 598/1000 [03:42<02:22, 2.83it/s, loss=0.28, lr=1e-6]
Steps: 60%|█████▉ | 599/1000 [03:42<02:22, 2.81it/s, loss=0.28, lr=1e-6]
Steps: 60%|██████ | 600/1000 [03:43<02:21, 2.82it/s, loss=0.28, lr=1e-6]
Steps: 60%|██████ | 600/1000 [03:43<02:21, 2.82it/s, loss=0.283, lr=1e-6]
Steps: 60%|██████ | 601/1000 [03:43<02:21, 2.82it/s, loss=0.283, lr=1e-6]
Steps: 60%|██████ | 602/1000 [03:43<02:20, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 60%|██████ | 603/1000 [03:44<02:20, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 60%|██████ | 604/1000 [03:44<02:21, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 60%|██████ | 605/1000 [03:44<02:22, 2.77it/s, loss=0.283, lr=1e-6]
Steps: 61%|██████ | 606/1000 [03:45<02:22, 2.76it/s, loss=0.283, lr=1e-6]
Steps: 61%|██████ | 607/1000 [03:45<02:21, 2.78it/s, loss=0.283, lr=1e-6]
Steps: 61%|██████ | 608/1000 [03:46<02:23, 2.73it/s, loss=0.283, lr=1e-6]
Steps: 61%|██████ | 609/1000 [03:46<02:21, 2.76it/s, loss=0.283, lr=1e-6]
Steps: 61%|██████ | 610/1000 [03:46<02:20, 2.77it/s, loss=0.283, lr=1e-6]
Steps: 61%|██████ | 610/1000 [03:47<02:20, 2.77it/s, loss=0.285, lr=1e-6]
Steps: 61%|██████ | 611/1000 [03:47<02:18, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 61%|██████ | 612/1000 [03:47<02:17, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 61%|██████▏ | 613/1000 [03:47<02:16, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 61%|██████▏ | 614/1000 [03:48<02:15, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 62%|██████▏ | 615/1000 [03:48<02:16, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 62%|██████▏ | 616/1000 [03:48<02:16, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 62%|██████▏ | 617/1000 [03:49<02:15, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 62%|██████▏ | 618/1000 [03:49<02:14, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 62%|██████▏ | 619/1000 [03:49<02:14, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 62%|██████▏ | 620/1000 [03:50<02:13, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 62%|██████▏ | 620/1000 [03:50<02:13, 2.84it/s, loss=0.284, lr=1e-6]
Steps: 62%|██████▏ | 621/1000 [03:50<02:14, 2.81it/s, loss=0.284, lr=1e-6]
Steps: 62%|██████▏ | 622/1000 [03:51<02:15, 2.78it/s, loss=0.284, lr=1e-6]
Steps: 62%|██████▏ | 623/1000 [03:51<02:15, 2.79it/s, loss=0.284, lr=1e-6]
Steps: 62%|██████▏ | 624/1000 [03:51<02:13, 2.81it/s, loss=0.284, lr=1e-6]
Steps: 62%|██████▎ | 625/1000 [03:52<02:13, 2.80it/s, loss=0.284, lr=1e-6]
Steps: 63%|██████▎ | 626/1000 [03:52<02:12, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 63%|██████▎ | 627/1000 [03:52<02:11, 2.83it/s, loss=0.284, lr=1e-6]
Steps: 63%|██████▎ | 628/1000 [03:53<02:10, 2.85it/s, loss=0.284, lr=1e-6]
Steps: 63%|██████▎ | 629/1000 [03:53<02:09, 2.86it/s, loss=0.284, lr=1e-6]
Steps: 63%|██████▎ | 630/1000 [03:53<02:08, 2.87it/s, loss=0.284, lr=1e-6]
Steps: 63%|██████▎ | 630/1000 [03:54<02:08, 2.87it/s, loss=0.283, lr=1e-6]
Steps: 63%|██████▎ | 631/1000 [03:54<02:08, 2.88it/s, loss=0.283, lr=1e-6]
Steps: 63%|██████▎ | 632/1000 [03:54<02:08, 2.86it/s, loss=0.283, lr=1e-6]
Steps: 63%|██████▎ | 633/1000 [03:54<02:09, 2.84it/s, loss=0.283, lr=1e-6]
Steps: 63%|██████▎ | 634/1000 [03:55<02:07, 2.86it/s, loss=0.283, lr=1e-6]
Steps: 64%|██████▎ | 635/1000 [03:55<02:06, 2.88it/s, loss=0.283, lr=1e-6]
Steps: 64%|██████▎ | 636/1000 [03:55<02:08, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 64%|██████▎ | 637/1000 [03:56<02:08, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 64%|██████▍ | 638/1000 [03:56<02:07, 2.84it/s, loss=0.283, lr=1e-6]
Steps: 64%|██████▍ | 639/1000 [03:57<02:07, 2.82it/s, loss=0.283, lr=1e-6]
Steps: 64%|██████▍ | 640/1000 [03:57<02:07, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 64%|██████▍ | 640/1000 [03:57<02:07, 2.83it/s, loss=0.284, lr=1e-6]
Steps: 64%|██████▍ | 641/1000 [03:57<02:07, 2.83it/s, loss=0.284, lr=1e-6]
Steps: 64%|██████▍ | 642/1000 [03:58<02:07, 2.81it/s, loss=0.284, lr=1e-6]
Steps: 64%|██████▍ | 643/1000 [03:58<02:07, 2.79it/s, loss=0.284, lr=1e-6]
Steps: 64%|██████▍ | 644/1000 [03:58<02:06, 2.81it/s, loss=0.284, lr=1e-6]
Steps: 64%|██████▍ | 645/1000 [03:59<02:08, 2.76it/s, loss=0.284, lr=1e-6]
Steps: 65%|██████▍ | 646/1000 [03:59<02:07, 2.77it/s, loss=0.284, lr=1e-6]
Steps: 65%|██████▍ | 647/1000 [03:59<02:07, 2.78it/s, loss=0.284, lr=1e-6]
Steps: 65%|██████▍ | 648/1000 [04:00<02:07, 2.76it/s, loss=0.284, lr=1e-6]
Steps: 65%|██████▍ | 649/1000 [04:00<02:07, 2.75it/s, loss=0.284, lr=1e-6]
Steps: 65%|██████▌ | 650/1000 [04:00<02:07, 2.75it/s, loss=0.284, lr=1e-6]
Steps: 65%|██████▌ | 650/1000 [04:01<02:07, 2.75it/s, loss=0.283, lr=1e-6]
Steps: 65%|██████▌ | 651/1000 [04:01<02:05, 2.77it/s, loss=0.283, lr=1e-6]
