Running 1 job
{
    "type": "diffusion_trainer",
    "training_folder": "/data/app/output",
    "sqlite_db_path": "/data/app/aitk_db.db",
    "device": "cuda",
    "trigger_word": "latex",
    "performance_log_every": 10,
    "network": {
        "type": "lora",
        "linear": 32,
        "linear_alpha": 32,
        "conv": 16,
        "conv_alpha": 16,
        "lokr_full_rank": true,
        "lokr_factor": -1,
        "network_kwargs": {
            "ignore_if_contains": []
        }
    },
    "save": {
        "dtype": "bf16",
        "save_every": 250,
        "max_step_saves_to_keep": 4,
        "save_format": "diffusers",
        "push_to_hub": false
    },
    "datasets": [
        {
            "folder_path": "/data/app/datasets/latex_01",
            "mask_path": null,
            "mask_min_value": 0.1,
            "default_caption": "",
            "caption_ext": "txt",
            "caption_dropout_rate": 0.05,
            "cache_latents_to_disk": false,
            "is_reg": false,
            "network_weight": 1,
            "resolution": [
                512,
                768,
                1024
            ],
            "controls": [],
            "shrink_video_to_frames": true,
            "num_frames": 1,
            "do_i2v": true,
            "flip_x": false,
            "flip_y": false
        }
    ],
    "train": {
        "batch_size": 1,
        "bypass_guidance_embedding": false,
        "steps": 3000,
        "gradient_accumulation": 1,
        "train_unet": true,
        "train_text_encoder": false,
        "gradient_checkpointing": true,
        "noise_scheduler": "flowmatch",
        "optimizer": "adamw8bit",
        "timestep_type": "weighted",
        "content_or_style": "balanced",
        "optimizer_params": {
            "weight_decay": 0.0001
        },
        "unload_text_encoder": false,
        "cache_text_embeddings": false,
        "lr": 0.0001,
        "ema_config": {
            "use_ema": false,
            "ema_decay": 0.99
        },
        "skip_first_sample": false,
        "force_first_sample": false,
        "disable_sampling": false,
        "dtype": "bf16",
        "diff_output_preservation": false,
        "diff_output_preservation_multiplier": 1,
        "diff_output_preservation_class": "person",
        "switch_boundary_every": 1,
        "loss_type": "mse",
        "do_differential_guidance": true,
        "differential_guidance_scale": 3
    },
    "model": {
        "name_or_path": "Tongyi-MAI/Z-Image-Turbo",
        "quantize": true,
        "qtype": "qfloat8",
        "quantize_te": true,
        "qtype_te": "qfloat8",
        "arch": "zimage:turbo",
        "low_vram": false,
        "model_kwargs": {},
        "layer_offloading": false,
        "layer_offloading_text_encoder_percent": 1,
        "layer_offloading_transformer_percent": 1,
        "assistant_lora_path": "ostris/zimage_turbo_training_adapter/zimage_turbo_training_adapter_v2.safetensors"
    },
    "sample": {
        "sampler": "flowmatch",
        "sample_every": 300,
        "width": 512,
        "height": 512,
        "samples": [
            {
                "prompt": "A high-detail editorial portrait of a woman wearing a sleek, shining black latex bodysuit. High neck, long sleeves. The surface shows intense specular highlights and realistic micro-creases at the joints. Soft studio lighting, 8k resolution, minimalist grey background."
            },
            {
                "prompt": "A fashion model walking in a neon-lit city street, wearing a form-fitting red latex crop top paired with baggy denim jeans. The glossy texture of the latex contrasts with the rough fabric of the denim. Cinematic lighting, rain-slicked pavement, vibrant reflections."
            },
            {
                "prompt": "Full body shot of a woman in a midnight blue latex catsuit performing a dynamic pose. The suit has a mirror-like finish, reflecting the surrounding environment. Sharp focus on the stretching material around the knees and elbows. Professional photography, clean composition."
            },
            {
                "prompt": "Extreme close-up macro shot of polished purple latex fabric. Focus on the smooth, non-porous surface and the way light curves around the edges. Subtle highlights and deep shadows, showing the thickness and elasticity of the material."
            },
            {
                "prompt": "A high-fashion avant-garde look featuring a structured emerald green latex dress with exaggerated shoulder pads. The material is highly reflective and stiff, shimmering under bright runway lights. Fashion photography, blurred audience in the background."
            },
            {
                "prompt": "A sci-fi heroine standing in a futuristic laboratory, wearing a white latex tactical suit with silver accents. The pearlescent latex surface catches the blue and orange glow of holographic displays. Hyper-realistic, volumetric lighting, intricate details."
            },
            {
                "prompt": "A professional fashion shot of a model in a high-gloss black latex outfit, standing next to a sleek, minimalist wall. On the wall is a high-quality acrylic sign that reads \"Valenti Dynasty\" in elegant typography. The reflective surface of the latex catches the glow from the sign. Sharp focus, cinematic studio lighting, premium aesthetic."
            }
        ],
        "neg": "",
        "seed": 42,
        "walk_seed": true,
        "guidance_scale": 1,
        "sample_steps": 8,
        "num_frames": 1,
        "fps": 1
    }
}
Using SQLite database at /data/app/aitk_db.db
Job ID: "cd2a6c79-7a1c-4e6d-8a8e-5000a39d0e97"

#############################################
# Running job: latex_v1
#############################################


Running  1 process
Loading ZImage model
Loading transformer

config.json:   0%|          | 0.00/473 [00:00<?, ?B/s]
config.json:   0%|          | 0.00/473 [00:00<?, ?B/s]
config.json: 100%|##########| 473/473 [00:00<00:00, 4.68MB/s]
config.json: 100%|##########| 473/473 [00:00<00:00, 4.68MB/s]


(…)ion_pytorch_model.safetensors.index.json: 0.00B [00:00, ?B/s]
(…)ion_pytorch_model.safetensors.index.json: 0.00B [00:00, ?B/s]
(…)ion_pytorch_model.safetensors.index.json: 49.0kB [00:00, 53.9MB/s]
(…)ion_pytorch_model.safetensors.index.json: 49.0kB [00:00, 53.9MB/s]


transformer/diffusion_pytorch_model-0000(…):   0%|          | 0.00/9.97G [00:00<?, ?B/s]
transformer/diffusion_pytorch_model-0000(…):   0%|          | 0.00/9.97G [00:00<?, ?B/s]
transformer/diffusion_pytorch_model-0000(…):   0%|          | 866k/9.97G [00:00<1:31:14, 1.82MB/s]
transformer/diffusion_pytorch_model-0000(…):   0%|          | 866k/9.97G [00:00<1:31:14, 1.82MB/s]
transformer/diffusion_pytorch_model-0000(…):   1%|          | 67.9M/9.97G [00:00<01:25, 116MB/s]  
transformer/diffusion_pytorch_model-0000(…):   1%|          | 67.9M/9.97G [00:00<01:25, 116MB/s]  
transformer/diffusion_pytorch_model-0000(…):   3%|3         | 338M/9.97G [00:00<00:20, 476MB/s] 
transformer/diffusion_pytorch_model-0000(…):   3%|3         | 338M/9.97G [00:00<00:20, 476MB/s] 
transformer/diffusion_pytorch_model-0000(…):   6%|6         | 608M/9.97G [00:01<00:10, 861MB/s]
transformer/diffusion_pytorch_model-0000(…):   6%|6         | 608M/9.97G [00:01<00:10, 861MB/s]
transformer/diffusion_pytorch_model-0000(…):   7%|7         | 745M/9.97G [00:01<00:10, 858MB/s]
transformer/diffusion_pytorch_model-0000(…):   7%|7         | 745M/9.97G [00:01<00:10, 858MB/s]
transformer/diffusion_pytorch_model-0000(…):   9%|9         | 946M/9.97G [00:01<00:10, 887MB/s]
transformer/diffusion_pytorch_model-0000(…):   9%|9         | 946M/9.97G [00:01<00:10, 887MB/s]
transformer/diffusion_pytorch_model-0000(…):  11%|#         | 1.08G/9.97G [00:01<00:09, 955MB/s]
transformer/diffusion_pytorch_model-0000(…):  11%|#         | 1.08G/9.97G [00:01<00:09, 955MB/s]
transformer/diffusion_pytorch_model-0000(…):  13%|#2        | 1.28G/9.97G [00:01<00:07, 1.12GB/s]
transformer/diffusion_pytorch_model-0000(…):  13%|#2        | 1.28G/9.97G [00:01<00:07, 1.12GB/s]
transformer/diffusion_pytorch_model-0000(…):  14%|#4        | 1.42G/9.97G [00:01<00:09, 942MB/s] 
transformer/diffusion_pytorch_model-0000(…):  14%|#4        | 1.42G/9.97G [00:01<00:09, 942MB/s] 
transformer/diffusion_pytorch_model-0000(…):  16%|#5        | 1.55G/9.97G [00:02<00:09, 884MB/s]
transformer/diffusion_pytorch_model-0000(…):  16%|#5        | 1.55G/9.97G [00:02<00:09, 884MB/s]
transformer/diffusion_pytorch_model-0000(…):  17%|#6        | 1.68G/9.97G [00:02<00:11, 720MB/s]
transformer/diffusion_pytorch_model-0000(…):  17%|#6        | 1.68G/9.97G [00:02<00:11, 720MB/s]
transformer/diffusion_pytorch_model-0000(…):  21%|##        | 2.09G/9.97G [00:02<00:06, 1.28GB/s]
transformer/diffusion_pytorch_model-0000(…):  21%|##        | 2.09G/9.97G [00:02<00:06, 1.28GB/s]
transformer/diffusion_pytorch_model-0000(…):  23%|##2       | 2.29G/9.97G [00:02<00:06, 1.27GB/s]
transformer/diffusion_pytorch_model-0000(…):  23%|##2       | 2.29G/9.97G [00:02<00:06, 1.27GB/s]
transformer/diffusion_pytorch_model-0000(…):  25%|##4       | 2.49G/9.97G [00:02<00:05, 1.40GB/s]
transformer/diffusion_pytorch_model-0000(…):  25%|##4       | 2.49G/9.97G [00:02<00:05, 1.40GB/s]
transformer/diffusion_pytorch_model-0000(…):  27%|##6       | 2.69G/9.97G [00:02<00:04, 1.50GB/s]
transformer/diffusion_pytorch_model-0000(…):  27%|##6       | 2.69G/9.97G [00:02<00:04, 1.50GB/s]
transformer/diffusion_pytorch_model-0000(…):  29%|##8       | 2.89G/9.97G [00:02<00:04, 1.52GB/s]
transformer/diffusion_pytorch_model-0000(…):  29%|##8       | 2.89G/9.97G [00:02<00:04, 1.52GB/s]
transformer/diffusion_pytorch_model-0000(…):  31%|###       | 3.09G/9.97G [00:03<00:04, 1.54GB/s]
transformer/diffusion_pytorch_model-0000(…):  31%|###       | 3.09G/9.97G [00:03<00:04, 1.54GB/s]
transformer/diffusion_pytorch_model-0000(…):  33%|###2      | 3.29G/9.97G [00:03<00:04, 1.56GB/s]
transformer/diffusion_pytorch_model-0000(…):  33%|###2      | 3.29G/9.97G [00:03<00:04, 1.56GB/s]
transformer/diffusion_pytorch_model-0000(…):  35%|###4      | 3.49G/9.97G [00:03<00:04, 1.59GB/s]
transformer/diffusion_pytorch_model-0000(…):  35%|###4      | 3.49G/9.97G [00:03<00:04, 1.59GB/s]
transformer/diffusion_pytorch_model-0000(…):  37%|###7      | 3.69G/9.97G [00:03<00:04, 1.44GB/s]
transformer/diffusion_pytorch_model-0000(…):  37%|###7      | 3.69G/9.97G [00:03<00:04, 1.44GB/s]
transformer/diffusion_pytorch_model-0000(…):  39%|###9      | 3.89G/9.97G [00:03<00:04, 1.39GB/s]
transformer/diffusion_pytorch_model-0000(…):  39%|###9      | 3.89G/9.97G [00:03<00:04, 1.39GB/s]
transformer/diffusion_pytorch_model-0000(…):  41%|####1     | 4.09G/9.97G [00:03<00:04, 1.44GB/s]
transformer/diffusion_pytorch_model-0000(…):  41%|####1     | 4.09G/9.97G [00:03<00:04, 1.44GB/s]
transformer/diffusion_pytorch_model-0000(…):  43%|####3     | 4.30G/9.97G [00:03<00:04, 1.36GB/s]
transformer/diffusion_pytorch_model-0000(…):  43%|####3     | 4.30G/9.97G [00:03<00:04, 1.36GB/s]
transformer/diffusion_pytorch_model-0000(…):  45%|####5     | 4.50G/9.97G [00:04<00:04, 1.28GB/s]
transformer/diffusion_pytorch_model-0000(…):  45%|####5     | 4.50G/9.97G [00:04<00:04, 1.28GB/s]
transformer/diffusion_pytorch_model-0000(…):  46%|####6     | 4.63G/9.97G [00:04<00:05, 1.02GB/s]
transformer/diffusion_pytorch_model-0000(…):  46%|####6     | 4.63G/9.97G [00:04<00:05, 1.02GB/s]
transformer/diffusion_pytorch_model-0000(…):  50%|####9     | 4.97G/9.97G [00:04<00:03, 1.47GB/s]
transformer/diffusion_pytorch_model-0000(…):  50%|####9     | 4.97G/9.97G [00:04<00:03, 1.47GB/s]
transformer/diffusion_pytorch_model-0000(…):  52%|#####1    | 5.17G/9.97G [00:04<00:04, 1.15GB/s]
transformer/diffusion_pytorch_model-0000(…):  52%|#####1    | 5.17G/9.97G [00:04<00:04, 1.15GB/s]
transformer/diffusion_pytorch_model-0000(…):  54%|#####3    | 5.37G/9.97G [00:04<00:04, 1.13GB/s]
transformer/diffusion_pytorch_model-0000(…):  54%|#####3    | 5.37G/9.97G [00:04<00:04, 1.13GB/s]
transformer/diffusion_pytorch_model-0000(…):  55%|#####5    | 5.50G/9.97G [00:05<00:03, 1.15GB/s]
transformer/diffusion_pytorch_model-0000(…):  55%|#####5    | 5.50G/9.97G [00:05<00:03, 1.15GB/s]
transformer/diffusion_pytorch_model-0000(…):  57%|#####6    | 5.64G/9.97G [00:05<00:04, 1.08GB/s]
transformer/diffusion_pytorch_model-0000(…):  57%|#####6    | 5.64G/9.97G [00:05<00:04, 1.08GB/s]
transformer/diffusion_pytorch_model-0000(…):  59%|#####8    | 5.84G/9.97G [00:05<00:03, 1.17GB/s]
transformer/diffusion_pytorch_model-0000(…):  59%|#####8    | 5.84G/9.97G [00:05<00:03, 1.17GB/s]
transformer/diffusion_pytorch_model-0000(…):  60%|#####9    | 5.97G/9.97G [00:05<00:03, 1.17GB/s]
transformer/diffusion_pytorch_model-0000(…):  60%|#####9    | 5.97G/9.97G [00:05<00:03, 1.17GB/s]
transformer/diffusion_pytorch_model-0000(…):  62%|######1   | 6.17G/9.97G [00:05<00:02, 1.27GB/s]
transformer/diffusion_pytorch_model-0000(…):  62%|######1   | 6.17G/9.97G [00:05<00:02, 1.27GB/s]
transformer/diffusion_pytorch_model-0000(…):  63%|######3   | 6.31G/9.97G [00:05<00:03, 952MB/s] 
transformer/diffusion_pytorch_model-0000(…):  63%|######3   | 6.31G/9.97G [00:05<00:03, 952MB/s] 
transformer/diffusion_pytorch_model-0000(…):  65%|######4   | 6.44G/9.97G [00:06<00:04, 797MB/s]
transformer/diffusion_pytorch_model-0000(…):  65%|######4   | 6.44G/9.97G [00:06<00:04, 797MB/s]
transformer/diffusion_pytorch_model-0000(…):  67%|######6   | 6.64G/9.97G [00:06<00:03, 954MB/s]
transformer/diffusion_pytorch_model-0000(…):  67%|######6   | 6.64G/9.97G [00:06<00:03, 954MB/s]
transformer/diffusion_pytorch_model-0000(…):  68%|######7   | 6.77G/9.97G [00:06<00:03, 1.01GB/s]
transformer/diffusion_pytorch_model-0000(…):  68%|######7   | 6.77G/9.97G [00:06<00:03, 1.01GB/s]
transformer/diffusion_pytorch_model-0000(…):  70%|######9   | 6.97G/9.97G [00:06<00:02, 1.09GB/s]
transformer/diffusion_pytorch_model-0000(…):  70%|######9   | 6.97G/9.97G [00:06<00:02, 1.09GB/s]
transformer/diffusion_pytorch_model-0000(…):  72%|#######1  | 7.18G/9.97G [00:06<00:02, 1.20GB/s]
transformer/diffusion_pytorch_model-0000(…):  72%|#######1  | 7.18G/9.97G [00:06<00:02, 1.20GB/s]
transformer/diffusion_pytorch_model-0000(…):  74%|#######3  | 7.38G/9.97G [00:06<00:01, 1.33GB/s]
transformer/diffusion_pytorch_model-0000(…):  74%|#######3  | 7.38G/9.97G [00:06<00:01, 1.33GB/s]
transformer/diffusion_pytorch_model-0000(…):  76%|#######5  | 7.56G/9.97G [00:06<00:01, 1.27GB/s]
transformer/diffusion_pytorch_model-0000(…):  76%|#######5  | 7.56G/9.97G [00:06<00:01, 1.27GB/s]
transformer/diffusion_pytorch_model-0000(…):  78%|#######7  | 7.76G/9.97G [00:07<00:01, 1.38GB/s]
transformer/diffusion_pytorch_model-0000(…):  78%|#######7  | 7.76G/9.97G [00:07<00:01, 1.38GB/s]
transformer/diffusion_pytorch_model-0000(…):  80%|#######9  | 7.96G/9.97G [00:07<00:01, 1.41GB/s]
transformer/diffusion_pytorch_model-0000(…):  80%|#######9  | 7.96G/9.97G [00:07<00:01, 1.41GB/s]
transformer/diffusion_pytorch_model-0000(…):  82%|########1 | 8.16G/9.97G [00:07<00:01, 1.45GB/s]
transformer/diffusion_pytorch_model-0000(…):  82%|########1 | 8.16G/9.97G [00:07<00:01, 1.45GB/s]
transformer/diffusion_pytorch_model-0000(…):  84%|########3 | 8.36G/9.97G [00:07<00:01, 1.46GB/s]
transformer/diffusion_pytorch_model-0000(…):  84%|########3 | 8.36G/9.97G [00:07<00:01, 1.46GB/s]
transformer/diffusion_pytorch_model-0000(…):  86%|########5 | 8.57G/9.97G [00:07<00:00, 1.55GB/s]
transformer/diffusion_pytorch_model-0000(…):  86%|########5 | 8.57G/9.97G [00:07<00:00, 1.55GB/s]
transformer/diffusion_pytorch_model-0000(…):  88%|########7 | 8.77G/9.97G [00:07<00:00, 1.54GB/s]
transformer/diffusion_pytorch_model-0000(…):  88%|########7 | 8.77G/9.97G [00:07<00:00, 1.54GB/s]
transformer/diffusion_pytorch_model-0000(…):  90%|########9 | 8.97G/9.97G [00:07<00:00, 1.64GB/s]
transformer/diffusion_pytorch_model-0000(…):  90%|########9 | 8.97G/9.97G [00:07<00:00, 1.64GB/s]
transformer/diffusion_pytorch_model-0000(…):  92%|#########1| 9.17G/9.97G [00:07<00:00, 1.69GB/s]
transformer/diffusion_pytorch_model-0000(…):  92%|#########1| 9.17G/9.97G [00:07<00:00, 1.69GB/s]
transformer/diffusion_pytorch_model-0000(…):  95%|#########5| 9.50G/9.97G [00:08<00:00, 1.90GB/s]
transformer/diffusion_pytorch_model-0000(…):  95%|#########5| 9.50G/9.97G [00:08<00:00, 1.90GB/s]
transformer/diffusion_pytorch_model-0000(…):  97%|#########7| 9.71G/9.97G [00:08<00:00, 1.92GB/s]
transformer/diffusion_pytorch_model-0000(…):  97%|#########7| 9.71G/9.97G [00:08<00:00, 1.92GB/s]
transformer/diffusion_pytorch_model-0000(…): 100%|##########| 9.97G/9.97G [00:08<00:00, 1.98GB/s]
transformer/diffusion_pytorch_model-0000(…): 100%|##########| 9.97G/9.97G [00:08<00:00, 1.98GB/s]
transformer/diffusion_pytorch_model-0000(…): 100%|##########| 9.97G/9.97G [00:08<00:00, 1.21GB/s]
transformer/diffusion_pytorch_model-0000(…): 100%|##########| 9.97G/9.97G [00:08<00:00, 1.21GB/s]


transformer/diffusion_pytorch_model-0000(…):   0%|          | 0.00/9.97G [00:00<?, ?B/s]
transformer/diffusion_pytorch_model-0000(…):   0%|          | 0.00/9.97G [00:00<?, ?B/s]
transformer/diffusion_pytorch_model-0000(…):   0%|          | 866k/9.97G [00:00<1:28:53, 1.87MB/s]
transformer/diffusion_pytorch_model-0000(…):   0%|          | 866k/9.97G [00:00<1:28:53, 1.87MB/s]
transformer/diffusion_pytorch_model-0000(…):   1%|          | 67.9M/9.97G [00:00<01:34, 104MB/s]  
transformer/diffusion_pytorch_model-0000(…):   1%|          | 67.9M/9.97G [00:00<01:34, 104MB/s]  
transformer/diffusion_pytorch_model-0000(…):   4%|4         | 403M/9.97G [00:01<00:17, 532MB/s] 
transformer/diffusion_pytorch_model-0000(…):   4%|4         | 403M/9.97G [00:01<00:17, 532MB/s] 
transformer/diffusion_pytorch_model-0000(…):   8%|8         | 810M/9.97G [00:01<00:08, 1.04GB/s]
transformer/diffusion_pytorch_model-0000(…):   8%|8         | 810M/9.97G [00:01<00:08, 1.04GB/s]
transformer/diffusion_pytorch_model-0000(…):  10%|#         | 1.01G/9.97G [00:01<00:10, 872MB/s]
transformer/diffusion_pytorch_model-0000(…):  10%|#         | 1.01G/9.97G [00:01<00:10, 872MB/s]
transformer/diffusion_pytorch_model-0000(…):  11%|#1        | 1.14G/9.97G [00:01<00:10, 871MB/s]
transformer/diffusion_pytorch_model-0000(…):  11%|#1        | 1.14G/9.97G [00:01<00:10, 871MB/s]
transformer/diffusion_pytorch_model-0000(…):  14%|#3        | 1.35G/9.97G [00:01<00:08, 983MB/s]
transformer/diffusion_pytorch_model-0000(…):  14%|#3        | 1.35G/9.97G [00:01<00:08, 983MB/s]
transformer/diffusion_pytorch_model-0000(…):  15%|#4        | 1.48G/9.97G [00:02<00:12, 668MB/s]
transformer/diffusion_pytorch_model-0000(…):  15%|#4        | 1.48G/9.97G [00:02<00:12, 668MB/s]
transformer/diffusion_pytorch_model-0000(…):  16%|#6        | 1.62G/9.97G [00:02<00:15, 553MB/s]
transformer/diffusion_pytorch_model-0000(…):  16%|#6        | 1.62G/9.97G [00:02<00:15, 553MB/s]
transformer/diffusion_pytorch_model-0000(…):  18%|#7        | 1.75G/9.97G [00:03<00:20, 396MB/s]
transformer/diffusion_pytorch_model-0000(…):  18%|#7        | 1.75G/9.97G [00:03<00:20, 396MB/s]
transformer/diffusion_pytorch_model-0000(…):  18%|#8        | 1.82G/9.97G [00:03<00:23, 347MB/s]
transformer/diffusion_pytorch_model-0000(…):  18%|#8        | 1.82G/9.97G [00:03<00:23, 347MB/s]
transformer/diffusion_pytorch_model-0000(…):  19%|#8        | 1.89G/9.97G [00:03<00:26, 309MB/s]
transformer/diffusion_pytorch_model-0000(…):  19%|#8        | 1.89G/9.97G [00:03<00:26, 309MB/s]
transformer/diffusion_pytorch_model-0000(…):  20%|#9        | 1.95G/9.97G [00:04<00:28, 283MB/s]
transformer/diffusion_pytorch_model-0000(…):  20%|#9        | 1.95G/9.97G [00:04<00:28, 283MB/s]
transformer/diffusion_pytorch_model-0000(…):  20%|##        | 2.02G/9.97G [00:04<00:30, 265MB/s]
transformer/diffusion_pytorch_model-0000(…):  20%|##        | 2.02G/9.97G [00:04<00:30, 265MB/s]
transformer/diffusion_pytorch_model-0000(…):  21%|##        | 2.09G/9.97G [00:04<00:31, 251MB/s]
transformer/diffusion_pytorch_model-0000(…):  21%|##        | 2.09G/9.97G [00:04<00:31, 251MB/s]
transformer/diffusion_pytorch_model-0000(…):  22%|##1       | 2.15G/9.97G [00:05<00:32, 243MB/s]
transformer/diffusion_pytorch_model-0000(…):  22%|##1       | 2.15G/9.97G [00:05<00:32, 243MB/s]
transformer/diffusion_pytorch_model-0000(…):  22%|##2       | 2.22G/9.97G [00:05<00:32, 237MB/s]
transformer/diffusion_pytorch_model-0000(…):  22%|##2       | 2.22G/9.97G [00:05<00:32, 237MB/s]
transformer/diffusion_pytorch_model-0000(…):  23%|##2       | 2.29G/9.97G [00:05<00:33, 231MB/s]
transformer/diffusion_pytorch_model-0000(…):  23%|##2       | 2.29G/9.97G [00:05<00:33, 231MB/s]
transformer/diffusion_pytorch_model-0000(…):  24%|##3       | 2.35G/9.97G [00:05<00:33, 229MB/s]
transformer/diffusion_pytorch_model-0000(…):  24%|##3       | 2.35G/9.97G [00:05<00:33, 229MB/s]
transformer/diffusion_pytorch_model-0000(…):  24%|##4       | 2.42G/9.97G [00:06<00:33, 226MB/s]
transformer/diffusion_pytorch_model-0000(…):  24%|##4       | 2.42G/9.97G [00:06<00:33, 226MB/s]
transformer/diffusion_pytorch_model-0000(…):  25%|##4       | 2.49G/9.97G [00:06<00:33, 223MB/s]
transformer/diffusion_pytorch_model-0000(…):  25%|##4       | 2.49G/9.97G [00:06<00:33, 223MB/s]
transformer/diffusion_pytorch_model-0000(…):  26%|##5       | 2.56G/9.97G [00:06<00:33, 223MB/s]
transformer/diffusion_pytorch_model-0000(…):  26%|##5       | 2.56G/9.97G [00:06<00:33, 223MB/s]
transformer/diffusion_pytorch_model-0000(…):  26%|##6       | 2.62G/9.97G [00:07<00:32, 225MB/s]
transformer/diffusion_pytorch_model-0000(…):  26%|##6       | 2.62G/9.97G [00:07<00:32, 225MB/s]
transformer/diffusion_pytorch_model-0000(…):  27%|##6       | 2.69G/9.97G [00:07<00:32, 225MB/s]
transformer/diffusion_pytorch_model-0000(…):  27%|##6       | 2.69G/9.97G [00:07<00:32, 225MB/s]
transformer/diffusion_pytorch_model-0000(…):  28%|##7       | 2.76G/9.97G [00:07<00:31, 226MB/s]
transformer/diffusion_pytorch_model-0000(…):  28%|##7       | 2.76G/9.97G [00:07<00:31, 226MB/s]
transformer/diffusion_pytorch_model-0000(…):  28%|##8       | 2.82G/9.97G [00:08<00:31, 227MB/s]
transformer/diffusion_pytorch_model-0000(…):  28%|##8       | 2.82G/9.97G [00:08<00:31, 227MB/s]
transformer/diffusion_pytorch_model-0000(…):  29%|##8       | 2.89G/9.97G [00:08<00:31, 228MB/s]
transformer/diffusion_pytorch_model-0000(…):  29%|##8       | 2.89G/9.97G [00:08<00:31, 228MB/s]
transformer/diffusion_pytorch_model-0000(…):  30%|##9       | 2.96G/9.97G [00:08<00:30, 227MB/s]
transformer/diffusion_pytorch_model-0000(…):  30%|##9       | 2.96G/9.97G [00:08<00:30, 227MB/s]
transformer/diffusion_pytorch_model-0000(…):  30%|###       | 3.02G/9.97G [00:08<00:30, 228MB/s]
transformer/diffusion_pytorch_model-0000(…):  30%|###       | 3.02G/9.97G [00:08<00:30, 228MB/s]
transformer/diffusion_pytorch_model-0000(…):  31%|###       | 3.09G/9.97G [00:09<00:30, 227MB/s]
transformer/diffusion_pytorch_model-0000(…):  31%|###       | 3.09G/9.97G [00:09<00:30, 227MB/s]
transformer/diffusion_pytorch_model-0000(…):  32%|###1      | 3.16G/9.97G [00:09<00:29, 227MB/s]
transformer/diffusion_pytorch_model-0000(…):  32%|###1      | 3.16G/9.97G [00:09<00:29, 227MB/s]
transformer/diffusion_pytorch_model-0000(…):  32%|###2      | 3.23G/9.97G [00:09<00:29, 225MB/s]
transformer/diffusion_pytorch_model-0000(…):  32%|###2      | 3.23G/9.97G [00:09<00:29, 225MB/s]
transformer/diffusion_pytorch_model-0000(…):  33%|###3      | 3.29G/9.97G [00:10<00:30, 221MB/s]
transformer/diffusion_pytorch_model-0000(…):  33%|###3      | 3.29G/9.97G [00:10<00:30, 221MB/s]
transformer/diffusion_pytorch_model-0000(…):  34%|###3      | 3.36G/9.97G [00:10<00:31, 211MB/s]
transformer/diffusion_pytorch_model-0000(…):  34%|###3      | 3.36G/9.97G [00:10<00:31, 211MB/s]
transformer/diffusion_pytorch_model-0000(…):  34%|###4      | 3.43G/9.97G [00:10<00:31, 205MB/s]
transformer/diffusion_pytorch_model-0000(…):  34%|###4      | 3.43G/9.97G [00:10<00:31, 205MB/s]
transformer/diffusion_pytorch_model-0000(…):  35%|###5      | 3.49G/9.97G [00:11<00:30, 209MB/s]
transformer/diffusion_pytorch_model-0000(…):  35%|###5      | 3.49G/9.97G [00:11<00:30, 209MB/s]
transformer/diffusion_pytorch_model-0000(…):  36%|###5      | 3.56G/9.97G [00:11<00:30, 209MB/s]
transformer/diffusion_pytorch_model-0000(…):  36%|###5      | 3.56G/9.97G [00:11<00:30, 209MB/s]
transformer/diffusion_pytorch_model-0000(…):  36%|###6      | 3.62G/9.97G [00:11<00:30, 208MB/s]
transformer/diffusion_pytorch_model-0000(…):  36%|###6      | 3.62G/9.97G [00:11<00:30, 208MB/s]
transformer/diffusion_pytorch_model-0000(…):  37%|###7      | 3.69G/9.97G [00:12<00:30, 207MB/s]
transformer/diffusion_pytorch_model-0000(…):  37%|###7      | 3.69G/9.97G [00:12<00:30, 207MB/s]
transformer/diffusion_pytorch_model-0000(…):  38%|###7      | 3.76G/9.97G [00:12<00:28, 217MB/s]
transformer/diffusion_pytorch_model-0000(…):  38%|###7      | 3.76G/9.97G [00:12<00:28, 217MB/s]
transformer/diffusion_pytorch_model-0000(…):  38%|###8      | 3.83G/9.97G [00:12<00:27, 226MB/s]
transformer/diffusion_pytorch_model-0000(…):  38%|###8      | 3.83G/9.97G [00:12<00:27, 226MB/s]
transformer/diffusion_pytorch_model-0000(…):  39%|###9      | 3.90G/9.97G [00:12<00:25, 235MB/s]
transformer/diffusion_pytorch_model-0000(…):  39%|###9      | 3.90G/9.97G [00:12<00:25, 235MB/s]
transformer/diffusion_pytorch_model-0000(…):  40%|###9      | 3.97G/9.97G [00:13<00:24, 243MB/s]
transformer/diffusion_pytorch_model-0000(…):  40%|###9      | 3.97G/9.97G [00:13<00:24, 243MB/s]
transformer/diffusion_pytorch_model-0000(…):  40%|####      | 4.03G/9.97G [00:13<00:23, 252MB/s]
transformer/diffusion_pytorch_model-0000(…):  40%|####      | 4.03G/9.97G [00:13<00:23, 252MB/s]
transformer/diffusion_pytorch_model-0000(…):  41%|####1     | 4.10G/9.97G [00:13<00:23, 255MB/s]
transformer/diffusion_pytorch_model-0000(…):  41%|####1     | 4.10G/9.97G [00:13<00:23, 255MB/s]
transformer/diffusion_pytorch_model-0000(…):  42%|####1     | 4.17G/9.97G [00:13<00:22, 260MB/s]
transformer/diffusion_pytorch_model-0000(…):  42%|####1     | 4.17G/9.97G [00:13<00:22, 260MB/s]
transformer/diffusion_pytorch_model-0000(…):  42%|####2     | 4.23G/9.97G [00:14<00:21, 263MB/s]
transformer/diffusion_pytorch_model-0000(…):  42%|####2     | 4.23G/9.97G [00:14<00:21, 263MB/s]
transformer/diffusion_pytorch_model-0000(…):  43%|####3     | 4.30G/9.97G [00:14<00:21, 268MB/s]
transformer/diffusion_pytorch_model-0000(…):  43%|####3     | 4.30G/9.97G [00:14<00:21, 268MB/s]
transformer/diffusion_pytorch_model-0000(…):  44%|####3     | 4.37G/9.97G [00:14<00:20, 270MB/s]
transformer/diffusion_pytorch_model-0000(…):  44%|####3     | 4.37G/9.97G [00:14<00:20, 270MB/s]
transformer/diffusion_pytorch_model-0000(…):  44%|####4     | 4.43G/9.97G [00:14<00:20, 270MB/s]
transformer/diffusion_pytorch_model-0000(…):  44%|####4     | 4.43G/9.97G [00:14<00:20, 270MB/s]
transformer/diffusion_pytorch_model-0000(…):  45%|####5     | 4.50G/9.97G [00:15<00:20, 266MB/s]
transformer/diffusion_pytorch_model-0000(…):  45%|####5     | 4.50G/9.97G [00:15<00:20, 266MB/s]
transformer/diffusion_pytorch_model-0000(…):  46%|####5     | 4.57G/9.97G [00:15<00:19, 272MB/s]
transformer/diffusion_pytorch_model-0000(…):  46%|####5     | 4.57G/9.97G [00:15<00:19, 272MB/s]
transformer/diffusion_pytorch_model-0000(…):  46%|####6     | 4.64G/9.97G [00:15<00:16, 329MB/s]
transformer/diffusion_pytorch_model-0000(…):  46%|####6     | 4.64G/9.97G [00:15<00:16, 329MB/s]
transformer/diffusion_pytorch_model-0000(…):  47%|####7     | 4.70G/9.97G [00:15<00:16, 312MB/s]
transformer/diffusion_pytorch_model-0000(…):  47%|####7     | 4.70G/9.97G [00:15<00:16, 312MB/s]
transformer/diffusion_pytorch_model-0000(…):  48%|####7     | 4.77G/9.97G [00:16<00:17, 300MB/s]
transformer/diffusion_pytorch_model-0000(…):  48%|####7     | 4.77G/9.97G [00:16<00:17, 300MB/s]
transformer/diffusion_pytorch_model-0000(…):  48%|####8     | 4.84G/9.97G [00:16<00:17, 292MB/s]
transformer/diffusion_pytorch_model-0000(…):  48%|####8     | 4.84G/9.97G [00:16<00:17, 292MB/s]
transformer/diffusion_pytorch_model-0000(…):  49%|####9     | 4.90G/9.97G [00:16<00:17, 285MB/s]
transformer/diffusion_pytorch_model-0000(…):  49%|####9     | 4.90G/9.97G [00:16<00:17, 285MB/s]
transformer/diffusion_pytorch_model-0000(…):  50%|####9     | 4.97G/9.97G [00:16<00:17, 282MB/s]
transformer/diffusion_pytorch_model-0000(…):  50%|####9     | 4.97G/9.97G [00:16<00:17, 282MB/s]
transformer/diffusion_pytorch_model-0000(…):  51%|#####     | 5.04G/9.97G [00:17<00:17, 280MB/s]
transformer/diffusion_pytorch_model-0000(…):  51%|#####     | 5.04G/9.97G [00:17<00:17, 280MB/s]
transformer/diffusion_pytorch_model-0000(…):  51%|#####1    | 5.11G/9.97G [00:17<00:17, 274MB/s]
transformer/diffusion_pytorch_model-0000(…):  51%|#####1    | 5.11G/9.97G [00:17<00:17, 274MB/s]
transformer/diffusion_pytorch_model-0000(…):  52%|#####1    | 5.17G/9.97G [00:17<00:17, 272MB/s]
transformer/diffusion_pytorch_model-0000(…):  52%|#####1    | 5.17G/9.97G [00:17<00:17, 272MB/s]
transformer/diffusion_pytorch_model-0000(…):  53%|#####2    | 5.24G/9.97G [00:17<00:17, 264MB/s]
transformer/diffusion_pytorch_model-0000(…):  53%|#####2    | 5.24G/9.97G [00:17<00:17, 264MB/s]
transformer/diffusion_pytorch_model-0000(…):  53%|#####3    | 5.31G/9.97G [00:18<00:19, 245MB/s]
transformer/diffusion_pytorch_model-0000(…):  53%|#####3    | 5.31G/9.97G [00:18<00:19, 245MB/s]
transformer/diffusion_pytorch_model-0000(…):  54%|#####3    | 5.37G/9.97G [00:18<00:20, 219MB/s]
transformer/diffusion_pytorch_model-0000(…):  54%|#####3    | 5.37G/9.97G [00:18<00:20, 219MB/s]
transformer/diffusion_pytorch_model-0000(…):  55%|#####4    | 5.44G/9.97G [00:18<00:21, 211MB/s]
transformer/diffusion_pytorch_model-0000(…):  55%|#####4    | 5.44G/9.97G [00:18<00:21, 211MB/s]
transformer/diffusion_pytorch_model-0000(…):  55%|#####5    | 5.51G/9.97G [00:19<00:22, 200MB/s]
transformer/diffusion_pytorch_model-0000(…):  55%|#####5    | 5.51G/9.97G [00:19<00:22, 200MB/s]
transformer/diffusion_pytorch_model-0000(…):  56%|#####5    | 5.57G/9.97G [00:19<00:22, 193MB/s]
transformer/diffusion_pytorch_model-0000(…):  56%|#####5    | 5.57G/9.97G [00:19<00:22, 193MB/s]
transformer/diffusion_pytorch_model-0000(…):  57%|#####6    | 5.64G/9.97G [00:19<00:21, 199MB/s]
transformer/diffusion_pytorch_model-0000(…):  57%|#####6    | 5.64G/9.97G [00:19<00:21, 199MB/s]
transformer/diffusion_pytorch_model-0000(…):  57%|#####7    | 5.71G/9.97G [00:20<00:21, 196MB/s]
transformer/diffusion_pytorch_model-0000(…):  57%|#####7    | 5.71G/9.97G [00:20<00:21, 196MB/s]
transformer/diffusion_pytorch_model-0000(…):  58%|#####7    | 5.78G/9.97G [00:20<00:21, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  58%|#####7    | 5.78G/9.97G [00:20<00:21, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  59%|#####8    | 5.84G/9.97G [00:20<00:20, 200MB/s]
transformer/diffusion_pytorch_model-0000(…):  59%|#####8    | 5.84G/9.97G [00:20<00:20, 200MB/s]
transformer/diffusion_pytorch_model-0000(…):  59%|#####9    | 5.91G/9.97G [00:21<00:20, 196MB/s]
transformer/diffusion_pytorch_model-0000(…):  59%|#####9    | 5.91G/9.97G [00:21<00:20, 196MB/s]
transformer/diffusion_pytorch_model-0000(…):  60%|#####9    | 5.98G/9.97G [00:21<00:20, 195MB/s]
transformer/diffusion_pytorch_model-0000(…):  60%|#####9    | 5.98G/9.97G [00:21<00:20, 195MB/s]
transformer/diffusion_pytorch_model-0000(…):  61%|######    | 6.04G/9.97G [00:21<00:19, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  61%|######    | 6.04G/9.97G [00:21<00:19, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  61%|######1   | 6.11G/9.97G [00:22<00:19, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  61%|######1   | 6.11G/9.97G [00:22<00:19, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  62%|######1   | 6.18G/9.97G [00:22<00:19, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  62%|######1   | 6.18G/9.97G [00:22<00:19, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  63%|######2   | 6.25G/9.97G [00:22<00:19, 196MB/s]
transformer/diffusion_pytorch_model-0000(…):  63%|######2   | 6.25G/9.97G [00:22<00:19, 196MB/s]
transformer/diffusion_pytorch_model-0000(…):  63%|######3   | 6.31G/9.97G [00:23<00:19, 192MB/s]
transformer/diffusion_pytorch_model-0000(…):  63%|######3   | 6.31G/9.97G [00:23<00:19, 192MB/s]
transformer/diffusion_pytorch_model-0000(…):  64%|######3   | 6.38G/9.97G [00:23<00:18, 192MB/s]
transformer/diffusion_pytorch_model-0000(…):  64%|######3   | 6.38G/9.97G [00:23<00:18, 192MB/s]
transformer/diffusion_pytorch_model-0000(…):  65%|######4   | 6.45G/9.97G [00:24<00:18, 188MB/s]
transformer/diffusion_pytorch_model-0000(…):  65%|######4   | 6.45G/9.97G [00:24<00:18, 188MB/s]
transformer/diffusion_pytorch_model-0000(…):  65%|######5   | 6.51G/9.97G [00:24<00:18, 192MB/s]
transformer/diffusion_pytorch_model-0000(…):  65%|######5   | 6.51G/9.97G [00:24<00:18, 192MB/s]
transformer/diffusion_pytorch_model-0000(…):  66%|######5   | 6.58G/9.97G [00:24<00:20, 169MB/s]
transformer/diffusion_pytorch_model-0000(…):  66%|######5   | 6.58G/9.97G [00:24<00:20, 169MB/s]
transformer/diffusion_pytorch_model-0000(…):  67%|######6   | 6.64G/9.97G [00:25<00:19, 173MB/s]
transformer/diffusion_pytorch_model-0000(…):  67%|######6   | 6.64G/9.97G [00:25<00:19, 173MB/s]
transformer/diffusion_pytorch_model-0000(…):  67%|######7   | 6.71G/9.97G [00:25<00:17, 182MB/s]
transformer/diffusion_pytorch_model-0000(…):  67%|######7   | 6.71G/9.97G [00:25<00:17, 182MB/s]
transformer/diffusion_pytorch_model-0000(…):  68%|######7   | 6.78G/9.97G [00:25<00:16, 188MB/s]
transformer/diffusion_pytorch_model-0000(…):  68%|######7   | 6.78G/9.97G [00:25<00:16, 188MB/s]
transformer/diffusion_pytorch_model-0000(…):  69%|######8   | 6.85G/9.97G [00:26<00:16, 192MB/s]
transformer/diffusion_pytorch_model-0000(…):  69%|######8   | 6.85G/9.97G [00:26<00:16, 192MB/s]
transformer/diffusion_pytorch_model-0000(…):  69%|######9   | 6.91G/9.97G [00:26<00:15, 198MB/s]
transformer/diffusion_pytorch_model-0000(…):  69%|######9   | 6.91G/9.97G [00:26<00:15, 198MB/s]
transformer/diffusion_pytorch_model-0000(…):  70%|######9   | 6.98G/9.97G [00:26<00:14, 201MB/s]
transformer/diffusion_pytorch_model-0000(…):  70%|######9   | 6.98G/9.97G [00:26<00:14, 201MB/s]
transformer/diffusion_pytorch_model-0000(…):  71%|#######   | 7.05G/9.97G [00:27<00:14, 199MB/s]
transformer/diffusion_pytorch_model-0000(…):  71%|#######   | 7.05G/9.97G [00:27<00:14, 199MB/s]
transformer/diffusion_pytorch_model-0000(…):  71%|#######1  | 7.11G/9.97G [00:27<00:14, 200MB/s]
transformer/diffusion_pytorch_model-0000(…):  71%|#######1  | 7.11G/9.97G [00:27<00:14, 200MB/s]
transformer/diffusion_pytorch_model-0000(…):  72%|#######1  | 7.18G/9.97G [00:27<00:13, 201MB/s]
transformer/diffusion_pytorch_model-0000(…):  72%|#######1  | 7.18G/9.97G [00:27<00:13, 201MB/s]
transformer/diffusion_pytorch_model-0000(…):  73%|#######2  | 7.25G/9.97G [00:28<00:13, 196MB/s]
transformer/diffusion_pytorch_model-0000(…):  73%|#######2  | 7.25G/9.97G [00:28<00:13, 196MB/s]
transformer/diffusion_pytorch_model-0000(…):  73%|#######3  | 7.32G/9.97G [00:28<00:13, 194MB/s]
transformer/diffusion_pytorch_model-0000(…):  73%|#######3  | 7.32G/9.97G [00:28<00:13, 194MB/s]
transformer/diffusion_pytorch_model-0000(…):  74%|#######4  | 7.38G/9.97G [00:28<00:13, 199MB/s]
transformer/diffusion_pytorch_model-0000(…):  74%|#######4  | 7.38G/9.97G [00:28<00:13, 199MB/s]
transformer/diffusion_pytorch_model-0000(…):  75%|#######4  | 7.45G/9.97G [00:29<00:12, 195MB/s]
transformer/diffusion_pytorch_model-0000(…):  75%|#######4  | 7.45G/9.97G [00:29<00:12, 195MB/s]
transformer/diffusion_pytorch_model-0000(…):  75%|#######5  | 7.52G/9.97G [00:29<00:12, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  75%|#######5  | 7.52G/9.97G [00:29<00:12, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  76%|#######6  | 7.58G/9.97G [00:29<00:11, 203MB/s]
transformer/diffusion_pytorch_model-0000(…):  76%|#######6  | 7.58G/9.97G [00:29<00:11, 203MB/s]
transformer/diffusion_pytorch_model-0000(…):  77%|#######6  | 7.65G/9.97G [00:30<00:11, 203MB/s]
transformer/diffusion_pytorch_model-0000(…):  77%|#######6  | 7.65G/9.97G [00:30<00:11, 203MB/s]
transformer/diffusion_pytorch_model-0000(…):  77%|#######7  | 7.72G/9.97G [00:30<00:10, 206MB/s]
transformer/diffusion_pytorch_model-0000(…):  77%|#######7  | 7.72G/9.97G [00:30<00:10, 206MB/s]
transformer/diffusion_pytorch_model-0000(…):  78%|#######8  | 7.78G/9.97G [00:30<00:10, 212MB/s]
transformer/diffusion_pytorch_model-0000(…):  78%|#######8  | 7.78G/9.97G [00:30<00:10, 212MB/s]
transformer/diffusion_pytorch_model-0000(…):  79%|#######8  | 7.85G/9.97G [00:31<00:10, 212MB/s]
transformer/diffusion_pytorch_model-0000(…):  79%|#######8  | 7.85G/9.97G [00:31<00:10, 212MB/s]
transformer/diffusion_pytorch_model-0000(…):  79%|#######9  | 7.92G/9.97G [00:31<00:09, 220MB/s]
transformer/diffusion_pytorch_model-0000(…):  79%|#######9  | 7.92G/9.97G [00:31<00:09, 220MB/s]
transformer/diffusion_pytorch_model-0000(…):  80%|########  | 7.99G/9.97G [00:31<00:08, 221MB/s]
transformer/diffusion_pytorch_model-0000(…):  80%|########  | 7.99G/9.97G [00:31<00:08, 221MB/s]
transformer/diffusion_pytorch_model-0000(…):  81%|########  | 8.05G/9.97G [00:32<00:08, 221MB/s]
transformer/diffusion_pytorch_model-0000(…):  81%|########  | 8.05G/9.97G [00:32<00:08, 221MB/s]
transformer/diffusion_pytorch_model-0000(…):  81%|########1 | 8.12G/9.97G [00:32<00:08, 222MB/s]
transformer/diffusion_pytorch_model-0000(…):  81%|########1 | 8.12G/9.97G [00:32<00:08, 222MB/s]
transformer/diffusion_pytorch_model-0000(…):  82%|########2 | 8.19G/9.97G [00:32<00:08, 215MB/s]
transformer/diffusion_pytorch_model-0000(…):  82%|########2 | 8.19G/9.97G [00:32<00:08, 215MB/s]
transformer/diffusion_pytorch_model-0000(…):  83%|########2 | 8.25G/9.97G [00:32<00:07, 215MB/s]
transformer/diffusion_pytorch_model-0000(…):  83%|########2 | 8.25G/9.97G [00:32<00:07, 215MB/s]
transformer/diffusion_pytorch_model-0000(…):  83%|########3 | 8.32G/9.97G [00:33<00:07, 222MB/s]
transformer/diffusion_pytorch_model-0000(…):  83%|########3 | 8.32G/9.97G [00:33<00:07, 222MB/s]
transformer/diffusion_pytorch_model-0000(…):  84%|########4 | 8.39G/9.97G [00:33<00:07, 226MB/s]
transformer/diffusion_pytorch_model-0000(…):  84%|########4 | 8.39G/9.97G [00:33<00:07, 226MB/s]
transformer/diffusion_pytorch_model-0000(…):  85%|########5 | 8.52G/9.97G [00:33<00:05, 258MB/s]
transformer/diffusion_pytorch_model-0000(…):  85%|########5 | 8.52G/9.97G [00:33<00:05, 258MB/s]
transformer/diffusion_pytorch_model-0000(…):  86%|########6 | 8.59G/9.97G [00:34<00:05, 256MB/s]
transformer/diffusion_pytorch_model-0000(…):  86%|########6 | 8.59G/9.97G [00:34<00:05, 256MB/s]
transformer/diffusion_pytorch_model-0000(…):  87%|########6 | 8.66G/9.97G [00:34<00:05, 256MB/s]
transformer/diffusion_pytorch_model-0000(…):  87%|########6 | 8.66G/9.97G [00:34<00:05, 256MB/s]
transformer/diffusion_pytorch_model-0000(…):  87%|########7 | 8.70G/9.97G [00:34<00:06, 211MB/s]
transformer/diffusion_pytorch_model-0000(…):  87%|########7 | 8.70G/9.97G [00:34<00:06, 211MB/s]
transformer/diffusion_pytorch_model-0000(…):  88%|########7 | 8.77G/9.97G [00:35<00:05, 203MB/s]
transformer/diffusion_pytorch_model-0000(…):  88%|########7 | 8.77G/9.97G [00:35<00:05, 203MB/s]
transformer/diffusion_pytorch_model-0000(…):  89%|########8 | 8.84G/9.97G [00:35<00:05, 207MB/s]
transformer/diffusion_pytorch_model-0000(…):  89%|########8 | 8.84G/9.97G [00:35<00:05, 207MB/s]
transformer/diffusion_pytorch_model-0000(…):  89%|########9 | 8.91G/9.97G [00:35<00:05, 210MB/s]
transformer/diffusion_pytorch_model-0000(…):  89%|########9 | 8.91G/9.97G [00:35<00:05, 210MB/s]
transformer/diffusion_pytorch_model-0000(…):  90%|########9 | 8.97G/9.97G [00:36<00:04, 217MB/s]
transformer/diffusion_pytorch_model-0000(…):  90%|########9 | 8.97G/9.97G [00:36<00:04, 217MB/s]
transformer/diffusion_pytorch_model-0000(…):  91%|######### | 9.04G/9.97G [00:36<00:04, 219MB/s]
transformer/diffusion_pytorch_model-0000(…):  91%|######### | 9.04G/9.97G [00:36<00:04, 219MB/s]
transformer/diffusion_pytorch_model-0000(…):  91%|#########1| 9.11G/9.97G [00:36<00:03, 224MB/s]
transformer/diffusion_pytorch_model-0000(…):  91%|#########1| 9.11G/9.97G [00:36<00:03, 224MB/s]
transformer/diffusion_pytorch_model-0000(…):  92%|#########1| 9.17G/9.97G [00:36<00:02, 274MB/s]
transformer/diffusion_pytorch_model-0000(…):  92%|#########1| 9.17G/9.97G [00:36<00:02, 274MB/s]
transformer/diffusion_pytorch_model-0000(…):  93%|#########2| 9.24G/9.97G [00:37<00:02, 271MB/s]
transformer/diffusion_pytorch_model-0000(…):  93%|#########2| 9.24G/9.97G [00:37<00:02, 271MB/s]
transformer/diffusion_pytorch_model-0000(…):  93%|#########3| 9.30G/9.97G [00:37<00:02, 261MB/s]
transformer/diffusion_pytorch_model-0000(…):  93%|#########3| 9.30G/9.97G [00:37<00:02, 261MB/s]
transformer/diffusion_pytorch_model-0000(…):  94%|#########3| 9.37G/9.97G [00:37<00:02, 258MB/s]
transformer/diffusion_pytorch_model-0000(…):  94%|#########3| 9.37G/9.97G [00:37<00:02, 258MB/s]
transformer/diffusion_pytorch_model-0000(…):  95%|#########4| 9.44G/9.97G [00:37<00:02, 249MB/s]
transformer/diffusion_pytorch_model-0000(…):  95%|#########4| 9.44G/9.97G [00:37<00:02, 249MB/s]
transformer/diffusion_pytorch_model-0000(…):  95%|#########5| 9.50G/9.97G [00:38<00:01, 246MB/s]
transformer/diffusion_pytorch_model-0000(…):  95%|#########5| 9.50G/9.97G [00:38<00:01, 246MB/s]
transformer/diffusion_pytorch_model-0000(…):  96%|#########5| 9.57G/9.97G [00:38<00:01, 247MB/s]
transformer/diffusion_pytorch_model-0000(…):  96%|#########5| 9.57G/9.97G [00:38<00:01, 247MB/s]
transformer/diffusion_pytorch_model-0000(…):  97%|#########6| 9.64G/9.97G [00:38<00:01, 241MB/s]
transformer/diffusion_pytorch_model-0000(…):  97%|#########6| 9.64G/9.97G [00:38<00:01, 241MB/s]
transformer/diffusion_pytorch_model-0000(…):  98%|#########7| 9.77G/9.97G [00:39<00:00, 295MB/s]
transformer/diffusion_pytorch_model-0000(…):  98%|#########7| 9.77G/9.97G [00:39<00:00, 295MB/s]
transformer/diffusion_pytorch_model-0000(…):  99%|#########8| 9.84G/9.97G [00:39<00:00, 281MB/s]
transformer/diffusion_pytorch_model-0000(…):  99%|#########8| 9.84G/9.97G [00:39<00:00, 281MB/s]
transformer/diffusion_pytorch_model-0000(…):  99%|#########9| 9.91G/9.97G [00:39<00:00, 270MB/s]
transformer/diffusion_pytorch_model-0000(…):  99%|#########9| 9.91G/9.97G [00:39<00:00, 270MB/s]
transformer/diffusion_pytorch_model-0000(…): 100%|##########| 9.97G/9.97G [00:39<00:00, 261MB/s]
transformer/diffusion_pytorch_model-0000(…): 100%|##########| 9.97G/9.97G [00:39<00:00, 261MB/s]
transformer/diffusion_pytorch_model-0000(…): 100%|##########| 9.97G/9.97G [00:39<00:00, 250MB/s]
transformer/diffusion_pytorch_model-0000(…): 100%|##########| 9.97G/9.97G [00:39<00:00, 250MB/s]


transformer/diffusion_pytorch_model-0000(…):   0%|          | 0.00/4.67G [00:00<?, ?B/s]
transformer/diffusion_pytorch_model-0000(…):   0%|          | 0.00/4.67G [00:00<?, ?B/s]
transformer/diffusion_pytorch_model-0000(…):   0%|          | 925k/4.67G [00:00<44:54, 1.73MB/s]
transformer/diffusion_pytorch_model-0000(…):   0%|          | 925k/4.67G [00:00<44:54, 1.73MB/s]
transformer/diffusion_pytorch_model-0000(…):   1%|1         | 68.0M/4.67G [00:00<00:41, 110MB/s]
transformer/diffusion_pytorch_model-0000(…):   1%|1         | 68.0M/4.67G [00:00<00:41, 110MB/s]
transformer/diffusion_pytorch_model-0000(…):   4%|4         | 202M/4.67G [00:01<00:21, 209MB/s] 
transformer/diffusion_pytorch_model-0000(…):   4%|4         | 202M/4.67G [00:01<00:21, 209MB/s] 
transformer/diffusion_pytorch_model-0000(…):   6%|5         | 269M/4.67G [00:01<00:24, 182MB/s]
transformer/diffusion_pytorch_model-0000(…):   6%|5         | 269M/4.67G [00:01<00:24, 182MB/s]
transformer/diffusion_pytorch_model-0000(…):   7%|7         | 336M/4.67G [00:02<00:23, 182MB/s]
transformer/diffusion_pytorch_model-0000(…):   7%|7         | 336M/4.67G [00:02<00:23, 182MB/s]
transformer/diffusion_pytorch_model-0000(…):   9%|8         | 403M/4.67G [00:02<00:22, 186MB/s]
transformer/diffusion_pytorch_model-0000(…):   9%|8         | 403M/4.67G [00:02<00:22, 186MB/s]
transformer/diffusion_pytorch_model-0000(…):  10%|#         | 470M/4.67G [00:02<00:22, 190MB/s]
transformer/diffusion_pytorch_model-0000(…):  10%|#         | 470M/4.67G [00:02<00:22, 190MB/s]
transformer/diffusion_pytorch_model-0000(…):  12%|#1        | 537M/4.67G [00:03<00:22, 185MB/s]
transformer/diffusion_pytorch_model-0000(…):  12%|#1        | 537M/4.67G [00:03<00:22, 185MB/s]
transformer/diffusion_pytorch_model-0000(…):  13%|#2        | 607M/4.67G [00:03<00:23, 170MB/s]
transformer/diffusion_pytorch_model-0000(…):  13%|#2        | 607M/4.67G [00:03<00:23, 170MB/s]
transformer/diffusion_pytorch_model-0000(…):  14%|#4        | 674M/4.67G [00:04<00:25, 159MB/s]
transformer/diffusion_pytorch_model-0000(…):  14%|#4        | 674M/4.67G [00:04<00:25, 159MB/s]
transformer/diffusion_pytorch_model-0000(…):  16%|#5        | 742M/4.67G [00:04<00:24, 159MB/s]
transformer/diffusion_pytorch_model-0000(…):  16%|#5        | 742M/4.67G [00:04<00:24, 159MB/s]
transformer/diffusion_pytorch_model-0000(…):  17%|#7        | 809M/4.67G [00:04<00:24, 155MB/s]
transformer/diffusion_pytorch_model-0000(…):  17%|#7        | 809M/4.67G [00:04<00:24, 155MB/s]
transformer/diffusion_pytorch_model-0000(…):  19%|#8        | 876M/4.67G [00:05<00:23, 164MB/s]
transformer/diffusion_pytorch_model-0000(…):  19%|#8        | 876M/4.67G [00:05<00:23, 164MB/s]
transformer/diffusion_pytorch_model-0000(…):  20%|##        | 943M/4.67G [00:05<00:22, 166MB/s]
transformer/diffusion_pytorch_model-0000(…):  20%|##        | 943M/4.67G [00:05<00:22, 166MB/s]
transformer/diffusion_pytorch_model-0000(…):  22%|##1       | 1.01G/4.67G [00:06<00:22, 166MB/s]
transformer/diffusion_pytorch_model-0000(…):  22%|##1       | 1.01G/4.67G [00:06<00:22, 166MB/s]
transformer/diffusion_pytorch_model-0000(…):  23%|##3       | 1.08G/4.67G [00:06<00:20, 171MB/s]
transformer/diffusion_pytorch_model-0000(…):  23%|##3       | 1.08G/4.67G [00:06<00:20, 171MB/s]
transformer/diffusion_pytorch_model-0000(…):  24%|##4       | 1.14G/4.67G [00:06<00:20, 175MB/s]
transformer/diffusion_pytorch_model-0000(…):  24%|##4       | 1.14G/4.67G [00:06<00:20, 175MB/s]
transformer/diffusion_pytorch_model-0000(…):  26%|##5       | 1.21G/4.67G [00:07<00:18, 183MB/s]
transformer/diffusion_pytorch_model-0000(…):  26%|##5       | 1.21G/4.67G [00:07<00:18, 183MB/s]
transformer/diffusion_pytorch_model-0000(…):  27%|##7       | 1.28G/4.67G [00:07<00:18, 183MB/s]
transformer/diffusion_pytorch_model-0000(…):  27%|##7       | 1.28G/4.67G [00:07<00:18, 183MB/s]
transformer/diffusion_pytorch_model-0000(…):  29%|##8       | 1.35G/4.67G [00:07<00:18, 182MB/s]
transformer/diffusion_pytorch_model-0000(…):  29%|##8       | 1.35G/4.67G [00:07<00:18, 182MB/s]
transformer/diffusion_pytorch_model-0000(…):  30%|###       | 1.41G/4.67G [00:08<00:17, 183MB/s]
transformer/diffusion_pytorch_model-0000(…):  30%|###       | 1.41G/4.67G [00:08<00:17, 183MB/s]
transformer/diffusion_pytorch_model-0000(…):  32%|###1      | 1.48G/4.67G [00:08<00:17, 187MB/s]
transformer/diffusion_pytorch_model-0000(…):  32%|###1      | 1.48G/4.67G [00:08<00:17, 187MB/s]
transformer/diffusion_pytorch_model-0000(…):  33%|###3      | 1.55G/4.67G [00:08<00:16, 191MB/s]
transformer/diffusion_pytorch_model-0000(…):  33%|###3      | 1.55G/4.67G [00:08<00:16, 191MB/s]
transformer/diffusion_pytorch_model-0000(…):  35%|###4      | 1.61G/4.67G [00:09<00:15, 193MB/s]
transformer/diffusion_pytorch_model-0000(…):  35%|###4      | 1.61G/4.67G [00:09<00:15, 193MB/s]
transformer/diffusion_pytorch_model-0000(…):  36%|###5      | 1.68G/4.67G [00:09<00:15, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  36%|###5      | 1.68G/4.67G [00:09<00:15, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  37%|###7      | 1.75G/4.67G [00:09<00:14, 196MB/s]
transformer/diffusion_pytorch_model-0000(…):  37%|###7      | 1.75G/4.67G [00:09<00:14, 196MB/s]
transformer/diffusion_pytorch_model-0000(…):  39%|###8      | 1.82G/4.67G [00:10<00:14, 198MB/s]
transformer/diffusion_pytorch_model-0000(…):  39%|###8      | 1.82G/4.67G [00:10<00:14, 198MB/s]
transformer/diffusion_pytorch_model-0000(…):  40%|####      | 1.88G/4.67G [00:10<00:14, 193MB/s]
transformer/diffusion_pytorch_model-0000(…):  40%|####      | 1.88G/4.67G [00:10<00:14, 193MB/s]
transformer/diffusion_pytorch_model-0000(…):  42%|####1     | 1.95G/4.67G [00:10<00:13, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  42%|####1     | 1.95G/4.67G [00:10<00:13, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  43%|####3     | 2.02G/4.67G [00:11<00:15, 172MB/s]
transformer/diffusion_pytorch_model-0000(…):  43%|####3     | 2.02G/4.67G [00:11<00:15, 172MB/s]
transformer/diffusion_pytorch_model-0000(…):  45%|####4     | 2.09G/4.67G [00:11<00:15, 163MB/s]
transformer/diffusion_pytorch_model-0000(…):  45%|####4     | 2.09G/4.67G [00:11<00:15, 163MB/s]
transformer/diffusion_pytorch_model-0000(…):  46%|####6     | 2.15G/4.67G [00:12<00:14, 173MB/s]
transformer/diffusion_pytorch_model-0000(…):  46%|####6     | 2.15G/4.67G [00:12<00:14, 173MB/s]
transformer/diffusion_pytorch_model-0000(…):  48%|####7     | 2.22G/4.67G [00:12<00:13, 176MB/s]
transformer/diffusion_pytorch_model-0000(…):  48%|####7     | 2.22G/4.67G [00:12<00:13, 176MB/s]
transformer/diffusion_pytorch_model-0000(…):  49%|####8     | 2.29G/4.67G [00:12<00:12, 184MB/s]
transformer/diffusion_pytorch_model-0000(…):  49%|####8     | 2.29G/4.67G [00:12<00:12, 184MB/s]
transformer/diffusion_pytorch_model-0000(…):  50%|#####     | 2.35G/4.67G [00:13<00:12, 190MB/s]
transformer/diffusion_pytorch_model-0000(…):  50%|#####     | 2.35G/4.67G [00:13<00:12, 190MB/s]
transformer/diffusion_pytorch_model-0000(…):  52%|#####1    | 2.42G/4.67G [00:13<00:11, 194MB/s]
transformer/diffusion_pytorch_model-0000(…):  52%|#####1    | 2.42G/4.67G [00:13<00:11, 194MB/s]
transformer/diffusion_pytorch_model-0000(…):  53%|#####3    | 2.49G/4.67G [00:13<00:11, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  53%|#####3    | 2.49G/4.67G [00:13<00:11, 197MB/s]
transformer/diffusion_pytorch_model-0000(…):  55%|#####4    | 2.56G/4.67G [00:14<00:10, 201MB/s]
transformer/diffusion_pytorch_model-0000(…):  55%|#####4    | 2.56G/4.67G [00:14<00:10, 201MB/s]
transformer/diffusion_pytorch_model-0000(…):  56%|#####6    | 2.62G/4.67G [00:14<00:09, 205MB/s]
transformer/diffusion_pytorch_model-0000(…):  56%|#####6    | 2.62G/4.67G [00:14<00:09, 205MB/s]
transformer/diffusion_pytorch_model-0000(…):  58%|#####7    | 2.69G/4.67G [00:14<00:09, 210MB/s]
transformer/diffusion_pytorch_model-0000(…):  58%|#####7    | 2.69G/4.67G [00:14<00:09, 210MB/s]
transformer/diffusion_pytorch_model-0000(…):  59%|#####9    | 2.76G/4.67G [00:15<00:09, 208MB/s]
transformer/diffusion_pytorch_model-0000(…):  59%|#####9    | 2.76G/4.67G [00:15<00:09, 208MB/s]
transformer/diffusion_pytorch_model-0000(…):  60%|######    | 2.82G/4.67G [00:15<00:08, 208MB/s]
transformer/diffusion_pytorch_model-0000(…):  60%|######    | 2.82G/4.67G [00:15<00:08, 208MB/s]
transformer/diffusion_pytorch_model-0000(…):  62%|######1   | 2.89G/4.67G [00:15<00:08, 209MB/s]
transformer/diffusion_pytorch_model-0000(…):  62%|######1   | 2.89G/4.67G [00:15<00:08, 209MB/s]
transformer/diffusion_pytorch_model-0000(…):  63%|######3   | 2.96G/4.67G [00:16<00:08, 212MB/s]
transformer/diffusion_pytorch_model-0000(…):  63%|######3   | 2.96G/4.67G [00:16<00:08, 212MB/s]
transformer/diffusion_pytorch_model-0000(…):  65%|######4   | 3.03G/4.67G [00:16<00:07, 214MB/s]
transformer/diffusion_pytorch_model-0000(…):  65%|######4   | 3.03G/4.67G [00:16<00:07, 214MB/s]
transformer/diffusion_pytorch_model-0000(…):  66%|######6   | 3.09G/4.67G [00:16<00:07, 218MB/s]
transformer/diffusion_pytorch_model-0000(…):  66%|######6   | 3.09G/4.67G [00:16<00:07, 218MB/s]
transformer/diffusion_pytorch_model-0000(…):  68%|######7   | 3.16G/4.67G [00:17<00:06, 225MB/s]
transformer/diffusion_pytorch_model-0000(…):  68%|######7   | 3.16G/4.67G [00:17<00:06, 225MB/s]
transformer/diffusion_pytorch_model-0000(…):  69%|######8   | 3.20G/4.67G [00:17<00:06, 233MB/s]
transformer/diffusion_pytorch_model-0000(…):  69%|######8   | 3.20G/4.67G [00:17<00:06, 233MB/s]
transformer/diffusion_pytorch_model-0000(…):  70%|######9   | 3.27G/4.67G [00:17<00:05, 239MB/s]
transformer/diffusion_pytorch_model-0000(…):  70%|######9   | 3.27G/4.67G [00:17<00:05, 239MB/s]
transformer/diffusion_pytorch_model-0000(…):  71%|#######1  | 3.34G/4.67G [00:17<00:05, 241MB/s]
transformer/diffusion_pytorch_model-0000(…):  71%|#######1  | 3.34G/4.67G [00:17<00:05, 241MB/s]
transformer/diffusion_pytorch_model-0000(…):  73%|#######2  | 3.40G/4.67G [00:18<00:05, 231MB/s]
transformer/diffusion_pytorch_model-0000(…):  73%|#######2  | 3.40G/4.67G [00:18<00:05, 231MB/s]
transformer/diffusion_pytorch_model-0000(…):  74%|#######4  | 3.47G/4.67G [00:18<00:05, 226MB/s]
transformer/diffusion_pytorch_model-0000(…):  74%|#######4  | 3.47G/4.67G [00:18<00:05, 226MB/s]
transformer/diffusion_pytorch_model-0000(…):  76%|#######5  | 3.54G/4.67G [00:18<00:04, 231MB/s]
transformer/diffusion_pytorch_model-0000(…):  76%|#######5  | 3.54G/4.67G [00:18<00:04, 231MB/s]
transformer/diffusion_pytorch_model-0000(…):  77%|#######7  | 3.60G/4.67G [00:18<00:04, 237MB/s]
transformer/diffusion_pytorch_model-0000(…):  77%|#######7  | 3.60G/4.67G [00:18<00:04, 237MB/s]
transformer/diffusion_pytorch_model-0000(…):  79%|#######8  | 3.67G/4.67G [00:19<00:04, 232MB/s]
transformer/diffusion_pytorch_model-0000(…):  79%|#######8  | 3.67G/4.67G [00:19<00:04, 232MB/s]
transformer/diffusion_pytorch_model-0000(…):  80%|#######9  | 3.74G/4.67G [00:19<00:03, 238MB/s]
transformer/diffusion_pytorch_model-0000(…):  80%|#######9  | 3.74G/4.67G [00:19<00:03, 238MB/s]
transformer/diffusion_pytorch_model-0000(…):  81%|########1 | 3.80G/4.67G [00:19<00:03, 234MB/s]
transformer/diffusion_pytorch_model-0000(…):  81%|########1 | 3.80G/4.67G [00:19<00:03, 234MB/s]
transformer/diffusion_pytorch_model-0000(…):  83%|########2 | 3.87G/4.67G [00:20<00:03, 221MB/s]
transformer/diffusion_pytorch_model-0000(…):  83%|########2 | 3.87G/4.67G [00:20<00:03, 221MB/s]
transformer/diffusion_pytorch_model-0000(…):  84%|########4 | 3.94G/4.67G [00:20<00:03, 222MB/s]
transformer/diffusion_pytorch_model-0000(…):  84%|########4 | 3.94G/4.67G [00:20<00:03, 222MB/s]
transformer/diffusion_pytorch_model-0000(…):  86%|########5 | 4.00G/4.67G [00:20<00:02, 224MB/s]
transformer/diffusion_pytorch_model-0000(…):  86%|########5 | 4.00G/4.67G [00:20<00:02, 224MB/s]
transformer/diffusion_pytorch_model-0000(…):  87%|########7 | 4.07G/4.67G [00:20<00:02, 229MB/s]
transformer/diffusion_pytorch_model-0000(…):  87%|########7 | 4.07G/4.67G [00:20<00:02, 229MB/s]
transformer/diffusion_pytorch_model-0000(…):  89%|########8 | 4.14G/4.67G [00:21<00:02, 235MB/s]
transformer/diffusion_pytorch_model-0000(…):  89%|########8 | 4.14G/4.67G [00:21<00:02, 235MB/s]
transformer/diffusion_pytorch_model-0000(…):  90%|########9 | 4.20G/4.67G [00:21<00:02, 231MB/s]
transformer/diffusion_pytorch_model-0000(…):  90%|########9 | 4.20G/4.67G [00:21<00:02, 231MB/s]
transformer/diffusion_pytorch_model-0000(…):  91%|#########1| 4.27G/4.67G [00:21<00:01, 235MB/s]
transformer/diffusion_pytorch_model-0000(…):  91%|#########1| 4.27G/4.67G [00:21<00:01, 235MB/s]
transformer/diffusion_pytorch_model-0000(…):  93%|#########2| 4.34G/4.67G [00:22<00:01, 239MB/s]
transformer/diffusion_pytorch_model-0000(…):  93%|#########2| 4.34G/4.67G [00:22<00:01, 239MB/s]
transformer/diffusion_pytorch_model-0000(…):  94%|#########4| 4.40G/4.67G [00:22<00:01, 237MB/s]
transformer/diffusion_pytorch_model-0000(…):  94%|#########4| 4.40G/4.67G [00:22<00:01, 237MB/s]
transformer/diffusion_pytorch_model-0000(…):  96%|#########5| 4.47G/4.67G [00:22<00:00, 239MB/s]
transformer/diffusion_pytorch_model-0000(…):  96%|#########5| 4.47G/4.67G [00:22<00:00, 239MB/s]
transformer/diffusion_pytorch_model-0000(…):  97%|#########7| 4.54G/4.67G [00:22<00:00, 295MB/s]
transformer/diffusion_pytorch_model-0000(…):  97%|#########7| 4.54G/4.67G [00:22<00:00, 295MB/s]
transformer/diffusion_pytorch_model-0000(…):  99%|#########8| 4.61G/4.67G [00:22<00:00, 286MB/s]
transformer/diffusion_pytorch_model-0000(…):  99%|#########8| 4.61G/4.67G [00:22<00:00, 286MB/s]
transformer/diffusion_pytorch_model-0000(…): 100%|##########| 4.67G/4.67G [00:23<00:00, 275MB/s]
transformer/diffusion_pytorch_model-0000(…): 100%|##########| 4.67G/4.67G [00:23<00:00, 275MB/s]
transformer/diffusion_pytorch_model-0000(…): 100%|##########| 4.67G/4.67G [00:23<00:00, 201MB/s]
transformer/diffusion_pytorch_model-0000(…): 100%|##########| 4.67G/4.67G [00:23<00:00, 201MB/s]


Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:  33%|###3      | 1/3 [00:01<00:02,  1.28s/it]
Loading checkpoint shards:  33%|###3      | 1/3 [00:01<00:02,  1.28s/it]
Loading checkpoint shards:  67%|######6   | 2/3 [00:02<00:01,  1.28s/it]
Loading checkpoint shards:  67%|######6   | 2/3 [00:02<00:01,  1.28s/it]
Loading checkpoint shards: 100%|##########| 3/3 [00:03<00:00,  1.04it/s]
Loading checkpoint shards: 100%|##########| 3/3 [00:03<00:00,  1.04it/s]
Loading checkpoint shards: 100%|##########| 3/3 [00:03<00:00,  1.05s/it]
Loading checkpoint shards: 100%|##########| 3/3 [00:03<00:00,  1.05s/it]

Loading assistant LoRA

zimage_turbo_training_adapter_v2.safeten(…):   0%|          | 0.00/340M [00:00<?, ?B/s]
zimage_turbo_training_adapter_v2.safeten(…):   0%|          | 0.00/340M [00:00<?, ?B/s]
zimage_turbo_training_adapter_v2.safeten(…):  17%|#6        | 56.3M/340M [00:01<00:05, 55.3MB/s]
zimage_turbo_training_adapter_v2.safeten(…):  17%|#6        | 56.3M/340M [00:01<00:05, 55.3MB/s]
zimage_turbo_training_adapter_v2.safeten(…):  54%|#####3    | 182M/340M [00:01<00:01, 100MB/s]  
zimage_turbo_training_adapter_v2.safeten(…):  54%|#####3    | 182M/340M [00:01<00:01, 100MB/s]  
zimage_turbo_training_adapter_v2.safeten(…): 100%|##########| 340M/340M [00:02<00:00, 164MB/s]
zimage_turbo_training_adapter_v2.safeten(…): 100%|##########| 340M/340M [00:02<00:00, 164MB/s]
zimage_turbo_training_adapter_v2.safeten(…): 100%|##########| 340M/340M [00:02<00:00, 138MB/s]
zimage_turbo_training_adapter_v2.safeten(…): 100%|##########| 340M/340M [00:02<00:00, 138MB/s]

create LoRA network. base dim (rank): 64, alpha: 64
neuron dropout: p=None, rank dropout: p=None, module dropout: p=None
create LoRA for Text Encoder: 0 modules.
create LoRA for U-Net: 276 modules.
enable LoRA for U-Net
Merging in assistant LoRA
Missing keys: []
Quantizing Transformer
 - quantizing 30 transformer blocks

  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|3         | 1/30 [00:00<00:04,  7.02it/s]
  3%|3         | 1/30 [00:00<00:04,  7.02it/s]
 10%|#         | 3/30 [00:00<00:02, 11.88it/s]
 10%|#         | 3/30 [00:00<00:02, 11.88it/s]
 17%|#6        | 5/30 [00:00<00:01, 13.57it/s]
 17%|#6        | 5/30 [00:00<00:01, 13.57it/s]
 23%|##3       | 7/30 [00:00<00:01, 14.39it/s]
 23%|##3       | 7/30 [00:00<00:01, 14.39it/s]
 30%|###       | 9/30 [00:00<00:01, 13.80it/s]
 30%|###       | 9/30 [00:00<00:01, 13.80it/s]
 37%|###6      | 11/30 [00:00<00:01, 12.04it/s]
 37%|###6      | 11/30 [00:00<00:01, 12.04it/s]
 43%|####3     | 13/30 [00:01<00:01, 11.18it/s]
 43%|####3     | 13/30 [00:01<00:01, 11.18it/s]
 50%|#####     | 15/30 [00:01<00:01, 10.66it/s]
 50%|#####     | 15/30 [00:01<00:01, 10.66it/s]
 57%|#####6    | 17/30 [00:01<00:01, 10.34it/s]
 57%|#####6    | 17/30 [00:01<00:01, 10.34it/s]
 63%|######3   | 19/30 [00:01<00:01, 10.15it/s]
 63%|######3   | 19/30 [00:01<00:01, 10.15it/s]
 70%|#######   | 21/30 [00:01<00:00,  9.78it/s]
 70%|#######   | 21/30 [00:01<00:00,  9.78it/s]
 73%|#######3  | 22/30 [00:02<00:00,  9.43it/s]
 73%|#######3  | 22/30 [00:02<00:00,  9.43it/s]
 80%|########  | 24/30 [00:02<00:00,  9.54it/s]
 80%|########  | 24/30 [00:02<00:00,  9.54it/s]
 87%|########6 | 26/30 [00:02<00:00,  9.77it/s]
 87%|########6 | 26/30 [00:02<00:00,  9.77it/s]
 90%|######### | 27/30 [00:02<00:00,  9.53it/s]
 90%|######### | 27/30 [00:02<00:00,  9.53it/s]
 93%|#########3| 28/30 [00:02<00:00,  9.43it/s]
 93%|#########3| 28/30 [00:02<00:00,  9.43it/s]
100%|##########| 30/30 [00:02<00:00,  9.55it/s]
100%|##########| 30/30 [00:02<00:00,  9.55it/s]
100%|##########| 30/30 [00:02<00:00, 10.41it/s]
100%|##########| 30/30 [00:02<00:00, 10.41it/s]

 - quantizing extras
Text Encoder

tokenizer_config.json: 0.00B [00:00, ?B/s]
tokenizer_config.json: 0.00B [00:00, ?B/s]
tokenizer_config.json: 9.73kB [00:00, 17.8MB/s]
tokenizer_config.json: 9.73kB [00:00, 17.8MB/s]


vocab.json: 0.00B [00:00, ?B/s]
vocab.json: 0.00B [00:00, ?B/s]
vocab.json: 2.78MB [00:00, 210MB/s]
vocab.json: 2.78MB [00:00, 210MB/s]


merges.txt: 0.00B [00:00, ?B/s]
merges.txt: 0.00B [00:00, ?B/s]
merges.txt: 1.67MB [00:00, 239MB/s]
merges.txt: 1.67MB [00:00, 239MB/s]


tokenizer/tokenizer.json:   0%|          | 0.00/11.4M [00:00<?, ?B/s]
tokenizer/tokenizer.json:   0%|          | 0.00/11.4M [00:00<?, ?B/s]
tokenizer/tokenizer.json: 100%|##########| 11.4M/11.4M [00:00<00:00, 88.4MB/s]
tokenizer/tokenizer.json: 100%|##########| 11.4M/11.4M [00:00<00:00, 88.4MB/s]
tokenizer/tokenizer.json: 100%|##########| 11.4M/11.4M [00:00<00:00, 88.0MB/s]
tokenizer/tokenizer.json: 100%|##########| 11.4M/11.4M [00:00<00:00, 88.0MB/s]

`torch_dtype` is deprecated! Use `dtype` instead!
`torch_dtype` is deprecated! Use `dtype` instead!

config.json:   0%|          | 0.00/726 [00:00<?, ?B/s]
config.json:   0%|          | 0.00/726 [00:00<?, ?B/s]
config.json: 100%|##########| 726/726 [00:00<00:00, 7.07MB/s]
config.json: 100%|##########| 726/726 [00:00<00:00, 7.07MB/s]


model.safetensors.index.json: 0.00B [00:00, ?B/s]
model.safetensors.index.json: 0.00B [00:00, ?B/s]
model.safetensors.index.json: 32.8kB [00:00, 136MB/s]
model.safetensors.index.json: 32.8kB [00:00, 136MB/s]


text_encoder/model-00001-of-00003.safete(…):   0%|          | 0.00/3.96G [00:00<?, ?B/s]
text_encoder/model-00001-of-00003.safete(…):   0%|          | 0.00/3.96G [00:00<?, ?B/s]
text_encoder/model-00001-of-00003.safete(…):   1%|1         | 40.2M/3.96G [00:00<00:51, 76.2MB/s]
text_encoder/model-00001-of-00003.safete(…):   1%|1         | 40.2M/3.96G [00:00<00:51, 76.2MB/s]
text_encoder/model-00001-of-00003.safete(…):   3%|2         | 107M/3.96G [00:00<00:27, 139MB/s]  
text_encoder/model-00001-of-00003.safete(…):   3%|2         | 107M/3.96G [00:00<00:27, 139MB/s]  
text_encoder/model-00001-of-00003.safete(…):   4%|4         | 174M/3.96G [00:01<00:19, 191MB/s]
text_encoder/model-00001-of-00003.safete(…):   4%|4         | 174M/3.96G [00:01<00:19, 191MB/s]
text_encoder/model-00001-of-00003.safete(…):   6%|6         | 241M/3.96G [00:01<00:15, 246MB/s]
text_encoder/model-00001-of-00003.safete(…):   6%|6         | 241M/3.96G [00:01<00:15, 246MB/s]
text_encoder/model-00001-of-00003.safete(…):  12%|#1        | 470M/3.96G [00:01<00:05, 597MB/s]
text_encoder/model-00001-of-00003.safete(…):  12%|#1        | 470M/3.96G [00:01<00:05, 597MB/s]
text_encoder/model-00001-of-00003.safete(…):  14%|#4        | 566M/3.96G [00:01<00:05, 570MB/s]
text_encoder/model-00001-of-00003.safete(…):  14%|#4        | 566M/3.96G [00:01<00:05, 570MB/s]
text_encoder/model-00001-of-00003.safete(…):  18%|#7        | 700M/3.96G [00:01<00:06, 522MB/s]
text_encoder/model-00001-of-00003.safete(…):  18%|#7        | 700M/3.96G [00:01<00:06, 522MB/s]
text_encoder/model-00001-of-00003.safete(…):  22%|##2       | 874M/3.96G [00:02<00:04, 625MB/s]
text_encoder/model-00001-of-00003.safete(…):  22%|##2       | 874M/3.96G [00:02<00:04, 625MB/s]
text_encoder/model-00001-of-00003.safete(…):  25%|##5       | 1.01G/3.96G [00:02<00:04, 631MB/s]
text_encoder/model-00001-of-00003.safete(…):  25%|##5       | 1.01G/3.96G [00:02<00:04, 631MB/s]
text_encoder/model-00001-of-00003.safete(…):  29%|##8       | 1.14G/3.96G [00:02<00:04, 704MB/s]
text_encoder/model-00001-of-00003.safete(…):  29%|##8       | 1.14G/3.96G [00:02<00:04, 704MB/s]
text_encoder/model-00001-of-00003.safete(…):  32%|###2      | 1.28G/3.96G [00:02<00:03, 695MB/s]
text_encoder/model-00001-of-00003.safete(…):  32%|###2      | 1.28G/3.96G [00:02<00:03, 695MB/s]
text_encoder/model-00001-of-00003.safete(…):  36%|###5      | 1.41G/3.96G [00:02<00:03, 671MB/s]
text_encoder/model-00001-of-00003.safete(…):  36%|###5      | 1.41G/3.96G [00:02<00:03, 671MB/s]
text_encoder/model-00001-of-00003.safete(…):  39%|###9      | 1.54G/3.96G [00:02<00:03, 733MB/s]
text_encoder/model-00001-of-00003.safete(…):  39%|###9      | 1.54G/3.96G [00:02<00:03, 733MB/s]
text_encoder/model-00001-of-00003.safete(…):  42%|####2     | 1.68G/3.96G [00:03<00:02, 786MB/s]
text_encoder/model-00001-of-00003.safete(…):  42%|####2     | 1.68G/3.96G [00:03<00:02, 786MB/s]
text_encoder/model-00001-of-00003.safete(…):  47%|####7     | 1.88G/3.96G [00:03<00:02, 770MB/s]
text_encoder/model-00001-of-00003.safete(…):  47%|####7     | 1.88G/3.96G [00:03<00:02, 770MB/s]
text_encoder/model-00001-of-00003.safete(…):  50%|#####     | 1.98G/3.96G [00:03<00:03, 594MB/s]
text_encoder/model-00001-of-00003.safete(…):  50%|#####     | 1.98G/3.96G [00:03<00:03, 594MB/s]
text_encoder/model-00001-of-00003.safete(…):  53%|#####2    | 2.08G/3.96G [00:03<00:03, 521MB/s]
text_encoder/model-00001-of-00003.safete(…):  53%|#####2    | 2.08G/3.96G [00:03<00:03, 521MB/s]
text_encoder/model-00001-of-00003.safete(…):  54%|#####4    | 2.15G/3.96G [00:04<00:04, 452MB/s]
text_encoder/model-00001-of-00003.safete(…):  54%|#####4    | 2.15G/3.96G [00:04<00:04, 452MB/s]
text_encoder/model-00001-of-00003.safete(…):  56%|#####5    | 2.21G/3.96G [00:04<00:04, 406MB/s]
text_encoder/model-00001-of-00003.safete(…):  56%|#####5    | 2.21G/3.96G [00:04<00:04, 406MB/s]
text_encoder/model-00001-of-00003.safete(…):  58%|#####7    | 2.28G/3.96G [00:04<00:04, 376MB/s]
text_encoder/model-00001-of-00003.safete(…):  58%|#####7    | 2.28G/3.96G [00:04<00:04, 376MB/s]
text_encoder/model-00001-of-00003.safete(…):  59%|#####9    | 2.35G/3.96G [00:04<00:04, 355MB/s]
text_encoder/model-00001-of-00003.safete(…):  59%|#####9    | 2.35G/3.96G [00:04<00:04, 355MB/s]
text_encoder/model-00001-of-00003.safete(…):  63%|######2   | 2.48G/3.96G [00:05<00:03, 380MB/s]
text_encoder/model-00001-of-00003.safete(…):  63%|######2   | 2.48G/3.96G [00:05<00:03, 380MB/s]
text_encoder/model-00001-of-00003.safete(…):  64%|######4   | 2.55G/3.96G [00:05<00:03, 357MB/s]
text_encoder/model-00001-of-00003.safete(…):  64%|######4   | 2.55G/3.96G [00:05<00:03, 357MB/s]
text_encoder/model-00001-of-00003.safete(…):  66%|######6   | 2.62G/3.96G [00:05<00:03, 344MB/s]
text_encoder/model-00001-of-00003.safete(…):  66%|######6   | 2.62G/3.96G [00:05<00:03, 344MB/s]
text_encoder/model-00001-of-00003.safete(…):  68%|######7   | 2.68G/3.96G [00:05<00:03, 334MB/s]
text_encoder/model-00001-of-00003.safete(…):  68%|######7   | 2.68G/3.96G [00:05<00:03, 334MB/s]
text_encoder/model-00001-of-00003.safete(…):  70%|######9   | 2.75G/3.96G [00:06<00:03, 326MB/s]
text_encoder/model-00001-of-00003.safete(…):  70%|######9   | 2.75G/3.96G [00:06<00:03, 326MB/s]
text_encoder/model-00001-of-00003.safete(…):  71%|#######1  | 2.82G/3.96G [00:06<00:03, 321MB/s]
text_encoder/model-00001-of-00003.safete(…):  71%|#######1  | 2.82G/3.96G [00:06<00:03, 321MB/s]
text_encoder/model-00001-of-00003.safete(…):  73%|#######2  | 2.88G/3.96G [00:06<00:03, 317MB/s]
text_encoder/model-00001-of-00003.safete(…):  73%|#######2  | 2.88G/3.96G [00:06<00:03, 317MB/s]
text_encoder/model-00001-of-00003.safete(…):  75%|#######4  | 2.95G/3.96G [00:06<00:03, 313MB/s]
text_encoder/model-00001-of-00003.safete(…):  75%|#######4  | 2.95G/3.96G [00:06<00:03, 313MB/s]
text_encoder/model-00001-of-00003.safete(…):  76%|#######6  | 3.02G/3.96G [00:06<00:03, 308MB/s]
text_encoder/model-00001-of-00003.safete(…):  76%|#######6  | 3.02G/3.96G [00:06<00:03, 308MB/s]
text_encoder/model-00001-of-00003.safete(…):  78%|#######7  | 3.09G/3.96G [00:07<00:02, 307MB/s]
text_encoder/model-00001-of-00003.safete(…):  78%|#######7  | 3.09G/3.96G [00:07<00:02, 307MB/s]
text_encoder/model-00001-of-00003.safete(…):  80%|#######9  | 3.15G/3.96G [00:07<00:02, 303MB/s]
text_encoder/model-00001-of-00003.safete(…):  80%|#######9  | 3.15G/3.96G [00:07<00:02, 303MB/s]
text_encoder/model-00001-of-00003.safete(…):  81%|########1 | 3.22G/3.96G [00:07<00:02, 303MB/s]
text_encoder/model-00001-of-00003.safete(…):  81%|########1 | 3.22G/3.96G [00:07<00:02, 303MB/s]
text_encoder/model-00001-of-00003.safete(…):  83%|########3 | 3.29G/3.96G [00:07<00:02, 301MB/s]
text_encoder/model-00001-of-00003.safete(…):  83%|########3 | 3.29G/3.96G [00:07<00:02, 301MB/s]
text_encoder/model-00001-of-00003.safete(…):  85%|########4 | 3.35G/3.96G [00:08<00:02, 302MB/s]
text_encoder/model-00001-of-00003.safete(…):  85%|########4 | 3.35G/3.96G [00:08<00:02, 302MB/s]
text_encoder/model-00001-of-00003.safete(…):  86%|########6 | 3.42G/3.96G [00:08<00:01, 303MB/s]
text_encoder/model-00001-of-00003.safete(…):  86%|########6 | 3.42G/3.96G [00:08<00:01, 303MB/s]
text_encoder/model-00001-of-00003.safete(…):  88%|########8 | 3.49G/3.96G [00:08<00:01, 305MB/s]
text_encoder/model-00001-of-00003.safete(…):  88%|########8 | 3.49G/3.96G [00:08<00:01, 305MB/s]
text_encoder/model-00001-of-00003.safete(…):  90%|########9 | 3.56G/3.96G [00:08<00:01, 306MB/s]
text_encoder/model-00001-of-00003.safete(…):  90%|########9 | 3.56G/3.96G [00:08<00:01, 306MB/s]
text_encoder/model-00001-of-00003.safete(…):  92%|#########1| 3.62G/3.96G [00:08<00:01, 306MB/s]
text_encoder/model-00001-of-00003.safete(…):  92%|#########1| 3.62G/3.96G [00:08<00:01, 306MB/s]
text_encoder/model-00001-of-00003.safete(…):  93%|#########3| 3.69G/3.96G [00:09<00:00, 306MB/s]
text_encoder/model-00001-of-00003.safete(…):  93%|#########3| 3.69G/3.96G [00:09<00:00, 306MB/s]
text_encoder/model-00001-of-00003.safete(…):  95%|#########4| 3.76G/3.96G [00:09<00:00, 305MB/s]
text_encoder/model-00001-of-00003.safete(…):  95%|#########4| 3.76G/3.96G [00:09<00:00, 305MB/s]
text_encoder/model-00001-of-00003.safete(…):  97%|#########6| 3.82G/3.96G [00:09<00:00, 307MB/s]
text_encoder/model-00001-of-00003.safete(…):  97%|#########6| 3.82G/3.96G [00:09<00:00, 307MB/s]
text_encoder/model-00001-of-00003.safete(…):  98%|#########8| 3.89G/3.96G [00:09<00:00, 303MB/s]
text_encoder/model-00001-of-00003.safete(…):  98%|#########8| 3.89G/3.96G [00:09<00:00, 303MB/s]
text_encoder/model-00001-of-00003.safete(…): 100%|##########| 3.96G/3.96G [00:09<00:00, 301MB/s]
text_encoder/model-00001-of-00003.safete(…): 100%|##########| 3.96G/3.96G [00:09<00:00, 301MB/s]
text_encoder/model-00001-of-00003.safete(…): 100%|##########| 3.96G/3.96G [00:10<00:00, 396MB/s]
text_encoder/model-00001-of-00003.safete(…): 100%|##########| 3.96G/3.96G [00:10<00:00, 396MB/s]


text_encoder/model-00002-of-00003.safete(…):   0%|          | 0.00/3.99G [00:00<?, ?B/s]
text_encoder/model-00002-of-00003.safete(…):   0%|          | 0.00/3.99G [00:00<?, ?B/s]
text_encoder/model-00002-of-00003.safete(…):   0%|          | 675k/3.99G [00:00<22:29, 2.95MB/s]
text_encoder/model-00002-of-00003.safete(…):   0%|          | 675k/3.99G [00:00<22:29, 2.95MB/s]
text_encoder/model-00002-of-00003.safete(…):   0%|          | 2.07M/3.99G [00:00<12:14, 5.43MB/s]
text_encoder/model-00002-of-00003.safete(…):   0%|          | 2.07M/3.99G [00:00<12:14, 5.43MB/s]
text_encoder/model-00002-of-00003.safete(…):   2%|1         | 69.1M/3.99G [00:00<00:21, 181MB/s] 
text_encoder/model-00002-of-00003.safete(…):   2%|1         | 69.1M/3.99G [00:00<00:21, 181MB/s] 
text_encoder/model-00002-of-00003.safete(…):   3%|3         | 138M/3.99G [00:00<00:17, 216MB/s] 
text_encoder/model-00002-of-00003.safete(…):   3%|3         | 138M/3.99G [00:00<00:17, 216MB/s] 
text_encoder/model-00002-of-00003.safete(…):   5%|5         | 205M/3.99G [00:00<00:13, 286MB/s]
text_encoder/model-00002-of-00003.safete(…):   5%|5         | 205M/3.99G [00:00<00:13, 286MB/s]
text_encoder/model-00002-of-00003.safete(…):   7%|6         | 272M/3.99G [00:01<00:10, 347MB/s]
text_encoder/model-00002-of-00003.safete(…):   7%|6         | 272M/3.99G [00:01<00:10, 347MB/s]
text_encoder/model-00002-of-00003.safete(…):   9%|8         | 339M/3.99G [00:01<00:11, 328MB/s]
text_encoder/model-00002-of-00003.safete(…):   9%|8         | 339M/3.99G [00:01<00:11, 328MB/s]
text_encoder/model-00002-of-00003.safete(…):  10%|#         | 407M/3.99G [00:01<00:11, 322MB/s]
text_encoder/model-00002-of-00003.safete(…):  10%|#         | 407M/3.99G [00:01<00:11, 322MB/s]
text_encoder/model-00002-of-00003.safete(…):  14%|#3        | 541M/3.99G [00:01<00:08, 416MB/s]
text_encoder/model-00002-of-00003.safete(…):  14%|#3        | 541M/3.99G [00:01<00:08, 416MB/s]
text_encoder/model-00002-of-00003.safete(…):  15%|#5        | 608M/3.99G [00:02<00:11, 287MB/s]
text_encoder/model-00002-of-00003.safete(…):  15%|#5        | 608M/3.99G [00:02<00:11, 287MB/s]
text_encoder/model-00002-of-00003.safete(…):  17%|#6        | 675M/3.99G [00:02<00:14, 230MB/s]
text_encoder/model-00002-of-00003.safete(…):  17%|#6        | 675M/3.99G [00:02<00:14, 230MB/s]
text_encoder/model-00002-of-00003.safete(…):  19%|#8        | 742M/3.99G [00:03<00:16, 201MB/s]
text_encoder/model-00002-of-00003.safete(…):  19%|#8        | 742M/3.99G [00:03<00:16, 201MB/s]
text_encoder/model-00002-of-00003.safete(…):  20%|##        | 809M/3.99G [00:03<00:17, 183MB/s]
text_encoder/model-00002-of-00003.safete(…):  20%|##        | 809M/3.99G [00:03<00:17, 183MB/s]
text_encoder/model-00002-of-00003.safete(…):  22%|##1       | 876M/3.99G [00:03<00:18, 173MB/s]
text_encoder/model-00002-of-00003.safete(…):  22%|##1       | 876M/3.99G [00:03<00:18, 173MB/s]
text_encoder/model-00002-of-00003.safete(…):  24%|##3       | 943M/3.99G [00:04<00:18, 166MB/s]
text_encoder/model-00002-of-00003.safete(…):  24%|##3       | 943M/3.99G [00:04<00:18, 166MB/s]
text_encoder/model-00002-of-00003.safete(…):  25%|##5       | 1.01G/3.99G [00:04<00:18, 161MB/s]
text_encoder/model-00002-of-00003.safete(…):  25%|##5       | 1.01G/3.99G [00:04<00:18, 161MB/s]
text_encoder/model-00002-of-00003.safete(…):  27%|##7       | 1.08G/3.99G [00:05<00:18, 158MB/s]
text_encoder/model-00002-of-00003.safete(…):  27%|##7       | 1.08G/3.99G [00:05<00:18, 158MB/s]
text_encoder/model-00002-of-00003.safete(…):  29%|##8       | 1.14G/3.99G [00:05<00:18, 156MB/s]
text_encoder/model-00002-of-00003.safete(…):  29%|##8       | 1.14G/3.99G [00:05<00:18, 156MB/s]
text_encoder/model-00002-of-00003.safete(…):  30%|###       | 1.21G/3.99G [00:06<00:18, 154MB/s]
text_encoder/model-00002-of-00003.safete(…):  30%|###       | 1.21G/3.99G [00:06<00:18, 154MB/s]
text_encoder/model-00002-of-00003.safete(…):  32%|###2      | 1.28G/3.99G [00:06<00:17, 153MB/s]
text_encoder/model-00002-of-00003.safete(…):  32%|###2      | 1.28G/3.99G [00:06<00:17, 153MB/s]
text_encoder/model-00002-of-00003.safete(…):  34%|###3      | 1.35G/3.99G [00:07<00:17, 153MB/s]
text_encoder/model-00002-of-00003.safete(…):  34%|###3      | 1.35G/3.99G [00:07<00:17, 153MB/s]
text_encoder/model-00002-of-00003.safete(…):  35%|###5      | 1.41G/3.99G [00:07<00:16, 155MB/s]
text_encoder/model-00002-of-00003.safete(…):  35%|###5      | 1.41G/3.99G [00:07<00:16, 155MB/s]
text_encoder/model-00002-of-00003.safete(…):  37%|###7      | 1.48G/3.99G [00:07<00:15, 164MB/s]
text_encoder/model-00002-of-00003.safete(…):  37%|###7      | 1.48G/3.99G [00:07<00:15, 164MB/s]
text_encoder/model-00002-of-00003.safete(…):  39%|###8      | 1.55G/3.99G [00:08<00:14, 173MB/s]
text_encoder/model-00002-of-00003.safete(…):  39%|###8      | 1.55G/3.99G [00:08<00:14, 173MB/s]
text_encoder/model-00002-of-00003.safete(…):  40%|####      | 1.61G/3.99G [00:08<00:13, 179MB/s]
text_encoder/model-00002-of-00003.safete(…):  40%|####      | 1.61G/3.99G [00:08<00:13, 179MB/s]
text_encoder/model-00002-of-00003.safete(…):  42%|####2     | 1.68G/3.99G [00:08<00:12, 184MB/s]
text_encoder/model-00002-of-00003.safete(…):  42%|####2     | 1.68G/3.99G [00:08<00:12, 184MB/s]
text_encoder/model-00002-of-00003.safete(…):  44%|####3     | 1.75G/3.99G [00:09<00:12, 185MB/s]
text_encoder/model-00002-of-00003.safete(…):  44%|####3     | 1.75G/3.99G [00:09<00:12, 185MB/s]
text_encoder/model-00002-of-00003.safete(…):  46%|####5     | 1.81G/3.99G [00:09<00:11, 184MB/s]
text_encoder/model-00002-of-00003.safete(…):  46%|####5     | 1.81G/3.99G [00:09<00:11, 184MB/s]
text_encoder/model-00002-of-00003.safete(…):  47%|####7     | 1.88G/3.99G [00:09<00:11, 186MB/s]
text_encoder/model-00002-of-00003.safete(…):  47%|####7     | 1.88G/3.99G [00:09<00:11, 186MB/s]
text_encoder/model-00002-of-00003.safete(…):  49%|####8     | 1.95G/3.99G [00:10<00:10, 192MB/s]
text_encoder/model-00002-of-00003.safete(…):  49%|####8     | 1.95G/3.99G [00:10<00:10, 192MB/s]
text_encoder/model-00002-of-00003.safete(…):  51%|#####     | 2.02G/3.99G [00:10<00:10, 193MB/s]
text_encoder/model-00002-of-00003.safete(…):  51%|#####     | 2.02G/3.99G [00:10<00:10, 193MB/s]
text_encoder/model-00002-of-00003.safete(…):  52%|#####2    | 2.08G/3.99G [00:10<00:09, 196MB/s]
text_encoder/model-00002-of-00003.safete(…):  52%|#####2    | 2.08G/3.99G [00:10<00:09, 196MB/s]
text_encoder/model-00002-of-00003.safete(…):  54%|#####3    | 2.15G/3.99G [00:11<00:09, 198MB/s]
text_encoder/model-00002-of-00003.safete(…):  54%|#####3    | 2.15G/3.99G [00:11<00:09, 198MB/s]
text_encoder/model-00002-of-00003.safete(…):  55%|#####4    | 2.18G/3.99G [00:11<00:08, 202MB/s]
text_encoder/model-00002-of-00003.safete(…):  55%|#####4    | 2.18G/3.99G [00:11<00:08, 202MB/s]
text_encoder/model-00002-of-00003.safete(…):  56%|#####6    | 2.25G/3.99G [00:11<00:09, 192MB/s]
text_encoder/model-00002-of-00003.safete(…):  56%|#####6    | 2.25G/3.99G [00:11<00:09, 192MB/s]
text_encoder/model-00002-of-00003.safete(…):  58%|#####8    | 2.31G/3.99G [00:12<00:08, 191MB/s]
text_encoder/model-00002-of-00003.safete(…):  58%|#####8    | 2.31G/3.99G [00:12<00:08, 191MB/s]
text_encoder/model-00002-of-00003.safete(…):  60%|#####9    | 2.38G/3.99G [00:12<00:08, 196MB/s]
text_encoder/model-00002-of-00003.safete(…):  60%|#####9    | 2.38G/3.99G [00:12<00:08, 196MB/s]
text_encoder/model-00002-of-00003.safete(…):  61%|######1   | 2.45G/3.99G [00:12<00:07, 200MB/s]
text_encoder/model-00002-of-00003.safete(…):  61%|######1   | 2.45G/3.99G [00:12<00:07, 200MB/s]
text_encoder/model-00002-of-00003.safete(…):  63%|######3   | 2.52G/3.99G [00:13<00:07, 202MB/s]
text_encoder/model-00002-of-00003.safete(…):  63%|######3   | 2.52G/3.99G [00:13<00:07, 202MB/s]
text_encoder/model-00002-of-00003.safete(…):  65%|######4   | 2.58G/3.99G [00:13<00:06, 213MB/s]
text_encoder/model-00002-of-00003.safete(…):  65%|######4   | 2.58G/3.99G [00:13<00:06, 213MB/s]
text_encoder/model-00002-of-00003.safete(…):  66%|######6   | 2.65G/3.99G [00:13<00:06, 212MB/s]
text_encoder/model-00002-of-00003.safete(…):  66%|######6   | 2.65G/3.99G [00:13<00:06, 212MB/s]
text_encoder/model-00002-of-00003.safete(…):  68%|######8   | 2.72G/3.99G [00:14<00:05, 214MB/s]
text_encoder/model-00002-of-00003.safete(…):  68%|######8   | 2.72G/3.99G [00:14<00:05, 214MB/s]
text_encoder/model-00002-of-00003.safete(…):  70%|######9   | 2.78G/3.99G [00:14<00:05, 219MB/s]
text_encoder/model-00002-of-00003.safete(…):  70%|######9   | 2.78G/3.99G [00:14<00:05, 219MB/s]
text_encoder/model-00002-of-00003.safete(…):  71%|#######1  | 2.85G/3.99G [00:14<00:05, 226MB/s]
text_encoder/model-00002-of-00003.safete(…):  71%|#######1  | 2.85G/3.99G [00:14<00:05, 226MB/s]
text_encoder/model-00002-of-00003.safete(…):  73%|#######3  | 2.92G/3.99G [00:14<00:04, 219MB/s]
text_encoder/model-00002-of-00003.safete(…):  73%|#######3  | 2.92G/3.99G [00:14<00:04, 219MB/s]
text_encoder/model-00002-of-00003.safete(…):  75%|#######4  | 2.98G/3.99G [00:15<00:04, 219MB/s]
text_encoder/model-00002-of-00003.safete(…):  75%|#######4  | 2.98G/3.99G [00:15<00:04, 219MB/s]
text_encoder/model-00002-of-00003.safete(…):  77%|#######6  | 3.05G/3.99G [00:15<00:04, 224MB/s]
text_encoder/model-00002-of-00003.safete(…):  77%|#######6  | 3.05G/3.99G [00:15<00:04, 224MB/s]
text_encoder/model-00002-of-00003.safete(…):  78%|#######8  | 3.12G/3.99G [00:15<00:03, 220MB/s]
text_encoder/model-00002-of-00003.safete(…):  78%|#######8  | 3.12G/3.99G [00:15<00:03, 220MB/s]
text_encoder/model-00002-of-00003.safete(…):  80%|#######9  | 3.18G/3.99G [00:16<00:03, 227MB/s]
text_encoder/model-00002-of-00003.safete(…):  80%|#######9  | 3.18G/3.99G [00:16<00:03, 227MB/s]
text_encoder/model-00002-of-00003.safete(…):  82%|########1 | 3.25G/3.99G [00:16<00:03, 237MB/s]
text_encoder/model-00002-of-00003.safete(…):  82%|########1 | 3.25G/3.99G [00:16<00:03, 237MB/s]
text_encoder/model-00002-of-00003.safete(…):  83%|########3 | 3.32G/3.99G [00:16<00:02, 235MB/s]
text_encoder/model-00002-of-00003.safete(…):  83%|########3 | 3.32G/3.99G [00:16<00:02, 235MB/s]
text_encoder/model-00002-of-00003.safete(…):  85%|########4 | 3.39G/3.99G [00:16<00:02, 233MB/s]
text_encoder/model-00002-of-00003.safete(…):  85%|########4 | 3.39G/3.99G [00:16<00:02, 233MB/s]
text_encoder/model-00002-of-00003.safete(…):  87%|########6 | 3.45G/3.99G [00:17<00:02, 230MB/s]
text_encoder/model-00002-of-00003.safete(…):  87%|########6 | 3.45G/3.99G [00:17<00:02, 230MB/s]
text_encoder/model-00002-of-00003.safete(…):  88%|########8 | 3.52G/3.99G [00:17<00:02, 234MB/s]
text_encoder/model-00002-of-00003.safete(…):  88%|########8 | 3.52G/3.99G [00:17<00:02, 234MB/s]
text_encoder/model-00002-of-00003.safete(…):  90%|########9 | 3.58G/3.99G [00:17<00:01, 242MB/s]
text_encoder/model-00002-of-00003.safete(…):  90%|########9 | 3.58G/3.99G [00:17<00:01, 242MB/s]
text_encoder/model-00002-of-00003.safete(…):  92%|#########1| 3.65G/3.99G [00:18<00:01, 243MB/s]
text_encoder/model-00002-of-00003.safete(…):  92%|#########1| 3.65G/3.99G [00:18<00:01, 243MB/s]
text_encoder/model-00002-of-00003.safete(…):  93%|#########3| 3.72G/3.99G [00:18<00:01, 245MB/s]
text_encoder/model-00002-of-00003.safete(…):  93%|#########3| 3.72G/3.99G [00:18<00:01, 245MB/s]
text_encoder/model-00002-of-00003.safete(…):  95%|#########4| 3.79G/3.99G [00:18<00:00, 243MB/s]
text_encoder/model-00002-of-00003.safete(…):  95%|#########4| 3.79G/3.99G [00:18<00:00, 243MB/s]
text_encoder/model-00002-of-00003.safete(…):  97%|#########6| 3.85G/3.99G [00:18<00:00, 240MB/s]
text_encoder/model-00002-of-00003.safete(…):  97%|#########6| 3.85G/3.99G [00:18<00:00, 240MB/s]
text_encoder/model-00002-of-00003.safete(…):  98%|#########8| 3.92G/3.99G [00:19<00:00, 241MB/s]
text_encoder/model-00002-of-00003.safete(…):  98%|#########8| 3.92G/3.99G [00:19<00:00, 241MB/s]
text_encoder/model-00002-of-00003.safete(…): 100%|##########| 3.99G/3.99G [00:19<00:00, 244MB/s]
text_encoder/model-00002-of-00003.safete(…): 100%|##########| 3.99G/3.99G [00:19<00:00, 244MB/s]
text_encoder/model-00002-of-00003.safete(…): 100%|##########| 3.99G/3.99G [00:19<00:00, 205MB/s]
text_encoder/model-00002-of-00003.safete(…): 100%|##########| 3.99G/3.99G [00:19<00:00, 205MB/s]


text_encoder/model-00003-of-00003.safete(…):   0%|          | 0.00/99.6M [00:00<?, ?B/s]
text_encoder/model-00003-of-00003.safete(…):   0%|          | 0.00/99.6M [00:00<?, ?B/s]
text_encoder/model-00003-of-00003.safete(…):  38%|###7      | 37.6M/99.6M [00:00<00:00, 211MB/s]
text_encoder/model-00003-of-00003.safete(…):  38%|###7      | 37.6M/99.6M [00:00<00:00, 211MB/s]
text_encoder/model-00003-of-00003.safete(…): 100%|##########| 99.6M/99.6M [00:00<00:00, 203MB/s]
text_encoder/model-00003-of-00003.safete(…): 100%|##########| 99.6M/99.6M [00:00<00:00, 203MB/s]
text_encoder/model-00003-of-00003.safete(…): 100%|##########| 99.6M/99.6M [00:00<00:00, 204MB/s]
text_encoder/model-00003-of-00003.safete(…): 100%|##########| 99.6M/99.6M [00:00<00:00, 204MB/s]


Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards: 100%|##########| 3/3 [00:00<00:00, 72.45it/s]
Loading checkpoint shards: 100%|##########| 3/3 [00:00<00:00, 72.45it/s]


generation_config.json:   0%|          | 0.00/239 [00:00<?, ?B/s]
generation_config.json:   0%|          | 0.00/239 [00:00<?, ?B/s]
generation_config.json: 100%|##########| 239/239 [00:00<00:00, 2.36MB/s]
generation_config.json: 100%|##########| 239/239 [00:00<00:00, 2.36MB/s]

Quantizing Text Encoder
Loading VAE

config.json:   0%|          | 0.00/805 [00:00<?, ?B/s]
config.json:   0%|          | 0.00/805 [00:00<?, ?B/s]
config.json: 100%|##########| 805/805 [00:00<00:00, 4.64MB/s]
config.json: 100%|##########| 805/805 [00:00<00:00, 4.64MB/s]


vae/diffusion_pytorch_model.safetensors:   0%|          | 0.00/168M [00:00<?, ?B/s]
vae/diffusion_pytorch_model.safetensors:   0%|          | 0.00/168M [00:00<?, ?B/s]
vae/diffusion_pytorch_model.safetensors:  40%|####      | 67.1M/168M [00:00<00:00, 113MB/s]
vae/diffusion_pytorch_model.safetensors:  40%|####      | 67.1M/168M [00:00<00:00, 113MB/s]
vae/diffusion_pytorch_model.safetensors:  60%|#####9    | 101M/168M [00:00<00:00, 155MB/s] 
vae/diffusion_pytorch_model.safetensors:  60%|#####9    | 101M/168M [00:00<00:00, 155MB/s] 
vae/diffusion_pytorch_model.safetensors: 100%|##########| 168M/168M [00:00<00:00, 214MB/s]
vae/diffusion_pytorch_model.safetensors: 100%|##########| 168M/168M [00:00<00:00, 214MB/s]
vae/diffusion_pytorch_model.safetensors: 100%|##########| 168M/168M [00:00<00:00, 184MB/s]
vae/diffusion_pytorch_model.safetensors: 100%|##########| 168M/168M [00:00<00:00, 184MB/s]

Making pipe
Preparing Model
Model Loaded
create LoRA network. base dim (rank): 32, alpha: 32
neuron dropout: p=None, rank dropout: p=None, module dropout: p=None
apply LoRA to Conv2d with kernel size (3,3). dim (rank): 16, alpha: 16
create LoRA for Text Encoder: 0 modules.
create LoRA for U-Net: 240 modules.
enable LoRA for U-Net
Dataset: /data/app/datasets/latex_01
  -  Preprocessing image dimensions

  0%|          | 0/31 [00:00<?, ?it/s]
  0%|          | 0/31 [00:00<?, ?it/s]
  3%|3         | 1/31 [00:00<00:03,  8.50it/s]
  3%|3         | 1/31 [00:00<00:03,  8.50it/s]
  6%|6         | 2/31 [00:00<00:03,  7.71it/s]
  6%|6         | 2/31 [00:00<00:03,  7.71it/s]
 10%|9         | 3/31 [00:00<00:03,  8.41it/s]
 10%|9         | 3/31 [00:00<00:03,  8.41it/s]
 13%|#2        | 4/31 [00:00<00:03,  8.55it/s]
 13%|#2        | 4/31 [00:00<00:03,  8.55it/s]
 16%|#6        | 5/31 [00:00<00:03,  7.66it/s]
 16%|#6        | 5/31 [00:00<00:03,  7.66it/s]
 19%|#9        | 6/31 [00:00<00:03,  7.71it/s]
 19%|#9        | 6/31 [00:00<00:03,  7.71it/s]
 23%|##2       | 7/31 [00:00<00:02,  8.19it/s]
 23%|##2       | 7/31 [00:00<00:02,  8.19it/s]
 26%|##5       | 8/31 [00:00<00:02,  8.35it/s]
 26%|##5       | 8/31 [00:00<00:02,  8.35it/s]
 29%|##9       | 9/31 [00:01<00:02,  7.67it/s]
 29%|##9       | 9/31 [00:01<00:02,  7.67it/s]
 35%|###5      | 11/31 [00:01<00:02,  7.84it/s]
 35%|###5      | 11/31 [00:01<00:02,  7.84it/s]
 39%|###8      | 12/31 [00:01<00:02,  7.77it/s]
 39%|###8      | 12/31 [00:01<00:02,  7.77it/s]
 45%|####5     | 14/31 [00:01<00:01,  8.98it/s]
 45%|####5     | 14/31 [00:01<00:01,  8.98it/s]
 48%|####8     | 15/31 [00:01<00:01,  8.81it/s]
 48%|####8     | 15/31 [00:01<00:01,  8.81it/s]
 52%|#####1    | 16/31 [00:01<00:01,  8.69it/s]
 52%|#####1    | 16/31 [00:01<00:01,  8.69it/s]
 55%|#####4    | 17/31 [00:02<00:01,  8.90it/s]
 55%|#####4    | 17/31 [00:02<00:01,  8.90it/s]
 58%|#####8    | 18/31 [00:02<00:01,  9.09it/s]
 58%|#####8    | 18/31 [00:02<00:01,  9.09it/s]
 61%|######1   | 19/31 [00:02<00:01,  8.80it/s]
 61%|######1   | 19/31 [00:02<00:01,  8.80it/s]
 65%|######4   | 20/31 [00:02<00:01,  8.19it/s]
 65%|######4   | 20/31 [00:02<00:01,  8.19it/s]
 68%|######7   | 21/31 [00:02<00:01,  7.30it/s]
 68%|######7   | 21/31 [00:02<00:01,  7.30it/s]
 71%|#######   | 22/31 [00:02<00:01,  7.51it/s]
 71%|#######   | 22/31 [00:02<00:01,  7.51it/s]
 74%|#######4  | 23/31 [00:02<00:01,  7.19it/s]
 74%|#######4  | 23/31 [00:02<00:01,  7.19it/s]
 77%|#######7  | 24/31 [00:02<00:00,  7.16it/s]
 77%|#######7  | 24/31 [00:02<00:00,  7.16it/s]
 81%|########  | 25/31 [00:03<00:00,  7.25it/s]
 81%|########  | 25/31 [00:03<00:00,  7.25it/s]
 84%|########3 | 26/31 [00:03<00:00,  6.98it/s]
 84%|########3 | 26/31 [00:03<00:00,  6.98it/s]
 87%|########7 | 27/31 [00:03<00:00,  6.88it/s]
 87%|########7 | 27/31 [00:03<00:00,  6.88it/s]
 94%|#########3| 29/31 [00:03<00:00,  7.49it/s]
 94%|#########3| 29/31 [00:03<00:00,  7.49it/s]
 97%|#########6| 30/31 [00:03<00:00,  7.92it/s]
 97%|#########6| 30/31 [00:03<00:00,  7.92it/s]
100%|##########| 31/31 [00:03<00:00,  8.14it/s]
100%|##########| 31/31 [00:03<00:00,  8.14it/s]
100%|##########| 31/31 [00:03<00:00,  7.96it/s]
100%|##########| 31/31 [00:03<00:00,  7.96it/s]

  -  Found 31 images
Bucket sizes for /data/app/datasets/latex_01:
416x576: 12 files
448x576: 4 files
384x672: 5 files
416x608: 7 files
384x640: 2 files
448x544: 1 files
6 buckets made
Dataset: /data/app/datasets/latex_01
  -  Preprocessing image dimensions

  0%|          | 0/31 [00:00<?, ?it/s]
  0%|          | 0/31 [00:00<?, ?it/s]
100%|##########| 31/31 [00:00<00:00, 11879.71it/s]
100%|##########| 31/31 [00:00<00:00, 11879.71it/s]

  -  Found 31 images
Bucket sizes for /data/app/datasets/latex_01:
672x864: 12 files
576x768: 2 files
608x832: 2 files
576x992: 4 files
512x768: 1 files
480x704: 1 files
608x896: 5 files
544x800: 1 files
672x800: 1 files
576x960: 1 files
544x960: 1 files
11 buckets made
Dataset: /data/app/datasets/latex_01
  -  Preprocessing image dimensions

  0%|          | 0/31 [00:00<?, ?it/s]
  0%|          | 0/31 [00:00<?, ?it/s]
100%|##########| 31/31 [00:00<00:00, 38423.00it/s]
100%|##########| 31/31 [00:00<00:00, 38423.00it/s]

  -  Found 31 images
Bucket sizes for /data/app/datasets/latex_01:
736x960: 6 files
832x1152: 1 files
736x1024: 1 files
576x768: 2 files
608x832: 2 files
896x1152: 2 files
672x928: 1 files
576x992: 3 files
512x768: 1 files
480x704: 1 files
832x1216: 5 files
704x928: 1 files
544x800: 1 files
896x1088: 1 files
704x1184: 1 files
768x1344: 1 files
544x960: 1 files
17 buckets made
Generating baseline samples before training
Unloading assistant lora

Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]
Generating Images:  14%|#4        | 1/7 [00:02<00:17,  2.95s/it]
Generating Images:  14%|#4        | 1/7 [00:02<00:17,  2.95s/it]
Generating Images:  29%|##8       | 2/7 [00:05<00:13,  2.69s/it]
Generating Images:  29%|##8       | 2/7 [00:05<00:13,  2.69s/it]
Generating Images:  43%|####2     | 3/7 [00:07<00:10,  2.53s/it]
Generating Images:  43%|####2     | 3/7 [00:07<00:10,  2.53s/it]
Generating Images:  57%|#####7    | 4/7 [00:10<00:07,  2.48s/it]
Generating Images:  57%|#####7    | 4/7 [00:10<00:07,  2.48s/it]
Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.43s/it]
Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.43s/it]
Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.44s/it]
Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.44s/it]
Generating Images: 100%|##########| 7/7 [00:17<00:00,  2.45s/it]
Generating Images: 100%|##########| 7/7 [00:17<00:00,  2.45s/it]
                                                                
                                                                