Steps: 65%|██████▌ | 652/1000 [04:01<02:04, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 65%|██████▌ | 653/1000 [04:02<02:03, 2.82it/s, loss=0.283, lr=1e-6]
Steps: 65%|██████▌ | 654/1000 [04:02<02:02, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 66%|██████▌ | 655/1000 [04:02<02:01, 2.84it/s, loss=0.283, lr=1e-6]
Steps: 66%|██████▌ | 656/1000 [04:03<02:01, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 66%|██████▌ | 657/1000 [04:03<02:01, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 66%|██████▌ | 658/1000 [04:03<02:00, 2.84it/s, loss=0.283, lr=1e-6]
Steps: 66%|██████▌ | 659/1000 [04:04<02:00, 2.84it/s, loss=0.283, lr=1e-6]
Steps: 66%|██████▌ | 660/1000 [04:04<01:59, 2.84it/s, loss=0.283, lr=1e-6]
Steps: 66%|██████▌ | 660/1000 [04:04<01:59, 2.84it/s, loss=0.282, lr=1e-6]
Steps: 66%|██████▌ | 661/1000 [04:04<02:00, 2.82it/s, loss=0.282, lr=1e-6]
Steps: 66%|██████▌ | 662/1000 [04:05<02:00, 2.79it/s, loss=0.282, lr=1e-6]
Steps: 66%|██████▋ | 663/1000 [04:05<02:00, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 66%|██████▋ | 664/1000 [04:05<02:01, 2.75it/s, loss=0.282, lr=1e-6]
Steps: 66%|██████▋ | 665/1000 [04:06<02:01, 2.75it/s, loss=0.282, lr=1e-6]
Steps: 67%|██████▋ | 666/1000 [04:06<02:00, 2.77it/s, loss=0.282, lr=1e-6]
Steps: 67%|██████▋ | 667/1000 [04:07<02:06, 2.64it/s, loss=0.282, lr=1e-6]
Steps: 67%|██████▋ | 668/1000 [04:07<02:03, 2.68it/s, loss=0.282, lr=1e-6]
Steps: 67%|██████▋ | 669/1000 [04:07<02:01, 2.72it/s, loss=0.282, lr=1e-6]
Steps: 67%|██████▋ | 670/1000 [04:08<02:00, 2.75it/s, loss=0.282, lr=1e-6]
Steps: 67%|██████▋ | 670/1000 [04:08<02:00, 2.75it/s, loss=0.283, lr=1e-6]
Steps: 67%|██████▋ | 671/1000 [04:08<01:58, 2.76it/s, loss=0.283, lr=1e-6]
Steps: 67%|██████▋ | 672/1000 [04:08<01:57, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 67%|██████▋ | 673/1000 [04:09<01:57, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 67%|██████▋ | 674/1000 [04:09<01:57, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 68%|██████▊ | 675/1000 [04:09<01:56, 2.80it/s, loss=0.283, lr=1e-6]
Steps: 68%|██████▊ | 676/1000 [04:10<01:56, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 68%|██████▊ | 677/1000 [04:10<01:55, 2.80it/s, loss=0.283, lr=1e-6]
Steps: 68%|██████▊ | 678/1000 [04:11<01:54, 2.80it/s, loss=0.283, lr=1e-6]
Steps: 68%|██████▊ | 679/1000 [04:11<01:54, 2.81it/s, loss=0.283, lr=1e-6]
Steps: 68%|██████▊ | 680/1000 [04:11<01:53, 2.81it/s, loss=0.283, lr=1e-6]
Steps: 68%|██████▊ | 680/1000 [04:12<01:53, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 68%|██████▊ | 681/1000 [04:12<01:53, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 68%|██████▊ | 682/1000 [04:12<01:53, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 68%|██████▊ | 683/1000 [04:12<01:52, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 68%|██████▊ | 684/1000 [04:13<01:52, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 68%|██████▊ | 685/1000 [04:13<01:52, 2.79it/s, loss=0.282, lr=1e-6]
Steps: 69%|██████▊ | 686/1000 [04:13<01:51, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 69%|██████▊ | 687/1000 [04:14<01:51, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 69%|██████▉ | 688/1000 [04:14<01:51, 2.79it/s, loss=0.282, lr=1e-6]
Steps: 69%|██████▉ | 689/1000 [04:14<01:51, 2.79it/s, loss=0.282, lr=1e-6]
Steps: 69%|██████▉ | 690/1000 [04:15<01:51, 2.78it/s, loss=0.282, lr=1e-6]
Steps: 69%|██████▉ | 690/1000 [04:15<01:51, 2.78it/s, loss=0.283, lr=1e-6]
Steps: 69%|██████▉ | 691/1000 [04:15<01:50, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 69%|██████▉ | 692/1000 [04:16<01:51, 2.75it/s, loss=0.283, lr=1e-6]
Steps: 69%|██████▉ | 693/1000 [04:16<01:50, 2.77it/s, loss=0.283, lr=1e-6]
Steps: 69%|██████▉ | 694/1000 [04:16<01:50, 2.77it/s, loss=0.283, lr=1e-6]
Steps: 70%|██████▉ | 695/1000 [04:17<01:49, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 70%|██████▉ | 696/1000 [04:17<01:49, 2.78it/s, loss=0.283, lr=1e-6]
Steps: 70%|██████▉ | 697/1000 [04:17<01:48, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 70%|██████▉ | 698/1000 [04:18<01:47, 2.80it/s, loss=0.283, lr=1e-6]
Steps: 70%|██████▉ | 699/1000 [04:18<01:47, 2.80it/s, loss=0.283, lr=1e-6]
Steps: 70%|███████ | 700/1000 [04:18<01:46, 2.82it/s, loss=0.283, lr=1e-6]
Steps: 70%|███████ | 700/1000 [04:19<01:46, 2.82it/s, loss=0.283, lr=1e-6]
Steps: 70%|███████ | 701/1000 [04:19<01:46, 2.81it/s, loss=0.283, lr=1e-6]
Steps: 70%|███████ | 702/1000 [04:19<01:46, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 70%|███████ | 703/1000 [04:19<01:46, 2.80it/s, loss=0.283, lr=1e-6]
Steps: 70%|███████ | 704/1000 [04:20<01:45, 2.80it/s, loss=0.283, lr=1e-6]
Steps: 70%|███████ | 705/1000 [04:20<01:45, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 71%|███████ | 706/1000 [04:21<01:45, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 71%|███████ | 707/1000 [04:21<01:45, 2.79it/s, loss=0.283, lr=1e-6]
Steps: 71%|███████ | 708/1000 [04:21<01:44, 2.80it/s, loss=0.283, lr=1e-6]
Steps: 71%|███████ | 709/1000 [04:22<01:43, 2.80it/s, loss=0.283, lr=1e-6]
Steps: 71%|███████ | 710/1000 [04:22<01:43, 2.80it/s, loss=0.283, lr=1e-6]
Steps: 71%|███████ | 710/1000 [04:22<01:43, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 71%|███████ | 711/1000 [04:22<01:42, 2.82it/s, loss=0.282, lr=1e-6]
Steps: 71%|███████ | 712/1000 [04:23<01:41, 2.84it/s, loss=0.282, lr=1e-6]
Steps: 71%|███████▏ | 713/1000 [04:23<01:41, 2.83it/s, loss=0.282, lr=1e-6]
Steps: 71%|███████▏ | 714/1000 [04:23<01:40, 2.84it/s, loss=0.282, lr=1e-6]
Steps: 72%|███████▏ | 715/1000 [04:24<01:39, 2.85it/s, loss=0.282, lr=1e-6]
Steps: 72%|███████▏ | 716/1000 [04:24<01:39, 2.85it/s, loss=0.282, lr=1e-6]
Steps: 72%|███████▏ | 717/1000 [04:24<01:40, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 72%|███████▏ | 718/1000 [04:25<01:39, 2.84it/s, loss=0.282, lr=1e-6]
Steps: 72%|███████▏ | 719/1000 [04:25<01:39, 2.82it/s, loss=0.282, lr=1e-6]
Steps: 72%|███████▏ | 720/1000 [04:26<01:41, 2.77it/s, loss=0.282, lr=1e-6]
Steps: 72%|███████▏ | 720/1000 [04:26<01:41, 2.77it/s, loss=0.282, lr=1e-6]
Steps: 72%|███████▏ | 721/1000 [04:26<01:39, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 72%|███████▏ | 722/1000 [04:26<01:38, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 72%|███████▏ | 723/1000 [04:27<01:38, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 72%|███████▏ | 724/1000 [04:27<01:38, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 72%|███████▎ | 725/1000 [04:27<01:38, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 73%|███████▎ | 726/1000 [04:28<01:37, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 73%|███████▎ | 727/1000 [04:28<01:37, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 73%|███████▎ | 728/1000 [04:28<01:37, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 73%|███████▎ | 729/1000 [04:29<01:36, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 73%|███████▎ | 730/1000 [04:29<01:36, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 73%|███████▎ | 730/1000 [04:29<01:36, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 73%|███████▎ | 731/1000 [04:29<01:35, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 73%|███████▎ | 732/1000 [04:30<01:35, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 73%|███████▎ | 733/1000 [04:30<01:34, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 73%|███████▎ | 734/1000 [04:30<01:34, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 74%|███████▎ | 735/1000 [04:31<01:33, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 74%|███████▎ | 736/1000 [04:31<01:32, 2.85it/s, loss=0.285, lr=1e-6]
Steps: 74%|███████▎ | 737/1000 [04:32<01:32, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 74%|███████▍ | 738/1000 [04:32<01:31, 2.87it/s, loss=0.285, lr=1e-6]
Steps: 74%|███████▍ | 739/1000 [04:32<01:31, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 74%|███████▍ | 740/1000 [04:33<01:30, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 74%|███████▍ | 740/1000 [04:33<01:30, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 74%|███████▍ | 741/1000 [04:33<01:30, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 74%|███████▍ | 742/1000 [04:33<01:30, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 74%|███████▍ | 743/1000 [04:34<01:31, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 74%|███████▍ | 744/1000 [04:34<01:30, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 74%|███████▍ | 745/1000 [04:34<01:30, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 75%|███████▍ | 746/1000 [04:35<01:31, 2.79it/s, loss=0.285, lr=1e-6]
Steps: 75%|███████▍ | 747/1000 [04:35<01:30, 2.79it/s, loss=0.285, lr=1e-6]
Steps: 75%|███████▍ | 748/1000 [04:35<01:30, 2.77it/s, loss=0.285, lr=1e-6]
Steps: 75%|███████▍ | 749/1000 [04:36<01:29, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 75%|███████▌ | 750/1000 [04:36<01:29, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 75%|███████▌ | 750/1000 [04:37<01:29, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 75%|███████▌ | 751/1000 [04:37<01:29, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 75%|███████▌ | 752/1000 [04:37<01:28, 2.79it/s, loss=0.285, lr=1e-6]