Loading assistant lora

latex_v1:   0%|          | 0/3000 [00:00<?, ?it/s]
latex_v1:   0%|          | 0/3000 [00:00<?, ?it/s]
latex_v1:   0%|          | 0/3000 [00:01<?, ?it/s, lr: 1.0e-04 loss: 1.995e-01]
latex_v1:   0%|          | 0/3000 [00:01<?, ?it/s, lr: 1.0e-04 loss: 1.995e-01]
latex_v1:   0%|          | 0/3000 [00:01<?, ?it/s, lr: 1.0e-04 loss: 1.995e-01]
latex_v1:   0%|          | 0/3000 [00:01<?, ?it/s, lr: 1.0e-04 loss: 1.995e-01]
latex_v1:   0%|          | 0/3000 [00:03<?, ?it/s, lr: 1.0e-04 loss: 5.912e-01]
latex_v1:   0%|          | 0/3000 [00:03<?, ?it/s, lr: 1.0e-04 loss: 5.912e-01]
latex_v1:   0%|          | 1/3000 [00:03<1:39:11,  1.98s/it, lr: 1.0e-04 loss: 5.912e-01]
latex_v1:   0%|          | 1/3000 [00:03<1:39:11,  1.98s/it, lr: 1.0e-04 loss: 5.912e-01]
latex_v1:   0%|          | 1/3000 [00:04<1:39:11,  1.98s/it, lr: 1.0e-04 loss: 3.028e-01]
latex_v1:   0%|          | 1/3000 [00:04<1:39:11,  1.98s/it, lr: 1.0e-04 loss: 3.028e-01]
latex_v1:   0%|          | 2/3000 [00:04<1:06:23,  1.33s/it, lr: 1.0e-04 loss: 3.028e-01]
latex_v1:   0%|          | 2/3000 [00:04<1:06:23,  1.33s/it, lr: 1.0e-04 loss: 3.028e-01]
latex_v1:   0%|          | 2/3000 [00:07<1:06:23,  1.33s/it, lr: 1.0e-04 loss: 6.103e-01]
latex_v1:   0%|          | 2/3000 [00:07<1:06:23,  1.33s/it, lr: 1.0e-04 loss: 6.103e-01]
latex_v1:   0%|          | 3/3000 [00:07<1:37:52,  1.96s/it, lr: 1.0e-04 loss: 6.103e-01]
latex_v1:   0%|          | 3/3000 [00:07<1:37:52,  1.96s/it, lr: 1.0e-04 loss: 6.103e-01]
latex_v1:   0%|          | 3/3000 [00:09<1:37:52,  1.96s/it, lr: 1.0e-04 loss: 2.916e-01]
latex_v1:   0%|          | 3/3000 [00:09<1:37:52,  1.96s/it, lr: 1.0e-04 loss: 2.916e-01]
latex_v1:   0%|          | 4/3000 [00:09<1:31:25,  1.83s/it, lr: 1.0e-04 loss: 2.916e-01]
latex_v1:   0%|          | 4/3000 [00:09<1:31:25,  1.83s/it, lr: 1.0e-04 loss: 2.916e-01]
latex_v1:   0%|          | 4/3000 [00:09<1:31:25,  1.83s/it, lr: 1.0e-04 loss: 7.455e-01]
latex_v1:   0%|          | 4/3000 [00:09<1:31:25,  1.83s/it, lr: 1.0e-04 loss: 7.455e-01]
latex_v1:   0%|          | 5/3000 [00:09<1:13:53,  1.48s/it, lr: 1.0e-04 loss: 7.455e-01]
latex_v1:   0%|          | 5/3000 [00:09<1:13:53,  1.48s/it, lr: 1.0e-04 loss: 7.455e-01]
latex_v1:   0%|          | 5/3000 [00:10<1:13:53,  1.48s/it, lr: 1.0e-04 loss: 6.491e-01]
latex_v1:   0%|          | 5/3000 [00:10<1:13:53,  1.48s/it, lr: 1.0e-04 loss: 6.491e-01]
latex_v1:   0%|          | 6/3000 [00:10<1:03:06,  1.26s/it, lr: 1.0e-04 loss: 6.491e-01]
latex_v1:   0%|          | 6/3000 [00:10<1:03:06,  1.26s/it, lr: 1.0e-04 loss: 6.491e-01]
latex_v1:   0%|          | 6/3000 [00:12<1:03:06,  1.26s/it, lr: 1.0e-04 loss: 6.541e-01]
latex_v1:   0%|          | 6/3000 [00:12<1:03:06,  1.26s/it, lr: 1.0e-04 loss: 6.541e-01]
latex_v1:   0%|          | 7/3000 [00:12<1:08:47,  1.38s/it, lr: 1.0e-04 loss: 6.541e-01]
latex_v1:   0%|          | 7/3000 [00:12<1:08:47,  1.38s/it, lr: 1.0e-04 loss: 6.541e-01]
latex_v1:   0%|          | 7/3000 [00:13<1:08:47,  1.38s/it, lr: 1.0e-04 loss: 3.381e-01]
latex_v1:   0%|          | 7/3000 [00:13<1:08:47,  1.38s/it, lr: 1.0e-04 loss: 3.381e-01]
latex_v1:   0%|          | 8/3000 [00:13<1:12:19,  1.45s/it, lr: 1.0e-04 loss: 3.381e-01]
latex_v1:   0%|          | 8/3000 [00:13<1:12:19,  1.45s/it, lr: 1.0e-04 loss: 3.381e-01]
latex_v1:   0%|          | 8/3000 [00:14<1:12:19,  1.45s/it, lr: 1.0e-04 loss: 4.492e-01]
latex_v1:   0%|          | 8/3000 [00:14<1:12:19,  1.45s/it, lr: 1.0e-04 loss: 4.492e-01]
latex_v1:   0%|          | 9/3000 [00:14<1:03:23,  1.27s/it, lr: 1.0e-04 loss: 4.492e-01]
latex_v1:   0%|          | 9/3000 [00:14<1:03:23,  1.27s/it, lr: 1.0e-04 loss: 4.492e-01]
latex_v1:   0%|          | 9/3000 [00:16<1:03:23,  1.27s/it, lr: 1.0e-04 loss: 2.356e-01]
latex_v1:   0%|          | 9/3000 [00:16<1:03:23,  1.27s/it, lr: 1.0e-04 loss: 2.356e-01]
latex_v1:   0%|          | 10/3000 [00:17<1:03:21,  1.27s/it, lr: 1.0e-04 loss: 8.655e-01]
latex_v1:   0%|          | 10/3000 [00:17<1:03:21,  1.27s/it, lr: 1.0e-04 loss: 8.655e-01]
latex_v1:   0%|          | 11/3000 [00:17<42:15,  1.18it/s, lr: 1.0e-04 loss: 8.655e-01]  
latex_v1:   0%|          | 11/3000 [00:17<42:15,  1.18it/s, lr: 1.0e-04 loss: 8.655e-01]  
latex_v1:   0%|          | 11/3000 [00:20<42:15,  1.18it/s, lr: 1.0e-04 loss: 4.328e-01]
latex_v1:   0%|          | 11/3000 [00:20<42:15,  1.18it/s, lr: 1.0e-04 loss: 4.328e-01]
latex_v1:   0%|          | 12/3000 [00:20<1:07:01,  1.35s/it, lr: 1.0e-04 loss: 4.328e-01]
latex_v1:   0%|          | 12/3000 [00:20<1:07:01,  1.35s/it, lr: 1.0e-04 loss: 4.328e-01]
latex_v1:   0%|          | 12/3000 [00:21<1:07:01,  1.35s/it, lr: 1.0e-04 loss: 9.794e-02]
latex_v1:   0%|          | 12/3000 [00:21<1:07:01,  1.35s/it, lr: 1.0e-04 loss: 9.794e-02]
latex_v1:   0%|          | 13/3000 [00:21<1:10:01,  1.41s/it, lr: 1.0e-04 loss: 9.794e-02]
latex_v1:   0%|          | 13/3000 [00:21<1:10:01,  1.41s/it, lr: 1.0e-04 loss: 9.794e-02]
latex_v1:   0%|          | 13/3000 [00:22<1:10:01,  1.41s/it, lr: 1.0e-04 loss: 6.231e-01]
latex_v1:   0%|          | 13/3000 [00:22<1:10:01,  1.41s/it, lr: 1.0e-04 loss: 6.231e-01]
latex_v1:   0%|          | 14/3000 [00:23<1:10:06,  1.41s/it, lr: 1.0e-04 loss: 6.231e-01]
latex_v1:   0%|          | 14/3000 [00:23<1:10:06,  1.41s/it, lr: 1.0e-04 loss: 6.231e-01]
latex_v1:   0%|          | 14/3000 [00:24<1:10:06,  1.41s/it, lr: 1.0e-04 loss: 4.736e-01]
latex_v1:   0%|          | 14/3000 [00:24<1:10:06,  1.41s/it, lr: 1.0e-04 loss: 4.736e-01]
latex_v1:   0%|          | 15/3000 [00:24<1:11:55,  1.45s/it, lr: 1.0e-04 loss: 4.736e-01]
latex_v1:   0%|          | 15/3000 [00:24<1:11:55,  1.45s/it, lr: 1.0e-04 loss: 4.736e-01]
latex_v1:   0%|          | 15/3000 [00:25<1:11:55,  1.45s/it, lr: 1.0e-04 loss: 1.720e-01]
latex_v1:   0%|          | 15/3000 [00:25<1:11:55,  1.45s/it, lr: 1.0e-04 loss: 1.720e-01]
latex_v1:   1%|          | 16/3000 [00:25<1:01:52,  1.24s/it, lr: 1.0e-04 loss: 1.720e-01]
latex_v1:   1%|          | 16/3000 [00:25<1:01:52,  1.24s/it, lr: 1.0e-04 loss: 1.720e-01]
latex_v1:   1%|          | 16/3000 [00:28<1:01:52,  1.24s/it, lr: 1.0e-04 loss: 1.257e-01]
latex_v1:   1%|          | 16/3000 [00:28<1:01:52,  1.24s/it, lr: 1.0e-04 loss: 1.257e-01]
latex_v1:   1%|          | 17/3000 [00:28<1:25:01,  1.71s/it, lr: 1.0e-04 loss: 1.257e-01]
latex_v1:   1%|          | 17/3000 [00:28<1:25:01,  1.71s/it, lr: 1.0e-04 loss: 1.257e-01]
latex_v1:   1%|          | 17/3000 [00:28<1:25:01,  1.71s/it, lr: 1.0e-04 loss: 2.760e-01]
latex_v1:   1%|          | 17/3000 [00:28<1:25:01,  1.71s/it, lr: 1.0e-04 loss: 2.760e-01]
latex_v1:   1%|          | 18/3000 [00:28<1:10:48,  1.42s/it, lr: 1.0e-04 loss: 2.760e-01]
latex_v1:   1%|          | 18/3000 [00:28<1:10:48,  1.42s/it, lr: 1.0e-04 loss: 2.760e-01]
latex_v1:   1%|          | 18/3000 [00:29<1:10:48,  1.42s/it, lr: 1.0e-04 loss: 1.901e-01]
latex_v1:   1%|          | 18/3000 [00:29<1:10:48,  1.42s/it, lr: 1.0e-04 loss: 1.901e-01]
latex_v1:   1%|          | 19/3000 [00:29<1:00:52,  1.23s/it, lr: 1.0e-04 loss: 1.901e-01]
latex_v1:   1%|          | 19/3000 [00:29<1:00:52,  1.23s/it, lr: 1.0e-04 loss: 1.901e-01]
latex_v1:   1%|          | 19/3000 [00:30<1:00:52,  1.23s/it, lr: 1.0e-04 loss: 3.643e-01]
latex_v1:   1%|          | 19/3000 [00:30<1:00:52,  1.23s/it, lr: 1.0e-04 loss: 3.643e-01]
latex_v1:   1%|          | 20/3000 [00:33<1:00:51,  1.23s/it, lr: 1.0e-04 loss: 7.728e-02]
latex_v1:   1%|          | 20/3000 [00:33<1:00:51,  1.23s/it, lr: 1.0e-04 loss: 7.728e-02]
latex_v1:   1%|          | 21/3000 [00:33<1:04:50,  1.31s/it, lr: 1.0e-04 loss: 7.728e-02]
latex_v1:   1%|          | 21/3000 [00:33<1:04:50,  1.31s/it, lr: 1.0e-04 loss: 7.728e-02]
latex_v1:   1%|          | 21/3000 [00:35<1:04:50,  1.31s/it, lr: 1.0e-04 loss: 4.723e-01]
latex_v1:   1%|          | 21/3000 [00:35<1:04:50,  1.31s/it, lr: 1.0e-04 loss: 4.723e-01]
latex_v1:   1%|          | 22/3000 [00:35<1:05:50,  1.33s/it, lr: 1.0e-04 loss: 4.723e-01]
latex_v1:   1%|          | 22/3000 [00:35<1:05:50,  1.33s/it, lr: 1.0e-04 loss: 4.723e-01]
latex_v1:   1%|          | 22/3000 [00:35<1:05:50,  1.33s/it, lr: 1.0e-04 loss: 2.236e-01]
latex_v1:   1%|          | 22/3000 [00:35<1:05:50,  1.33s/it, lr: 1.0e-04 loss: 2.236e-01]
latex_v1:   1%|          | 23/3000 [00:35<58:13,  1.17s/it, lr: 1.0e-04 loss: 2.236e-01]  
latex_v1:   1%|          | 23/3000 [00:35<58:13,  1.17s/it, lr: 1.0e-04 loss: 2.236e-01]  
latex_v1:   1%|          | 23/3000 [00:36<58:13,  1.17s/it, lr: 1.0e-04 loss: 4.726e-01]
latex_v1:   1%|          | 23/3000 [00:36<58:13,  1.17s/it, lr: 1.0e-04 loss: 4.726e-01]
latex_v1:   1%|          | 24/3000 [00:36<55:30,  1.12s/it, lr: 1.0e-04 loss: 4.726e-01]
latex_v1:   1%|          | 24/3000 [00:36<55:30,  1.12s/it, lr: 1.0e-04 loss: 4.726e-01]
latex_v1:   1%|          | 24/3000 [00:37<55:30,  1.12s/it, lr: 1.0e-04 loss: 6.029e-01]
latex_v1:   1%|          | 24/3000 [00:37<55:30,  1.12s/it, lr: 1.0e-04 loss: 6.029e-01]
latex_v1:   1%|          | 25/3000 [00:37<50:12,  1.01s/it, lr: 1.0e-04 loss: 6.029e-01]
latex_v1:   1%|          | 25/3000 [00:37<50:12,  1.01s/it, lr: 1.0e-04 loss: 6.029e-01]
latex_v1:   1%|          | 25/3000 [00:39<50:12,  1.01s/it, lr: 1.0e-04 loss: 2.251e-01]
latex_v1:   1%|          | 25/3000 [00:39<50:12,  1.01s/it, lr: 1.0e-04 loss: 2.251e-01]
latex_v1:   1%|          | 26/3000 [00:39<1:02:17,  1.26s/it, lr: 1.0e-04 loss: 2.251e-01]
latex_v1:   1%|          | 26/3000 [00:39<1:02:17,  1.26s/it, lr: 1.0e-04 loss: 2.251e-01]
latex_v1:   1%|          | 26/3000 [00:42<1:02:17,  1.26s/it, lr: 1.0e-04 loss: 3.451e-01]
latex_v1:   1%|          | 26/3000 [00:42<1:02:17,  1.26s/it, lr: 1.0e-04 loss: 3.451e-01]
latex_v1:   1%|          | 27/3000 [00:42<1:25:36,  1.73s/it, lr: 1.0e-04 loss: 3.451e-01]
latex_v1:   1%|          | 27/3000 [00:42<1:25:36,  1.73s/it, lr: 1.0e-04 loss: 3.451e-01]
latex_v1:   1%|          | 27/3000 [00:43<1:25:36,  1.73s/it, lr: 1.0e-04 loss: 6.528e-01]
latex_v1:   1%|          | 27/3000 [00:43<1:25:36,  1.73s/it, lr: 1.0e-04 loss: 6.528e-01]
latex_v1:   1%|          | 28/3000 [00:43<1:11:14,  1.44s/it, lr: 1.0e-04 loss: 6.528e-01]
latex_v1:   1%|          | 28/3000 [00:43<1:11:14,  1.44s/it, lr: 1.0e-04 loss: 6.528e-01]
latex_v1:   1%|          | 28/3000 [00:44<1:11:14,  1.44s/it, lr: 1.0e-04 loss: 2.676e-01]
latex_v1:   1%|          | 28/3000 [00:44<1:11:14,  1.44s/it, lr: 1.0e-04 loss: 2.676e-01]
latex_v1:   1%|          | 29/3000 [00:44<1:05:47,  1.33s/it, lr: 1.0e-04 loss: 2.676e-01]
latex_v1:   1%|          | 29/3000 [00:44<1:05:47,  1.33s/it, lr: 1.0e-04 loss: 2.676e-01]
latex_v1:   1%|          | 29/3000 [00:44<1:05:47,  1.33s/it, lr: 1.0e-04 loss: 5.513e-01]
latex_v1:   1%|          | 29/3000 [00:44<1:05:47,  1.33s/it, lr: 1.0e-04 loss: 5.513e-01]
latex_v1:   1%|1         | 30/3000 [00:45<1:05:45,  1.33s/it, lr: 1.0e-04 loss: 6.130e-01]
latex_v1:   1%|1         | 30/3000 [00:45<1:05:45,  1.33s/it, lr: 1.0e-04 loss: 6.130e-01]
latex_v1:   1%|1         | 31/3000 [00:45<43:55,  1.13it/s, lr: 1.0e-04 loss: 6.130e-01]  
latex_v1:   1%|1         | 31/3000 [00:45<43:55,  1.13it/s, lr: 1.0e-04 loss: 6.130e-01]  
latex_v1:   1%|1         | 31/3000 [00:47<43:55,  1.13it/s, lr: 1.0e-04 loss: 3.116e-01]
latex_v1:   1%|1         | 31/3000 [00:47<43:55,  1.13it/s, lr: 1.0e-04 loss: 3.116e-01]
latex_v1:   1%|1         | 32/3000 [00:47<50:35,  1.02s/it, lr: 1.0e-04 loss: 3.116e-01]
latex_v1:   1%|1         | 32/3000 [00:47<50:35,  1.02s/it, lr: 1.0e-04 loss: 3.116e-01]
latex_v1:   1%|1         | 32/3000 [00:48<50:35,  1.02s/it, lr: 1.0e-04 loss: 3.018e-01]
latex_v1:   1%|1         | 32/3000 [00:48<50:35,  1.02s/it, lr: 1.0e-04 loss: 3.018e-01]
latex_v1:   1%|1         | 33/3000 [00:48<54:57,  1.11s/it, lr: 1.0e-04 loss: 3.018e-01]
latex_v1:   1%|1         | 33/3000 [00:48<54:57,  1.11s/it, lr: 1.0e-04 loss: 3.018e-01]
latex_v1:   1%|1         | 33/3000 [00:49<54:57,  1.11s/it, lr: 1.0e-04 loss: 7.081e-01]
latex_v1:   1%|1         | 33/3000 [00:49<54:57,  1.11s/it, lr: 1.0e-04 loss: 7.081e-01]
latex_v1:   1%|1         | 34/3000 [00:49<55:44,  1.13s/it, lr: 1.0e-04 loss: 7.081e-01]
latex_v1:   1%|1         | 34/3000 [00:49<55:44,  1.13s/it, lr: 1.0e-04 loss: 7.081e-01]
latex_v1:   1%|1         | 34/3000 [00:51<55:44,  1.13s/it, lr: 1.0e-04 loss: 6.079e-01]
latex_v1:   1%|1         | 34/3000 [00:51<55:44,  1.13s/it, lr: 1.0e-04 loss: 6.079e-01]
latex_v1:   1%|1         | 35/3000 [00:51<1:01:18,  1.24s/it, lr: 1.0e-04 loss: 6.079e-01]
latex_v1:   1%|1         | 35/3000 [00:51<1:01:18,  1.24s/it, lr: 1.0e-04 loss: 6.079e-01]
latex_v1:   1%|1         | 35/3000 [00:52<1:01:18,  1.24s/it, lr: 1.0e-04 loss: 3.746e-01]
latex_v1:   1%|1         | 35/3000 [00:52<1:01:18,  1.24s/it, lr: 1.0e-04 loss: 3.746e-01]
latex_v1:   1%|1         | 36/3000 [00:52<1:02:30,  1.27s/it, lr: 1.0e-04 loss: 3.746e-01]
latex_v1:   1%|1         | 36/3000 [00:52<1:02:30,  1.27s/it, lr: 1.0e-04 loss: 3.746e-01]
latex_v1:   1%|1         | 36/3000 [00:54<1:02:30,  1.27s/it, lr: 1.0e-04 loss: 3.477e-01]
latex_v1:   1%|1         | 36/3000 [00:54<1:02:30,  1.27s/it, lr: 1.0e-04 loss: 3.477e-01]
latex_v1:   1%|1         | 37/3000 [00:54<1:15:34,  1.53s/it, lr: 1.0e-04 loss: 3.477e-01]
latex_v1:   1%|1         | 37/3000 [00:54<1:15:34,  1.53s/it, lr: 1.0e-04 loss: 3.477e-01]
latex_v1:   1%|1         | 37/3000 [00:55<1:15:34,  1.53s/it, lr: 1.0e-04 loss: 7.901e-01]
latex_v1:   1%|1         | 37/3000 [00:55<1:15:34,  1.53s/it, lr: 1.0e-04 loss: 7.901e-01]
latex_v1:   1%|1         | 38/3000 [00:55<1:12:33,  1.47s/it, lr: 1.0e-04 loss: 7.901e-01]
latex_v1:   1%|1         | 38/3000 [00:55<1:12:33,  1.47s/it, lr: 1.0e-04 loss: 7.901e-01]
latex_v1:   1%|1         | 38/3000 [00:57<1:12:33,  1.47s/it, lr: 1.0e-04 loss: 6.747e-01]
latex_v1:   1%|1         | 38/3000 [00:57<1:12:33,  1.47s/it, lr: 1.0e-04 loss: 6.747e-01]
latex_v1:   1%|1         | 39/3000 [00:57<1:13:45,  1.49s/it, lr: 1.0e-04 loss: 6.747e-01]
latex_v1:   1%|1         | 39/3000 [00:57<1:13:45,  1.49s/it, lr: 1.0e-04 loss: 6.747e-01]
latex_v1:   1%|1         | 39/3000 [01:00<1:13:45,  1.49s/it, lr: 1.0e-04 loss: 1.233e-01]
latex_v1:   1%|1         | 39/3000 [01:00<1:13:45,  1.49s/it, lr: 1.0e-04 loss: 1.233e-01]
latex_v1:   1%|1         | 40/3000 [01:01<1:13:43,  1.49s/it, lr: 1.0e-04 loss: 6.572e-01]
latex_v1:   1%|1         | 40/3000 [01:01<1:13:43,  1.49s/it, lr: 1.0e-04 loss: 6.572e-01]
latex_v1:   1%|1         | 41/3000 [01:01<51:08,  1.04s/it, lr: 1.0e-04 loss: 6.572e-01]  
latex_v1:   1%|1         | 41/3000 [01:01<51:08,  1.04s/it, lr: 1.0e-04 loss: 6.572e-01]  
latex_v1:   1%|1         | 41/3000 [01:02<51:08,  1.04s/it, lr: 1.0e-04 loss: 2.045e-01]
latex_v1:   1%|1         | 41/3000 [01:02<51:08,  1.04s/it, lr: 1.0e-04 loss: 2.045e-01]
latex_v1:   1%|1         | 42/3000 [01:02<57:22,  1.16s/it, lr: 1.0e-04 loss: 2.045e-01]
latex_v1:   1%|1         | 42/3000 [01:02<57:22,  1.16s/it, lr: 1.0e-04 loss: 2.045e-01]
latex_v1:   1%|1         | 42/3000 [01:04<57:22,  1.16s/it, lr: 1.0e-04 loss: 1.247e-01]
latex_v1:   1%|1         | 42/3000 [01:04<57:22,  1.16s/it, lr: 1.0e-04 loss: 1.247e-01]
latex_v1:   1%|1         | 43/3000 [01:04<1:01:04,  1.24s/it, lr: 1.0e-04 loss: 1.247e-01]
latex_v1:   1%|1         | 43/3000 [01:04<1:01:04,  1.24s/it, lr: 1.0e-04 loss: 1.247e-01]
latex_v1:   1%|1         | 43/3000 [01:05<1:01:04,  1.24s/it, lr: 1.0e-04 loss: 1.188e-01]
latex_v1:   1%|1         | 43/3000 [01:05<1:01:04,  1.24s/it, lr: 1.0e-04 loss: 1.188e-01]
latex_v1:   1%|1         | 44/3000 [01:05<1:04:52,  1.32s/it, lr: 1.0e-04 loss: 1.188e-01]
latex_v1:   1%|1         | 44/3000 [01:05<1:04:52,  1.32s/it, lr: 1.0e-04 loss: 1.188e-01]
latex_v1:   1%|1         | 44/3000 [01:06<1:04:52,  1.32s/it, lr: 1.0e-04 loss: 8.004e-02]
latex_v1:   1%|1         | 44/3000 [01:06<1:04:52,  1.32s/it, lr: 1.0e-04 loss: 8.004e-02]
latex_v1:   2%|1         | 45/3000 [01:06<1:02:52,  1.28s/it, lr: 1.0e-04 loss: 8.004e-02]
latex_v1:   2%|1         | 45/3000 [01:06<1:02:52,  1.28s/it, lr: 1.0e-04 loss: 8.004e-02]
latex_v1:   2%|1         | 45/3000 [01:09<1:02:52,  1.28s/it, lr: 1.0e-04 loss: 1.500e-01]
latex_v1:   2%|1         | 45/3000 [01:09<1:02:52,  1.28s/it, lr: 1.0e-04 loss: 1.500e-01]
latex_v1:   2%|1         | 46/3000 [01:09<1:24:25,  1.71s/it, lr: 1.0e-04 loss: 1.500e-01]
latex_v1:   2%|1         | 46/3000 [01:09<1:24:25,  1.71s/it, lr: 1.0e-04 loss: 1.500e-01]
latex_v1:   2%|1         | 46/3000 [01:10<1:24:25,  1.71s/it, lr: 1.0e-04 loss: 4.170e-01]
latex_v1:   2%|1         | 46/3000 [01:10<1:24:25,  1.71s/it, lr: 1.0e-04 loss: 4.170e-01]
latex_v1:   2%|1         | 47/3000 [01:10<1:10:34,  1.43s/it, lr: 1.0e-04 loss: 4.170e-01]
latex_v1:   2%|1         | 47/3000 [01:10<1:10:34,  1.43s/it, lr: 1.0e-04 loss: 4.170e-01]
latex_v1:   2%|1         | 47/3000 [01:11<1:10:34,  1.43s/it, lr: 1.0e-04 loss: 1.322e-01]
latex_v1:   2%|1         | 47/3000 [01:11<1:10:34,  1.43s/it, lr: 1.0e-04 loss: 1.322e-01]
latex_v1:   2%|1         | 48/3000 [01:11<1:11:57,  1.46s/it, lr: 1.0e-04 loss: 1.322e-01]
latex_v1:   2%|1         | 48/3000 [01:11<1:11:57,  1.46s/it, lr: 1.0e-04 loss: 1.322e-01]
latex_v1:   2%|1         | 48/3000 [01:12<1:11:57,  1.46s/it, lr: 1.0e-04 loss: 1.496e-01]
latex_v1:   2%|1         | 48/3000 [01:12<1:11:57,  1.46s/it, lr: 1.0e-04 loss: 1.496e-01]
latex_v1:   2%|1         | 49/3000 [01:12<1:01:50,  1.26s/it, lr: 1.0e-04 loss: 1.496e-01]
latex_v1:   2%|1         | 49/3000 [01:12<1:01:50,  1.26s/it, lr: 1.0e-04 loss: 1.496e-01]
latex_v1:   2%|1         | 49/3000 [01:14<1:01:50,  1.26s/it, lr: 1.0e-04 loss: 2.718e-01]
latex_v1:   2%|1         | 49/3000 [01:14<1:01:50,  1.26s/it, lr: 1.0e-04 loss: 2.718e-01]
latex_v1:   2%|1         | 50/3000 [01:16<1:01:48,  1.26s/it, lr: 1.0e-04 loss: 5.307e-01]
latex_v1:   2%|1         | 50/3000 [01:16<1:01:48,  1.26s/it, lr: 1.0e-04 loss: 5.307e-01]
latex_v1:   2%|1         | 51/3000 [01:16<54:44,  1.11s/it, lr: 1.0e-04 loss: 5.307e-01]  
latex_v1:   2%|1         | 51/3000 [01:16<54:44,  1.11s/it, lr: 1.0e-04 loss: 5.307e-01]  
latex_v1:   2%|1         | 51/3000 [01:17<54:44,  1.11s/it, lr: 1.0e-04 loss: 5.706e-01]
latex_v1:   2%|1         | 51/3000 [01:17<54:44,  1.11s/it, lr: 1.0e-04 loss: 5.706e-01]
latex_v1:   2%|1         | 52/3000 [01:17<58:48,  1.20s/it, lr: 1.0e-04 loss: 5.706e-01]
latex_v1:   2%|1         | 52/3000 [01:17<58:48,  1.20s/it, lr: 1.0e-04 loss: 5.706e-01]
latex_v1:   2%|1         | 52/3000 [01:19<58:48,  1.20s/it, lr: 1.0e-04 loss: 6.550e-02]
latex_v1:   2%|1         | 52/3000 [01:19<58:48,  1.20s/it, lr: 1.0e-04 loss: 6.550e-02]
latex_v1:   2%|1         | 53/3000 [01:19<1:04:35,  1.32s/it, lr: 1.0e-04 loss: 6.550e-02]
latex_v1:   2%|1         | 53/3000 [01:19<1:04:35,  1.32s/it, lr: 1.0e-04 loss: 6.550e-02]
latex_v1:   2%|1         | 53/3000 [01:21<1:04:35,  1.32s/it, lr: 1.0e-04 loss: 6.621e-01]
latex_v1:   2%|1         | 53/3000 [01:21<1:04:35,  1.32s/it, lr: 1.0e-04 loss: 6.621e-01]
latex_v1:   2%|1         | 54/3000 [01:21<1:13:44,  1.50s/it, lr: 1.0e-04 loss: 6.621e-01]
latex_v1:   2%|1         | 54/3000 [01:21<1:13:44,  1.50s/it, lr: 1.0e-04 loss: 6.621e-01]
latex_v1:   2%|1         | 54/3000 [01:21<1:13:44,  1.50s/it, lr: 1.0e-04 loss: 7.271e-02]
latex_v1:   2%|1         | 54/3000 [01:21<1:13:44,  1.50s/it, lr: 1.0e-04 loss: 7.271e-02]
latex_v1:   2%|1         | 55/3000 [01:21<1:03:15,  1.29s/it, lr: 1.0e-04 loss: 7.271e-02]
latex_v1:   2%|1         | 55/3000 [01:21<1:03:15,  1.29s/it, lr: 1.0e-04 loss: 7.271e-02]
latex_v1:   2%|1         | 55/3000 [01:22<1:03:15,  1.29s/it, lr: 1.0e-04 loss: 8.805e-02]
latex_v1:   2%|1         | 55/3000 [01:22<1:03:15,  1.29s/it, lr: 1.0e-04 loss: 8.805e-02]
latex_v1:   2%|1         | 56/3000 [01:22<55:45,  1.14s/it, lr: 1.0e-04 loss: 8.805e-02]  
latex_v1:   2%|1         | 56/3000 [01:22<55:45,  1.14s/it, lr: 1.0e-04 loss: 8.805e-02]  
latex_v1:   2%|1         | 56/3000 [01:24<55:45,  1.14s/it, lr: 1.0e-04 loss: 4.085e-01]
latex_v1:   2%|1         | 56/3000 [01:24<55:45,  1.14s/it, lr: 1.0e-04 loss: 4.085e-01]
latex_v1:   2%|1         | 57/3000 [01:24<1:05:40,  1.34s/it, lr: 1.0e-04 loss: 4.085e-01]
latex_v1:   2%|1         | 57/3000 [01:24<1:05:40,  1.34s/it, lr: 1.0e-04 loss: 4.085e-01]
latex_v1:   2%|1         | 57/3000 [01:25<1:05:40,  1.34s/it, lr: 1.0e-04 loss: 7.196e-01]
latex_v1:   2%|1         | 57/3000 [01:25<1:05:40,  1.34s/it, lr: 1.0e-04 loss: 7.196e-01]
latex_v1:   2%|1         | 58/3000 [01:25<57:13,  1.17s/it, lr: 1.0e-04 loss: 7.196e-01]  
latex_v1:   2%|1         | 58/3000 [01:25<57:13,  1.17s/it, lr: 1.0e-04 loss: 7.196e-01]  
latex_v1:   2%|1         | 58/3000 [01:28<57:13,  1.17s/it, lr: 1.0e-04 loss: 1.516e-01]
latex_v1:   2%|1         | 58/3000 [01:28<57:13,  1.17s/it, lr: 1.0e-04 loss: 1.516e-01]
latex_v1:   2%|1         | 59/3000 [01:28<1:21:45,  1.67s/it, lr: 1.0e-04 loss: 1.516e-01]
latex_v1:   2%|1         | 59/3000 [01:28<1:21:45,  1.67s/it, lr: 1.0e-04 loss: 1.516e-01]
latex_v1:   2%|1         | 59/3000 [01:29<1:21:45,  1.67s/it, lr: 1.0e-04 loss: 5.271e-01]
latex_v1:   2%|1         | 59/3000 [01:29<1:21:45,  1.67s/it, lr: 1.0e-04 loss: 5.271e-01]
latex_v1:   2%|2         | 60/3000 [01:31<1:21:43,  1.67s/it, lr: 1.0e-04 loss: 1.534e-01]
latex_v1:   2%|2         | 60/3000 [01:31<1:21:43,  1.67s/it, lr: 1.0e-04 loss: 1.534e-01]
latex_v1:   2%|2         | 61/3000 [01:31<1:06:23,  1.36s/it, lr: 1.0e-04 loss: 1.534e-01]
latex_v1:   2%|2         | 61/3000 [01:31<1:06:23,  1.36s/it, lr: 1.0e-04 loss: 1.534e-01]
latex_v1:   2%|2         | 61/3000 [01:33<1:06:23,  1.36s/it, lr: 1.0e-04 loss: 5.562e-01]
latex_v1:   2%|2         | 61/3000 [01:33<1:06:23,  1.36s/it, lr: 1.0e-04 loss: 5.562e-01]
latex_v1:   2%|2         | 62/3000 [01:33<1:08:26,  1.40s/it, lr: 1.0e-04 loss: 5.562e-01]
latex_v1:   2%|2         | 62/3000 [01:33<1:08:26,  1.40s/it, lr: 1.0e-04 loss: 5.562e-01]
latex_v1:   2%|2         | 62/3000 [01:34<1:08:26,  1.40s/it, lr: 1.0e-04 loss: 5.926e-01]
latex_v1:   2%|2         | 62/3000 [01:34<1:08:26,  1.40s/it, lr: 1.0e-04 loss: 5.926e-01]
latex_v1:   2%|2         | 63/3000 [01:34<1:04:06,  1.31s/it, lr: 1.0e-04 loss: 5.926e-01]
latex_v1:   2%|2         | 63/3000 [01:34<1:04:06,  1.31s/it, lr: 1.0e-04 loss: 5.926e-01]
latex_v1:   2%|2         | 63/3000 [01:37<1:04:06,  1.31s/it, lr: 1.0e-04 loss: 9.768e-02]
latex_v1:   2%|2         | 63/3000 [01:37<1:04:06,  1.31s/it, lr: 1.0e-04 loss: 9.768e-02]
latex_v1:   2%|2         | 64/3000 [01:37<1:25:05,  1.74s/it, lr: 1.0e-04 loss: 9.768e-02]
latex_v1:   2%|2         | 64/3000 [01:37<1:25:05,  1.74s/it, lr: 1.0e-04 loss: 9.768e-02]
latex_v1:   2%|2         | 64/3000 [01:38<1:25:05,  1.74s/it, lr: 1.0e-04 loss: 4.730e-01]
latex_v1:   2%|2         | 64/3000 [01:38<1:25:05,  1.74s/it, lr: 1.0e-04 loss: 4.730e-01]
latex_v1:   2%|2         | 65/3000 [01:38<1:11:31,  1.46s/it, lr: 1.0e-04 loss: 4.730e-01]
latex_v1:   2%|2         | 65/3000 [01:38<1:11:31,  1.46s/it, lr: 1.0e-04 loss: 4.730e-01]
latex_v1:   2%|2         | 65/3000 [01:39<1:11:31,  1.46s/it, lr: 1.0e-04 loss: 5.257e-02]
latex_v1:   2%|2         | 65/3000 [01:39<1:11:31,  1.46s/it, lr: 1.0e-04 loss: 5.257e-02]
latex_v1:   2%|2         | 66/3000 [01:39<1:12:16,  1.48s/it, lr: 1.0e-04 loss: 5.257e-02]
latex_v1:   2%|2         | 66/3000 [01:39<1:12:16,  1.48s/it, lr: 1.0e-04 loss: 5.257e-02]
latex_v1:   2%|2         | 66/3000 [01:41<1:12:16,  1.48s/it, lr: 1.0e-04 loss: 2.655e-01]
latex_v1:   2%|2         | 66/3000 [01:41<1:12:16,  1.48s/it, lr: 1.0e-04 loss: 2.655e-01]
latex_v1:   2%|2         | 67/3000 [01:41<1:15:07,  1.54s/it, lr: 1.0e-04 loss: 2.655e-01]
latex_v1:   2%|2         | 67/3000 [01:41<1:15:07,  1.54s/it, lr: 1.0e-04 loss: 2.655e-01]
latex_v1:   2%|2         | 67/3000 [01:42<1:15:07,  1.54s/it, lr: 1.0e-04 loss: 2.163e-01]
latex_v1:   2%|2         | 67/3000 [01:42<1:15:07,  1.54s/it, lr: 1.0e-04 loss: 2.163e-01]
latex_v1:   2%|2         | 68/3000 [01:42<1:03:54,  1.31s/it, lr: 1.0e-04 loss: 2.163e-01]
latex_v1:   2%|2         | 68/3000 [01:42<1:03:54,  1.31s/it, lr: 1.0e-04 loss: 2.163e-01]
latex_v1:   2%|2         | 68/3000 [01:43<1:03:54,  1.31s/it, lr: 1.0e-04 loss: 2.188e-01]
latex_v1:   2%|2         | 68/3000 [01:43<1:03:54,  1.31s/it, lr: 1.0e-04 loss: 2.188e-01]
latex_v1:   2%|2         | 69/3000 [01:43<1:05:48,  1.35s/it, lr: 1.0e-04 loss: 2.188e-01]
latex_v1:   2%|2         | 69/3000 [01:43<1:05:48,  1.35s/it, lr: 1.0e-04 loss: 2.188e-01]
latex_v1:   2%|2         | 69/3000 [01:44<1:05:48,  1.35s/it, lr: 1.0e-04 loss: 7.097e-01]
latex_v1:   2%|2         | 69/3000 [01:44<1:05:48,  1.35s/it, lr: 1.0e-04 loss: 7.097e-01]
latex_v1:   2%|2         | 70/3000 [01:45<1:05:47,  1.35s/it, lr: 1.0e-04 loss: 2.738e-01]
latex_v1:   2%|2         | 70/3000 [01:45<1:05:47,  1.35s/it, lr: 1.0e-04 loss: 2.738e-01]
latex_v1:   2%|2         | 71/3000 [01:45<44:00,  1.11it/s, lr: 1.0e-04 loss: 2.738e-01]  
latex_v1:   2%|2         | 71/3000 [01:45<44:00,  1.11it/s, lr: 1.0e-04 loss: 2.738e-01]  
latex_v1:   2%|2         | 71/3000 [01:47<44:00,  1.11it/s, lr: 1.0e-04 loss: 2.692e-01]
latex_v1:   2%|2         | 71/3000 [01:47<44:00,  1.11it/s, lr: 1.0e-04 loss: 2.692e-01]
latex_v1:   2%|2         | 72/3000 [01:47<53:47,  1.10s/it, lr: 1.0e-04 loss: 2.692e-01]
latex_v1:   2%|2         | 72/3000 [01:47<53:47,  1.10s/it, lr: 1.0e-04 loss: 2.692e-01]
latex_v1:   2%|2         | 72/3000 [01:48<53:47,  1.10s/it, lr: 1.0e-04 loss: 9.963e-02]
latex_v1:   2%|2         | 72/3000 [01:48<53:47,  1.10s/it, lr: 1.0e-04 loss: 9.963e-02]
latex_v1:   2%|2         | 73/3000 [01:48<49:31,  1.02s/it, lr: 1.0e-04 loss: 9.963e-02]
latex_v1:   2%|2         | 73/3000 [01:48<49:31,  1.02s/it, lr: 1.0e-04 loss: 9.963e-02]
latex_v1:   2%|2         | 73/3000 [01:48<49:31,  1.02s/it, lr: 1.0e-04 loss: 2.722e-01]
latex_v1:   2%|2         | 73/3000 [01:48<49:31,  1.02s/it, lr: 1.0e-04 loss: 2.722e-01]
latex_v1:   2%|2         | 74/3000 [01:48<45:58,  1.06it/s, lr: 1.0e-04 loss: 2.722e-01]
latex_v1:   2%|2         | 74/3000 [01:48<45:58,  1.06it/s, lr: 1.0e-04 loss: 2.722e-01]
latex_v1:   2%|2         | 74/3000 [01:49<45:58,  1.06it/s, lr: 1.0e-04 loss: 6.239e-01]
latex_v1:   2%|2         | 74/3000 [01:49<45:58,  1.06it/s, lr: 1.0e-04 loss: 6.239e-01]
latex_v1:   2%|2         | 75/3000 [01:49<46:07,  1.06it/s, lr: 1.0e-04 loss: 6.239e-01]
latex_v1:   2%|2         | 75/3000 [01:49<46:07,  1.06it/s, lr: 1.0e-04 loss: 6.239e-01]
latex_v1:   2%|2         | 75/3000 [01:50<46:07,  1.06it/s, lr: 1.0e-04 loss: 2.614e-02]
latex_v1:   2%|2         | 75/3000 [01:50<46:07,  1.06it/s, lr: 1.0e-04 loss: 2.614e-02]
latex_v1:   3%|2         | 76/3000 [01:50<43:21,  1.12it/s, lr: 1.0e-04 loss: 2.614e-02]
latex_v1:   3%|2         | 76/3000 [01:50<43:21,  1.12it/s, lr: 1.0e-04 loss: 2.614e-02]
latex_v1:   3%|2         | 76/3000 [01:51<43:21,  1.12it/s, lr: 1.0e-04 loss: 2.392e-02]
latex_v1:   3%|2         | 76/3000 [01:51<43:21,  1.12it/s, lr: 1.0e-04 loss: 2.392e-02]
latex_v1:   3%|2         | 77/3000 [01:51<47:27,  1.03it/s, lr: 1.0e-04 loss: 2.392e-02]
latex_v1:   3%|2         | 77/3000 [01:51<47:27,  1.03it/s, lr: 1.0e-04 loss: 2.392e-02]
latex_v1:   3%|2         | 77/3000 [01:52<47:27,  1.03it/s, lr: 1.0e-04 loss: 6.532e-01]
latex_v1:   3%|2         | 77/3000 [01:52<47:27,  1.03it/s, lr: 1.0e-04 loss: 6.532e-01]
latex_v1:   3%|2         | 78/3000 [01:52<44:05,  1.10it/s, lr: 1.0e-04 loss: 6.532e-01]
latex_v1:   3%|2         | 78/3000 [01:52<44:05,  1.10it/s, lr: 1.0e-04 loss: 6.532e-01]
latex_v1:   3%|2         | 78/3000 [01:53<44:05,  1.10it/s, lr: 1.0e-04 loss: 4.258e-01]
latex_v1:   3%|2         | 78/3000 [01:53<44:05,  1.10it/s, lr: 1.0e-04 loss: 4.258e-01]
latex_v1:   3%|2         | 79/3000 [01:53<51:09,  1.05s/it, lr: 1.0e-04 loss: 4.258e-01]
latex_v1:   3%|2         | 79/3000 [01:53<51:09,  1.05s/it, lr: 1.0e-04 loss: 4.258e-01]
latex_v1:   3%|2         | 79/3000 [01:55<51:09,  1.05s/it, lr: 1.0e-04 loss: 2.708e-01]
latex_v1:   3%|2         | 79/3000 [01:55<51:09,  1.05s/it, lr: 1.0e-04 loss: 2.708e-01]
latex_v1:   3%|2         | 80/3000 [01:56<51:08,  1.05s/it, lr: 1.0e-04 loss: 3.210e-01]
latex_v1:   3%|2         | 80/3000 [01:56<51:08,  1.05s/it, lr: 1.0e-04 loss: 3.210e-01]
latex_v1:   3%|2         | 81/3000 [01:56<44:48,  1.09it/s, lr: 1.0e-04 loss: 3.210e-01]
latex_v1:   3%|2         | 81/3000 [01:56<44:48,  1.09it/s, lr: 1.0e-04 loss: 3.210e-01]
latex_v1:   3%|2         | 81/3000 [01:57<44:48,  1.09it/s, lr: 1.0e-04 loss: 3.026e-01]
latex_v1:   3%|2         | 81/3000 [01:57<44:48,  1.09it/s, lr: 1.0e-04 loss: 3.026e-01]
latex_v1:   3%|2         | 82/3000 [01:57<47:48,  1.02it/s, lr: 1.0e-04 loss: 3.026e-01]
latex_v1:   3%|2         | 82/3000 [01:57<47:48,  1.02it/s, lr: 1.0e-04 loss: 3.026e-01]
latex_v1:   3%|2         | 82/3000 [01:59<47:48,  1.02it/s, lr: 1.0e-04 loss: 2.065e-01]
latex_v1:   3%|2         | 82/3000 [01:59<47:48,  1.02it/s, lr: 1.0e-04 loss: 2.065e-01]
latex_v1:   3%|2         | 83/3000 [01:59<50:05,  1.03s/it, lr: 1.0e-04 loss: 2.065e-01]
latex_v1:   3%|2         | 83/3000 [01:59<50:05,  1.03s/it, lr: 1.0e-04 loss: 2.065e-01]
latex_v1:   3%|2         | 83/3000 [01:59<50:05,  1.03s/it, lr: 1.0e-04 loss: 5.629e-01]
latex_v1:   3%|2         | 83/3000 [01:59<50:05,  1.03s/it, lr: 1.0e-04 loss: 5.629e-01]
latex_v1:   3%|2         | 84/3000 [01:59<46:15,  1.05it/s, lr: 1.0e-04 loss: 5.629e-01]
latex_v1:   3%|2         | 84/3000 [01:59<46:15,  1.05it/s, lr: 1.0e-04 loss: 5.629e-01]
latex_v1:   3%|2         | 84/3000 [02:01<46:15,  1.05it/s, lr: 1.0e-04 loss: 2.503e-01]
latex_v1:   3%|2         | 84/3000 [02:01<46:15,  1.05it/s, lr: 1.0e-04 loss: 2.503e-01]
latex_v1:   3%|2         | 85/3000 [02:01<54:06,  1.11s/it, lr: 1.0e-04 loss: 2.503e-01]
latex_v1:   3%|2         | 85/3000 [02:01<54:06,  1.11s/it, lr: 1.0e-04 loss: 2.503e-01]
latex_v1:   3%|2         | 85/3000 [02:02<54:06,  1.11s/it, lr: 1.0e-04 loss: 5.858e-01]
latex_v1:   3%|2         | 85/3000 [02:02<54:06,  1.11s/it, lr: 1.0e-04 loss: 5.858e-01]
latex_v1:   3%|2         | 86/3000 [02:02<58:23,  1.20s/it, lr: 1.0e-04 loss: 5.858e-01]
latex_v1:   3%|2         | 86/3000 [02:02<58:23,  1.20s/it, lr: 1.0e-04 loss: 5.858e-01]
latex_v1:   3%|2         | 86/3000 [02:05<58:23,  1.20s/it, lr: 1.0e-04 loss: 6.096e-01]
latex_v1:   3%|2         | 86/3000 [02:05<58:23,  1.20s/it, lr: 1.0e-04 loss: 6.096e-01]
latex_v1:   3%|2         | 87/3000 [02:05<1:21:00,  1.67s/it, lr: 1.0e-04 loss: 6.096e-01]
latex_v1:   3%|2         | 87/3000 [02:05<1:21:00,  1.67s/it, lr: 1.0e-04 loss: 6.096e-01]
latex_v1:   3%|2         | 87/3000 [02:06<1:21:00,  1.67s/it, lr: 1.0e-04 loss: 5.744e-01]
latex_v1:   3%|2         | 87/3000 [02:06<1:21:00,  1.67s/it, lr: 1.0e-04 loss: 5.744e-01]
latex_v1:   3%|2         | 88/3000 [02:06<1:08:01,  1.40s/it, lr: 1.0e-04 loss: 5.744e-01]
latex_v1:   3%|2         | 88/3000 [02:06<1:08:01,  1.40s/it, lr: 1.0e-04 loss: 5.744e-01]
latex_v1:   3%|2         | 88/3000 [02:07<1:08:01,  1.40s/it, lr: 1.0e-04 loss: 7.628e-01]
latex_v1:   3%|2         | 88/3000 [02:07<1:08:01,  1.40s/it, lr: 1.0e-04 loss: 7.628e-01]
latex_v1:   3%|2         | 89/3000 [02:07<58:49,  1.21s/it, lr: 1.0e-04 loss: 7.628e-01]  
latex_v1:   3%|2         | 89/3000 [02:07<58:49,  1.21s/it, lr: 1.0e-04 loss: 7.628e-01]  
latex_v1:   3%|2         | 89/3000 [02:07<58:49,  1.21s/it, lr: 1.0e-04 loss: 6.509e-01]
latex_v1:   3%|2         | 89/3000 [02:07<58:49,  1.21s/it, lr: 1.0e-04 loss: 6.509e-01]
latex_v1:   3%|3         | 90/3000 [02:08<58:47,  1.21s/it, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:   3%|3         | 90/3000 [02:08<58:47,  1.21s/it, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:   3%|3         | 91/3000 [02:08<39:56,  1.21it/s, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:   3%|3         | 91/3000 [02:08<39:56,  1.21it/s, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:   3%|3         | 91/3000 [02:10<39:56,  1.21it/s, lr: 1.0e-04 loss: 5.288e-01]
latex_v1:   3%|3         | 91/3000 [02:10<39:56,  1.21it/s, lr: 1.0e-04 loss: 5.288e-01]
latex_v1:   3%|3         | 92/3000 [02:10<48:46,  1.01s/it, lr: 1.0e-04 loss: 5.288e-01]
latex_v1:   3%|3         | 92/3000 [02:10<48:46,  1.01s/it, lr: 1.0e-04 loss: 5.288e-01]
latex_v1:   3%|3         | 92/3000 [02:11<48:46,  1.01s/it, lr: 1.0e-04 loss: 5.904e-01]
latex_v1:   3%|3         | 92/3000 [02:11<48:46,  1.01s/it, lr: 1.0e-04 loss: 5.904e-01]
latex_v1:   3%|3         | 93/3000 [02:11<55:50,  1.15s/it, lr: 1.0e-04 loss: 5.904e-01]
latex_v1:   3%|3         | 93/3000 [02:11<55:50,  1.15s/it, lr: 1.0e-04 loss: 5.904e-01]
latex_v1:   3%|3         | 93/3000 [02:12<55:50,  1.15s/it, lr: 1.0e-04 loss: 3.868e-01]
latex_v1:   3%|3         | 93/3000 [02:12<55:50,  1.15s/it, lr: 1.0e-04 loss: 3.868e-01]
latex_v1:   3%|3         | 94/3000 [02:12<50:21,  1.04s/it, lr: 1.0e-04 loss: 3.868e-01]
latex_v1:   3%|3         | 94/3000 [02:12<50:21,  1.04s/it, lr: 1.0e-04 loss: 3.868e-01]
latex_v1:   3%|3         | 94/3000 [02:13<50:21,  1.04s/it, lr: 1.0e-04 loss: 8.076e-01]
latex_v1:   3%|3         | 94/3000 [02:13<50:21,  1.04s/it, lr: 1.0e-04 loss: 8.076e-01]
latex_v1:   3%|3         | 95/3000 [02:13<50:19,  1.04s/it, lr: 1.0e-04 loss: 8.076e-01]
latex_v1:   3%|3         | 95/3000 [02:13<50:19,  1.04s/it, lr: 1.0e-04 loss: 8.076e-01]
latex_v1:   3%|3         | 95/3000 [02:14<50:19,  1.04s/it, lr: 1.0e-04 loss: 2.320e-01]
latex_v1:   3%|3         | 95/3000 [02:14<50:19,  1.04s/it, lr: 1.0e-04 loss: 2.320e-01]
latex_v1:   3%|3         | 96/3000 [02:14<46:15,  1.05it/s, lr: 1.0e-04 loss: 2.320e-01]
latex_v1:   3%|3         | 96/3000 [02:14<46:15,  1.05it/s, lr: 1.0e-04 loss: 2.320e-01]
latex_v1:   3%|3         | 96/3000 [02:15<46:15,  1.05it/s, lr: 1.0e-04 loss: 1.668e-01]
latex_v1:   3%|3         | 96/3000 [02:15<46:15,  1.05it/s, lr: 1.0e-04 loss: 1.668e-01]
latex_v1:   3%|3         | 97/3000 [02:15<53:07,  1.10s/it, lr: 1.0e-04 loss: 1.668e-01]
latex_v1:   3%|3         | 97/3000 [02:15<53:07,  1.10s/it, lr: 1.0e-04 loss: 1.668e-01]
latex_v1:   3%|3         | 97/3000 [02:17<53:07,  1.10s/it, lr: 1.0e-04 loss: 9.997e-02]
latex_v1:   3%|3         | 97/3000 [02:17<53:07,  1.10s/it, lr: 1.0e-04 loss: 9.997e-02]
latex_v1:   3%|3         | 98/3000 [02:17<1:04:05,  1.32s/it, lr: 1.0e-04 loss: 9.997e-02]
latex_v1:   3%|3         | 98/3000 [02:17<1:04:05,  1.32s/it, lr: 1.0e-04 loss: 9.997e-02]
latex_v1:   3%|3         | 98/3000 [02:20<1:04:05,  1.32s/it, lr: 1.0e-04 loss: 1.076e-01]
latex_v1:   3%|3         | 98/3000 [02:20<1:04:05,  1.32s/it, lr: 1.0e-04 loss: 1.076e-01]
latex_v1:   3%|3         | 99/3000 [02:20<1:25:48,  1.77s/it, lr: 1.0e-04 loss: 1.076e-01]
latex_v1:   3%|3         | 99/3000 [02:20<1:25:48,  1.77s/it, lr: 1.0e-04 loss: 1.076e-01]
latex_v1:   3%|3         | 99/3000 [02:22<1:25:48,  1.77s/it, lr: 1.0e-04 loss: 1.842e-01]
latex_v1:   3%|3         | 99/3000 [02:22<1:25:48,  1.77s/it, lr: 1.0e-04 loss: 1.842e-01]
latex_v1:   3%|3         | 100/3000 [02:23<1:25:46,  1.77s/it, lr: 1.0e-04 loss: 2.481e-01]
latex_v1:   3%|3         | 100/3000 [02:23<1:25:46,  1.77s/it, lr: 1.0e-04 loss: 2.481e-01]
latex_v1:   3%|3         | 101/3000 [02:23<57:01,  1.18s/it, lr: 1.0e-04 loss: 2.481e-01]  
latex_v1:   3%|3         | 101/3000 [02:23<57:01,  1.18s/it, lr: 1.0e-04 loss: 2.481e-01]  
latex_v1:   3%|3         | 101/3000 [02:25<57:01,  1.18s/it, lr: 1.0e-04 loss: 2.293e-01]
latex_v1:   3%|3         | 101/3000 [02:25<57:01,  1.18s/it, lr: 1.0e-04 loss: 2.293e-01]
latex_v1:   3%|3         | 102/3000 [02:25<1:05:16,  1.35s/it, lr: 1.0e-04 loss: 2.293e-01]
latex_v1:   3%|3         | 102/3000 [02:25<1:05:16,  1.35s/it, lr: 1.0e-04 loss: 2.293e-01]
latex_v1:   3%|3         | 102/3000 [02:26<1:05:16,  1.35s/it, lr: 1.0e-04 loss: 6.385e-01]
latex_v1:   3%|3         | 102/3000 [02:26<1:05:16,  1.35s/it, lr: 1.0e-04 loss: 6.385e-01]
latex_v1:   3%|3         | 103/3000 [02:26<1:05:58,  1.37s/it, lr: 1.0e-04 loss: 6.385e-01]
latex_v1:   3%|3         | 103/3000 [02:26<1:05:58,  1.37s/it, lr: 1.0e-04 loss: 6.385e-01]
latex_v1:   3%|3         | 103/3000 [02:27<1:05:58,  1.37s/it, lr: 1.0e-04 loss: 4.218e-01]
latex_v1:   3%|3         | 103/3000 [02:27<1:05:58,  1.37s/it, lr: 1.0e-04 loss: 4.218e-01]
latex_v1:   3%|3         | 104/3000 [02:27<57:43,  1.20s/it, lr: 1.0e-04 loss: 4.218e-01]  
latex_v1:   3%|3         | 104/3000 [02:27<57:43,  1.20s/it, lr: 1.0e-04 loss: 4.218e-01]  
latex_v1:   3%|3         | 104/3000 [02:28<57:43,  1.20s/it, lr: 1.0e-04 loss: 7.045e-01]
latex_v1:   3%|3         | 104/3000 [02:28<57:43,  1.20s/it, lr: 1.0e-04 loss: 7.045e-01]
latex_v1:   4%|3         | 105/3000 [02:28<57:32,  1.19s/it, lr: 1.0e-04 loss: 7.045e-01]
latex_v1:   4%|3         | 105/3000 [02:28<57:32,  1.19s/it, lr: 1.0e-04 loss: 7.045e-01]
latex_v1:   4%|3         | 105/3000 [02:29<57:32,  1.19s/it, lr: 1.0e-04 loss: 6.928e-02]
latex_v1:   4%|3         | 105/3000 [02:29<57:32,  1.19s/it, lr: 1.0e-04 loss: 6.928e-02]
latex_v1:   4%|3         | 106/3000 [02:29<1:02:09,  1.29s/it, lr: 1.0e-04 loss: 6.928e-02]
latex_v1:   4%|3         | 106/3000 [02:29<1:02:09,  1.29s/it, lr: 1.0e-04 loss: 6.928e-02]
latex_v1:   4%|3         | 106/3000 [02:31<1:02:09,  1.29s/it, lr: 1.0e-04 loss: 1.657e-01]
latex_v1:   4%|3         | 106/3000 [02:31<1:02:09,  1.29s/it, lr: 1.0e-04 loss: 1.657e-01]
latex_v1:   4%|3         | 107/3000 [02:31<1:05:31,  1.36s/it, lr: 1.0e-04 loss: 1.657e-01]
latex_v1:   4%|3         | 107/3000 [02:31<1:05:31,  1.36s/it, lr: 1.0e-04 loss: 1.657e-01]
latex_v1:   4%|3         | 107/3000 [02:33<1:05:31,  1.36s/it, lr: 1.0e-04 loss: 6.368e-01]
latex_v1:   4%|3         | 107/3000 [02:33<1:05:31,  1.36s/it, lr: 1.0e-04 loss: 6.368e-01]
latex_v1:   4%|3         | 108/3000 [02:33<1:10:14,  1.46s/it, lr: 1.0e-04 loss: 6.368e-01]
latex_v1:   4%|3         | 108/3000 [02:33<1:10:14,  1.46s/it, lr: 1.0e-04 loss: 6.368e-01]
latex_v1:   4%|3         | 108/3000 [02:34<1:10:14,  1.46s/it, lr: 1.0e-04 loss: 2.025e-01]
latex_v1:   4%|3         | 108/3000 [02:34<1:10:14,  1.46s/it, lr: 1.0e-04 loss: 2.025e-01]
latex_v1:   4%|3         | 109/3000 [02:35<1:16:14,  1.58s/it, lr: 1.0e-04 loss: 2.025e-01]
latex_v1:   4%|3         | 109/3000 [02:35<1:16:14,  1.58s/it, lr: 1.0e-04 loss: 2.025e-01]
latex_v1:   4%|3         | 109/3000 [02:36<1:16:14,  1.58s/it, lr: 1.0e-04 loss: 8.535e-01]
latex_v1:   4%|3         | 109/3000 [02:36<1:16:14,  1.58s/it, lr: 1.0e-04 loss: 8.535e-01]
latex_v1:   4%|3         | 110/3000 [02:37<1:16:13,  1.58s/it, lr: 1.0e-04 loss: 4.069e-01]
latex_v1:   4%|3         | 110/3000 [02:37<1:16:13,  1.58s/it, lr: 1.0e-04 loss: 4.069e-01]
latex_v1:   4%|3         | 111/3000 [02:37<56:24,  1.17s/it, lr: 1.0e-04 loss: 4.069e-01]  
latex_v1:   4%|3         | 111/3000 [02:37<56:24,  1.17s/it, lr: 1.0e-04 loss: 4.069e-01]  
latex_v1:   4%|3         | 111/3000 [02:39<56:24,  1.17s/it, lr: 1.0e-04 loss: 3.242e-01]
latex_v1:   4%|3         | 111/3000 [02:39<56:24,  1.17s/it, lr: 1.0e-04 loss: 3.242e-01]
latex_v1:   4%|3         | 112/3000 [02:39<1:04:41,  1.34s/it, lr: 1.0e-04 loss: 3.242e-01]
latex_v1:   4%|3         | 112/3000 [02:39<1:04:41,  1.34s/it, lr: 1.0e-04 loss: 3.242e-01]
latex_v1:   4%|3         | 112/3000 [02:40<1:04:41,  1.34s/it, lr: 1.0e-04 loss: 5.734e-01]
latex_v1:   4%|3         | 112/3000 [02:40<1:04:41,  1.34s/it, lr: 1.0e-04 loss: 5.734e-01]
latex_v1:   4%|3         | 113/3000 [02:40<56:56,  1.18s/it, lr: 1.0e-04 loss: 5.734e-01]  
latex_v1:   4%|3         | 113/3000 [02:40<56:56,  1.18s/it, lr: 1.0e-04 loss: 5.734e-01]  
latex_v1:   4%|3         | 113/3000 [02:41<56:56,  1.18s/it, lr: 1.0e-04 loss: 6.314e-01]
latex_v1:   4%|3         | 113/3000 [02:41<56:56,  1.18s/it, lr: 1.0e-04 loss: 6.314e-01]
latex_v1:   4%|3         | 114/3000 [02:41<59:51,  1.24s/it, lr: 1.0e-04 loss: 6.314e-01]
latex_v1:   4%|3         | 114/3000 [02:41<59:51,  1.24s/it, lr: 1.0e-04 loss: 6.314e-01]
latex_v1:   4%|3         | 114/3000 [02:42<59:51,  1.24s/it, lr: 1.0e-04 loss: 1.550e-01]
latex_v1:   4%|3         | 114/3000 [02:42<59:51,  1.24s/it, lr: 1.0e-04 loss: 1.550e-01]
latex_v1:   4%|3         | 115/3000 [02:42<53:35,  1.11s/it, lr: 1.0e-04 loss: 1.550e-01]
latex_v1:   4%|3         | 115/3000 [02:42<53:35,  1.11s/it, lr: 1.0e-04 loss: 1.550e-01]
latex_v1:   4%|3         | 115/3000 [02:43<53:35,  1.11s/it, lr: 1.0e-04 loss: 5.585e-02]
latex_v1:   4%|3         | 115/3000 [02:43<53:35,  1.11s/it, lr: 1.0e-04 loss: 5.585e-02]
latex_v1:   4%|3         | 116/3000 [02:43<48:52,  1.02s/it, lr: 1.0e-04 loss: 5.585e-02]
latex_v1:   4%|3         | 116/3000 [02:43<48:52,  1.02s/it, lr: 1.0e-04 loss: 5.585e-02]
latex_v1:   4%|3         | 116/3000 [02:43<48:52,  1.02s/it, lr: 1.0e-04 loss: 4.827e-01]
latex_v1:   4%|3         | 116/3000 [02:43<48:52,  1.02s/it, lr: 1.0e-04 loss: 4.827e-01]
latex_v1:   4%|3         | 117/3000 [02:43<45:16,  1.06it/s, lr: 1.0e-04 loss: 4.827e-01]
latex_v1:   4%|3         | 117/3000 [02:43<45:16,  1.06it/s, lr: 1.0e-04 loss: 4.827e-01]
latex_v1:   4%|3         | 117/3000 [02:45<45:16,  1.06it/s, lr: 1.0e-04 loss: 5.547e-01]
latex_v1:   4%|3         | 117/3000 [02:45<45:16,  1.06it/s, lr: 1.0e-04 loss: 5.547e-01]
latex_v1:   4%|3         | 118/3000 [02:45<59:51,  1.25s/it, lr: 1.0e-04 loss: 5.547e-01]
latex_v1:   4%|3         | 118/3000 [02:45<59:51,  1.25s/it, lr: 1.0e-04 loss: 5.547e-01]
latex_v1:   4%|3         | 118/3000 [02:48<59:51,  1.25s/it, lr: 1.0e-04 loss: 6.018e-01]
latex_v1:   4%|3         | 118/3000 [02:48<59:51,  1.25s/it, lr: 1.0e-04 loss: 6.018e-01]
latex_v1:   4%|3         | 119/3000 [02:48<1:22:46,  1.72s/it, lr: 1.0e-04 loss: 6.018e-01]
latex_v1:   4%|3         | 119/3000 [02:48<1:22:46,  1.72s/it, lr: 1.0e-04 loss: 6.018e-01]
latex_v1:   4%|3         | 119/3000 [02:49<1:22:46,  1.72s/it, lr: 1.0e-04 loss: 5.525e-01]
latex_v1:   4%|3         | 119/3000 [02:49<1:22:46,  1.72s/it, lr: 1.0e-04 loss: 5.525e-01]
latex_v1:   4%|4         | 120/3000 [02:50<1:22:44,  1.72s/it, lr: 1.0e-04 loss: 1.326e-01]
latex_v1:   4%|4         | 120/3000 [02:50<1:22:44,  1.72s/it, lr: 1.0e-04 loss: 1.326e-01]
latex_v1:   4%|4         | 121/3000 [02:50<55:42,  1.16s/it, lr: 1.0e-04 loss: 1.326e-01]  
latex_v1:   4%|4         | 121/3000 [02:50<55:42,  1.16s/it, lr: 1.0e-04 loss: 1.326e-01]  
latex_v1:   4%|4         | 121/3000 [02:51<55:42,  1.16s/it, lr: 1.0e-04 loss: 6.076e-01]
latex_v1:   4%|4         | 121/3000 [02:51<55:42,  1.16s/it, lr: 1.0e-04 loss: 6.076e-01]
latex_v1:   4%|4         | 122/3000 [02:51<50:53,  1.06s/it, lr: 1.0e-04 loss: 6.076e-01]
latex_v1:   4%|4         | 122/3000 [02:51<50:53,  1.06s/it, lr: 1.0e-04 loss: 6.076e-01]
latex_v1:   4%|4         | 122/3000 [02:52<50:53,  1.06s/it, lr: 1.0e-04 loss: 9.270e-02]
latex_v1:   4%|4         | 122/3000 [02:52<50:53,  1.06s/it, lr: 1.0e-04 loss: 9.270e-02]
latex_v1:   4%|4         | 123/3000 [02:52<57:12,  1.19s/it, lr: 1.0e-04 loss: 9.270e-02]
latex_v1:   4%|4         | 123/3000 [02:52<57:12,  1.19s/it, lr: 1.0e-04 loss: 9.270e-02]
latex_v1:   4%|4         | 123/3000 [02:53<57:12,  1.19s/it, lr: 1.0e-04 loss: 5.959e-02]
latex_v1:   4%|4         | 123/3000 [02:53<57:12,  1.19s/it, lr: 1.0e-04 loss: 5.959e-02]
latex_v1:   4%|4         | 124/3000 [02:53<51:15,  1.07s/it, lr: 1.0e-04 loss: 5.959e-02]
latex_v1:   4%|4         | 124/3000 [02:53<51:15,  1.07s/it, lr: 1.0e-04 loss: 5.959e-02]
latex_v1:   4%|4         | 124/3000 [02:54<51:15,  1.07s/it, lr: 1.0e-04 loss: 1.217e-01]
latex_v1:   4%|4         | 124/3000 [02:54<51:15,  1.07s/it, lr: 1.0e-04 loss: 1.217e-01]
latex_v1:   4%|4         | 125/3000 [02:54<56:15,  1.17s/it, lr: 1.0e-04 loss: 1.217e-01]
latex_v1:   4%|4         | 125/3000 [02:54<56:15,  1.17s/it, lr: 1.0e-04 loss: 1.217e-01]
latex_v1:   4%|4         | 125/3000 [02:57<56:15,  1.17s/it, lr: 1.0e-04 loss: 1.434e-01]
latex_v1:   4%|4         | 125/3000 [02:57<56:15,  1.17s/it, lr: 1.0e-04 loss: 1.434e-01]
latex_v1:   4%|4         | 126/3000 [02:57<1:19:38,  1.66s/it, lr: 1.0e-04 loss: 1.434e-01]
latex_v1:   4%|4         | 126/3000 [02:57<1:19:38,  1.66s/it, lr: 1.0e-04 loss: 1.434e-01]
latex_v1:   4%|4         | 126/3000 [02:58<1:19:38,  1.66s/it, lr: 1.0e-04 loss: 4.647e-01]
latex_v1:   4%|4         | 126/3000 [02:58<1:19:38,  1.66s/it, lr: 1.0e-04 loss: 4.647e-01]
latex_v1:   4%|4         | 127/3000 [02:58<1:06:53,  1.40s/it, lr: 1.0e-04 loss: 4.647e-01]
latex_v1:   4%|4         | 127/3000 [02:58<1:06:53,  1.40s/it, lr: 1.0e-04 loss: 4.647e-01]
latex_v1:   4%|4         | 127/3000 [03:00<1:06:53,  1.40s/it, lr: 1.0e-04 loss: 6.426e-02]
latex_v1:   4%|4         | 127/3000 [03:00<1:06:53,  1.40s/it, lr: 1.0e-04 loss: 6.426e-02]
latex_v1:   4%|4         | 128/3000 [03:00<1:08:37,  1.43s/it, lr: 1.0e-04 loss: 6.426e-02]
latex_v1:   4%|4         | 128/3000 [03:00<1:08:37,  1.43s/it, lr: 1.0e-04 loss: 6.426e-02]
latex_v1:   4%|4         | 128/3000 [03:01<1:08:37,  1.43s/it, lr: 1.0e-04 loss: 1.729e-01]
latex_v1:   4%|4         | 128/3000 [03:01<1:08:37,  1.43s/it, lr: 1.0e-04 loss: 1.729e-01]
latex_v1:   4%|4         | 129/3000 [03:01<1:10:02,  1.46s/it, lr: 1.0e-04 loss: 1.729e-01]
latex_v1:   4%|4         | 129/3000 [03:01<1:10:02,  1.46s/it, lr: 1.0e-04 loss: 1.729e-01]
latex_v1:   4%|4         | 129/3000 [03:02<1:10:02,  1.46s/it, lr: 1.0e-04 loss: 6.310e-01]
latex_v1:   4%|4         | 129/3000 [03:02<1:10:02,  1.46s/it, lr: 1.0e-04 loss: 6.310e-01]
latex_v1:   4%|4         | 130/3000 [03:03<1:10:00,  1.46s/it, lr: 1.0e-04 loss: 3.790e-01]
latex_v1:   4%|4         | 130/3000 [03:03<1:10:00,  1.46s/it, lr: 1.0e-04 loss: 3.790e-01]
latex_v1:   4%|4         | 131/3000 [03:03<52:21,  1.10s/it, lr: 1.0e-04 loss: 3.790e-01]  
latex_v1:   4%|4         | 131/3000 [03:03<52:21,  1.10s/it, lr: 1.0e-04 loss: 3.790e-01]  
latex_v1:   4%|4         | 131/3000 [03:05<52:21,  1.10s/it, lr: 1.0e-04 loss: 7.324e-01]
latex_v1:   4%|4         | 131/3000 [03:05<52:21,  1.10s/it, lr: 1.0e-04 loss: 7.324e-01]
latex_v1:   4%|4         | 132/3000 [03:05<55:04,  1.15s/it, lr: 1.0e-04 loss: 7.324e-01]
latex_v1:   4%|4         | 132/3000 [03:05<55:04,  1.15s/it, lr: 1.0e-04 loss: 7.324e-01]
latex_v1:   4%|4         | 132/3000 [03:06<55:04,  1.15s/it, lr: 1.0e-04 loss: 1.476e-01]
latex_v1:   4%|4         | 132/3000 [03:06<55:04,  1.15s/it, lr: 1.0e-04 loss: 1.476e-01]
latex_v1:   4%|4         | 133/3000 [03:06<58:24,  1.22s/it, lr: 1.0e-04 loss: 1.476e-01]
latex_v1:   4%|4         | 133/3000 [03:06<58:24,  1.22s/it, lr: 1.0e-04 loss: 1.476e-01]
latex_v1:   4%|4         | 133/3000 [03:07<58:24,  1.22s/it, lr: 1.0e-04 loss: 4.355e-01]
latex_v1:   4%|4         | 133/3000 [03:07<58:24,  1.22s/it, lr: 1.0e-04 loss: 4.355e-01]
latex_v1:   4%|4         | 134/3000 [03:07<1:01:19,  1.28s/it, lr: 1.0e-04 loss: 4.355e-01]
latex_v1:   4%|4         | 134/3000 [03:07<1:01:19,  1.28s/it, lr: 1.0e-04 loss: 4.355e-01]
latex_v1:   4%|4         | 134/3000 [03:09<1:01:19,  1.28s/it, lr: 1.0e-04 loss: 1.156e-01]
latex_v1:   4%|4         | 134/3000 [03:09<1:01:19,  1.28s/it, lr: 1.0e-04 loss: 1.156e-01]
latex_v1:   4%|4         | 135/3000 [03:09<1:05:44,  1.38s/it, lr: 1.0e-04 loss: 1.156e-01]
latex_v1:   4%|4         | 135/3000 [03:09<1:05:44,  1.38s/it, lr: 1.0e-04 loss: 1.156e-01]
latex_v1:   4%|4         | 135/3000 [03:10<1:05:44,  1.38s/it, lr: 1.0e-04 loss: 3.246e-02]
latex_v1:   4%|4         | 135/3000 [03:10<1:05:44,  1.38s/it, lr: 1.0e-04 loss: 3.246e-02]
latex_v1:   5%|4         | 136/3000 [03:10<1:06:01,  1.38s/it, lr: 1.0e-04 loss: 3.246e-02]
latex_v1:   5%|4         | 136/3000 [03:10<1:06:01,  1.38s/it, lr: 1.0e-04 loss: 3.246e-02]
latex_v1:   5%|4         | 136/3000 [03:12<1:06:01,  1.38s/it, lr: 1.0e-04 loss: 1.358e-01]
latex_v1:   5%|4         | 136/3000 [03:12<1:06:01,  1.38s/it, lr: 1.0e-04 loss: 1.358e-01]
latex_v1:   5%|4         | 137/3000 [03:12<1:06:37,  1.40s/it, lr: 1.0e-04 loss: 1.358e-01]
latex_v1:   5%|4         | 137/3000 [03:12<1:06:37,  1.40s/it, lr: 1.0e-04 loss: 1.358e-01]
latex_v1:   5%|4         | 137/3000 [03:13<1:06:37,  1.40s/it, lr: 1.0e-04 loss: 8.403e-01]
latex_v1:   5%|4         | 137/3000 [03:13<1:06:37,  1.40s/it, lr: 1.0e-04 loss: 8.403e-01]
latex_v1:   5%|4         | 138/3000 [03:13<1:03:20,  1.33s/it, lr: 1.0e-04 loss: 8.403e-01]
latex_v1:   5%|4         | 138/3000 [03:13<1:03:20,  1.33s/it, lr: 1.0e-04 loss: 8.403e-01]
latex_v1:   5%|4         | 138/3000 [03:16<1:03:20,  1.33s/it, lr: 1.0e-04 loss: 2.489e-01]
latex_v1:   5%|4         | 138/3000 [03:16<1:03:20,  1.33s/it, lr: 1.0e-04 loss: 2.489e-01]
latex_v1:   5%|4         | 139/3000 [03:16<1:24:40,  1.78s/it, lr: 1.0e-04 loss: 2.489e-01]
latex_v1:   5%|4         | 139/3000 [03:16<1:24:40,  1.78s/it, lr: 1.0e-04 loss: 2.489e-01]
latex_v1:   5%|4         | 139/3000 [03:17<1:24:40,  1.78s/it, lr: 1.0e-04 loss: 5.348e-01]
latex_v1:   5%|4         | 139/3000 [03:17<1:24:40,  1.78s/it, lr: 1.0e-04 loss: 5.348e-01]
latex_v1:   5%|4         | 140/3000 [03:17<1:24:38,  1.78s/it, lr: 1.0e-04 loss: 5.495e-01]
latex_v1:   5%|4         | 140/3000 [03:17<1:24:38,  1.78s/it, lr: 1.0e-04 loss: 5.495e-01]
latex_v1:   5%|4         | 141/3000 [03:17<54:09,  1.14s/it, lr: 1.0e-04 loss: 5.495e-01]  
latex_v1:   5%|4         | 141/3000 [03:17<54:09,  1.14s/it, lr: 1.0e-04 loss: 5.495e-01]  
latex_v1:   5%|4         | 141/3000 [03:19<54:09,  1.14s/it, lr: 1.0e-04 loss: 1.774e-01]
latex_v1:   5%|4         | 141/3000 [03:19<54:09,  1.14s/it, lr: 1.0e-04 loss: 1.774e-01]
latex_v1:   5%|4         | 142/3000 [03:19<58:46,  1.23s/it, lr: 1.0e-04 loss: 1.774e-01]
latex_v1:   5%|4         | 142/3000 [03:19<58:46,  1.23s/it, lr: 1.0e-04 loss: 1.774e-01]
latex_v1:   5%|4         | 142/3000 [03:20<58:46,  1.23s/it, lr: 1.0e-04 loss: 7.239e-01]
latex_v1:   5%|4         | 142/3000 [03:20<58:46,  1.23s/it, lr: 1.0e-04 loss: 7.239e-01]
latex_v1:   5%|4         | 143/3000 [03:20<57:57,  1.22s/it, lr: 1.0e-04 loss: 7.239e-01]
latex_v1:   5%|4         | 143/3000 [03:20<57:57,  1.22s/it, lr: 1.0e-04 loss: 7.239e-01]
latex_v1:   5%|4         | 143/3000 [03:22<57:57,  1.22s/it, lr: 1.0e-04 loss: 1.662e-01]
latex_v1:   5%|4         | 143/3000 [03:22<57:57,  1.22s/it, lr: 1.0e-04 loss: 1.662e-01]
latex_v1:   5%|4         | 144/3000 [03:22<1:04:24,  1.35s/it, lr: 1.0e-04 loss: 1.662e-01]
latex_v1:   5%|4         | 144/3000 [03:22<1:04:24,  1.35s/it, lr: 1.0e-04 loss: 1.662e-01]
latex_v1:   5%|4         | 144/3000 [03:23<1:04:24,  1.35s/it, lr: 1.0e-04 loss: 5.889e-01]
latex_v1:   5%|4         | 144/3000 [03:23<1:04:24,  1.35s/it, lr: 1.0e-04 loss: 5.889e-01]
latex_v1:   5%|4         | 145/3000 [03:23<56:20,  1.18s/it, lr: 1.0e-04 loss: 5.889e-01]  
latex_v1:   5%|4         | 145/3000 [03:23<56:20,  1.18s/it, lr: 1.0e-04 loss: 5.889e-01]  
latex_v1:   5%|4         | 145/3000 [03:24<56:20,  1.18s/it, lr: 1.0e-04 loss: 2.728e-01]
latex_v1:   5%|4         | 145/3000 [03:24<56:20,  1.18s/it, lr: 1.0e-04 loss: 2.728e-01]
latex_v1:   5%|4         | 146/3000 [03:24<59:48,  1.26s/it, lr: 1.0e-04 loss: 2.728e-01]
latex_v1:   5%|4         | 146/3000 [03:24<59:48,  1.26s/it, lr: 1.0e-04 loss: 2.728e-01]
latex_v1:   5%|4         | 146/3000 [03:27<59:48,  1.26s/it, lr: 1.0e-04 loss: 7.601e-02]
latex_v1:   5%|4         | 146/3000 [03:27<59:48,  1.26s/it, lr: 1.0e-04 loss: 7.601e-02]
latex_v1:   5%|4         | 147/3000 [03:27<1:19:40,  1.68s/it, lr: 1.0e-04 loss: 7.601e-02]
latex_v1:   5%|4         | 147/3000 [03:27<1:19:40,  1.68s/it, lr: 1.0e-04 loss: 7.601e-02]
latex_v1:   5%|4         | 147/3000 [03:28<1:19:40,  1.68s/it, lr: 1.0e-04 loss: 2.787e-01]
latex_v1:   5%|4         | 147/3000 [03:28<1:19:40,  1.68s/it, lr: 1.0e-04 loss: 2.787e-01]
latex_v1:   5%|4         | 148/3000 [03:28<1:16:05,  1.60s/it, lr: 1.0e-04 loss: 2.787e-01]
latex_v1:   5%|4         | 148/3000 [03:28<1:16:05,  1.60s/it, lr: 1.0e-04 loss: 2.787e-01]
latex_v1:   5%|4         | 148/3000 [03:29<1:16:05,  1.60s/it, lr: 1.0e-04 loss: 7.208e-01]
latex_v1:   5%|4         | 148/3000 [03:29<1:16:05,  1.60s/it, lr: 1.0e-04 loss: 7.208e-01]
latex_v1:   5%|4         | 149/3000 [03:29<1:07:42,  1.42s/it, lr: 1.0e-04 loss: 7.208e-01]
latex_v1:   5%|4         | 149/3000 [03:29<1:07:42,  1.42s/it, lr: 1.0e-04 loss: 7.208e-01]
latex_v1:   5%|4         | 149/3000 [03:30<1:07:42,  1.42s/it, lr: 1.0e-04 loss: 2.289e-01]
latex_v1:   5%|4         | 149/3000 [03:30<1:07:42,  1.42s/it, lr: 1.0e-04 loss: 2.289e-01]
latex_v1:   5%|5         | 150/3000 [03:31<1:07:40,  1.42s/it, lr: 1.0e-04 loss: 8.929e-02]
latex_v1:   5%|5         | 150/3000 [03:31<1:07:40,  1.42s/it, lr: 1.0e-04 loss: 8.929e-02]
latex_v1:   5%|5         | 151/3000 [03:31<44:51,  1.06it/s, lr: 1.0e-04 loss: 8.929e-02]  
latex_v1:   5%|5         | 151/3000 [03:31<44:51,  1.06it/s, lr: 1.0e-04 loss: 8.929e-02]  
latex_v1:   5%|5         | 151/3000 [03:33<44:51,  1.06it/s, lr: 1.0e-04 loss: 2.261e-01]
latex_v1:   5%|5         | 151/3000 [03:33<44:51,  1.06it/s, lr: 1.0e-04 loss: 2.261e-01]
latex_v1:   5%|5         | 152/3000 [03:33<56:01,  1.18s/it, lr: 1.0e-04 loss: 2.261e-01]
latex_v1:   5%|5         | 152/3000 [03:33<56:01,  1.18s/it, lr: 1.0e-04 loss: 2.261e-01]
latex_v1:   5%|5         | 152/3000 [03:33<56:01,  1.18s/it, lr: 1.0e-04 loss: 3.723e-01]
latex_v1:   5%|5         | 152/3000 [03:33<56:01,  1.18s/it, lr: 1.0e-04 loss: 3.723e-01]
latex_v1:   5%|5         | 153/3000 [03:33<50:58,  1.07s/it, lr: 1.0e-04 loss: 3.723e-01]
latex_v1:   5%|5         | 153/3000 [03:33<50:58,  1.07s/it, lr: 1.0e-04 loss: 3.723e-01]
latex_v1:   5%|5         | 153/3000 [03:35<50:58,  1.07s/it, lr: 1.0e-04 loss: 6.147e-01]
latex_v1:   5%|5         | 153/3000 [03:35<50:58,  1.07s/it, lr: 1.0e-04 loss: 6.147e-01]
latex_v1:   5%|5         | 154/3000 [03:35<1:01:16,  1.29s/it, lr: 1.0e-04 loss: 6.147e-01]
latex_v1:   5%|5         | 154/3000 [03:35<1:01:16,  1.29s/it, lr: 1.0e-04 loss: 6.147e-01]
latex_v1:   5%|5         | 154/3000 [03:37<1:01:16,  1.29s/it, lr: 1.0e-04 loss: 5.430e-01]
latex_v1:   5%|5         | 154/3000 [03:37<1:01:16,  1.29s/it, lr: 1.0e-04 loss: 5.430e-01]
latex_v1:   5%|5         | 155/3000 [03:37<1:04:34,  1.36s/it, lr: 1.0e-04 loss: 5.430e-01]
latex_v1:   5%|5         | 155/3000 [03:37<1:04:34,  1.36s/it, lr: 1.0e-04 loss: 5.430e-01]
latex_v1:   5%|5         | 155/3000 [03:39<1:04:34,  1.36s/it, lr: 1.0e-04 loss: 2.174e-01]
latex_v1:   5%|5         | 155/3000 [03:39<1:04:34,  1.36s/it, lr: 1.0e-04 loss: 2.174e-01]
latex_v1:   5%|5         | 156/3000 [03:39<1:21:43,  1.72s/it, lr: 1.0e-04 loss: 2.174e-01]
latex_v1:   5%|5         | 156/3000 [03:39<1:21:43,  1.72s/it, lr: 1.0e-04 loss: 2.174e-01]
latex_v1:   5%|5         | 156/3000 [03:41<1:21:43,  1.72s/it, lr: 1.0e-04 loss: 6.922e-01]
latex_v1:   5%|5         | 156/3000 [03:41<1:21:43,  1.72s/it, lr: 1.0e-04 loss: 6.922e-01]
latex_v1:   5%|5         | 157/3000 [03:41<1:19:00,  1.67s/it, lr: 1.0e-04 loss: 6.922e-01]
latex_v1:   5%|5         | 157/3000 [03:41<1:19:00,  1.67s/it, lr: 1.0e-04 loss: 6.922e-01]
latex_v1:   5%|5         | 157/3000 [03:42<1:19:00,  1.67s/it, lr: 1.0e-04 loss: 4.690e-01]
latex_v1:   5%|5         | 157/3000 [03:42<1:19:00,  1.67s/it, lr: 1.0e-04 loss: 4.690e-01]
latex_v1:   5%|5         | 158/3000 [03:42<1:14:47,  1.58s/it, lr: 1.0e-04 loss: 4.690e-01]
latex_v1:   5%|5         | 158/3000 [03:42<1:14:47,  1.58s/it, lr: 1.0e-04 loss: 4.690e-01]
latex_v1:   5%|5         | 158/3000 [03:43<1:14:47,  1.58s/it, lr: 1.0e-04 loss: 4.776e-01]
latex_v1:   5%|5         | 158/3000 [03:43<1:14:47,  1.58s/it, lr: 1.0e-04 loss: 4.776e-01]
latex_v1:   5%|5         | 159/3000 [03:43<1:03:21,  1.34s/it, lr: 1.0e-04 loss: 4.776e-01]
latex_v1:   5%|5         | 159/3000 [03:43<1:03:21,  1.34s/it, lr: 1.0e-04 loss: 4.776e-01]
latex_v1:   5%|5         | 159/3000 [03:45<1:03:21,  1.34s/it, lr: 1.0e-04 loss: 5.492e-01]
latex_v1:   5%|5         | 159/3000 [03:45<1:03:21,  1.34s/it, lr: 1.0e-04 loss: 5.492e-01]
latex_v1:   5%|5         | 160/3000 [03:46<1:03:19,  1.34s/it, lr: 1.0e-04 loss: 5.252e-01]
latex_v1:   5%|5         | 160/3000 [03:46<1:03:19,  1.34s/it, lr: 1.0e-04 loss: 5.252e-01]
latex_v1:   5%|5         | 161/3000 [03:46<45:48,  1.03it/s, lr: 1.0e-04 loss: 5.252e-01]  
latex_v1:   5%|5         | 161/3000 [03:46<45:48,  1.03it/s, lr: 1.0e-04 loss: 5.252e-01]  
latex_v1:   5%|5         | 161/3000 [03:48<45:48,  1.03it/s, lr: 1.0e-04 loss: 5.297e-01]
latex_v1:   5%|5         | 161/3000 [03:48<45:48,  1.03it/s, lr: 1.0e-04 loss: 5.297e-01]
latex_v1:   5%|5         | 162/3000 [03:48<54:09,  1.14s/it, lr: 1.0e-04 loss: 5.297e-01]
latex_v1:   5%|5         | 162/3000 [03:48<54:09,  1.14s/it, lr: 1.0e-04 loss: 5.297e-01]
latex_v1:   5%|5         | 162/3000 [03:51<54:09,  1.14s/it, lr: 1.0e-04 loss: 4.907e-01]
latex_v1:   5%|5         | 162/3000 [03:51<54:09,  1.14s/it, lr: 1.0e-04 loss: 4.907e-01]
latex_v1:   5%|5         | 163/3000 [03:51<1:14:45,  1.58s/it, lr: 1.0e-04 loss: 4.907e-01]
latex_v1:   5%|5         | 163/3000 [03:51<1:14:45,  1.58s/it, lr: 1.0e-04 loss: 4.907e-01]
latex_v1:   5%|5         | 163/3000 [03:52<1:14:45,  1.58s/it, lr: 1.0e-04 loss: 1.261e-01]
latex_v1:   5%|5         | 163/3000 [03:52<1:14:45,  1.58s/it, lr: 1.0e-04 loss: 1.261e-01]
latex_v1:   5%|5         | 164/3000 [03:52<1:11:28,  1.51s/it, lr: 1.0e-04 loss: 1.261e-01]
latex_v1:   5%|5         | 164/3000 [03:52<1:11:28,  1.51s/it, lr: 1.0e-04 loss: 1.261e-01]
latex_v1:   5%|5         | 164/3000 [03:53<1:11:28,  1.51s/it, lr: 1.0e-04 loss: 1.919e-01]
latex_v1:   5%|5         | 164/3000 [03:53<1:11:28,  1.51s/it, lr: 1.0e-04 loss: 1.919e-01]
latex_v1:   6%|5         | 165/3000 [03:53<1:01:34,  1.30s/it, lr: 1.0e-04 loss: 1.919e-01]
latex_v1:   6%|5         | 165/3000 [03:53<1:01:34,  1.30s/it, lr: 1.0e-04 loss: 1.919e-01]
latex_v1:   6%|5         | 165/3000 [03:54<1:01:34,  1.30s/it, lr: 1.0e-04 loss: 7.598e-01]
latex_v1:   6%|5         | 165/3000 [03:54<1:01:34,  1.30s/it, lr: 1.0e-04 loss: 7.598e-01]
latex_v1:   6%|5         | 166/3000 [03:54<56:51,  1.20s/it, lr: 1.0e-04 loss: 7.598e-01]  
latex_v1:   6%|5         | 166/3000 [03:54<56:51,  1.20s/it, lr: 1.0e-04 loss: 7.598e-01]  
latex_v1:   6%|5         | 166/3000 [03:55<56:51,  1.20s/it, lr: 1.0e-04 loss: 8.993e-01]
latex_v1:   6%|5         | 166/3000 [03:55<56:51,  1.20s/it, lr: 1.0e-04 loss: 8.993e-01]
latex_v1:   6%|5         | 167/3000 [03:55<50:34,  1.07s/it, lr: 1.0e-04 loss: 8.993e-01]
latex_v1:   6%|5         | 167/3000 [03:55<50:34,  1.07s/it, lr: 1.0e-04 loss: 8.993e-01]
latex_v1:   6%|5         | 167/3000 [03:55<50:34,  1.07s/it, lr: 1.0e-04 loss: 3.835e-01]
latex_v1:   6%|5         | 167/3000 [03:55<50:34,  1.07s/it, lr: 1.0e-04 loss: 3.835e-01]
latex_v1:   6%|5         | 168/3000 [03:55<46:10,  1.02it/s, lr: 1.0e-04 loss: 3.835e-01]
latex_v1:   6%|5         | 168/3000 [03:55<46:10,  1.02it/s, lr: 1.0e-04 loss: 3.835e-01]
latex_v1:   6%|5         | 168/3000 [03:58<46:10,  1.02it/s, lr: 1.0e-04 loss: 6.204e-02]
latex_v1:   6%|5         | 168/3000 [03:58<46:10,  1.02it/s, lr: 1.0e-04 loss: 6.204e-02]
latex_v1:   6%|5         | 169/3000 [03:58<1:12:23,  1.53s/it, lr: 1.0e-04 loss: 6.204e-02]
latex_v1:   6%|5         | 169/3000 [03:58<1:12:23,  1.53s/it, lr: 1.0e-04 loss: 6.204e-02]
latex_v1:   6%|5         | 169/3000 [03:59<1:12:23,  1.53s/it, lr: 1.0e-04 loss: 6.317e-01]
latex_v1:   6%|5         | 169/3000 [03:59<1:12:23,  1.53s/it, lr: 1.0e-04 loss: 6.317e-01]
latex_v1:   6%|5         | 170/3000 [04:02<1:12:21,  1.53s/it, lr: 1.0e-04 loss: 4.488e-01]
latex_v1:   6%|5         | 170/3000 [04:02<1:12:21,  1.53s/it, lr: 1.0e-04 loss: 4.488e-01]
latex_v1:   6%|5         | 171/3000 [04:02<1:10:39,  1.50s/it, lr: 1.0e-04 loss: 4.488e-01]
latex_v1:   6%|5         | 171/3000 [04:02<1:10:39,  1.50s/it, lr: 1.0e-04 loss: 4.488e-01]
latex_v1:   6%|5         | 171/3000 [04:05<1:10:39,  1.50s/it, lr: 1.0e-04 loss: 2.465e-01]
latex_v1:   6%|5         | 171/3000 [04:05<1:10:39,  1.50s/it, lr: 1.0e-04 loss: 2.465e-01]
latex_v1:   6%|5         | 172/3000 [04:05<1:26:02,  1.83s/it, lr: 1.0e-04 loss: 2.465e-01]
latex_v1:   6%|5         | 172/3000 [04:05<1:26:02,  1.83s/it, lr: 1.0e-04 loss: 2.465e-01]
latex_v1:   6%|5         | 172/3000 [04:06<1:26:02,  1.83s/it, lr: 1.0e-04 loss: 2.657e-01]
latex_v1:   6%|5         | 172/3000 [04:06<1:26:02,  1.83s/it, lr: 1.0e-04 loss: 2.657e-01]
latex_v1:   6%|5         | 173/3000 [04:06<1:18:02,  1.66s/it, lr: 1.0e-04 loss: 2.657e-01]
latex_v1:   6%|5         | 173/3000 [04:06<1:18:02,  1.66s/it, lr: 1.0e-04 loss: 2.657e-01]
latex_v1:   6%|5         | 173/3000 [04:07<1:18:02,  1.66s/it, lr: 1.0e-04 loss: 2.179e-01]
latex_v1:   6%|5         | 173/3000 [04:07<1:18:02,  1.66s/it, lr: 1.0e-04 loss: 2.179e-01]
latex_v1:   6%|5         | 174/3000 [04:07<1:10:30,  1.50s/it, lr: 1.0e-04 loss: 2.179e-01]
latex_v1:   6%|5         | 174/3000 [04:07<1:10:30,  1.50s/it, lr: 1.0e-04 loss: 2.179e-01]
latex_v1:   6%|5         | 174/3000 [04:09<1:10:30,  1.50s/it, lr: 1.0e-04 loss: 4.680e-02]
latex_v1:   6%|5         | 174/3000 [04:09<1:10:30,  1.50s/it, lr: 1.0e-04 loss: 4.680e-02]
latex_v1:   6%|5         | 175/3000 [04:09<1:12:57,  1.55s/it, lr: 1.0e-04 loss: 4.680e-02]
latex_v1:   6%|5         | 175/3000 [04:09<1:12:57,  1.55s/it, lr: 1.0e-04 loss: 4.680e-02]
latex_v1:   6%|5         | 175/3000 [04:10<1:12:57,  1.55s/it, lr: 1.0e-04 loss: 2.387e-01]
latex_v1:   6%|5         | 175/3000 [04:10<1:12:57,  1.55s/it, lr: 1.0e-04 loss: 2.387e-01]
latex_v1:   6%|5         | 176/3000 [04:10<1:02:28,  1.33s/it, lr: 1.0e-04 loss: 2.387e-01]
latex_v1:   6%|5         | 176/3000 [04:10<1:02:28,  1.33s/it, lr: 1.0e-04 loss: 2.387e-01]
latex_v1:   6%|5         | 176/3000 [04:11<1:02:28,  1.33s/it, lr: 1.0e-04 loss: 6.640e-01]
latex_v1:   6%|5         | 176/3000 [04:11<1:02:28,  1.33s/it, lr: 1.0e-04 loss: 6.640e-01]
latex_v1:   6%|5         | 177/3000 [04:11<1:05:54,  1.40s/it, lr: 1.0e-04 loss: 6.640e-01]
latex_v1:   6%|5         | 177/3000 [04:11<1:05:54,  1.40s/it, lr: 1.0e-04 loss: 6.640e-01]
latex_v1:   6%|5         | 177/3000 [04:13<1:05:54,  1.40s/it, lr: 1.0e-04 loss: 1.055e-01]
latex_v1:   6%|5         | 177/3000 [04:13<1:05:54,  1.40s/it, lr: 1.0e-04 loss: 1.055e-01]
latex_v1:   6%|5         | 178/3000 [04:13<1:04:46,  1.38s/it, lr: 1.0e-04 loss: 1.055e-01]
latex_v1:   6%|5         | 178/3000 [04:13<1:04:46,  1.38s/it, lr: 1.0e-04 loss: 1.055e-01]
latex_v1:   6%|5         | 178/3000 [04:13<1:04:46,  1.38s/it, lr: 1.0e-04 loss: 2.158e-01]
latex_v1:   6%|5         | 178/3000 [04:13<1:04:46,  1.38s/it, lr: 1.0e-04 loss: 2.158e-01]
latex_v1:   6%|5         | 179/3000 [04:13<56:02,  1.19s/it, lr: 1.0e-04 loss: 2.158e-01]  
latex_v1:   6%|5         | 179/3000 [04:13<56:02,  1.19s/it, lr: 1.0e-04 loss: 2.158e-01]  
latex_v1:   6%|5         | 179/3000 [04:15<56:02,  1.19s/it, lr: 1.0e-04 loss: 5.429e-01]
latex_v1:   6%|5         | 179/3000 [04:15<56:02,  1.19s/it, lr: 1.0e-04 loss: 5.429e-01]
latex_v1:   6%|6         | 180/3000 [04:17<56:01,  1.19s/it, lr: 1.0e-04 loss: 1.939e-01]
latex_v1:   6%|6         | 180/3000 [04:17<56:01,  1.19s/it, lr: 1.0e-04 loss: 1.939e-01]
latex_v1:   6%|6         | 181/3000 [04:17<45:39,  1.03it/s, lr: 1.0e-04 loss: 1.939e-01]
latex_v1:   6%|6         | 181/3000 [04:17<45:39,  1.03it/s, lr: 1.0e-04 loss: 1.939e-01]
latex_v1:   6%|6         | 181/3000 [04:17<45:39,  1.03it/s, lr: 1.0e-04 loss: 3.794e-01]
latex_v1:   6%|6         | 181/3000 [04:17<45:39,  1.03it/s, lr: 1.0e-04 loss: 3.794e-01]
latex_v1:   6%|6         | 182/3000 [04:17<43:01,  1.09it/s, lr: 1.0e-04 loss: 3.794e-01]
latex_v1:   6%|6         | 182/3000 [04:17<43:01,  1.09it/s, lr: 1.0e-04 loss: 3.794e-01]
latex_v1:   6%|6         | 182/3000 [04:18<43:01,  1.09it/s, lr: 1.0e-04 loss: 6.656e-01]
latex_v1:   6%|6         | 182/3000 [04:18<43:01,  1.09it/s, lr: 1.0e-04 loss: 6.656e-01]
latex_v1:   6%|6         | 183/3000 [04:18<41:06,  1.14it/s, lr: 1.0e-04 loss: 6.656e-01]
latex_v1:   6%|6         | 183/3000 [04:18<41:06,  1.14it/s, lr: 1.0e-04 loss: 6.656e-01]
latex_v1:   6%|6         | 183/3000 [04:19<41:06,  1.14it/s, lr: 1.0e-04 loss: 7.337e-01]
latex_v1:   6%|6         | 183/3000 [04:19<41:06,  1.14it/s, lr: 1.0e-04 loss: 7.337e-01]
latex_v1:   6%|6         | 184/3000 [04:19<39:27,  1.19it/s, lr: 1.0e-04 loss: 7.337e-01]
latex_v1:   6%|6         | 184/3000 [04:19<39:27,  1.19it/s, lr: 1.0e-04 loss: 7.337e-01]
latex_v1:   6%|6         | 184/3000 [04:20<39:27,  1.19it/s, lr: 1.0e-04 loss: 4.804e-01]
latex_v1:   6%|6         | 184/3000 [04:20<39:27,  1.19it/s, lr: 1.0e-04 loss: 4.804e-01]
latex_v1:   6%|6         | 185/3000 [04:20<38:27,  1.22it/s, lr: 1.0e-04 loss: 4.804e-01]
latex_v1:   6%|6         | 185/3000 [04:20<38:27,  1.22it/s, lr: 1.0e-04 loss: 4.804e-01]
latex_v1:   6%|6         | 185/3000 [04:21<38:27,  1.22it/s, lr: 1.0e-04 loss: 6.237e-01]
latex_v1:   6%|6         | 185/3000 [04:21<38:27,  1.22it/s, lr: 1.0e-04 loss: 6.237e-01]
latex_v1:   6%|6         | 186/3000 [04:21<38:30,  1.22it/s, lr: 1.0e-04 loss: 6.237e-01]
latex_v1:   6%|6         | 186/3000 [04:21<38:30,  1.22it/s, lr: 1.0e-04 loss: 6.237e-01]
latex_v1:   6%|6         | 186/3000 [04:21<38:30,  1.22it/s, lr: 1.0e-04 loss: 1.924e-01]
latex_v1:   6%|6         | 186/3000 [04:21<38:30,  1.22it/s, lr: 1.0e-04 loss: 1.924e-01]
latex_v1:   6%|6         | 187/3000 [04:21<37:35,  1.25it/s, lr: 1.0e-04 loss: 1.924e-01]
latex_v1:   6%|6         | 187/3000 [04:21<37:35,  1.25it/s, lr: 1.0e-04 loss: 1.924e-01]
latex_v1:   6%|6         | 187/3000 [04:23<37:35,  1.25it/s, lr: 1.0e-04 loss: 5.286e-01]
latex_v1:   6%|6         | 187/3000 [04:23<37:35,  1.25it/s, lr: 1.0e-04 loss: 5.286e-01]
latex_v1:   6%|6         | 188/3000 [04:23<52:33,  1.12s/it, lr: 1.0e-04 loss: 5.286e-01]
latex_v1:   6%|6         | 188/3000 [04:23<52:33,  1.12s/it, lr: 1.0e-04 loss: 5.286e-01]
latex_v1:   6%|6         | 188/3000 [04:25<52:33,  1.12s/it, lr: 1.0e-04 loss: 6.921e-01]
latex_v1:   6%|6         | 188/3000 [04:25<52:33,  1.12s/it, lr: 1.0e-04 loss: 6.921e-01]
latex_v1:   6%|6         | 189/3000 [04:25<53:21,  1.14s/it, lr: 1.0e-04 loss: 6.921e-01]
latex_v1:   6%|6         | 189/3000 [04:25<53:21,  1.14s/it, lr: 1.0e-04 loss: 6.921e-01]
latex_v1:   6%|6         | 189/3000 [04:26<53:21,  1.14s/it, lr: 1.0e-04 loss: 2.804e-01]
latex_v1:   6%|6         | 189/3000 [04:26<53:21,  1.14s/it, lr: 1.0e-04 loss: 2.804e-01]
latex_v1:   6%|6         | 190/3000 [04:27<53:20,  1.14s/it, lr: 1.0e-04 loss: 4.627e-01]
latex_v1:   6%|6         | 190/3000 [04:27<53:20,  1.14s/it, lr: 1.0e-04 loss: 4.627e-01]
latex_v1:   6%|6         | 191/3000 [04:27<41:36,  1.13it/s, lr: 1.0e-04 loss: 4.627e-01]
latex_v1:   6%|6         | 191/3000 [04:27<41:36,  1.13it/s, lr: 1.0e-04 loss: 4.627e-01]
latex_v1:   6%|6         | 191/3000 [04:28<41:36,  1.13it/s, lr: 1.0e-04 loss: 3.812e-01]
latex_v1:   6%|6         | 191/3000 [04:28<41:36,  1.13it/s, lr: 1.0e-04 loss: 3.812e-01]
latex_v1:   6%|6         | 192/3000 [04:28<48:00,  1.03s/it, lr: 1.0e-04 loss: 3.812e-01]
latex_v1:   6%|6         | 192/3000 [04:28<48:00,  1.03s/it, lr: 1.0e-04 loss: 3.812e-01]
latex_v1:   6%|6         | 192/3000 [04:29<48:00,  1.03s/it, lr: 1.0e-04 loss: 1.686e-01]
latex_v1:   6%|6         | 192/3000 [04:29<48:00,  1.03s/it, lr: 1.0e-04 loss: 1.686e-01]
latex_v1:   6%|6         | 193/3000 [04:29<44:27,  1.05it/s, lr: 1.0e-04 loss: 1.686e-01]
latex_v1:   6%|6         | 193/3000 [04:29<44:27,  1.05it/s, lr: 1.0e-04 loss: 1.686e-01]
latex_v1:   6%|6         | 193/3000 [04:31<44:27,  1.05it/s, lr: 1.0e-04 loss: 3.249e-01]
latex_v1:   6%|6         | 193/3000 [04:31<44:27,  1.05it/s, lr: 1.0e-04 loss: 3.249e-01]
latex_v1:   6%|6         | 194/3000 [04:31<52:08,  1.11s/it, lr: 1.0e-04 loss: 3.249e-01]
latex_v1:   6%|6         | 194/3000 [04:31<52:08,  1.11s/it, lr: 1.0e-04 loss: 3.249e-01]
latex_v1:   6%|6         | 194/3000 [04:32<52:08,  1.11s/it, lr: 1.0e-04 loss: 2.132e-01]
latex_v1:   6%|6         | 194/3000 [04:32<52:08,  1.11s/it, lr: 1.0e-04 loss: 2.132e-01]
latex_v1:   6%|6         | 195/3000 [04:32<56:10,  1.20s/it, lr: 1.0e-04 loss: 2.132e-01]
latex_v1:   6%|6         | 195/3000 [04:32<56:10,  1.20s/it, lr: 1.0e-04 loss: 2.132e-01]
latex_v1:   6%|6         | 195/3000 [04:33<56:10,  1.20s/it, lr: 1.0e-04 loss: 6.420e-01]
latex_v1:   6%|6         | 195/3000 [04:33<56:10,  1.20s/it, lr: 1.0e-04 loss: 6.420e-01]
latex_v1:   7%|6         | 196/3000 [04:33<59:23,  1.27s/it, lr: 1.0e-04 loss: 6.420e-01]
latex_v1:   7%|6         | 196/3000 [04:33<59:23,  1.27s/it, lr: 1.0e-04 loss: 6.420e-01]
latex_v1:   7%|6         | 196/3000 [04:34<59:23,  1.27s/it, lr: 1.0e-04 loss: 5.176e-01]
latex_v1:   7%|6         | 196/3000 [04:34<59:23,  1.27s/it, lr: 1.0e-04 loss: 5.176e-01]
latex_v1:   7%|6         | 197/3000 [04:34<52:30,  1.12s/it, lr: 1.0e-04 loss: 5.176e-01]
latex_v1:   7%|6         | 197/3000 [04:34<52:30,  1.12s/it, lr: 1.0e-04 loss: 5.176e-01]
latex_v1:   7%|6         | 197/3000 [04:35<52:30,  1.12s/it, lr: 1.0e-04 loss: 6.010e-01]
latex_v1:   7%|6         | 197/3000 [04:35<52:30,  1.12s/it, lr: 1.0e-04 loss: 6.010e-01]
latex_v1:   7%|6         | 198/3000 [04:35<47:34,  1.02s/it, lr: 1.0e-04 loss: 6.010e-01]
latex_v1:   7%|6         | 198/3000 [04:35<47:34,  1.02s/it, lr: 1.0e-04 loss: 6.010e-01]
latex_v1:   7%|6         | 198/3000 [04:36<47:34,  1.02s/it, lr: 1.0e-04 loss: 1.408e-01]
latex_v1:   7%|6         | 198/3000 [04:36<47:34,  1.02s/it, lr: 1.0e-04 loss: 1.408e-01]
latex_v1:   7%|6         | 199/3000 [04:36<54:43,  1.17s/it, lr: 1.0e-04 loss: 1.408e-01]
latex_v1:   7%|6         | 199/3000 [04:36<54:43,  1.17s/it, lr: 1.0e-04 loss: 1.408e-01]
latex_v1:   7%|6         | 199/3000 [04:38<54:43,  1.17s/it, lr: 1.0e-04 loss: 7.031e-02]
latex_v1:   7%|6         | 199/3000 [04:38<54:43,  1.17s/it, lr: 1.0e-04 loss: 7.031e-02]
latex_v1:   7%|6         | 200/3000 [04:39<54:41,  1.17s/it, lr: 1.0e-04 loss: 9.063e-02]
latex_v1:   7%|6         | 200/3000 [04:39<54:41,  1.17s/it, lr: 1.0e-04 loss: 9.063e-02]
latex_v1:   7%|6         | 201/3000 [04:39<46:05,  1.01it/s, lr: 1.0e-04 loss: 9.063e-02]
latex_v1:   7%|6         | 201/3000 [04:39<46:05,  1.01it/s, lr: 1.0e-04 loss: 9.063e-02]
latex_v1:   7%|6         | 201/3000 [04:41<46:05,  1.01it/s, lr: 1.0e-04 loss: 2.752e-01]
latex_v1:   7%|6         | 201/3000 [04:41<46:05,  1.01it/s, lr: 1.0e-04 loss: 2.752e-01]
latex_v1:   7%|6         | 202/3000 [04:41<52:24,  1.12s/it, lr: 1.0e-04 loss: 2.752e-01]
latex_v1:   7%|6         | 202/3000 [04:41<52:24,  1.12s/it, lr: 1.0e-04 loss: 2.752e-01]
latex_v1:   7%|6         | 202/3000 [04:43<52:24,  1.12s/it, lr: 1.0e-04 loss: 2.217e-01]
latex_v1:   7%|6         | 202/3000 [04:43<52:24,  1.12s/it, lr: 1.0e-04 loss: 2.217e-01]
latex_v1:   7%|6         | 203/3000 [04:43<57:59,  1.24s/it, lr: 1.0e-04 loss: 2.217e-01]
latex_v1:   7%|6         | 203/3000 [04:43<57:59,  1.24s/it, lr: 1.0e-04 loss: 2.217e-01]
latex_v1:   7%|6         | 203/3000 [04:44<57:59,  1.24s/it, lr: 1.0e-04 loss: 4.790e-01]
latex_v1:   7%|6         | 203/3000 [04:44<57:59,  1.24s/it, lr: 1.0e-04 loss: 4.790e-01]
latex_v1:   7%|6         | 204/3000 [04:44<1:01:34,  1.32s/it, lr: 1.0e-04 loss: 4.790e-01]
latex_v1:   7%|6         | 204/3000 [04:44<1:01:34,  1.32s/it, lr: 1.0e-04 loss: 4.790e-01]
latex_v1:   7%|6         | 204/3000 [04:47<1:01:34,  1.32s/it, lr: 1.0e-04 loss: 5.770e-02]
latex_v1:   7%|6         | 204/3000 [04:47<1:01:34,  1.32s/it, lr: 1.0e-04 loss: 5.770e-02]
latex_v1:   7%|6         | 205/3000 [04:47<1:22:09,  1.76s/it, lr: 1.0e-04 loss: 5.770e-02]
latex_v1:   7%|6         | 205/3000 [04:47<1:22:09,  1.76s/it, lr: 1.0e-04 loss: 5.770e-02]
latex_v1:   7%|6         | 205/3000 [04:48<1:22:09,  1.76s/it, lr: 1.0e-04 loss: 2.000e-02]
latex_v1:   7%|6         | 205/3000 [04:48<1:22:09,  1.76s/it, lr: 1.0e-04 loss: 2.000e-02]
latex_v1:   7%|6         | 206/3000 [04:48<1:08:42,  1.48s/it, lr: 1.0e-04 loss: 2.000e-02]
latex_v1:   7%|6         | 206/3000 [04:48<1:08:42,  1.48s/it, lr: 1.0e-04 loss: 2.000e-02]
latex_v1:   7%|6         | 206/3000 [04:49<1:08:42,  1.48s/it, lr: 1.0e-04 loss: 3.685e-01]
latex_v1:   7%|6         | 206/3000 [04:49<1:08:42,  1.48s/it, lr: 1.0e-04 loss: 3.685e-01]
latex_v1:   7%|6         | 207/3000 [04:49<1:09:22,  1.49s/it, lr: 1.0e-04 loss: 3.685e-01]
latex_v1:   7%|6         | 207/3000 [04:49<1:09:22,  1.49s/it, lr: 1.0e-04 loss: 3.685e-01]
latex_v1:   7%|6         | 207/3000 [04:51<1:09:22,  1.49s/it, lr: 1.0e-04 loss: 1.237e-01]
latex_v1:   7%|6         | 207/3000 [04:51<1:09:22,  1.49s/it, lr: 1.0e-04 loss: 1.237e-01]
latex_v1:   7%|6         | 208/3000 [04:51<1:07:38,  1.45s/it, lr: 1.0e-04 loss: 1.237e-01]
latex_v1:   7%|6         | 208/3000 [04:51<1:07:38,  1.45s/it, lr: 1.0e-04 loss: 1.237e-01]
latex_v1:   7%|6         | 208/3000 [04:51<1:07:38,  1.45s/it, lr: 1.0e-04 loss: 1.590e-01]
latex_v1:   7%|6         | 208/3000 [04:51<1:07:38,  1.45s/it, lr: 1.0e-04 loss: 1.590e-01]
latex_v1:   7%|6         | 209/3000 [04:51<57:41,  1.24s/it, lr: 1.0e-04 loss: 1.590e-01]  
latex_v1:   7%|6         | 209/3000 [04:51<57:41,  1.24s/it, lr: 1.0e-04 loss: 1.590e-01]  
latex_v1:   7%|6         | 209/3000 [04:52<57:41,  1.24s/it, lr: 1.0e-04 loss: 3.405e-01]
latex_v1:   7%|6         | 209/3000 [04:52<57:41,  1.24s/it, lr: 1.0e-04 loss: 3.405e-01]
latex_v1:   7%|7         | 210/3000 [04:55<57:40,  1.24s/it, lr: 1.0e-04 loss: 2.924e-01]
latex_v1:   7%|7         | 210/3000 [04:55<57:40,  1.24s/it, lr: 1.0e-04 loss: 2.924e-01]
latex_v1:   7%|7         | 211/3000 [04:55<59:57,  1.29s/it, lr: 1.0e-04 loss: 2.924e-01]
latex_v1:   7%|7         | 211/3000 [04:55<59:57,  1.29s/it, lr: 1.0e-04 loss: 2.924e-01]
latex_v1:   7%|7         | 211/3000 [04:56<59:57,  1.29s/it, lr: 1.0e-04 loss: 1.360e-01]
latex_v1:   7%|7         | 211/3000 [04:56<59:57,  1.29s/it, lr: 1.0e-04 loss: 1.360e-01]
latex_v1:   7%|7         | 212/3000 [04:56<53:39,  1.15s/it, lr: 1.0e-04 loss: 1.360e-01]
latex_v1:   7%|7         | 212/3000 [04:56<53:39,  1.15s/it, lr: 1.0e-04 loss: 1.360e-01]
latex_v1:   7%|7         | 212/3000 [04:57<53:39,  1.15s/it, lr: 1.0e-04 loss: 2.034e-01]
latex_v1:   7%|7         | 212/3000 [04:57<53:39,  1.15s/it, lr: 1.0e-04 loss: 2.034e-01]
latex_v1:   7%|7         | 213/3000 [04:57<56:40,  1.22s/it, lr: 1.0e-04 loss: 2.034e-01]
latex_v1:   7%|7         | 213/3000 [04:57<56:40,  1.22s/it, lr: 1.0e-04 loss: 2.034e-01]
latex_v1:   7%|7         | 213/3000 [04:58<56:40,  1.22s/it, lr: 1.0e-04 loss: 1.576e-01]
latex_v1:   7%|7         | 213/3000 [04:58<56:40,  1.22s/it, lr: 1.0e-04 loss: 1.576e-01]
latex_v1:   7%|7         | 214/3000 [04:58<1:00:36,  1.31s/it, lr: 1.0e-04 loss: 1.576e-01]
latex_v1:   7%|7         | 214/3000 [04:58<1:00:36,  1.31s/it, lr: 1.0e-04 loss: 1.576e-01]
latex_v1:   7%|7         | 214/3000 [05:01<1:00:36,  1.31s/it, lr: 1.0e-04 loss: 1.695e-01]
latex_v1:   7%|7         | 214/3000 [05:01<1:00:36,  1.31s/it, lr: 1.0e-04 loss: 1.695e-01]
latex_v1:   7%|7         | 215/3000 [05:01<1:20:16,  1.73s/it, lr: 1.0e-04 loss: 1.695e-01]
latex_v1:   7%|7         | 215/3000 [05:01<1:20:16,  1.73s/it, lr: 1.0e-04 loss: 1.695e-01]
latex_v1:   7%|7         | 215/3000 [05:02<1:20:16,  1.73s/it, lr: 1.0e-04 loss: 5.898e-01]
latex_v1:   7%|7         | 215/3000 [05:02<1:20:16,  1.73s/it, lr: 1.0e-04 loss: 5.898e-01]
latex_v1:   7%|7         | 216/3000 [05:02<1:11:24,  1.54s/it, lr: 1.0e-04 loss: 5.898e-01]
latex_v1:   7%|7         | 216/3000 [05:02<1:11:24,  1.54s/it, lr: 1.0e-04 loss: 5.898e-01]
latex_v1:   7%|7         | 216/3000 [05:04<1:11:24,  1.54s/it, lr: 1.0e-04 loss: 5.946e-01]
latex_v1:   7%|7         | 216/3000 [05:04<1:11:24,  1.54s/it, lr: 1.0e-04 loss: 5.946e-01]
latex_v1:   7%|7         | 217/3000 [05:04<1:13:24,  1.58s/it, lr: 1.0e-04 loss: 5.946e-01]
latex_v1:   7%|7         | 217/3000 [05:04<1:13:24,  1.58s/it, lr: 1.0e-04 loss: 5.946e-01]
latex_v1:   7%|7         | 217/3000 [05:05<1:13:24,  1.58s/it, lr: 1.0e-04 loss: 9.610e-02]
latex_v1:   7%|7         | 217/3000 [05:05<1:13:24,  1.58s/it, lr: 1.0e-04 loss: 9.610e-02]
latex_v1:   7%|7         | 218/3000 [05:05<1:02:03,  1.34s/it, lr: 1.0e-04 loss: 9.610e-02]
latex_v1:   7%|7         | 218/3000 [05:05<1:02:03,  1.34s/it, lr: 1.0e-04 loss: 9.610e-02]
latex_v1:   7%|7         | 218/3000 [05:07<1:02:03,  1.34s/it, lr: 1.0e-04 loss: 2.689e-01]
latex_v1:   7%|7         | 218/3000 [05:07<1:02:03,  1.34s/it, lr: 1.0e-04 loss: 2.689e-01]
latex_v1:   7%|7         | 219/3000 [05:07<1:09:18,  1.50s/it, lr: 1.0e-04 loss: 2.689e-01]
latex_v1:   7%|7         | 219/3000 [05:07<1:09:18,  1.50s/it, lr: 1.0e-04 loss: 2.689e-01]
latex_v1:   7%|7         | 219/3000 [05:07<1:09:18,  1.50s/it, lr: 1.0e-04 loss: 6.315e-01]
latex_v1:   7%|7         | 219/3000 [05:07<1:09:18,  1.50s/it, lr: 1.0e-04 loss: 6.315e-01]
latex_v1:   7%|7         | 220/3000 [05:09<1:09:16,  1.50s/it, lr: 1.0e-04 loss: 9.322e-02]
latex_v1:   7%|7         | 220/3000 [05:09<1:09:16,  1.50s/it, lr: 1.0e-04 loss: 9.322e-02]
latex_v1:   7%|7         | 221/3000 [05:09<53:04,  1.15s/it, lr: 1.0e-04 loss: 9.322e-02]  
latex_v1:   7%|7         | 221/3000 [05:09<53:04,  1.15s/it, lr: 1.0e-04 loss: 9.322e-02]  
latex_v1:   7%|7         | 221/3000 [05:10<53:04,  1.15s/it, lr: 1.0e-04 loss: 5.677e-01]
latex_v1:   7%|7         | 221/3000 [05:10<53:04,  1.15s/it, lr: 1.0e-04 loss: 5.677e-01]
latex_v1:   7%|7         | 222/3000 [05:10<56:28,  1.22s/it, lr: 1.0e-04 loss: 5.677e-01]
latex_v1:   7%|7         | 222/3000 [05:10<56:28,  1.22s/it, lr: 1.0e-04 loss: 5.677e-01]
latex_v1:   7%|7         | 222/3000 [05:13<56:28,  1.22s/it, lr: 1.0e-04 loss: 5.613e-02]
latex_v1:   7%|7         | 222/3000 [05:13<56:28,  1.22s/it, lr: 1.0e-04 loss: 5.613e-02]
latex_v1:   7%|7         | 223/3000 [05:13<1:16:02,  1.64s/it, lr: 1.0e-04 loss: 5.613e-02]
latex_v1:   7%|7         | 223/3000 [05:13<1:16:02,  1.64s/it, lr: 1.0e-04 loss: 5.613e-02]
latex_v1:   7%|7         | 223/3000 [05:14<1:16:02,  1.64s/it, lr: 1.0e-04 loss: 6.172e-01]
latex_v1:   7%|7         | 223/3000 [05:14<1:16:02,  1.64s/it, lr: 1.0e-04 loss: 6.172e-01]
latex_v1:   7%|7         | 224/3000 [05:14<1:04:59,  1.40s/it, lr: 1.0e-04 loss: 6.172e-01]
latex_v1:   7%|7         | 224/3000 [05:14<1:04:59,  1.40s/it, lr: 1.0e-04 loss: 6.172e-01]
latex_v1:   7%|7         | 224/3000 [05:16<1:04:59,  1.40s/it, lr: 1.0e-04 loss: 5.402e-01]
latex_v1:   7%|7         | 224/3000 [05:16<1:04:59,  1.40s/it, lr: 1.0e-04 loss: 5.402e-01]
latex_v1:   8%|7         | 225/3000 [05:16<1:15:07,  1.62s/it, lr: 1.0e-04 loss: 5.402e-01]
latex_v1:   8%|7         | 225/3000 [05:16<1:15:07,  1.62s/it, lr: 1.0e-04 loss: 5.402e-01]
latex_v1:   8%|7         | 225/3000 [05:19<1:15:07,  1.62s/it, lr: 1.0e-04 loss: 5.164e-01]
latex_v1:   8%|7         | 225/3000 [05:19<1:15:07,  1.62s/it, lr: 1.0e-04 loss: 5.164e-01]
latex_v1:   8%|7         | 226/3000 [05:19<1:31:18,  1.97s/it, lr: 1.0e-04 loss: 5.164e-01]
latex_v1:   8%|7         | 226/3000 [05:19<1:31:18,  1.97s/it, lr: 1.0e-04 loss: 5.164e-01]
latex_v1:   8%|7         | 226/3000 [05:20<1:31:18,  1.97s/it, lr: 1.0e-04 loss: 3.167e-02]
latex_v1:   8%|7         | 226/3000 [05:20<1:31:18,  1.97s/it, lr: 1.0e-04 loss: 3.167e-02]
latex_v1:   8%|7         | 227/3000 [05:20<1:14:56,  1.62s/it, lr: 1.0e-04 loss: 3.167e-02]
latex_v1:   8%|7         | 227/3000 [05:20<1:14:56,  1.62s/it, lr: 1.0e-04 loss: 3.167e-02]
latex_v1:   8%|7         | 227/3000 [05:21<1:14:56,  1.62s/it, lr: 1.0e-04 loss: 5.283e-01]
latex_v1:   8%|7         | 227/3000 [05:21<1:14:56,  1.62s/it, lr: 1.0e-04 loss: 5.283e-01]
latex_v1:   8%|7         | 228/3000 [05:21<1:07:20,  1.46s/it, lr: 1.0e-04 loss: 5.283e-01]
latex_v1:   8%|7         | 228/3000 [05:21<1:07:20,  1.46s/it, lr: 1.0e-04 loss: 5.283e-01]
latex_v1:   8%|7         | 228/3000 [05:22<1:07:20,  1.46s/it, lr: 1.0e-04 loss: 2.560e-01]
latex_v1:   8%|7         | 228/3000 [05:22<1:07:20,  1.46s/it, lr: 1.0e-04 loss: 2.560e-01]
latex_v1:   8%|7         | 229/3000 [05:22<1:08:11,  1.48s/it, lr: 1.0e-04 loss: 2.560e-01]
latex_v1:   8%|7         | 229/3000 [05:22<1:08:11,  1.48s/it, lr: 1.0e-04 loss: 2.560e-01]
latex_v1:   8%|7         | 229/3000 [05:23<1:08:11,  1.48s/it, lr: 1.0e-04 loss: 2.768e-01]
latex_v1:   8%|7         | 229/3000 [05:23<1:08:11,  1.48s/it, lr: 1.0e-04 loss: 2.768e-01]
latex_v1:   8%|7         | 230/3000 [05:24<1:08:10,  1.48s/it, lr: 1.0e-04 loss: 2.134e-01]
latex_v1:   8%|7         | 230/3000 [05:24<1:08:10,  1.48s/it, lr: 1.0e-04 loss: 2.134e-01]
latex_v1:   8%|7         | 231/3000 [05:24<44:51,  1.03it/s, lr: 1.0e-04 loss: 2.134e-01]  
latex_v1:   8%|7         | 231/3000 [05:24<44:51,  1.03it/s, lr: 1.0e-04 loss: 2.134e-01]  
latex_v1:   8%|7         | 231/3000 [05:26<44:51,  1.03it/s, lr: 1.0e-04 loss: 4.863e-01]
latex_v1:   8%|7         | 231/3000 [05:26<44:51,  1.03it/s, lr: 1.0e-04 loss: 4.863e-01]
latex_v1:   8%|7         | 232/3000 [05:26<53:32,  1.16s/it, lr: 1.0e-04 loss: 4.863e-01]
latex_v1:   8%|7         | 232/3000 [05:26<53:32,  1.16s/it, lr: 1.0e-04 loss: 4.863e-01]
latex_v1:   8%|7         | 232/3000 [05:28<53:32,  1.16s/it, lr: 1.0e-04 loss: 5.848e-01]
latex_v1:   8%|7         | 232/3000 [05:28<53:32,  1.16s/it, lr: 1.0e-04 loss: 5.848e-01]
latex_v1:   8%|7         | 233/3000 [05:28<1:02:10,  1.35s/it, lr: 1.0e-04 loss: 5.848e-01]
latex_v1:   8%|7         | 233/3000 [05:28<1:02:10,  1.35s/it, lr: 1.0e-04 loss: 5.848e-01]
latex_v1:   8%|7         | 233/3000 [05:28<1:02:10,  1.35s/it, lr: 1.0e-04 loss: 5.285e-01]
latex_v1:   8%|7         | 233/3000 [05:28<1:02:10,  1.35s/it, lr: 1.0e-04 loss: 5.285e-01]
latex_v1:   8%|7         | 234/3000 [05:28<54:52,  1.19s/it, lr: 1.0e-04 loss: 5.285e-01]  
latex_v1:   8%|7         | 234/3000 [05:28<54:52,  1.19s/it, lr: 1.0e-04 loss: 5.285e-01]  
latex_v1:   8%|7         | 234/3000 [05:31<54:52,  1.19s/it, lr: 1.0e-04 loss: 5.326e-02]
latex_v1:   8%|7         | 234/3000 [05:31<54:52,  1.19s/it, lr: 1.0e-04 loss: 5.326e-02]
latex_v1:   8%|7         | 235/3000 [05:31<1:16:24,  1.66s/it, lr: 1.0e-04 loss: 5.326e-02]
latex_v1:   8%|7         | 235/3000 [05:31<1:16:24,  1.66s/it, lr: 1.0e-04 loss: 5.326e-02]
latex_v1:   8%|7         | 235/3000 [05:34<1:16:24,  1.66s/it, lr: 1.0e-04 loss: 6.006e-01]
latex_v1:   8%|7         | 235/3000 [05:34<1:16:24,  1.66s/it, lr: 1.0e-04 loss: 6.006e-01]
latex_v1:   8%|7         | 236/3000 [05:34<1:29:17,  1.94s/it, lr: 1.0e-04 loss: 6.006e-01]
latex_v1:   8%|7         | 236/3000 [05:34<1:29:17,  1.94s/it, lr: 1.0e-04 loss: 6.006e-01]
latex_v1:   8%|7         | 236/3000 [05:35<1:29:17,  1.94s/it, lr: 1.0e-04 loss: 8.393e-01]
latex_v1:   8%|7         | 236/3000 [05:35<1:29:17,  1.94s/it, lr: 1.0e-04 loss: 8.393e-01]
latex_v1:   8%|7         | 237/3000 [05:35<1:13:27,  1.60s/it, lr: 1.0e-04 loss: 8.393e-01]
latex_v1:   8%|7         | 237/3000 [05:35<1:13:27,  1.60s/it, lr: 1.0e-04 loss: 8.393e-01]
latex_v1:   8%|7         | 237/3000 [05:36<1:13:27,  1.60s/it, lr: 1.0e-04 loss: 2.190e-01]
latex_v1:   8%|7         | 237/3000 [05:36<1:13:27,  1.60s/it, lr: 1.0e-04 loss: 2.190e-01]
latex_v1:   8%|7         | 238/3000 [05:36<1:10:16,  1.53s/it, lr: 1.0e-04 loss: 2.190e-01]
latex_v1:   8%|7         | 238/3000 [05:36<1:10:16,  1.53s/it, lr: 1.0e-04 loss: 2.190e-01]
latex_v1:   8%|7         | 238/3000 [05:39<1:10:16,  1.53s/it, lr: 1.0e-04 loss: 5.076e-01]
latex_v1:   8%|7         | 238/3000 [05:39<1:10:16,  1.53s/it, lr: 1.0e-04 loss: 5.076e-01]
latex_v1:   8%|7         | 239/3000 [05:39<1:27:57,  1.91s/it, lr: 1.0e-04 loss: 5.076e-01]
latex_v1:   8%|7         | 239/3000 [05:39<1:27:57,  1.91s/it, lr: 1.0e-04 loss: 5.076e-01]
latex_v1:   8%|7         | 239/3000 [05:40<1:27:57,  1.91s/it, lr: 1.0e-04 loss: 6.056e-01]
latex_v1:   8%|7         | 239/3000 [05:40<1:27:57,  1.91s/it, lr: 1.0e-04 loss: 6.056e-01]
latex_v1:   8%|8         | 240/3000 [05:42<1:27:56,  1.91s/it, lr: 1.0e-04 loss: 3.210e-01]
latex_v1:   8%|8         | 240/3000 [05:42<1:27:56,  1.91s/it, lr: 1.0e-04 loss: 3.210e-01]
latex_v1:   8%|8         | 241/3000 [05:42<1:00:05,  1.31s/it, lr: 1.0e-04 loss: 3.210e-01]
latex_v1:   8%|8         | 241/3000 [05:42<1:00:05,  1.31s/it, lr: 1.0e-04 loss: 3.210e-01]
latex_v1:   8%|8         | 241/3000 [05:42<1:00:05,  1.31s/it, lr: 1.0e-04 loss: 4.406e-02]
latex_v1:   8%|8         | 241/3000 [05:42<1:00:05,  1.31s/it, lr: 1.0e-04 loss: 4.406e-02]
latex_v1:   8%|8         | 242/3000 [05:42<53:40,  1.17s/it, lr: 1.0e-04 loss: 4.406e-02]  
latex_v1:   8%|8         | 242/3000 [05:42<53:40,  1.17s/it, lr: 1.0e-04 loss: 4.406e-02]  
latex_v1:   8%|8         | 242/3000 [05:44<53:40,  1.17s/it, lr: 1.0e-04 loss: 3.846e-01]
latex_v1:   8%|8         | 242/3000 [05:44<53:40,  1.17s/it, lr: 1.0e-04 loss: 3.846e-01]
latex_v1:   8%|8         | 243/3000 [05:44<55:37,  1.21s/it, lr: 1.0e-04 loss: 3.846e-01]
latex_v1:   8%|8         | 243/3000 [05:44<55:37,  1.21s/it, lr: 1.0e-04 loss: 3.846e-01]
latex_v1:   8%|8         | 243/3000 [05:45<55:37,  1.21s/it, lr: 1.0e-04 loss: 2.981e-01]
latex_v1:   8%|8         | 243/3000 [05:45<55:37,  1.21s/it, lr: 1.0e-04 loss: 2.981e-01]
latex_v1:   8%|8         | 244/3000 [05:45<52:36,  1.15s/it, lr: 1.0e-04 loss: 2.981e-01]
latex_v1:   8%|8         | 244/3000 [05:45<52:36,  1.15s/it, lr: 1.0e-04 loss: 2.981e-01]
latex_v1:   8%|8         | 244/3000 [05:46<52:36,  1.15s/it, lr: 1.0e-04 loss: 7.076e-02]
latex_v1:   8%|8         | 244/3000 [05:46<52:36,  1.15s/it, lr: 1.0e-04 loss: 7.076e-02]
latex_v1:   8%|8         | 245/3000 [05:46<57:43,  1.26s/it, lr: 1.0e-04 loss: 7.076e-02]
latex_v1:   8%|8         | 245/3000 [05:46<57:43,  1.26s/it, lr: 1.0e-04 loss: 7.076e-02]
latex_v1:   8%|8         | 245/3000 [05:47<57:43,  1.26s/it, lr: 1.0e-04 loss: 1.588e-01]
latex_v1:   8%|8         | 245/3000 [05:47<57:43,  1.26s/it, lr: 1.0e-04 loss: 1.588e-01]
latex_v1:   8%|8         | 246/3000 [05:47<51:05,  1.11s/it, lr: 1.0e-04 loss: 1.588e-01]
latex_v1:   8%|8         | 246/3000 [05:47<51:05,  1.11s/it, lr: 1.0e-04 loss: 1.588e-01]
latex_v1:   8%|8         | 246/3000 [05:48<51:05,  1.11s/it, lr: 1.0e-04 loss: 4.005e-01]
latex_v1:   8%|8         | 246/3000 [05:48<51:05,  1.11s/it, lr: 1.0e-04 loss: 4.005e-01]
latex_v1:   8%|8         | 247/3000 [05:48<54:54,  1.20s/it, lr: 1.0e-04 loss: 4.005e-01]
latex_v1:   8%|8         | 247/3000 [05:48<54:54,  1.20s/it, lr: 1.0e-04 loss: 4.005e-01]
latex_v1:   8%|8         | 247/3000 [05:49<54:54,  1.20s/it, lr: 1.0e-04 loss: 8.071e-01]
latex_v1:   8%|8         | 247/3000 [05:49<54:54,  1.20s/it, lr: 1.0e-04 loss: 8.071e-01]
latex_v1:   8%|8         | 248/3000 [05:49<54:29,  1.19s/it, lr: 1.0e-04 loss: 8.071e-01]
latex_v1:   8%|8         | 248/3000 [05:49<54:29,  1.19s/it, lr: 1.0e-04 loss: 8.071e-01]
latex_v1:   8%|8         | 248/3000 [05:51<54:29,  1.19s/it, lr: 1.0e-04 loss: 3.306e-01]
latex_v1:   8%|8         | 248/3000 [05:51<54:29,  1.19s/it, lr: 1.0e-04 loss: 3.306e-01]
latex_v1:   8%|8         | 249/3000 [05:51<59:18,  1.29s/it, lr: 1.0e-04 loss: 3.306e-01]
latex_v1:   8%|8         | 249/3000 [05:51<59:18,  1.29s/it, lr: 1.0e-04 loss: 3.306e-01]
latex_v1:   8%|8         | 249/3000 [05:52<59:18,  1.29s/it, lr: 1.0e-04 loss: 1.715e-01]
latex_v1:   8%|8         | 249/3000 [05:52<59:18,  1.29s/it, lr: 1.0e-04 loss: 1.715e-01]
Saving at step 250
Saved checkpoint to /data/app/output/latex_v1/latex_v1_000000250.safetensors
Saved optimizer to /data/app/output/latex_v1/optimizer.pt