Steps: 75%|███████▌ | 753/1000 [04:37<01:28, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 75%|███████▌ | 754/1000 [04:38<01:27, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 76%|███████▌ | 755/1000 [04:38<01:26, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 76%|███████▌ | 756/1000 [04:38<01:26, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 76%|███████▌ | 757/1000 [04:39<01:26, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 76%|███████▌ | 758/1000 [04:39<01:25, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 76%|███████▌ | 759/1000 [04:39<01:24, 2.85it/s, loss=0.285, lr=1e-6]
Steps: 76%|███████▌ | 760/1000 [04:40<01:24, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 76%|███████▌ | 760/1000 [04:40<01:24, 2.86it/s, loss=0.284, lr=1e-6]
Steps: 76%|███████▌ | 761/1000 [04:40<01:23, 2.85it/s, loss=0.284, lr=1e-6]
Steps: 76%|███████▌ | 762/1000 [04:40<01:23, 2.86it/s, loss=0.284, lr=1e-6]
Steps: 76%|███████▋ | 763/1000 [04:41<01:24, 2.81it/s, loss=0.284, lr=1e-6]
Steps: 76%|███████▋ | 764/1000 [04:41<01:23, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 76%|███████▋ | 765/1000 [04:41<01:23, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 77%|███████▋ | 766/1000 [04:42<01:22, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 77%|███████▋ | 767/1000 [04:42<01:22, 2.83it/s, loss=0.284, lr=1e-6]
Steps: 77%|███████▋ | 768/1000 [04:43<01:21, 2.84it/s, loss=0.284, lr=1e-6]
Steps: 77%|███████▋ | 769/1000 [04:43<01:21, 2.84it/s, loss=0.284, lr=1e-6]
Steps: 77%|███████▋ | 770/1000 [04:43<01:20, 2.84it/s, loss=0.284, lr=1e-6]
Steps: 77%|███████▋ | 770/1000 [04:44<01:20, 2.84it/s, loss=0.284, lr=1e-6]
Steps: 77%|███████▋ | 771/1000 [04:44<01:21, 2.80it/s, loss=0.284, lr=1e-6]
Steps: 77%|███████▋ | 772/1000 [04:44<01:21, 2.80it/s, loss=0.284, lr=1e-6]
Steps: 77%|███████▋ | 773/1000 [04:44<01:21, 2.80it/s, loss=0.284, lr=1e-6]
Steps: 77%|███████▋ | 774/1000 [04:45<01:21, 2.78it/s, loss=0.284, lr=1e-6]
Steps: 78%|███████▊ | 775/1000 [04:45<01:20, 2.79it/s, loss=0.284, lr=1e-6]
Steps: 78%|███████▊ | 776/1000 [04:45<01:20, 2.80it/s, loss=0.284, lr=1e-6]
Steps: 78%|███████▊ | 777/1000 [04:46<01:20, 2.78it/s, loss=0.284, lr=1e-6]
Steps: 78%|███████▊ | 778/1000 [04:46<01:19, 2.79it/s, loss=0.284, lr=1e-6]
Steps: 78%|███████▊ | 779/1000 [04:46<01:18, 2.80it/s, loss=0.284, lr=1e-6]
Steps: 78%|███████▊ | 780/1000 [04:47<01:18, 2.79it/s, loss=0.284, lr=1e-6]
Steps: 78%|███████▊ | 780/1000 [04:47<01:18, 2.79it/s, loss=0.285, lr=1e-6]
Steps: 78%|███████▊ | 781/1000 [04:47<01:17, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 78%|███████▊ | 782/1000 [04:48<01:16, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 78%|███████▊ | 783/1000 [04:48<01:16, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 78%|███████▊ | 784/1000 [04:48<01:15, 2.85it/s, loss=0.285, lr=1e-6]
Steps: 78%|███████▊ | 785/1000 [04:49<01:15, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 79%|███████▊ | 786/1000 [04:49<01:15, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 79%|███████▊ | 787/1000 [04:49<01:14, 2.87it/s, loss=0.285, lr=1e-6]
Steps: 79%|███████▉ | 788/1000 [04:50<01:13, 2.88it/s, loss=0.285, lr=1e-6]
Steps: 79%|███████▉ | 789/1000 [04:50<01:13, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 79%|███████▉ | 790/1000 [04:50<01:13, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 79%|███████▉ | 790/1000 [04:51<01:13, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 79%|███████▉ | 791/1000 [04:51<01:13, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 79%|███████▉ | 792/1000 [04:51<01:13, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 79%|███████▉ | 793/1000 [04:51<01:13, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 79%|███████▉ | 794/1000 [04:52<01:13, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 80%|███████▉ | 795/1000 [04:52<01:12, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 80%|███████▉ | 796/1000 [04:52<01:12, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 80%|███████▉ | 797/1000 [04:53<01:12, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 80%|███████▉ | 798/1000 [04:53<01:11, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 80%|███████▉ | 799/1000 [04:54<01:11, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 80%|████████ | 800/1000 [04:54<01:10, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 80%|████████ | 800/1000 [04:54<01:10, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 80%|████████ | 801/1000 [04:54<01:10, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 80%|████████ | 802/1000 [04:55<01:10, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 80%|████████ | 803/1000 [04:55<01:09, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 80%|████████ | 804/1000 [04:55<01:09, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 80%|████████ | 805/1000 [04:56<01:09, 2.79it/s, loss=0.285, lr=1e-6]
Steps: 81%|████████ | 806/1000 [04:56<01:09, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 81%|████████ | 807/1000 [04:56<01:08, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 81%|████████ | 808/1000 [04:57<01:08, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 81%|████████ | 809/1000 [04:57<01:08, 2.80it/s, loss=0.285, lr=1e-6]
Steps: 81%|████████ | 810/1000 [04:57<01:07, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 81%|████████ | 810/1000 [04:58<01:07, 2.82it/s, loss=0.286, lr=1e-6]
Steps: 81%|████████ | 811/1000 [04:58<01:06, 2.82it/s, loss=0.286, lr=1e-6]
Steps: 81%|████████ | 812/1000 [04:58<01:07, 2.80it/s, loss=0.286, lr=1e-6]
Steps: 81%|████████▏ | 813/1000 [04:58<01:06, 2.81it/s, loss=0.286, lr=1e-6]
Steps: 81%|████████▏ | 814/1000 [04:59<01:06, 2.81it/s, loss=0.286, lr=1e-6]
Steps: 82%|████████▏ | 815/1000 [04:59<01:05, 2.81it/s, loss=0.286, lr=1e-6]
Steps: 82%|████████▏ | 816/1000 [05:00<01:05, 2.81it/s, loss=0.286, lr=1e-6]
Steps: 82%|████████▏ | 817/1000 [05:00<01:05, 2.81it/s, loss=0.286, lr=1e-6]
Steps: 82%|████████▏ | 818/1000 [05:00<01:04, 2.82it/s, loss=0.286, lr=1e-6]
Steps: 82%|████████▏ | 819/1000 [05:01<01:03, 2.84it/s, loss=0.286, lr=1e-6]
Steps: 82%|████████▏ | 820/1000 [05:01<01:03, 2.85it/s, loss=0.286, lr=1e-6]
Steps: 82%|████████▏ | 820/1000 [05:01<01:03, 2.85it/s, loss=0.285, lr=1e-6]
Steps: 82%|████████▏ | 821/1000 [05:01<01:02, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 82%|████████▏ | 822/1000 [05:02<01:02, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 82%|████████▏ | 823/1000 [05:02<01:02, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 82%|████████▏ | 824/1000 [05:02<01:02, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 82%|████████▎ | 825/1000 [05:03<01:02, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 83%|████████▎ | 826/1000 [05:03<01:01, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 83%|████████▎ | 827/1000 [05:03<01:01, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 83%|████████▎ | 828/1000 [05:04<01:00, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 83%|████████▎ | 829/1000 [05:04<01:00, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 83%|████████▎ | 830/1000 [05:05<01:00, 2.81it/s, loss=0.285, lr=1e-6]
Steps: 83%|████████▎ | 830/1000 [05:05<01:00, 2.81it/s, loss=0.286, lr=1e-6]
Steps: 83%|████████▎ | 831/1000 [05:05<00:59, 2.82it/s, loss=0.286, lr=1e-6]
Steps: 83%|████████▎ | 832/1000 [05:05<00:59, 2.83it/s, loss=0.286, lr=1e-6]
Steps: 83%|████████▎ | 833/1000 [05:06<00:59, 2.83it/s, loss=0.286, lr=1e-6]
Steps: 83%|████████▎ | 834/1000 [05:06<00:58, 2.83it/s, loss=0.286, lr=1e-6]
Steps: 84%|████████▎ | 835/1000 [05:06<00:58, 2.83it/s, loss=0.286, lr=1e-6]
Steps: 84%|████████▎ | 836/1000 [05:07<00:58, 2.82it/s, loss=0.286, lr=1e-6]
Steps: 84%|████████▎ | 837/1000 [05:07<00:57, 2.81it/s, loss=0.286, lr=1e-6]
Steps: 84%|████████▍ | 838/1000 [05:07<00:57, 2.83it/s, loss=0.286, lr=1e-6]
Steps: 84%|████████▍ | 839/1000 [05:08<00:56, 2.84it/s, loss=0.286, lr=1e-6]
Steps: 84%|████████▍ | 840/1000 [05:08<00:56, 2.83it/s, loss=0.286, lr=1e-6]
Steps: 84%|████████▍ | 840/1000 [05:08<00:56, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 84%|████████▍ | 841/1000 [05:08<00:56, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 84%|████████▍ | 842/1000 [05:09<00:55, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 84%|████████▍ | 843/1000 [05:09<00:55, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 84%|████████▍ | 844/1000 [05:09<00:54, 2.85it/s, loss=0.285, lr=1e-6]
Steps: 84%|████████▍ | 845/1000 [05:10<00:54, 2.86it/s, loss=0.285, lr=1e-6]
Steps: 85%|████████▍ | 846/1000 [05:10<00:54, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 85%|████████▍ | 847/1000 [05:10<00:53, 2.84it/s, loss=0.285, lr=1e-6]
Steps: 85%|████████▍ | 848/1000 [05:11<00:53, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 85%|████████▍ | 849/1000 [05:11<00:53, 2.83it/s, loss=0.285, lr=1e-6]
Steps: 85%|████████▌ | 850/1000 [05:12<00:53, 2.82it/s, loss=0.285, lr=1e-6]
Steps: 85%|████████▌ | 850/1000 [05:12<00:53, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 85%|████████▌ | 851/1000 [05:12<00:53, 2.81it/s, loss=0.284, lr=1e-6]
Steps: 85%|████████▌ | 852/1000 [05:12<00:52, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 85%|████████▌ | 853/1000 [05:13<00:52, 2.81it/s, loss=0.284, lr=1e-6]
Steps: 85%|████████▌ | 854/1000 [05:13<00:51, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 86%|████████▌ | 855/1000 [05:13<00:51, 2.83it/s, loss=0.284, lr=1e-6]
Steps: 86%|████████▌ | 856/1000 [05:14<00:51, 2.82it/s, loss=0.284, lr=1e-6]
Steps: 86%|████████▌ | 857/1000 [05:14<00:50, 2.81it/s, loss=0.284, lr=1e-6]
Steps: 86%|████████▌ | 858/1000 [05:14<00:51, 2.76it/s, loss=0.284, lr=1e-6]