latex_v1:   8%|8         | 250/3000 [05:55<59:17,  1.29s/it, lr: 1.0e-04 loss: 7.057e-01]
latex_v1:   8%|8         | 250/3000 [05:55<59:17,  1.29s/it, lr: 1.0e-04 loss: 7.057e-01]
latex_v1:   8%|8         | 251/3000 [05:55<1:04:03,  1.40s/it, lr: 1.0e-04 loss: 7.057e-01]
latex_v1:   8%|8         | 251/3000 [05:55<1:04:03,  1.40s/it, lr: 1.0e-04 loss: 7.057e-01]
latex_v1:   8%|8         | 251/3000 [05:56<1:04:03,  1.40s/it, lr: 1.0e-04 loss: 2.920e-01]
latex_v1:   8%|8         | 251/3000 [05:56<1:04:03,  1.40s/it, lr: 1.0e-04 loss: 2.920e-01]
latex_v1:   8%|8         | 252/3000 [05:56<1:05:38,  1.43s/it, lr: 1.0e-04 loss: 2.920e-01]
latex_v1:   8%|8         | 252/3000 [05:56<1:05:38,  1.43s/it, lr: 1.0e-04 loss: 2.920e-01]
latex_v1:   8%|8         | 252/3000 [05:57<1:05:38,  1.43s/it, lr: 1.0e-04 loss: 2.698e-01]
latex_v1:   8%|8         | 252/3000 [05:57<1:05:38,  1.43s/it, lr: 1.0e-04 loss: 2.698e-01]
latex_v1:   8%|8         | 253/3000 [05:57<57:42,  1.26s/it, lr: 1.0e-04 loss: 2.698e-01]  
latex_v1:   8%|8         | 253/3000 [05:57<57:42,  1.26s/it, lr: 1.0e-04 loss: 2.698e-01]  
latex_v1:   8%|8         | 253/3000 [05:58<57:42,  1.26s/it, lr: 1.0e-04 loss: 6.629e-01]
latex_v1:   8%|8         | 253/3000 [05:58<57:42,  1.26s/it, lr: 1.0e-04 loss: 6.629e-01]
latex_v1:   8%|8         | 254/3000 [05:58<51:16,  1.12s/it, lr: 1.0e-04 loss: 6.629e-01]
latex_v1:   8%|8         | 254/3000 [05:58<51:16,  1.12s/it, lr: 1.0e-04 loss: 6.629e-01]
latex_v1:   8%|8         | 254/3000 [06:00<51:16,  1.12s/it, lr: 1.0e-04 loss: 3.135e-01]
latex_v1:   8%|8         | 254/3000 [06:00<51:16,  1.12s/it, lr: 1.0e-04 loss: 3.135e-01]
latex_v1:   8%|8         | 255/3000 [06:00<1:00:30,  1.32s/it, lr: 1.0e-04 loss: 3.135e-01]
latex_v1:   8%|8         | 255/3000 [06:00<1:00:30,  1.32s/it, lr: 1.0e-04 loss: 3.135e-01]
latex_v1:   8%|8         | 255/3000 [06:01<1:00:30,  1.32s/it, lr: 1.0e-04 loss: 2.680e-01]
latex_v1:   8%|8         | 255/3000 [06:01<1:00:30,  1.32s/it, lr: 1.0e-04 loss: 2.680e-01]
latex_v1:   9%|8         | 256/3000 [06:01<1:03:45,  1.39s/it, lr: 1.0e-04 loss: 2.680e-01]
latex_v1:   9%|8         | 256/3000 [06:01<1:03:45,  1.39s/it, lr: 1.0e-04 loss: 2.680e-01]
latex_v1:   9%|8         | 256/3000 [06:02<1:03:45,  1.39s/it, lr: 1.0e-04 loss: 2.397e-01]
latex_v1:   9%|8         | 256/3000 [06:02<1:03:45,  1.39s/it, lr: 1.0e-04 loss: 2.397e-01]
latex_v1:   9%|8         | 257/3000 [06:02<55:24,  1.21s/it, lr: 1.0e-04 loss: 2.397e-01]  
latex_v1:   9%|8         | 257/3000 [06:02<55:24,  1.21s/it, lr: 1.0e-04 loss: 2.397e-01]  
latex_v1:   9%|8         | 257/3000 [06:03<55:24,  1.21s/it, lr: 1.0e-04 loss: 5.740e-01]
latex_v1:   9%|8         | 257/3000 [06:03<55:24,  1.21s/it, lr: 1.0e-04 loss: 5.740e-01]
latex_v1:   9%|8         | 258/3000 [06:03<56:31,  1.24s/it, lr: 1.0e-04 loss: 5.740e-01]
latex_v1:   9%|8         | 258/3000 [06:03<56:31,  1.24s/it, lr: 1.0e-04 loss: 5.740e-01]
latex_v1:   9%|8         | 258/3000 [06:04<56:31,  1.24s/it, lr: 1.0e-04 loss: 9.017e-02]
latex_v1:   9%|8         | 258/3000 [06:04<56:31,  1.24s/it, lr: 1.0e-04 loss: 9.017e-02]
latex_v1:   9%|8         | 259/3000 [06:05<55:46,  1.22s/it, lr: 1.0e-04 loss: 9.017e-02]
latex_v1:   9%|8         | 259/3000 [06:05<55:46,  1.22s/it, lr: 1.0e-04 loss: 9.017e-02]
latex_v1:   9%|8         | 259/3000 [06:06<55:46,  1.22s/it, lr: 1.0e-04 loss: 2.446e-01]
latex_v1:   9%|8         | 259/3000 [06:06<55:46,  1.22s/it, lr: 1.0e-04 loss: 2.446e-01]
latex_v1:   9%|8         | 260/3000 [06:07<55:44,  1.22s/it, lr: 1.0e-04 loss: 1.196e-01]
latex_v1:   9%|8         | 260/3000 [06:07<55:44,  1.22s/it, lr: 1.0e-04 loss: 1.196e-01]
latex_v1:   9%|8         | 261/3000 [06:07<40:17,  1.13it/s, lr: 1.0e-04 loss: 1.196e-01]
latex_v1:   9%|8         | 261/3000 [06:07<40:17,  1.13it/s, lr: 1.0e-04 loss: 1.196e-01]
latex_v1:   9%|8         | 261/3000 [06:08<40:17,  1.13it/s, lr: 1.0e-04 loss: 5.252e-01]
latex_v1:   9%|8         | 261/3000 [06:08<40:17,  1.13it/s, lr: 1.0e-04 loss: 5.252e-01]
latex_v1:   9%|8         | 262/3000 [06:08<41:28,  1.10it/s, lr: 1.0e-04 loss: 5.252e-01]
latex_v1:   9%|8         | 262/3000 [06:08<41:28,  1.10it/s, lr: 1.0e-04 loss: 5.252e-01]
latex_v1:   9%|8         | 262/3000 [06:10<41:28,  1.10it/s, lr: 1.0e-04 loss: 3.478e-01]
latex_v1:   9%|8         | 262/3000 [06:10<41:28,  1.10it/s, lr: 1.0e-04 loss: 3.478e-01]
latex_v1:   9%|8         | 263/3000 [06:10<54:40,  1.20s/it, lr: 1.0e-04 loss: 3.478e-01]
latex_v1:   9%|8         | 263/3000 [06:10<54:40,  1.20s/it, lr: 1.0e-04 loss: 3.478e-01]
latex_v1:   9%|8         | 263/3000 [06:11<54:40,  1.20s/it, lr: 1.0e-04 loss: 4.353e-01]
latex_v1:   9%|8         | 263/3000 [06:11<54:40,  1.20s/it, lr: 1.0e-04 loss: 4.353e-01]
latex_v1:   9%|8         | 264/3000 [06:11<49:21,  1.08s/it, lr: 1.0e-04 loss: 4.353e-01]
latex_v1:   9%|8         | 264/3000 [06:11<49:21,  1.08s/it, lr: 1.0e-04 loss: 4.353e-01]
latex_v1:   9%|8         | 264/3000 [06:11<49:21,  1.08s/it, lr: 1.0e-04 loss: 3.787e-02]
latex_v1:   9%|8         | 264/3000 [06:11<49:21,  1.08s/it, lr: 1.0e-04 loss: 3.787e-02]
latex_v1:   9%|8         | 265/3000 [06:11<45:18,  1.01it/s, lr: 1.0e-04 loss: 3.787e-02]
latex_v1:   9%|8         | 265/3000 [06:11<45:18,  1.01it/s, lr: 1.0e-04 loss: 3.787e-02]
latex_v1:   9%|8         | 265/3000 [06:12<45:18,  1.01it/s, lr: 1.0e-04 loss: 2.036e-01]
latex_v1:   9%|8         | 265/3000 [06:12<45:18,  1.01it/s, lr: 1.0e-04 loss: 2.036e-01]
latex_v1:   9%|8         | 266/3000 [06:12<42:04,  1.08it/s, lr: 1.0e-04 loss: 2.036e-01]
latex_v1:   9%|8         | 266/3000 [06:12<42:04,  1.08it/s, lr: 1.0e-04 loss: 2.036e-01]
latex_v1:   9%|8         | 266/3000 [06:15<42:04,  1.08it/s, lr: 1.0e-04 loss: 1.146e-01]
latex_v1:   9%|8         | 266/3000 [06:15<42:04,  1.08it/s, lr: 1.0e-04 loss: 1.146e-01]
latex_v1:   9%|8         | 267/3000 [06:15<1:07:49,  1.49s/it, lr: 1.0e-04 loss: 1.146e-01]
latex_v1:   9%|8         | 267/3000 [06:15<1:07:49,  1.49s/it, lr: 1.0e-04 loss: 1.146e-01]
latex_v1:   9%|8         | 267/3000 [06:16<1:07:49,  1.49s/it, lr: 1.0e-04 loss: 1.075e-01]
latex_v1:   9%|8         | 267/3000 [06:16<1:07:49,  1.49s/it, lr: 1.0e-04 loss: 1.075e-01]
latex_v1:   9%|8         | 268/3000 [06:16<58:01,  1.27s/it, lr: 1.0e-04 loss: 1.075e-01]  
latex_v1:   9%|8         | 268/3000 [06:16<58:01,  1.27s/it, lr: 1.0e-04 loss: 1.075e-01]  
latex_v1:   9%|8         | 268/3000 [06:17<58:01,  1.27s/it, lr: 1.0e-04 loss: 6.607e-01]
latex_v1:   9%|8         | 268/3000 [06:17<58:01,  1.27s/it, lr: 1.0e-04 loss: 6.607e-01]
latex_v1:   9%|8         | 269/3000 [06:17<56:49,  1.25s/it, lr: 1.0e-04 loss: 6.607e-01]
latex_v1:   9%|8         | 269/3000 [06:17<56:49,  1.25s/it, lr: 1.0e-04 loss: 6.607e-01]
latex_v1:   9%|8         | 269/3000 [06:19<56:49,  1.25s/it, lr: 1.0e-04 loss: 4.673e-01]
latex_v1:   9%|8         | 269/3000 [06:19<56:49,  1.25s/it, lr: 1.0e-04 loss: 4.673e-01]
latex_v1:   9%|9         | 270/3000 [06:19<56:47,  1.25s/it, lr: 1.0e-04 loss: 1.435e-01]
latex_v1:   9%|9         | 270/3000 [06:19<56:47,  1.25s/it, lr: 1.0e-04 loss: 1.435e-01]
latex_v1:   9%|9         | 271/3000 [06:19<38:43,  1.17it/s, lr: 1.0e-04 loss: 1.435e-01]
latex_v1:   9%|9         | 271/3000 [06:19<38:43,  1.17it/s, lr: 1.0e-04 loss: 1.435e-01]
latex_v1:   9%|9         | 271/3000 [06:20<38:43,  1.17it/s, lr: 1.0e-04 loss: 5.916e-01]
latex_v1:   9%|9         | 271/3000 [06:20<38:43,  1.17it/s, lr: 1.0e-04 loss: 5.916e-01]
latex_v1:   9%|9         | 272/3000 [06:20<37:34,  1.21it/s, lr: 1.0e-04 loss: 5.916e-01]
latex_v1:   9%|9         | 272/3000 [06:20<37:34,  1.21it/s, lr: 1.0e-04 loss: 5.916e-01]
latex_v1:   9%|9         | 272/3000 [06:22<37:34,  1.21it/s, lr: 1.0e-04 loss: 5.258e-01]
latex_v1:   9%|9         | 272/3000 [06:22<37:34,  1.21it/s, lr: 1.0e-04 loss: 5.258e-01]
latex_v1:   9%|9         | 273/3000 [06:22<51:09,  1.13s/it, lr: 1.0e-04 loss: 5.258e-01]
latex_v1:   9%|9         | 273/3000 [06:22<51:09,  1.13s/it, lr: 1.0e-04 loss: 5.258e-01]
latex_v1:   9%|9         | 273/3000 [06:24<51:09,  1.13s/it, lr: 1.0e-04 loss: 1.929e-01]
latex_v1:   9%|9         | 273/3000 [06:24<51:09,  1.13s/it, lr: 1.0e-04 loss: 1.929e-01]
latex_v1:   9%|9         | 274/3000 [06:24<56:17,  1.24s/it, lr: 1.0e-04 loss: 1.929e-01]
latex_v1:   9%|9         | 274/3000 [06:24<56:17,  1.24s/it, lr: 1.0e-04 loss: 1.929e-01]
latex_v1:   9%|9         | 274/3000 [06:26<56:17,  1.24s/it, lr: 1.0e-04 loss: 2.705e-01]
latex_v1:   9%|9         | 274/3000 [06:26<56:17,  1.24s/it, lr: 1.0e-04 loss: 2.705e-01]
latex_v1:   9%|9         | 275/3000 [06:26<1:04:38,  1.42s/it, lr: 1.0e-04 loss: 2.705e-01]
latex_v1:   9%|9         | 275/3000 [06:26<1:04:38,  1.42s/it, lr: 1.0e-04 loss: 2.705e-01]
latex_v1:   9%|9         | 275/3000 [06:27<1:04:38,  1.42s/it, lr: 1.0e-04 loss: 2.992e-01]
latex_v1:   9%|9         | 275/3000 [06:27<1:04:38,  1.42s/it, lr: 1.0e-04 loss: 2.992e-01]
latex_v1:   9%|9         | 276/3000 [06:27<1:03:27,  1.40s/it, lr: 1.0e-04 loss: 2.992e-01]
latex_v1:   9%|9         | 276/3000 [06:27<1:03:27,  1.40s/it, lr: 1.0e-04 loss: 2.992e-01]
latex_v1:   9%|9         | 276/3000 [06:28<1:03:27,  1.40s/it, lr: 1.0e-04 loss: 3.781e-01]
latex_v1:   9%|9         | 276/3000 [06:28<1:03:27,  1.40s/it, lr: 1.0e-04 loss: 3.781e-01]
latex_v1:   9%|9         | 277/3000 [06:28<1:04:37,  1.42s/it, lr: 1.0e-04 loss: 3.781e-01]
latex_v1:   9%|9         | 277/3000 [06:28<1:04:37,  1.42s/it, lr: 1.0e-04 loss: 3.781e-01]
latex_v1:   9%|9         | 277/3000 [06:30<1:04:37,  1.42s/it, lr: 1.0e-04 loss: 9.421e-02]
latex_v1:   9%|9         | 277/3000 [06:30<1:04:37,  1.42s/it, lr: 1.0e-04 loss: 9.421e-02]
latex_v1:   9%|9         | 278/3000 [06:30<1:05:06,  1.44s/it, lr: 1.0e-04 loss: 9.421e-02]
latex_v1:   9%|9         | 278/3000 [06:30<1:05:06,  1.44s/it, lr: 1.0e-04 loss: 9.421e-02]
latex_v1:   9%|9         | 278/3000 [06:31<1:05:06,  1.44s/it, lr: 1.0e-04 loss: 1.272e-01]
latex_v1:   9%|9         | 278/3000 [06:31<1:05:06,  1.44s/it, lr: 1.0e-04 loss: 1.272e-01]
latex_v1:   9%|9         | 279/3000 [06:31<56:54,  1.25s/it, lr: 1.0e-04 loss: 1.272e-01]  
latex_v1:   9%|9         | 279/3000 [06:31<56:54,  1.25s/it, lr: 1.0e-04 loss: 1.272e-01]  
latex_v1:   9%|9         | 279/3000 [06:33<56:54,  1.25s/it, lr: 1.0e-04 loss: 5.010e-01]
latex_v1:   9%|9         | 279/3000 [06:33<56:54,  1.25s/it, lr: 1.0e-04 loss: 5.010e-01]
latex_v1:   9%|9         | 280/3000 [06:34<56:53,  1.25s/it, lr: 1.0e-04 loss: 1.262e-01]
latex_v1:   9%|9         | 280/3000 [06:34<56:53,  1.25s/it, lr: 1.0e-04 loss: 1.262e-01]
latex_v1:   9%|9         | 281/3000 [06:34<49:55,  1.10s/it, lr: 1.0e-04 loss: 1.262e-01]
latex_v1:   9%|9         | 281/3000 [06:34<49:55,  1.10s/it, lr: 1.0e-04 loss: 1.262e-01]
latex_v1:   9%|9         | 281/3000 [06:36<49:55,  1.10s/it, lr: 1.0e-04 loss: 5.105e-02]
latex_v1:   9%|9         | 281/3000 [06:36<49:55,  1.10s/it, lr: 1.0e-04 loss: 5.105e-02]
latex_v1:   9%|9         | 282/3000 [06:36<53:47,  1.19s/it, lr: 1.0e-04 loss: 5.105e-02]
latex_v1:   9%|9         | 282/3000 [06:36<53:47,  1.19s/it, lr: 1.0e-04 loss: 5.105e-02]
latex_v1:   9%|9         | 282/3000 [06:37<53:47,  1.19s/it, lr: 1.0e-04 loss: 5.495e-01]
latex_v1:   9%|9         | 282/3000 [06:37<53:47,  1.19s/it, lr: 1.0e-04 loss: 5.495e-01]
latex_v1:   9%|9         | 283/3000 [06:37<48:55,  1.08s/it, lr: 1.0e-04 loss: 5.495e-01]
latex_v1:   9%|9         | 283/3000 [06:37<48:55,  1.08s/it, lr: 1.0e-04 loss: 5.495e-01]
latex_v1:   9%|9         | 283/3000 [06:39<48:55,  1.08s/it, lr: 1.0e-04 loss: 4.030e-01]
latex_v1:   9%|9         | 283/3000 [06:39<48:55,  1.08s/it, lr: 1.0e-04 loss: 4.030e-01]
latex_v1:   9%|9         | 284/3000 [06:40<1:10:22,  1.55s/it, lr: 1.0e-04 loss: 4.030e-01]
latex_v1:   9%|9         | 284/3000 [06:40<1:10:22,  1.55s/it, lr: 1.0e-04 loss: 4.030e-01]
latex_v1:   9%|9         | 284/3000 [06:41<1:10:22,  1.55s/it, lr: 1.0e-04 loss: 1.193e-01]
latex_v1:   9%|9         | 284/3000 [06:41<1:10:22,  1.55s/it, lr: 1.0e-04 loss: 1.193e-01]
latex_v1:  10%|9         | 285/3000 [06:41<1:04:06,  1.42s/it, lr: 1.0e-04 loss: 1.193e-01]
latex_v1:  10%|9         | 285/3000 [06:41<1:04:06,  1.42s/it, lr: 1.0e-04 loss: 1.193e-01]
latex_v1:  10%|9         | 285/3000 [06:42<1:04:06,  1.42s/it, lr: 1.0e-04 loss: 7.122e-02]
latex_v1:  10%|9         | 285/3000 [06:42<1:04:06,  1.42s/it, lr: 1.0e-04 loss: 7.122e-02]
latex_v1:  10%|9         | 286/3000 [06:42<1:03:52,  1.41s/it, lr: 1.0e-04 loss: 7.122e-02]
latex_v1:  10%|9         | 286/3000 [06:42<1:03:52,  1.41s/it, lr: 1.0e-04 loss: 7.122e-02]
latex_v1:  10%|9         | 286/3000 [06:45<1:03:52,  1.41s/it, lr: 1.0e-04 loss: 1.049e-01]
latex_v1:  10%|9         | 286/3000 [06:45<1:03:52,  1.41s/it, lr: 1.0e-04 loss: 1.049e-01]
latex_v1:  10%|9         | 287/3000 [06:45<1:23:08,  1.84s/it, lr: 1.0e-04 loss: 1.049e-01]
latex_v1:  10%|9         | 287/3000 [06:45<1:23:08,  1.84s/it, lr: 1.0e-04 loss: 1.049e-01]
latex_v1:  10%|9         | 287/3000 [06:46<1:23:08,  1.84s/it, lr: 1.0e-04 loss: 5.188e-02]
latex_v1:  10%|9         | 287/3000 [06:46<1:23:08,  1.84s/it, lr: 1.0e-04 loss: 5.188e-02]
latex_v1:  10%|9         | 288/3000 [06:46<1:08:38,  1.52s/it, lr: 1.0e-04 loss: 5.188e-02]
latex_v1:  10%|9         | 288/3000 [06:46<1:08:38,  1.52s/it, lr: 1.0e-04 loss: 5.188e-02]
latex_v1:  10%|9         | 288/3000 [06:47<1:08:38,  1.52s/it, lr: 1.0e-04 loss: 2.873e-01]
latex_v1:  10%|9         | 288/3000 [06:47<1:08:38,  1.52s/it, lr: 1.0e-04 loss: 2.873e-01]
latex_v1:  10%|9         | 289/3000 [06:47<1:04:04,  1.42s/it, lr: 1.0e-04 loss: 2.873e-01]
latex_v1:  10%|9         | 289/3000 [06:47<1:04:04,  1.42s/it, lr: 1.0e-04 loss: 2.873e-01]
latex_v1:  10%|9         | 289/3000 [06:47<1:04:04,  1.42s/it, lr: 1.0e-04 loss: 6.302e-01]
latex_v1:  10%|9         | 289/3000 [06:47<1:04:04,  1.42s/it, lr: 1.0e-04 loss: 6.302e-01]
latex_v1:  10%|9         | 290/3000 [06:51<1:04:03,  1.42s/it, lr: 1.0e-04 loss: 1.160e-01]
latex_v1:  10%|9         | 290/3000 [06:51<1:04:03,  1.42s/it, lr: 1.0e-04 loss: 1.160e-01]
latex_v1:  10%|9         | 291/3000 [06:51<1:05:56,  1.46s/it, lr: 1.0e-04 loss: 1.160e-01]
latex_v1:  10%|9         | 291/3000 [06:51<1:05:56,  1.46s/it, lr: 1.0e-04 loss: 1.160e-01]
latex_v1:  10%|9         | 291/3000 [06:52<1:05:56,  1.46s/it, lr: 1.0e-04 loss: 3.304e-01]
latex_v1:  10%|9         | 291/3000 [06:52<1:05:56,  1.46s/it, lr: 1.0e-04 loss: 3.304e-01]
latex_v1:  10%|9         | 292/3000 [06:52<1:05:21,  1.45s/it, lr: 1.0e-04 loss: 3.304e-01]
latex_v1:  10%|9         | 292/3000 [06:52<1:05:21,  1.45s/it, lr: 1.0e-04 loss: 3.304e-01]
latex_v1:  10%|9         | 292/3000 [06:53<1:05:21,  1.45s/it, lr: 1.0e-04 loss: 2.050e-01]
latex_v1:  10%|9         | 292/3000 [06:53<1:05:21,  1.45s/it, lr: 1.0e-04 loss: 2.050e-01]
latex_v1:  10%|9         | 293/3000 [06:53<1:02:06,  1.38s/it, lr: 1.0e-04 loss: 2.050e-01]
latex_v1:  10%|9         | 293/3000 [06:53<1:02:06,  1.38s/it, lr: 1.0e-04 loss: 2.050e-01]
latex_v1:  10%|9         | 293/3000 [06:54<1:02:06,  1.38s/it, lr: 1.0e-04 loss: 4.301e-01]
latex_v1:  10%|9         | 293/3000 [06:54<1:02:06,  1.38s/it, lr: 1.0e-04 loss: 4.301e-01]
latex_v1:  10%|9         | 294/3000 [06:54<54:17,  1.20s/it, lr: 1.0e-04 loss: 4.301e-01]  
latex_v1:  10%|9         | 294/3000 [06:54<54:17,  1.20s/it, lr: 1.0e-04 loss: 4.301e-01]  
latex_v1:  10%|9         | 294/3000 [06:55<54:17,  1.20s/it, lr: 1.0e-04 loss: 5.457e-01]
latex_v1:  10%|9         | 294/3000 [06:55<54:17,  1.20s/it, lr: 1.0e-04 loss: 5.457e-01]
latex_v1:  10%|9         | 295/3000 [06:55<48:30,  1.08s/it, lr: 1.0e-04 loss: 5.457e-01]
latex_v1:  10%|9         | 295/3000 [06:55<48:30,  1.08s/it, lr: 1.0e-04 loss: 5.457e-01]
latex_v1:  10%|9         | 295/3000 [06:56<48:30,  1.08s/it, lr: 1.0e-04 loss: 1.085e-01]
latex_v1:  10%|9         | 295/3000 [06:56<48:30,  1.08s/it, lr: 1.0e-04 loss: 1.085e-01]
latex_v1:  10%|9         | 296/3000 [06:56<54:23,  1.21s/it, lr: 1.0e-04 loss: 1.085e-01]
latex_v1:  10%|9         | 296/3000 [06:56<54:23,  1.21s/it, lr: 1.0e-04 loss: 1.085e-01]
latex_v1:  10%|9         | 296/3000 [06:58<54:23,  1.21s/it, lr: 1.0e-04 loss: 5.118e-01]
latex_v1:  10%|9         | 296/3000 [06:58<54:23,  1.21s/it, lr: 1.0e-04 loss: 5.118e-01]
latex_v1:  10%|9         | 297/3000 [06:58<57:26,  1.27s/it, lr: 1.0e-04 loss: 5.118e-01]
latex_v1:  10%|9         | 297/3000 [06:58<57:26,  1.27s/it, lr: 1.0e-04 loss: 5.118e-01]
latex_v1:  10%|9         | 297/3000 [06:59<57:26,  1.27s/it, lr: 1.0e-04 loss: 1.864e-01]
latex_v1:  10%|9         | 297/3000 [06:59<57:26,  1.27s/it, lr: 1.0e-04 loss: 1.864e-01]
latex_v1:  10%|9         | 298/3000 [06:59<1:00:59,  1.35s/it, lr: 1.0e-04 loss: 1.864e-01]
latex_v1:  10%|9         | 298/3000 [06:59<1:00:59,  1.35s/it, lr: 1.0e-04 loss: 1.864e-01]
latex_v1:  10%|9         | 298/3000 [07:01<1:00:59,  1.35s/it, lr: 1.0e-04 loss: 1.265e-01]
latex_v1:  10%|9         | 298/3000 [07:01<1:00:59,  1.35s/it, lr: 1.0e-04 loss: 1.265e-01]
latex_v1:  10%|9         | 299/3000 [07:01<1:08:09,  1.51s/it, lr: 1.0e-04 loss: 1.265e-01]
latex_v1:  10%|9         | 299/3000 [07:01<1:08:09,  1.51s/it, lr: 1.0e-04 loss: 1.265e-01]
latex_v1:  10%|9         | 299/3000 [07:02<1:08:09,  1.51s/it, lr: 1.0e-04 loss: 6.248e-01]
latex_v1:  10%|9         | 299/3000 [07:02<1:08:09,  1.51s/it, lr: 1.0e-04 loss: 6.248e-01]Unloading assistant lora



Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]


Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.36s/it]
Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.36s/it]


Generating Images:  29%|##8       | 2/7 [00:04<00:11,  2.36s/it]
Generating Images:  29%|##8       | 2/7 [00:04<00:11,  2.36s/it]


Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.43s/it]
Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.43s/it]


Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.42s/it]
Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.42s/it]


Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.40s/it]
Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.40s/it]


Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.42s/it]
Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.42s/it]


Generating Images: 100%|##########| 7/7 [00:16<00:00,  2.42s/it]
Generating Images: 100%|##########| 7/7 [00:16<00:00,  2.42s/it]