Steps: 86%|████████▌ | 859/1000 [05:15<00:50, 2.79it/s, loss=0.284, lr=1e-6]
Steps: 86%|████████▌ | 860/1000 [05:15<00:49, 2.81it/s, loss=0.284, lr=1e-6]
Steps: 86%|████████▌ | 860/1000 [05:15<00:49, 2.81it/s, loss=0.283, lr=1e-6]
Steps: 86%|████████▌ | 861/1000 [05:15<00:49, 2.80it/s, loss=0.283, lr=1e-6]
Steps: 86%|████████▌ | 862/1000 [05:16<00:48, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 86%|████████▋ | 863/1000 [05:16<00:48, 2.84it/s, loss=0.283, lr=1e-6]
Steps: 86%|████████▋ | 864/1000 [05:17<00:48, 2.82it/s, loss=0.283, lr=1e-6]
Steps: 86%|████████▋ | 865/1000 [05:17<00:47, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 87%|████████▋ | 866/1000 [05:17<00:46, 2.85it/s, loss=0.283, lr=1e-6]
Steps: 87%|████████▋ | 867/1000 [05:18<00:46, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 87%|████████▋ | 868/1000 [05:18<00:46, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 87%|████████▋ | 869/1000 [05:18<00:46, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 87%|████████▋ | 870/1000 [05:19<00:46, 2.83it/s, loss=0.283, lr=1e-6]
Steps: 87%|████████▋ | 870/1000 [05:19<00:46, 2.83it/s, loss=0.282, lr=1e-6]
Steps: 87%|████████▋ | 871/1000 [05:19<00:45, 2.84it/s, loss=0.282, lr=1e-6]
Steps: 87%|████████▋ | 872/1000 [05:19<00:45, 2.84it/s, loss=0.282, lr=1e-6]
Steps: 87%|████████▋ | 873/1000 [05:20<00:44, 2.83it/s, loss=0.282, lr=1e-6]
Steps: 87%|████████▋ | 874/1000 [05:20<00:44, 2.83it/s, loss=0.282, lr=1e-6]
Steps: 88%|████████▊ | 875/1000 [05:20<00:44, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 88%|████████▊ | 876/1000 [05:21<00:44, 2.82it/s, loss=0.282, lr=1e-6]
Steps: 88%|████████▊ | 877/1000 [05:21<00:43, 2.82it/s, loss=0.282, lr=1e-6]
Steps: 88%|████████▊ | 878/1000 [05:21<00:43, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 88%|████████▊ | 879/1000 [05:22<00:43, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 88%|████████▊ | 880/1000 [05:22<00:42, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 88%|████████▊ | 880/1000 [05:23<00:42, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 88%|████████▊ | 881/1000 [05:23<00:42, 2.79it/s, loss=0.282, lr=1e-6]
Steps: 88%|████████▊ | 882/1000 [05:23<00:42, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 88%|████████▊ | 883/1000 [05:23<00:41, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 88%|████████▊ | 884/1000 [05:24<00:41, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 88%|████████▊ | 885/1000 [05:24<00:41, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 89%|████████▊ | 886/1000 [05:24<00:41, 2.76it/s, loss=0.282, lr=1e-6]
Steps: 89%|████████▊ | 887/1000 [05:25<00:40, 2.77it/s, loss=0.282, lr=1e-6]
Steps: 89%|████████▉ | 888/1000 [05:25<00:40, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 89%|████████▉ | 889/1000 [05:25<00:40, 2.77it/s, loss=0.282, lr=1e-6]
Steps: 89%|████████▉ | 890/1000 [05:26<00:39, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 89%|████████▉ | 890/1000 [05:26<00:39, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 89%|████████▉ | 891/1000 [05:26<00:38, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 89%|████████▉ | 892/1000 [05:27<00:38, 2.79it/s, loss=0.281, lr=1e-6]
Steps: 89%|████████▉ | 893/1000 [05:27<00:38, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 89%|████████▉ | 894/1000 [05:27<00:37, 2.82it/s, loss=0.281, lr=1e-6]
Steps: 90%|████████▉ | 895/1000 [05:28<00:37, 2.81it/s, loss=0.281, lr=1e-6]
Steps: 90%|████████▉ | 896/1000 [05:28<00:37, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 90%|████████▉ | 897/1000 [05:28<00:36, 2.81it/s, loss=0.281, lr=1e-6]
Steps: 90%|████████▉ | 898/1000 [05:29<00:36, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 90%|████████▉ | 899/1000 [05:29<00:36, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 90%|█████████ | 900/1000 [05:29<00:35, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 90%|█████████ | 900/1000 [05:30<00:35, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 90%|█████████ | 901/1000 [05:30<00:35, 2.78it/s, loss=0.281, lr=1e-6]
Steps: 90%|█████████ | 902/1000 [05:30<00:35, 2.79it/s, loss=0.281, lr=1e-6]
Steps: 90%|█████████ | 903/1000 [05:30<00:34, 2.79it/s, loss=0.281, lr=1e-6]
Steps: 90%|█████████ | 904/1000 [05:31<00:34, 2.78it/s, loss=0.281, lr=1e-6]
Steps: 90%|█████████ | 905/1000 [05:31<00:33, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 91%|█████████ | 906/1000 [05:32<00:33, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 91%|█████████ | 907/1000 [05:32<00:33, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 91%|█████████ | 908/1000 [05:32<00:32, 2.81it/s, loss=0.281, lr=1e-6]
Steps: 91%|█████████ | 909/1000 [05:33<00:32, 2.81it/s, loss=0.281, lr=1e-6]