                                                                
                                                                Loading assistant lora

latex_v1:  10%|#         | 300/3000 [07:03<1:08:07,  1.51s/it, lr: 1.0e-04 loss: 2.639e-01]
latex_v1:  10%|#         | 300/3000 [07:03<1:08:07,  1.51s/it, lr: 1.0e-04 loss: 2.639e-01]
latex_v1:  10%|#         | 301/3000 [07:03<44:51,  1.00it/s, lr: 1.0e-04 loss: 2.639e-01]  
latex_v1:  10%|#         | 301/3000 [07:03<44:51,  1.00it/s, lr: 1.0e-04 loss: 2.639e-01]  
latex_v1:  10%|#         | 301/3000 [07:04<44:51,  1.00it/s, lr: 1.0e-04 loss: 4.675e-01]
latex_v1:  10%|#         | 301/3000 [07:04<44:51,  1.00it/s, lr: 1.0e-04 loss: 4.675e-01]
latex_v1:  10%|#         | 302/3000 [07:04<48:51,  1.09s/it, lr: 1.0e-04 loss: 4.675e-01]
latex_v1:  10%|#         | 302/3000 [07:04<48:51,  1.09s/it, lr: 1.0e-04 loss: 4.675e-01]
latex_v1:  10%|#         | 302/3000 [07:05<48:51,  1.09s/it, lr: 1.0e-04 loss: 7.654e-01]
latex_v1:  10%|#         | 302/3000 [07:05<48:51,  1.09s/it, lr: 1.0e-04 loss: 7.654e-01]
latex_v1:  10%|#         | 303/3000 [07:05<44:50,  1.00it/s, lr: 1.0e-04 loss: 7.654e-01]
latex_v1:  10%|#         | 303/3000 [07:05<44:50,  1.00it/s, lr: 1.0e-04 loss: 7.654e-01]
latex_v1:  10%|#         | 303/3000 [07:06<44:50,  1.00it/s, lr: 1.0e-04 loss: 2.603e-01]
latex_v1:  10%|#         | 303/3000 [07:06<44:50,  1.00it/s, lr: 1.0e-04 loss: 2.603e-01]
latex_v1:  10%|#         | 304/3000 [07:06<48:44,  1.08s/it, lr: 1.0e-04 loss: 2.603e-01]
latex_v1:  10%|#         | 304/3000 [07:06<48:44,  1.08s/it, lr: 1.0e-04 loss: 2.603e-01]
latex_v1:  10%|#         | 304/3000 [07:08<48:44,  1.08s/it, lr: 1.0e-04 loss: 5.787e-01]
latex_v1:  10%|#         | 304/3000 [07:08<48:44,  1.08s/it, lr: 1.0e-04 loss: 5.787e-01]
latex_v1:  10%|#         | 305/3000 [07:08<53:28,  1.19s/it, lr: 1.0e-04 loss: 5.787e-01]
latex_v1:  10%|#         | 305/3000 [07:08<53:28,  1.19s/it, lr: 1.0e-04 loss: 5.787e-01]
latex_v1:  10%|#         | 305/3000 [07:09<53:28,  1.19s/it, lr: 1.0e-04 loss: 5.155e-01]
latex_v1:  10%|#         | 305/3000 [07:09<53:28,  1.19s/it, lr: 1.0e-04 loss: 5.155e-01]
latex_v1:  10%|#         | 306/3000 [07:09<47:51,  1.07s/it, lr: 1.0e-04 loss: 5.155e-01]
latex_v1:  10%|#         | 306/3000 [07:09<47:51,  1.07s/it, lr: 1.0e-04 loss: 5.155e-01]
latex_v1:  10%|#         | 306/3000 [07:10<47:51,  1.07s/it, lr: 1.0e-04 loss: 3.783e-01]
latex_v1:  10%|#         | 306/3000 [07:10<47:51,  1.07s/it, lr: 1.0e-04 loss: 3.783e-01]
latex_v1:  10%|#         | 307/3000 [07:10<54:16,  1.21s/it, lr: 1.0e-04 loss: 3.783e-01]
latex_v1:  10%|#         | 307/3000 [07:10<54:16,  1.21s/it, lr: 1.0e-04 loss: 3.783e-01]
latex_v1:  10%|#         | 307/3000 [07:11<54:16,  1.21s/it, lr: 1.0e-04 loss: 1.763e-01]
latex_v1:  10%|#         | 307/3000 [07:11<54:16,  1.21s/it, lr: 1.0e-04 loss: 1.763e-01]
latex_v1:  10%|#         | 308/3000 [07:11<48:14,  1.08s/it, lr: 1.0e-04 loss: 1.763e-01]
latex_v1:  10%|#         | 308/3000 [07:11<48:14,  1.08s/it, lr: 1.0e-04 loss: 1.763e-01]
latex_v1:  10%|#         | 308/3000 [07:12<48:14,  1.08s/it, lr: 1.0e-04 loss: 3.838e-01]
latex_v1:  10%|#         | 308/3000 [07:12<48:14,  1.08s/it, lr: 1.0e-04 loss: 3.838e-01]
latex_v1:  10%|#         | 309/3000 [07:12<43:55,  1.02it/s, lr: 1.0e-04 loss: 3.838e-01]
latex_v1:  10%|#         | 309/3000 [07:12<43:55,  1.02it/s, lr: 1.0e-04 loss: 3.838e-01]
latex_v1:  10%|#         | 309/3000 [07:13<43:55,  1.02it/s, lr: 1.0e-04 loss: 1.644e-01]
latex_v1:  10%|#         | 309/3000 [07:13<43:55,  1.02it/s, lr: 1.0e-04 loss: 1.644e-01]
latex_v1:  10%|#         | 310/3000 [07:14<43:54,  1.02it/s, lr: 1.0e-04 loss: 4.190e-01]
latex_v1:  10%|#         | 310/3000 [07:14<43:54,  1.02it/s, lr: 1.0e-04 loss: 4.190e-01]
latex_v1:  10%|#         | 311/3000 [07:14<31:26,  1.43it/s, lr: 1.0e-04 loss: 4.190e-01]
latex_v1:  10%|#         | 311/3000 [07:14<31:26,  1.43it/s, lr: 1.0e-04 loss: 4.190e-01]
latex_v1:  10%|#         | 311/3000 [07:15<31:26,  1.43it/s, lr: 1.0e-04 loss: 1.718e-01]
latex_v1:  10%|#         | 311/3000 [07:15<31:26,  1.43it/s, lr: 1.0e-04 loss: 1.718e-01]
latex_v1:  10%|#         | 312/3000 [07:15<39:21,  1.14it/s, lr: 1.0e-04 loss: 1.718e-01]
latex_v1:  10%|#         | 312/3000 [07:15<39:21,  1.14it/s, lr: 1.0e-04 loss: 1.718e-01]
latex_v1:  10%|#         | 312/3000 [07:17<39:21,  1.14it/s, lr: 1.0e-04 loss: 2.666e-01]
latex_v1:  10%|#         | 312/3000 [07:17<39:21,  1.14it/s, lr: 1.0e-04 loss: 2.666e-01]
latex_v1:  10%|#         | 313/3000 [07:17<47:51,  1.07s/it, lr: 1.0e-04 loss: 2.666e-01]
latex_v1:  10%|#         | 313/3000 [07:17<47:51,  1.07s/it, lr: 1.0e-04 loss: 2.666e-01]
latex_v1:  10%|#         | 313/3000 [07:18<47:51,  1.07s/it, lr: 1.0e-04 loss: 1.905e-01]
latex_v1:  10%|#         | 313/3000 [07:18<47:51,  1.07s/it, lr: 1.0e-04 loss: 1.905e-01]
latex_v1:  10%|#         | 314/3000 [07:18<44:15,  1.01it/s, lr: 1.0e-04 loss: 1.905e-01]
latex_v1:  10%|#         | 314/3000 [07:18<44:15,  1.01it/s, lr: 1.0e-04 loss: 1.905e-01]
latex_v1:  10%|#         | 314/3000 [07:20<44:15,  1.01it/s, lr: 1.0e-04 loss: 5.461e-01]
latex_v1:  10%|#         | 314/3000 [07:20<44:15,  1.01it/s, lr: 1.0e-04 loss: 5.461e-01]
latex_v1:  10%|#         | 315/3000 [07:20<55:46,  1.25s/it, lr: 1.0e-04 loss: 5.461e-01]
latex_v1:  10%|#         | 315/3000 [07:20<55:46,  1.25s/it, lr: 1.0e-04 loss: 5.461e-01]
latex_v1:  10%|#         | 315/3000 [07:22<55:46,  1.25s/it, lr: 1.0e-04 loss: 5.166e-01]
latex_v1:  10%|#         | 315/3000 [07:22<55:46,  1.25s/it, lr: 1.0e-04 loss: 5.166e-01]
latex_v1:  11%|#         | 316/3000 [07:22<1:03:55,  1.43s/it, lr: 1.0e-04 loss: 5.166e-01]
latex_v1:  11%|#         | 316/3000 [07:22<1:03:55,  1.43s/it, lr: 1.0e-04 loss: 5.166e-01]
latex_v1:  11%|#         | 316/3000 [07:23<1:03:55,  1.43s/it, lr: 1.0e-04 loss: 1.083e-01]
latex_v1:  11%|#         | 316/3000 [07:23<1:03:55,  1.43s/it, lr: 1.0e-04 loss: 1.083e-01]
latex_v1:  11%|#         | 317/3000 [07:23<1:03:48,  1.43s/it, lr: 1.0e-04 loss: 1.083e-01]
latex_v1:  11%|#         | 317/3000 [07:23<1:03:48,  1.43s/it, lr: 1.0e-04 loss: 1.083e-01]
latex_v1:  11%|#         | 317/3000 [07:24<1:03:48,  1.43s/it, lr: 1.0e-04 loss: 5.005e-01]
latex_v1:  11%|#         | 317/3000 [07:24<1:03:48,  1.43s/it, lr: 1.0e-04 loss: 5.005e-01]
latex_v1:  11%|#         | 318/3000 [07:24<57:35,  1.29s/it, lr: 1.0e-04 loss: 5.005e-01]  
latex_v1:  11%|#         | 318/3000 [07:24<57:35,  1.29s/it, lr: 1.0e-04 loss: 5.005e-01]  
latex_v1:  11%|#         | 318/3000 [07:27<57:35,  1.29s/it, lr: 1.0e-04 loss: 2.330e-01]
latex_v1:  11%|#         | 318/3000 [07:27<57:35,  1.29s/it, lr: 1.0e-04 loss: 2.330e-01]
latex_v1:  11%|#         | 319/3000 [07:27<1:16:17,  1.71s/it, lr: 1.0e-04 loss: 2.330e-01]
latex_v1:  11%|#         | 319/3000 [07:27<1:16:17,  1.71s/it, lr: 1.0e-04 loss: 2.330e-01]
latex_v1:  11%|#         | 319/3000 [07:28<1:16:17,  1.71s/it, lr: 1.0e-04 loss: 5.149e-01]
latex_v1:  11%|#         | 319/3000 [07:28<1:16:17,  1.71s/it, lr: 1.0e-04 loss: 5.149e-01]
latex_v1:  11%|#         | 320/3000 [07:29<1:16:16,  1.71s/it, lr: 1.0e-04 loss: 3.935e-01]
latex_v1:  11%|#         | 320/3000 [07:29<1:16:16,  1.71s/it, lr: 1.0e-04 loss: 3.935e-01]
latex_v1:  11%|#         | 321/3000 [07:29<49:06,  1.10s/it, lr: 1.0e-04 loss: 3.935e-01]  
latex_v1:  11%|#         | 321/3000 [07:29<49:06,  1.10s/it, lr: 1.0e-04 loss: 3.935e-01]  
latex_v1:  11%|#         | 321/3000 [07:32<49:06,  1.10s/it, lr: 1.0e-04 loss: 3.780e-01]
latex_v1:  11%|#         | 321/3000 [07:32<49:06,  1.10s/it, lr: 1.0e-04 loss: 3.780e-01]
latex_v1:  11%|#         | 322/3000 [07:32<1:05:56,  1.48s/it, lr: 1.0e-04 loss: 3.780e-01]
latex_v1:  11%|#         | 322/3000 [07:32<1:05:56,  1.48s/it, lr: 1.0e-04 loss: 3.780e-01]
latex_v1:  11%|#         | 322/3000 [07:32<1:05:56,  1.48s/it, lr: 1.0e-04 loss: 5.315e-01]
latex_v1:  11%|#         | 322/3000 [07:32<1:05:56,  1.48s/it, lr: 1.0e-04 loss: 5.315e-01]
latex_v1:  11%|#         | 323/3000 [07:32<57:40,  1.29s/it, lr: 1.0e-04 loss: 5.315e-01]  
latex_v1:  11%|#         | 323/3000 [07:32<57:40,  1.29s/it, lr: 1.0e-04 loss: 5.315e-01]  
latex_v1:  11%|#         | 323/3000 [07:35<57:40,  1.29s/it, lr: 1.0e-04 loss: 1.190e-01]
latex_v1:  11%|#         | 323/3000 [07:35<57:40,  1.29s/it, lr: 1.0e-04 loss: 1.190e-01]
latex_v1:  11%|#         | 324/3000 [07:35<1:16:25,  1.71s/it, lr: 1.0e-04 loss: 1.190e-01]
latex_v1:  11%|#         | 324/3000 [07:35<1:16:25,  1.71s/it, lr: 1.0e-04 loss: 1.190e-01]
latex_v1:  11%|#         | 324/3000 [07:38<1:16:25,  1.71s/it, lr: 1.0e-04 loss: 6.053e-01]
latex_v1:  11%|#         | 324/3000 [07:38<1:16:25,  1.71s/it, lr: 1.0e-04 loss: 6.053e-01]
latex_v1:  11%|#         | 325/3000 [07:38<1:30:29,  2.03s/it, lr: 1.0e-04 loss: 6.053e-01]
latex_v1:  11%|#         | 325/3000 [07:38<1:30:29,  2.03s/it, lr: 1.0e-04 loss: 6.053e-01]
latex_v1:  11%|#         | 325/3000 [07:40<1:30:29,  2.03s/it, lr: 1.0e-04 loss: 5.638e-01]
latex_v1:  11%|#         | 325/3000 [07:40<1:30:29,  2.03s/it, lr: 1.0e-04 loss: 5.638e-01]
latex_v1:  11%|#         | 326/3000 [07:40<1:24:14,  1.89s/it, lr: 1.0e-04 loss: 5.638e-01]
latex_v1:  11%|#         | 326/3000 [07:40<1:24:14,  1.89s/it, lr: 1.0e-04 loss: 5.638e-01]
latex_v1:  11%|#         | 326/3000 [07:41<1:24:14,  1.89s/it, lr: 1.0e-04 loss: 6.799e-01]
latex_v1:  11%|#         | 326/3000 [07:41<1:24:14,  1.89s/it, lr: 1.0e-04 loss: 6.799e-01]
latex_v1:  11%|#         | 327/3000 [07:41<1:21:38,  1.83s/it, lr: 1.0e-04 loss: 6.799e-01]
latex_v1:  11%|#         | 327/3000 [07:41<1:21:38,  1.83s/it, lr: 1.0e-04 loss: 6.799e-01]
latex_v1:  11%|#         | 327/3000 [07:43<1:21:38,  1.83s/it, lr: 1.0e-04 loss: 3.722e-01]
latex_v1:  11%|#         | 327/3000 [07:43<1:21:38,  1.83s/it, lr: 1.0e-04 loss: 3.722e-01]
latex_v1:  11%|#         | 328/3000 [07:43<1:15:01,  1.68s/it, lr: 1.0e-04 loss: 3.722e-01]
latex_v1:  11%|#         | 328/3000 [07:43<1:15:01,  1.68s/it, lr: 1.0e-04 loss: 3.722e-01]
latex_v1:  11%|#         | 328/3000 [07:44<1:15:01,  1.68s/it, lr: 1.0e-04 loss: 5.000e-02]
latex_v1:  11%|#         | 328/3000 [07:44<1:15:01,  1.68s/it, lr: 1.0e-04 loss: 5.000e-02]
latex_v1:  11%|#         | 329/3000 [07:44<1:13:00,  1.64s/it, lr: 1.0e-04 loss: 5.000e-02]
latex_v1:  11%|#         | 329/3000 [07:44<1:13:00,  1.64s/it, lr: 1.0e-04 loss: 5.000e-02]
latex_v1:  11%|#         | 329/3000 [07:45<1:13:00,  1.64s/it, lr: 1.0e-04 loss: 1.451e-01]
latex_v1:  11%|#         | 329/3000 [07:45<1:13:00,  1.64s/it, lr: 1.0e-04 loss: 1.451e-01]
latex_v1:  11%|#1        | 330/3000 [07:46<1:12:58,  1.64s/it, lr: 1.0e-04 loss: 6.113e-01]
latex_v1:  11%|#1        | 330/3000 [07:46<1:12:58,  1.64s/it, lr: 1.0e-04 loss: 6.113e-01]
latex_v1:  11%|#1        | 331/3000 [07:46<55:16,  1.24s/it, lr: 1.0e-04 loss: 6.113e-01]  
latex_v1:  11%|#1        | 331/3000 [07:46<55:16,  1.24s/it, lr: 1.0e-04 loss: 6.113e-01]  
latex_v1:  11%|#1        | 331/3000 [07:48<55:16,  1.24s/it, lr: 1.0e-04 loss: 9.651e-02]
latex_v1:  11%|#1        | 331/3000 [07:48<55:16,  1.24s/it, lr: 1.0e-04 loss: 9.651e-02]
latex_v1:  11%|#1        | 332/3000 [07:48<58:47,  1.32s/it, lr: 1.0e-04 loss: 9.651e-02]
latex_v1:  11%|#1        | 332/3000 [07:48<58:47,  1.32s/it, lr: 1.0e-04 loss: 9.651e-02]
latex_v1:  11%|#1        | 332/3000 [07:49<58:47,  1.32s/it, lr: 1.0e-04 loss: 2.229e-01]
latex_v1:  11%|#1        | 332/3000 [07:49<58:47,  1.32s/it, lr: 1.0e-04 loss: 2.229e-01]
latex_v1:  11%|#1        | 333/3000 [07:49<52:03,  1.17s/it, lr: 1.0e-04 loss: 2.229e-01]
latex_v1:  11%|#1        | 333/3000 [07:49<52:03,  1.17s/it, lr: 1.0e-04 loss: 2.229e-01]
latex_v1:  11%|#1        | 333/3000 [07:50<52:03,  1.17s/it, lr: 1.0e-04 loss: 1.033e-01]
latex_v1:  11%|#1        | 333/3000 [07:50<52:03,  1.17s/it, lr: 1.0e-04 loss: 1.033e-01]
latex_v1:  11%|#1        | 334/3000 [07:50<52:02,  1.17s/it, lr: 1.0e-04 loss: 1.033e-01]
latex_v1:  11%|#1        | 334/3000 [07:50<52:02,  1.17s/it, lr: 1.0e-04 loss: 1.033e-01]
latex_v1:  11%|#1        | 334/3000 [07:51<52:02,  1.17s/it, lr: 1.0e-04 loss: 6.229e-01]
latex_v1:  11%|#1        | 334/3000 [07:51<52:02,  1.17s/it, lr: 1.0e-04 loss: 6.229e-01]
latex_v1:  11%|#1        | 335/3000 [07:51<46:37,  1.05s/it, lr: 1.0e-04 loss: 6.229e-01]
latex_v1:  11%|#1        | 335/3000 [07:51<46:37,  1.05s/it, lr: 1.0e-04 loss: 6.229e-01]
latex_v1:  11%|#1        | 335/3000 [07:52<46:37,  1.05s/it, lr: 1.0e-04 loss: 1.481e-01]
latex_v1:  11%|#1        | 335/3000 [07:52<46:37,  1.05s/it, lr: 1.0e-04 loss: 1.481e-01]
latex_v1:  11%|#1        | 336/3000 [07:52<48:01,  1.08s/it, lr: 1.0e-04 loss: 1.481e-01]
latex_v1:  11%|#1        | 336/3000 [07:52<48:01,  1.08s/it, lr: 1.0e-04 loss: 1.481e-01]
latex_v1:  11%|#1        | 336/3000 [07:53<48:01,  1.08s/it, lr: 1.0e-04 loss: 2.029e-01]
latex_v1:  11%|#1        | 336/3000 [07:53<48:01,  1.08s/it, lr: 1.0e-04 loss: 2.029e-01]
latex_v1:  11%|#1        | 337/3000 [07:53<43:42,  1.02it/s, lr: 1.0e-04 loss: 2.029e-01]
latex_v1:  11%|#1        | 337/3000 [07:53<43:42,  1.02it/s, lr: 1.0e-04 loss: 2.029e-01]
latex_v1:  11%|#1        | 337/3000 [07:54<43:42,  1.02it/s, lr: 1.0e-04 loss: 3.396e-01]
latex_v1:  11%|#1        | 337/3000 [07:54<43:42,  1.02it/s, lr: 1.0e-04 loss: 3.396e-01]
latex_v1:  11%|#1        | 338/3000 [07:54<50:37,  1.14s/it, lr: 1.0e-04 loss: 3.396e-01]
latex_v1:  11%|#1        | 338/3000 [07:54<50:37,  1.14s/it, lr: 1.0e-04 loss: 3.396e-01]
latex_v1:  11%|#1        | 338/3000 [07:55<50:37,  1.14s/it, lr: 1.0e-04 loss: 4.036e-02]
latex_v1:  11%|#1        | 338/3000 [07:55<50:37,  1.14s/it, lr: 1.0e-04 loss: 4.036e-02]
latex_v1:  11%|#1        | 339/3000 [07:55<45:31,  1.03s/it, lr: 1.0e-04 loss: 4.036e-02]
latex_v1:  11%|#1        | 339/3000 [07:55<45:31,  1.03s/it, lr: 1.0e-04 loss: 4.036e-02]
latex_v1:  11%|#1        | 339/3000 [07:57<45:31,  1.03s/it, lr: 1.0e-04 loss: 4.770e-01]
latex_v1:  11%|#1        | 339/3000 [07:57<45:31,  1.03s/it, lr: 1.0e-04 loss: 4.770e-01]
latex_v1:  11%|#1        | 340/3000 [07:58<45:30,  1.03s/it, lr: 1.0e-04 loss: 1.459e-01]
latex_v1:  11%|#1        | 340/3000 [07:58<45:30,  1.03s/it, lr: 1.0e-04 loss: 1.459e-01]
latex_v1:  11%|#1        | 341/3000 [07:58<34:36,  1.28it/s, lr: 1.0e-04 loss: 1.459e-01]
latex_v1:  11%|#1        | 341/3000 [07:58<34:36,  1.28it/s, lr: 1.0e-04 loss: 1.459e-01]
latex_v1:  11%|#1        | 341/3000 [07:59<34:36,  1.28it/s, lr: 1.0e-04 loss: 7.843e-01]
latex_v1:  11%|#1        | 341/3000 [07:59<34:36,  1.28it/s, lr: 1.0e-04 loss: 7.843e-01]
latex_v1:  11%|#1        | 342/3000 [07:59<40:31,  1.09it/s, lr: 1.0e-04 loss: 7.843e-01]
latex_v1:  11%|#1        | 342/3000 [07:59<40:31,  1.09it/s, lr: 1.0e-04 loss: 7.843e-01]
latex_v1:  11%|#1        | 342/3000 [08:01<40:31,  1.09it/s, lr: 1.0e-04 loss: 5.083e-01]
latex_v1:  11%|#1        | 342/3000 [08:01<40:31,  1.09it/s, lr: 1.0e-04 loss: 5.083e-01]
latex_v1:  11%|#1        | 343/3000 [08:01<46:18,  1.05s/it, lr: 1.0e-04 loss: 5.083e-01]
latex_v1:  11%|#1        | 343/3000 [08:01<46:18,  1.05s/it, lr: 1.0e-04 loss: 5.083e-01]
latex_v1:  11%|#1        | 343/3000 [08:02<46:18,  1.05s/it, lr: 1.0e-04 loss: 2.245e-01]
latex_v1:  11%|#1        | 343/3000 [08:02<46:18,  1.05s/it, lr: 1.0e-04 loss: 2.245e-01]
latex_v1:  11%|#1        | 344/3000 [08:02<50:34,  1.14s/it, lr: 1.0e-04 loss: 2.245e-01]
latex_v1:  11%|#1        | 344/3000 [08:02<50:34,  1.14s/it, lr: 1.0e-04 loss: 2.245e-01]
latex_v1:  11%|#1        | 344/3000 [08:03<50:34,  1.14s/it, lr: 1.0e-04 loss: 3.545e-01]
latex_v1:  11%|#1        | 344/3000 [08:03<50:34,  1.14s/it, lr: 1.0e-04 loss: 3.545e-01]
latex_v1:  12%|#1        | 345/3000 [08:03<45:39,  1.03s/it, lr: 1.0e-04 loss: 3.545e-01]
latex_v1:  12%|#1        | 345/3000 [08:03<45:39,  1.03s/it, lr: 1.0e-04 loss: 3.545e-01]
latex_v1:  12%|#1        | 345/3000 [08:05<45:39,  1.03s/it, lr: 1.0e-04 loss: 1.659e-01]
latex_v1:  12%|#1        | 345/3000 [08:05<45:39,  1.03s/it, lr: 1.0e-04 loss: 1.659e-01]
latex_v1:  12%|#1        | 346/3000 [08:05<54:26,  1.23s/it, lr: 1.0e-04 loss: 1.659e-01]
latex_v1:  12%|#1        | 346/3000 [08:05<54:26,  1.23s/it, lr: 1.0e-04 loss: 1.659e-01]
latex_v1:  12%|#1        | 346/3000 [08:07<54:26,  1.23s/it, lr: 1.0e-04 loss: 9.391e-02]
latex_v1:  12%|#1        | 346/3000 [08:07<54:26,  1.23s/it, lr: 1.0e-04 loss: 9.391e-02]
latex_v1:  12%|#1        | 347/3000 [08:07<1:15:15,  1.70s/it, lr: 1.0e-04 loss: 9.391e-02]
latex_v1:  12%|#1        | 347/3000 [08:07<1:15:15,  1.70s/it, lr: 1.0e-04 loss: 9.391e-02]
latex_v1:  12%|#1        | 347/3000 [08:09<1:15:15,  1.70s/it, lr: 1.0e-04 loss: 4.257e-01]
latex_v1:  12%|#1        | 347/3000 [08:09<1:15:15,  1.70s/it, lr: 1.0e-04 loss: 4.257e-01]
latex_v1:  12%|#1        | 348/3000 [08:09<1:13:07,  1.65s/it, lr: 1.0e-04 loss: 4.257e-01]
latex_v1:  12%|#1        | 348/3000 [08:09<1:13:07,  1.65s/it, lr: 1.0e-04 loss: 4.257e-01]
latex_v1:  12%|#1        | 348/3000 [08:11<1:13:07,  1.65s/it, lr: 1.0e-04 loss: 1.968e-01]
latex_v1:  12%|#1        | 348/3000 [08:11<1:13:07,  1.65s/it, lr: 1.0e-04 loss: 1.968e-01]
latex_v1:  12%|#1        | 349/3000 [08:11<1:17:14,  1.75s/it, lr: 1.0e-04 loss: 1.968e-01]
latex_v1:  12%|#1        | 349/3000 [08:11<1:17:14,  1.75s/it, lr: 1.0e-04 loss: 1.968e-01]
latex_v1:  12%|#1        | 349/3000 [08:12<1:17:14,  1.75s/it, lr: 1.0e-04 loss: 5.994e-01]
latex_v1:  12%|#1        | 349/3000 [08:12<1:17:14,  1.75s/it, lr: 1.0e-04 loss: 5.994e-01]
latex_v1:  12%|#1        | 350/3000 [08:13<1:17:12,  1.75s/it, lr: 1.0e-04 loss: 1.469e-01]
latex_v1:  12%|#1        | 350/3000 [08:13<1:17:12,  1.75s/it, lr: 1.0e-04 loss: 1.469e-01]
latex_v1:  12%|#1        | 351/3000 [08:13<55:37,  1.26s/it, lr: 1.0e-04 loss: 1.469e-01]  
latex_v1:  12%|#1        | 351/3000 [08:13<55:37,  1.26s/it, lr: 1.0e-04 loss: 1.469e-01]  
latex_v1:  12%|#1        | 351/3000 [08:14<55:37,  1.26s/it, lr: 1.0e-04 loss: 6.577e-01]
latex_v1:  12%|#1        | 351/3000 [08:14<55:37,  1.26s/it, lr: 1.0e-04 loss: 6.577e-01]
latex_v1:  12%|#1        | 352/3000 [08:14<50:14,  1.14s/it, lr: 1.0e-04 loss: 6.577e-01]
latex_v1:  12%|#1        | 352/3000 [08:14<50:14,  1.14s/it, lr: 1.0e-04 loss: 6.577e-01]
latex_v1:  12%|#1        | 352/3000 [08:15<50:14,  1.14s/it, lr: 1.0e-04 loss: 4.161e-02]
latex_v1:  12%|#1        | 352/3000 [08:15<50:14,  1.14s/it, lr: 1.0e-04 loss: 4.161e-02]
latex_v1:  12%|#1        | 353/3000 [08:15<45:36,  1.03s/it, lr: 1.0e-04 loss: 4.161e-02]
latex_v1:  12%|#1        | 353/3000 [08:15<45:36,  1.03s/it, lr: 1.0e-04 loss: 4.161e-02]
latex_v1:  12%|#1        | 353/3000 [08:16<45:36,  1.03s/it, lr: 1.0e-04 loss: 5.687e-01]
latex_v1:  12%|#1        | 353/3000 [08:16<45:36,  1.03s/it, lr: 1.0e-04 loss: 5.687e-01]
latex_v1:  12%|#1        | 354/3000 [08:16<47:55,  1.09s/it, lr: 1.0e-04 loss: 5.687e-01]
latex_v1:  12%|#1        | 354/3000 [08:16<47:55,  1.09s/it, lr: 1.0e-04 loss: 5.687e-01]
latex_v1:  12%|#1        | 354/3000 [08:17<47:55,  1.09s/it, lr: 1.0e-04 loss: 4.230e-01]
latex_v1:  12%|#1        | 354/3000 [08:17<47:55,  1.09s/it, lr: 1.0e-04 loss: 4.230e-01]
latex_v1:  12%|#1        | 355/3000 [08:17<52:21,  1.19s/it, lr: 1.0e-04 loss: 4.230e-01]
latex_v1:  12%|#1        | 355/3000 [08:17<52:21,  1.19s/it, lr: 1.0e-04 loss: 4.230e-01]
latex_v1:  12%|#1        | 355/3000 [08:18<52:21,  1.19s/it, lr: 1.0e-04 loss: 3.827e-01]
latex_v1:  12%|#1        | 355/3000 [08:18<52:21,  1.19s/it, lr: 1.0e-04 loss: 3.827e-01]
latex_v1:  12%|#1        | 356/3000 [08:18<52:03,  1.18s/it, lr: 1.0e-04 loss: 3.827e-01]
latex_v1:  12%|#1        | 356/3000 [08:18<52:03,  1.18s/it, lr: 1.0e-04 loss: 3.827e-01]
latex_v1:  12%|#1        | 356/3000 [08:20<52:03,  1.18s/it, lr: 1.0e-04 loss: 7.107e-01]
latex_v1:  12%|#1        | 356/3000 [08:20<52:03,  1.18s/it, lr: 1.0e-04 loss: 7.107e-01]
latex_v1:  12%|#1        | 357/3000 [08:20<55:12,  1.25s/it, lr: 1.0e-04 loss: 7.107e-01]
latex_v1:  12%|#1        | 357/3000 [08:20<55:12,  1.25s/it, lr: 1.0e-04 loss: 7.107e-01]
latex_v1:  12%|#1        | 357/3000 [08:21<55:12,  1.25s/it, lr: 1.0e-04 loss: 2.341e-01]
latex_v1:  12%|#1        | 357/3000 [08:21<55:12,  1.25s/it, lr: 1.0e-04 loss: 2.341e-01]
latex_v1:  12%|#1        | 358/3000 [08:21<56:12,  1.28s/it, lr: 1.0e-04 loss: 2.341e-01]
latex_v1:  12%|#1        | 358/3000 [08:21<56:12,  1.28s/it, lr: 1.0e-04 loss: 2.341e-01]
latex_v1:  12%|#1        | 358/3000 [08:24<56:12,  1.28s/it, lr: 1.0e-04 loss: 4.441e-01]
latex_v1:  12%|#1        | 358/3000 [08:24<56:12,  1.28s/it, lr: 1.0e-04 loss: 4.441e-01]
latex_v1:  12%|#1        | 359/3000 [08:24<1:16:42,  1.74s/it, lr: 1.0e-04 loss: 4.441e-01]
latex_v1:  12%|#1        | 359/3000 [08:24<1:16:42,  1.74s/it, lr: 1.0e-04 loss: 4.441e-01]
latex_v1:  12%|#1        | 359/3000 [08:26<1:16:42,  1.74s/it, lr: 1.0e-04 loss: 1.995e-02]
latex_v1:  12%|#1        | 359/3000 [08:26<1:16:42,  1.74s/it, lr: 1.0e-04 loss: 1.995e-02]
latex_v1:  12%|#2        | 360/3000 [08:26<1:16:40,  1.74s/it, lr: 1.0e-04 loss: 3.240e-01]
latex_v1:  12%|#2        | 360/3000 [08:26<1:16:40,  1.74s/it, lr: 1.0e-04 loss: 3.240e-01]
latex_v1:  12%|#2        | 361/3000 [08:26<49:06,  1.12s/it, lr: 1.0e-04 loss: 3.240e-01]  
latex_v1:  12%|#2        | 361/3000 [08:26<49:06,  1.12s/it, lr: 1.0e-04 loss: 3.240e-01]  
latex_v1:  12%|#2        | 361/3000 [08:29<49:06,  1.12s/it, lr: 1.0e-04 loss: 1.043e-01]
latex_v1:  12%|#2        | 361/3000 [08:29<49:06,  1.12s/it, lr: 1.0e-04 loss: 1.043e-01]
latex_v1:  12%|#2        | 362/3000 [08:29<1:08:09,  1.55s/it, lr: 1.0e-04 loss: 1.043e-01]
latex_v1:  12%|#2        | 362/3000 [08:29<1:08:09,  1.55s/it, lr: 1.0e-04 loss: 1.043e-01]
latex_v1:  12%|#2        | 362/3000 [08:30<1:08:09,  1.55s/it, lr: 1.0e-04 loss: 1.986e-01]
latex_v1:  12%|#2        | 362/3000 [08:30<1:08:09,  1.55s/it, lr: 1.0e-04 loss: 1.986e-01]
latex_v1:  12%|#2        | 363/3000 [08:30<59:00,  1.34s/it, lr: 1.0e-04 loss: 1.986e-01]  
latex_v1:  12%|#2        | 363/3000 [08:30<59:00,  1.34s/it, lr: 1.0e-04 loss: 1.986e-01]  
latex_v1:  12%|#2        | 363/3000 [08:31<59:00,  1.34s/it, lr: 1.0e-04 loss: 5.230e-01]
latex_v1:  12%|#2        | 363/3000 [08:31<59:00,  1.34s/it, lr: 1.0e-04 loss: 5.230e-01]
latex_v1:  12%|#2        | 364/3000 [08:31<52:00,  1.18s/it, lr: 1.0e-04 loss: 5.230e-01]
latex_v1:  12%|#2        | 364/3000 [08:31<52:00,  1.18s/it, lr: 1.0e-04 loss: 5.230e-01]
latex_v1:  12%|#2        | 364/3000 [08:32<52:00,  1.18s/it, lr: 1.0e-04 loss: 8.166e-01]
latex_v1:  12%|#2        | 364/3000 [08:32<52:00,  1.18s/it, lr: 1.0e-04 loss: 8.166e-01]
latex_v1:  12%|#2        | 365/3000 [08:32<49:13,  1.12s/it, lr: 1.0e-04 loss: 8.166e-01]
latex_v1:  12%|#2        | 365/3000 [08:32<49:13,  1.12s/it, lr: 1.0e-04 loss: 8.166e-01]
latex_v1:  12%|#2        | 365/3000 [08:33<49:13,  1.12s/it, lr: 1.0e-04 loss: 5.313e-01]
latex_v1:  12%|#2        | 365/3000 [08:33<49:13,  1.12s/it, lr: 1.0e-04 loss: 5.313e-01]
latex_v1:  12%|#2        | 366/3000 [08:33<44:37,  1.02s/it, lr: 1.0e-04 loss: 5.313e-01]
latex_v1:  12%|#2        | 366/3000 [08:33<44:37,  1.02s/it, lr: 1.0e-04 loss: 5.313e-01]
latex_v1:  12%|#2        | 366/3000 [08:34<44:37,  1.02s/it, lr: 1.0e-04 loss: 1.333e-01]
latex_v1:  12%|#2        | 366/3000 [08:34<44:37,  1.02s/it, lr: 1.0e-04 loss: 1.333e-01]
latex_v1:  12%|#2        | 367/3000 [08:34<52:06,  1.19s/it, lr: 1.0e-04 loss: 1.333e-01]
latex_v1:  12%|#2        | 367/3000 [08:34<52:06,  1.19s/it, lr: 1.0e-04 loss: 1.333e-01]
latex_v1:  12%|#2        | 367/3000 [08:35<52:06,  1.19s/it, lr: 1.0e-04 loss: 5.688e-01]
latex_v1:  12%|#2        | 367/3000 [08:35<52:06,  1.19s/it, lr: 1.0e-04 loss: 5.688e-01]
latex_v1:  12%|#2        | 368/3000 [08:35<46:27,  1.06s/it, lr: 1.0e-04 loss: 5.688e-01]
latex_v1:  12%|#2        | 368/3000 [08:35<46:27,  1.06s/it, lr: 1.0e-04 loss: 5.688e-01]
latex_v1:  12%|#2        | 368/3000 [08:37<46:27,  1.06s/it, lr: 1.0e-04 loss: 3.421e-01]
latex_v1:  12%|#2        | 368/3000 [08:37<46:27,  1.06s/it, lr: 1.0e-04 loss: 3.421e-01]
latex_v1:  12%|#2        | 369/3000 [08:37<57:09,  1.30s/it, lr: 1.0e-04 loss: 3.421e-01]
latex_v1:  12%|#2        | 369/3000 [08:37<57:09,  1.30s/it, lr: 1.0e-04 loss: 3.421e-01]
latex_v1:  12%|#2        | 369/3000 [08:39<57:09,  1.30s/it, lr: 1.0e-04 loss: 1.347e-01]
latex_v1:  12%|#2        | 369/3000 [08:39<57:09,  1.30s/it, lr: 1.0e-04 loss: 1.347e-01]
latex_v1:  12%|#2        | 370/3000 [08:39<57:08,  1.30s/it, lr: 1.0e-04 loss: 4.536e-01]
latex_v1:  12%|#2        | 370/3000 [08:39<57:08,  1.30s/it, lr: 1.0e-04 loss: 4.536e-01]
latex_v1:  12%|#2        | 371/3000 [08:39<38:35,  1.14it/s, lr: 1.0e-04 loss: 4.536e-01]
latex_v1:  12%|#2        | 371/3000 [08:39<38:35,  1.14it/s, lr: 1.0e-04 loss: 4.536e-01]
latex_v1:  12%|#2        | 371/3000 [08:41<38:35,  1.14it/s, lr: 1.0e-04 loss: 6.295e-01]
latex_v1:  12%|#2        | 371/3000 [08:41<38:35,  1.14it/s, lr: 1.0e-04 loss: 6.295e-01]
latex_v1:  12%|#2        | 372/3000 [08:41<46:03,  1.05s/it, lr: 1.0e-04 loss: 6.295e-01]
latex_v1:  12%|#2        | 372/3000 [08:41<46:03,  1.05s/it, lr: 1.0e-04 loss: 6.295e-01]
latex_v1:  12%|#2        | 372/3000 [08:43<46:03,  1.05s/it, lr: 1.0e-04 loss: 2.523e-01]
latex_v1:  12%|#2        | 372/3000 [08:43<46:03,  1.05s/it, lr: 1.0e-04 loss: 2.523e-01]
latex_v1:  12%|#2        | 373/3000 [08:43<47:32,  1.09s/it, lr: 1.0e-04 loss: 2.523e-01]
latex_v1:  12%|#2        | 373/3000 [08:43<47:32,  1.09s/it, lr: 1.0e-04 loss: 2.523e-01]
latex_v1:  12%|#2        | 373/3000 [08:43<47:32,  1.09s/it, lr: 1.0e-04 loss: 4.076e-01]
latex_v1:  12%|#2        | 373/3000 [08:43<47:32,  1.09s/it, lr: 1.0e-04 loss: 4.076e-01]
latex_v1:  12%|#2        | 374/3000 [08:43<43:29,  1.01it/s, lr: 1.0e-04 loss: 4.076e-01]
latex_v1:  12%|#2        | 374/3000 [08:43<43:29,  1.01it/s, lr: 1.0e-04 loss: 4.076e-01]
latex_v1:  12%|#2        | 374/3000 [08:44<43:29,  1.01it/s, lr: 1.0e-04 loss: 5.814e-01]
latex_v1:  12%|#2        | 374/3000 [08:44<43:29,  1.01it/s, lr: 1.0e-04 loss: 5.814e-01]
latex_v1:  12%|#2        | 375/3000 [08:44<40:40,  1.08it/s, lr: 1.0e-04 loss: 5.814e-01]
latex_v1:  12%|#2        | 375/3000 [08:44<40:40,  1.08it/s, lr: 1.0e-04 loss: 5.814e-01]
latex_v1:  12%|#2        | 375/3000 [08:45<40:40,  1.08it/s, lr: 1.0e-04 loss: 1.367e-01]
latex_v1:  12%|#2        | 375/3000 [08:45<40:40,  1.08it/s, lr: 1.0e-04 loss: 1.367e-01]
latex_v1:  13%|#2        | 376/3000 [08:45<38:35,  1.13it/s, lr: 1.0e-04 loss: 1.367e-01]
latex_v1:  13%|#2        | 376/3000 [08:45<38:35,  1.13it/s, lr: 1.0e-04 loss: 1.367e-01]
latex_v1:  13%|#2        | 376/3000 [08:47<38:35,  1.13it/s, lr: 1.0e-04 loss: 1.473e-01]
latex_v1:  13%|#2        | 376/3000 [08:47<38:35,  1.13it/s, lr: 1.0e-04 loss: 1.473e-01]
latex_v1:  13%|#2        | 377/3000 [08:47<1:00:59,  1.40s/it, lr: 1.0e-04 loss: 1.473e-01]
latex_v1:  13%|#2        | 377/3000 [08:47<1:00:59,  1.40s/it, lr: 1.0e-04 loss: 1.473e-01]
latex_v1:  13%|#2        | 377/3000 [08:48<1:00:59,  1.40s/it, lr: 1.0e-04 loss: 5.603e-01]
latex_v1:  13%|#2        | 377/3000 [08:48<1:00:59,  1.40s/it, lr: 1.0e-04 loss: 5.603e-01]
latex_v1:  13%|#2        | 378/3000 [08:48<52:39,  1.21s/it, lr: 1.0e-04 loss: 5.603e-01]  
latex_v1:  13%|#2        | 378/3000 [08:48<52:39,  1.21s/it, lr: 1.0e-04 loss: 5.603e-01]  
latex_v1:  13%|#2        | 378/3000 [08:50<52:39,  1.21s/it, lr: 1.0e-04 loss: 2.231e-01]
latex_v1:  13%|#2        | 378/3000 [08:50<52:39,  1.21s/it, lr: 1.0e-04 loss: 2.231e-01]
latex_v1:  13%|#2        | 379/3000 [08:50<1:05:20,  1.50s/it, lr: 1.0e-04 loss: 2.231e-01]
latex_v1:  13%|#2        | 379/3000 [08:50<1:05:20,  1.50s/it, lr: 1.0e-04 loss: 2.231e-01]
latex_v1:  13%|#2        | 379/3000 [08:51<1:05:20,  1.50s/it, lr: 1.0e-04 loss: 3.800e-01]
latex_v1:  13%|#2        | 379/3000 [08:51<1:05:20,  1.50s/it, lr: 1.0e-04 loss: 3.800e-01]
latex_v1:  13%|#2        | 380/3000 [08:53<1:05:18,  1.50s/it, lr: 1.0e-04 loss: 1.224e-01]
latex_v1:  13%|#2        | 380/3000 [08:53<1:05:18,  1.50s/it, lr: 1.0e-04 loss: 1.224e-01]
latex_v1:  13%|#2        | 381/3000 [08:53<52:16,  1.20s/it, lr: 1.0e-04 loss: 1.224e-01]  
latex_v1:  13%|#2        | 381/3000 [08:53<52:16,  1.20s/it, lr: 1.0e-04 loss: 1.224e-01]  
latex_v1:  13%|#2        | 381/3000 [08:54<52:16,  1.20s/it, lr: 1.0e-04 loss: 6.634e-01]
latex_v1:  13%|#2        | 381/3000 [08:54<52:16,  1.20s/it, lr: 1.0e-04 loss: 6.634e-01]
latex_v1:  13%|#2        | 382/3000 [08:54<47:43,  1.09s/it, lr: 1.0e-04 loss: 6.634e-01]
latex_v1:  13%|#2        | 382/3000 [08:54<47:43,  1.09s/it, lr: 1.0e-04 loss: 6.634e-01]
latex_v1:  13%|#2        | 382/3000 [08:55<47:43,  1.09s/it, lr: 1.0e-04 loss: 2.691e-01]
latex_v1:  13%|#2        | 382/3000 [08:55<47:43,  1.09s/it, lr: 1.0e-04 loss: 2.691e-01]
latex_v1:  13%|#2        | 383/3000 [08:55<55:06,  1.26s/it, lr: 1.0e-04 loss: 2.691e-01]
latex_v1:  13%|#2        | 383/3000 [08:55<55:06,  1.26s/it, lr: 1.0e-04 loss: 2.691e-01]
latex_v1:  13%|#2        | 383/3000 [08:57<55:06,  1.26s/it, lr: 1.0e-04 loss: 5.184e-01]
latex_v1:  13%|#2        | 383/3000 [08:57<55:06,  1.26s/it, lr: 1.0e-04 loss: 5.184e-01]
latex_v1:  13%|#2        | 384/3000 [08:57<56:53,  1.30s/it, lr: 1.0e-04 loss: 5.184e-01]
latex_v1:  13%|#2        | 384/3000 [08:57<56:53,  1.30s/it, lr: 1.0e-04 loss: 5.184e-01]
latex_v1:  13%|#2        | 384/3000 [08:58<56:53,  1.30s/it, lr: 1.0e-04 loss: 3.228e-01]
latex_v1:  13%|#2        | 384/3000 [08:58<56:53,  1.30s/it, lr: 1.0e-04 loss: 3.228e-01]
latex_v1:  13%|#2        | 385/3000 [08:58<58:40,  1.35s/it, lr: 1.0e-04 loss: 3.228e-01]
latex_v1:  13%|#2        | 385/3000 [08:58<58:40,  1.35s/it, lr: 1.0e-04 loss: 3.228e-01]
latex_v1:  13%|#2        | 385/3000 [08:59<58:40,  1.35s/it, lr: 1.0e-04 loss: 5.603e-01]
latex_v1:  13%|#2        | 385/3000 [08:59<58:40,  1.35s/it, lr: 1.0e-04 loss: 5.603e-01]
latex_v1:  13%|#2        | 386/3000 [08:59<51:15,  1.18s/it, lr: 1.0e-04 loss: 5.603e-01]
latex_v1:  13%|#2        | 386/3000 [08:59<51:15,  1.18s/it, lr: 1.0e-04 loss: 5.603e-01]
latex_v1:  13%|#2        | 386/3000 [09:00<51:15,  1.18s/it, lr: 1.0e-04 loss: 1.400e-01]
latex_v1:  13%|#2        | 386/3000 [09:00<51:15,  1.18s/it, lr: 1.0e-04 loss: 1.400e-01]
latex_v1:  13%|#2        | 387/3000 [09:00<53:10,  1.22s/it, lr: 1.0e-04 loss: 1.400e-01]
latex_v1:  13%|#2        | 387/3000 [09:00<53:10,  1.22s/it, lr: 1.0e-04 loss: 1.400e-01]
latex_v1:  13%|#2        | 387/3000 [09:02<53:10,  1.22s/it, lr: 1.0e-04 loss: 1.558e-01]
latex_v1:  13%|#2        | 387/3000 [09:02<53:10,  1.22s/it, lr: 1.0e-04 loss: 1.558e-01]
latex_v1:  13%|#2        | 388/3000 [09:02<56:09,  1.29s/it, lr: 1.0e-04 loss: 1.558e-01]
latex_v1:  13%|#2        | 388/3000 [09:02<56:09,  1.29s/it, lr: 1.0e-04 loss: 1.558e-01]
latex_v1:  13%|#2        | 388/3000 [09:03<56:09,  1.29s/it, lr: 1.0e-04 loss: 4.902e-01]
latex_v1:  13%|#2        | 388/3000 [09:03<56:09,  1.29s/it, lr: 1.0e-04 loss: 4.902e-01]
latex_v1:  13%|#2        | 389/3000 [09:03<49:05,  1.13s/it, lr: 1.0e-04 loss: 4.902e-01]
latex_v1:  13%|#2        | 389/3000 [09:03<49:05,  1.13s/it, lr: 1.0e-04 loss: 4.902e-01]
latex_v1:  13%|#2        | 389/3000 [09:05<49:05,  1.13s/it, lr: 1.0e-04 loss: 3.238e-01]
latex_v1:  13%|#2        | 389/3000 [09:05<49:05,  1.13s/it, lr: 1.0e-04 loss: 3.238e-01]
latex_v1:  13%|#3        | 390/3000 [09:07<49:04,  1.13s/it, lr: 1.0e-04 loss: 5.558e-01]
latex_v1:  13%|#3        | 390/3000 [09:07<49:04,  1.13s/it, lr: 1.0e-04 loss: 5.558e-01]
latex_v1:  13%|#3        | 391/3000 [09:07<40:51,  1.06it/s, lr: 1.0e-04 loss: 5.558e-01]
latex_v1:  13%|#3        | 391/3000 [09:07<40:51,  1.06it/s, lr: 1.0e-04 loss: 5.558e-01]
latex_v1:  13%|#3        | 391/3000 [09:10<40:51,  1.06it/s, lr: 1.0e-04 loss: 5.802e-01]
latex_v1:  13%|#3        | 391/3000 [09:10<40:51,  1.06it/s, lr: 1.0e-04 loss: 5.802e-01]
latex_v1:  13%|#3        | 392/3000 [09:10<1:01:31,  1.42s/it, lr: 1.0e-04 loss: 5.802e-01]
latex_v1:  13%|#3        | 392/3000 [09:10<1:01:31,  1.42s/it, lr: 1.0e-04 loss: 5.802e-01]
latex_v1:  13%|#3        | 392/3000 [09:10<1:01:31,  1.42s/it, lr: 1.0e-04 loss: 6.880e-01]
latex_v1:  13%|#3        | 392/3000 [09:10<1:01:31,  1.42s/it, lr: 1.0e-04 loss: 6.880e-01]
latex_v1:  13%|#3        | 393/3000 [09:10<53:50,  1.24s/it, lr: 1.0e-04 loss: 6.880e-01]  
latex_v1:  13%|#3        | 393/3000 [09:10<53:50,  1.24s/it, lr: 1.0e-04 loss: 6.880e-01]  
latex_v1:  13%|#3        | 393/3000 [09:12<53:50,  1.24s/it, lr: 1.0e-04 loss: 1.135e-01]
latex_v1:  13%|#3        | 393/3000 [09:12<53:50,  1.24s/it, lr: 1.0e-04 loss: 1.135e-01]
latex_v1:  13%|#3        | 394/3000 [09:12<57:14,  1.32s/it, lr: 1.0e-04 loss: 1.135e-01]
latex_v1:  13%|#3        | 394/3000 [09:12<57:14,  1.32s/it, lr: 1.0e-04 loss: 1.135e-01]
latex_v1:  13%|#3        | 394/3000 [09:14<57:14,  1.32s/it, lr: 1.0e-04 loss: 6.553e-01]
latex_v1:  13%|#3        | 394/3000 [09:14<57:14,  1.32s/it, lr: 1.0e-04 loss: 6.553e-01]
latex_v1:  13%|#3        | 395/3000 [09:14<1:00:44,  1.40s/it, lr: 1.0e-04 loss: 6.553e-01]
latex_v1:  13%|#3        | 395/3000 [09:14<1:00:44,  1.40s/it, lr: 1.0e-04 loss: 6.553e-01]
latex_v1:  13%|#3        | 395/3000 [09:15<1:00:44,  1.40s/it, lr: 1.0e-04 loss: 4.060e-01]
latex_v1:  13%|#3        | 395/3000 [09:15<1:00:44,  1.40s/it, lr: 1.0e-04 loss: 4.060e-01]
latex_v1:  13%|#3        | 396/3000 [09:15<59:57,  1.38s/it, lr: 1.0e-04 loss: 4.060e-01]  
latex_v1:  13%|#3        | 396/3000 [09:15<59:57,  1.38s/it, lr: 1.0e-04 loss: 4.060e-01]  
latex_v1:  13%|#3        | 396/3000 [09:16<59:57,  1.38s/it, lr: 1.0e-04 loss: 4.996e-01]
latex_v1:  13%|#3        | 396/3000 [09:16<59:57,  1.38s/it, lr: 1.0e-04 loss: 4.996e-01]
latex_v1:  13%|#3        | 397/3000 [09:16<1:02:05,  1.43s/it, lr: 1.0e-04 loss: 4.996e-01]
latex_v1:  13%|#3        | 397/3000 [09:16<1:02:05,  1.43s/it, lr: 1.0e-04 loss: 4.996e-01]
latex_v1:  13%|#3        | 397/3000 [09:18<1:02:05,  1.43s/it, lr: 1.0e-04 loss: 4.062e-01]
latex_v1:  13%|#3        | 397/3000 [09:18<1:02:05,  1.43s/it, lr: 1.0e-04 loss: 4.062e-01]
latex_v1:  13%|#3        | 398/3000 [09:18<1:03:28,  1.46s/it, lr: 1.0e-04 loss: 4.062e-01]
latex_v1:  13%|#3        | 398/3000 [09:18<1:03:28,  1.46s/it, lr: 1.0e-04 loss: 4.062e-01]
latex_v1:  13%|#3        | 398/3000 [09:19<1:03:28,  1.46s/it, lr: 1.0e-04 loss: 4.034e-01]
latex_v1:  13%|#3        | 398/3000 [09:19<1:03:28,  1.46s/it, lr: 1.0e-04 loss: 4.034e-01]
latex_v1:  13%|#3        | 399/3000 [09:19<1:04:15,  1.48s/it, lr: 1.0e-04 loss: 4.034e-01]
latex_v1:  13%|#3        | 399/3000 [09:19<1:04:15,  1.48s/it, lr: 1.0e-04 loss: 4.034e-01]
latex_v1:  13%|#3        | 399/3000 [09:21<1:04:15,  1.48s/it, lr: 1.0e-04 loss: 5.727e-01]
latex_v1:  13%|#3        | 399/3000 [09:21<1:04:15,  1.48s/it, lr: 1.0e-04 loss: 5.727e-01]
latex_v1:  13%|#3        | 400/3000 [09:22<1:04:13,  1.48s/it, lr: 1.0e-04 loss: 7.190e-01]
latex_v1:  13%|#3        | 400/3000 [09:22<1:04:13,  1.48s/it, lr: 1.0e-04 loss: 7.190e-01]
latex_v1:  13%|#3        | 401/3000 [09:22<46:32,  1.07s/it, lr: 1.0e-04 loss: 7.190e-01]  
latex_v1:  13%|#3        | 401/3000 [09:22<46:32,  1.07s/it, lr: 1.0e-04 loss: 7.190e-01]  
latex_v1:  13%|#3        | 401/3000 [09:24<46:32,  1.07s/it, lr: 1.0e-04 loss: 6.454e-01]
latex_v1:  13%|#3        | 401/3000 [09:24<46:32,  1.07s/it, lr: 1.0e-04 loss: 6.454e-01]
latex_v1:  13%|#3        | 402/3000 [09:24<55:16,  1.28s/it, lr: 1.0e-04 loss: 6.454e-01]
latex_v1:  13%|#3        | 402/3000 [09:24<55:16,  1.28s/it, lr: 1.0e-04 loss: 6.454e-01]
latex_v1:  13%|#3        | 402/3000 [09:25<55:16,  1.28s/it, lr: 1.0e-04 loss: 5.529e-01]
latex_v1:  13%|#3        | 402/3000 [09:25<55:16,  1.28s/it, lr: 1.0e-04 loss: 5.529e-01]
latex_v1:  13%|#3        | 403/3000 [09:25<49:30,  1.14s/it, lr: 1.0e-04 loss: 5.529e-01]
latex_v1:  13%|#3        | 403/3000 [09:25<49:30,  1.14s/it, lr: 1.0e-04 loss: 5.529e-01]
latex_v1:  13%|#3        | 403/3000 [09:28<49:30,  1.14s/it, lr: 1.0e-04 loss: 6.331e-01]
latex_v1:  13%|#3        | 403/3000 [09:28<49:30,  1.14s/it, lr: 1.0e-04 loss: 6.331e-01]
latex_v1:  13%|#3        | 404/3000 [09:28<1:09:44,  1.61s/it, lr: 1.0e-04 loss: 6.331e-01]
latex_v1:  13%|#3        | 404/3000 [09:28<1:09:44,  1.61s/it, lr: 1.0e-04 loss: 6.331e-01]
latex_v1:  13%|#3        | 404/3000 [09:29<1:09:44,  1.61s/it, lr: 1.0e-04 loss: 5.896e-01]
latex_v1:  13%|#3        | 404/3000 [09:29<1:09:44,  1.61s/it, lr: 1.0e-04 loss: 5.896e-01]
latex_v1:  14%|#3        | 405/3000 [09:29<1:03:02,  1.46s/it, lr: 1.0e-04 loss: 5.896e-01]
latex_v1:  14%|#3        | 405/3000 [09:29<1:03:02,  1.46s/it, lr: 1.0e-04 loss: 5.896e-01]
latex_v1:  14%|#3        | 405/3000 [09:30<1:03:02,  1.46s/it, lr: 1.0e-04 loss: 3.833e-01]
latex_v1:  14%|#3        | 405/3000 [09:30<1:03:02,  1.46s/it, lr: 1.0e-04 loss: 3.833e-01]
latex_v1:  14%|#3        | 406/3000 [09:30<1:04:40,  1.50s/it, lr: 1.0e-04 loss: 3.833e-01]
latex_v1:  14%|#3        | 406/3000 [09:30<1:04:40,  1.50s/it, lr: 1.0e-04 loss: 3.833e-01]
latex_v1:  14%|#3        | 406/3000 [09:32<1:04:40,  1.50s/it, lr: 1.0e-04 loss: 5.718e-01]
latex_v1:  14%|#3        | 406/3000 [09:32<1:04:40,  1.50s/it, lr: 1.0e-04 loss: 5.718e-01]
latex_v1:  14%|#3        | 407/3000 [09:32<1:09:29,  1.61s/it, lr: 1.0e-04 loss: 5.718e-01]
latex_v1:  14%|#3        | 407/3000 [09:32<1:09:29,  1.61s/it, lr: 1.0e-04 loss: 5.718e-01]
latex_v1:  14%|#3        | 407/3000 [09:34<1:09:29,  1.61s/it, lr: 1.0e-04 loss: 3.193e-01]
latex_v1:  14%|#3        | 407/3000 [09:34<1:09:29,  1.61s/it, lr: 1.0e-04 loss: 3.193e-01]
latex_v1:  14%|#3        | 408/3000 [09:34<1:07:11,  1.56s/it, lr: 1.0e-04 loss: 3.193e-01]
latex_v1:  14%|#3        | 408/3000 [09:34<1:07:11,  1.56s/it, lr: 1.0e-04 loss: 3.193e-01]
latex_v1:  14%|#3        | 408/3000 [09:36<1:07:11,  1.56s/it, lr: 1.0e-04 loss: 3.796e-01]
latex_v1:  14%|#3        | 408/3000 [09:36<1:07:11,  1.56s/it, lr: 1.0e-04 loss: 3.796e-01]
latex_v1:  14%|#3        | 409/3000 [09:36<1:13:33,  1.70s/it, lr: 1.0e-04 loss: 3.796e-01]
latex_v1:  14%|#3        | 409/3000 [09:36<1:13:33,  1.70s/it, lr: 1.0e-04 loss: 3.796e-01]
latex_v1:  14%|#3        | 409/3000 [09:37<1:13:33,  1.70s/it, lr: 1.0e-04 loss: 1.381e-01]
latex_v1:  14%|#3        | 409/3000 [09:37<1:13:33,  1.70s/it, lr: 1.0e-04 loss: 1.381e-01]
latex_v1:  14%|#3        | 410/3000 [09:38<1:13:31,  1.70s/it, lr: 1.0e-04 loss: 4.891e-01]
latex_v1:  14%|#3        | 410/3000 [09:38<1:13:31,  1.70s/it, lr: 1.0e-04 loss: 4.891e-01]
latex_v1:  14%|#3        | 411/3000 [09:38<47:26,  1.10s/it, lr: 1.0e-04 loss: 4.891e-01]  
latex_v1:  14%|#3        | 411/3000 [09:38<47:26,  1.10s/it, lr: 1.0e-04 loss: 4.891e-01]  
latex_v1:  14%|#3        | 411/3000 [09:39<47:26,  1.10s/it, lr: 1.0e-04 loss: 5.821e-01]
latex_v1:  14%|#3        | 411/3000 [09:39<47:26,  1.10s/it, lr: 1.0e-04 loss: 5.821e-01]
latex_v1:  14%|#3        | 412/3000 [09:40<50:47,  1.18s/it, lr: 1.0e-04 loss: 5.821e-01]
latex_v1:  14%|#3        | 412/3000 [09:40<50:47,  1.18s/it, lr: 1.0e-04 loss: 5.821e-01]
latex_v1:  14%|#3        | 412/3000 [09:40<50:47,  1.18s/it, lr: 1.0e-04 loss: 5.960e-01]
latex_v1:  14%|#3        | 412/3000 [09:40<50:47,  1.18s/it, lr: 1.0e-04 loss: 5.960e-01]
latex_v1:  14%|#3        | 413/3000 [09:40<45:53,  1.06s/it, lr: 1.0e-04 loss: 5.960e-01]
latex_v1:  14%|#3        | 413/3000 [09:40<45:53,  1.06s/it, lr: 1.0e-04 loss: 5.960e-01]
latex_v1:  14%|#3        | 413/3000 [09:42<45:53,  1.06s/it, lr: 1.0e-04 loss: 1.960e-01]
latex_v1:  14%|#3        | 413/3000 [09:42<45:53,  1.06s/it, lr: 1.0e-04 loss: 1.960e-01]
latex_v1:  14%|#3        | 414/3000 [09:42<52:38,  1.22s/it, lr: 1.0e-04 loss: 1.960e-01]
latex_v1:  14%|#3        | 414/3000 [09:42<52:38,  1.22s/it, lr: 1.0e-04 loss: 1.960e-01]
latex_v1:  14%|#3        | 414/3000 [09:43<52:38,  1.22s/it, lr: 1.0e-04 loss: 5.732e-01]
latex_v1:  14%|#3        | 414/3000 [09:43<52:38,  1.22s/it, lr: 1.0e-04 loss: 5.732e-01]
latex_v1:  14%|#3        | 415/3000 [09:43<46:50,  1.09s/it, lr: 1.0e-04 loss: 5.732e-01]
latex_v1:  14%|#3        | 415/3000 [09:43<46:50,  1.09s/it, lr: 1.0e-04 loss: 5.732e-01]
latex_v1:  14%|#3        | 415/3000 [09:43<46:50,  1.09s/it, lr: 1.0e-04 loss: 1.574e-01]
latex_v1:  14%|#3        | 415/3000 [09:43<46:50,  1.09s/it, lr: 1.0e-04 loss: 1.574e-01]
latex_v1:  14%|#3        | 416/3000 [09:43<42:44,  1.01it/s, lr: 1.0e-04 loss: 1.574e-01]
latex_v1:  14%|#3        | 416/3000 [09:43<42:44,  1.01it/s, lr: 1.0e-04 loss: 1.574e-01]
latex_v1:  14%|#3        | 416/3000 [09:46<42:44,  1.01it/s, lr: 1.0e-04 loss: 1.867e-01]
latex_v1:  14%|#3        | 416/3000 [09:46<42:44,  1.01it/s, lr: 1.0e-04 loss: 1.867e-01]
latex_v1:  14%|#3        | 417/3000 [09:46<1:05:36,  1.52s/it, lr: 1.0e-04 loss: 1.867e-01]
latex_v1:  14%|#3        | 417/3000 [09:46<1:05:36,  1.52s/it, lr: 1.0e-04 loss: 1.867e-01]
latex_v1:  14%|#3        | 417/3000 [09:48<1:05:36,  1.52s/it, lr: 1.0e-04 loss: 6.938e-01]
latex_v1:  14%|#3        | 417/3000 [09:48<1:05:36,  1.52s/it, lr: 1.0e-04 loss: 6.938e-01]
latex_v1:  14%|#3        | 418/3000 [09:48<1:03:29,  1.48s/it, lr: 1.0e-04 loss: 6.938e-01]
latex_v1:  14%|#3        | 418/3000 [09:48<1:03:29,  1.48s/it, lr: 1.0e-04 loss: 6.938e-01]
latex_v1:  14%|#3        | 418/3000 [09:48<1:03:29,  1.48s/it, lr: 1.0e-04 loss: 6.833e-01]
latex_v1:  14%|#3        | 418/3000 [09:48<1:03:29,  1.48s/it, lr: 1.0e-04 loss: 6.833e-01]
latex_v1:  14%|#3        | 419/3000 [09:48<56:29,  1.31s/it, lr: 1.0e-04 loss: 6.833e-01]  
latex_v1:  14%|#3        | 419/3000 [09:48<56:29,  1.31s/it, lr: 1.0e-04 loss: 6.833e-01]  
latex_v1:  14%|#3        | 419/3000 [09:49<56:29,  1.31s/it, lr: 1.0e-04 loss: 5.859e-02]
latex_v1:  14%|#3        | 419/3000 [09:49<56:29,  1.31s/it, lr: 1.0e-04 loss: 5.859e-02]
latex_v1:  14%|#4        | 420/3000 [09:51<56:28,  1.31s/it, lr: 1.0e-04 loss: 4.031e-01]
latex_v1:  14%|#4        | 420/3000 [09:51<56:28,  1.31s/it, lr: 1.0e-04 loss: 4.031e-01]
latex_v1:  14%|#4        | 421/3000 [09:51<45:48,  1.07s/it, lr: 1.0e-04 loss: 4.031e-01]
latex_v1:  14%|#4        | 421/3000 [09:51<45:48,  1.07s/it, lr: 1.0e-04 loss: 4.031e-01]
latex_v1:  14%|#4        | 421/3000 [09:52<45:48,  1.07s/it, lr: 1.0e-04 loss: 9.356e-02]
latex_v1:  14%|#4        | 421/3000 [09:52<45:48,  1.07s/it, lr: 1.0e-04 loss: 9.356e-02]
latex_v1:  14%|#4        | 422/3000 [09:52<44:43,  1.04s/it, lr: 1.0e-04 loss: 9.356e-02]
latex_v1:  14%|#4        | 422/3000 [09:52<44:43,  1.04s/it, lr: 1.0e-04 loss: 9.356e-02]
latex_v1:  14%|#4        | 422/3000 [09:52<44:43,  1.04s/it, lr: 1.0e-04 loss: 7.800e-02]
latex_v1:  14%|#4        | 422/3000 [09:52<44:43,  1.04s/it, lr: 1.0e-04 loss: 7.800e-02]
latex_v1:  14%|#4        | 423/3000 [09:52<41:18,  1.04it/s, lr: 1.0e-04 loss: 7.800e-02]
latex_v1:  14%|#4        | 423/3000 [09:52<41:18,  1.04it/s, lr: 1.0e-04 loss: 7.800e-02]
latex_v1:  14%|#4        | 423/3000 [09:53<41:18,  1.04it/s, lr: 1.0e-04 loss: 3.097e-02]
latex_v1:  14%|#4        | 423/3000 [09:53<41:18,  1.04it/s, lr: 1.0e-04 loss: 3.097e-02]
latex_v1:  14%|#4        | 424/3000 [09:53<38:46,  1.11it/s, lr: 1.0e-04 loss: 3.097e-02]
latex_v1:  14%|#4        | 424/3000 [09:53<38:46,  1.11it/s, lr: 1.0e-04 loss: 3.097e-02]
latex_v1:  14%|#4        | 424/3000 [09:54<38:46,  1.11it/s, lr: 1.0e-04 loss: 3.814e-02]
latex_v1:  14%|#4        | 424/3000 [09:54<38:46,  1.11it/s, lr: 1.0e-04 loss: 3.814e-02]
latex_v1:  14%|#4        | 425/3000 [09:54<42:13,  1.02it/s, lr: 1.0e-04 loss: 3.814e-02]
latex_v1:  14%|#4        | 425/3000 [09:54<42:13,  1.02it/s, lr: 1.0e-04 loss: 3.814e-02]
latex_v1:  14%|#4        | 425/3000 [09:56<42:13,  1.02it/s, lr: 1.0e-04 loss: 1.751e-01]
latex_v1:  14%|#4        | 425/3000 [09:56<42:13,  1.02it/s, lr: 1.0e-04 loss: 1.751e-01]
latex_v1:  14%|#4        | 426/3000 [09:56<53:07,  1.24s/it, lr: 1.0e-04 loss: 1.751e-01]
latex_v1:  14%|#4        | 426/3000 [09:56<53:07,  1.24s/it, lr: 1.0e-04 loss: 1.751e-01]
latex_v1:  14%|#4        | 426/3000 [09:57<53:07,  1.24s/it, lr: 1.0e-04 loss: 1.341e-01]
latex_v1:  14%|#4        | 426/3000 [09:57<53:07,  1.24s/it, lr: 1.0e-04 loss: 1.341e-01]
latex_v1:  14%|#4        | 427/3000 [09:57<47:05,  1.10s/it, lr: 1.0e-04 loss: 1.341e-01]
latex_v1:  14%|#4        | 427/3000 [09:57<47:05,  1.10s/it, lr: 1.0e-04 loss: 1.341e-01]
latex_v1:  14%|#4        | 427/3000 [09:58<47:05,  1.10s/it, lr: 1.0e-04 loss: 8.458e-01]
latex_v1:  14%|#4        | 427/3000 [09:58<47:05,  1.10s/it, lr: 1.0e-04 loss: 8.458e-01]
latex_v1:  14%|#4        | 428/3000 [09:58<45:25,  1.06s/it, lr: 1.0e-04 loss: 8.458e-01]
latex_v1:  14%|#4        | 428/3000 [09:58<45:25,  1.06s/it, lr: 1.0e-04 loss: 8.458e-01]
latex_v1:  14%|#4        | 428/3000 [10:00<45:25,  1.06s/it, lr: 1.0e-04 loss: 1.797e-01]
latex_v1:  14%|#4        | 428/3000 [10:00<45:25,  1.06s/it, lr: 1.0e-04 loss: 1.797e-01]
latex_v1:  14%|#4        | 429/3000 [10:00<55:52,  1.30s/it, lr: 1.0e-04 loss: 1.797e-01]
latex_v1:  14%|#4        | 429/3000 [10:00<55:52,  1.30s/it, lr: 1.0e-04 loss: 1.797e-01]
latex_v1:  14%|#4        | 429/3000 [10:01<55:52,  1.30s/it, lr: 1.0e-04 loss: 8.948e-01]
latex_v1:  14%|#4        | 429/3000 [10:01<55:52,  1.30s/it, lr: 1.0e-04 loss: 8.948e-01]
latex_v1:  14%|#4        | 430/3000 [10:03<55:51,  1.30s/it, lr: 1.0e-04 loss: 1.807e-01]
latex_v1:  14%|#4        | 430/3000 [10:03<55:51,  1.30s/it, lr: 1.0e-04 loss: 1.807e-01]
latex_v1:  14%|#4        | 431/3000 [10:03<49:39,  1.16s/it, lr: 1.0e-04 loss: 1.807e-01]
latex_v1:  14%|#4        | 431/3000 [10:03<49:39,  1.16s/it, lr: 1.0e-04 loss: 1.807e-01]
latex_v1:  14%|#4        | 431/3000 [10:03<49:39,  1.16s/it, lr: 1.0e-04 loss: 9.523e-02]
latex_v1:  14%|#4        | 431/3000 [10:03<49:39,  1.16s/it, lr: 1.0e-04 loss: 9.523e-02]
latex_v1:  14%|#4        | 432/3000 [10:03<45:19,  1.06s/it, lr: 1.0e-04 loss: 9.523e-02]
latex_v1:  14%|#4        | 432/3000 [10:03<45:19,  1.06s/it, lr: 1.0e-04 loss: 9.523e-02]
latex_v1:  14%|#4        | 432/3000 [10:06<45:19,  1.06s/it, lr: 1.0e-04 loss: 4.521e-02]
latex_v1:  14%|#4        | 432/3000 [10:06<45:19,  1.06s/it, lr: 1.0e-04 loss: 4.521e-02]
latex_v1:  14%|#4        | 433/3000 [10:06<1:06:01,  1.54s/it, lr: 1.0e-04 loss: 4.521e-02]
latex_v1:  14%|#4        | 433/3000 [10:06<1:06:01,  1.54s/it, lr: 1.0e-04 loss: 4.521e-02]
latex_v1:  14%|#4        | 433/3000 [10:08<1:06:01,  1.54s/it, lr: 1.0e-04 loss: 1.298e-01]
latex_v1:  14%|#4        | 433/3000 [10:08<1:06:01,  1.54s/it, lr: 1.0e-04 loss: 1.298e-01]
latex_v1:  14%|#4        | 434/3000 [10:08<1:04:40,  1.51s/it, lr: 1.0e-04 loss: 1.298e-01]
latex_v1:  14%|#4        | 434/3000 [10:08<1:04:40,  1.51s/it, lr: 1.0e-04 loss: 1.298e-01]
latex_v1:  14%|#4        | 434/3000 [10:09<1:04:40,  1.51s/it, lr: 1.0e-04 loss: 3.198e-01]
latex_v1:  14%|#4        | 434/3000 [10:09<1:04:40,  1.51s/it, lr: 1.0e-04 loss: 3.198e-01]
latex_v1:  14%|#4        | 435/3000 [10:09<55:46,  1.30s/it, lr: 1.0e-04 loss: 3.198e-01]  
latex_v1:  14%|#4        | 435/3000 [10:09<55:46,  1.30s/it, lr: 1.0e-04 loss: 3.198e-01]  
latex_v1:  14%|#4        | 435/3000 [10:09<55:46,  1.30s/it, lr: 1.0e-04 loss: 6.085e-01]
latex_v1:  14%|#4        | 435/3000 [10:09<55:46,  1.30s/it, lr: 1.0e-04 loss: 6.085e-01]
latex_v1:  15%|#4        | 436/3000 [10:09<51:44,  1.21s/it, lr: 1.0e-04 loss: 6.085e-01]
latex_v1:  15%|#4        | 436/3000 [10:09<51:44,  1.21s/it, lr: 1.0e-04 loss: 6.085e-01]
latex_v1:  15%|#4        | 436/3000 [10:11<51:44,  1.21s/it, lr: 1.0e-04 loss: 7.175e-01]
latex_v1:  15%|#4        | 436/3000 [10:11<51:44,  1.21s/it, lr: 1.0e-04 loss: 7.175e-01]
latex_v1:  15%|#4        | 437/3000 [10:11<51:18,  1.20s/it, lr: 1.0e-04 loss: 7.175e-01]
latex_v1:  15%|#4        | 437/3000 [10:11<51:18,  1.20s/it, lr: 1.0e-04 loss: 7.175e-01]
latex_v1:  15%|#4        | 437/3000 [10:11<51:18,  1.20s/it, lr: 1.0e-04 loss: 1.629e-01]
latex_v1:  15%|#4        | 437/3000 [10:11<51:18,  1.20s/it, lr: 1.0e-04 loss: 1.629e-01]
latex_v1:  15%|#4        | 438/3000 [10:11<45:36,  1.07s/it, lr: 1.0e-04 loss: 1.629e-01]
latex_v1:  15%|#4        | 438/3000 [10:11<45:36,  1.07s/it, lr: 1.0e-04 loss: 1.629e-01]
latex_v1:  15%|#4        | 438/3000 [10:12<45:36,  1.07s/it, lr: 1.0e-04 loss: 3.616e-01]
latex_v1:  15%|#4        | 438/3000 [10:12<45:36,  1.07s/it, lr: 1.0e-04 loss: 3.616e-01]
latex_v1:  15%|#4        | 439/3000 [10:12<41:37,  1.03it/s, lr: 1.0e-04 loss: 3.616e-01]
latex_v1:  15%|#4        | 439/3000 [10:12<41:37,  1.03it/s, lr: 1.0e-04 loss: 3.616e-01]
latex_v1:  15%|#4        | 439/3000 [10:14<41:37,  1.03it/s, lr: 1.0e-04 loss: 5.475e-01]
latex_v1:  15%|#4        | 439/3000 [10:14<41:37,  1.03it/s, lr: 1.0e-04 loss: 5.475e-01]
latex_v1:  15%|#4        | 440/3000 [10:15<41:36,  1.03it/s, lr: 1.0e-04 loss: 2.713e-01]
latex_v1:  15%|#4        | 440/3000 [10:15<41:36,  1.03it/s, lr: 1.0e-04 loss: 2.713e-01]
latex_v1:  15%|#4        | 441/3000 [10:15<35:32,  1.20it/s, lr: 1.0e-04 loss: 2.713e-01]
latex_v1:  15%|#4        | 441/3000 [10:15<35:32,  1.20it/s, lr: 1.0e-04 loss: 2.713e-01]
latex_v1:  15%|#4        | 441/3000 [10:16<35:32,  1.20it/s, lr: 1.0e-04 loss: 5.290e-01]
latex_v1:  15%|#4        | 441/3000 [10:16<35:32,  1.20it/s, lr: 1.0e-04 loss: 5.290e-01]
latex_v1:  15%|#4        | 442/3000 [10:16<39:14,  1.09it/s, lr: 1.0e-04 loss: 5.290e-01]
latex_v1:  15%|#4        | 442/3000 [10:16<39:14,  1.09it/s, lr: 1.0e-04 loss: 5.290e-01]
latex_v1:  15%|#4        | 442/3000 [10:18<39:14,  1.09it/s, lr: 1.0e-04 loss: 7.313e-01]
latex_v1:  15%|#4        | 442/3000 [10:18<39:14,  1.09it/s, lr: 1.0e-04 loss: 7.313e-01]
latex_v1:  15%|#4        | 443/3000 [10:18<44:04,  1.03s/it, lr: 1.0e-04 loss: 7.313e-01]
latex_v1:  15%|#4        | 443/3000 [10:18<44:04,  1.03s/it, lr: 1.0e-04 loss: 7.313e-01]
latex_v1:  15%|#4        | 443/3000 [10:19<44:04,  1.03s/it, lr: 1.0e-04 loss: 1.049e-01]
latex_v1:  15%|#4        | 443/3000 [10:19<44:04,  1.03s/it, lr: 1.0e-04 loss: 1.049e-01]
latex_v1:  15%|#4        | 444/3000 [10:19<50:18,  1.18s/it, lr: 1.0e-04 loss: 1.049e-01]
latex_v1:  15%|#4        | 444/3000 [10:19<50:18,  1.18s/it, lr: 1.0e-04 loss: 1.049e-01]
latex_v1:  15%|#4        | 444/3000 [10:21<50:18,  1.18s/it, lr: 1.0e-04 loss: 1.352e-01]
latex_v1:  15%|#4        | 444/3000 [10:21<50:18,  1.18s/it, lr: 1.0e-04 loss: 1.352e-01]
latex_v1:  15%|#4        | 445/3000 [10:21<58:48,  1.38s/it, lr: 1.0e-04 loss: 1.352e-01]
latex_v1:  15%|#4        | 445/3000 [10:21<58:48,  1.38s/it, lr: 1.0e-04 loss: 1.352e-01]
latex_v1:  15%|#4        | 445/3000 [10:24<58:48,  1.38s/it, lr: 1.0e-04 loss: 7.511e-02]
latex_v1:  15%|#4        | 445/3000 [10:24<58:48,  1.38s/it, lr: 1.0e-04 loss: 7.511e-02]
latex_v1:  15%|#4        | 446/3000 [10:24<1:17:07,  1.81s/it, lr: 1.0e-04 loss: 7.511e-02]
latex_v1:  15%|#4        | 446/3000 [10:24<1:17:07,  1.81s/it, lr: 1.0e-04 loss: 7.511e-02]
latex_v1:  15%|#4        | 446/3000 [10:27<1:17:07,  1.81s/it, lr: 1.0e-04 loss: 7.279e-01]
latex_v1:  15%|#4        | 446/3000 [10:27<1:17:07,  1.81s/it, lr: 1.0e-04 loss: 7.279e-01]
latex_v1:  15%|#4        | 447/3000 [10:27<1:30:08,  2.12s/it, lr: 1.0e-04 loss: 7.279e-01]
latex_v1:  15%|#4        | 447/3000 [10:27<1:30:08,  2.12s/it, lr: 1.0e-04 loss: 7.279e-01]
latex_v1:  15%|#4        | 447/3000 [10:28<1:30:08,  2.12s/it, lr: 1.0e-04 loss: 1.699e-01]
latex_v1:  15%|#4        | 447/3000 [10:28<1:30:08,  2.12s/it, lr: 1.0e-04 loss: 1.699e-01]
latex_v1:  15%|#4        | 448/3000 [10:28<1:13:06,  1.72s/it, lr: 1.0e-04 loss: 1.699e-01]
latex_v1:  15%|#4        | 448/3000 [10:28<1:13:06,  1.72s/it, lr: 1.0e-04 loss: 1.699e-01]
latex_v1:  15%|#4        | 448/3000 [10:29<1:13:06,  1.72s/it, lr: 1.0e-04 loss: 6.503e-01]
latex_v1:  15%|#4        | 448/3000 [10:29<1:13:06,  1.72s/it, lr: 1.0e-04 loss: 6.503e-01]
latex_v1:  15%|#4        | 449/3000 [10:29<1:09:59,  1.65s/it, lr: 1.0e-04 loss: 6.503e-01]
latex_v1:  15%|#4        | 449/3000 [10:29<1:09:59,  1.65s/it, lr: 1.0e-04 loss: 6.503e-01]
latex_v1:  15%|#4        | 449/3000 [10:30<1:09:59,  1.65s/it, lr: 1.0e-04 loss: 7.322e-01]
latex_v1:  15%|#4        | 449/3000 [10:30<1:09:59,  1.65s/it, lr: 1.0e-04 loss: 7.322e-01]
latex_v1:  15%|#5        | 450/3000 [10:31<1:09:58,  1.65s/it, lr: 1.0e-04 loss: 5.535e-01]
latex_v1:  15%|#5        | 450/3000 [10:31<1:09:58,  1.65s/it, lr: 1.0e-04 loss: 5.535e-01]
latex_v1:  15%|#5        | 451/3000 [10:31<45:33,  1.07s/it, lr: 1.0e-04 loss: 5.535e-01]  
latex_v1:  15%|#5        | 451/3000 [10:31<45:33,  1.07s/it, lr: 1.0e-04 loss: 5.535e-01]  
latex_v1:  15%|#5        | 451/3000 [10:32<45:33,  1.07s/it, lr: 1.0e-04 loss: 5.299e-01]
latex_v1:  15%|#5        | 451/3000 [10:32<45:33,  1.07s/it, lr: 1.0e-04 loss: 5.299e-01]
latex_v1:  15%|#5        | 452/3000 [10:32<50:01,  1.18s/it, lr: 1.0e-04 loss: 5.299e-01]
latex_v1:  15%|#5        | 452/3000 [10:32<50:01,  1.18s/it, lr: 1.0e-04 loss: 5.299e-01]
latex_v1:  15%|#5        | 452/3000 [10:34<50:01,  1.18s/it, lr: 1.0e-04 loss: 8.032e-01]
latex_v1:  15%|#5        | 452/3000 [10:34<50:01,  1.18s/it, lr: 1.0e-04 loss: 8.032e-01]
latex_v1:  15%|#5        | 453/3000 [10:34<50:07,  1.18s/it, lr: 1.0e-04 loss: 8.032e-01]
latex_v1:  15%|#5        | 453/3000 [10:34<50:07,  1.18s/it, lr: 1.0e-04 loss: 8.032e-01]
latex_v1:  15%|#5        | 453/3000 [10:34<50:07,  1.18s/it, lr: 1.0e-04 loss: 8.501e-01]
latex_v1:  15%|#5        | 453/3000 [10:34<50:07,  1.18s/it, lr: 1.0e-04 loss: 8.501e-01]
latex_v1:  15%|#5        | 454/3000 [10:34<45:06,  1.06s/it, lr: 1.0e-04 loss: 8.501e-01]
latex_v1:  15%|#5        | 454/3000 [10:34<45:06,  1.06s/it, lr: 1.0e-04 loss: 8.501e-01]
latex_v1:  15%|#5        | 454/3000 [10:37<45:06,  1.06s/it, lr: 1.0e-04 loss: 1.966e-01]
latex_v1:  15%|#5        | 454/3000 [10:37<45:06,  1.06s/it, lr: 1.0e-04 loss: 1.966e-01]
latex_v1:  15%|#5        | 455/3000 [10:37<1:04:05,  1.51s/it, lr: 1.0e-04 loss: 1.966e-01]
latex_v1:  15%|#5        | 455/3000 [10:37<1:04:05,  1.51s/it, lr: 1.0e-04 loss: 1.966e-01]
latex_v1:  15%|#5        | 455/3000 [10:38<1:04:05,  1.51s/it, lr: 1.0e-04 loss: 1.749e-01]
latex_v1:  15%|#5        | 455/3000 [10:38<1:04:05,  1.51s/it, lr: 1.0e-04 loss: 1.749e-01]
latex_v1:  15%|#5        | 456/3000 [10:39<1:04:42,  1.53s/it, lr: 1.0e-04 loss: 1.749e-01]
latex_v1:  15%|#5        | 456/3000 [10:39<1:04:42,  1.53s/it, lr: 1.0e-04 loss: 1.749e-01]
latex_v1:  15%|#5        | 456/3000 [10:39<1:04:42,  1.53s/it, lr: 1.0e-04 loss: 2.189e-01]
latex_v1:  15%|#5        | 456/3000 [10:39<1:04:42,  1.53s/it, lr: 1.0e-04 loss: 2.189e-01]
latex_v1:  15%|#5        | 457/3000 [10:39<55:30,  1.31s/it, lr: 1.0e-04 loss: 2.189e-01]  
latex_v1:  15%|#5        | 457/3000 [10:39<55:30,  1.31s/it, lr: 1.0e-04 loss: 2.189e-01]  
latex_v1:  15%|#5        | 457/3000 [10:41<55:30,  1.31s/it, lr: 1.0e-04 loss: 2.615e-01]
latex_v1:  15%|#5        | 457/3000 [10:41<55:30,  1.31s/it, lr: 1.0e-04 loss: 2.615e-01]
latex_v1:  15%|#5        | 458/3000 [10:41<56:45,  1.34s/it, lr: 1.0e-04 loss: 2.615e-01]
latex_v1:  15%|#5        | 458/3000 [10:41<56:45,  1.34s/it, lr: 1.0e-04 loss: 2.615e-01]
latex_v1:  15%|#5        | 458/3000 [10:42<56:45,  1.34s/it, lr: 1.0e-04 loss: 5.288e-01]
latex_v1:  15%|#5        | 458/3000 [10:42<56:45,  1.34s/it, lr: 1.0e-04 loss: 5.288e-01]
latex_v1:  15%|#5        | 459/3000 [10:42<53:29,  1.26s/it, lr: 1.0e-04 loss: 5.288e-01]
latex_v1:  15%|#5        | 459/3000 [10:42<53:29,  1.26s/it, lr: 1.0e-04 loss: 5.288e-01]
latex_v1:  15%|#5        | 459/3000 [10:43<53:29,  1.26s/it, lr: 1.0e-04 loss: 6.267e-01]
latex_v1:  15%|#5        | 459/3000 [10:43<53:29,  1.26s/it, lr: 1.0e-04 loss: 6.267e-01]
latex_v1:  15%|#5        | 460/3000 [10:44<53:28,  1.26s/it, lr: 1.0e-04 loss: 1.404e-01]
latex_v1:  15%|#5        | 460/3000 [10:44<53:28,  1.26s/it, lr: 1.0e-04 loss: 1.404e-01]
latex_v1:  15%|#5        | 461/3000 [10:44<43:48,  1.04s/it, lr: 1.0e-04 loss: 1.404e-01]
latex_v1:  15%|#5        | 461/3000 [10:44<43:48,  1.04s/it, lr: 1.0e-04 loss: 1.404e-01]
latex_v1:  15%|#5        | 461/3000 [10:47<43:48,  1.04s/it, lr: 1.0e-04 loss: 1.845e-01]
latex_v1:  15%|#5        | 461/3000 [10:47<43:48,  1.04s/it, lr: 1.0e-04 loss: 1.845e-01]
latex_v1:  15%|#5        | 462/3000 [10:47<1:02:58,  1.49s/it, lr: 1.0e-04 loss: 1.845e-01]
latex_v1:  15%|#5        | 462/3000 [10:47<1:02:58,  1.49s/it, lr: 1.0e-04 loss: 1.845e-01]
latex_v1:  15%|#5        | 462/3000 [10:49<1:02:58,  1.49s/it, lr: 1.0e-04 loss: 5.121e-01]
latex_v1:  15%|#5        | 462/3000 [10:49<1:02:58,  1.49s/it, lr: 1.0e-04 loss: 5.121e-01]
latex_v1:  15%|#5        | 463/3000 [10:49<1:04:16,  1.52s/it, lr: 1.0e-04 loss: 5.121e-01]
latex_v1:  15%|#5        | 463/3000 [10:49<1:04:16,  1.52s/it, lr: 1.0e-04 loss: 5.121e-01]
latex_v1:  15%|#5        | 463/3000 [10:50<1:04:16,  1.52s/it, lr: 1.0e-04 loss: 6.449e-02]
latex_v1:  15%|#5        | 463/3000 [10:50<1:04:16,  1.52s/it, lr: 1.0e-04 loss: 6.449e-02]
latex_v1:  15%|#5        | 464/3000 [10:50<1:01:54,  1.46s/it, lr: 1.0e-04 loss: 6.449e-02]
latex_v1:  15%|#5        | 464/3000 [10:50<1:01:54,  1.46s/it, lr: 1.0e-04 loss: 6.449e-02]
latex_v1:  15%|#5        | 464/3000 [10:53<1:01:54,  1.46s/it, lr: 1.0e-04 loss: 9.060e-02]
latex_v1:  15%|#5        | 464/3000 [10:53<1:01:54,  1.46s/it, lr: 1.0e-04 loss: 9.060e-02]
latex_v1:  16%|#5        | 465/3000 [10:53<1:18:44,  1.86s/it, lr: 1.0e-04 loss: 9.060e-02]
latex_v1:  16%|#5        | 465/3000 [10:53<1:18:44,  1.86s/it, lr: 1.0e-04 loss: 9.060e-02]
latex_v1:  16%|#5        | 465/3000 [10:54<1:18:44,  1.86s/it, lr: 1.0e-04 loss: 4.221e-01]
latex_v1:  16%|#5        | 465/3000 [10:54<1:18:44,  1.86s/it, lr: 1.0e-04 loss: 4.221e-01]
latex_v1:  16%|#5        | 466/3000 [10:54<1:05:26,  1.55s/it, lr: 1.0e-04 loss: 4.221e-01]
latex_v1:  16%|#5        | 466/3000 [10:54<1:05:26,  1.55s/it, lr: 1.0e-04 loss: 4.221e-01]
latex_v1:  16%|#5        | 466/3000 [10:55<1:05:26,  1.55s/it, lr: 1.0e-04 loss: 5.325e-01]
latex_v1:  16%|#5        | 466/3000 [10:55<1:05:26,  1.55s/it, lr: 1.0e-04 loss: 5.325e-01]
latex_v1:  16%|#5        | 467/3000 [10:55<1:00:41,  1.44s/it, lr: 1.0e-04 loss: 5.325e-01]
latex_v1:  16%|#5        | 467/3000 [10:55<1:00:41,  1.44s/it, lr: 1.0e-04 loss: 5.325e-01]
latex_v1:  16%|#5        | 467/3000 [10:56<1:00:41,  1.44s/it, lr: 1.0e-04 loss: 9.500e-02]
latex_v1:  16%|#5        | 467/3000 [10:56<1:00:41,  1.44s/it, lr: 1.0e-04 loss: 9.500e-02]
latex_v1:  16%|#5        | 468/3000 [10:56<52:15,  1.24s/it, lr: 1.0e-04 loss: 9.500e-02]  
latex_v1:  16%|#5        | 468/3000 [10:56<52:15,  1.24s/it, lr: 1.0e-04 loss: 9.500e-02]  
latex_v1:  16%|#5        | 468/3000 [10:58<52:15,  1.24s/it, lr: 1.0e-04 loss: 7.788e-02]
latex_v1:  16%|#5        | 468/3000 [10:58<52:15,  1.24s/it, lr: 1.0e-04 loss: 7.788e-02]
latex_v1:  16%|#5        | 469/3000 [10:58<1:01:01,  1.45s/it, lr: 1.0e-04 loss: 7.788e-02]
latex_v1:  16%|#5        | 469/3000 [10:58<1:01:01,  1.45s/it, lr: 1.0e-04 loss: 7.788e-02]
latex_v1:  16%|#5        | 469/3000 [10:59<1:01:01,  1.45s/it, lr: 1.0e-04 loss: 5.097e-01]
latex_v1:  16%|#5        | 469/3000 [10:59<1:01:01,  1.45s/it, lr: 1.0e-04 loss: 5.097e-01]
latex_v1:  16%|#5        | 470/3000 [11:00<1:00:59,  1.45s/it, lr: 1.0e-04 loss: 2.864e-01]
latex_v1:  16%|#5        | 470/3000 [11:00<1:00:59,  1.45s/it, lr: 1.0e-04 loss: 2.864e-01]
latex_v1:  16%|#5        | 471/3000 [11:00<40:15,  1.05it/s, lr: 1.0e-04 loss: 2.864e-01]  
latex_v1:  16%|#5        | 471/3000 [11:00<40:15,  1.05it/s, lr: 1.0e-04 loss: 2.864e-01]  
latex_v1:  16%|#5        | 471/3000 [11:03<40:15,  1.05it/s, lr: 1.0e-04 loss: 3.064e-01]
latex_v1:  16%|#5        | 471/3000 [11:03<40:15,  1.05it/s, lr: 1.0e-04 loss: 3.064e-01]
latex_v1:  16%|#5        | 472/3000 [11:03<58:19,  1.38s/it, lr: 1.0e-04 loss: 3.064e-01]
latex_v1:  16%|#5        | 472/3000 [11:03<58:19,  1.38s/it, lr: 1.0e-04 loss: 3.064e-01]
latex_v1:  16%|#5        | 472/3000 [11:04<58:19,  1.38s/it, lr: 1.0e-04 loss: 1.093e-01]
latex_v1:  16%|#5        | 472/3000 [11:04<58:19,  1.38s/it, lr: 1.0e-04 loss: 1.093e-01]
latex_v1:  16%|#5        | 473/3000 [11:04<1:00:03,  1.43s/it, lr: 1.0e-04 loss: 1.093e-01]
latex_v1:  16%|#5        | 473/3000 [11:04<1:00:03,  1.43s/it, lr: 1.0e-04 loss: 1.093e-01]
latex_v1:  16%|#5        | 473/3000 [11:05<1:00:03,  1.43s/it, lr: 1.0e-04 loss: 1.199e-01]
latex_v1:  16%|#5        | 473/3000 [11:05<1:00:03,  1.43s/it, lr: 1.0e-04 loss: 1.199e-01]
latex_v1:  16%|#5        | 474/3000 [11:05<52:17,  1.24s/it, lr: 1.0e-04 loss: 1.199e-01]  
latex_v1:  16%|#5        | 474/3000 [11:05<52:17,  1.24s/it, lr: 1.0e-04 loss: 1.199e-01]  
latex_v1:  16%|#5        | 474/3000 [11:07<52:17,  1.24s/it, lr: 1.0e-04 loss: 2.404e-01]
latex_v1:  16%|#5        | 474/3000 [11:07<52:17,  1.24s/it, lr: 1.0e-04 loss: 2.404e-01]
latex_v1:  16%|#5        | 475/3000 [11:07<55:55,  1.33s/it, lr: 1.0e-04 loss: 2.404e-01]
latex_v1:  16%|#5        | 475/3000 [11:07<55:55,  1.33s/it, lr: 1.0e-04 loss: 2.404e-01]
latex_v1:  16%|#5        | 475/3000 [11:08<55:55,  1.33s/it, lr: 1.0e-04 loss: 1.286e-01]
latex_v1:  16%|#5        | 475/3000 [11:08<55:55,  1.33s/it, lr: 1.0e-04 loss: 1.286e-01]
latex_v1:  16%|#5        | 476/3000 [11:08<1:01:25,  1.46s/it, lr: 1.0e-04 loss: 1.286e-01]
latex_v1:  16%|#5        | 476/3000 [11:08<1:01:25,  1.46s/it, lr: 1.0e-04 loss: 1.286e-01]
latex_v1:  16%|#5        | 476/3000 [11:10<1:01:25,  1.46s/it, lr: 1.0e-04 loss: 1.599e-01]
latex_v1:  16%|#5        | 476/3000 [11:10<1:01:25,  1.46s/it, lr: 1.0e-04 loss: 1.599e-01]
latex_v1:  16%|#5        | 477/3000 [11:10<1:02:43,  1.49s/it, lr: 1.0e-04 loss: 1.599e-01]
latex_v1:  16%|#5        | 477/3000 [11:10<1:02:43,  1.49s/it, lr: 1.0e-04 loss: 1.599e-01]
latex_v1:  16%|#5        | 477/3000 [11:11<1:02:43,  1.49s/it, lr: 1.0e-04 loss: 4.435e-01]
latex_v1:  16%|#5        | 477/3000 [11:11<1:02:43,  1.49s/it, lr: 1.0e-04 loss: 4.435e-01]
latex_v1:  16%|#5        | 478/3000 [11:11<56:05,  1.33s/it, lr: 1.0e-04 loss: 4.435e-01]  
latex_v1:  16%|#5        | 478/3000 [11:11<56:05,  1.33s/it, lr: 1.0e-04 loss: 4.435e-01]  
latex_v1:  16%|#5        | 478/3000 [11:14<56:05,  1.33s/it, lr: 1.0e-04 loss: 1.067e-01]
latex_v1:  16%|#5        | 478/3000 [11:14<56:05,  1.33s/it, lr: 1.0e-04 loss: 1.067e-01]
latex_v1:  16%|#5        | 479/3000 [11:14<1:12:07,  1.72s/it, lr: 1.0e-04 loss: 1.067e-01]
latex_v1:  16%|#5        | 479/3000 [11:14<1:12:07,  1.72s/it, lr: 1.0e-04 loss: 1.067e-01]
latex_v1:  16%|#5        | 479/3000 [11:15<1:12:07,  1.72s/it, lr: 1.0e-04 loss: 4.049e-01]
latex_v1:  16%|#5        | 479/3000 [11:15<1:12:07,  1.72s/it, lr: 1.0e-04 loss: 4.049e-01]
latex_v1:  16%|#6        | 480/3000 [11:17<1:12:05,  1.72s/it, lr: 1.0e-04 loss: 7.156e-01]
latex_v1:  16%|#6        | 480/3000 [11:17<1:12:05,  1.72s/it, lr: 1.0e-04 loss: 7.156e-01]
latex_v1:  16%|#6        | 481/3000 [11:17<52:49,  1.26s/it, lr: 1.0e-04 loss: 7.156e-01]  
latex_v1:  16%|#6        | 481/3000 [11:17<52:49,  1.26s/it, lr: 1.0e-04 loss: 7.156e-01]  
latex_v1:  16%|#6        | 481/3000 [11:17<52:49,  1.26s/it, lr: 1.0e-04 loss: 2.995e-02]
latex_v1:  16%|#6        | 481/3000 [11:17<52:49,  1.26s/it, lr: 1.0e-04 loss: 2.995e-02]
latex_v1:  16%|#6        | 482/3000 [11:17<47:54,  1.14s/it, lr: 1.0e-04 loss: 2.995e-02]
latex_v1:  16%|#6        | 482/3000 [11:17<47:54,  1.14s/it, lr: 1.0e-04 loss: 2.995e-02]
latex_v1:  16%|#6        | 482/3000 [11:19<47:54,  1.14s/it, lr: 1.0e-04 loss: 6.202e-01]
latex_v1:  16%|#6        | 482/3000 [11:19<47:54,  1.14s/it, lr: 1.0e-04 loss: 6.202e-01]
latex_v1:  16%|#6        | 483/3000 [11:19<48:19,  1.15s/it, lr: 1.0e-04 loss: 6.202e-01]
latex_v1:  16%|#6        | 483/3000 [11:19<48:19,  1.15s/it, lr: 1.0e-04 loss: 6.202e-01]
latex_v1:  16%|#6        | 483/3000 [11:20<48:19,  1.15s/it, lr: 1.0e-04 loss: 1.688e-01]
latex_v1:  16%|#6        | 483/3000 [11:20<48:19,  1.15s/it, lr: 1.0e-04 loss: 1.688e-01]
latex_v1:  16%|#6        | 484/3000 [11:20<50:22,  1.20s/it, lr: 1.0e-04 loss: 1.688e-01]
latex_v1:  16%|#6        | 484/3000 [11:20<50:22,  1.20s/it, lr: 1.0e-04 loss: 1.688e-01]
latex_v1:  16%|#6        | 484/3000 [11:21<50:22,  1.20s/it, lr: 1.0e-04 loss: 2.362e-01]
latex_v1:  16%|#6        | 484/3000 [11:21<50:22,  1.20s/it, lr: 1.0e-04 loss: 2.362e-01]
latex_v1:  16%|#6        | 485/3000 [11:21<47:31,  1.13s/it, lr: 1.0e-04 loss: 2.362e-01]
latex_v1:  16%|#6        | 485/3000 [11:21<47:31,  1.13s/it, lr: 1.0e-04 loss: 2.362e-01]
latex_v1:  16%|#6        | 485/3000 [11:22<47:31,  1.13s/it, lr: 1.0e-04 loss: 1.670e-01]
latex_v1:  16%|#6        | 485/3000 [11:22<47:31,  1.13s/it, lr: 1.0e-04 loss: 1.670e-01]
latex_v1:  16%|#6        | 486/3000 [11:22<51:17,  1.22s/it, lr: 1.0e-04 loss: 1.670e-01]
latex_v1:  16%|#6        | 486/3000 [11:22<51:17,  1.22s/it, lr: 1.0e-04 loss: 1.670e-01]
latex_v1:  16%|#6        | 486/3000 [11:24<51:17,  1.22s/it, lr: 1.0e-04 loss: 7.683e-01]
latex_v1:  16%|#6        | 486/3000 [11:24<51:17,  1.22s/it, lr: 1.0e-04 loss: 7.683e-01]
latex_v1:  16%|#6        | 487/3000 [11:24<52:33,  1.25s/it, lr: 1.0e-04 loss: 7.683e-01]
latex_v1:  16%|#6        | 487/3000 [11:24<52:33,  1.25s/it, lr: 1.0e-04 loss: 7.683e-01]
latex_v1:  16%|#6        | 487/3000 [11:24<52:33,  1.25s/it, lr: 1.0e-04 loss: 1.152e-01]
latex_v1:  16%|#6        | 487/3000 [11:24<52:33,  1.25s/it, lr: 1.0e-04 loss: 1.152e-01]
latex_v1:  16%|#6        | 488/3000 [11:24<46:19,  1.11s/it, lr: 1.0e-04 loss: 1.152e-01]
latex_v1:  16%|#6        | 488/3000 [11:24<46:19,  1.11s/it, lr: 1.0e-04 loss: 1.152e-01]
latex_v1:  16%|#6        | 488/3000 [11:26<46:19,  1.11s/it, lr: 1.0e-04 loss: 1.900e-01]
latex_v1:  16%|#6        | 488/3000 [11:26<46:19,  1.11s/it, lr: 1.0e-04 loss: 1.900e-01]
latex_v1:  16%|#6        | 489/3000 [11:26<51:33,  1.23s/it, lr: 1.0e-04 loss: 1.900e-01]
latex_v1:  16%|#6        | 489/3000 [11:26<51:33,  1.23s/it, lr: 1.0e-04 loss: 1.900e-01]
latex_v1:  16%|#6        | 489/3000 [11:28<51:33,  1.23s/it, lr: 1.0e-04 loss: 5.048e-01]
latex_v1:  16%|#6        | 489/3000 [11:28<51:33,  1.23s/it, lr: 1.0e-04 loss: 5.048e-01]
latex_v1:  16%|#6        | 490/3000 [11:29<51:32,  1.23s/it, lr: 1.0e-04 loss: 5.084e-02]
latex_v1:  16%|#6        | 490/3000 [11:29<51:32,  1.23s/it, lr: 1.0e-04 loss: 5.084e-02]
latex_v1:  16%|#6        | 491/3000 [11:29<42:30,  1.02s/it, lr: 1.0e-04 loss: 5.084e-02]
latex_v1:  16%|#6        | 491/3000 [11:29<42:30,  1.02s/it, lr: 1.0e-04 loss: 5.084e-02]
latex_v1:  16%|#6        | 491/3000 [11:31<42:30,  1.02s/it, lr: 1.0e-04 loss: 5.354e-01]
latex_v1:  16%|#6        | 491/3000 [11:31<42:30,  1.02s/it, lr: 1.0e-04 loss: 5.354e-01]
latex_v1:  16%|#6        | 492/3000 [11:31<47:57,  1.15s/it, lr: 1.0e-04 loss: 5.354e-01]
latex_v1:  16%|#6        | 492/3000 [11:31<47:57,  1.15s/it, lr: 1.0e-04 loss: 5.354e-01]
latex_v1:  16%|#6        | 492/3000 [11:31<47:57,  1.15s/it, lr: 1.0e-04 loss: 2.509e-01]
latex_v1:  16%|#6        | 492/3000 [11:31<47:57,  1.15s/it, lr: 1.0e-04 loss: 2.509e-01]
latex_v1:  16%|#6        | 493/3000 [11:31<43:33,  1.04s/it, lr: 1.0e-04 loss: 2.509e-01]
latex_v1:  16%|#6        | 493/3000 [11:31<43:33,  1.04s/it, lr: 1.0e-04 loss: 2.509e-01]
latex_v1:  16%|#6        | 493/3000 [11:34<43:33,  1.04s/it, lr: 1.0e-04 loss: 5.921e-01]
latex_v1:  16%|#6        | 493/3000 [11:34<43:33,  1.04s/it, lr: 1.0e-04 loss: 5.921e-01]
latex_v1:  16%|#6        | 494/3000 [11:34<1:04:10,  1.54s/it, lr: 1.0e-04 loss: 5.921e-01]
latex_v1:  16%|#6        | 494/3000 [11:34<1:04:10,  1.54s/it, lr: 1.0e-04 loss: 5.921e-01]
latex_v1:  16%|#6        | 494/3000 [11:36<1:04:10,  1.54s/it, lr: 1.0e-04 loss: 1.864e-01]
latex_v1:  16%|#6        | 494/3000 [11:36<1:04:10,  1.54s/it, lr: 1.0e-04 loss: 1.864e-01]
latex_v1:  16%|#6        | 495/3000 [11:36<1:03:11,  1.51s/it, lr: 1.0e-04 loss: 1.864e-01]
latex_v1:  16%|#6        | 495/3000 [11:36<1:03:11,  1.51s/it, lr: 1.0e-04 loss: 1.864e-01]
latex_v1:  16%|#6        | 495/3000 [11:36<1:03:11,  1.51s/it, lr: 1.0e-04 loss: 5.104e-01]
latex_v1:  16%|#6        | 495/3000 [11:36<1:03:11,  1.51s/it, lr: 1.0e-04 loss: 5.104e-01]
latex_v1:  17%|#6        | 496/3000 [11:36<54:09,  1.30s/it, lr: 1.0e-04 loss: 5.104e-01]  
latex_v1:  17%|#6        | 496/3000 [11:36<54:09,  1.30s/it, lr: 1.0e-04 loss: 5.104e-01]  
latex_v1:  17%|#6        | 496/3000 [11:38<54:09,  1.30s/it, lr: 1.0e-04 loss: 1.316e-01]
latex_v1:  17%|#6        | 496/3000 [11:38<54:09,  1.30s/it, lr: 1.0e-04 loss: 1.316e-01]
latex_v1:  17%|#6        | 497/3000 [11:38<1:01:16,  1.47s/it, lr: 1.0e-04 loss: 1.316e-01]
latex_v1:  17%|#6        | 497/3000 [11:38<1:01:16,  1.47s/it, lr: 1.0e-04 loss: 1.316e-01]
latex_v1:  17%|#6        | 497/3000 [11:39<1:01:16,  1.47s/it, lr: 1.0e-04 loss: 5.387e-01]
latex_v1:  17%|#6        | 497/3000 [11:39<1:01:16,  1.47s/it, lr: 1.0e-04 loss: 5.387e-01]
latex_v1:  17%|#6        | 498/3000 [11:39<52:22,  1.26s/it, lr: 1.0e-04 loss: 5.387e-01]  
latex_v1:  17%|#6        | 498/3000 [11:39<52:22,  1.26s/it, lr: 1.0e-04 loss: 5.387e-01]  
latex_v1:  17%|#6        | 498/3000 [11:41<52:22,  1.26s/it, lr: 1.0e-04 loss: 4.909e-01]
latex_v1:  17%|#6        | 498/3000 [11:41<52:22,  1.26s/it, lr: 1.0e-04 loss: 4.909e-01]
latex_v1:  17%|#6        | 499/3000 [11:41<1:00:13,  1.44s/it, lr: 1.0e-04 loss: 4.909e-01]
latex_v1:  17%|#6        | 499/3000 [11:41<1:00:13,  1.44s/it, lr: 1.0e-04 loss: 4.909e-01]
latex_v1:  17%|#6        | 499/3000 [11:42<1:00:13,  1.44s/it, lr: 1.0e-04 loss: 1.461e-01]
latex_v1:  17%|#6        | 499/3000 [11:42<1:00:13,  1.44s/it, lr: 1.0e-04 loss: 1.461e-01]
Saving at step 500
Saved checkpoint to /data/app/output/latex_v1/latex_v1_000000500.safetensors
Saved optimizer to /data/app/output/latex_v1/optimizer.pt

latex_v1:  17%|#6        | 500/3000 [11:43<1:00:12,  1.44s/it, lr: 1.0e-04 loss: 2.979e-01]
latex_v1:  17%|#6        | 500/3000 [11:43<1:00:12,  1.44s/it, lr: 1.0e-04 loss: 2.979e-01]
latex_v1:  17%|#6        | 501/3000 [11:43<47:35,  1.14s/it, lr: 1.0e-04 loss: 2.979e-01]  
latex_v1:  17%|#6        | 501/3000 [11:43<47:35,  1.14s/it, lr: 1.0e-04 loss: 2.979e-01]  
latex_v1:  17%|#6        | 501/3000 [11:44<47:35,  1.14s/it, lr: 1.0e-04 loss: 8.957e-01]
latex_v1:  17%|#6        | 501/3000 [11:44<47:35,  1.14s/it, lr: 1.0e-04 loss: 8.957e-01]
latex_v1:  17%|#6        | 502/3000 [11:44<47:46,  1.15s/it, lr: 1.0e-04 loss: 8.957e-01]
latex_v1:  17%|#6        | 502/3000 [11:44<47:46,  1.15s/it, lr: 1.0e-04 loss: 8.957e-01]
latex_v1:  17%|#6        | 502/3000 [11:45<47:46,  1.15s/it, lr: 1.0e-04 loss: 1.082e-01]
latex_v1:  17%|#6        | 502/3000 [11:45<47:46,  1.15s/it, lr: 1.0e-04 loss: 1.082e-01]
latex_v1:  17%|#6        | 503/3000 [11:45<43:18,  1.04s/it, lr: 1.0e-04 loss: 1.082e-01]
latex_v1:  17%|#6        | 503/3000 [11:45<43:18,  1.04s/it, lr: 1.0e-04 loss: 1.082e-01]
latex_v1:  17%|#6        | 503/3000 [11:47<43:18,  1.04s/it, lr: 1.0e-04 loss: 3.898e-01]
latex_v1:  17%|#6        | 503/3000 [11:47<43:18,  1.04s/it, lr: 1.0e-04 loss: 3.898e-01]
latex_v1:  17%|#6        | 504/3000 [11:47<48:42,  1.17s/it, lr: 1.0e-04 loss: 3.898e-01]
latex_v1:  17%|#6        | 504/3000 [11:47<48:42,  1.17s/it, lr: 1.0e-04 loss: 3.898e-01]
latex_v1:  17%|#6        | 504/3000 [11:47<48:42,  1.17s/it, lr: 1.0e-04 loss: 6.050e-01]
latex_v1:  17%|#6        | 504/3000 [11:47<48:42,  1.17s/it, lr: 1.0e-04 loss: 6.050e-01]
latex_v1:  17%|#6        | 505/3000 [11:47<43:30,  1.05s/it, lr: 1.0e-04 loss: 6.050e-01]
latex_v1:  17%|#6        | 505/3000 [11:47<43:30,  1.05s/it, lr: 1.0e-04 loss: 6.050e-01]
latex_v1:  17%|#6        | 505/3000 [11:48<43:30,  1.05s/it, lr: 1.0e-04 loss: 2.566e-01]
latex_v1:  17%|#6        | 505/3000 [11:48<43:30,  1.05s/it, lr: 1.0e-04 loss: 2.566e-01]
latex_v1:  17%|#6        | 506/3000 [11:48<39:53,  1.04it/s, lr: 1.0e-04 loss: 2.566e-01]
latex_v1:  17%|#6        | 506/3000 [11:48<39:53,  1.04it/s, lr: 1.0e-04 loss: 2.566e-01]
latex_v1:  17%|#6        | 506/3000 [11:49<39:53,  1.04it/s, lr: 1.0e-04 loss: 9.612e-02]
latex_v1:  17%|#6        | 506/3000 [11:49<39:53,  1.04it/s, lr: 1.0e-04 loss: 9.612e-02]
latex_v1:  17%|#6        | 507/3000 [11:49<37:22,  1.11it/s, lr: 1.0e-04 loss: 9.612e-02]
latex_v1:  17%|#6        | 507/3000 [11:49<37:22,  1.11it/s, lr: 1.0e-04 loss: 9.612e-02]
latex_v1:  17%|#6        | 507/3000 [11:50<37:22,  1.11it/s, lr: 1.0e-04 loss: 2.631e-02]
latex_v1:  17%|#6        | 507/3000 [11:50<37:22,  1.11it/s, lr: 1.0e-04 loss: 2.631e-02]
latex_v1:  17%|#6        | 508/3000 [11:50<35:40,  1.16it/s, lr: 1.0e-04 loss: 2.631e-02]
latex_v1:  17%|#6        | 508/3000 [11:50<35:40,  1.16it/s, lr: 1.0e-04 loss: 2.631e-02]
latex_v1:  17%|#6        | 508/3000 [11:53<35:40,  1.16it/s, lr: 1.0e-04 loss: 1.287e-01]
latex_v1:  17%|#6        | 508/3000 [11:53<35:40,  1.16it/s, lr: 1.0e-04 loss: 1.287e-01]
latex_v1:  17%|#6        | 509/3000 [11:53<1:00:22,  1.45s/it, lr: 1.0e-04 loss: 1.287e-01]
latex_v1:  17%|#6        | 509/3000 [11:53<1:00:22,  1.45s/it, lr: 1.0e-04 loss: 1.287e-01]
latex_v1:  17%|#6        | 509/3000 [11:54<1:00:22,  1.45s/it, lr: 1.0e-04 loss: 4.188e-01]
latex_v1:  17%|#6        | 509/3000 [11:54<1:00:22,  1.45s/it, lr: 1.0e-04 loss: 4.188e-01]
latex_v1:  17%|#7        | 510/3000 [11:55<1:00:20,  1.45s/it, lr: 1.0e-04 loss: 4.050e-01]
latex_v1:  17%|#7        | 510/3000 [11:55<1:00:20,  1.45s/it, lr: 1.0e-04 loss: 4.050e-01]
latex_v1:  17%|#7        | 511/3000 [11:55<43:59,  1.06s/it, lr: 1.0e-04 loss: 4.050e-01]  
latex_v1:  17%|#7        | 511/3000 [11:55<43:59,  1.06s/it, lr: 1.0e-04 loss: 4.050e-01]  
latex_v1:  17%|#7        | 511/3000 [11:56<43:59,  1.06s/it, lr: 1.0e-04 loss: 3.446e-01]
latex_v1:  17%|#7        | 511/3000 [11:56<43:59,  1.06s/it, lr: 1.0e-04 loss: 3.446e-01]
latex_v1:  17%|#7        | 512/3000 [11:56<46:43,  1.13s/it, lr: 1.0e-04 loss: 3.446e-01]
latex_v1:  17%|#7        | 512/3000 [11:56<46:43,  1.13s/it, lr: 1.0e-04 loss: 3.446e-01]
latex_v1:  17%|#7        | 512/3000 [11:58<46:43,  1.13s/it, lr: 1.0e-04 loss: 6.104e-01]
latex_v1:  17%|#7        | 512/3000 [11:58<46:43,  1.13s/it, lr: 1.0e-04 loss: 6.104e-01]
latex_v1:  17%|#7        | 513/3000 [11:58<51:26,  1.24s/it, lr: 1.0e-04 loss: 6.104e-01]
latex_v1:  17%|#7        | 513/3000 [11:58<51:26,  1.24s/it, lr: 1.0e-04 loss: 6.104e-01]
latex_v1:  17%|#7        | 513/3000 [11:59<51:26,  1.24s/it, lr: 1.0e-04 loss: 8.558e-02]
latex_v1:  17%|#7        | 513/3000 [11:59<51:26,  1.24s/it, lr: 1.0e-04 loss: 8.558e-02]
latex_v1:  17%|#7        | 514/3000 [11:59<46:06,  1.11s/it, lr: 1.0e-04 loss: 8.558e-02]
latex_v1:  17%|#7        | 514/3000 [11:59<46:06,  1.11s/it, lr: 1.0e-04 loss: 8.558e-02]
latex_v1:  17%|#7        | 514/3000 [12:00<46:06,  1.11s/it, lr: 1.0e-04 loss: 5.329e-01]
latex_v1:  17%|#7        | 514/3000 [12:00<46:06,  1.11s/it, lr: 1.0e-04 loss: 5.329e-01]
latex_v1:  17%|#7        | 515/3000 [12:00<51:13,  1.24s/it, lr: 1.0e-04 loss: 5.329e-01]
latex_v1:  17%|#7        | 515/3000 [12:00<51:13,  1.24s/it, lr: 1.0e-04 loss: 5.329e-01]
latex_v1:  17%|#7        | 515/3000 [12:01<51:13,  1.24s/it, lr: 1.0e-04 loss: 5.179e-01]
latex_v1:  17%|#7        | 515/3000 [12:01<51:13,  1.24s/it, lr: 1.0e-04 loss: 5.179e-01]
latex_v1:  17%|#7        | 516/3000 [12:01<45:28,  1.10s/it, lr: 1.0e-04 loss: 5.179e-01]
latex_v1:  17%|#7        | 516/3000 [12:01<45:28,  1.10s/it, lr: 1.0e-04 loss: 5.179e-01]
latex_v1:  17%|#7        | 516/3000 [12:02<45:28,  1.10s/it, lr: 1.0e-04 loss: 2.635e-01]
latex_v1:  17%|#7        | 516/3000 [12:02<45:28,  1.10s/it, lr: 1.0e-04 loss: 2.635e-01]
latex_v1:  17%|#7        | 517/3000 [12:02<48:25,  1.17s/it, lr: 1.0e-04 loss: 2.635e-01]
latex_v1:  17%|#7        | 517/3000 [12:02<48:25,  1.17s/it, lr: 1.0e-04 loss: 2.635e-01]
latex_v1:  17%|#7        | 517/3000 [12:03<48:25,  1.17s/it, lr: 1.0e-04 loss: 4.546e-01]
latex_v1:  17%|#7        | 517/3000 [12:03<48:25,  1.17s/it, lr: 1.0e-04 loss: 4.546e-01]
latex_v1:  17%|#7        | 518/3000 [12:03<43:33,  1.05s/it, lr: 1.0e-04 loss: 4.546e-01]
latex_v1:  17%|#7        | 518/3000 [12:03<43:33,  1.05s/it, lr: 1.0e-04 loss: 4.546e-01]
latex_v1:  17%|#7        | 518/3000 [12:04<43:33,  1.05s/it, lr: 1.0e-04 loss: 4.235e-01]
latex_v1:  17%|#7        | 518/3000 [12:04<43:33,  1.05s/it, lr: 1.0e-04 loss: 4.235e-01]
latex_v1:  17%|#7        | 519/3000 [12:04<43:45,  1.06s/it, lr: 1.0e-04 loss: 4.235e-01]
latex_v1:  17%|#7        | 519/3000 [12:04<43:45,  1.06s/it, lr: 1.0e-04 loss: 4.235e-01]
latex_v1:  17%|#7        | 519/3000 [12:05<43:45,  1.06s/it, lr: 1.0e-04 loss: 3.189e-01]
latex_v1:  17%|#7        | 519/3000 [12:05<43:45,  1.06s/it, lr: 1.0e-04 loss: 3.189e-01]
latex_v1:  17%|#7        | 520/3000 [12:06<43:44,  1.06s/it, lr: 1.0e-04 loss: 3.667e-01]
latex_v1:  17%|#7        | 520/3000 [12:06<43:44,  1.06s/it, lr: 1.0e-04 loss: 3.667e-01]
latex_v1:  17%|#7        | 521/3000 [12:06<37:10,  1.11it/s, lr: 1.0e-04 loss: 3.667e-01]
latex_v1:  17%|#7        | 521/3000 [12:06<37:10,  1.11it/s, lr: 1.0e-04 loss: 3.667e-01]
latex_v1:  17%|#7        | 521/3000 [12:08<37:10,  1.11it/s, lr: 1.0e-04 loss: 7.012e-02]
latex_v1:  17%|#7        | 521/3000 [12:08<37:10,  1.11it/s, lr: 1.0e-04 loss: 7.012e-02]
latex_v1:  17%|#7        | 522/3000 [12:08<47:11,  1.14s/it, lr: 1.0e-04 loss: 7.012e-02]
latex_v1:  17%|#7        | 522/3000 [12:08<47:11,  1.14s/it, lr: 1.0e-04 loss: 7.012e-02]
latex_v1:  17%|#7        | 522/3000 [12:09<47:11,  1.14s/it, lr: 1.0e-04 loss: 4.688e-01]
latex_v1:  17%|#7        | 522/3000 [12:09<47:11,  1.14s/it, lr: 1.0e-04 loss: 4.688e-01]
latex_v1:  17%|#7        | 523/3000 [12:09<43:08,  1.05s/it, lr: 1.0e-04 loss: 4.688e-01]
latex_v1:  17%|#7        | 523/3000 [12:09<43:08,  1.05s/it, lr: 1.0e-04 loss: 4.688e-01]
latex_v1:  17%|#7        | 523/3000 [12:10<43:08,  1.05s/it, lr: 1.0e-04 loss: 2.346e-01]
latex_v1:  17%|#7        | 523/3000 [12:10<43:08,  1.05s/it, lr: 1.0e-04 loss: 2.346e-01]
latex_v1:  17%|#7        | 524/3000 [12:10<39:57,  1.03it/s, lr: 1.0e-04 loss: 2.346e-01]
latex_v1:  17%|#7        | 524/3000 [12:10<39:57,  1.03it/s, lr: 1.0e-04 loss: 2.346e-01]
latex_v1:  17%|#7        | 524/3000 [12:11<39:57,  1.03it/s, lr: 1.0e-04 loss: 4.892e-01]
latex_v1:  17%|#7        | 524/3000 [12:11<39:57,  1.03it/s, lr: 1.0e-04 loss: 4.892e-01]
latex_v1:  18%|#7        | 525/3000 [12:11<48:51,  1.18s/it, lr: 1.0e-04 loss: 4.892e-01]
latex_v1:  18%|#7        | 525/3000 [12:11<48:51,  1.18s/it, lr: 1.0e-04 loss: 4.892e-01]
latex_v1:  18%|#7        | 525/3000 [12:12<48:51,  1.18s/it, lr: 1.0e-04 loss: 4.797e-01]
latex_v1:  18%|#7        | 525/3000 [12:12<48:51,  1.18s/it, lr: 1.0e-04 loss: 4.797e-01]
latex_v1:  18%|#7        | 526/3000 [12:12<47:22,  1.15s/it, lr: 1.0e-04 loss: 4.797e-01]
latex_v1:  18%|#7        | 526/3000 [12:12<47:22,  1.15s/it, lr: 1.0e-04 loss: 4.797e-01]
latex_v1:  18%|#7        | 526/3000 [12:14<47:22,  1.15s/it, lr: 1.0e-04 loss: 3.641e-01]
latex_v1:  18%|#7        | 526/3000 [12:14<47:22,  1.15s/it, lr: 1.0e-04 loss: 3.641e-01]
latex_v1:  18%|#7        | 527/3000 [12:14<49:19,  1.20s/it, lr: 1.0e-04 loss: 3.641e-01]
latex_v1:  18%|#7        | 527/3000 [12:14<49:19,  1.20s/it, lr: 1.0e-04 loss: 3.641e-01]
latex_v1:  18%|#7        | 527/3000 [12:16<49:19,  1.20s/it, lr: 1.0e-04 loss: 8.807e-02]
latex_v1:  18%|#7        | 527/3000 [12:16<49:19,  1.20s/it, lr: 1.0e-04 loss: 8.807e-02]
latex_v1:  18%|#7        | 528/3000 [12:16<1:01:24,  1.49s/it, lr: 1.0e-04 loss: 8.807e-02]
latex_v1:  18%|#7        | 528/3000 [12:16<1:01:24,  1.49s/it, lr: 1.0e-04 loss: 8.807e-02]
latex_v1:  18%|#7        | 528/3000 [12:17<1:01:24,  1.49s/it, lr: 1.0e-04 loss: 5.927e-01]
latex_v1:  18%|#7        | 528/3000 [12:17<1:01:24,  1.49s/it, lr: 1.0e-04 loss: 5.927e-01]
latex_v1:  18%|#7        | 529/3000 [12:17<1:01:02,  1.48s/it, lr: 1.0e-04 loss: 5.927e-01]
latex_v1:  18%|#7        | 529/3000 [12:17<1:01:02,  1.48s/it, lr: 1.0e-04 loss: 5.927e-01]
latex_v1:  18%|#7        | 529/3000 [12:18<1:01:02,  1.48s/it, lr: 1.0e-04 loss: 7.542e-01]
latex_v1:  18%|#7        | 529/3000 [12:18<1:01:02,  1.48s/it, lr: 1.0e-04 loss: 7.542e-01]
latex_v1:  18%|#7        | 530/3000 [12:19<1:01:01,  1.48s/it, lr: 1.0e-04 loss: 6.256e-01]
latex_v1:  18%|#7        | 530/3000 [12:19<1:01:01,  1.48s/it, lr: 1.0e-04 loss: 6.256e-01]
latex_v1:  18%|#7        | 531/3000 [12:19<40:04,  1.03it/s, lr: 1.0e-04 loss: 6.256e-01]  
latex_v1:  18%|#7        | 531/3000 [12:19<40:04,  1.03it/s, lr: 1.0e-04 loss: 6.256e-01]  
latex_v1:  18%|#7        | 531/3000 [12:20<40:04,  1.03it/s, lr: 1.0e-04 loss: 4.451e-01]
latex_v1:  18%|#7        | 531/3000 [12:20<40:04,  1.03it/s, lr: 1.0e-04 loss: 4.451e-01]
latex_v1:  18%|#7        | 532/3000 [12:20<37:53,  1.09it/s, lr: 1.0e-04 loss: 4.451e-01]
latex_v1:  18%|#7        | 532/3000 [12:20<37:53,  1.09it/s, lr: 1.0e-04 loss: 4.451e-01]
latex_v1:  18%|#7        | 532/3000 [12:20<37:53,  1.09it/s, lr: 1.0e-04 loss: 5.133e-01]
latex_v1:  18%|#7        | 532/3000 [12:20<37:53,  1.09it/s, lr: 1.0e-04 loss: 5.133e-01]
latex_v1:  18%|#7        | 533/3000 [12:20<35:41,  1.15it/s, lr: 1.0e-04 loss: 5.133e-01]
latex_v1:  18%|#7        | 533/3000 [12:20<35:41,  1.15it/s, lr: 1.0e-04 loss: 5.133e-01]
latex_v1:  18%|#7        | 533/3000 [12:22<35:41,  1.15it/s, lr: 1.0e-04 loss: 1.984e-01]
latex_v1:  18%|#7        | 533/3000 [12:22<35:41,  1.15it/s, lr: 1.0e-04 loss: 1.984e-01]
latex_v1:  18%|#7        | 534/3000 [12:22<46:57,  1.14s/it, lr: 1.0e-04 loss: 1.984e-01]
latex_v1:  18%|#7        | 534/3000 [12:22<46:57,  1.14s/it, lr: 1.0e-04 loss: 1.984e-01]
latex_v1:  18%|#7        | 534/3000 [12:24<46:57,  1.14s/it, lr: 1.0e-04 loss: 2.537e-01]
latex_v1:  18%|#7        | 534/3000 [12:24<46:57,  1.14s/it, lr: 1.0e-04 loss: 2.537e-01]
latex_v1:  18%|#7        | 535/3000 [12:24<50:06,  1.22s/it, lr: 1.0e-04 loss: 2.537e-01]
latex_v1:  18%|#7        | 535/3000 [12:24<50:06,  1.22s/it, lr: 1.0e-04 loss: 2.537e-01]
latex_v1:  18%|#7        | 535/3000 [12:24<50:06,  1.22s/it, lr: 1.0e-04 loss: 2.360e-01]
latex_v1:  18%|#7        | 535/3000 [12:24<50:06,  1.22s/it, lr: 1.0e-04 loss: 2.360e-01]
latex_v1:  18%|#7        | 536/3000 [12:24<44:28,  1.08s/it, lr: 1.0e-04 loss: 2.360e-01]
latex_v1:  18%|#7        | 536/3000 [12:24<44:28,  1.08s/it, lr: 1.0e-04 loss: 2.360e-01]
latex_v1:  18%|#7        | 536/3000 [12:26<44:28,  1.08s/it, lr: 1.0e-04 loss: 3.574e-01]
latex_v1:  18%|#7        | 536/3000 [12:26<44:28,  1.08s/it, lr: 1.0e-04 loss: 3.574e-01]
latex_v1:  18%|#7        | 537/3000 [12:26<48:18,  1.18s/it, lr: 1.0e-04 loss: 3.574e-01]
latex_v1:  18%|#7        | 537/3000 [12:26<48:18,  1.18s/it, lr: 1.0e-04 loss: 3.574e-01]
latex_v1:  18%|#7        | 537/3000 [12:27<48:18,  1.18s/it, lr: 1.0e-04 loss: 3.408e-01]
latex_v1:  18%|#7        | 537/3000 [12:27<48:18,  1.18s/it, lr: 1.0e-04 loss: 3.408e-01]
latex_v1:  18%|#7        | 538/3000 [12:27<43:16,  1.05s/it, lr: 1.0e-04 loss: 3.408e-01]
latex_v1:  18%|#7        | 538/3000 [12:27<43:16,  1.05s/it, lr: 1.0e-04 loss: 3.408e-01]
latex_v1:  18%|#7        | 538/3000 [12:29<43:16,  1.05s/it, lr: 1.0e-04 loss: 2.819e-01]
latex_v1:  18%|#7        | 538/3000 [12:29<43:16,  1.05s/it, lr: 1.0e-04 loss: 2.819e-01]
latex_v1:  18%|#7        | 539/3000 [12:29<1:04:31,  1.57s/it, lr: 1.0e-04 loss: 2.819e-01]
latex_v1:  18%|#7        | 539/3000 [12:29<1:04:31,  1.57s/it, lr: 1.0e-04 loss: 2.819e-01]
latex_v1:  18%|#7        | 539/3000 [12:32<1:04:31,  1.57s/it, lr: 1.0e-04 loss: 4.611e-02]
latex_v1:  18%|#7        | 539/3000 [12:32<1:04:31,  1.57s/it, lr: 1.0e-04 loss: 4.611e-02]
latex_v1:  18%|#8        | 540/3000 [12:34<1:04:30,  1.57s/it, lr: 1.0e-04 loss: 5.743e-01]
latex_v1:  18%|#8        | 540/3000 [12:34<1:04:30,  1.57s/it, lr: 1.0e-04 loss: 5.743e-01]
latex_v1:  18%|#8        | 541/3000 [12:34<51:00,  1.24s/it, lr: 1.0e-04 loss: 5.743e-01]  
latex_v1:  18%|#8        | 541/3000 [12:34<51:00,  1.24s/it, lr: 1.0e-04 loss: 5.743e-01]  
latex_v1:  18%|#8        | 541/3000 [12:35<51:00,  1.24s/it, lr: 1.0e-04 loss: 6.226e-01]
latex_v1:  18%|#8        | 541/3000 [12:35<51:00,  1.24s/it, lr: 1.0e-04 loss: 6.226e-01]
latex_v1:  18%|#8        | 542/3000 [12:35<52:13,  1.27s/it, lr: 1.0e-04 loss: 6.226e-01]
latex_v1:  18%|#8        | 542/3000 [12:35<52:13,  1.27s/it, lr: 1.0e-04 loss: 6.226e-01]
latex_v1:  18%|#8        | 542/3000 [12:36<52:13,  1.27s/it, lr: 1.0e-04 loss: 8.334e-02]
latex_v1:  18%|#8        | 542/3000 [12:36<52:13,  1.27s/it, lr: 1.0e-04 loss: 8.334e-02]
latex_v1:  18%|#8        | 543/3000 [12:36<46:33,  1.14s/it, lr: 1.0e-04 loss: 8.334e-02]
latex_v1:  18%|#8        | 543/3000 [12:36<46:33,  1.14s/it, lr: 1.0e-04 loss: 8.334e-02]
latex_v1:  18%|#8        | 543/3000 [12:38<46:33,  1.14s/it, lr: 1.0e-04 loss: 2.007e-02]
latex_v1:  18%|#8        | 543/3000 [12:38<46:33,  1.14s/it, lr: 1.0e-04 loss: 2.007e-02]
latex_v1:  18%|#8        | 544/3000 [12:38<50:54,  1.24s/it, lr: 1.0e-04 loss: 2.007e-02]
latex_v1:  18%|#8        | 544/3000 [12:38<50:54,  1.24s/it, lr: 1.0e-04 loss: 2.007e-02]
latex_v1:  18%|#8        | 544/3000 [12:40<50:54,  1.24s/it, lr: 1.0e-04 loss: 3.952e-01]
latex_v1:  18%|#8        | 544/3000 [12:40<50:54,  1.24s/it, lr: 1.0e-04 loss: 3.952e-01]
latex_v1:  18%|#8        | 545/3000 [12:40<58:14,  1.42s/it, lr: 1.0e-04 loss: 3.952e-01]
latex_v1:  18%|#8        | 545/3000 [12:40<58:14,  1.42s/it, lr: 1.0e-04 loss: 3.952e-01]
latex_v1:  18%|#8        | 545/3000 [12:40<58:14,  1.42s/it, lr: 1.0e-04 loss: 2.257e-01]
latex_v1:  18%|#8        | 545/3000 [12:40<58:14,  1.42s/it, lr: 1.0e-04 loss: 2.257e-01]
latex_v1:  18%|#8        | 546/3000 [12:40<50:20,  1.23s/it, lr: 1.0e-04 loss: 2.257e-01]
latex_v1:  18%|#8        | 546/3000 [12:40<50:20,  1.23s/it, lr: 1.0e-04 loss: 2.257e-01]
latex_v1:  18%|#8        | 546/3000 [12:43<50:20,  1.23s/it, lr: 1.0e-04 loss: 1.629e-01]
latex_v1:  18%|#8        | 546/3000 [12:43<50:20,  1.23s/it, lr: 1.0e-04 loss: 1.629e-01]
latex_v1:  18%|#8        | 547/3000 [12:43<1:09:35,  1.70s/it, lr: 1.0e-04 loss: 1.629e-01]
latex_v1:  18%|#8        | 547/3000 [12:43<1:09:35,  1.70s/it, lr: 1.0e-04 loss: 1.629e-01]
latex_v1:  18%|#8        | 547/3000 [12:44<1:09:35,  1.70s/it, lr: 1.0e-04 loss: 7.143e-01]
latex_v1:  18%|#8        | 547/3000 [12:44<1:09:35,  1.70s/it, lr: 1.0e-04 loss: 7.143e-01]
latex_v1:  18%|#8        | 548/3000 [12:44<58:09,  1.42s/it, lr: 1.0e-04 loss: 7.143e-01]  
latex_v1:  18%|#8        | 548/3000 [12:44<58:09,  1.42s/it, lr: 1.0e-04 loss: 7.143e-01]  
latex_v1:  18%|#8        | 548/3000 [12:46<58:09,  1.42s/it, lr: 1.0e-04 loss: 5.174e-01]
latex_v1:  18%|#8        | 548/3000 [12:46<58:09,  1.42s/it, lr: 1.0e-04 loss: 5.174e-01]
latex_v1:  18%|#8        | 549/3000 [12:46<1:03:43,  1.56s/it, lr: 1.0e-04 loss: 5.174e-01]
latex_v1:  18%|#8        | 549/3000 [12:46<1:03:43,  1.56s/it, lr: 1.0e-04 loss: 5.174e-01]
latex_v1:  18%|#8        | 549/3000 [12:47<1:03:43,  1.56s/it, lr: 1.0e-04 loss: 2.471e-01]
latex_v1:  18%|#8        | 549/3000 [12:47<1:03:43,  1.56s/it, lr: 1.0e-04 loss: 2.471e-01]
latex_v1:  18%|#8        | 550/3000 [12:50<1:03:41,  1.56s/it, lr: 1.0e-04 loss: 2.381e-01]
latex_v1:  18%|#8        | 550/3000 [12:50<1:03:41,  1.56s/it, lr: 1.0e-04 loss: 2.381e-01]
latex_v1:  18%|#8        | 551/3000 [12:50<1:00:59,  1.49s/it, lr: 1.0e-04 loss: 2.381e-01]
latex_v1:  18%|#8        | 551/3000 [12:50<1:00:59,  1.49s/it, lr: 1.0e-04 loss: 2.381e-01]
latex_v1:  18%|#8        | 551/3000 [12:53<1:00:59,  1.49s/it, lr: 1.0e-04 loss: 2.620e-01]
latex_v1:  18%|#8        | 551/3000 [12:53<1:00:59,  1.49s/it, lr: 1.0e-04 loss: 2.620e-01]
latex_v1:  18%|#8        | 552/3000 [12:53<1:15:09,  1.84s/it, lr: 1.0e-04 loss: 2.620e-01]
latex_v1:  18%|#8        | 552/3000 [12:53<1:15:09,  1.84s/it, lr: 1.0e-04 loss: 2.620e-01]
latex_v1:  18%|#8        | 552/3000 [12:55<1:15:09,  1.84s/it, lr: 1.0e-04 loss: 8.117e-03]
latex_v1:  18%|#8        | 552/3000 [12:55<1:15:09,  1.84s/it, lr: 1.0e-04 loss: 8.117e-03]
latex_v1:  18%|#8        | 553/3000 [12:55<1:11:54,  1.76s/it, lr: 1.0e-04 loss: 8.117e-03]
latex_v1:  18%|#8        | 553/3000 [12:55<1:11:54,  1.76s/it, lr: 1.0e-04 loss: 8.117e-03]
latex_v1:  18%|#8        | 553/3000 [12:56<1:11:54,  1.76s/it, lr: 1.0e-04 loss: 6.104e-01]
latex_v1:  18%|#8        | 553/3000 [12:56<1:11:54,  1.76s/it, lr: 1.0e-04 loss: 6.104e-01]
latex_v1:  18%|#8        | 554/3000 [12:56<1:11:02,  1.74s/it, lr: 1.0e-04 loss: 6.104e-01]
latex_v1:  18%|#8        | 554/3000 [12:56<1:11:02,  1.74s/it, lr: 1.0e-04 loss: 6.104e-01]
latex_v1:  18%|#8        | 554/3000 [12:58<1:11:02,  1.74s/it, lr: 1.0e-04 loss: 1.420e-01]
latex_v1:  18%|#8        | 554/3000 [12:58<1:11:02,  1.74s/it, lr: 1.0e-04 loss: 1.420e-01]
latex_v1:  18%|#8        | 555/3000 [12:58<1:07:36,  1.66s/it, lr: 1.0e-04 loss: 1.420e-01]
latex_v1:  18%|#8        | 555/3000 [12:58<1:07:36,  1.66s/it, lr: 1.0e-04 loss: 1.420e-01]
latex_v1:  18%|#8        | 555/3000 [12:59<1:07:36,  1.66s/it, lr: 1.0e-04 loss: 1.400e-01]
latex_v1:  18%|#8        | 555/3000 [12:59<1:07:36,  1.66s/it, lr: 1.0e-04 loss: 1.400e-01]
latex_v1:  19%|#8        | 556/3000 [12:59<1:06:35,  1.63s/it, lr: 1.0e-04 loss: 1.400e-01]
latex_v1:  19%|#8        | 556/3000 [12:59<1:06:35,  1.63s/it, lr: 1.0e-04 loss: 1.400e-01]
latex_v1:  19%|#8        | 556/3000 [13:00<1:06:35,  1.63s/it, lr: 1.0e-04 loss: 1.066e-01]
latex_v1:  19%|#8        | 556/3000 [13:00<1:06:35,  1.63s/it, lr: 1.0e-04 loss: 1.066e-01]
latex_v1:  19%|#8        | 557/3000 [13:00<56:03,  1.38s/it, lr: 1.0e-04 loss: 1.066e-01]  
latex_v1:  19%|#8        | 557/3000 [13:00<56:03,  1.38s/it, lr: 1.0e-04 loss: 1.066e-01]  
latex_v1:  19%|#8        | 557/3000 [13:01<56:03,  1.38s/it, lr: 1.0e-04 loss: 3.666e-01]
latex_v1:  19%|#8        | 557/3000 [13:01<56:03,  1.38s/it, lr: 1.0e-04 loss: 3.666e-01]
latex_v1:  19%|#8        | 558/3000 [13:01<51:45,  1.27s/it, lr: 1.0e-04 loss: 3.666e-01]
latex_v1:  19%|#8        | 558/3000 [13:01<51:45,  1.27s/it, lr: 1.0e-04 loss: 3.666e-01]
latex_v1:  19%|#8        | 558/3000 [13:02<51:45,  1.27s/it, lr: 1.0e-04 loss: 1.032e-01]
latex_v1:  19%|#8        | 558/3000 [13:02<51:45,  1.27s/it, lr: 1.0e-04 loss: 1.032e-01]
latex_v1:  19%|#8        | 559/3000 [13:02<49:01,  1.21s/it, lr: 1.0e-04 loss: 1.032e-01]
latex_v1:  19%|#8        | 559/3000 [13:02<49:01,  1.21s/it, lr: 1.0e-04 loss: 1.032e-01]
latex_v1:  19%|#8        | 559/3000 [13:03<49:01,  1.21s/it, lr: 1.0e-04 loss: 5.719e-01]
latex_v1:  19%|#8        | 559/3000 [13:03<49:01,  1.21s/it, lr: 1.0e-04 loss: 5.719e-01]
latex_v1:  19%|#8        | 560/3000 [13:05<49:00,  1.21s/it, lr: 1.0e-04 loss: 5.390e-01]
latex_v1:  19%|#8        | 560/3000 [13:05<49:00,  1.21s/it, lr: 1.0e-04 loss: 5.390e-01]
latex_v1:  19%|#8        | 561/3000 [13:05<39:45,  1.02it/s, lr: 1.0e-04 loss: 5.390e-01]
latex_v1:  19%|#8        | 561/3000 [13:05<39:45,  1.02it/s, lr: 1.0e-04 loss: 5.390e-01]
latex_v1:  19%|#8        | 561/3000 [13:05<39:45,  1.02it/s, lr: 1.0e-04 loss: 1.448e-01]
latex_v1:  19%|#8        | 561/3000 [13:05<39:45,  1.02it/s, lr: 1.0e-04 loss: 1.448e-01]
latex_v1:  19%|#8        | 562/3000 [13:05<37:36,  1.08it/s, lr: 1.0e-04 loss: 1.448e-01]
latex_v1:  19%|#8        | 562/3000 [13:05<37:36,  1.08it/s, lr: 1.0e-04 loss: 1.448e-01]
latex_v1:  19%|#8        | 562/3000 [13:07<37:36,  1.08it/s, lr: 1.0e-04 loss: 4.481e-01]
latex_v1:  19%|#8        | 562/3000 [13:07<37:36,  1.08it/s, lr: 1.0e-04 loss: 4.481e-01]
latex_v1:  19%|#8        | 563/3000 [13:07<42:17,  1.04s/it, lr: 1.0e-04 loss: 4.481e-01]
latex_v1:  19%|#8        | 563/3000 [13:07<42:17,  1.04s/it, lr: 1.0e-04 loss: 4.481e-01]
latex_v1:  19%|#8        | 563/3000 [13:07<42:17,  1.04s/it, lr: 1.0e-04 loss: 6.136e-01]
latex_v1:  19%|#8        | 563/3000 [13:07<42:17,  1.04s/it, lr: 1.0e-04 loss: 6.136e-01]
latex_v1:  19%|#8        | 564/3000 [13:07<39:06,  1.04it/s, lr: 1.0e-04 loss: 6.136e-01]
latex_v1:  19%|#8        | 564/3000 [13:07<39:06,  1.04it/s, lr: 1.0e-04 loss: 6.136e-01]
latex_v1:  19%|#8        | 564/3000 [13:08<39:06,  1.04it/s, lr: 1.0e-04 loss: 2.604e-01]
latex_v1:  19%|#8        | 564/3000 [13:08<39:06,  1.04it/s, lr: 1.0e-04 loss: 2.604e-01]
latex_v1:  19%|#8        | 565/3000 [13:08<36:36,  1.11it/s, lr: 1.0e-04 loss: 2.604e-01]
latex_v1:  19%|#8        | 565/3000 [13:08<36:36,  1.11it/s, lr: 1.0e-04 loss: 2.604e-01]
latex_v1:  19%|#8        | 565/3000 [13:09<36:36,  1.11it/s, lr: 1.0e-04 loss: 8.874e-01]
latex_v1:  19%|#8        | 565/3000 [13:09<36:36,  1.11it/s, lr: 1.0e-04 loss: 8.874e-01]
latex_v1:  19%|#8        | 566/3000 [13:09<39:11,  1.04it/s, lr: 1.0e-04 loss: 8.874e-01]
latex_v1:  19%|#8        | 566/3000 [13:09<39:11,  1.04it/s, lr: 1.0e-04 loss: 8.874e-01]
latex_v1:  19%|#8        | 566/3000 [13:11<39:11,  1.04it/s, lr: 1.0e-04 loss: 4.133e-01]
latex_v1:  19%|#8        | 566/3000 [13:11<39:11,  1.04it/s, lr: 1.0e-04 loss: 4.133e-01]
latex_v1:  19%|#8        | 567/3000 [13:11<48:34,  1.20s/it, lr: 1.0e-04 loss: 4.133e-01]
latex_v1:  19%|#8        | 567/3000 [13:11<48:34,  1.20s/it, lr: 1.0e-04 loss: 4.133e-01]
latex_v1:  19%|#8        | 567/3000 [13:13<48:34,  1.20s/it, lr: 1.0e-04 loss: 1.348e-01]
latex_v1:  19%|#8        | 567/3000 [13:13<48:34,  1.20s/it, lr: 1.0e-04 loss: 1.348e-01]
latex_v1:  19%|#8        | 568/3000 [13:13<52:53,  1.31s/it, lr: 1.0e-04 loss: 1.348e-01]
latex_v1:  19%|#8        | 568/3000 [13:13<52:53,  1.31s/it, lr: 1.0e-04 loss: 1.348e-01]
latex_v1:  19%|#8        | 568/3000 [13:14<52:53,  1.31s/it, lr: 1.0e-04 loss: 6.772e-01]
latex_v1:  19%|#8        | 568/3000 [13:14<52:53,  1.31s/it, lr: 1.0e-04 loss: 6.772e-01]
latex_v1:  19%|#8        | 569/3000 [13:14<51:23,  1.27s/it, lr: 1.0e-04 loss: 6.772e-01]
latex_v1:  19%|#8        | 569/3000 [13:14<51:23,  1.27s/it, lr: 1.0e-04 loss: 6.772e-01]
latex_v1:  19%|#8        | 569/3000 [13:15<51:23,  1.27s/it, lr: 1.0e-04 loss: 6.373e-01]
latex_v1:  19%|#8        | 569/3000 [13:15<51:23,  1.27s/it, lr: 1.0e-04 loss: 6.373e-01]
latex_v1:  19%|#9        | 570/3000 [13:16<51:22,  1.27s/it, lr: 1.0e-04 loss: 5.694e-01]
latex_v1:  19%|#9        | 570/3000 [13:16<51:22,  1.27s/it, lr: 1.0e-04 loss: 5.694e-01]
latex_v1:  19%|#9        | 571/3000 [13:16<41:17,  1.02s/it, lr: 1.0e-04 loss: 5.694e-01]
latex_v1:  19%|#9        | 571/3000 [13:16<41:17,  1.02s/it, lr: 1.0e-04 loss: 5.694e-01]
latex_v1:  19%|#9        | 571/3000 [13:18<41:17,  1.02s/it, lr: 1.0e-04 loss: 6.130e-02]
latex_v1:  19%|#9        | 571/3000 [13:18<41:17,  1.02s/it, lr: 1.0e-04 loss: 6.130e-02]
latex_v1:  19%|#9        | 572/3000 [13:18<49:46,  1.23s/it, lr: 1.0e-04 loss: 6.130e-02]
latex_v1:  19%|#9        | 572/3000 [13:18<49:46,  1.23s/it, lr: 1.0e-04 loss: 6.130e-02]
latex_v1:  19%|#9        | 572/3000 [13:19<49:46,  1.23s/it, lr: 1.0e-04 loss: 7.647e-01]
latex_v1:  19%|#9        | 572/3000 [13:19<49:46,  1.23s/it, lr: 1.0e-04 loss: 7.647e-01]
latex_v1:  19%|#9        | 573/3000 [13:19<49:09,  1.22s/it, lr: 1.0e-04 loss: 7.647e-01]
latex_v1:  19%|#9        | 573/3000 [13:19<49:09,  1.22s/it, lr: 1.0e-04 loss: 7.647e-01]
latex_v1:  19%|#9        | 573/3000 [13:20<49:09,  1.22s/it, lr: 1.0e-04 loss: 2.112e-01]
latex_v1:  19%|#9        | 573/3000 [13:20<49:09,  1.22s/it, lr: 1.0e-04 loss: 2.112e-01]
latex_v1:  19%|#9        | 574/3000 [13:20<48:35,  1.20s/it, lr: 1.0e-04 loss: 2.112e-01]
latex_v1:  19%|#9        | 574/3000 [13:20<48:35,  1.20s/it, lr: 1.0e-04 loss: 2.112e-01]
latex_v1:  19%|#9        | 574/3000 [13:22<48:35,  1.20s/it, lr: 1.0e-04 loss: 2.925e-01]
latex_v1:  19%|#9        | 574/3000 [13:22<48:35,  1.20s/it, lr: 1.0e-04 loss: 2.925e-01]
latex_v1:  19%|#9        | 575/3000 [13:22<51:27,  1.27s/it, lr: 1.0e-04 loss: 2.925e-01]
latex_v1:  19%|#9        | 575/3000 [13:22<51:27,  1.27s/it, lr: 1.0e-04 loss: 2.925e-01]
latex_v1:  19%|#9        | 575/3000 [13:22<51:27,  1.27s/it, lr: 1.0e-04 loss: 4.175e-01]
latex_v1:  19%|#9        | 575/3000 [13:22<51:27,  1.27s/it, lr: 1.0e-04 loss: 4.175e-01]
latex_v1:  19%|#9        | 576/3000 [13:22<45:36,  1.13s/it, lr: 1.0e-04 loss: 4.175e-01]
latex_v1:  19%|#9        | 576/3000 [13:22<45:36,  1.13s/it, lr: 1.0e-04 loss: 4.175e-01]
latex_v1:  19%|#9        | 576/3000 [13:24<45:36,  1.13s/it, lr: 1.0e-04 loss: 7.386e-01]
latex_v1:  19%|#9        | 576/3000 [13:24<45:36,  1.13s/it, lr: 1.0e-04 loss: 7.386e-01]
latex_v1:  19%|#9        | 577/3000 [13:24<47:55,  1.19s/it, lr: 1.0e-04 loss: 7.386e-01]
latex_v1:  19%|#9        | 577/3000 [13:24<47:55,  1.19s/it, lr: 1.0e-04 loss: 7.386e-01]
latex_v1:  19%|#9        | 577/3000 [13:25<47:55,  1.19s/it, lr: 1.0e-04 loss: 1.092e-01]
latex_v1:  19%|#9        | 577/3000 [13:25<47:55,  1.19s/it, lr: 1.0e-04 loss: 1.092e-01]
latex_v1:  19%|#9        | 578/3000 [13:25<42:35,  1.06s/it, lr: 1.0e-04 loss: 1.092e-01]
latex_v1:  19%|#9        | 578/3000 [13:25<42:35,  1.06s/it, lr: 1.0e-04 loss: 1.092e-01]
latex_v1:  19%|#9        | 578/3000 [13:26<42:35,  1.06s/it, lr: 1.0e-04 loss: 2.067e-01]
latex_v1:  19%|#9        | 578/3000 [13:26<42:35,  1.06s/it, lr: 1.0e-04 loss: 2.067e-01]
latex_v1:  19%|#9        | 579/3000 [13:26<47:14,  1.17s/it, lr: 1.0e-04 loss: 2.067e-01]
latex_v1:  19%|#9        | 579/3000 [13:26<47:14,  1.17s/it, lr: 1.0e-04 loss: 2.067e-01]
latex_v1:  19%|#9        | 579/3000 [13:28<47:14,  1.17s/it, lr: 1.0e-04 loss: 1.887e-01]
latex_v1:  19%|#9        | 579/3000 [13:28<47:14,  1.17s/it, lr: 1.0e-04 loss: 1.887e-01]
latex_v1:  19%|#9        | 580/3000 [13:29<47:13,  1.17s/it, lr: 1.0e-04 loss: 6.710e-01]
latex_v1:  19%|#9        | 580/3000 [13:29<47:13,  1.17s/it, lr: 1.0e-04 loss: 6.710e-01]
latex_v1:  19%|#9        | 581/3000 [13:29<34:37,  1.16it/s, lr: 1.0e-04 loss: 6.710e-01]
latex_v1:  19%|#9        | 581/3000 [13:29<34:37,  1.16it/s, lr: 1.0e-04 loss: 6.710e-01]
latex_v1:  19%|#9        | 581/3000 [13:30<34:37,  1.16it/s, lr: 1.0e-04 loss: 5.190e-01]
latex_v1:  19%|#9        | 581/3000 [13:30<34:37,  1.16it/s, lr: 1.0e-04 loss: 5.190e-01]
latex_v1:  19%|#9        | 582/3000 [13:30<35:36,  1.13it/s, lr: 1.0e-04 loss: 5.190e-01]
latex_v1:  19%|#9        | 582/3000 [13:30<35:36,  1.13it/s, lr: 1.0e-04 loss: 5.190e-01]
latex_v1:  19%|#9        | 582/3000 [13:31<35:36,  1.13it/s, lr: 1.0e-04 loss: 4.568e-01]
latex_v1:  19%|#9        | 582/3000 [13:31<35:36,  1.13it/s, lr: 1.0e-04 loss: 4.568e-01]
latex_v1:  19%|#9        | 583/3000 [13:31<34:39,  1.16it/s, lr: 1.0e-04 loss: 4.568e-01]
latex_v1:  19%|#9        | 583/3000 [13:31<34:39,  1.16it/s, lr: 1.0e-04 loss: 4.568e-01]
latex_v1:  19%|#9        | 583/3000 [13:32<34:39,  1.16it/s, lr: 1.0e-04 loss: 3.065e-01]
latex_v1:  19%|#9        | 583/3000 [13:32<34:39,  1.16it/s, lr: 1.0e-04 loss: 3.065e-01]
latex_v1:  19%|#9        | 584/3000 [13:32<41:04,  1.02s/it, lr: 1.0e-04 loss: 3.065e-01]
latex_v1:  19%|#9        | 584/3000 [13:32<41:04,  1.02s/it, lr: 1.0e-04 loss: 3.065e-01]
latex_v1:  19%|#9        | 584/3000 [13:35<41:04,  1.02s/it, lr: 1.0e-04 loss: 1.547e-01]
latex_v1:  19%|#9        | 584/3000 [13:35<41:04,  1.02s/it, lr: 1.0e-04 loss: 1.547e-01]
latex_v1:  20%|#9        | 585/3000 [13:35<1:01:57,  1.54s/it, lr: 1.0e-04 loss: 1.547e-01]
latex_v1:  20%|#9        | 585/3000 [13:35<1:01:57,  1.54s/it, lr: 1.0e-04 loss: 1.547e-01]
latex_v1:  20%|#9        | 585/3000 [13:36<1:01:57,  1.54s/it, lr: 1.0e-04 loss: 3.660e-01]
latex_v1:  20%|#9        | 585/3000 [13:36<1:01:57,  1.54s/it, lr: 1.0e-04 loss: 3.660e-01]
latex_v1:  20%|#9        | 586/3000 [13:36<52:55,  1.32s/it, lr: 1.0e-04 loss: 3.660e-01]  
latex_v1:  20%|#9        | 586/3000 [13:36<52:55,  1.32s/it, lr: 1.0e-04 loss: 3.660e-01]  
latex_v1:  20%|#9        | 586/3000 [13:37<52:55,  1.32s/it, lr: 1.0e-04 loss: 2.076e-01]
latex_v1:  20%|#9        | 586/3000 [13:37<52:55,  1.32s/it, lr: 1.0e-04 loss: 2.076e-01]
latex_v1:  20%|#9        | 587/3000 [13:37<46:38,  1.16s/it, lr: 1.0e-04 loss: 2.076e-01]
latex_v1:  20%|#9        | 587/3000 [13:37<46:38,  1.16s/it, lr: 1.0e-04 loss: 2.076e-01]
latex_v1:  20%|#9        | 587/3000 [13:38<46:38,  1.16s/it, lr: 1.0e-04 loss: 1.891e-01]
latex_v1:  20%|#9        | 587/3000 [13:38<46:38,  1.16s/it, lr: 1.0e-04 loss: 1.891e-01]
latex_v1:  20%|#9        | 588/3000 [13:38<51:00,  1.27s/it, lr: 1.0e-04 loss: 1.891e-01]
latex_v1:  20%|#9        | 588/3000 [13:38<51:00,  1.27s/it, lr: 1.0e-04 loss: 1.891e-01]
latex_v1:  20%|#9        | 588/3000 [13:40<51:00,  1.27s/it, lr: 1.0e-04 loss: 8.192e-02]
latex_v1:  20%|#9        | 588/3000 [13:40<51:00,  1.27s/it, lr: 1.0e-04 loss: 8.192e-02]
latex_v1:  20%|#9        | 589/3000 [13:40<58:22,  1.45s/it, lr: 1.0e-04 loss: 8.192e-02]
latex_v1:  20%|#9        | 589/3000 [13:40<58:22,  1.45s/it, lr: 1.0e-04 loss: 8.192e-02]
latex_v1:  20%|#9        | 589/3000 [13:41<58:22,  1.45s/it, lr: 1.0e-04 loss: 4.912e-01]
latex_v1:  20%|#9        | 589/3000 [13:41<58:22,  1.45s/it, lr: 1.0e-04 loss: 4.912e-01]
latex_v1:  20%|#9        | 590/3000 [13:44<58:20,  1.45s/it, lr: 1.0e-04 loss: 5.973e-01]
latex_v1:  20%|#9        | 590/3000 [13:44<58:20,  1.45s/it, lr: 1.0e-04 loss: 5.973e-01]
latex_v1:  20%|#9        | 591/3000 [13:44<57:41,  1.44s/it, lr: 1.0e-04 loss: 5.973e-01]
latex_v1:  20%|#9        | 591/3000 [13:44<57:41,  1.44s/it, lr: 1.0e-04 loss: 5.973e-01]
latex_v1:  20%|#9        | 591/3000 [13:47<57:41,  1.44s/it, lr: 1.0e-04 loss: 1.774e-01]
latex_v1:  20%|#9        | 591/3000 [13:47<57:41,  1.44s/it, lr: 1.0e-04 loss: 1.774e-01]
latex_v1:  20%|#9        | 592/3000 [13:47<1:11:56,  1.79s/it, lr: 1.0e-04 loss: 1.774e-01]
latex_v1:  20%|#9        | 592/3000 [13:47<1:11:56,  1.79s/it, lr: 1.0e-04 loss: 1.774e-01]
latex_v1:  20%|#9        | 592/3000 [13:48<1:11:56,  1.79s/it, lr: 1.0e-04 loss: 5.554e-01]
latex_v1:  20%|#9        | 592/3000 [13:48<1:11:56,  1.79s/it, lr: 1.0e-04 loss: 5.554e-01]
latex_v1:  20%|#9        | 593/3000 [13:48<1:09:21,  1.73s/it, lr: 1.0e-04 loss: 5.554e-01]
latex_v1:  20%|#9        | 593/3000 [13:48<1:09:21,  1.73s/it, lr: 1.0e-04 loss: 5.554e-01]
latex_v1:  20%|#9        | 593/3000 [13:49<1:09:21,  1.73s/it, lr: 1.0e-04 loss: 1.391e-01]
latex_v1:  20%|#9        | 593/3000 [13:49<1:09:21,  1.73s/it, lr: 1.0e-04 loss: 1.391e-01]
latex_v1:  20%|#9        | 594/3000 [13:49<58:39,  1.46s/it, lr: 1.0e-04 loss: 1.391e-01]  
latex_v1:  20%|#9        | 594/3000 [13:49<58:39,  1.46s/it, lr: 1.0e-04 loss: 1.391e-01]  
latex_v1:  20%|#9        | 594/3000 [13:50<58:39,  1.46s/it, lr: 1.0e-04 loss: 2.711e-01]
latex_v1:  20%|#9        | 594/3000 [13:50<58:39,  1.46s/it, lr: 1.0e-04 loss: 2.711e-01]
latex_v1:  20%|#9        | 595/3000 [13:50<53:27,  1.33s/it, lr: 1.0e-04 loss: 2.711e-01]
latex_v1:  20%|#9        | 595/3000 [13:50<53:27,  1.33s/it, lr: 1.0e-04 loss: 2.711e-01]
latex_v1:  20%|#9        | 595/3000 [13:51<53:27,  1.33s/it, lr: 1.0e-04 loss: 4.571e-01]
latex_v1:  20%|#9        | 595/3000 [13:51<53:27,  1.33s/it, lr: 1.0e-04 loss: 4.571e-01]
latex_v1:  20%|#9        | 596/3000 [13:51<46:50,  1.17s/it, lr: 1.0e-04 loss: 4.571e-01]
latex_v1:  20%|#9        | 596/3000 [13:51<46:50,  1.17s/it, lr: 1.0e-04 loss: 4.571e-01]
latex_v1:  20%|#9        | 596/3000 [13:53<46:50,  1.17s/it, lr: 1.0e-04 loss: 4.172e-01]
latex_v1:  20%|#9        | 596/3000 [13:53<46:50,  1.17s/it, lr: 1.0e-04 loss: 4.172e-01]
latex_v1:  20%|#9        | 597/3000 [13:53<55:02,  1.37s/it, lr: 1.0e-04 loss: 4.172e-01]
latex_v1:  20%|#9        | 597/3000 [13:53<55:02,  1.37s/it, lr: 1.0e-04 loss: 4.172e-01]
latex_v1:  20%|#9        | 597/3000 [13:54<55:02,  1.37s/it, lr: 1.0e-04 loss: 6.632e-01]
latex_v1:  20%|#9        | 597/3000 [13:54<55:02,  1.37s/it, lr: 1.0e-04 loss: 6.632e-01]
latex_v1:  20%|#9        | 598/3000 [13:54<55:28,  1.39s/it, lr: 1.0e-04 loss: 6.632e-01]
latex_v1:  20%|#9        | 598/3000 [13:54<55:28,  1.39s/it, lr: 1.0e-04 loss: 6.632e-01]
latex_v1:  20%|#9        | 598/3000 [13:55<55:28,  1.39s/it, lr: 1.0e-04 loss: 2.273e-01]
latex_v1:  20%|#9        | 598/3000 [13:55<55:28,  1.39s/it, lr: 1.0e-04 loss: 2.273e-01]
latex_v1:  20%|#9        | 599/3000 [13:55<47:57,  1.20s/it, lr: 1.0e-04 loss: 2.273e-01]
latex_v1:  20%|#9        | 599/3000 [13:55<47:57,  1.20s/it, lr: 1.0e-04 loss: 2.273e-01]
latex_v1:  20%|#9        | 599/3000 [13:57<47:57,  1.20s/it, lr: 1.0e-04 loss: 5.213e-01]
latex_v1:  20%|#9        | 599/3000 [13:57<47:57,  1.20s/it, lr: 1.0e-04 loss: 5.213e-01]Unloading assistant lora



Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]


Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.50s/it]
Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.50s/it]


Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.45s/it]
Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.45s/it]


Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.43s/it]
Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.43s/it]


Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.42s/it]
Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.42s/it]


Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.42s/it]
Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.42s/it]


Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.40s/it]
Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.40s/it]


Generating Images: 100%|##########| 7/7 [00:16<00:00,  2.40s/it]
Generating Images: 100%|##########| 7/7 [00:16<00:00,  2.40s/it]