Steps: 91%|█████████ | 910/1000 [05:33<00:32, 2.79it/s, loss=0.281, lr=1e-6]
Steps: 91%|█████████ | 910/1000 [05:33<00:32, 2.79it/s, loss=0.282, lr=1e-6]
Steps: 91%|█████████ | 911/1000 [05:33<00:31, 2.82it/s, loss=0.282, lr=1e-6]
Steps: 91%|█████████ | 912/1000 [05:34<00:31, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 91%|█████████▏| 913/1000 [05:34<00:31, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 91%|█████████▏| 914/1000 [05:34<00:31, 2.77it/s, loss=0.282, lr=1e-6]
Steps: 92%|█████████▏| 915/1000 [05:35<00:30, 2.78it/s, loss=0.282, lr=1e-6]
Steps: 92%|█████████▏| 916/1000 [05:35<00:30, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 92%|█████████▏| 917/1000 [05:35<00:29, 2.78it/s, loss=0.282, lr=1e-6]
Steps: 92%|█████████▏| 918/1000 [05:36<00:29, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 92%|█████████▏| 919/1000 [05:36<00:28, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 92%|█████████▏| 920/1000 [05:37<00:28, 2.80it/s, loss=0.282, lr=1e-6]
Steps: 92%|█████████▏| 920/1000 [05:37<00:28, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 92%|█████████▏| 921/1000 [05:37<00:28, 2.76it/s, loss=0.281, lr=1e-6]
Steps: 92%|█████████▏| 922/1000 [05:37<00:28, 2.78it/s, loss=0.281, lr=1e-6]
Steps: 92%|█████████▏| 923/1000 [05:38<00:27, 2.79it/s, loss=0.281, lr=1e-6]
Steps: 92%|█████████▏| 924/1000 [05:38<00:27, 2.79it/s, loss=0.281, lr=1e-6]
Steps: 92%|█████████▎| 925/1000 [05:38<00:26, 2.81it/s, loss=0.281, lr=1e-6]
Steps: 93%|█████████▎| 926/1000 [05:39<00:26, 2.81it/s, loss=0.281, lr=1e-6]
Steps: 93%|█████████▎| 927/1000 [05:39<00:26, 2.79it/s, loss=0.281, lr=1e-6]
Steps: 93%|█████████▎| 928/1000 [05:39<00:25, 2.81it/s, loss=0.281, lr=1e-6]
Steps: 93%|█████████▎| 929/1000 [05:40<00:25, 2.83it/s, loss=0.281, lr=1e-6]
Steps: 93%|█████████▎| 930/1000 [05:40<00:24, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 93%|█████████▎| 930/1000 [05:40<00:24, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 93%|█████████▎| 931/1000 [05:40<00:24, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 93%|█████████▎| 932/1000 [05:41<00:24, 2.78it/s, loss=0.281, lr=1e-6]
Steps: 93%|█████████▎| 933/1000 [05:41<00:24, 2.78it/s, loss=0.281, lr=1e-6]
Steps: 93%|█████████▎| 934/1000 [05:42<00:23, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 94%|█████████▎| 935/1000 [05:42<00:23, 2.82it/s, loss=0.281, lr=1e-6]
Steps: 94%|█████████▎| 936/1000 [05:42<00:22, 2.82it/s, loss=0.281, lr=1e-6]
Steps: 94%|█████████▎| 937/1000 [05:43<00:22, 2.81it/s, loss=0.281, lr=1e-6]
Steps: 94%|█████████▍| 938/1000 [05:43<00:22, 2.78it/s, loss=0.281, lr=1e-6]
Steps: 94%|█████████▍| 939/1000 [05:43<00:21, 2.78it/s, loss=0.281, lr=1e-6]
Steps: 94%|█████████▍| 940/1000 [05:44<00:21, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 94%|█████████▍| 940/1000 [05:44<00:21, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 94%|█████████▍| 941/1000 [05:44<00:21, 2.79it/s, loss=0.281, lr=1e-6]
Steps: 94%|█████████▍| 942/1000 [05:44<00:20, 2.79it/s, loss=0.281, lr=1e-6]
Steps: 94%|█████████▍| 943/1000 [05:45<00:20, 2.79it/s, loss=0.281, lr=1e-6]
Steps: 94%|█████████▍| 944/1000 [05:45<00:20, 2.78it/s, loss=0.281, lr=1e-6]
Steps: 94%|█████████▍| 945/1000 [05:45<00:20, 2.75it/s, loss=0.281, lr=1e-6]
Steps: 95%|█████████▍| 946/1000 [05:46<00:19, 2.78it/s, loss=0.281, lr=1e-6]
Steps: 95%|█████████▍| 947/1000 [05:46<00:19, 2.78it/s, loss=0.281, lr=1e-6]
Steps: 95%|█████████▍| 948/1000 [05:47<00:18, 2.81it/s, loss=0.281, lr=1e-6]
Steps: 95%|█████████▍| 949/1000 [05:47<00:18, 2.81it/s, loss=0.281, lr=1e-6]
Steps: 95%|█████████▌| 950/1000 [05:47<00:17, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 95%|█████████▌| 950/1000 [05:48<00:17, 2.80it/s, loss=0.28, lr=1e-6]
Steps: 95%|█████████▌| 951/1000 [05:48<00:17, 2.80it/s, loss=0.28, lr=1e-6]
Steps: 95%|█████████▌| 952/1000 [05:48<00:17, 2.82it/s, loss=0.28, lr=1e-6]
Steps: 95%|█████████▌| 953/1000 [05:48<00:16, 2.84it/s, loss=0.28, lr=1e-6]
Steps: 95%|█████████▌| 954/1000 [05:49<00:16, 2.85it/s, loss=0.28, lr=1e-6]
Steps: 96%|█████████▌| 955/1000 [05:49<00:15, 2.87it/s, loss=0.28, lr=1e-6]
Steps: 96%|█████████▌| 956/1000 [05:49<00:15, 2.87it/s, loss=0.28, lr=1e-6]
Steps: 96%|█████████▌| 957/1000 [05:50<00:15, 2.87it/s, loss=0.28, lr=1e-6]
Steps: 96%|█████████▌| 958/1000 [05:50<00:14, 2.87it/s, loss=0.28, lr=1e-6]
Steps: 96%|█████████▌| 959/1000 [05:50<00:14, 2.87it/s, loss=0.28, lr=1e-6]
Steps: 96%|█████████▌| 960/1000 [05:51<00:13, 2.88it/s, loss=0.28, lr=1e-6]
Steps: 96%|█████████▌| 960/1000 [05:51<00:13, 2.88it/s, loss=0.28, lr=1e-6]
Steps: 96%|█████████▌| 961/1000 [05:51<00:13, 2.86it/s, loss=0.28, lr=1e-6]
Steps: 96%|█████████▌| 962/1000 [05:51<00:13, 2.85it/s, loss=0.28, lr=1e-6]