                                                                
                                                                Loading assistant lora

latex_v1:  20%|##        | 600/3000 [13:59<47:56,  1.20s/it, lr: 1.0e-04 loss: 2.196e-01]
latex_v1:  20%|##        | 600/3000 [13:59<47:56,  1.20s/it, lr: 1.0e-04 loss: 2.196e-01]
latex_v1:  20%|##        | 601/3000 [13:59<40:07,  1.00s/it, lr: 1.0e-04 loss: 2.196e-01]
latex_v1:  20%|##        | 601/3000 [13:59<40:07,  1.00s/it, lr: 1.0e-04 loss: 2.196e-01]
latex_v1:  20%|##        | 601/3000 [14:00<40:07,  1.00s/it, lr: 1.0e-04 loss: 6.013e-01]
latex_v1:  20%|##        | 601/3000 [14:00<40:07,  1.00s/it, lr: 1.0e-04 loss: 6.013e-01]
latex_v1:  20%|##        | 602/3000 [14:00<37:28,  1.07it/s, lr: 1.0e-04 loss: 6.013e-01]
latex_v1:  20%|##        | 602/3000 [14:00<37:28,  1.07it/s, lr: 1.0e-04 loss: 6.013e-01]
latex_v1:  20%|##        | 602/3000 [14:01<37:28,  1.07it/s, lr: 1.0e-04 loss: 5.976e-01]
latex_v1:  20%|##        | 602/3000 [14:01<37:28,  1.07it/s, lr: 1.0e-04 loss: 5.976e-01]
latex_v1:  20%|##        | 603/3000 [14:01<39:41,  1.01it/s, lr: 1.0e-04 loss: 5.976e-01]
latex_v1:  20%|##        | 603/3000 [14:01<39:41,  1.01it/s, lr: 1.0e-04 loss: 5.976e-01]
latex_v1:  20%|##        | 603/3000 [14:02<39:41,  1.01it/s, lr: 1.0e-04 loss: 3.110e-01]
latex_v1:  20%|##        | 603/3000 [14:02<39:41,  1.01it/s, lr: 1.0e-04 loss: 3.110e-01]
latex_v1:  20%|##        | 604/3000 [14:02<37:12,  1.07it/s, lr: 1.0e-04 loss: 3.110e-01]
latex_v1:  20%|##        | 604/3000 [14:02<37:12,  1.07it/s, lr: 1.0e-04 loss: 3.110e-01]
latex_v1:  20%|##        | 604/3000 [14:02<37:12,  1.07it/s, lr: 1.0e-04 loss: 3.321e-01]
latex_v1:  20%|##        | 604/3000 [14:02<37:12,  1.07it/s, lr: 1.0e-04 loss: 3.321e-01]
latex_v1:  20%|##        | 605/3000 [14:02<35:23,  1.13it/s, lr: 1.0e-04 loss: 3.321e-01]
latex_v1:  20%|##        | 605/3000 [14:02<35:23,  1.13it/s, lr: 1.0e-04 loss: 3.321e-01]
latex_v1:  20%|##        | 605/3000 [14:04<35:23,  1.13it/s, lr: 1.0e-04 loss: 2.715e-01]
latex_v1:  20%|##        | 605/3000 [14:04<35:23,  1.13it/s, lr: 1.0e-04 loss: 2.715e-01]
latex_v1:  20%|##        | 606/3000 [14:04<47:43,  1.20s/it, lr: 1.0e-04 loss: 2.715e-01]
latex_v1:  20%|##        | 606/3000 [14:04<47:43,  1.20s/it, lr: 1.0e-04 loss: 2.715e-01]
latex_v1:  20%|##        | 606/3000 [14:06<47:43,  1.20s/it, lr: 1.0e-04 loss: 1.572e-01]
latex_v1:  20%|##        | 606/3000 [14:06<47:43,  1.20s/it, lr: 1.0e-04 loss: 1.572e-01]
latex_v1:  20%|##        | 607/3000 [14:06<51:57,  1.30s/it, lr: 1.0e-04 loss: 1.572e-01]
latex_v1:  20%|##        | 607/3000 [14:06<51:57,  1.30s/it, lr: 1.0e-04 loss: 1.572e-01]
latex_v1:  20%|##        | 607/3000 [14:09<51:57,  1.30s/it, lr: 1.0e-04 loss: 1.888e-01]
latex_v1:  20%|##        | 607/3000 [14:09<51:57,  1.30s/it, lr: 1.0e-04 loss: 1.888e-01]
latex_v1:  20%|##        | 608/3000 [14:09<1:09:54,  1.75s/it, lr: 1.0e-04 loss: 1.888e-01]
latex_v1:  20%|##        | 608/3000 [14:09<1:09:54,  1.75s/it, lr: 1.0e-04 loss: 1.888e-01]
latex_v1:  20%|##        | 608/3000 [14:12<1:09:54,  1.75s/it, lr: 1.0e-04 loss: 1.804e-01]
latex_v1:  20%|##        | 608/3000 [14:12<1:09:54,  1.75s/it, lr: 1.0e-04 loss: 1.804e-01]
latex_v1:  20%|##        | 609/3000 [14:12<1:23:11,  2.09s/it, lr: 1.0e-04 loss: 1.804e-01]
latex_v1:  20%|##        | 609/3000 [14:12<1:23:11,  2.09s/it, lr: 1.0e-04 loss: 1.804e-01]
latex_v1:  20%|##        | 609/3000 [14:12<1:23:11,  2.09s/it, lr: 1.0e-04 loss: 7.717e-01]
latex_v1:  20%|##        | 609/3000 [14:12<1:23:11,  2.09s/it, lr: 1.0e-04 loss: 7.717e-01]
latex_v1:  20%|##        | 610/3000 [14:13<1:23:09,  2.09s/it, lr: 1.0e-04 loss: 5.056e-02]
latex_v1:  20%|##        | 610/3000 [14:13<1:23:09,  2.09s/it, lr: 1.0e-04 loss: 5.056e-02]
latex_v1:  20%|##        | 611/3000 [14:13<51:54,  1.30s/it, lr: 1.0e-04 loss: 5.056e-02]  
latex_v1:  20%|##        | 611/3000 [14:13<51:54,  1.30s/it, lr: 1.0e-04 loss: 5.056e-02]  
latex_v1:  20%|##        | 611/3000 [14:15<51:54,  1.30s/it, lr: 1.0e-04 loss: 5.328e-01]
latex_v1:  20%|##        | 611/3000 [14:15<51:54,  1.30s/it, lr: 1.0e-04 loss: 5.328e-01]
latex_v1:  20%|##        | 612/3000 [14:15<55:55,  1.41s/it, lr: 1.0e-04 loss: 5.328e-01]
latex_v1:  20%|##        | 612/3000 [14:15<55:55,  1.41s/it, lr: 1.0e-04 loss: 5.328e-01]
latex_v1:  20%|##        | 612/3000 [14:16<55:55,  1.41s/it, lr: 1.0e-04 loss: 2.884e-01]
latex_v1:  20%|##        | 612/3000 [14:16<55:55,  1.41s/it, lr: 1.0e-04 loss: 2.884e-01]
latex_v1:  20%|##        | 613/3000 [14:16<51:59,  1.31s/it, lr: 1.0e-04 loss: 2.884e-01]
latex_v1:  20%|##        | 613/3000 [14:16<51:59,  1.31s/it, lr: 1.0e-04 loss: 2.884e-01]
latex_v1:  20%|##        | 613/3000 [14:17<51:59,  1.31s/it, lr: 1.0e-04 loss: 1.701e-01]
latex_v1:  20%|##        | 613/3000 [14:17<51:59,  1.31s/it, lr: 1.0e-04 loss: 1.701e-01]
latex_v1:  20%|##        | 614/3000 [14:17<45:40,  1.15s/it, lr: 1.0e-04 loss: 1.701e-01]
latex_v1:  20%|##        | 614/3000 [14:17<45:40,  1.15s/it, lr: 1.0e-04 loss: 1.701e-01]
latex_v1:  20%|##        | 614/3000 [14:19<45:40,  1.15s/it, lr: 1.0e-04 loss: 2.136e-01]
latex_v1:  20%|##        | 614/3000 [14:19<45:40,  1.15s/it, lr: 1.0e-04 loss: 2.136e-01]
latex_v1:  20%|##        | 615/3000 [14:19<1:04:36,  1.63s/it, lr: 1.0e-04 loss: 2.136e-01]
latex_v1:  20%|##        | 615/3000 [14:19<1:04:36,  1.63s/it, lr: 1.0e-04 loss: 2.136e-01]
latex_v1:  20%|##        | 615/3000 [14:20<1:04:36,  1.63s/it, lr: 1.0e-04 loss: 1.114e-01]
latex_v1:  20%|##        | 615/3000 [14:20<1:04:36,  1.63s/it, lr: 1.0e-04 loss: 1.114e-01]
latex_v1:  21%|##        | 616/3000 [14:20<54:31,  1.37s/it, lr: 1.0e-04 loss: 1.114e-01]  
latex_v1:  21%|##        | 616/3000 [14:20<54:31,  1.37s/it, lr: 1.0e-04 loss: 1.114e-01]  
latex_v1:  21%|##        | 616/3000 [14:22<54:31,  1.37s/it, lr: 1.0e-04 loss: 1.158e-01]
latex_v1:  21%|##        | 616/3000 [14:22<54:31,  1.37s/it, lr: 1.0e-04 loss: 1.158e-01]
latex_v1:  21%|##        | 617/3000 [14:22<1:00:53,  1.53s/it, lr: 1.0e-04 loss: 1.158e-01]
latex_v1:  21%|##        | 617/3000 [14:22<1:00:53,  1.53s/it, lr: 1.0e-04 loss: 1.158e-01]
latex_v1:  21%|##        | 617/3000 [14:24<1:00:53,  1.53s/it, lr: 1.0e-04 loss: 6.010e-01]
latex_v1:  21%|##        | 617/3000 [14:24<1:00:53,  1.53s/it, lr: 1.0e-04 loss: 6.010e-01]
latex_v1:  21%|##        | 618/3000 [14:24<59:21,  1.50s/it, lr: 1.0e-04 loss: 6.010e-01]  
latex_v1:  21%|##        | 618/3000 [14:24<59:21,  1.50s/it, lr: 1.0e-04 loss: 6.010e-01]  
latex_v1:  21%|##        | 618/3000 [14:25<59:21,  1.50s/it, lr: 1.0e-04 loss: 7.450e-01]
latex_v1:  21%|##        | 618/3000 [14:25<59:21,  1.50s/it, lr: 1.0e-04 loss: 7.450e-01]
latex_v1:  21%|##        | 619/3000 [14:25<58:09,  1.47s/it, lr: 1.0e-04 loss: 7.450e-01]
latex_v1:  21%|##        | 619/3000 [14:25<58:09,  1.47s/it, lr: 1.0e-04 loss: 7.450e-01]
latex_v1:  21%|##        | 619/3000 [14:26<58:09,  1.47s/it, lr: 1.0e-04 loss: 5.768e-01]
latex_v1:  21%|##        | 619/3000 [14:26<58:09,  1.47s/it, lr: 1.0e-04 loss: 5.768e-01]
latex_v1:  21%|##        | 620/3000 [14:27<58:08,  1.47s/it, lr: 1.0e-04 loss: 1.368e-01]
latex_v1:  21%|##        | 620/3000 [14:27<58:08,  1.47s/it, lr: 1.0e-04 loss: 1.368e-01]
latex_v1:  21%|##        | 621/3000 [14:27<44:37,  1.13s/it, lr: 1.0e-04 loss: 1.368e-01]
latex_v1:  21%|##        | 621/3000 [14:27<44:37,  1.13s/it, lr: 1.0e-04 loss: 1.368e-01]
latex_v1:  21%|##        | 621/3000 [14:28<44:37,  1.13s/it, lr: 1.0e-04 loss: 2.979e-01]
latex_v1:  21%|##        | 621/3000 [14:28<44:37,  1.13s/it, lr: 1.0e-04 loss: 2.979e-01]
latex_v1:  21%|##        | 622/3000 [14:28<40:46,  1.03s/it, lr: 1.0e-04 loss: 2.979e-01]
latex_v1:  21%|##        | 622/3000 [14:28<40:46,  1.03s/it, lr: 1.0e-04 loss: 2.979e-01]
latex_v1:  21%|##        | 622/3000 [14:30<40:46,  1.03s/it, lr: 1.0e-04 loss: 2.287e-01]
latex_v1:  21%|##        | 622/3000 [14:30<40:46,  1.03s/it, lr: 1.0e-04 loss: 2.287e-01]
latex_v1:  21%|##        | 623/3000 [14:30<45:49,  1.16s/it, lr: 1.0e-04 loss: 2.287e-01]
latex_v1:  21%|##        | 623/3000 [14:30<45:49,  1.16s/it, lr: 1.0e-04 loss: 2.287e-01]
latex_v1:  21%|##        | 623/3000 [14:31<45:49,  1.16s/it, lr: 1.0e-04 loss: 1.198e-01]
latex_v1:  21%|##        | 623/3000 [14:31<45:49,  1.16s/it, lr: 1.0e-04 loss: 1.198e-01]
latex_v1:  21%|##        | 624/3000 [14:31<49:38,  1.25s/it, lr: 1.0e-04 loss: 1.198e-01]
latex_v1:  21%|##        | 624/3000 [14:31<49:38,  1.25s/it, lr: 1.0e-04 loss: 1.198e-01]
latex_v1:  21%|##        | 624/3000 [14:33<49:38,  1.25s/it, lr: 1.0e-04 loss: 4.340e-01]
latex_v1:  21%|##        | 624/3000 [14:33<49:38,  1.25s/it, lr: 1.0e-04 loss: 4.340e-01]
latex_v1:  21%|##        | 625/3000 [14:33<52:43,  1.33s/it, lr: 1.0e-04 loss: 4.340e-01]
latex_v1:  21%|##        | 625/3000 [14:33<52:43,  1.33s/it, lr: 1.0e-04 loss: 4.340e-01]
latex_v1:  21%|##        | 625/3000 [14:33<52:43,  1.33s/it, lr: 1.0e-04 loss: 2.219e-01]
latex_v1:  21%|##        | 625/3000 [14:33<52:43,  1.33s/it, lr: 1.0e-04 loss: 2.219e-01]
latex_v1:  21%|##        | 626/3000 [14:33<46:04,  1.16s/it, lr: 1.0e-04 loss: 2.219e-01]
latex_v1:  21%|##        | 626/3000 [14:33<46:04,  1.16s/it, lr: 1.0e-04 loss: 2.219e-01]
latex_v1:  21%|##        | 626/3000 [14:36<46:04,  1.16s/it, lr: 1.0e-04 loss: 4.248e-01]
latex_v1:  21%|##        | 626/3000 [14:36<46:04,  1.16s/it, lr: 1.0e-04 loss: 4.248e-01]
latex_v1:  21%|##        | 627/3000 [14:36<55:49,  1.41s/it, lr: 1.0e-04 loss: 4.248e-01]
latex_v1:  21%|##        | 627/3000 [14:36<55:49,  1.41s/it, lr: 1.0e-04 loss: 4.248e-01]
latex_v1:  21%|##        | 627/3000 [14:37<55:49,  1.41s/it, lr: 1.0e-04 loss: 7.034e-01]
latex_v1:  21%|##        | 627/3000 [14:37<55:49,  1.41s/it, lr: 1.0e-04 loss: 7.034e-01]
latex_v1:  21%|##        | 628/3000 [14:37<54:42,  1.38s/it, lr: 1.0e-04 loss: 7.034e-01]
latex_v1:  21%|##        | 628/3000 [14:37<54:42,  1.38s/it, lr: 1.0e-04 loss: 7.034e-01]
latex_v1:  21%|##        | 628/3000 [14:39<54:42,  1.38s/it, lr: 1.0e-04 loss: 5.081e-01]
latex_v1:  21%|##        | 628/3000 [14:39<54:42,  1.38s/it, lr: 1.0e-04 loss: 5.081e-01]
latex_v1:  21%|##        | 629/3000 [14:39<1:00:09,  1.52s/it, lr: 1.0e-04 loss: 5.081e-01]
latex_v1:  21%|##        | 629/3000 [14:39<1:00:09,  1.52s/it, lr: 1.0e-04 loss: 5.081e-01]
latex_v1:  21%|##        | 629/3000 [14:39<1:00:09,  1.52s/it, lr: 1.0e-04 loss: 2.496e-01]
latex_v1:  21%|##        | 629/3000 [14:39<1:00:09,  1.52s/it, lr: 1.0e-04 loss: 2.496e-01]
latex_v1:  21%|##1       | 630/3000 [14:41<1:00:08,  1.52s/it, lr: 1.0e-04 loss: 6.700e-01]
latex_v1:  21%|##1       | 630/3000 [14:41<1:00:08,  1.52s/it, lr: 1.0e-04 loss: 6.700e-01]
latex_v1:  21%|##1       | 631/3000 [14:41<46:15,  1.17s/it, lr: 1.0e-04 loss: 6.700e-01]  
latex_v1:  21%|##1       | 631/3000 [14:41<46:15,  1.17s/it, lr: 1.0e-04 loss: 6.700e-01]  
latex_v1:  21%|##1       | 631/3000 [14:42<46:15,  1.17s/it, lr: 1.0e-04 loss: 2.212e-01]
latex_v1:  21%|##1       | 631/3000 [14:42<46:15,  1.17s/it, lr: 1.0e-04 loss: 2.212e-01]
latex_v1:  21%|##1       | 632/3000 [14:42<49:45,  1.26s/it, lr: 1.0e-04 loss: 2.212e-01]
latex_v1:  21%|##1       | 632/3000 [14:42<49:45,  1.26s/it, lr: 1.0e-04 loss: 2.212e-01]
latex_v1:  21%|##1       | 632/3000 [14:44<49:45,  1.26s/it, lr: 1.0e-04 loss: 3.360e-01]
latex_v1:  21%|##1       | 632/3000 [14:44<49:45,  1.26s/it, lr: 1.0e-04 loss: 3.360e-01]
latex_v1:  21%|##1       | 633/3000 [14:44<52:34,  1.33s/it, lr: 1.0e-04 loss: 3.360e-01]
latex_v1:  21%|##1       | 633/3000 [14:44<52:34,  1.33s/it, lr: 1.0e-04 loss: 3.360e-01]
latex_v1:  21%|##1       | 633/3000 [14:45<52:34,  1.33s/it, lr: 1.0e-04 loss: 6.752e-01]
latex_v1:  21%|##1       | 633/3000 [14:45<52:34,  1.33s/it, lr: 1.0e-04 loss: 6.752e-01]
latex_v1:  21%|##1       | 634/3000 [14:45<52:46,  1.34s/it, lr: 1.0e-04 loss: 6.752e-01]
latex_v1:  21%|##1       | 634/3000 [14:45<52:46,  1.34s/it, lr: 1.0e-04 loss: 6.752e-01]
latex_v1:  21%|##1       | 634/3000 [14:46<52:46,  1.34s/it, lr: 1.0e-04 loss: 5.381e-01]
latex_v1:  21%|##1       | 634/3000 [14:46<52:46,  1.34s/it, lr: 1.0e-04 loss: 5.381e-01]
latex_v1:  21%|##1       | 635/3000 [14:46<46:04,  1.17s/it, lr: 1.0e-04 loss: 5.381e-01]
latex_v1:  21%|##1       | 635/3000 [14:46<46:04,  1.17s/it, lr: 1.0e-04 loss: 5.381e-01]
latex_v1:  21%|##1       | 635/3000 [14:47<46:04,  1.17s/it, lr: 1.0e-04 loss: 5.171e-01]
latex_v1:  21%|##1       | 635/3000 [14:47<46:04,  1.17s/it, lr: 1.0e-04 loss: 5.171e-01]
latex_v1:  21%|##1       | 636/3000 [14:47<41:21,  1.05s/it, lr: 1.0e-04 loss: 5.171e-01]
latex_v1:  21%|##1       | 636/3000 [14:47<41:21,  1.05s/it, lr: 1.0e-04 loss: 5.171e-01]
latex_v1:  21%|##1       | 636/3000 [14:48<41:21,  1.05s/it, lr: 1.0e-04 loss: 5.913e-01]
latex_v1:  21%|##1       | 636/3000 [14:48<41:21,  1.05s/it, lr: 1.0e-04 loss: 5.913e-01]
latex_v1:  21%|##1       | 637/3000 [14:48<37:48,  1.04it/s, lr: 1.0e-04 loss: 5.913e-01]
latex_v1:  21%|##1       | 637/3000 [14:48<37:48,  1.04it/s, lr: 1.0e-04 loss: 5.913e-01]
latex_v1:  21%|##1       | 637/3000 [14:49<37:48,  1.04it/s, lr: 1.0e-04 loss: 1.971e-01]
latex_v1:  21%|##1       | 637/3000 [14:49<37:48,  1.04it/s, lr: 1.0e-04 loss: 1.971e-01]
latex_v1:  21%|##1       | 638/3000 [14:49<41:26,  1.05s/it, lr: 1.0e-04 loss: 1.971e-01]
latex_v1:  21%|##1       | 638/3000 [14:49<41:26,  1.05s/it, lr: 1.0e-04 loss: 1.971e-01]
latex_v1:  21%|##1       | 638/3000 [14:50<41:26,  1.05s/it, lr: 1.0e-04 loss: 1.768e-01]
latex_v1:  21%|##1       | 638/3000 [14:50<41:26,  1.05s/it, lr: 1.0e-04 loss: 1.768e-01]
latex_v1:  21%|##1       | 639/3000 [14:51<48:19,  1.23s/it, lr: 1.0e-04 loss: 1.768e-01]
latex_v1:  21%|##1       | 639/3000 [14:51<48:19,  1.23s/it, lr: 1.0e-04 loss: 1.768e-01]
latex_v1:  21%|##1       | 639/3000 [14:52<48:19,  1.23s/it, lr: 1.0e-04 loss: 3.948e-01]
latex_v1:  21%|##1       | 639/3000 [14:52<48:19,  1.23s/it, lr: 1.0e-04 loss: 3.948e-01]
latex_v1:  21%|##1       | 640/3000 [14:55<48:17,  1.23s/it, lr: 1.0e-04 loss: 1.363e-01]
latex_v1:  21%|##1       | 640/3000 [14:55<48:17,  1.23s/it, lr: 1.0e-04 loss: 1.363e-01]
latex_v1:  21%|##1       | 641/3000 [14:55<50:35,  1.29s/it, lr: 1.0e-04 loss: 1.363e-01]
latex_v1:  21%|##1       | 641/3000 [14:55<50:35,  1.29s/it, lr: 1.0e-04 loss: 1.363e-01]
latex_v1:  21%|##1       | 641/3000 [14:57<50:35,  1.29s/it, lr: 1.0e-04 loss: 7.065e-01]
latex_v1:  21%|##1       | 641/3000 [14:57<50:35,  1.29s/it, lr: 1.0e-04 loss: 7.065e-01]
latex_v1:  21%|##1       | 642/3000 [14:57<1:05:21,  1.66s/it, lr: 1.0e-04 loss: 7.065e-01]
latex_v1:  21%|##1       | 642/3000 [14:57<1:05:21,  1.66s/it, lr: 1.0e-04 loss: 7.065e-01]
latex_v1:  21%|##1       | 642/3000 [15:00<1:05:21,  1.66s/it, lr: 1.0e-04 loss: 2.212e-01]
latex_v1:  21%|##1       | 642/3000 [15:00<1:05:21,  1.66s/it, lr: 1.0e-04 loss: 2.212e-01]
latex_v1:  21%|##1       | 643/3000 [15:00<1:17:02,  1.96s/it, lr: 1.0e-04 loss: 2.212e-01]
latex_v1:  21%|##1       | 643/3000 [15:00<1:17:02,  1.96s/it, lr: 1.0e-04 loss: 2.212e-01]
latex_v1:  21%|##1       | 643/3000 [15:02<1:17:02,  1.96s/it, lr: 1.0e-04 loss: 2.324e-01]
latex_v1:  21%|##1       | 643/3000 [15:02<1:17:02,  1.96s/it, lr: 1.0e-04 loss: 2.324e-01]
latex_v1:  21%|##1       | 644/3000 [15:02<1:12:21,  1.84s/it, lr: 1.0e-04 loss: 2.324e-01]
latex_v1:  21%|##1       | 644/3000 [15:02<1:12:21,  1.84s/it, lr: 1.0e-04 loss: 2.324e-01]
latex_v1:  21%|##1       | 644/3000 [15:03<1:12:21,  1.84s/it, lr: 1.0e-04 loss: 4.580e-02]
latex_v1:  21%|##1       | 644/3000 [15:03<1:12:21,  1.84s/it, lr: 1.0e-04 loss: 4.580e-02]
latex_v1:  22%|##1       | 645/3000 [15:03<1:07:24,  1.72s/it, lr: 1.0e-04 loss: 4.580e-02]
latex_v1:  22%|##1       | 645/3000 [15:03<1:07:24,  1.72s/it, lr: 1.0e-04 loss: 4.580e-02]
latex_v1:  22%|##1       | 645/3000 [15:04<1:07:24,  1.72s/it, lr: 1.0e-04 loss: 2.665e-01]
latex_v1:  22%|##1       | 645/3000 [15:04<1:07:24,  1.72s/it, lr: 1.0e-04 loss: 2.665e-01]
latex_v1:  22%|##1       | 646/3000 [15:04<1:01:08,  1.56s/it, lr: 1.0e-04 loss: 2.665e-01]
latex_v1:  22%|##1       | 646/3000 [15:04<1:01:08,  1.56s/it, lr: 1.0e-04 loss: 2.665e-01]
latex_v1:  22%|##1       | 646/3000 [15:06<1:01:08,  1.56s/it, lr: 1.0e-04 loss: 5.699e-01]
latex_v1:  22%|##1       | 646/3000 [15:06<1:01:08,  1.56s/it, lr: 1.0e-04 loss: 5.699e-01]
latex_v1:  22%|##1       | 647/3000 [15:06<59:29,  1.52s/it, lr: 1.0e-04 loss: 5.699e-01]  
latex_v1:  22%|##1       | 647/3000 [15:06<59:29,  1.52s/it, lr: 1.0e-04 loss: 5.699e-01]  
latex_v1:  22%|##1       | 647/3000 [15:07<59:29,  1.52s/it, lr: 1.0e-04 loss: 7.104e-02]
latex_v1:  22%|##1       | 647/3000 [15:07<59:29,  1.52s/it, lr: 1.0e-04 loss: 7.104e-02]
latex_v1:  22%|##1       | 648/3000 [15:07<59:31,  1.52s/it, lr: 1.0e-04 loss: 7.104e-02]
latex_v1:  22%|##1       | 648/3000 [15:07<59:31,  1.52s/it, lr: 1.0e-04 loss: 7.104e-02]
latex_v1:  22%|##1       | 648/3000 [15:09<59:31,  1.52s/it, lr: 1.0e-04 loss: 6.661e-01]
latex_v1:  22%|##1       | 648/3000 [15:09<59:31,  1.52s/it, lr: 1.0e-04 loss: 6.661e-01]
latex_v1:  22%|##1       | 649/3000 [15:09<57:34,  1.47s/it, lr: 1.0e-04 loss: 6.661e-01]
latex_v1:  22%|##1       | 649/3000 [15:09<57:34,  1.47s/it, lr: 1.0e-04 loss: 6.661e-01]
latex_v1:  22%|##1       | 649/3000 [15:09<57:34,  1.47s/it, lr: 1.0e-04 loss: 2.350e-01]
latex_v1:  22%|##1       | 649/3000 [15:09<57:34,  1.47s/it, lr: 1.0e-04 loss: 2.350e-01]
latex_v1:  22%|##1       | 650/3000 [15:11<57:32,  1.47s/it, lr: 1.0e-04 loss: 1.083e-01]
latex_v1:  22%|##1       | 650/3000 [15:11<57:32,  1.47s/it, lr: 1.0e-04 loss: 1.083e-01]
latex_v1:  22%|##1       | 651/3000 [15:11<43:09,  1.10s/it, lr: 1.0e-04 loss: 1.083e-01]
latex_v1:  22%|##1       | 651/3000 [15:11<43:09,  1.10s/it, lr: 1.0e-04 loss: 1.083e-01]
latex_v1:  22%|##1       | 651/3000 [15:12<43:09,  1.10s/it, lr: 1.0e-04 loss: 5.204e-01]
latex_v1:  22%|##1       | 651/3000 [15:12<43:09,  1.10s/it, lr: 1.0e-04 loss: 5.204e-01]
latex_v1:  22%|##1       | 652/3000 [15:12<46:26,  1.19s/it, lr: 1.0e-04 loss: 5.204e-01]
latex_v1:  22%|##1       | 652/3000 [15:12<46:26,  1.19s/it, lr: 1.0e-04 loss: 5.204e-01]
latex_v1:  22%|##1       | 652/3000 [15:13<46:26,  1.19s/it, lr: 1.0e-04 loss: 3.405e-01]
latex_v1:  22%|##1       | 652/3000 [15:13<46:26,  1.19s/it, lr: 1.0e-04 loss: 3.405e-01]
latex_v1:  22%|##1       | 653/3000 [15:13<41:56,  1.07s/it, lr: 1.0e-04 loss: 3.405e-01]
latex_v1:  22%|##1       | 653/3000 [15:13<41:56,  1.07s/it, lr: 1.0e-04 loss: 3.405e-01]
latex_v1:  22%|##1       | 653/3000 [15:14<41:56,  1.07s/it, lr: 1.0e-04 loss: 6.125e-01]
latex_v1:  22%|##1       | 653/3000 [15:14<41:56,  1.07s/it, lr: 1.0e-04 loss: 6.125e-01]
latex_v1:  22%|##1       | 654/3000 [15:14<41:43,  1.07s/it, lr: 1.0e-04 loss: 6.125e-01]
latex_v1:  22%|##1       | 654/3000 [15:14<41:43,  1.07s/it, lr: 1.0e-04 loss: 6.125e-01]
latex_v1:  22%|##1       | 654/3000 [15:16<41:43,  1.07s/it, lr: 1.0e-04 loss: 4.911e-01]
latex_v1:  22%|##1       | 654/3000 [15:16<41:43,  1.07s/it, lr: 1.0e-04 loss: 4.911e-01]
latex_v1:  22%|##1       | 655/3000 [15:16<50:36,  1.29s/it, lr: 1.0e-04 loss: 4.911e-01]
latex_v1:  22%|##1       | 655/3000 [15:16<50:36,  1.29s/it, lr: 1.0e-04 loss: 4.911e-01]
latex_v1:  22%|##1       | 655/3000 [15:17<50:36,  1.29s/it, lr: 1.0e-04 loss: 2.686e-01]
latex_v1:  22%|##1       | 655/3000 [15:17<50:36,  1.29s/it, lr: 1.0e-04 loss: 2.686e-01]
latex_v1:  22%|##1       | 656/3000 [15:17<51:19,  1.31s/it, lr: 1.0e-04 loss: 2.686e-01]
latex_v1:  22%|##1       | 656/3000 [15:17<51:19,  1.31s/it, lr: 1.0e-04 loss: 2.686e-01]
latex_v1:  22%|##1       | 656/3000 [15:18<51:19,  1.31s/it, lr: 1.0e-04 loss: 2.954e-01]
latex_v1:  22%|##1       | 656/3000 [15:18<51:19,  1.31s/it, lr: 1.0e-04 loss: 2.954e-01]
latex_v1:  22%|##1       | 657/3000 [15:18<44:53,  1.15s/it, lr: 1.0e-04 loss: 2.954e-01]
latex_v1:  22%|##1       | 657/3000 [15:18<44:53,  1.15s/it, lr: 1.0e-04 loss: 2.954e-01]
latex_v1:  22%|##1       | 657/3000 [15:19<44:53,  1.15s/it, lr: 1.0e-04 loss: 5.321e-01]
latex_v1:  22%|##1       | 657/3000 [15:19<44:53,  1.15s/it, lr: 1.0e-04 loss: 5.321e-01]
latex_v1:  22%|##1       | 658/3000 [15:19<40:20,  1.03s/it, lr: 1.0e-04 loss: 5.321e-01]
latex_v1:  22%|##1       | 658/3000 [15:19<40:20,  1.03s/it, lr: 1.0e-04 loss: 5.321e-01]
latex_v1:  22%|##1       | 658/3000 [15:20<40:20,  1.03s/it, lr: 1.0e-04 loss: 2.596e-01]
latex_v1:  22%|##1       | 658/3000 [15:20<40:20,  1.03s/it, lr: 1.0e-04 loss: 2.596e-01]
latex_v1:  22%|##1       | 659/3000 [15:20<41:57,  1.08s/it, lr: 1.0e-04 loss: 2.596e-01]
latex_v1:  22%|##1       | 659/3000 [15:20<41:57,  1.08s/it, lr: 1.0e-04 loss: 2.596e-01]
latex_v1:  22%|##1       | 659/3000 [15:22<41:57,  1.08s/it, lr: 1.0e-04 loss: 4.892e-02]
latex_v1:  22%|##1       | 659/3000 [15:22<41:57,  1.08s/it, lr: 1.0e-04 loss: 4.892e-02]
latex_v1:  22%|##2       | 660/3000 [15:23<41:56,  1.08s/it, lr: 1.0e-04 loss: 2.224e-01]
latex_v1:  22%|##2       | 660/3000 [15:23<41:56,  1.08s/it, lr: 1.0e-04 loss: 2.224e-01]
latex_v1:  22%|##2       | 661/3000 [15:23<29:22,  1.33it/s, lr: 1.0e-04 loss: 2.224e-01]
latex_v1:  22%|##2       | 661/3000 [15:23<29:22,  1.33it/s, lr: 1.0e-04 loss: 2.224e-01]
latex_v1:  22%|##2       | 661/3000 [15:25<29:22,  1.33it/s, lr: 1.0e-04 loss: 5.923e-01]
latex_v1:  22%|##2       | 661/3000 [15:25<29:22,  1.33it/s, lr: 1.0e-04 loss: 5.923e-01]
latex_v1:  22%|##2       | 662/3000 [15:25<49:28,  1.27s/it, lr: 1.0e-04 loss: 5.923e-01]
latex_v1:  22%|##2       | 662/3000 [15:25<49:28,  1.27s/it, lr: 1.0e-04 loss: 5.923e-01]
latex_v1:  22%|##2       | 662/3000 [15:27<49:28,  1.27s/it, lr: 1.0e-04 loss: 1.530e-01]
latex_v1:  22%|##2       | 662/3000 [15:27<49:28,  1.27s/it, lr: 1.0e-04 loss: 1.530e-01]
latex_v1:  22%|##2       | 663/3000 [15:27<52:06,  1.34s/it, lr: 1.0e-04 loss: 1.530e-01]
latex_v1:  22%|##2       | 663/3000 [15:27<52:06,  1.34s/it, lr: 1.0e-04 loss: 1.530e-01]
latex_v1:  22%|##2       | 663/3000 [15:28<52:06,  1.34s/it, lr: 1.0e-04 loss: 1.383e-01]
latex_v1:  22%|##2       | 663/3000 [15:28<52:06,  1.34s/it, lr: 1.0e-04 loss: 1.383e-01]
latex_v1:  22%|##2       | 664/3000 [15:28<45:54,  1.18s/it, lr: 1.0e-04 loss: 1.383e-01]
latex_v1:  22%|##2       | 664/3000 [15:28<45:54,  1.18s/it, lr: 1.0e-04 loss: 1.383e-01]
latex_v1:  22%|##2       | 664/3000 [15:29<45:54,  1.18s/it, lr: 1.0e-04 loss: 3.434e-01]
latex_v1:  22%|##2       | 664/3000 [15:29<45:54,  1.18s/it, lr: 1.0e-04 loss: 3.434e-01]
latex_v1:  22%|##2       | 665/3000 [15:29<48:47,  1.25s/it, lr: 1.0e-04 loss: 3.434e-01]
latex_v1:  22%|##2       | 665/3000 [15:29<48:47,  1.25s/it, lr: 1.0e-04 loss: 3.434e-01]
latex_v1:  22%|##2       | 665/3000 [15:31<48:47,  1.25s/it, lr: 1.0e-04 loss: 1.611e-01]
latex_v1:  22%|##2       | 665/3000 [15:31<48:47,  1.25s/it, lr: 1.0e-04 loss: 1.611e-01]
latex_v1:  22%|##2       | 666/3000 [15:31<55:05,  1.42s/it, lr: 1.0e-04 loss: 1.611e-01]
latex_v1:  22%|##2       | 666/3000 [15:31<55:05,  1.42s/it, lr: 1.0e-04 loss: 1.611e-01]
latex_v1:  22%|##2       | 666/3000 [15:32<55:05,  1.42s/it, lr: 1.0e-04 loss: 2.504e-01]
latex_v1:  22%|##2       | 666/3000 [15:32<55:05,  1.42s/it, lr: 1.0e-04 loss: 2.504e-01]
latex_v1:  22%|##2       | 667/3000 [15:32<50:23,  1.30s/it, lr: 1.0e-04 loss: 2.504e-01]
latex_v1:  22%|##2       | 667/3000 [15:32<50:23,  1.30s/it, lr: 1.0e-04 loss: 2.504e-01]
latex_v1:  22%|##2       | 667/3000 [15:35<50:23,  1.30s/it, lr: 1.0e-04 loss: 5.230e-01]
latex_v1:  22%|##2       | 667/3000 [15:35<50:23,  1.30s/it, lr: 1.0e-04 loss: 5.230e-01]
latex_v1:  22%|##2       | 668/3000 [15:35<1:07:56,  1.75s/it, lr: 1.0e-04 loss: 5.230e-01]
latex_v1:  22%|##2       | 668/3000 [15:35<1:07:56,  1.75s/it, lr: 1.0e-04 loss: 5.230e-01]
latex_v1:  22%|##2       | 668/3000 [15:38<1:07:56,  1.75s/it, lr: 1.0e-04 loss: 6.845e-01]
latex_v1:  22%|##2       | 668/3000 [15:38<1:07:56,  1.75s/it, lr: 1.0e-04 loss: 6.845e-01]
latex_v1:  22%|##2       | 669/3000 [15:38<1:20:31,  2.07s/it, lr: 1.0e-04 loss: 6.845e-01]
latex_v1:  22%|##2       | 669/3000 [15:38<1:20:31,  2.07s/it, lr: 1.0e-04 loss: 6.845e-01]
latex_v1:  22%|##2       | 669/3000 [15:40<1:20:31,  2.07s/it, lr: 1.0e-04 loss: 6.252e-02]
latex_v1:  22%|##2       | 669/3000 [15:40<1:20:31,  2.07s/it, lr: 1.0e-04 loss: 6.252e-02]
latex_v1:  22%|##2       | 670/3000 [15:41<1:20:29,  2.07s/it, lr: 1.0e-04 loss: 5.257e-01]
latex_v1:  22%|##2       | 670/3000 [15:41<1:20:29,  2.07s/it, lr: 1.0e-04 loss: 5.257e-01]
latex_v1:  22%|##2       | 671/3000 [15:41<50:13,  1.29s/it, lr: 1.0e-04 loss: 5.257e-01]  
latex_v1:  22%|##2       | 671/3000 [15:41<50:13,  1.29s/it, lr: 1.0e-04 loss: 5.257e-01]  
latex_v1:  22%|##2       | 671/3000 [15:42<50:13,  1.29s/it, lr: 1.0e-04 loss: 1.202e-01]
latex_v1:  22%|##2       | 671/3000 [15:42<50:13,  1.29s/it, lr: 1.0e-04 loss: 1.202e-01]
latex_v1:  22%|##2       | 672/3000 [15:42<45:12,  1.17s/it, lr: 1.0e-04 loss: 1.202e-01]
latex_v1:  22%|##2       | 672/3000 [15:42<45:12,  1.17s/it, lr: 1.0e-04 loss: 1.202e-01]
latex_v1:  22%|##2       | 672/3000 [15:43<45:12,  1.17s/it, lr: 1.0e-04 loss: 3.852e-01]
latex_v1:  22%|##2       | 672/3000 [15:43<45:12,  1.17s/it, lr: 1.0e-04 loss: 3.852e-01]
latex_v1:  22%|##2       | 673/3000 [15:43<40:57,  1.06s/it, lr: 1.0e-04 loss: 3.852e-01]
latex_v1:  22%|##2       | 673/3000 [15:43<40:57,  1.06s/it, lr: 1.0e-04 loss: 3.852e-01]
latex_v1:  22%|##2       | 673/3000 [15:46<40:57,  1.06s/it, lr: 1.0e-04 loss: 7.268e-02]
latex_v1:  22%|##2       | 673/3000 [15:46<40:57,  1.06s/it, lr: 1.0e-04 loss: 7.268e-02]
latex_v1:  22%|##2       | 674/3000 [15:46<59:26,  1.53s/it, lr: 1.0e-04 loss: 7.268e-02]
latex_v1:  22%|##2       | 674/3000 [15:46<59:26,  1.53s/it, lr: 1.0e-04 loss: 7.268e-02]
latex_v1:  22%|##2       | 674/3000 [15:47<59:26,  1.53s/it, lr: 1.0e-04 loss: 5.528e-01]
latex_v1:  22%|##2       | 674/3000 [15:47<59:26,  1.53s/it, lr: 1.0e-04 loss: 5.528e-01]
latex_v1:  22%|##2       | 675/3000 [15:47<58:10,  1.50s/it, lr: 1.0e-04 loss: 5.528e-01]
latex_v1:  22%|##2       | 675/3000 [15:47<58:10,  1.50s/it, lr: 1.0e-04 loss: 5.528e-01]
latex_v1:  22%|##2       | 675/3000 [15:50<58:10,  1.50s/it, lr: 1.0e-04 loss: 5.412e-02]
latex_v1:  22%|##2       | 675/3000 [15:50<58:10,  1.50s/it, lr: 1.0e-04 loss: 5.412e-02]
latex_v1:  23%|##2       | 676/3000 [15:50<1:13:38,  1.90s/it, lr: 1.0e-04 loss: 5.412e-02]
latex_v1:  23%|##2       | 676/3000 [15:50<1:13:38,  1.90s/it, lr: 1.0e-04 loss: 5.412e-02]
latex_v1:  23%|##2       | 676/3000 [15:51<1:13:38,  1.90s/it, lr: 1.0e-04 loss: 1.277e-01]
latex_v1:  23%|##2       | 676/3000 [15:51<1:13:38,  1.90s/it, lr: 1.0e-04 loss: 1.277e-01]
latex_v1:  23%|##2       | 677/3000 [15:51<1:09:29,  1.79s/it, lr: 1.0e-04 loss: 1.277e-01]
latex_v1:  23%|##2       | 677/3000 [15:51<1:09:29,  1.79s/it, lr: 1.0e-04 loss: 1.277e-01]
latex_v1:  23%|##2       | 677/3000 [15:52<1:09:29,  1.79s/it, lr: 1.0e-04 loss: 3.075e-01]
latex_v1:  23%|##2       | 677/3000 [15:52<1:09:29,  1.79s/it, lr: 1.0e-04 loss: 3.075e-01]
latex_v1:  23%|##2       | 678/3000 [15:52<57:33,  1.49s/it, lr: 1.0e-04 loss: 3.075e-01]  
latex_v1:  23%|##2       | 678/3000 [15:52<57:33,  1.49s/it, lr: 1.0e-04 loss: 3.075e-01]  
latex_v1:  23%|##2       | 678/3000 [15:53<57:33,  1.49s/it, lr: 1.0e-04 loss: 3.963e-01]
latex_v1:  23%|##2       | 678/3000 [15:53<57:33,  1.49s/it, lr: 1.0e-04 loss: 3.963e-01]
latex_v1:  23%|##2       | 679/3000 [15:53<49:04,  1.27s/it, lr: 1.0e-04 loss: 3.963e-01]
latex_v1:  23%|##2       | 679/3000 [15:53<49:04,  1.27s/it, lr: 1.0e-04 loss: 3.963e-01]
latex_v1:  23%|##2       | 679/3000 [15:54<49:04,  1.27s/it, lr: 1.0e-04 loss: 2.958e-01]
latex_v1:  23%|##2       | 679/3000 [15:54<49:04,  1.27s/it, lr: 1.0e-04 loss: 2.958e-01]
latex_v1:  23%|##2       | 680/3000 [15:55<49:03,  1.27s/it, lr: 1.0e-04 loss: 2.723e-01]
latex_v1:  23%|##2       | 680/3000 [15:55<49:03,  1.27s/it, lr: 1.0e-04 loss: 2.723e-01]
latex_v1:  23%|##2       | 681/3000 [15:55<35:15,  1.10it/s, lr: 1.0e-04 loss: 2.723e-01]
latex_v1:  23%|##2       | 681/3000 [15:55<35:15,  1.10it/s, lr: 1.0e-04 loss: 2.723e-01]
latex_v1:  23%|##2       | 681/3000 [15:56<35:15,  1.10it/s, lr: 1.0e-04 loss: 4.416e-01]
latex_v1:  23%|##2       | 681/3000 [15:56<35:15,  1.10it/s, lr: 1.0e-04 loss: 4.416e-01]
latex_v1:  23%|##2       | 682/3000 [15:56<33:46,  1.14it/s, lr: 1.0e-04 loss: 4.416e-01]
latex_v1:  23%|##2       | 682/3000 [15:56<33:46,  1.14it/s, lr: 1.0e-04 loss: 4.416e-01]
latex_v1:  23%|##2       | 682/3000 [15:58<33:46,  1.14it/s, lr: 1.0e-04 loss: 1.069e-01]
latex_v1:  23%|##2       | 682/3000 [15:58<33:46,  1.14it/s, lr: 1.0e-04 loss: 1.069e-01]
latex_v1:  23%|##2       | 683/3000 [15:58<43:47,  1.13s/it, lr: 1.0e-04 loss: 1.069e-01]
latex_v1:  23%|##2       | 683/3000 [15:58<43:47,  1.13s/it, lr: 1.0e-04 loss: 1.069e-01]
latex_v1:  23%|##2       | 683/3000 [15:59<43:47,  1.13s/it, lr: 1.0e-04 loss: 3.617e-01]
latex_v1:  23%|##2       | 683/3000 [15:59<43:47,  1.13s/it, lr: 1.0e-04 loss: 3.617e-01]
latex_v1:  23%|##2       | 684/3000 [15:59<41:52,  1.08s/it, lr: 1.0e-04 loss: 3.617e-01]
latex_v1:  23%|##2       | 684/3000 [15:59<41:52,  1.08s/it, lr: 1.0e-04 loss: 3.617e-01]
latex_v1:  23%|##2       | 684/3000 [16:01<41:52,  1.08s/it, lr: 1.0e-04 loss: 4.451e-01]
latex_v1:  23%|##2       | 684/3000 [16:01<41:52,  1.08s/it, lr: 1.0e-04 loss: 4.451e-01]
latex_v1:  23%|##2       | 685/3000 [16:01<48:41,  1.26s/it, lr: 1.0e-04 loss: 4.451e-01]
latex_v1:  23%|##2       | 685/3000 [16:01<48:41,  1.26s/it, lr: 1.0e-04 loss: 4.451e-01]
latex_v1:  23%|##2       | 685/3000 [16:04<48:41,  1.26s/it, lr: 1.0e-04 loss: 2.249e-01]
latex_v1:  23%|##2       | 685/3000 [16:04<48:41,  1.26s/it, lr: 1.0e-04 loss: 2.249e-01]
latex_v1:  23%|##2       | 686/3000 [16:04<1:05:56,  1.71s/it, lr: 1.0e-04 loss: 2.249e-01]
latex_v1:  23%|##2       | 686/3000 [16:04<1:05:56,  1.71s/it, lr: 1.0e-04 loss: 2.249e-01]
latex_v1:  23%|##2       | 686/3000 [16:05<1:05:56,  1.71s/it, lr: 1.0e-04 loss: 4.504e-01]
latex_v1:  23%|##2       | 686/3000 [16:05<1:05:56,  1.71s/it, lr: 1.0e-04 loss: 4.504e-01]
latex_v1:  23%|##2       | 687/3000 [16:05<1:04:01,  1.66s/it, lr: 1.0e-04 loss: 4.504e-01]
latex_v1:  23%|##2       | 687/3000 [16:05<1:04:01,  1.66s/it, lr: 1.0e-04 loss: 4.504e-01]
latex_v1:  23%|##2       | 687/3000 [16:06<1:04:01,  1.66s/it, lr: 1.0e-04 loss: 2.480e-01]
latex_v1:  23%|##2       | 687/3000 [16:06<1:04:01,  1.66s/it, lr: 1.0e-04 loss: 2.480e-01]
latex_v1:  23%|##2       | 688/3000 [16:06<1:00:14,  1.56s/it, lr: 1.0e-04 loss: 2.480e-01]
latex_v1:  23%|##2       | 688/3000 [16:06<1:00:14,  1.56s/it, lr: 1.0e-04 loss: 2.480e-01]
latex_v1:  23%|##2       | 688/3000 [16:07<1:00:14,  1.56s/it, lr: 1.0e-04 loss: 2.121e-01]
latex_v1:  23%|##2       | 688/3000 [16:07<1:00:14,  1.56s/it, lr: 1.0e-04 loss: 2.121e-01]
latex_v1:  23%|##2       | 689/3000 [16:07<50:57,  1.32s/it, lr: 1.0e-04 loss: 2.121e-01]  
latex_v1:  23%|##2       | 689/3000 [16:07<50:57,  1.32s/it, lr: 1.0e-04 loss: 2.121e-01]  
latex_v1:  23%|##2       | 689/3000 [16:09<50:57,  1.32s/it, lr: 1.0e-04 loss: 6.610e-01]
latex_v1:  23%|##2       | 689/3000 [16:09<50:57,  1.32s/it, lr: 1.0e-04 loss: 6.610e-01]
latex_v1:  23%|##3       | 690/3000 [16:10<50:55,  1.32s/it, lr: 1.0e-04 loss: 2.564e-01]
latex_v1:  23%|##3       | 690/3000 [16:10<50:55,  1.32s/it, lr: 1.0e-04 loss: 2.564e-01]
latex_v1:  23%|##3       | 691/3000 [16:10<39:59,  1.04s/it, lr: 1.0e-04 loss: 2.564e-01]
latex_v1:  23%|##3       | 691/3000 [16:10<39:59,  1.04s/it, lr: 1.0e-04 loss: 2.564e-01]
latex_v1:  23%|##3       | 691/3000 [16:11<39:59,  1.04s/it, lr: 1.0e-04 loss: 7.315e-01]
latex_v1:  23%|##3       | 691/3000 [16:11<39:59,  1.04s/it, lr: 1.0e-04 loss: 7.315e-01]
latex_v1:  23%|##3       | 692/3000 [16:11<37:13,  1.03it/s, lr: 1.0e-04 loss: 7.315e-01]
latex_v1:  23%|##3       | 692/3000 [16:11<37:13,  1.03it/s, lr: 1.0e-04 loss: 7.315e-01]
latex_v1:  23%|##3       | 692/3000 [16:12<37:13,  1.03it/s, lr: 1.0e-04 loss: 1.990e-01]
latex_v1:  23%|##3       | 692/3000 [16:12<37:13,  1.03it/s, lr: 1.0e-04 loss: 1.990e-01]
latex_v1:  23%|##3       | 693/3000 [16:12<39:13,  1.02s/it, lr: 1.0e-04 loss: 1.990e-01]
latex_v1:  23%|##3       | 693/3000 [16:12<39:13,  1.02s/it, lr: 1.0e-04 loss: 1.990e-01]
latex_v1:  23%|##3       | 693/3000 [16:13<39:13,  1.02s/it, lr: 1.0e-04 loss: 4.669e-01]
latex_v1:  23%|##3       | 693/3000 [16:13<39:13,  1.02s/it, lr: 1.0e-04 loss: 4.669e-01]
latex_v1:  23%|##3       | 694/3000 [16:13<36:31,  1.05it/s, lr: 1.0e-04 loss: 4.669e-01]
latex_v1:  23%|##3       | 694/3000 [16:13<36:31,  1.05it/s, lr: 1.0e-04 loss: 4.669e-01]
latex_v1:  23%|##3       | 694/3000 [16:14<36:31,  1.05it/s, lr: 1.0e-04 loss: 4.099e-01]
latex_v1:  23%|##3       | 694/3000 [16:14<36:31,  1.05it/s, lr: 1.0e-04 loss: 4.099e-01]
latex_v1:  23%|##3       | 695/3000 [16:14<36:43,  1.05it/s, lr: 1.0e-04 loss: 4.099e-01]
latex_v1:  23%|##3       | 695/3000 [16:14<36:43,  1.05it/s, lr: 1.0e-04 loss: 4.099e-01]
latex_v1:  23%|##3       | 695/3000 [16:14<36:43,  1.05it/s, lr: 1.0e-04 loss: 7.365e-01]
latex_v1:  23%|##3       | 695/3000 [16:14<36:43,  1.05it/s, lr: 1.0e-04 loss: 7.365e-01]
latex_v1:  23%|##3       | 696/3000 [16:14<34:23,  1.12it/s, lr: 1.0e-04 loss: 7.365e-01]
latex_v1:  23%|##3       | 696/3000 [16:14<34:23,  1.12it/s, lr: 1.0e-04 loss: 7.365e-01]
latex_v1:  23%|##3       | 696/3000 [16:15<34:23,  1.12it/s, lr: 1.0e-04 loss: 4.177e-01]
latex_v1:  23%|##3       | 696/3000 [16:15<34:23,  1.12it/s, lr: 1.0e-04 loss: 4.177e-01]
latex_v1:  23%|##3       | 697/3000 [16:15<32:42,  1.17it/s, lr: 1.0e-04 loss: 4.177e-01]
latex_v1:  23%|##3       | 697/3000 [16:15<32:42,  1.17it/s, lr: 1.0e-04 loss: 4.177e-01]
latex_v1:  23%|##3       | 697/3000 [16:18<32:42,  1.17it/s, lr: 1.0e-04 loss: 1.169e-01]
latex_v1:  23%|##3       | 697/3000 [16:18<32:42,  1.17it/s, lr: 1.0e-04 loss: 1.169e-01]
latex_v1:  23%|##3       | 698/3000 [16:18<55:17,  1.44s/it, lr: 1.0e-04 loss: 1.169e-01]
latex_v1:  23%|##3       | 698/3000 [16:18<55:17,  1.44s/it, lr: 1.0e-04 loss: 1.169e-01]
latex_v1:  23%|##3       | 698/3000 [16:19<55:17,  1.44s/it, lr: 1.0e-04 loss: 7.664e-01]
latex_v1:  23%|##3       | 698/3000 [16:19<55:17,  1.44s/it, lr: 1.0e-04 loss: 7.664e-01]
latex_v1:  23%|##3       | 699/3000 [16:19<51:39,  1.35s/it, lr: 1.0e-04 loss: 7.664e-01]
latex_v1:  23%|##3       | 699/3000 [16:19<51:39,  1.35s/it, lr: 1.0e-04 loss: 7.664e-01]
latex_v1:  23%|##3       | 699/3000 [16:20<51:39,  1.35s/it, lr: 1.0e-04 loss: 3.357e-01]
latex_v1:  23%|##3       | 699/3000 [16:20<51:39,  1.35s/it, lr: 1.0e-04 loss: 3.357e-01]
latex_v1:  23%|##3       | 700/3000 [16:22<51:38,  1.35s/it, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  23%|##3       | 700/3000 [16:22<51:38,  1.35s/it, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  23%|##3       | 701/3000 [16:22<41:22,  1.08s/it, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  23%|##3       | 701/3000 [16:22<41:22,  1.08s/it, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  23%|##3       | 701/3000 [16:22<41:22,  1.08s/it, lr: 1.0e-04 loss: 1.884e-01]
latex_v1:  23%|##3       | 701/3000 [16:22<41:22,  1.08s/it, lr: 1.0e-04 loss: 1.884e-01]
latex_v1:  23%|##3       | 702/3000 [16:22<38:24,  1.00s/it, lr: 1.0e-04 loss: 1.884e-01]
latex_v1:  23%|##3       | 702/3000 [16:22<38:24,  1.00s/it, lr: 1.0e-04 loss: 1.884e-01]
latex_v1:  23%|##3       | 702/3000 [16:24<38:24,  1.00s/it, lr: 1.0e-04 loss: 7.101e-01]
latex_v1:  23%|##3       | 702/3000 [16:24<38:24,  1.00s/it, lr: 1.0e-04 loss: 7.101e-01]
latex_v1:  23%|##3       | 703/3000 [16:24<42:31,  1.11s/it, lr: 1.0e-04 loss: 7.101e-01]
latex_v1:  23%|##3       | 703/3000 [16:24<42:31,  1.11s/it, lr: 1.0e-04 loss: 7.101e-01]
latex_v1:  23%|##3       | 703/3000 [16:25<42:31,  1.11s/it, lr: 1.0e-04 loss: 2.970e-01]
latex_v1:  23%|##3       | 703/3000 [16:25<42:31,  1.11s/it, lr: 1.0e-04 loss: 2.970e-01]
latex_v1:  23%|##3       | 704/3000 [16:25<45:36,  1.19s/it, lr: 1.0e-04 loss: 2.970e-01]
latex_v1:  23%|##3       | 704/3000 [16:25<45:36,  1.19s/it, lr: 1.0e-04 loss: 2.970e-01]
latex_v1:  23%|##3       | 704/3000 [16:27<45:36,  1.19s/it, lr: 1.0e-04 loss: 2.781e-01]
latex_v1:  23%|##3       | 704/3000 [16:27<45:36,  1.19s/it, lr: 1.0e-04 loss: 2.781e-01]
latex_v1:  24%|##3       | 705/3000 [16:27<49:18,  1.29s/it, lr: 1.0e-04 loss: 2.781e-01]
latex_v1:  24%|##3       | 705/3000 [16:27<49:18,  1.29s/it, lr: 1.0e-04 loss: 2.781e-01]
latex_v1:  24%|##3       | 705/3000 [16:28<49:18,  1.29s/it, lr: 1.0e-04 loss: 1.037e-01]
latex_v1:  24%|##3       | 705/3000 [16:28<49:18,  1.29s/it, lr: 1.0e-04 loss: 1.037e-01]
latex_v1:  24%|##3       | 706/3000 [16:28<51:07,  1.34s/it, lr: 1.0e-04 loss: 1.037e-01]
latex_v1:  24%|##3       | 706/3000 [16:28<51:07,  1.34s/it, lr: 1.0e-04 loss: 1.037e-01]
latex_v1:  24%|##3       | 706/3000 [16:31<51:07,  1.34s/it, lr: 1.0e-04 loss: 4.132e-01]
latex_v1:  24%|##3       | 706/3000 [16:31<51:07,  1.34s/it, lr: 1.0e-04 loss: 4.132e-01]
latex_v1:  24%|##3       | 707/3000 [16:31<1:05:37,  1.72s/it, lr: 1.0e-04 loss: 4.132e-01]
latex_v1:  24%|##3       | 707/3000 [16:31<1:05:37,  1.72s/it, lr: 1.0e-04 loss: 4.132e-01]
latex_v1:  24%|##3       | 707/3000 [16:32<1:05:37,  1.72s/it, lr: 1.0e-04 loss: 1.767e-01]
latex_v1:  24%|##3       | 707/3000 [16:32<1:05:37,  1.72s/it, lr: 1.0e-04 loss: 1.767e-01]
latex_v1:  24%|##3       | 708/3000 [16:32<1:03:44,  1.67s/it, lr: 1.0e-04 loss: 1.767e-01]
latex_v1:  24%|##3       | 708/3000 [16:32<1:03:44,  1.67s/it, lr: 1.0e-04 loss: 1.767e-01]
latex_v1:  24%|##3       | 708/3000 [16:34<1:03:44,  1.67s/it, lr: 1.0e-04 loss: 6.351e-01]
latex_v1:  24%|##3       | 708/3000 [16:34<1:03:44,  1.67s/it, lr: 1.0e-04 loss: 6.351e-01]
latex_v1:  24%|##3       | 709/3000 [16:34<1:00:28,  1.58s/it, lr: 1.0e-04 loss: 6.351e-01]
latex_v1:  24%|##3       | 709/3000 [16:34<1:00:28,  1.58s/it, lr: 1.0e-04 loss: 6.351e-01]
latex_v1:  24%|##3       | 709/3000 [16:34<1:00:28,  1.58s/it, lr: 1.0e-04 loss: 2.043e-01]
latex_v1:  24%|##3       | 709/3000 [16:34<1:00:28,  1.58s/it, lr: 1.0e-04 loss: 2.043e-01]
latex_v1:  24%|##3       | 710/3000 [16:36<1:00:26,  1.58s/it, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  24%|##3       | 710/3000 [16:36<1:00:26,  1.58s/it, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  24%|##3       | 711/3000 [16:36<45:29,  1.19s/it, lr: 1.0e-04 loss: 4.547e-01]  
latex_v1:  24%|##3       | 711/3000 [16:36<45:29,  1.19s/it, lr: 1.0e-04 loss: 4.547e-01]  
latex_v1:  24%|##3       | 711/3000 [16:37<45:29,  1.19s/it, lr: 1.0e-04 loss: 5.142e-01]
latex_v1:  24%|##3       | 711/3000 [16:37<45:29,  1.19s/it, lr: 1.0e-04 loss: 5.142e-01]
latex_v1:  24%|##3       | 712/3000 [16:37<41:19,  1.08s/it, lr: 1.0e-04 loss: 5.142e-01]
latex_v1:  24%|##3       | 712/3000 [16:37<41:19,  1.08s/it, lr: 1.0e-04 loss: 5.142e-01]
latex_v1:  24%|##3       | 712/3000 [16:38<41:19,  1.08s/it, lr: 1.0e-04 loss: 5.628e-01]
latex_v1:  24%|##3       | 712/3000 [16:38<41:19,  1.08s/it, lr: 1.0e-04 loss: 5.628e-01]
latex_v1:  24%|##3       | 713/3000 [16:38<41:03,  1.08s/it, lr: 1.0e-04 loss: 5.628e-01]
latex_v1:  24%|##3       | 713/3000 [16:38<41:03,  1.08s/it, lr: 1.0e-04 loss: 5.628e-01]
latex_v1:  24%|##3       | 713/3000 [16:38<41:03,  1.08s/it, lr: 1.0e-04 loss: 6.177e-01]
latex_v1:  24%|##3       | 713/3000 [16:38<41:03,  1.08s/it, lr: 1.0e-04 loss: 6.177e-01]
latex_v1:  24%|##3       | 714/3000 [16:38<37:51,  1.01it/s, lr: 1.0e-04 loss: 6.177e-01]
latex_v1:  24%|##3       | 714/3000 [16:38<37:51,  1.01it/s, lr: 1.0e-04 loss: 6.177e-01]
latex_v1:  24%|##3       | 714/3000 [16:40<37:51,  1.01it/s, lr: 1.0e-04 loss: 3.750e-01]
latex_v1:  24%|##3       | 714/3000 [16:40<37:51,  1.01it/s, lr: 1.0e-04 loss: 3.750e-01]
latex_v1:  24%|##3       | 715/3000 [16:40<41:30,  1.09s/it, lr: 1.0e-04 loss: 3.750e-01]
latex_v1:  24%|##3       | 715/3000 [16:40<41:30,  1.09s/it, lr: 1.0e-04 loss: 3.750e-01]
latex_v1:  24%|##3       | 715/3000 [16:43<41:30,  1.09s/it, lr: 1.0e-04 loss: 1.067e-01]
latex_v1:  24%|##3       | 715/3000 [16:43<41:30,  1.09s/it, lr: 1.0e-04 loss: 1.067e-01]
latex_v1:  24%|##3       | 716/3000 [16:43<58:59,  1.55s/it, lr: 1.0e-04 loss: 1.067e-01]
latex_v1:  24%|##3       | 716/3000 [16:43<58:59,  1.55s/it, lr: 1.0e-04 loss: 1.067e-01]
latex_v1:  24%|##3       | 716/3000 [16:45<58:59,  1.55s/it, lr: 1.0e-04 loss: 1.764e-01]
latex_v1:  24%|##3       | 716/3000 [16:45<58:59,  1.55s/it, lr: 1.0e-04 loss: 1.764e-01]
latex_v1:  24%|##3       | 717/3000 [16:45<1:06:10,  1.74s/it, lr: 1.0e-04 loss: 1.764e-01]
latex_v1:  24%|##3       | 717/3000 [16:45<1:06:10,  1.74s/it, lr: 1.0e-04 loss: 1.764e-01]
latex_v1:  24%|##3       | 717/3000 [16:46<1:06:10,  1.74s/it, lr: 1.0e-04 loss: 1.802e-01]
latex_v1:  24%|##3       | 717/3000 [16:46<1:06:10,  1.74s/it, lr: 1.0e-04 loss: 1.802e-01]
latex_v1:  24%|##3       | 718/3000 [16:46<1:04:20,  1.69s/it, lr: 1.0e-04 loss: 1.802e-01]
latex_v1:  24%|##3       | 718/3000 [16:46<1:04:20,  1.69s/it, lr: 1.0e-04 loss: 1.802e-01]
latex_v1:  24%|##3       | 718/3000 [16:48<1:04:20,  1.69s/it, lr: 1.0e-04 loss: 1.246e-01]
latex_v1:  24%|##3       | 718/3000 [16:48<1:04:20,  1.69s/it, lr: 1.0e-04 loss: 1.246e-01]
latex_v1:  24%|##3       | 719/3000 [16:48<1:02:30,  1.64s/it, lr: 1.0e-04 loss: 1.246e-01]
latex_v1:  24%|##3       | 719/3000 [16:48<1:02:30,  1.64s/it, lr: 1.0e-04 loss: 1.246e-01]
latex_v1:  24%|##3       | 719/3000 [16:49<1:02:30,  1.64s/it, lr: 1.0e-04 loss: 5.223e-01]
latex_v1:  24%|##3       | 719/3000 [16:49<1:02:30,  1.64s/it, lr: 1.0e-04 loss: 5.223e-01]
latex_v1:  24%|##4       | 720/3000 [16:51<1:02:29,  1.64s/it, lr: 1.0e-04 loss: 3.818e-01]
latex_v1:  24%|##4       | 720/3000 [16:51<1:02:29,  1.64s/it, lr: 1.0e-04 loss: 3.818e-01]
latex_v1:  24%|##4       | 721/3000 [16:51<47:18,  1.25s/it, lr: 1.0e-04 loss: 3.818e-01]  
latex_v1:  24%|##4       | 721/3000 [16:51<47:18,  1.25s/it, lr: 1.0e-04 loss: 3.818e-01]  
latex_v1:  24%|##4       | 721/3000 [16:52<47:18,  1.25s/it, lr: 1.0e-04 loss: 1.499e-01]
latex_v1:  24%|##4       | 721/3000 [16:52<47:18,  1.25s/it, lr: 1.0e-04 loss: 1.499e-01]
latex_v1:  24%|##4       | 722/3000 [16:52<52:05,  1.37s/it, lr: 1.0e-04 loss: 1.499e-01]
latex_v1:  24%|##4       | 722/3000 [16:52<52:05,  1.37s/it, lr: 1.0e-04 loss: 1.499e-01]
latex_v1:  24%|##4       | 722/3000 [16:54<52:05,  1.37s/it, lr: 1.0e-04 loss: 6.750e-01]
latex_v1:  24%|##4       | 722/3000 [16:54<52:05,  1.37s/it, lr: 1.0e-04 loss: 6.750e-01]
latex_v1:  24%|##4       | 723/3000 [16:54<52:33,  1.38s/it, lr: 1.0e-04 loss: 6.750e-01]
latex_v1:  24%|##4       | 723/3000 [16:54<52:33,  1.38s/it, lr: 1.0e-04 loss: 6.750e-01]
latex_v1:  24%|##4       | 723/3000 [16:55<52:33,  1.38s/it, lr: 1.0e-04 loss: 5.354e-01]
latex_v1:  24%|##4       | 723/3000 [16:55<52:33,  1.38s/it, lr: 1.0e-04 loss: 5.354e-01]
latex_v1:  24%|##4       | 724/3000 [16:55<45:55,  1.21s/it, lr: 1.0e-04 loss: 5.354e-01]
latex_v1:  24%|##4       | 724/3000 [16:55<45:55,  1.21s/it, lr: 1.0e-04 loss: 5.354e-01]
latex_v1:  24%|##4       | 724/3000 [16:56<45:55,  1.21s/it, lr: 1.0e-04 loss: 2.534e-01]
latex_v1:  24%|##4       | 724/3000 [16:56<45:55,  1.21s/it, lr: 1.0e-04 loss: 2.534e-01]
latex_v1:  24%|##4       | 725/3000 [16:56<48:14,  1.27s/it, lr: 1.0e-04 loss: 2.534e-01]
latex_v1:  24%|##4       | 725/3000 [16:56<48:14,  1.27s/it, lr: 1.0e-04 loss: 2.534e-01]
latex_v1:  24%|##4       | 725/3000 [16:58<48:14,  1.27s/it, lr: 1.0e-04 loss: 2.772e-01]
latex_v1:  24%|##4       | 725/3000 [16:58<48:14,  1.27s/it, lr: 1.0e-04 loss: 2.772e-01]
latex_v1:  24%|##4       | 726/3000 [16:58<51:12,  1.35s/it, lr: 1.0e-04 loss: 2.772e-01]
latex_v1:  24%|##4       | 726/3000 [16:58<51:12,  1.35s/it, lr: 1.0e-04 loss: 2.772e-01]
latex_v1:  24%|##4       | 726/3000 [16:58<51:12,  1.35s/it, lr: 1.0e-04 loss: 2.745e-01]
latex_v1:  24%|##4       | 726/3000 [16:58<51:12,  1.35s/it, lr: 1.0e-04 loss: 2.745e-01]
latex_v1:  24%|##4       | 727/3000 [16:58<44:33,  1.18s/it, lr: 1.0e-04 loss: 2.745e-01]
latex_v1:  24%|##4       | 727/3000 [16:58<44:33,  1.18s/it, lr: 1.0e-04 loss: 2.745e-01]
latex_v1:  24%|##4       | 727/3000 [16:59<44:33,  1.18s/it, lr: 1.0e-04 loss: 7.041e-01]
latex_v1:  24%|##4       | 727/3000 [16:59<44:33,  1.18s/it, lr: 1.0e-04 loss: 7.041e-01]
latex_v1:  24%|##4       | 728/3000 [16:59<39:58,  1.06s/it, lr: 1.0e-04 loss: 7.041e-01]
latex_v1:  24%|##4       | 728/3000 [16:59<39:58,  1.06s/it, lr: 1.0e-04 loss: 7.041e-01]
latex_v1:  24%|##4       | 728/3000 [17:00<39:58,  1.06s/it, lr: 1.0e-04 loss: 6.516e-02]
latex_v1:  24%|##4       | 728/3000 [17:00<39:58,  1.06s/it, lr: 1.0e-04 loss: 6.516e-02]
latex_v1:  24%|##4       | 729/3000 [17:00<36:35,  1.03it/s, lr: 1.0e-04 loss: 6.516e-02]
latex_v1:  24%|##4       | 729/3000 [17:00<36:35,  1.03it/s, lr: 1.0e-04 loss: 6.516e-02]
latex_v1:  24%|##4       | 729/3000 [17:01<36:35,  1.03it/s, lr: 1.0e-04 loss: 6.482e-01]
latex_v1:  24%|##4       | 729/3000 [17:01<36:35,  1.03it/s, lr: 1.0e-04 loss: 6.482e-01]
latex_v1:  24%|##4       | 730/3000 [17:02<36:34,  1.03it/s, lr: 1.0e-04 loss: 3.497e-01]
latex_v1:  24%|##4       | 730/3000 [17:02<36:34,  1.03it/s, lr: 1.0e-04 loss: 3.497e-01]
latex_v1:  24%|##4       | 731/3000 [17:02<28:07,  1.34it/s, lr: 1.0e-04 loss: 3.497e-01]
latex_v1:  24%|##4       | 731/3000 [17:02<28:07,  1.34it/s, lr: 1.0e-04 loss: 3.497e-01]
latex_v1:  24%|##4       | 731/3000 [17:03<28:07,  1.34it/s, lr: 1.0e-04 loss: 3.637e-01]
latex_v1:  24%|##4       | 731/3000 [17:03<28:07,  1.34it/s, lr: 1.0e-04 loss: 3.637e-01]
latex_v1:  24%|##4       | 732/3000 [17:03<32:04,  1.18it/s, lr: 1.0e-04 loss: 3.637e-01]
latex_v1:  24%|##4       | 732/3000 [17:03<32:04,  1.18it/s, lr: 1.0e-04 loss: 3.637e-01]
latex_v1:  24%|##4       | 732/3000 [17:05<32:04,  1.18it/s, lr: 1.0e-04 loss: 3.570e-01]
latex_v1:  24%|##4       | 732/3000 [17:05<32:04,  1.18it/s, lr: 1.0e-04 loss: 3.570e-01]
latex_v1:  24%|##4       | 733/3000 [17:05<39:18,  1.04s/it, lr: 1.0e-04 loss: 3.570e-01]
latex_v1:  24%|##4       | 733/3000 [17:05<39:18,  1.04s/it, lr: 1.0e-04 loss: 3.570e-01]
latex_v1:  24%|##4       | 733/3000 [17:07<39:18,  1.04s/it, lr: 1.0e-04 loss: 3.534e-01]
latex_v1:  24%|##4       | 733/3000 [17:07<39:18,  1.04s/it, lr: 1.0e-04 loss: 3.534e-01]
latex_v1:  24%|##4       | 734/3000 [17:07<48:07,  1.27s/it, lr: 1.0e-04 loss: 3.534e-01]
latex_v1:  24%|##4       | 734/3000 [17:07<48:07,  1.27s/it, lr: 1.0e-04 loss: 3.534e-01]
latex_v1:  24%|##4       | 734/3000 [17:07<48:07,  1.27s/it, lr: 1.0e-04 loss: 5.314e-01]
latex_v1:  24%|##4       | 734/3000 [17:07<48:07,  1.27s/it, lr: 1.0e-04 loss: 5.314e-01]
latex_v1:  24%|##4       | 735/3000 [17:07<42:49,  1.13s/it, lr: 1.0e-04 loss: 5.314e-01]
latex_v1:  24%|##4       | 735/3000 [17:07<42:49,  1.13s/it, lr: 1.0e-04 loss: 5.314e-01]
latex_v1:  24%|##4       | 735/3000 [17:09<42:49,  1.13s/it, lr: 1.0e-04 loss: 3.071e-01]
latex_v1:  24%|##4       | 735/3000 [17:09<42:49,  1.13s/it, lr: 1.0e-04 loss: 3.071e-01]
latex_v1:  25%|##4       | 736/3000 [17:09<47:01,  1.25s/it, lr: 1.0e-04 loss: 3.071e-01]
latex_v1:  25%|##4       | 736/3000 [17:09<47:01,  1.25s/it, lr: 1.0e-04 loss: 3.071e-01]
latex_v1:  25%|##4       | 736/3000 [17:10<47:01,  1.25s/it, lr: 1.0e-04 loss: 4.855e-01]
latex_v1:  25%|##4       | 736/3000 [17:10<47:01,  1.25s/it, lr: 1.0e-04 loss: 4.855e-01]
latex_v1:  25%|##4       | 737/3000 [17:10<44:59,  1.19s/it, lr: 1.0e-04 loss: 4.855e-01]
latex_v1:  25%|##4       | 737/3000 [17:10<44:59,  1.19s/it, lr: 1.0e-04 loss: 4.855e-01]
latex_v1:  25%|##4       | 737/3000 [17:12<44:59,  1.19s/it, lr: 1.0e-04 loss: 4.190e-01]
latex_v1:  25%|##4       | 737/3000 [17:12<44:59,  1.19s/it, lr: 1.0e-04 loss: 4.190e-01]
latex_v1:  25%|##4       | 738/3000 [17:12<48:44,  1.29s/it, lr: 1.0e-04 loss: 4.190e-01]
latex_v1:  25%|##4       | 738/3000 [17:12<48:44,  1.29s/it, lr: 1.0e-04 loss: 4.190e-01]
latex_v1:  25%|##4       | 738/3000 [17:12<48:44,  1.29s/it, lr: 1.0e-04 loss: 9.127e-02]
latex_v1:  25%|##4       | 738/3000 [17:12<48:44,  1.29s/it, lr: 1.0e-04 loss: 9.127e-02]
latex_v1:  25%|##4       | 739/3000 [17:12<42:49,  1.14s/it, lr: 1.0e-04 loss: 9.127e-02]
latex_v1:  25%|##4       | 739/3000 [17:12<42:49,  1.14s/it, lr: 1.0e-04 loss: 9.127e-02]
latex_v1:  25%|##4       | 739/3000 [17:14<42:49,  1.14s/it, lr: 1.0e-04 loss: 1.027e-01]
latex_v1:  25%|##4       | 739/3000 [17:14<42:49,  1.14s/it, lr: 1.0e-04 loss: 1.027e-01]
latex_v1:  25%|##4       | 740/3000 [17:16<42:48,  1.14s/it, lr: 1.0e-04 loss: 5.812e-01]
latex_v1:  25%|##4       | 740/3000 [17:16<42:48,  1.14s/it, lr: 1.0e-04 loss: 5.812e-01]
latex_v1:  25%|##4       | 741/3000 [17:16<35:41,  1.05it/s, lr: 1.0e-04 loss: 5.812e-01]
latex_v1:  25%|##4       | 741/3000 [17:16<35:41,  1.05it/s, lr: 1.0e-04 loss: 5.812e-01]
latex_v1:  25%|##4       | 741/3000 [17:18<35:41,  1.05it/s, lr: 1.0e-04 loss: 2.191e-01]
latex_v1:  25%|##4       | 741/3000 [17:18<35:41,  1.05it/s, lr: 1.0e-04 loss: 2.191e-01]
latex_v1:  25%|##4       | 742/3000 [17:18<44:20,  1.18s/it, lr: 1.0e-04 loss: 2.191e-01]
latex_v1:  25%|##4       | 742/3000 [17:18<44:20,  1.18s/it, lr: 1.0e-04 loss: 2.191e-01]
latex_v1:  25%|##4       | 742/3000 [17:19<44:20,  1.18s/it, lr: 1.0e-04 loss: 1.810e-01]
latex_v1:  25%|##4       | 742/3000 [17:19<44:20,  1.18s/it, lr: 1.0e-04 loss: 1.810e-01]
latex_v1:  25%|##4       | 743/3000 [17:20<52:12,  1.39s/it, lr: 1.0e-04 loss: 1.810e-01]
latex_v1:  25%|##4       | 743/3000 [17:20<52:12,  1.39s/it, lr: 1.0e-04 loss: 1.810e-01]
latex_v1:  25%|##4       | 743/3000 [17:21<52:12,  1.39s/it, lr: 1.0e-04 loss: 4.076e-01]
latex_v1:  25%|##4       | 743/3000 [17:21<52:12,  1.39s/it, lr: 1.0e-04 loss: 4.076e-01]
latex_v1:  25%|##4       | 744/3000 [17:21<46:36,  1.24s/it, lr: 1.0e-04 loss: 4.076e-01]
latex_v1:  25%|##4       | 744/3000 [17:21<46:36,  1.24s/it, lr: 1.0e-04 loss: 4.076e-01]
latex_v1:  25%|##4       | 744/3000 [17:22<46:36,  1.24s/it, lr: 1.0e-04 loss: 2.704e-01]
latex_v1:  25%|##4       | 744/3000 [17:22<46:36,  1.24s/it, lr: 1.0e-04 loss: 2.704e-01]
latex_v1:  25%|##4       | 745/3000 [17:22<41:19,  1.10s/it, lr: 1.0e-04 loss: 2.704e-01]
latex_v1:  25%|##4       | 745/3000 [17:22<41:19,  1.10s/it, lr: 1.0e-04 loss: 2.704e-01]
latex_v1:  25%|##4       | 745/3000 [17:23<41:19,  1.10s/it, lr: 1.0e-04 loss: 5.880e-01]
latex_v1:  25%|##4       | 745/3000 [17:23<41:19,  1.10s/it, lr: 1.0e-04 loss: 5.880e-01]
latex_v1:  25%|##4       | 746/3000 [17:23<45:00,  1.20s/it, lr: 1.0e-04 loss: 5.880e-01]
latex_v1:  25%|##4       | 746/3000 [17:23<45:00,  1.20s/it, lr: 1.0e-04 loss: 5.880e-01]
latex_v1:  25%|##4       | 746/3000 [17:24<45:00,  1.20s/it, lr: 1.0e-04 loss: 1.700e-01]
latex_v1:  25%|##4       | 746/3000 [17:24<45:00,  1.20s/it, lr: 1.0e-04 loss: 1.700e-01]
latex_v1:  25%|##4       | 747/3000 [17:24<39:57,  1.06s/it, lr: 1.0e-04 loss: 1.700e-01]
latex_v1:  25%|##4       | 747/3000 [17:24<39:57,  1.06s/it, lr: 1.0e-04 loss: 1.700e-01]
latex_v1:  25%|##4       | 747/3000 [17:25<39:57,  1.06s/it, lr: 1.0e-04 loss: 1.659e-01]
latex_v1:  25%|##4       | 747/3000 [17:25<39:57,  1.06s/it, lr: 1.0e-04 loss: 1.659e-01]
latex_v1:  25%|##4       | 748/3000 [17:25<45:07,  1.20s/it, lr: 1.0e-04 loss: 1.659e-01]
latex_v1:  25%|##4       | 748/3000 [17:25<45:07,  1.20s/it, lr: 1.0e-04 loss: 1.659e-01]
latex_v1:  25%|##4       | 748/3000 [17:27<45:07,  1.20s/it, lr: 1.0e-04 loss: 1.482e-01]
latex_v1:  25%|##4       | 748/3000 [17:27<45:07,  1.20s/it, lr: 1.0e-04 loss: 1.482e-01]
latex_v1:  25%|##4       | 749/3000 [17:27<46:22,  1.24s/it, lr: 1.0e-04 loss: 1.482e-01]
latex_v1:  25%|##4       | 749/3000 [17:27<46:22,  1.24s/it, lr: 1.0e-04 loss: 1.482e-01]
latex_v1:  25%|##4       | 749/3000 [17:28<46:22,  1.24s/it, lr: 1.0e-04 loss: 8.444e-01]
latex_v1:  25%|##4       | 749/3000 [17:28<46:22,  1.24s/it, lr: 1.0e-04 loss: 8.444e-01]
Saving at step 750
Saved checkpoint to /data/app/output/latex_v1/latex_v1_000000750.safetensors
Saved optimizer to /data/app/output/latex_v1/optimizer.pt