Steps: 96%|█████████▋| 963/1000 [05:52<00:13, 2.85it/s, loss=0.28, lr=1e-6]
Steps: 96%|█████████▋| 964/1000 [05:52<00:12, 2.84it/s, loss=0.28, lr=1e-6]
Steps: 96%|█████████▋| 965/1000 [05:53<00:12, 2.85it/s, loss=0.28, lr=1e-6]
Steps: 97%|█████████▋| 966/1000 [05:53<00:11, 2.86it/s, loss=0.28, lr=1e-6]
Steps: 97%|█████████▋| 967/1000 [05:53<00:11, 2.86it/s, loss=0.28, lr=1e-6]
Steps: 97%|█████████▋| 968/1000 [05:54<00:11, 2.86it/s, loss=0.28, lr=1e-6]
Steps: 97%|█████████▋| 969/1000 [05:54<00:10, 2.85it/s, loss=0.28, lr=1e-6]
Steps: 97%|█████████▋| 970/1000 [05:54<00:10, 2.85it/s, loss=0.28, lr=1e-6]
Steps: 97%|█████████▋| 970/1000 [05:55<00:10, 2.85it/s, loss=0.281, lr=1e-6]
Steps: 97%|█████████▋| 971/1000 [05:55<00:10, 2.85it/s, loss=0.281, lr=1e-6]
Steps: 97%|█████████▋| 972/1000 [05:55<00:09, 2.86it/s, loss=0.281, lr=1e-6]
Steps: 97%|█████████▋| 973/1000 [05:55<00:09, 2.81it/s, loss=0.281, lr=1e-6]
Steps: 97%|█████████▋| 974/1000 [05:56<00:09, 2.82it/s, loss=0.281, lr=1e-6]
Steps: 98%|█████████▊| 975/1000 [05:56<00:08, 2.84it/s, loss=0.281, lr=1e-6]
Steps: 98%|█████████▊| 976/1000 [05:56<00:08, 2.85it/s, loss=0.281, lr=1e-6]
Steps: 98%|█████████▊| 977/1000 [05:57<00:08, 2.85it/s, loss=0.281, lr=1e-6]
Steps: 98%|█████████▊| 978/1000 [05:57<00:07, 2.85it/s, loss=0.281, lr=1e-6]
Steps: 98%|█████████▊| 979/1000 [05:57<00:07, 2.84it/s, loss=0.281, lr=1e-6]
Steps: 98%|█████████▊| 980/1000 [05:58<00:07, 2.84it/s, loss=0.281, lr=1e-6]
Steps: 98%|█████████▊| 980/1000 [05:58<00:07, 2.84it/s, loss=0.281, lr=1e-6]
Steps: 98%|█████████▊| 981/1000 [05:58<00:06, 2.84it/s, loss=0.281, lr=1e-6]
Steps: 98%|█████████▊| 982/1000 [05:58<00:06, 2.82it/s, loss=0.281, lr=1e-6]
Steps: 98%|█████████▊| 983/1000 [05:59<00:06, 2.82it/s, loss=0.281, lr=1e-6]
Steps: 98%|█████████▊| 984/1000 [05:59<00:05, 2.82it/s, loss=0.281, lr=1e-6]
Steps: 98%|█████████▊| 985/1000 [06:00<00:05, 2.81it/s, loss=0.281, lr=1e-6]
Steps: 99%|█████████▊| 986/1000 [06:00<00:05, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 99%|█████████▊| 987/1000 [06:00<00:04, 2.78it/s, loss=0.281, lr=1e-6]
Steps: 99%|█████████▉| 988/1000 [06:01<00:04, 2.79it/s, loss=0.281, lr=1e-6]
Steps: 99%|█████████▉| 989/1000 [06:01<00:03, 2.80it/s, loss=0.281, lr=1e-6]
Steps: 99%|█████████▉| 990/1000 [06:01<00:03, 2.82it/s, loss=0.281, lr=1e-6]
Steps: 99%|█████████▉| 990/1000 [06:02<00:03, 2.82it/s, loss=0.282, lr=1e-6]
Steps: 99%|█████████▉| 991/1000 [06:02<00:03, 2.82it/s, loss=0.282, lr=1e-6]
Steps: 99%|█████████▉| 992/1000 [06:02<00:02, 2.83it/s, loss=0.282, lr=1e-6]
Steps: 99%|█████████▉| 993/1000 [06:02<00:02, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 99%|█████████▉| 994/1000 [06:03<00:02, 2.81it/s, loss=0.282, lr=1e-6]
Steps: 100%|█████████▉| 995/1000 [06:03<00:01, 2.83it/s, loss=0.282, lr=1e-6]
Steps: 100%|█████████▉| 996/1000 [06:03<00:01, 2.84it/s, loss=0.282, lr=1e-6]
Steps: 100%|█████████▉| 997/1000 [06:04<00:01, 2.86it/s, loss=0.282, lr=1e-6]
Steps: 100%|█████████▉| 998/1000 [06:04<00:00, 2.85it/s, loss=0.282, lr=1e-6]
Steps: 100%|█████████▉| 999/1000 [06:05<00:00, 2.83it/s, loss=0.282, lr=1e-6]
Steps: 100%|██████████| 1000/1000 [06:05<00:00, 2.83it/s, loss=0.282, lr=1e-6]You have passed `None` for safety_checker to disable its functionality in <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'>. Note that this might lead to problems when using <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> and is not recommended.
[*] Weights saved at checkpoints
Steps: 100%|██████████| 1000/1000 [06:09<00:00, 2.71it/s, loss=0.282, lr=1e-6]
Thu Nov 17 02:47:06 2022
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 510.47.03 Driver Version: 510.47.03 CUDA Version: 11.6 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 NVIDIA A100-SXM... Off | 00000000:00:04.0 Off | 0 |
| N/A 39C P0 58W / 400W | 2122MiB / 40960MiB | 15% Default |
| | | Disabled |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 399088 C 2119MiB |
+-----------------------------------------------------------------------------+
checkpoints/tokenizer
checkpoints/unet
checkpoints/vae
checkpoints/text_encoder
checkpoints/feature_extractor
checkpoints/args.json
checkpoints/model_index.json
checkpoints/scheduler
checkpoints/tokenizer/vocab.json
checkpoints/tokenizer/special_tokens_map.json
checkpoints/tokenizer/merges.txt
checkpoints/tokenizer/tokenizer_config.json
checkpoints/unet/diffusion_pytorch_model.bin
checkpoints/unet/config.json
checkpoints/vae/diffusion_pytorch_model.bin
checkpoints/vae/config.json
checkpoints/text_encoder/pytorch_model.bin
checkpoints/text_encoder/config.json
checkpoints/feature_extractor/preprocessor_config.json
checkpoints/scheduler/scheduler_config.json