latex_v1:  25%|##5       | 750/3000 [17:31<46:21,  1.24s/it, lr: 1.0e-04 loss: 1.053e-01]
latex_v1:  25%|##5       | 750/3000 [17:31<46:21,  1.24s/it, lr: 1.0e-04 loss: 1.053e-01]
latex_v1:  25%|##5       | 751/3000 [17:31<51:34,  1.38s/it, lr: 1.0e-04 loss: 1.053e-01]
latex_v1:  25%|##5       | 751/3000 [17:31<51:34,  1.38s/it, lr: 1.0e-04 loss: 1.053e-01]
latex_v1:  25%|##5       | 751/3000 [17:32<51:34,  1.38s/it, lr: 1.0e-04 loss: 6.678e-02]
latex_v1:  25%|##5       | 751/3000 [17:32<51:34,  1.38s/it, lr: 1.0e-04 loss: 6.678e-02]
latex_v1:  25%|##5       | 752/3000 [17:32<52:51,  1.41s/it, lr: 1.0e-04 loss: 6.678e-02]
latex_v1:  25%|##5       | 752/3000 [17:32<52:51,  1.41s/it, lr: 1.0e-04 loss: 6.678e-02]
latex_v1:  25%|##5       | 752/3000 [17:33<52:51,  1.41s/it, lr: 1.0e-04 loss: 1.398e-01]
latex_v1:  25%|##5       | 752/3000 [17:33<52:51,  1.41s/it, lr: 1.0e-04 loss: 1.398e-01]
latex_v1:  25%|##5       | 753/3000 [17:33<46:15,  1.24s/it, lr: 1.0e-04 loss: 1.398e-01]
latex_v1:  25%|##5       | 753/3000 [17:33<46:15,  1.24s/it, lr: 1.0e-04 loss: 1.398e-01]
latex_v1:  25%|##5       | 753/3000 [17:34<46:15,  1.24s/it, lr: 1.0e-04 loss: 4.372e-01]
latex_v1:  25%|##5       | 753/3000 [17:34<46:15,  1.24s/it, lr: 1.0e-04 loss: 4.372e-01]
latex_v1:  25%|##5       | 754/3000 [17:34<47:23,  1.27s/it, lr: 1.0e-04 loss: 4.372e-01]
latex_v1:  25%|##5       | 754/3000 [17:34<47:23,  1.27s/it, lr: 1.0e-04 loss: 4.372e-01]
latex_v1:  25%|##5       | 754/3000 [17:35<47:23,  1.27s/it, lr: 1.0e-04 loss: 6.834e-02]
latex_v1:  25%|##5       | 754/3000 [17:35<47:23,  1.27s/it, lr: 1.0e-04 loss: 6.834e-02]
latex_v1:  25%|##5       | 755/3000 [17:35<42:03,  1.12s/it, lr: 1.0e-04 loss: 6.834e-02]
latex_v1:  25%|##5       | 755/3000 [17:35<42:03,  1.12s/it, lr: 1.0e-04 loss: 6.834e-02]
latex_v1:  25%|##5       | 755/3000 [17:37<42:03,  1.12s/it, lr: 1.0e-04 loss: 3.468e-01]
latex_v1:  25%|##5       | 755/3000 [17:37<42:03,  1.12s/it, lr: 1.0e-04 loss: 3.468e-01]
latex_v1:  25%|##5       | 756/3000 [17:37<45:06,  1.21s/it, lr: 1.0e-04 loss: 3.468e-01]
latex_v1:  25%|##5       | 756/3000 [17:37<45:06,  1.21s/it, lr: 1.0e-04 loss: 3.468e-01]
latex_v1:  25%|##5       | 756/3000 [17:38<45:06,  1.21s/it, lr: 1.0e-04 loss: 4.678e-01]
latex_v1:  25%|##5       | 756/3000 [17:38<45:06,  1.21s/it, lr: 1.0e-04 loss: 4.678e-01]
latex_v1:  25%|##5       | 757/3000 [17:38<44:41,  1.20s/it, lr: 1.0e-04 loss: 4.678e-01]
latex_v1:  25%|##5       | 757/3000 [17:38<44:41,  1.20s/it, lr: 1.0e-04 loss: 4.678e-01]
latex_v1:  25%|##5       | 757/3000 [17:39<44:41,  1.20s/it, lr: 1.0e-04 loss: 2.414e-01]
latex_v1:  25%|##5       | 757/3000 [17:39<44:41,  1.20s/it, lr: 1.0e-04 loss: 2.414e-01]
latex_v1:  25%|##5       | 758/3000 [17:39<39:44,  1.06s/it, lr: 1.0e-04 loss: 2.414e-01]
latex_v1:  25%|##5       | 758/3000 [17:39<39:44,  1.06s/it, lr: 1.0e-04 loss: 2.414e-01]
latex_v1:  25%|##5       | 758/3000 [17:40<39:44,  1.06s/it, lr: 1.0e-04 loss: 7.274e-02]
latex_v1:  25%|##5       | 758/3000 [17:40<39:44,  1.06s/it, lr: 1.0e-04 loss: 7.274e-02]
latex_v1:  25%|##5       | 759/3000 [17:40<44:02,  1.18s/it, lr: 1.0e-04 loss: 7.274e-02]
latex_v1:  25%|##5       | 759/3000 [17:40<44:02,  1.18s/it, lr: 1.0e-04 loss: 7.274e-02]
latex_v1:  25%|##5       | 759/3000 [17:42<44:02,  1.18s/it, lr: 1.0e-04 loss: 6.009e-01]
latex_v1:  25%|##5       | 759/3000 [17:42<44:02,  1.18s/it, lr: 1.0e-04 loss: 6.009e-01]
latex_v1:  25%|##5       | 760/3000 [17:42<44:00,  1.18s/it, lr: 1.0e-04 loss: 1.225e-01]
latex_v1:  25%|##5       | 760/3000 [17:42<44:00,  1.18s/it, lr: 1.0e-04 loss: 1.225e-01]
latex_v1:  25%|##5       | 761/3000 [17:42<30:28,  1.22it/s, lr: 1.0e-04 loss: 1.225e-01]
latex_v1:  25%|##5       | 761/3000 [17:42<30:28,  1.22it/s, lr: 1.0e-04 loss: 1.225e-01]
latex_v1:  25%|##5       | 761/3000 [17:44<30:28,  1.22it/s, lr: 1.0e-04 loss: 5.732e-01]
latex_v1:  25%|##5       | 761/3000 [17:44<30:28,  1.22it/s, lr: 1.0e-04 loss: 5.732e-01]
latex_v1:  25%|##5       | 762/3000 [17:44<33:41,  1.11it/s, lr: 1.0e-04 loss: 5.732e-01]
latex_v1:  25%|##5       | 762/3000 [17:44<33:41,  1.11it/s, lr: 1.0e-04 loss: 5.732e-01]
latex_v1:  25%|##5       | 762/3000 [17:45<33:41,  1.11it/s, lr: 1.0e-04 loss: 4.186e-01]
latex_v1:  25%|##5       | 762/3000 [17:45<33:41,  1.11it/s, lr: 1.0e-04 loss: 4.186e-01]
latex_v1:  25%|##5       | 763/3000 [17:45<39:27,  1.06s/it, lr: 1.0e-04 loss: 4.186e-01]
latex_v1:  25%|##5       | 763/3000 [17:45<39:27,  1.06s/it, lr: 1.0e-04 loss: 4.186e-01]
latex_v1:  25%|##5       | 763/3000 [17:46<39:27,  1.06s/it, lr: 1.0e-04 loss: 2.634e-01]
latex_v1:  25%|##5       | 763/3000 [17:46<39:27,  1.06s/it, lr: 1.0e-04 loss: 2.634e-01]
latex_v1:  25%|##5       | 764/3000 [17:46<43:18,  1.16s/it, lr: 1.0e-04 loss: 2.634e-01]
latex_v1:  25%|##5       | 764/3000 [17:46<43:18,  1.16s/it, lr: 1.0e-04 loss: 2.634e-01]
latex_v1:  25%|##5       | 764/3000 [17:48<43:18,  1.16s/it, lr: 1.0e-04 loss: 5.806e-01]
latex_v1:  25%|##5       | 764/3000 [17:48<43:18,  1.16s/it, lr: 1.0e-04 loss: 5.806e-01]
latex_v1:  26%|##5       | 765/3000 [17:48<47:09,  1.27s/it, lr: 1.0e-04 loss: 5.806e-01]
latex_v1:  26%|##5       | 765/3000 [17:48<47:09,  1.27s/it, lr: 1.0e-04 loss: 5.806e-01]
latex_v1:  26%|##5       | 765/3000 [17:49<47:09,  1.27s/it, lr: 1.0e-04 loss: 2.510e-01]
latex_v1:  26%|##5       | 765/3000 [17:49<47:09,  1.27s/it, lr: 1.0e-04 loss: 2.510e-01]
latex_v1:  26%|##5       | 766/3000 [17:49<41:40,  1.12s/it, lr: 1.0e-04 loss: 2.510e-01]
latex_v1:  26%|##5       | 766/3000 [17:49<41:40,  1.12s/it, lr: 1.0e-04 loss: 2.510e-01]
latex_v1:  26%|##5       | 766/3000 [17:50<41:40,  1.12s/it, lr: 1.0e-04 loss: 5.524e-01]
latex_v1:  26%|##5       | 766/3000 [17:50<41:40,  1.12s/it, lr: 1.0e-04 loss: 5.524e-01]
latex_v1:  26%|##5       | 767/3000 [17:50<45:00,  1.21s/it, lr: 1.0e-04 loss: 5.524e-01]
latex_v1:  26%|##5       | 767/3000 [17:50<45:00,  1.21s/it, lr: 1.0e-04 loss: 5.524e-01]
latex_v1:  26%|##5       | 767/3000 [17:51<45:00,  1.21s/it, lr: 1.0e-04 loss: 6.798e-01]
latex_v1:  26%|##5       | 767/3000 [17:51<45:00,  1.21s/it, lr: 1.0e-04 loss: 6.798e-01]
latex_v1:  26%|##5       | 768/3000 [17:51<44:33,  1.20s/it, lr: 1.0e-04 loss: 6.798e-01]
latex_v1:  26%|##5       | 768/3000 [17:51<44:33,  1.20s/it, lr: 1.0e-04 loss: 6.798e-01]
latex_v1:  26%|##5       | 768/3000 [17:53<44:33,  1.20s/it, lr: 1.0e-04 loss: 5.493e-01]
latex_v1:  26%|##5       | 768/3000 [17:53<44:33,  1.20s/it, lr: 1.0e-04 loss: 5.493e-01]
latex_v1:  26%|##5       | 769/3000 [17:53<47:17,  1.27s/it, lr: 1.0e-04 loss: 5.493e-01]
latex_v1:  26%|##5       | 769/3000 [17:53<47:17,  1.27s/it, lr: 1.0e-04 loss: 5.493e-01]
latex_v1:  26%|##5       | 769/3000 [17:54<47:17,  1.27s/it, lr: 1.0e-04 loss: 5.828e-01]
latex_v1:  26%|##5       | 769/3000 [17:54<47:17,  1.27s/it, lr: 1.0e-04 loss: 5.828e-01]
latex_v1:  26%|##5       | 770/3000 [17:54<47:16,  1.27s/it, lr: 1.0e-04 loss: 7.680e-01]
latex_v1:  26%|##5       | 770/3000 [17:54<47:16,  1.27s/it, lr: 1.0e-04 loss: 7.680e-01]
latex_v1:  26%|##5       | 771/3000 [17:54<31:59,  1.16it/s, lr: 1.0e-04 loss: 7.680e-01]
latex_v1:  26%|##5       | 771/3000 [17:54<31:59,  1.16it/s, lr: 1.0e-04 loss: 7.680e-01]
latex_v1:  26%|##5       | 771/3000 [17:56<31:59,  1.16it/s, lr: 1.0e-04 loss: 5.991e-01]
latex_v1:  26%|##5       | 771/3000 [17:56<31:59,  1.16it/s, lr: 1.0e-04 loss: 5.991e-01]
latex_v1:  26%|##5       | 772/3000 [17:56<41:16,  1.11s/it, lr: 1.0e-04 loss: 5.991e-01]
latex_v1:  26%|##5       | 772/3000 [17:56<41:16,  1.11s/it, lr: 1.0e-04 loss: 5.991e-01]
latex_v1:  26%|##5       | 772/3000 [17:58<41:16,  1.11s/it, lr: 1.0e-04 loss: 5.211e-02]
latex_v1:  26%|##5       | 772/3000 [17:58<41:16,  1.11s/it, lr: 1.0e-04 loss: 5.211e-02]
latex_v1:  26%|##5       | 773/3000 [17:58<46:14,  1.25s/it, lr: 1.0e-04 loss: 5.211e-02]
latex_v1:  26%|##5       | 773/3000 [17:58<46:14,  1.25s/it, lr: 1.0e-04 loss: 5.211e-02]
latex_v1:  26%|##5       | 773/3000 [17:59<46:14,  1.25s/it, lr: 1.0e-04 loss: 3.564e-01]
latex_v1:  26%|##5       | 773/3000 [17:59<46:14,  1.25s/it, lr: 1.0e-04 loss: 3.564e-01]
latex_v1:  26%|##5       | 774/3000 [17:59<41:24,  1.12s/it, lr: 1.0e-04 loss: 3.564e-01]
latex_v1:  26%|##5       | 774/3000 [17:59<41:24,  1.12s/it, lr: 1.0e-04 loss: 3.564e-01]
latex_v1:  26%|##5       | 774/3000 [18:00<41:24,  1.12s/it, lr: 1.0e-04 loss: 1.329e-01]
latex_v1:  26%|##5       | 774/3000 [18:00<41:24,  1.12s/it, lr: 1.0e-04 loss: 1.329e-01]
latex_v1:  26%|##5       | 775/3000 [18:00<40:28,  1.09s/it, lr: 1.0e-04 loss: 1.329e-01]
latex_v1:  26%|##5       | 775/3000 [18:00<40:28,  1.09s/it, lr: 1.0e-04 loss: 1.329e-01]
latex_v1:  26%|##5       | 775/3000 [18:02<40:28,  1.09s/it, lr: 1.0e-04 loss: 1.841e-01]
latex_v1:  26%|##5       | 775/3000 [18:02<40:28,  1.09s/it, lr: 1.0e-04 loss: 1.841e-01]
latex_v1:  26%|##5       | 776/3000 [18:02<58:48,  1.59s/it, lr: 1.0e-04 loss: 1.841e-01]
latex_v1:  26%|##5       | 776/3000 [18:02<58:48,  1.59s/it, lr: 1.0e-04 loss: 1.841e-01]
latex_v1:  26%|##5       | 776/3000 [18:05<58:48,  1.59s/it, lr: 1.0e-04 loss: 4.959e-01]
latex_v1:  26%|##5       | 776/3000 [18:05<58:48,  1.59s/it, lr: 1.0e-04 loss: 4.959e-01]
latex_v1:  26%|##5       | 777/3000 [18:05<1:11:40,  1.93s/it, lr: 1.0e-04 loss: 4.959e-01]
latex_v1:  26%|##5       | 777/3000 [18:05<1:11:40,  1.93s/it, lr: 1.0e-04 loss: 4.959e-01]
latex_v1:  26%|##5       | 777/3000 [18:06<1:11:40,  1.93s/it, lr: 1.0e-04 loss: 8.271e-02]
latex_v1:  26%|##5       | 777/3000 [18:06<1:11:40,  1.93s/it, lr: 1.0e-04 loss: 8.271e-02]
latex_v1:  26%|##5       | 778/3000 [18:06<59:00,  1.59s/it, lr: 1.0e-04 loss: 8.271e-02]  
latex_v1:  26%|##5       | 778/3000 [18:06<59:00,  1.59s/it, lr: 1.0e-04 loss: 8.271e-02]  
latex_v1:  26%|##5       | 778/3000 [18:07<59:00,  1.59s/it, lr: 1.0e-04 loss: 2.485e-01]
latex_v1:  26%|##5       | 778/3000 [18:07<59:00,  1.59s/it, lr: 1.0e-04 loss: 2.485e-01]
latex_v1:  26%|##5       | 779/3000 [18:07<51:58,  1.40s/it, lr: 1.0e-04 loss: 2.485e-01]
latex_v1:  26%|##5       | 779/3000 [18:07<51:58,  1.40s/it, lr: 1.0e-04 loss: 2.485e-01]
latex_v1:  26%|##5       | 779/3000 [18:08<51:58,  1.40s/it, lr: 1.0e-04 loss: 1.906e-01]
latex_v1:  26%|##5       | 779/3000 [18:08<51:58,  1.40s/it, lr: 1.0e-04 loss: 1.906e-01]
latex_v1:  26%|##6       | 780/3000 [18:09<51:56,  1.40s/it, lr: 1.0e-04 loss: 1.053e-02]
latex_v1:  26%|##6       | 780/3000 [18:09<51:56,  1.40s/it, lr: 1.0e-04 loss: 1.053e-02]
latex_v1:  26%|##6       | 781/3000 [18:09<41:31,  1.12s/it, lr: 1.0e-04 loss: 1.053e-02]
latex_v1:  26%|##6       | 781/3000 [18:09<41:31,  1.12s/it, lr: 1.0e-04 loss: 1.053e-02]
latex_v1:  26%|##6       | 781/3000 [18:10<41:31,  1.12s/it, lr: 1.0e-04 loss: 3.290e-01]
latex_v1:  26%|##6       | 781/3000 [18:10<41:31,  1.12s/it, lr: 1.0e-04 loss: 3.290e-01]
latex_v1:  26%|##6       | 782/3000 [18:10<40:51,  1.11s/it, lr: 1.0e-04 loss: 3.290e-01]
latex_v1:  26%|##6       | 782/3000 [18:10<40:51,  1.11s/it, lr: 1.0e-04 loss: 3.290e-01]
latex_v1:  26%|##6       | 782/3000 [18:11<40:51,  1.11s/it, lr: 1.0e-04 loss: 4.387e-01]
latex_v1:  26%|##6       | 782/3000 [18:11<40:51,  1.11s/it, lr: 1.0e-04 loss: 4.387e-01]
latex_v1:  26%|##6       | 783/3000 [18:11<37:25,  1.01s/it, lr: 1.0e-04 loss: 4.387e-01]
latex_v1:  26%|##6       | 783/3000 [18:11<37:25,  1.01s/it, lr: 1.0e-04 loss: 4.387e-01]
latex_v1:  26%|##6       | 783/3000 [18:14<37:25,  1.01s/it, lr: 1.0e-04 loss: 8.963e-02]
latex_v1:  26%|##6       | 783/3000 [18:14<37:25,  1.01s/it, lr: 1.0e-04 loss: 8.963e-02]
latex_v1:  26%|##6       | 784/3000 [18:14<56:09,  1.52s/it, lr: 1.0e-04 loss: 8.963e-02]
latex_v1:  26%|##6       | 784/3000 [18:14<56:09,  1.52s/it, lr: 1.0e-04 loss: 8.963e-02]
latex_v1:  26%|##6       | 784/3000 [18:16<56:09,  1.52s/it, lr: 1.0e-04 loss: 6.501e-01]
latex_v1:  26%|##6       | 784/3000 [18:16<56:09,  1.52s/it, lr: 1.0e-04 loss: 6.501e-01]
latex_v1:  26%|##6       | 785/3000 [18:16<59:52,  1.62s/it, lr: 1.0e-04 loss: 6.501e-01]
latex_v1:  26%|##6       | 785/3000 [18:16<59:52,  1.62s/it, lr: 1.0e-04 loss: 6.501e-01]
latex_v1:  26%|##6       | 785/3000 [18:17<59:52,  1.62s/it, lr: 1.0e-04 loss: 1.710e-01]
latex_v1:  26%|##6       | 785/3000 [18:17<59:52,  1.62s/it, lr: 1.0e-04 loss: 1.710e-01]
latex_v1:  26%|##6       | 786/3000 [18:17<57:12,  1.55s/it, lr: 1.0e-04 loss: 1.710e-01]
latex_v1:  26%|##6       | 786/3000 [18:17<57:12,  1.55s/it, lr: 1.0e-04 loss: 1.710e-01]
latex_v1:  26%|##6       | 786/3000 [18:20<57:12,  1.55s/it, lr: 1.0e-04 loss: 3.777e-01]
latex_v1:  26%|##6       | 786/3000 [18:20<57:12,  1.55s/it, lr: 1.0e-04 loss: 3.777e-01]
latex_v1:  26%|##6       | 787/3000 [18:20<1:11:23,  1.94s/it, lr: 1.0e-04 loss: 3.777e-01]
latex_v1:  26%|##6       | 787/3000 [18:20<1:11:23,  1.94s/it, lr: 1.0e-04 loss: 3.777e-01]
latex_v1:  26%|##6       | 787/3000 [18:21<1:11:23,  1.94s/it, lr: 1.0e-04 loss: 6.438e-01]
latex_v1:  26%|##6       | 787/3000 [18:21<1:11:23,  1.94s/it, lr: 1.0e-04 loss: 6.438e-01]
latex_v1:  26%|##6       | 788/3000 [18:22<1:05:51,  1.79s/it, lr: 1.0e-04 loss: 6.438e-01]
latex_v1:  26%|##6       | 788/3000 [18:22<1:05:51,  1.79s/it, lr: 1.0e-04 loss: 6.438e-01]
latex_v1:  26%|##6       | 788/3000 [18:23<1:05:51,  1.79s/it, lr: 1.0e-04 loss: 5.531e-01]
latex_v1:  26%|##6       | 788/3000 [18:23<1:05:51,  1.79s/it, lr: 1.0e-04 loss: 5.531e-01]
latex_v1:  26%|##6       | 789/3000 [18:23<1:03:05,  1.71s/it, lr: 1.0e-04 loss: 5.531e-01]
latex_v1:  26%|##6       | 789/3000 [18:23<1:03:05,  1.71s/it, lr: 1.0e-04 loss: 5.531e-01]
latex_v1:  26%|##6       | 789/3000 [18:25<1:03:05,  1.71s/it, lr: 1.0e-04 loss: 1.281e-01]
latex_v1:  26%|##6       | 789/3000 [18:25<1:03:05,  1.71s/it, lr: 1.0e-04 loss: 1.281e-01]
latex_v1:  26%|##6       | 790/3000 [18:26<1:03:03,  1.71s/it, lr: 1.0e-04 loss: 1.079e-01]
latex_v1:  26%|##6       | 790/3000 [18:26<1:03:03,  1.71s/it, lr: 1.0e-04 loss: 1.079e-01]
latex_v1:  26%|##6       | 791/3000 [18:26<42:26,  1.15s/it, lr: 1.0e-04 loss: 1.079e-01]  
latex_v1:  26%|##6       | 791/3000 [18:26<42:26,  1.15s/it, lr: 1.0e-04 loss: 1.079e-01]  
latex_v1:  26%|##6       | 791/3000 [18:27<42:26,  1.15s/it, lr: 1.0e-04 loss: 7.382e-01]
latex_v1:  26%|##6       | 791/3000 [18:27<42:26,  1.15s/it, lr: 1.0e-04 loss: 7.382e-01]
latex_v1:  26%|##6       | 792/3000 [18:27<42:48,  1.16s/it, lr: 1.0e-04 loss: 7.382e-01]
latex_v1:  26%|##6       | 792/3000 [18:27<42:48,  1.16s/it, lr: 1.0e-04 loss: 7.382e-01]
latex_v1:  26%|##6       | 792/3000 [18:28<42:48,  1.16s/it, lr: 1.0e-04 loss: 7.057e-01]
latex_v1:  26%|##6       | 792/3000 [18:28<42:48,  1.16s/it, lr: 1.0e-04 loss: 7.057e-01]
latex_v1:  26%|##6       | 793/3000 [18:28<39:01,  1.06s/it, lr: 1.0e-04 loss: 7.057e-01]
latex_v1:  26%|##6       | 793/3000 [18:28<39:01,  1.06s/it, lr: 1.0e-04 loss: 7.057e-01]
latex_v1:  26%|##6       | 793/3000 [18:29<39:01,  1.06s/it, lr: 1.0e-04 loss: 1.466e-01]
latex_v1:  26%|##6       | 793/3000 [18:29<39:01,  1.06s/it, lr: 1.0e-04 loss: 1.466e-01]
latex_v1:  26%|##6       | 794/3000 [18:29<35:54,  1.02it/s, lr: 1.0e-04 loss: 1.466e-01]
latex_v1:  26%|##6       | 794/3000 [18:29<35:54,  1.02it/s, lr: 1.0e-04 loss: 1.466e-01]
latex_v1:  26%|##6       | 794/3000 [18:29<35:54,  1.02it/s, lr: 1.0e-04 loss: 5.276e-01]
latex_v1:  26%|##6       | 794/3000 [18:29<35:54,  1.02it/s, lr: 1.0e-04 loss: 5.276e-01]
latex_v1:  26%|##6       | 795/3000 [18:29<33:26,  1.10it/s, lr: 1.0e-04 loss: 5.276e-01]
latex_v1:  26%|##6       | 795/3000 [18:29<33:26,  1.10it/s, lr: 1.0e-04 loss: 5.276e-01]
latex_v1:  26%|##6       | 795/3000 [18:31<33:26,  1.10it/s, lr: 1.0e-04 loss: 3.545e-01]
latex_v1:  26%|##6       | 795/3000 [18:31<33:26,  1.10it/s, lr: 1.0e-04 loss: 3.545e-01]
latex_v1:  27%|##6       | 796/3000 [18:31<44:39,  1.22s/it, lr: 1.0e-04 loss: 3.545e-01]
latex_v1:  27%|##6       | 796/3000 [18:31<44:39,  1.22s/it, lr: 1.0e-04 loss: 3.545e-01]
latex_v1:  27%|##6       | 796/3000 [18:33<44:39,  1.22s/it, lr: 1.0e-04 loss: 2.225e-01]
latex_v1:  27%|##6       | 796/3000 [18:33<44:39,  1.22s/it, lr: 1.0e-04 loss: 2.225e-01]
latex_v1:  27%|##6       | 797/3000 [18:33<51:47,  1.41s/it, lr: 1.0e-04 loss: 2.225e-01]
latex_v1:  27%|##6       | 797/3000 [18:33<51:47,  1.41s/it, lr: 1.0e-04 loss: 2.225e-01]
latex_v1:  27%|##6       | 797/3000 [18:34<51:47,  1.41s/it, lr: 1.0e-04 loss: 4.263e-01]
latex_v1:  27%|##6       | 797/3000 [18:34<51:47,  1.41s/it, lr: 1.0e-04 loss: 4.263e-01]
latex_v1:  27%|##6       | 798/3000 [18:34<44:32,  1.21s/it, lr: 1.0e-04 loss: 4.263e-01]
latex_v1:  27%|##6       | 798/3000 [18:34<44:32,  1.21s/it, lr: 1.0e-04 loss: 4.263e-01]
latex_v1:  27%|##6       | 798/3000 [18:36<44:32,  1.21s/it, lr: 1.0e-04 loss: 3.185e-01]
latex_v1:  27%|##6       | 798/3000 [18:36<44:32,  1.21s/it, lr: 1.0e-04 loss: 3.185e-01]
latex_v1:  27%|##6       | 799/3000 [18:36<48:23,  1.32s/it, lr: 1.0e-04 loss: 3.185e-01]
latex_v1:  27%|##6       | 799/3000 [18:36<48:23,  1.32s/it, lr: 1.0e-04 loss: 3.185e-01]
latex_v1:  27%|##6       | 799/3000 [18:37<48:23,  1.32s/it, lr: 1.0e-04 loss: 6.380e-01]
latex_v1:  27%|##6       | 799/3000 [18:37<48:23,  1.32s/it, lr: 1.0e-04 loss: 6.380e-01]
latex_v1:  27%|##6       | 800/3000 [18:38<48:22,  1.32s/it, lr: 1.0e-04 loss: 2.355e-01]
latex_v1:  27%|##6       | 800/3000 [18:38<48:22,  1.32s/it, lr: 1.0e-04 loss: 2.355e-01]
latex_v1:  27%|##6       | 801/3000 [18:38<39:11,  1.07s/it, lr: 1.0e-04 loss: 2.355e-01]
latex_v1:  27%|##6       | 801/3000 [18:38<39:11,  1.07s/it, lr: 1.0e-04 loss: 2.355e-01]
latex_v1:  27%|##6       | 801/3000 [18:39<39:11,  1.07s/it, lr: 1.0e-04 loss: 1.800e-01]
latex_v1:  27%|##6       | 801/3000 [18:39<39:11,  1.07s/it, lr: 1.0e-04 loss: 1.800e-01]
latex_v1:  27%|##6       | 802/3000 [18:39<36:25,  1.01it/s, lr: 1.0e-04 loss: 1.800e-01]
latex_v1:  27%|##6       | 802/3000 [18:39<36:25,  1.01it/s, lr: 1.0e-04 loss: 1.800e-01]
latex_v1:  27%|##6       | 802/3000 [18:42<36:25,  1.01it/s, lr: 1.0e-04 loss: 1.853e-01]
latex_v1:  27%|##6       | 802/3000 [18:42<36:25,  1.01it/s, lr: 1.0e-04 loss: 1.853e-01]
latex_v1:  27%|##6       | 803/3000 [18:42<54:15,  1.48s/it, lr: 1.0e-04 loss: 1.853e-01]
latex_v1:  27%|##6       | 803/3000 [18:42<54:15,  1.48s/it, lr: 1.0e-04 loss: 1.853e-01]
latex_v1:  27%|##6       | 803/3000 [18:44<54:15,  1.48s/it, lr: 1.0e-04 loss: 3.464e-01]
latex_v1:  27%|##6       | 803/3000 [18:44<54:15,  1.48s/it, lr: 1.0e-04 loss: 3.464e-01]
latex_v1:  27%|##6       | 804/3000 [18:44<59:40,  1.63s/it, lr: 1.0e-04 loss: 3.464e-01]
latex_v1:  27%|##6       | 804/3000 [18:44<59:40,  1.63s/it, lr: 1.0e-04 loss: 3.464e-01]
latex_v1:  27%|##6       | 804/3000 [18:45<59:40,  1.63s/it, lr: 1.0e-04 loss: 4.939e-01]
latex_v1:  27%|##6       | 804/3000 [18:45<59:40,  1.63s/it, lr: 1.0e-04 loss: 4.939e-01]
latex_v1:  27%|##6       | 805/3000 [18:46<58:52,  1.61s/it, lr: 1.0e-04 loss: 4.939e-01]
latex_v1:  27%|##6       | 805/3000 [18:46<58:52,  1.61s/it, lr: 1.0e-04 loss: 4.939e-01]
latex_v1:  27%|##6       | 805/3000 [18:46<58:52,  1.61s/it, lr: 1.0e-04 loss: 3.611e-01]
latex_v1:  27%|##6       | 805/3000 [18:46<58:52,  1.61s/it, lr: 1.0e-04 loss: 3.611e-01]
latex_v1:  27%|##6       | 806/3000 [18:46<49:52,  1.36s/it, lr: 1.0e-04 loss: 3.611e-01]
latex_v1:  27%|##6       | 806/3000 [18:46<49:52,  1.36s/it, lr: 1.0e-04 loss: 3.611e-01]
latex_v1:  27%|##6       | 806/3000 [18:49<49:52,  1.36s/it, lr: 1.0e-04 loss: 5.428e-01]
latex_v1:  27%|##6       | 806/3000 [18:49<49:52,  1.36s/it, lr: 1.0e-04 loss: 5.428e-01]
latex_v1:  27%|##6       | 807/3000 [18:49<1:03:27,  1.74s/it, lr: 1.0e-04 loss: 5.428e-01]
latex_v1:  27%|##6       | 807/3000 [18:49<1:03:27,  1.74s/it, lr: 1.0e-04 loss: 5.428e-01]
latex_v1:  27%|##6       | 807/3000 [18:50<1:03:27,  1.74s/it, lr: 1.0e-04 loss: 1.577e-01]
latex_v1:  27%|##6       | 807/3000 [18:50<1:03:27,  1.74s/it, lr: 1.0e-04 loss: 1.577e-01]
latex_v1:  27%|##6       | 808/3000 [18:50<53:13,  1.46s/it, lr: 1.0e-04 loss: 1.577e-01]  
latex_v1:  27%|##6       | 808/3000 [18:50<53:13,  1.46s/it, lr: 1.0e-04 loss: 1.577e-01]  
latex_v1:  27%|##6       | 808/3000 [18:50<53:13,  1.46s/it, lr: 1.0e-04 loss: 1.585e-01]
latex_v1:  27%|##6       | 808/3000 [18:50<53:13,  1.46s/it, lr: 1.0e-04 loss: 1.585e-01]
latex_v1:  27%|##6       | 809/3000 [18:50<45:44,  1.25s/it, lr: 1.0e-04 loss: 1.585e-01]
latex_v1:  27%|##6       | 809/3000 [18:50<45:44,  1.25s/it, lr: 1.0e-04 loss: 1.585e-01]
latex_v1:  27%|##6       | 809/3000 [18:51<45:44,  1.25s/it, lr: 1.0e-04 loss: 5.216e-01]
latex_v1:  27%|##6       | 809/3000 [18:51<45:44,  1.25s/it, lr: 1.0e-04 loss: 5.216e-01]
latex_v1:  27%|##7       | 810/3000 [18:54<45:42,  1.25s/it, lr: 1.0e-04 loss: 4.488e-01]
latex_v1:  27%|##7       | 810/3000 [18:54<45:42,  1.25s/it, lr: 1.0e-04 loss: 4.488e-01]
latex_v1:  27%|##7       | 811/3000 [18:54<48:58,  1.34s/it, lr: 1.0e-04 loss: 4.488e-01]
latex_v1:  27%|##7       | 811/3000 [18:54<48:58,  1.34s/it, lr: 1.0e-04 loss: 4.488e-01]
latex_v1:  27%|##7       | 811/3000 [18:56<48:58,  1.34s/it, lr: 1.0e-04 loss: 6.317e-01]
latex_v1:  27%|##7       | 811/3000 [18:56<48:58,  1.34s/it, lr: 1.0e-04 loss: 6.317e-01]
latex_v1:  27%|##7       | 812/3000 [18:56<50:52,  1.40s/it, lr: 1.0e-04 loss: 6.317e-01]
latex_v1:  27%|##7       | 812/3000 [18:56<50:52,  1.40s/it, lr: 1.0e-04 loss: 6.317e-01]
latex_v1:  27%|##7       | 812/3000 [18:58<50:52,  1.40s/it, lr: 1.0e-04 loss: 8.858e-02]
latex_v1:  27%|##7       | 812/3000 [18:58<50:52,  1.40s/it, lr: 1.0e-04 loss: 8.858e-02]
latex_v1:  27%|##7       | 813/3000 [18:58<58:25,  1.60s/it, lr: 1.0e-04 loss: 8.858e-02]
latex_v1:  27%|##7       | 813/3000 [18:58<58:25,  1.60s/it, lr: 1.0e-04 loss: 8.858e-02]
latex_v1:  27%|##7       | 813/3000 [18:59<58:25,  1.60s/it, lr: 1.0e-04 loss: 5.852e-01]
latex_v1:  27%|##7       | 813/3000 [18:59<58:25,  1.60s/it, lr: 1.0e-04 loss: 5.852e-01]
latex_v1:  27%|##7       | 814/3000 [18:59<49:58,  1.37s/it, lr: 1.0e-04 loss: 5.852e-01]
latex_v1:  27%|##7       | 814/3000 [18:59<49:58,  1.37s/it, lr: 1.0e-04 loss: 5.852e-01]
latex_v1:  27%|##7       | 814/3000 [19:00<49:58,  1.37s/it, lr: 1.0e-04 loss: 3.139e-01]
latex_v1:  27%|##7       | 814/3000 [19:00<49:58,  1.37s/it, lr: 1.0e-04 loss: 3.139e-01]
latex_v1:  27%|##7       | 815/3000 [19:00<51:40,  1.42s/it, lr: 1.0e-04 loss: 3.139e-01]
latex_v1:  27%|##7       | 815/3000 [19:00<51:40,  1.42s/it, lr: 1.0e-04 loss: 3.139e-01]
latex_v1:  27%|##7       | 815/3000 [19:01<51:40,  1.42s/it, lr: 1.0e-04 loss: 7.960e-01]
latex_v1:  27%|##7       | 815/3000 [19:01<51:40,  1.42s/it, lr: 1.0e-04 loss: 7.960e-01]
latex_v1:  27%|##7       | 816/3000 [19:01<50:42,  1.39s/it, lr: 1.0e-04 loss: 7.960e-01]
latex_v1:  27%|##7       | 816/3000 [19:01<50:42,  1.39s/it, lr: 1.0e-04 loss: 7.960e-01]
latex_v1:  27%|##7       | 816/3000 [19:03<50:42,  1.39s/it, lr: 1.0e-04 loss: 3.006e-01]
latex_v1:  27%|##7       | 816/3000 [19:03<50:42,  1.39s/it, lr: 1.0e-04 loss: 3.006e-01]
latex_v1:  27%|##7       | 817/3000 [19:03<51:51,  1.43s/it, lr: 1.0e-04 loss: 3.006e-01]
latex_v1:  27%|##7       | 817/3000 [19:03<51:51,  1.43s/it, lr: 1.0e-04 loss: 3.006e-01]
latex_v1:  27%|##7       | 817/3000 [19:04<51:51,  1.43s/it, lr: 1.0e-04 loss: 6.640e-01]
latex_v1:  27%|##7       | 817/3000 [19:04<51:51,  1.43s/it, lr: 1.0e-04 loss: 6.640e-01]
latex_v1:  27%|##7       | 818/3000 [19:04<51:10,  1.41s/it, lr: 1.0e-04 loss: 6.640e-01]
latex_v1:  27%|##7       | 818/3000 [19:04<51:10,  1.41s/it, lr: 1.0e-04 loss: 6.640e-01]
latex_v1:  27%|##7       | 818/3000 [19:05<51:10,  1.41s/it, lr: 1.0e-04 loss: 8.980e-01]
latex_v1:  27%|##7       | 818/3000 [19:05<51:10,  1.41s/it, lr: 1.0e-04 loss: 8.980e-01]
latex_v1:  27%|##7       | 819/3000 [19:06<48:38,  1.34s/it, lr: 1.0e-04 loss: 8.980e-01]
latex_v1:  27%|##7       | 819/3000 [19:06<48:38,  1.34s/it, lr: 1.0e-04 loss: 8.980e-01]
latex_v1:  27%|##7       | 819/3000 [19:07<48:38,  1.34s/it, lr: 1.0e-04 loss: 2.684e-01]
latex_v1:  27%|##7       | 819/3000 [19:07<48:38,  1.34s/it, lr: 1.0e-04 loss: 2.684e-01]
latex_v1:  27%|##7       | 820/3000 [19:08<48:37,  1.34s/it, lr: 1.0e-04 loss: 4.308e-01]
latex_v1:  27%|##7       | 820/3000 [19:08<48:37,  1.34s/it, lr: 1.0e-04 loss: 4.308e-01]
latex_v1:  27%|##7       | 821/3000 [19:08<39:02,  1.08s/it, lr: 1.0e-04 loss: 4.308e-01]
latex_v1:  27%|##7       | 821/3000 [19:08<39:02,  1.08s/it, lr: 1.0e-04 loss: 4.308e-01]
latex_v1:  27%|##7       | 821/3000 [19:09<39:02,  1.08s/it, lr: 1.0e-04 loss: 1.340e-01]
latex_v1:  27%|##7       | 821/3000 [19:09<39:02,  1.08s/it, lr: 1.0e-04 loss: 1.340e-01]
latex_v1:  27%|##7       | 822/3000 [19:09<36:06,  1.01it/s, lr: 1.0e-04 loss: 1.340e-01]
latex_v1:  27%|##7       | 822/3000 [19:09<36:06,  1.01it/s, lr: 1.0e-04 loss: 1.340e-01]
latex_v1:  27%|##7       | 822/3000 [19:11<36:06,  1.01it/s, lr: 1.0e-04 loss: 5.937e-02]
latex_v1:  27%|##7       | 822/3000 [19:11<36:06,  1.01it/s, lr: 1.0e-04 loss: 5.937e-02]
latex_v1:  27%|##7       | 823/3000 [19:11<40:02,  1.10s/it, lr: 1.0e-04 loss: 5.937e-02]
latex_v1:  27%|##7       | 823/3000 [19:11<40:02,  1.10s/it, lr: 1.0e-04 loss: 5.937e-02]
latex_v1:  27%|##7       | 823/3000 [19:12<40:02,  1.10s/it, lr: 1.0e-04 loss: 1.496e-01]
latex_v1:  27%|##7       | 823/3000 [19:12<40:02,  1.10s/it, lr: 1.0e-04 loss: 1.496e-01]
latex_v1:  27%|##7       | 824/3000 [19:12<47:14,  1.30s/it, lr: 1.0e-04 loss: 1.496e-01]
latex_v1:  27%|##7       | 824/3000 [19:12<47:14,  1.30s/it, lr: 1.0e-04 loss: 1.496e-01]
latex_v1:  27%|##7       | 824/3000 [19:13<47:14,  1.30s/it, lr: 1.0e-04 loss: 3.407e-01]
latex_v1:  27%|##7       | 824/3000 [19:13<47:14,  1.30s/it, lr: 1.0e-04 loss: 3.407e-01]
latex_v1:  28%|##7       | 825/3000 [19:13<41:40,  1.15s/it, lr: 1.0e-04 loss: 3.407e-01]
latex_v1:  28%|##7       | 825/3000 [19:13<41:40,  1.15s/it, lr: 1.0e-04 loss: 3.407e-01]
latex_v1:  28%|##7       | 825/3000 [19:16<41:40,  1.15s/it, lr: 1.0e-04 loss: 2.633e-01]
latex_v1:  28%|##7       | 825/3000 [19:16<41:40,  1.15s/it, lr: 1.0e-04 loss: 2.633e-01]
latex_v1:  28%|##7       | 826/3000 [19:16<59:06,  1.63s/it, lr: 1.0e-04 loss: 2.633e-01]
latex_v1:  28%|##7       | 826/3000 [19:16<59:06,  1.63s/it, lr: 1.0e-04 loss: 2.633e-01]
latex_v1:  28%|##7       | 826/3000 [19:17<59:06,  1.63s/it, lr: 1.0e-04 loss: 6.751e-01]
latex_v1:  28%|##7       | 826/3000 [19:17<59:06,  1.63s/it, lr: 1.0e-04 loss: 6.751e-01]
latex_v1:  28%|##7       | 827/3000 [19:17<49:48,  1.38s/it, lr: 1.0e-04 loss: 6.751e-01]
latex_v1:  28%|##7       | 827/3000 [19:17<49:48,  1.38s/it, lr: 1.0e-04 loss: 6.751e-01]
latex_v1:  28%|##7       | 827/3000 [19:18<49:48,  1.38s/it, lr: 1.0e-04 loss: 6.310e-01]
latex_v1:  28%|##7       | 827/3000 [19:18<49:48,  1.38s/it, lr: 1.0e-04 loss: 6.310e-01]
latex_v1:  28%|##7       | 828/3000 [19:18<51:00,  1.41s/it, lr: 1.0e-04 loss: 6.310e-01]
latex_v1:  28%|##7       | 828/3000 [19:18<51:00,  1.41s/it, lr: 1.0e-04 loss: 6.310e-01]
latex_v1:  28%|##7       | 828/3000 [19:20<51:00,  1.41s/it, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  28%|##7       | 828/3000 [19:20<51:00,  1.41s/it, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  28%|##7       | 829/3000 [19:20<54:23,  1.50s/it, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  28%|##7       | 829/3000 [19:20<54:23,  1.50s/it, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  28%|##7       | 829/3000 [19:23<54:23,  1.50s/it, lr: 1.0e-04 loss: 1.554e-01]
latex_v1:  28%|##7       | 829/3000 [19:23<54:23,  1.50s/it, lr: 1.0e-04 loss: 1.554e-01]
latex_v1:  28%|##7       | 830/3000 [19:24<54:21,  1.50s/it, lr: 1.0e-04 loss: 5.955e-01]
latex_v1:  28%|##7       | 830/3000 [19:24<54:21,  1.50s/it, lr: 1.0e-04 loss: 5.955e-01]
latex_v1:  28%|##7       | 831/3000 [19:24<37:31,  1.04s/it, lr: 1.0e-04 loss: 5.955e-01]
latex_v1:  28%|##7       | 831/3000 [19:24<37:31,  1.04s/it, lr: 1.0e-04 loss: 5.955e-01]
latex_v1:  28%|##7       | 831/3000 [19:25<37:31,  1.04s/it, lr: 1.0e-04 loss: 4.778e-01]
latex_v1:  28%|##7       | 831/3000 [19:25<37:31,  1.04s/it, lr: 1.0e-04 loss: 4.778e-01]
latex_v1:  28%|##7       | 832/3000 [19:25<34:55,  1.03it/s, lr: 1.0e-04 loss: 4.778e-01]
latex_v1:  28%|##7       | 832/3000 [19:25<34:55,  1.03it/s, lr: 1.0e-04 loss: 4.778e-01]
latex_v1:  28%|##7       | 832/3000 [19:26<34:55,  1.03it/s, lr: 1.0e-04 loss: 1.116e-01]
latex_v1:  28%|##7       | 832/3000 [19:26<34:55,  1.03it/s, lr: 1.0e-04 loss: 1.116e-01]
latex_v1:  28%|##7       | 833/3000 [19:26<39:23,  1.09s/it, lr: 1.0e-04 loss: 1.116e-01]
latex_v1:  28%|##7       | 833/3000 [19:26<39:23,  1.09s/it, lr: 1.0e-04 loss: 1.116e-01]
latex_v1:  28%|##7       | 833/3000 [19:28<39:23,  1.09s/it, lr: 1.0e-04 loss: 1.186e-01]
latex_v1:  28%|##7       | 833/3000 [19:28<39:23,  1.09s/it, lr: 1.0e-04 loss: 1.186e-01]
latex_v1:  28%|##7       | 834/3000 [19:28<43:33,  1.21s/it, lr: 1.0e-04 loss: 1.186e-01]
latex_v1:  28%|##7       | 834/3000 [19:28<43:33,  1.21s/it, lr: 1.0e-04 loss: 1.186e-01]
latex_v1:  28%|##7       | 834/3000 [19:28<43:33,  1.21s/it, lr: 1.0e-04 loss: 3.000e-01]
latex_v1:  28%|##7       | 834/3000 [19:28<43:33,  1.21s/it, lr: 1.0e-04 loss: 3.000e-01]
latex_v1:  28%|##7       | 835/3000 [19:28<38:51,  1.08s/it, lr: 1.0e-04 loss: 3.000e-01]
latex_v1:  28%|##7       | 835/3000 [19:28<38:51,  1.08s/it, lr: 1.0e-04 loss: 3.000e-01]
latex_v1:  28%|##7       | 835/3000 [19:30<38:51,  1.08s/it, lr: 1.0e-04 loss: 4.657e-01]
latex_v1:  28%|##7       | 835/3000 [19:30<38:51,  1.08s/it, lr: 1.0e-04 loss: 4.657e-01]
latex_v1:  28%|##7       | 836/3000 [19:30<43:38,  1.21s/it, lr: 1.0e-04 loss: 4.657e-01]
latex_v1:  28%|##7       | 836/3000 [19:30<43:38,  1.21s/it, lr: 1.0e-04 loss: 4.657e-01]
latex_v1:  28%|##7       | 836/3000 [19:33<43:38,  1.21s/it, lr: 1.0e-04 loss: 4.432e-01]
latex_v1:  28%|##7       | 836/3000 [19:33<43:38,  1.21s/it, lr: 1.0e-04 loss: 4.432e-01]
latex_v1:  28%|##7       | 837/3000 [19:33<1:01:38,  1.71s/it, lr: 1.0e-04 loss: 4.432e-01]
latex_v1:  28%|##7       | 837/3000 [19:33<1:01:38,  1.71s/it, lr: 1.0e-04 loss: 4.432e-01]
latex_v1:  28%|##7       | 837/3000 [19:35<1:01:38,  1.71s/it, lr: 1.0e-04 loss: 3.665e-01]
latex_v1:  28%|##7       | 837/3000 [19:35<1:01:38,  1.71s/it, lr: 1.0e-04 loss: 3.665e-01]
latex_v1:  28%|##7       | 838/3000 [19:35<59:49,  1.66s/it, lr: 1.0e-04 loss: 3.665e-01]  
latex_v1:  28%|##7       | 838/3000 [19:35<59:49,  1.66s/it, lr: 1.0e-04 loss: 3.665e-01]  
latex_v1:  28%|##7       | 838/3000 [19:37<59:49,  1.66s/it, lr: 1.0e-04 loss: 4.823e-01]
latex_v1:  28%|##7       | 838/3000 [19:37<59:49,  1.66s/it, lr: 1.0e-04 loss: 4.823e-01]
latex_v1:  28%|##7       | 839/3000 [19:37<1:02:21,  1.73s/it, lr: 1.0e-04 loss: 4.823e-01]
latex_v1:  28%|##7       | 839/3000 [19:37<1:02:21,  1.73s/it, lr: 1.0e-04 loss: 4.823e-01]
latex_v1:  28%|##7       | 839/3000 [19:37<1:02:21,  1.73s/it, lr: 1.0e-04 loss: 6.353e-01]
latex_v1:  28%|##7       | 839/3000 [19:37<1:02:21,  1.73s/it, lr: 1.0e-04 loss: 6.353e-01]
latex_v1:  28%|##8       | 840/3000 [19:38<1:02:20,  1.73s/it, lr: 1.0e-04 loss: 4.152e-01]
latex_v1:  28%|##8       | 840/3000 [19:38<1:02:20,  1.73s/it, lr: 1.0e-04 loss: 4.152e-01]
latex_v1:  28%|##8       | 841/3000 [19:38<40:09,  1.12s/it, lr: 1.0e-04 loss: 4.152e-01]  
latex_v1:  28%|##8       | 841/3000 [19:38<40:09,  1.12s/it, lr: 1.0e-04 loss: 4.152e-01]  
latex_v1:  28%|##8       | 841/3000 [19:39<40:09,  1.12s/it, lr: 1.0e-04 loss: 3.616e-02]
latex_v1:  28%|##8       | 841/3000 [19:39<40:09,  1.12s/it, lr: 1.0e-04 loss: 3.616e-02]
latex_v1:  28%|##8       | 842/3000 [19:39<36:58,  1.03s/it, lr: 1.0e-04 loss: 3.616e-02]
latex_v1:  28%|##8       | 842/3000 [19:39<36:58,  1.03s/it, lr: 1.0e-04 loss: 3.616e-02]
latex_v1:  28%|##8       | 842/3000 [19:41<36:58,  1.03s/it, lr: 1.0e-04 loss: 5.430e-01]
latex_v1:  28%|##8       | 842/3000 [19:41<36:58,  1.03s/it, lr: 1.0e-04 loss: 5.430e-01]
latex_v1:  28%|##8       | 843/3000 [19:41<43:35,  1.21s/it, lr: 1.0e-04 loss: 5.430e-01]
latex_v1:  28%|##8       | 843/3000 [19:41<43:35,  1.21s/it, lr: 1.0e-04 loss: 5.430e-01]
latex_v1:  28%|##8       | 843/3000 [19:42<43:35,  1.21s/it, lr: 1.0e-04 loss: 7.689e-01]
latex_v1:  28%|##8       | 843/3000 [19:42<43:35,  1.21s/it, lr: 1.0e-04 loss: 7.689e-01]
latex_v1:  28%|##8       | 844/3000 [19:42<45:36,  1.27s/it, lr: 1.0e-04 loss: 7.689e-01]
latex_v1:  28%|##8       | 844/3000 [19:42<45:36,  1.27s/it, lr: 1.0e-04 loss: 7.689e-01]
latex_v1:  28%|##8       | 844/3000 [19:43<45:36,  1.27s/it, lr: 1.0e-04 loss: 6.951e-01]
latex_v1:  28%|##8       | 844/3000 [19:43<45:36,  1.27s/it, lr: 1.0e-04 loss: 6.951e-01]
latex_v1:  28%|##8       | 845/3000 [19:43<43:23,  1.21s/it, lr: 1.0e-04 loss: 6.951e-01]
latex_v1:  28%|##8       | 845/3000 [19:43<43:23,  1.21s/it, lr: 1.0e-04 loss: 6.951e-01]
latex_v1:  28%|##8       | 845/3000 [19:46<43:23,  1.21s/it, lr: 1.0e-04 loss: 4.303e-02]
latex_v1:  28%|##8       | 845/3000 [19:46<43:23,  1.21s/it, lr: 1.0e-04 loss: 4.303e-02]
latex_v1:  28%|##8       | 846/3000 [19:46<1:00:29,  1.69s/it, lr: 1.0e-04 loss: 4.303e-02]
latex_v1:  28%|##8       | 846/3000 [19:46<1:00:29,  1.69s/it, lr: 1.0e-04 loss: 4.303e-02]
latex_v1:  28%|##8       | 846/3000 [19:47<1:00:29,  1.69s/it, lr: 1.0e-04 loss: 1.957e-01]
latex_v1:  28%|##8       | 846/3000 [19:47<1:00:29,  1.69s/it, lr: 1.0e-04 loss: 1.957e-01]
latex_v1:  28%|##8       | 847/3000 [19:47<50:57,  1.42s/it, lr: 1.0e-04 loss: 1.957e-01]  
latex_v1:  28%|##8       | 847/3000 [19:47<50:57,  1.42s/it, lr: 1.0e-04 loss: 1.957e-01]  
latex_v1:  28%|##8       | 847/3000 [19:48<50:57,  1.42s/it, lr: 1.0e-04 loss: 1.737e-01]
latex_v1:  28%|##8       | 847/3000 [19:48<50:57,  1.42s/it, lr: 1.0e-04 loss: 1.737e-01]
latex_v1:  28%|##8       | 848/3000 [19:48<51:01,  1.42s/it, lr: 1.0e-04 loss: 1.737e-01]
latex_v1:  28%|##8       | 848/3000 [19:48<51:01,  1.42s/it, lr: 1.0e-04 loss: 1.737e-01]
latex_v1:  28%|##8       | 848/3000 [19:49<51:01,  1.42s/it, lr: 1.0e-04 loss: 2.167e-01]
latex_v1:  28%|##8       | 848/3000 [19:49<51:01,  1.42s/it, lr: 1.0e-04 loss: 2.167e-01]
latex_v1:  28%|##8       | 849/3000 [19:49<44:00,  1.23s/it, lr: 1.0e-04 loss: 2.167e-01]
latex_v1:  28%|##8       | 849/3000 [19:49<44:00,  1.23s/it, lr: 1.0e-04 loss: 2.167e-01]
latex_v1:  28%|##8       | 849/3000 [19:51<44:00,  1.23s/it, lr: 1.0e-04 loss: 2.005e-01]
latex_v1:  28%|##8       | 849/3000 [19:51<44:00,  1.23s/it, lr: 1.0e-04 loss: 2.005e-01]
latex_v1:  28%|##8       | 850/3000 [19:52<43:59,  1.23s/it, lr: 1.0e-04 loss: 8.635e-01]
latex_v1:  28%|##8       | 850/3000 [19:52<43:59,  1.23s/it, lr: 1.0e-04 loss: 8.635e-01]
latex_v1:  28%|##8       | 851/3000 [19:52<33:27,  1.07it/s, lr: 1.0e-04 loss: 8.635e-01]
latex_v1:  28%|##8       | 851/3000 [19:52<33:27,  1.07it/s, lr: 1.0e-04 loss: 8.635e-01]
latex_v1:  28%|##8       | 851/3000 [19:53<33:27,  1.07it/s, lr: 1.0e-04 loss: 1.215e-01]
latex_v1:  28%|##8       | 851/3000 [19:53<33:27,  1.07it/s, lr: 1.0e-04 loss: 1.215e-01]
latex_v1:  28%|##8       | 852/3000 [19:53<37:10,  1.04s/it, lr: 1.0e-04 loss: 1.215e-01]
latex_v1:  28%|##8       | 852/3000 [19:53<37:10,  1.04s/it, lr: 1.0e-04 loss: 1.215e-01]
latex_v1:  28%|##8       | 852/3000 [19:54<37:10,  1.04s/it, lr: 1.0e-04 loss: 3.530e-01]
latex_v1:  28%|##8       | 852/3000 [19:54<37:10,  1.04s/it, lr: 1.0e-04 loss: 3.530e-01]
latex_v1:  28%|##8       | 853/3000 [19:54<36:27,  1.02s/it, lr: 1.0e-04 loss: 3.530e-01]
latex_v1:  28%|##8       | 853/3000 [19:54<36:27,  1.02s/it, lr: 1.0e-04 loss: 3.530e-01]
latex_v1:  28%|##8       | 853/3000 [19:55<36:27,  1.02s/it, lr: 1.0e-04 loss: 4.990e-01]
latex_v1:  28%|##8       | 853/3000 [19:55<36:27,  1.02s/it, lr: 1.0e-04 loss: 4.990e-01]
latex_v1:  28%|##8       | 854/3000 [19:55<36:01,  1.01s/it, lr: 1.0e-04 loss: 4.990e-01]
latex_v1:  28%|##8       | 854/3000 [19:55<36:01,  1.01s/it, lr: 1.0e-04 loss: 4.990e-01]
latex_v1:  28%|##8       | 854/3000 [19:56<36:01,  1.01s/it, lr: 1.0e-04 loss: 6.821e-01]
latex_v1:  28%|##8       | 854/3000 [19:56<36:01,  1.01s/it, lr: 1.0e-04 loss: 6.821e-01]
latex_v1:  28%|##8       | 855/3000 [19:56<38:02,  1.06s/it, lr: 1.0e-04 loss: 6.821e-01]
latex_v1:  28%|##8       | 855/3000 [19:56<38:02,  1.06s/it, lr: 1.0e-04 loss: 6.821e-01]
latex_v1:  28%|##8       | 855/3000 [19:57<38:02,  1.06s/it, lr: 1.0e-04 loss: 2.381e-01]
latex_v1:  28%|##8       | 855/3000 [19:57<38:02,  1.06s/it, lr: 1.0e-04 loss: 2.381e-01]
latex_v1:  29%|##8       | 856/3000 [19:57<34:51,  1.03it/s, lr: 1.0e-04 loss: 2.381e-01]
latex_v1:  29%|##8       | 856/3000 [19:57<34:51,  1.03it/s, lr: 1.0e-04 loss: 2.381e-01]
latex_v1:  29%|##8       | 856/3000 [19:58<34:51,  1.03it/s, lr: 1.0e-04 loss: 4.173e-01]
latex_v1:  29%|##8       | 856/3000 [19:58<34:51,  1.03it/s, lr: 1.0e-04 loss: 4.173e-01]
latex_v1:  29%|##8       | 857/3000 [19:58<39:53,  1.12s/it, lr: 1.0e-04 loss: 4.173e-01]
latex_v1:  29%|##8       | 857/3000 [19:58<39:53,  1.12s/it, lr: 1.0e-04 loss: 4.173e-01]
latex_v1:  29%|##8       | 857/3000 [20:01<39:53,  1.12s/it, lr: 1.0e-04 loss: 4.846e-01]
latex_v1:  29%|##8       | 857/3000 [20:01<39:53,  1.12s/it, lr: 1.0e-04 loss: 4.846e-01]
latex_v1:  29%|##8       | 858/3000 [20:01<51:11,  1.43s/it, lr: 1.0e-04 loss: 4.846e-01]
latex_v1:  29%|##8       | 858/3000 [20:01<51:11,  1.43s/it, lr: 1.0e-04 loss: 4.846e-01]
latex_v1:  29%|##8       | 858/3000 [20:02<51:11,  1.43s/it, lr: 1.0e-04 loss: 5.807e-01]
latex_v1:  29%|##8       | 858/3000 [20:02<51:11,  1.43s/it, lr: 1.0e-04 loss: 5.807e-01]
latex_v1:  29%|##8       | 859/3000 [20:02<54:12,  1.52s/it, lr: 1.0e-04 loss: 5.807e-01]
latex_v1:  29%|##8       | 859/3000 [20:02<54:12,  1.52s/it, lr: 1.0e-04 loss: 5.807e-01]
latex_v1:  29%|##8       | 859/3000 [20:04<54:12,  1.52s/it, lr: 1.0e-04 loss: 4.354e-01]
latex_v1:  29%|##8       | 859/3000 [20:04<54:12,  1.52s/it, lr: 1.0e-04 loss: 4.354e-01]
latex_v1:  29%|##8       | 860/3000 [20:05<54:11,  1.52s/it, lr: 1.0e-04 loss: 6.106e-01]
latex_v1:  29%|##8       | 860/3000 [20:05<54:11,  1.52s/it, lr: 1.0e-04 loss: 6.106e-01]
latex_v1:  29%|##8       | 861/3000 [20:05<42:06,  1.18s/it, lr: 1.0e-04 loss: 6.106e-01]
latex_v1:  29%|##8       | 861/3000 [20:05<42:06,  1.18s/it, lr: 1.0e-04 loss: 6.106e-01]
latex_v1:  29%|##8       | 861/3000 [20:08<42:06,  1.18s/it, lr: 1.0e-04 loss: 4.515e-02]
latex_v1:  29%|##8       | 861/3000 [20:08<42:06,  1.18s/it, lr: 1.0e-04 loss: 4.515e-02]
latex_v1:  29%|##8       | 862/3000 [20:08<57:03,  1.60s/it, lr: 1.0e-04 loss: 4.515e-02]
latex_v1:  29%|##8       | 862/3000 [20:08<57:03,  1.60s/it, lr: 1.0e-04 loss: 4.515e-02]
latex_v1:  29%|##8       | 862/3000 [20:09<57:03,  1.60s/it, lr: 1.0e-04 loss: 1.135e-01]
latex_v1:  29%|##8       | 862/3000 [20:09<57:03,  1.60s/it, lr: 1.0e-04 loss: 1.135e-01]
latex_v1:  29%|##8       | 863/3000 [20:09<49:14,  1.38s/it, lr: 1.0e-04 loss: 1.135e-01]
latex_v1:  29%|##8       | 863/3000 [20:09<49:14,  1.38s/it, lr: 1.0e-04 loss: 1.135e-01]
latex_v1:  29%|##8       | 863/3000 [20:10<49:14,  1.38s/it, lr: 1.0e-04 loss: 3.566e-01]
latex_v1:  29%|##8       | 863/3000 [20:10<49:14,  1.38s/it, lr: 1.0e-04 loss: 3.566e-01]
latex_v1:  29%|##8       | 864/3000 [20:10<43:05,  1.21s/it, lr: 1.0e-04 loss: 3.566e-01]
latex_v1:  29%|##8       | 864/3000 [20:10<43:05,  1.21s/it, lr: 1.0e-04 loss: 3.566e-01]
latex_v1:  29%|##8       | 864/3000 [20:11<43:05,  1.21s/it, lr: 1.0e-04 loss: 1.777e-01]
latex_v1:  29%|##8       | 864/3000 [20:11<43:05,  1.21s/it, lr: 1.0e-04 loss: 1.777e-01]
latex_v1:  29%|##8       | 865/3000 [20:11<46:27,  1.31s/it, lr: 1.0e-04 loss: 1.777e-01]
latex_v1:  29%|##8       | 865/3000 [20:11<46:27,  1.31s/it, lr: 1.0e-04 loss: 1.777e-01]
latex_v1:  29%|##8       | 865/3000 [20:12<46:27,  1.31s/it, lr: 1.0e-04 loss: 1.277e-01]
latex_v1:  29%|##8       | 865/3000 [20:12<46:27,  1.31s/it, lr: 1.0e-04 loss: 1.277e-01]
latex_v1:  29%|##8       | 866/3000 [20:12<40:48,  1.15s/it, lr: 1.0e-04 loss: 1.277e-01]
latex_v1:  29%|##8       | 866/3000 [20:12<40:48,  1.15s/it, lr: 1.0e-04 loss: 1.277e-01]
latex_v1:  29%|##8       | 866/3000 [20:13<40:48,  1.15s/it, lr: 1.0e-04 loss: 4.827e-01]
latex_v1:  29%|##8       | 866/3000 [20:13<40:48,  1.15s/it, lr: 1.0e-04 loss: 4.827e-01]
latex_v1:  29%|##8       | 867/3000 [20:13<37:16,  1.05s/it, lr: 1.0e-04 loss: 4.827e-01]
latex_v1:  29%|##8       | 867/3000 [20:13<37:16,  1.05s/it, lr: 1.0e-04 loss: 4.827e-01]
latex_v1:  29%|##8       | 867/3000 [20:14<37:16,  1.05s/it, lr: 1.0e-04 loss: 4.438e-01]
latex_v1:  29%|##8       | 867/3000 [20:14<37:16,  1.05s/it, lr: 1.0e-04 loss: 4.438e-01]
latex_v1:  29%|##8       | 868/3000 [20:14<40:42,  1.15s/it, lr: 1.0e-04 loss: 4.438e-01]
latex_v1:  29%|##8       | 868/3000 [20:14<40:42,  1.15s/it, lr: 1.0e-04 loss: 4.438e-01]
latex_v1:  29%|##8       | 868/3000 [20:15<40:42,  1.15s/it, lr: 1.0e-04 loss: 1.793e-01]
latex_v1:  29%|##8       | 868/3000 [20:15<40:42,  1.15s/it, lr: 1.0e-04 loss: 1.793e-01]
latex_v1:  29%|##8       | 869/3000 [20:15<36:33,  1.03s/it, lr: 1.0e-04 loss: 1.793e-01]
latex_v1:  29%|##8       | 869/3000 [20:15<36:33,  1.03s/it, lr: 1.0e-04 loss: 1.793e-01]
latex_v1:  29%|##8       | 869/3000 [20:18<36:33,  1.03s/it, lr: 1.0e-04 loss: 7.661e-01]
latex_v1:  29%|##8       | 869/3000 [20:18<36:33,  1.03s/it, lr: 1.0e-04 loss: 7.661e-01]
latex_v1:  29%|##9       | 870/3000 [20:19<36:32,  1.03s/it, lr: 1.0e-04 loss: 2.047e-01]
latex_v1:  29%|##9       | 870/3000 [20:19<36:32,  1.03s/it, lr: 1.0e-04 loss: 2.047e-01]
latex_v1:  29%|##9       | 871/3000 [20:19<31:12,  1.14it/s, lr: 1.0e-04 loss: 2.047e-01]
latex_v1:  29%|##9       | 871/3000 [20:19<31:12,  1.14it/s, lr: 1.0e-04 loss: 2.047e-01]
latex_v1:  29%|##9       | 871/3000 [20:20<31:12,  1.14it/s, lr: 1.0e-04 loss: 5.692e-01]
latex_v1:  29%|##9       | 871/3000 [20:20<31:12,  1.14it/s, lr: 1.0e-04 loss: 5.692e-01]
latex_v1:  29%|##9       | 872/3000 [20:20<32:22,  1.10it/s, lr: 1.0e-04 loss: 5.692e-01]
latex_v1:  29%|##9       | 872/3000 [20:20<32:22,  1.10it/s, lr: 1.0e-04 loss: 5.692e-01]
latex_v1:  29%|##9       | 872/3000 [20:22<32:22,  1.10it/s, lr: 1.0e-04 loss: 4.198e-01]
latex_v1:  29%|##9       | 872/3000 [20:22<32:22,  1.10it/s, lr: 1.0e-04 loss: 4.198e-01]
latex_v1:  29%|##9       | 873/3000 [20:22<37:23,  1.05s/it, lr: 1.0e-04 loss: 4.198e-01]
latex_v1:  29%|##9       | 873/3000 [20:22<37:23,  1.05s/it, lr: 1.0e-04 loss: 4.198e-01]
latex_v1:  29%|##9       | 873/3000 [20:24<37:23,  1.05s/it, lr: 1.0e-04 loss: 8.813e-02]
latex_v1:  29%|##9       | 873/3000 [20:24<37:23,  1.05s/it, lr: 1.0e-04 loss: 8.813e-02]
latex_v1:  29%|##9       | 874/3000 [20:24<45:28,  1.28s/it, lr: 1.0e-04 loss: 8.813e-02]
latex_v1:  29%|##9       | 874/3000 [20:24<45:28,  1.28s/it, lr: 1.0e-04 loss: 8.813e-02]
latex_v1:  29%|##9       | 874/3000 [20:25<45:28,  1.28s/it, lr: 1.0e-04 loss: 4.077e-01]
latex_v1:  29%|##9       | 874/3000 [20:25<45:28,  1.28s/it, lr: 1.0e-04 loss: 4.077e-01]
latex_v1:  29%|##9       | 875/3000 [20:25<40:25,  1.14s/it, lr: 1.0e-04 loss: 4.077e-01]
latex_v1:  29%|##9       | 875/3000 [20:25<40:25,  1.14s/it, lr: 1.0e-04 loss: 4.077e-01]
latex_v1:  29%|##9       | 875/3000 [20:26<40:25,  1.14s/it, lr: 1.0e-04 loss: 4.133e-01]
latex_v1:  29%|##9       | 875/3000 [20:26<40:25,  1.14s/it, lr: 1.0e-04 loss: 4.133e-01]
latex_v1:  29%|##9       | 876/3000 [20:26<40:49,  1.15s/it, lr: 1.0e-04 loss: 4.133e-01]
latex_v1:  29%|##9       | 876/3000 [20:26<40:49,  1.15s/it, lr: 1.0e-04 loss: 4.133e-01]
latex_v1:  29%|##9       | 876/3000 [20:27<40:49,  1.15s/it, lr: 1.0e-04 loss: 2.005e-01]
latex_v1:  29%|##9       | 876/3000 [20:27<40:49,  1.15s/it, lr: 1.0e-04 loss: 2.005e-01]
latex_v1:  29%|##9       | 877/3000 [20:27<42:40,  1.21s/it, lr: 1.0e-04 loss: 2.005e-01]
latex_v1:  29%|##9       | 877/3000 [20:27<42:40,  1.21s/it, lr: 1.0e-04 loss: 2.005e-01]
latex_v1:  29%|##9       | 877/3000 [20:28<42:40,  1.21s/it, lr: 1.0e-04 loss: 6.833e-02]
latex_v1:  29%|##9       | 877/3000 [20:28<42:40,  1.21s/it, lr: 1.0e-04 loss: 6.833e-02]
latex_v1:  29%|##9       | 878/3000 [20:28<42:31,  1.20s/it, lr: 1.0e-04 loss: 6.833e-02]
latex_v1:  29%|##9       | 878/3000 [20:28<42:31,  1.20s/it, lr: 1.0e-04 loss: 6.833e-02]
latex_v1:  29%|##9       | 878/3000 [20:30<42:31,  1.20s/it, lr: 1.0e-04 loss: 3.992e-01]
latex_v1:  29%|##9       | 878/3000 [20:30<42:31,  1.20s/it, lr: 1.0e-04 loss: 3.992e-01]
latex_v1:  29%|##9       | 879/3000 [20:30<46:06,  1.30s/it, lr: 1.0e-04 loss: 3.992e-01]
latex_v1:  29%|##9       | 879/3000 [20:30<46:06,  1.30s/it, lr: 1.0e-04 loss: 3.992e-01]
latex_v1:  29%|##9       | 879/3000 [20:31<46:06,  1.30s/it, lr: 1.0e-04 loss: 2.604e-01]
latex_v1:  29%|##9       | 879/3000 [20:31<46:06,  1.30s/it, lr: 1.0e-04 loss: 2.604e-01]
latex_v1:  29%|##9       | 880/3000 [20:33<46:05,  1.30s/it, lr: 1.0e-04 loss: 1.465e-01]
latex_v1:  29%|##9       | 880/3000 [20:33<46:05,  1.30s/it, lr: 1.0e-04 loss: 1.465e-01]
latex_v1:  29%|##9       | 881/3000 [20:33<38:26,  1.09s/it, lr: 1.0e-04 loss: 1.465e-01]
latex_v1:  29%|##9       | 881/3000 [20:33<38:26,  1.09s/it, lr: 1.0e-04 loss: 1.465e-01]
latex_v1:  29%|##9       | 881/3000 [20:35<38:26,  1.09s/it, lr: 1.0e-04 loss: 6.144e-01]
latex_v1:  29%|##9       | 881/3000 [20:35<38:26,  1.09s/it, lr: 1.0e-04 loss: 6.144e-01]
latex_v1:  29%|##9       | 882/3000 [20:35<42:26,  1.20s/it, lr: 1.0e-04 loss: 6.144e-01]
latex_v1:  29%|##9       | 882/3000 [20:35<42:26,  1.20s/it, lr: 1.0e-04 loss: 6.144e-01]
latex_v1:  29%|##9       | 882/3000 [20:36<42:26,  1.20s/it, lr: 1.0e-04 loss: 1.180e-01]
latex_v1:  29%|##9       | 882/3000 [20:36<42:26,  1.20s/it, lr: 1.0e-04 loss: 1.180e-01]
latex_v1:  29%|##9       | 883/3000 [20:36<43:33,  1.23s/it, lr: 1.0e-04 loss: 1.180e-01]
latex_v1:  29%|##9       | 883/3000 [20:36<43:33,  1.23s/it, lr: 1.0e-04 loss: 1.180e-01]
latex_v1:  29%|##9       | 883/3000 [20:37<43:33,  1.23s/it, lr: 1.0e-04 loss: 3.721e-01]
latex_v1:  29%|##9       | 883/3000 [20:37<43:33,  1.23s/it, lr: 1.0e-04 loss: 3.721e-01]
latex_v1:  29%|##9       | 884/3000 [20:37<38:50,  1.10s/it, lr: 1.0e-04 loss: 3.721e-01]
latex_v1:  29%|##9       | 884/3000 [20:37<38:50,  1.10s/it, lr: 1.0e-04 loss: 3.721e-01]
latex_v1:  29%|##9       | 884/3000 [20:39<38:50,  1.10s/it, lr: 1.0e-04 loss: 2.171e-01]
latex_v1:  29%|##9       | 884/3000 [20:39<38:50,  1.10s/it, lr: 1.0e-04 loss: 2.171e-01]
latex_v1:  30%|##9       | 885/3000 [20:39<54:49,  1.56s/it, lr: 1.0e-04 loss: 2.171e-01]
latex_v1:  30%|##9       | 885/3000 [20:39<54:49,  1.56s/it, lr: 1.0e-04 loss: 2.171e-01]
latex_v1:  30%|##9       | 885/3000 [20:40<54:49,  1.56s/it, lr: 1.0e-04 loss: 3.094e-01]
latex_v1:  30%|##9       | 885/3000 [20:40<54:49,  1.56s/it, lr: 1.0e-04 loss: 3.094e-01]
latex_v1:  30%|##9       | 886/3000 [20:40<49:05,  1.39s/it, lr: 1.0e-04 loss: 3.094e-01]
latex_v1:  30%|##9       | 886/3000 [20:40<49:05,  1.39s/it, lr: 1.0e-04 loss: 3.094e-01]
latex_v1:  30%|##9       | 886/3000 [20:41<49:05,  1.39s/it, lr: 1.0e-04 loss: 4.203e-01]
latex_v1:  30%|##9       | 886/3000 [20:41<49:05,  1.39s/it, lr: 1.0e-04 loss: 4.203e-01]
latex_v1:  30%|##9       | 887/3000 [20:41<42:43,  1.21s/it, lr: 1.0e-04 loss: 4.203e-01]
latex_v1:  30%|##9       | 887/3000 [20:41<42:43,  1.21s/it, lr: 1.0e-04 loss: 4.203e-01]
latex_v1:  30%|##9       | 887/3000 [20:44<42:43,  1.21s/it, lr: 1.0e-04 loss: 8.653e-02]
latex_v1:  30%|##9       | 887/3000 [20:44<42:43,  1.21s/it, lr: 1.0e-04 loss: 8.653e-02]
latex_v1:  30%|##9       | 888/3000 [20:44<59:35,  1.69s/it, lr: 1.0e-04 loss: 8.653e-02]
latex_v1:  30%|##9       | 888/3000 [20:44<59:35,  1.69s/it, lr: 1.0e-04 loss: 8.653e-02]
latex_v1:  30%|##9       | 888/3000 [20:45<59:35,  1.69s/it, lr: 1.0e-04 loss: 2.959e-01]
latex_v1:  30%|##9       | 888/3000 [20:45<59:35,  1.69s/it, lr: 1.0e-04 loss: 2.959e-01]
latex_v1:  30%|##9       | 889/3000 [20:45<57:10,  1.63s/it, lr: 1.0e-04 loss: 2.959e-01]
latex_v1:  30%|##9       | 889/3000 [20:45<57:10,  1.63s/it, lr: 1.0e-04 loss: 2.959e-01]
latex_v1:  30%|##9       | 889/3000 [20:47<57:10,  1.63s/it, lr: 1.0e-04 loss: 7.793e-02]
latex_v1:  30%|##9       | 889/3000 [20:47<57:10,  1.63s/it, lr: 1.0e-04 loss: 7.793e-02]
latex_v1:  30%|##9       | 890/3000 [20:50<57:08,  1.63s/it, lr: 1.0e-04 loss: 6.132e-01]
latex_v1:  30%|##9       | 890/3000 [20:50<57:08,  1.63s/it, lr: 1.0e-04 loss: 6.132e-01]
latex_v1:  30%|##9       | 891/3000 [20:50<53:58,  1.54s/it, lr: 1.0e-04 loss: 6.132e-01]
latex_v1:  30%|##9       | 891/3000 [20:50<53:58,  1.54s/it, lr: 1.0e-04 loss: 6.132e-01]
latex_v1:  30%|##9       | 891/3000 [20:52<53:58,  1.54s/it, lr: 1.0e-04 loss: 6.898e-02]
latex_v1:  30%|##9       | 891/3000 [20:52<53:58,  1.54s/it, lr: 1.0e-04 loss: 6.898e-02]
latex_v1:  30%|##9       | 892/3000 [20:52<53:57,  1.54s/it, lr: 1.0e-04 loss: 6.898e-02]
latex_v1:  30%|##9       | 892/3000 [20:52<53:57,  1.54s/it, lr: 1.0e-04 loss: 6.898e-02]
latex_v1:  30%|##9       | 892/3000 [20:52<53:57,  1.54s/it, lr: 1.0e-04 loss: 1.779e-01]
latex_v1:  30%|##9       | 892/3000 [20:52<53:57,  1.54s/it, lr: 1.0e-04 loss: 1.779e-01]
latex_v1:  30%|##9       | 893/3000 [20:52<46:50,  1.33s/it, lr: 1.0e-04 loss: 1.779e-01]
latex_v1:  30%|##9       | 893/3000 [20:52<46:50,  1.33s/it, lr: 1.0e-04 loss: 1.779e-01]
latex_v1:  30%|##9       | 893/3000 [20:53<46:50,  1.33s/it, lr: 1.0e-04 loss: 1.211e-01]
latex_v1:  30%|##9       | 893/3000 [20:53<46:50,  1.33s/it, lr: 1.0e-04 loss: 1.211e-01]
latex_v1:  30%|##9       | 894/3000 [20:53<41:19,  1.18s/it, lr: 1.0e-04 loss: 1.211e-01]
latex_v1:  30%|##9       | 894/3000 [20:53<41:19,  1.18s/it, lr: 1.0e-04 loss: 1.211e-01]
latex_v1:  30%|##9       | 894/3000 [20:55<41:19,  1.18s/it, lr: 1.0e-04 loss: 4.627e-01]
latex_v1:  30%|##9       | 894/3000 [20:55<41:19,  1.18s/it, lr: 1.0e-04 loss: 4.627e-01]
latex_v1:  30%|##9       | 895/3000 [20:55<48:17,  1.38s/it, lr: 1.0e-04 loss: 4.627e-01]
latex_v1:  30%|##9       | 895/3000 [20:55<48:17,  1.38s/it, lr: 1.0e-04 loss: 4.627e-01]
latex_v1:  30%|##9       | 895/3000 [20:56<48:17,  1.38s/it, lr: 1.0e-04 loss: 6.890e-01]
latex_v1:  30%|##9       | 895/3000 [20:56<48:17,  1.38s/it, lr: 1.0e-04 loss: 6.890e-01]
latex_v1:  30%|##9       | 896/3000 [20:56<42:03,  1.20s/it, lr: 1.0e-04 loss: 6.890e-01]
latex_v1:  30%|##9       | 896/3000 [20:56<42:03,  1.20s/it, lr: 1.0e-04 loss: 6.890e-01]
latex_v1:  30%|##9       | 896/3000 [20:57<42:03,  1.20s/it, lr: 1.0e-04 loss: 6.710e-01]
latex_v1:  30%|##9       | 896/3000 [20:57<42:03,  1.20s/it, lr: 1.0e-04 loss: 6.710e-01]
latex_v1:  30%|##9       | 897/3000 [20:57<44:39,  1.27s/it, lr: 1.0e-04 loss: 6.710e-01]
latex_v1:  30%|##9       | 897/3000 [20:57<44:39,  1.27s/it, lr: 1.0e-04 loss: 6.710e-01]
latex_v1:  30%|##9       | 897/3000 [20:59<44:39,  1.27s/it, lr: 1.0e-04 loss: 4.677e-01]
latex_v1:  30%|##9       | 897/3000 [20:59<44:39,  1.27s/it, lr: 1.0e-04 loss: 4.677e-01]
latex_v1:  30%|##9       | 898/3000 [20:59<51:01,  1.46s/it, lr: 1.0e-04 loss: 4.677e-01]
latex_v1:  30%|##9       | 898/3000 [20:59<51:01,  1.46s/it, lr: 1.0e-04 loss: 4.677e-01]
latex_v1:  30%|##9       | 898/3000 [21:01<51:01,  1.46s/it, lr: 1.0e-04 loss: 9.444e-02]
latex_v1:  30%|##9       | 898/3000 [21:01<51:01,  1.46s/it, lr: 1.0e-04 loss: 9.444e-02]
latex_v1:  30%|##9       | 899/3000 [21:01<51:50,  1.48s/it, lr: 1.0e-04 loss: 9.444e-02]
latex_v1:  30%|##9       | 899/3000 [21:01<51:50,  1.48s/it, lr: 1.0e-04 loss: 9.444e-02]
latex_v1:  30%|##9       | 899/3000 [21:03<51:50,  1.48s/it, lr: 1.0e-04 loss: 4.309e-01]
latex_v1:  30%|##9       | 899/3000 [21:03<51:50,  1.48s/it, lr: 1.0e-04 loss: 4.309e-01]Unloading assistant lora



Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]


Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.43s/it]
Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.43s/it]


Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.41s/it]
Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.41s/it]


Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.40s/it]
Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.40s/it]


Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.40s/it]
Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.40s/it]


Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.39s/it]
Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.39s/it]


Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.41s/it]
Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.41s/it]


Generating Images: 100%|##########| 7/7 [00:16<00:00,  2.43s/it]
Generating Images: 100%|##########| 7/7 [00:16<00:00,  2.43s/it]


                                                                
                                                                Loading assistant lora

latex_v1:  30%|###       | 900/3000 [21:05<51:48,  1.48s/it, lr: 1.0e-04 loss: 2.204e-01]
latex_v1:  30%|###       | 900/3000 [21:05<51:48,  1.48s/it, lr: 1.0e-04 loss: 2.204e-01]
latex_v1:  30%|###       | 901/3000 [21:05<43:58,  1.26s/it, lr: 1.0e-04 loss: 2.204e-01]
latex_v1:  30%|###       | 901/3000 [21:05<43:58,  1.26s/it, lr: 1.0e-04 loss: 2.204e-01]
latex_v1:  30%|###       | 901/3000 [21:08<43:58,  1.26s/it, lr: 1.0e-04 loss: 3.417e-01]
latex_v1:  30%|###       | 901/3000 [21:08<43:58,  1.26s/it, lr: 1.0e-04 loss: 3.417e-01]
latex_v1:  30%|###       | 902/3000 [21:08<57:43,  1.65s/it, lr: 1.0e-04 loss: 3.417e-01]
latex_v1:  30%|###       | 902/3000 [21:08<57:43,  1.65s/it, lr: 1.0e-04 loss: 3.417e-01]
latex_v1:  30%|###       | 902/3000 [21:08<57:43,  1.65s/it, lr: 1.0e-04 loss: 6.490e-01]
latex_v1:  30%|###       | 902/3000 [21:08<57:43,  1.65s/it, lr: 1.0e-04 loss: 6.490e-01]
latex_v1:  30%|###       | 903/3000 [21:08<49:30,  1.42s/it, lr: 1.0e-04 loss: 6.490e-01]
latex_v1:  30%|###       | 903/3000 [21:08<49:30,  1.42s/it, lr: 1.0e-04 loss: 6.490e-01]
latex_v1:  30%|###       | 903/3000 [21:09<49:30,  1.42s/it, lr: 1.0e-04 loss: 3.979e-01]
latex_v1:  30%|###       | 903/3000 [21:09<49:30,  1.42s/it, lr: 1.0e-04 loss: 3.979e-01]
latex_v1:  30%|###       | 904/3000 [21:09<43:18,  1.24s/it, lr: 1.0e-04 loss: 3.979e-01]
latex_v1:  30%|###       | 904/3000 [21:09<43:18,  1.24s/it, lr: 1.0e-04 loss: 3.979e-01]
latex_v1:  30%|###       | 904/3000 [21:12<43:18,  1.24s/it, lr: 1.0e-04 loss: 2.468e-02]
latex_v1:  30%|###       | 904/3000 [21:12<43:18,  1.24s/it, lr: 1.0e-04 loss: 2.468e-02]
latex_v1:  30%|###       | 905/3000 [21:12<59:10,  1.69s/it, lr: 1.0e-04 loss: 2.468e-02]
latex_v1:  30%|###       | 905/3000 [21:12<59:10,  1.69s/it, lr: 1.0e-04 loss: 2.468e-02]
latex_v1:  30%|###       | 905/3000 [21:13<59:10,  1.69s/it, lr: 1.0e-04 loss: 5.884e-01]
latex_v1:  30%|###       | 905/3000 [21:13<59:10,  1.69s/it, lr: 1.0e-04 loss: 5.884e-01]
latex_v1:  30%|###       | 906/3000 [21:13<52:53,  1.52s/it, lr: 1.0e-04 loss: 5.884e-01]
latex_v1:  30%|###       | 906/3000 [21:13<52:53,  1.52s/it, lr: 1.0e-04 loss: 5.884e-01]
latex_v1:  30%|###       | 906/3000 [21:14<52:53,  1.52s/it, lr: 1.0e-04 loss: 4.313e-01]
latex_v1:  30%|###       | 906/3000 [21:14<52:53,  1.52s/it, lr: 1.0e-04 loss: 4.313e-01]
latex_v1:  30%|###       | 907/3000 [21:14<45:05,  1.29s/it, lr: 1.0e-04 loss: 4.313e-01]
latex_v1:  30%|###       | 907/3000 [21:14<45:05,  1.29s/it, lr: 1.0e-04 loss: 4.313e-01]
latex_v1:  30%|###       | 907/3000 [21:15<45:05,  1.29s/it, lr: 1.0e-04 loss: 5.822e-01]
latex_v1:  30%|###       | 907/3000 [21:15<45:05,  1.29s/it, lr: 1.0e-04 loss: 5.822e-01]
latex_v1:  30%|###       | 908/3000 [21:15<39:35,  1.14s/it, lr: 1.0e-04 loss: 5.822e-01]
latex_v1:  30%|###       | 908/3000 [21:15<39:35,  1.14s/it, lr: 1.0e-04 loss: 5.822e-01]
latex_v1:  30%|###       | 908/3000 [21:16<39:35,  1.14s/it, lr: 1.0e-04 loss: 2.942e-01]
latex_v1:  30%|###       | 908/3000 [21:16<39:35,  1.14s/it, lr: 1.0e-04 loss: 2.942e-01]
latex_v1:  30%|###       | 909/3000 [21:16<38:50,  1.11s/it, lr: 1.0e-04 loss: 2.942e-01]
latex_v1:  30%|###       | 909/3000 [21:16<38:50,  1.11s/it, lr: 1.0e-04 loss: 2.942e-01]
latex_v1:  30%|###       | 909/3000 [21:17<38:50,  1.11s/it, lr: 1.0e-04 loss: 6.013e-01]
latex_v1:  30%|###       | 909/3000 [21:17<38:50,  1.11s/it, lr: 1.0e-04 loss: 6.013e-01]
latex_v1:  30%|###       | 910/3000 [21:19<38:49,  1.11s/it, lr: 1.0e-04 loss: 4.758e-01]
latex_v1:  30%|###       | 910/3000 [21:19<38:49,  1.11s/it, lr: 1.0e-04 loss: 4.758e-01]
latex_v1:  30%|###       | 911/3000 [21:19<32:35,  1.07it/s, lr: 1.0e-04 loss: 4.758e-01]
latex_v1:  30%|###       | 911/3000 [21:19<32:35,  1.07it/s, lr: 1.0e-04 loss: 4.758e-01]
latex_v1:  30%|###       | 911/3000 [21:19<32:35,  1.07it/s, lr: 1.0e-04 loss: 7.025e-01]
latex_v1:  30%|###       | 911/3000 [21:19<32:35,  1.07it/s, lr: 1.0e-04 loss: 7.025e-01]
latex_v1:  30%|###       | 912/3000 [21:19<31:00,  1.12it/s, lr: 1.0e-04 loss: 7.025e-01]
latex_v1:  30%|###       | 912/3000 [21:19<31:00,  1.12it/s, lr: 1.0e-04 loss: 7.025e-01]
latex_v1:  30%|###       | 912/3000 [21:21<31:00,  1.12it/s, lr: 1.0e-04 loss: 2.545e-01]
latex_v1:  30%|###       | 912/3000 [21:21<31:00,  1.12it/s, lr: 1.0e-04 loss: 2.545e-01]
latex_v1:  30%|###       | 913/3000 [21:21<37:02,  1.06s/it, lr: 1.0e-04 loss: 2.545e-01]
latex_v1:  30%|###       | 913/3000 [21:21<37:02,  1.06s/it, lr: 1.0e-04 loss: 2.545e-01]
latex_v1:  30%|###       | 913/3000 [21:23<37:02,  1.06s/it, lr: 1.0e-04 loss: 1.383e-01]
latex_v1:  30%|###       | 913/3000 [21:23<37:02,  1.06s/it, lr: 1.0e-04 loss: 1.383e-01]
latex_v1:  30%|###       | 914/3000 [21:23<41:34,  1.20s/it, lr: 1.0e-04 loss: 1.383e-01]
latex_v1:  30%|###       | 914/3000 [21:23<41:34,  1.20s/it, lr: 1.0e-04 loss: 1.383e-01]
latex_v1:  30%|###       | 914/3000 [21:25<41:34,  1.20s/it, lr: 1.0e-04 loss: 4.569e-01]
latex_v1:  30%|###       | 914/3000 [21:25<41:34,  1.20s/it, lr: 1.0e-04 loss: 4.569e-01]
latex_v1:  30%|###       | 915/3000 [21:25<55:35,  1.60s/it, lr: 1.0e-04 loss: 4.569e-01]
latex_v1:  30%|###       | 915/3000 [21:25<55:35,  1.60s/it, lr: 1.0e-04 loss: 4.569e-01]
latex_v1:  30%|###       | 915/3000 [21:26<55:35,  1.60s/it, lr: 1.0e-04 loss: 4.231e-01]
latex_v1:  30%|###       | 915/3000 [21:26<55:35,  1.60s/it, lr: 1.0e-04 loss: 4.231e-01]
latex_v1:  31%|###       | 916/3000 [21:26<47:15,  1.36s/it, lr: 1.0e-04 loss: 4.231e-01]
latex_v1:  31%|###       | 916/3000 [21:26<47:15,  1.36s/it, lr: 1.0e-04 loss: 4.231e-01]
latex_v1:  31%|###       | 916/3000 [21:27<47:15,  1.36s/it, lr: 1.0e-04 loss: 4.334e-01]
latex_v1:  31%|###       | 916/3000 [21:27<47:15,  1.36s/it, lr: 1.0e-04 loss: 4.334e-01]
latex_v1:  31%|###       | 917/3000 [21:27<47:47,  1.38s/it, lr: 1.0e-04 loss: 4.334e-01]
latex_v1:  31%|###       | 917/3000 [21:27<47:47,  1.38s/it, lr: 1.0e-04 loss: 4.334e-01]
latex_v1:  31%|###       | 917/3000 [21:29<47:47,  1.38s/it, lr: 1.0e-04 loss: 5.357e-01]
latex_v1:  31%|###       | 917/3000 [21:29<47:47,  1.38s/it, lr: 1.0e-04 loss: 5.357e-01]
latex_v1:  31%|###       | 918/3000 [21:29<47:13,  1.36s/it, lr: 1.0e-04 loss: 5.357e-01]
latex_v1:  31%|###       | 918/3000 [21:29<47:13,  1.36s/it, lr: 1.0e-04 loss: 5.357e-01]
latex_v1:  31%|###       | 918/3000 [21:30<47:13,  1.36s/it, lr: 1.0e-04 loss: 8.851e-01]
latex_v1:  31%|###       | 918/3000 [21:30<47:13,  1.36s/it, lr: 1.0e-04 loss: 8.851e-01]
latex_v1:  31%|###       | 919/3000 [21:30<44:51,  1.29s/it, lr: 1.0e-04 loss: 8.851e-01]
latex_v1:  31%|###       | 919/3000 [21:30<44:51,  1.29s/it, lr: 1.0e-04 loss: 8.851e-01]
latex_v1:  31%|###       | 919/3000 [21:31<44:51,  1.29s/it, lr: 1.0e-04 loss: 4.009e-01]
latex_v1:  31%|###       | 919/3000 [21:31<44:51,  1.29s/it, lr: 1.0e-04 loss: 4.009e-01]
latex_v1:  31%|###       | 920/3000 [21:32<44:49,  1.29s/it, lr: 1.0e-04 loss: 3.873e-01]
latex_v1:  31%|###       | 920/3000 [21:32<44:49,  1.29s/it, lr: 1.0e-04 loss: 3.873e-01]
latex_v1:  31%|###       | 921/3000 [21:32<30:09,  1.15it/s, lr: 1.0e-04 loss: 3.873e-01]
latex_v1:  31%|###       | 921/3000 [21:32<30:09,  1.15it/s, lr: 1.0e-04 loss: 3.873e-01]
latex_v1:  31%|###       | 921/3000 [21:33<30:09,  1.15it/s, lr: 1.0e-04 loss: 1.679e-01]
latex_v1:  31%|###       | 921/3000 [21:33<30:09,  1.15it/s, lr: 1.0e-04 loss: 1.679e-01]
latex_v1:  31%|###       | 922/3000 [21:33<35:07,  1.01s/it, lr: 1.0e-04 loss: 1.679e-01]
latex_v1:  31%|###       | 922/3000 [21:33<35:07,  1.01s/it, lr: 1.0e-04 loss: 1.679e-01]
latex_v1:  31%|###       | 922/3000 [21:34<35:07,  1.01s/it, lr: 1.0e-04 loss: 4.946e-01]
latex_v1:  31%|###       | 922/3000 [21:34<35:07,  1.01s/it, lr: 1.0e-04 loss: 4.946e-01]
latex_v1:  31%|###       | 923/3000 [21:34<32:41,  1.06it/s, lr: 1.0e-04 loss: 4.946e-01]
latex_v1:  31%|###       | 923/3000 [21:34<32:41,  1.06it/s, lr: 1.0e-04 loss: 4.946e-01]
latex_v1:  31%|###       | 923/3000 [21:36<32:41,  1.06it/s, lr: 1.0e-04 loss: 1.974e-01]
latex_v1:  31%|###       | 923/3000 [21:36<32:41,  1.06it/s, lr: 1.0e-04 loss: 1.974e-01]
latex_v1:  31%|###       | 924/3000 [21:36<36:41,  1.06s/it, lr: 1.0e-04 loss: 1.974e-01]
latex_v1:  31%|###       | 924/3000 [21:36<36:41,  1.06s/it, lr: 1.0e-04 loss: 1.974e-01]
latex_v1:  31%|###       | 924/3000 [21:36<36:41,  1.06s/it, lr: 1.0e-04 loss: 2.096e-01]
latex_v1:  31%|###       | 924/3000 [21:36<36:41,  1.06s/it, lr: 1.0e-04 loss: 2.096e-01]
latex_v1:  31%|###       | 925/3000 [21:36<33:44,  1.02it/s, lr: 1.0e-04 loss: 2.096e-01]
latex_v1:  31%|###       | 925/3000 [21:36<33:44,  1.02it/s, lr: 1.0e-04 loss: 2.096e-01]
latex_v1:  31%|###       | 925/3000 [21:37<33:44,  1.02it/s, lr: 1.0e-04 loss: 4.623e-01]
latex_v1:  31%|###       | 925/3000 [21:37<33:44,  1.02it/s, lr: 1.0e-04 loss: 4.623e-01]
latex_v1:  31%|###       | 926/3000 [21:37<31:33,  1.10it/s, lr: 1.0e-04 loss: 4.623e-01]
latex_v1:  31%|###       | 926/3000 [21:37<31:33,  1.10it/s, lr: 1.0e-04 loss: 4.623e-01]
latex_v1:  31%|###       | 926/3000 [21:38<31:33,  1.10it/s, lr: 1.0e-04 loss: 7.242e-01]
latex_v1:  31%|###       | 926/3000 [21:38<31:33,  1.10it/s, lr: 1.0e-04 loss: 7.242e-01]
latex_v1:  31%|###       | 927/3000 [21:38<36:11,  1.05s/it, lr: 1.0e-04 loss: 7.242e-01]
latex_v1:  31%|###       | 927/3000 [21:38<36:11,  1.05s/it, lr: 1.0e-04 loss: 7.242e-01]
latex_v1:  31%|###       | 927/3000 [21:39<36:11,  1.05s/it, lr: 1.0e-04 loss: 3.980e-01]
latex_v1:  31%|###       | 927/3000 [21:39<36:11,  1.05s/it, lr: 1.0e-04 loss: 3.980e-01]
latex_v1:  31%|###       | 928/3000 [21:39<33:12,  1.04it/s, lr: 1.0e-04 loss: 3.980e-01]
latex_v1:  31%|###       | 928/3000 [21:39<33:12,  1.04it/s, lr: 1.0e-04 loss: 3.980e-01]
latex_v1:  31%|###       | 928/3000 [21:41<33:12,  1.04it/s, lr: 1.0e-04 loss: 5.035e-01]
latex_v1:  31%|###       | 928/3000 [21:41<33:12,  1.04it/s, lr: 1.0e-04 loss: 5.035e-01]
latex_v1:  31%|###       | 929/3000 [21:41<39:18,  1.14s/it, lr: 1.0e-04 loss: 5.035e-01]
latex_v1:  31%|###       | 929/3000 [21:41<39:18,  1.14s/it, lr: 1.0e-04 loss: 5.035e-01]
latex_v1:  31%|###       | 929/3000 [21:42<39:18,  1.14s/it, lr: 1.0e-04 loss: 4.010e-01]
latex_v1:  31%|###       | 929/3000 [21:42<39:18,  1.14s/it, lr: 1.0e-04 loss: 4.010e-01]
latex_v1:  31%|###1      | 930/3000 [21:43<39:17,  1.14s/it, lr: 1.0e-04 loss: 4.112e-01]
latex_v1:  31%|###1      | 930/3000 [21:43<39:17,  1.14s/it, lr: 1.0e-04 loss: 4.112e-01]
latex_v1:  31%|###1      | 931/3000 [21:43<27:16,  1.26it/s, lr: 1.0e-04 loss: 4.112e-01]
latex_v1:  31%|###1      | 931/3000 [21:43<27:16,  1.26it/s, lr: 1.0e-04 loss: 4.112e-01]
latex_v1:  31%|###1      | 931/3000 [21:46<27:16,  1.26it/s, lr: 1.0e-04 loss: 2.185e-01]
latex_v1:  31%|###1      | 931/3000 [21:46<27:16,  1.26it/s, lr: 1.0e-04 loss: 2.185e-01]
latex_v1:  31%|###1      | 932/3000 [21:46<43:35,  1.26s/it, lr: 1.0e-04 loss: 2.185e-01]
latex_v1:  31%|###1      | 932/3000 [21:46<43:35,  1.26s/it, lr: 1.0e-04 loss: 2.185e-01]
latex_v1:  31%|###1      | 932/3000 [21:48<43:35,  1.26s/it, lr: 1.0e-04 loss: 2.897e-01]
latex_v1:  31%|###1      | 932/3000 [21:48<43:35,  1.26s/it, lr: 1.0e-04 loss: 2.897e-01]
latex_v1:  31%|###1      | 933/3000 [21:49<57:59,  1.68s/it, lr: 1.0e-04 loss: 2.897e-01]
latex_v1:  31%|###1      | 933/3000 [21:49<57:59,  1.68s/it, lr: 1.0e-04 loss: 2.897e-01]
latex_v1:  31%|###1      | 933/3000 [21:50<57:59,  1.68s/it, lr: 1.0e-04 loss: 1.482e-01]
latex_v1:  31%|###1      | 933/3000 [21:50<57:59,  1.68s/it, lr: 1.0e-04 loss: 1.482e-01]
latex_v1:  31%|###1      | 934/3000 [21:50<52:08,  1.51s/it, lr: 1.0e-04 loss: 1.482e-01]
latex_v1:  31%|###1      | 934/3000 [21:50<52:08,  1.51s/it, lr: 1.0e-04 loss: 1.482e-01]
latex_v1:  31%|###1      | 934/3000 [21:51<52:08,  1.51s/it, lr: 1.0e-04 loss: 6.333e-01]
latex_v1:  31%|###1      | 934/3000 [21:51<52:08,  1.51s/it, lr: 1.0e-04 loss: 6.333e-01]
latex_v1:  31%|###1      | 935/3000 [21:51<52:34,  1.53s/it, lr: 1.0e-04 loss: 6.333e-01]
latex_v1:  31%|###1      | 935/3000 [21:51<52:34,  1.53s/it, lr: 1.0e-04 loss: 6.333e-01]
latex_v1:  31%|###1      | 935/3000 [21:52<52:34,  1.53s/it, lr: 1.0e-04 loss: 6.997e-01]
latex_v1:  31%|###1      | 935/3000 [21:52<52:34,  1.53s/it, lr: 1.0e-04 loss: 6.997e-01]
latex_v1:  31%|###1      | 936/3000 [21:52<44:54,  1.31s/it, lr: 1.0e-04 loss: 6.997e-01]
latex_v1:  31%|###1      | 936/3000 [21:52<44:54,  1.31s/it, lr: 1.0e-04 loss: 6.997e-01]
latex_v1:  31%|###1      | 936/3000 [21:53<44:54,  1.31s/it, lr: 1.0e-04 loss: 4.313e-01]
latex_v1:  31%|###1      | 936/3000 [21:53<44:54,  1.31s/it, lr: 1.0e-04 loss: 4.313e-01]
latex_v1:  31%|###1      | 937/3000 [21:53<47:37,  1.39s/it, lr: 1.0e-04 loss: 4.313e-01]
latex_v1:  31%|###1      | 937/3000 [21:53<47:37,  1.39s/it, lr: 1.0e-04 loss: 4.313e-01]
latex_v1:  31%|###1      | 937/3000 [21:54<47:37,  1.39s/it, lr: 1.0e-04 loss: 3.294e-01]
latex_v1:  31%|###1      | 937/3000 [21:54<47:37,  1.39s/it, lr: 1.0e-04 loss: 3.294e-01]
latex_v1:  31%|###1      | 938/3000 [21:54<41:24,  1.21s/it, lr: 1.0e-04 loss: 3.294e-01]
latex_v1:  31%|###1      | 938/3000 [21:54<41:24,  1.21s/it, lr: 1.0e-04 loss: 3.294e-01]
latex_v1:  31%|###1      | 938/3000 [21:56<41:24,  1.21s/it, lr: 1.0e-04 loss: 1.345e-01]
latex_v1:  31%|###1      | 938/3000 [21:56<41:24,  1.21s/it, lr: 1.0e-04 loss: 1.345e-01]
latex_v1:  31%|###1      | 939/3000 [21:56<45:13,  1.32s/it, lr: 1.0e-04 loss: 1.345e-01]
latex_v1:  31%|###1      | 939/3000 [21:56<45:13,  1.32s/it, lr: 1.0e-04 loss: 1.345e-01]
latex_v1:  31%|###1      | 939/3000 [21:58<45:13,  1.32s/it, lr: 1.0e-04 loss: 2.784e-01]
latex_v1:  31%|###1      | 939/3000 [21:58<45:13,  1.32s/it, lr: 1.0e-04 loss: 2.784e-01]
latex_v1:  31%|###1      | 940/3000 [21:59<45:11,  1.32s/it, lr: 1.0e-04 loss: 7.479e-01]
latex_v1:  31%|###1      | 940/3000 [21:59<45:11,  1.32s/it, lr: 1.0e-04 loss: 7.479e-01]
latex_v1:  31%|###1      | 941/3000 [21:59<32:51,  1.04it/s, lr: 1.0e-04 loss: 7.479e-01]
latex_v1:  31%|###1      | 941/3000 [21:59<32:51,  1.04it/s, lr: 1.0e-04 loss: 7.479e-01]
latex_v1:  31%|###1      | 941/3000 [22:00<32:51,  1.04it/s, lr: 1.0e-04 loss: 5.097e-01]
latex_v1:  31%|###1      | 941/3000 [22:00<32:51,  1.04it/s, lr: 1.0e-04 loss: 5.097e-01]
latex_v1:  31%|###1      | 942/3000 [22:00<37:51,  1.10s/it, lr: 1.0e-04 loss: 5.097e-01]
latex_v1:  31%|###1      | 942/3000 [22:00<37:51,  1.10s/it, lr: 1.0e-04 loss: 5.097e-01]
latex_v1:  31%|###1      | 942/3000 [22:02<37:51,  1.10s/it, lr: 1.0e-04 loss: 3.338e-01]
latex_v1:  31%|###1      | 942/3000 [22:02<37:51,  1.10s/it, lr: 1.0e-04 loss: 3.338e-01]
latex_v1:  31%|###1      | 943/3000 [22:02<41:44,  1.22s/it, lr: 1.0e-04 loss: 3.338e-01]
latex_v1:  31%|###1      | 943/3000 [22:02<41:44,  1.22s/it, lr: 1.0e-04 loss: 3.338e-01]
latex_v1:  31%|###1      | 943/3000 [22:04<41:44,  1.22s/it, lr: 1.0e-04 loss: 2.043e-01]
latex_v1:  31%|###1      | 943/3000 [22:04<41:44,  1.22s/it, lr: 1.0e-04 loss: 2.043e-01]
latex_v1:  31%|###1      | 944/3000 [22:04<47:41,  1.39s/it, lr: 1.0e-04 loss: 2.043e-01]
latex_v1:  31%|###1      | 944/3000 [22:04<47:41,  1.39s/it, lr: 1.0e-04 loss: 2.043e-01]
latex_v1:  31%|###1      | 944/3000 [22:05<47:41,  1.39s/it, lr: 1.0e-04 loss: 1.640e-01]
latex_v1:  31%|###1      | 944/3000 [22:05<47:41,  1.39s/it, lr: 1.0e-04 loss: 1.640e-01]
latex_v1:  32%|###1      | 945/3000 [22:05<49:12,  1.44s/it, lr: 1.0e-04 loss: 1.640e-01]
latex_v1:  32%|###1      | 945/3000 [22:05<49:12,  1.44s/it, lr: 1.0e-04 loss: 1.640e-01]
latex_v1:  32%|###1      | 945/3000 [22:07<49:12,  1.44s/it, lr: 1.0e-04 loss: 3.490e-01]
latex_v1:  32%|###1      | 945/3000 [22:07<49:12,  1.44s/it, lr: 1.0e-04 loss: 3.490e-01]
latex_v1:  32%|###1      | 946/3000 [22:07<53:41,  1.57s/it, lr: 1.0e-04 loss: 3.490e-01]
latex_v1:  32%|###1      | 946/3000 [22:07<53:41,  1.57s/it, lr: 1.0e-04 loss: 3.490e-01]
latex_v1:  32%|###1      | 946/3000 [22:09<53:41,  1.57s/it, lr: 1.0e-04 loss: 5.322e-01]
latex_v1:  32%|###1      | 946/3000 [22:09<53:41,  1.57s/it, lr: 1.0e-04 loss: 5.322e-01]
latex_v1:  32%|###1      | 947/3000 [22:09<55:03,  1.61s/it, lr: 1.0e-04 loss: 5.322e-01]
latex_v1:  32%|###1      | 947/3000 [22:09<55:03,  1.61s/it, lr: 1.0e-04 loss: 5.322e-01]
latex_v1:  32%|###1      | 947/3000 [22:10<55:03,  1.61s/it, lr: 1.0e-04 loss: 1.085e-01]
latex_v1:  32%|###1      | 947/3000 [22:10<55:03,  1.61s/it, lr: 1.0e-04 loss: 1.085e-01]
latex_v1:  32%|###1      | 948/3000 [22:10<52:17,  1.53s/it, lr: 1.0e-04 loss: 1.085e-01]
latex_v1:  32%|###1      | 948/3000 [22:10<52:17,  1.53s/it, lr: 1.0e-04 loss: 1.085e-01]
latex_v1:  32%|###1      | 948/3000 [22:12<52:17,  1.53s/it, lr: 1.0e-04 loss: 9.993e-02]
latex_v1:  32%|###1      | 948/3000 [22:12<52:17,  1.53s/it, lr: 1.0e-04 loss: 9.993e-02]
latex_v1:  32%|###1      | 949/3000 [22:12<52:34,  1.54s/it, lr: 1.0e-04 loss: 9.993e-02]
latex_v1:  32%|###1      | 949/3000 [22:12<52:34,  1.54s/it, lr: 1.0e-04 loss: 9.993e-02]
latex_v1:  32%|###1      | 949/3000 [22:13<52:34,  1.54s/it, lr: 1.0e-04 loss: 1.858e-01]
latex_v1:  32%|###1      | 949/3000 [22:13<52:34,  1.54s/it, lr: 1.0e-04 loss: 1.858e-01]
latex_v1:  32%|###1      | 950/3000 [22:14<52:33,  1.54s/it, lr: 1.0e-04 loss: 2.655e-01]
latex_v1:  32%|###1      | 950/3000 [22:14<52:33,  1.54s/it, lr: 1.0e-04 loss: 2.655e-01]
latex_v1:  32%|###1      | 951/3000 [22:14<34:26,  1.01s/it, lr: 1.0e-04 loss: 2.655e-01]
latex_v1:  32%|###1      | 951/3000 [22:14<34:26,  1.01s/it, lr: 1.0e-04 loss: 2.655e-01]
latex_v1:  32%|###1      | 951/3000 [22:15<34:26,  1.01s/it, lr: 1.0e-04 loss: 2.722e-01]
latex_v1:  32%|###1      | 951/3000 [22:15<34:26,  1.01s/it, lr: 1.0e-04 loss: 2.722e-01]
latex_v1:  32%|###1      | 952/3000 [22:15<32:21,  1.05it/s, lr: 1.0e-04 loss: 2.722e-01]
latex_v1:  32%|###1      | 952/3000 [22:15<32:21,  1.05it/s, lr: 1.0e-04 loss: 2.722e-01]
latex_v1:  32%|###1      | 952/3000 [22:16<32:21,  1.05it/s, lr: 1.0e-04 loss: 3.848e-01]
latex_v1:  32%|###1      | 952/3000 [22:16<32:21,  1.05it/s, lr: 1.0e-04 loss: 3.848e-01]
latex_v1:  32%|###1      | 953/3000 [22:16<37:36,  1.10s/it, lr: 1.0e-04 loss: 3.848e-01]
latex_v1:  32%|###1      | 953/3000 [22:16<37:36,  1.10s/it, lr: 1.0e-04 loss: 3.848e-01]
latex_v1:  32%|###1      | 953/3000 [22:18<37:36,  1.10s/it, lr: 1.0e-04 loss: 3.121e-01]
latex_v1:  32%|###1      | 953/3000 [22:18<37:36,  1.10s/it, lr: 1.0e-04 loss: 3.121e-01]
latex_v1:  32%|###1      | 954/3000 [22:18<39:54,  1.17s/it, lr: 1.0e-04 loss: 3.121e-01]
latex_v1:  32%|###1      | 954/3000 [22:18<39:54,  1.17s/it, lr: 1.0e-04 loss: 3.121e-01]
latex_v1:  32%|###1      | 954/3000 [22:19<39:54,  1.17s/it, lr: 1.0e-04 loss: 4.975e-01]
latex_v1:  32%|###1      | 954/3000 [22:19<39:54,  1.17s/it, lr: 1.0e-04 loss: 4.975e-01]
latex_v1:  32%|###1      | 955/3000 [22:19<42:13,  1.24s/it, lr: 1.0e-04 loss: 4.975e-01]
latex_v1:  32%|###1      | 955/3000 [22:19<42:13,  1.24s/it, lr: 1.0e-04 loss: 4.975e-01]
latex_v1:  32%|###1      | 955/3000 [22:21<42:13,  1.24s/it, lr: 1.0e-04 loss: 4.645e-01]
latex_v1:  32%|###1      | 955/3000 [22:21<42:13,  1.24s/it, lr: 1.0e-04 loss: 4.645e-01]
latex_v1:  32%|###1      | 956/3000 [22:21<48:44,  1.43s/it, lr: 1.0e-04 loss: 4.645e-01]
latex_v1:  32%|###1      | 956/3000 [22:21<48:44,  1.43s/it, lr: 1.0e-04 loss: 4.645e-01]
latex_v1:  32%|###1      | 956/3000 [22:22<48:44,  1.43s/it, lr: 1.0e-04 loss: 7.461e-01]
latex_v1:  32%|###1      | 956/3000 [22:22<48:44,  1.43s/it, lr: 1.0e-04 loss: 7.461e-01]
latex_v1:  32%|###1      | 957/3000 [22:22<44:04,  1.29s/it, lr: 1.0e-04 loss: 7.461e-01]
latex_v1:  32%|###1      | 957/3000 [22:22<44:04,  1.29s/it, lr: 1.0e-04 loss: 7.461e-01]
latex_v1:  32%|###1      | 957/3000 [22:23<44:04,  1.29s/it, lr: 1.0e-04 loss: 5.810e-01]
latex_v1:  32%|###1      | 957/3000 [22:23<44:04,  1.29s/it, lr: 1.0e-04 loss: 5.810e-01]
latex_v1:  32%|###1      | 958/3000 [22:23<44:23,  1.30s/it, lr: 1.0e-04 loss: 5.810e-01]
latex_v1:  32%|###1      | 958/3000 [22:23<44:23,  1.30s/it, lr: 1.0e-04 loss: 5.810e-01]
latex_v1:  32%|###1      | 958/3000 [22:26<44:23,  1.30s/it, lr: 1.0e-04 loss: 3.903e-01]
latex_v1:  32%|###1      | 958/3000 [22:26<44:23,  1.30s/it, lr: 1.0e-04 loss: 3.903e-01]
latex_v1:  32%|###1      | 959/3000 [22:26<57:43,  1.70s/it, lr: 1.0e-04 loss: 3.903e-01]
latex_v1:  32%|###1      | 959/3000 [22:26<57:43,  1.70s/it, lr: 1.0e-04 loss: 3.903e-01]
latex_v1:  32%|###1      | 959/3000 [22:29<57:43,  1.70s/it, lr: 1.0e-04 loss: 6.069e-02]
latex_v1:  32%|###1      | 959/3000 [22:29<57:43,  1.70s/it, lr: 1.0e-04 loss: 6.069e-02]
latex_v1:  32%|###2      | 960/3000 [22:30<57:41,  1.70s/it, lr: 1.0e-04 loss: 3.519e-01]
latex_v1:  32%|###2      | 960/3000 [22:30<57:41,  1.70s/it, lr: 1.0e-04 loss: 3.519e-01]
latex_v1:  32%|###2      | 961/3000 [22:30<43:11,  1.27s/it, lr: 1.0e-04 loss: 3.519e-01]
latex_v1:  32%|###2      | 961/3000 [22:30<43:11,  1.27s/it, lr: 1.0e-04 loss: 3.519e-01]
latex_v1:  32%|###2      | 961/3000 [22:33<43:11,  1.27s/it, lr: 1.0e-04 loss: 1.049e-01]
latex_v1:  32%|###2      | 961/3000 [22:33<43:11,  1.27s/it, lr: 1.0e-04 loss: 1.049e-01]
latex_v1:  32%|###2      | 962/3000 [22:33<56:39,  1.67s/it, lr: 1.0e-04 loss: 1.049e-01]
latex_v1:  32%|###2      | 962/3000 [22:33<56:39,  1.67s/it, lr: 1.0e-04 loss: 1.049e-01]
latex_v1:  32%|###2      | 962/3000 [22:34<56:39,  1.67s/it, lr: 1.0e-04 loss: 1.897e-01]
latex_v1:  32%|###2      | 962/3000 [22:34<56:39,  1.67s/it, lr: 1.0e-04 loss: 1.897e-01]
latex_v1:  32%|###2      | 963/3000 [22:34<48:15,  1.42s/it, lr: 1.0e-04 loss: 1.897e-01]
latex_v1:  32%|###2      | 963/3000 [22:34<48:15,  1.42s/it, lr: 1.0e-04 loss: 1.897e-01]
latex_v1:  32%|###2      | 963/3000 [22:35<48:15,  1.42s/it, lr: 1.0e-04 loss: 1.055e-01]
latex_v1:  32%|###2      | 963/3000 [22:35<48:15,  1.42s/it, lr: 1.0e-04 loss: 1.055e-01]
latex_v1:  32%|###2      | 964/3000 [22:35<42:11,  1.24s/it, lr: 1.0e-04 loss: 1.055e-01]
latex_v1:  32%|###2      | 964/3000 [22:35<42:11,  1.24s/it, lr: 1.0e-04 loss: 1.055e-01]
latex_v1:  32%|###2      | 964/3000 [22:35<42:11,  1.24s/it, lr: 1.0e-04 loss: 9.262e-02]
latex_v1:  32%|###2      | 964/3000 [22:35<42:11,  1.24s/it, lr: 1.0e-04 loss: 9.262e-02]
latex_v1:  32%|###2      | 965/3000 [22:35<37:27,  1.10s/it, lr: 1.0e-04 loss: 9.262e-02]
latex_v1:  32%|###2      | 965/3000 [22:35<37:27,  1.10s/it, lr: 1.0e-04 loss: 9.262e-02]
latex_v1:  32%|###2      | 965/3000 [22:36<37:27,  1.10s/it, lr: 1.0e-04 loss: 6.078e-01]
latex_v1:  32%|###2      | 965/3000 [22:36<37:27,  1.10s/it, lr: 1.0e-04 loss: 6.078e-01]
latex_v1:  32%|###2      | 966/3000 [22:36<34:01,  1.00s/it, lr: 1.0e-04 loss: 6.078e-01]
latex_v1:  32%|###2      | 966/3000 [22:36<34:01,  1.00s/it, lr: 1.0e-04 loss: 6.078e-01]
latex_v1:  32%|###2      | 966/3000 [22:37<34:01,  1.00s/it, lr: 1.0e-04 loss: 3.974e-01]
latex_v1:  32%|###2      | 966/3000 [22:37<34:01,  1.00s/it, lr: 1.0e-04 loss: 3.974e-01]
latex_v1:  32%|###2      | 967/3000 [22:37<33:39,  1.01it/s, lr: 1.0e-04 loss: 3.974e-01]
latex_v1:  32%|###2      | 967/3000 [22:37<33:39,  1.01it/s, lr: 1.0e-04 loss: 3.974e-01]
latex_v1:  32%|###2      | 967/3000 [22:38<33:39,  1.01it/s, lr: 1.0e-04 loss: 5.576e-01]
latex_v1:  32%|###2      | 967/3000 [22:38<33:39,  1.01it/s, lr: 1.0e-04 loss: 5.576e-01]
latex_v1:  32%|###2      | 968/3000 [22:38<31:12,  1.09it/s, lr: 1.0e-04 loss: 5.576e-01]
latex_v1:  32%|###2      | 968/3000 [22:38<31:12,  1.09it/s, lr: 1.0e-04 loss: 5.576e-01]
latex_v1:  32%|###2      | 968/3000 [22:39<31:12,  1.09it/s, lr: 1.0e-04 loss: 5.518e-01]
latex_v1:  32%|###2      | 968/3000 [22:39<31:12,  1.09it/s, lr: 1.0e-04 loss: 5.518e-01]
latex_v1:  32%|###2      | 969/3000 [22:39<33:35,  1.01it/s, lr: 1.0e-04 loss: 5.518e-01]
latex_v1:  32%|###2      | 969/3000 [22:39<33:35,  1.01it/s, lr: 1.0e-04 loss: 5.518e-01]
latex_v1:  32%|###2      | 969/3000 [22:40<33:35,  1.01it/s, lr: 1.0e-04 loss: 5.432e-01]
latex_v1:  32%|###2      | 969/3000 [22:40<33:35,  1.01it/s, lr: 1.0e-04 loss: 5.432e-01]
latex_v1:  32%|###2      | 970/3000 [22:41<33:34,  1.01it/s, lr: 1.0e-04 loss: 1.762e-01]
latex_v1:  32%|###2      | 970/3000 [22:41<33:34,  1.01it/s, lr: 1.0e-04 loss: 1.762e-01]
latex_v1:  32%|###2      | 971/3000 [22:41<23:58,  1.41it/s, lr: 1.0e-04 loss: 1.762e-01]
latex_v1:  32%|###2      | 971/3000 [22:41<23:58,  1.41it/s, lr: 1.0e-04 loss: 1.762e-01]
latex_v1:  32%|###2      | 971/3000 [22:43<23:58,  1.41it/s, lr: 1.0e-04 loss: 1.654e-01]
latex_v1:  32%|###2      | 971/3000 [22:43<23:58,  1.41it/s, lr: 1.0e-04 loss: 1.654e-01]
latex_v1:  32%|###2      | 972/3000 [22:43<30:00,  1.13it/s, lr: 1.0e-04 loss: 1.654e-01]
latex_v1:  32%|###2      | 972/3000 [22:43<30:00,  1.13it/s, lr: 1.0e-04 loss: 1.654e-01]
latex_v1:  32%|###2      | 972/3000 [22:45<30:00,  1.13it/s, lr: 1.0e-04 loss: 1.324e-01]
latex_v1:  32%|###2      | 972/3000 [22:45<30:00,  1.13it/s, lr: 1.0e-04 loss: 1.324e-01]
latex_v1:  32%|###2      | 973/3000 [22:45<39:30,  1.17s/it, lr: 1.0e-04 loss: 1.324e-01]
latex_v1:  32%|###2      | 973/3000 [22:45<39:30,  1.17s/it, lr: 1.0e-04 loss: 1.324e-01]
latex_v1:  32%|###2      | 973/3000 [22:45<39:30,  1.17s/it, lr: 1.0e-04 loss: 5.509e-01]
latex_v1:  32%|###2      | 973/3000 [22:45<39:30,  1.17s/it, lr: 1.0e-04 loss: 5.509e-01]
latex_v1:  32%|###2      | 974/3000 [22:45<35:48,  1.06s/it, lr: 1.0e-04 loss: 5.509e-01]
latex_v1:  32%|###2      | 974/3000 [22:45<35:48,  1.06s/it, lr: 1.0e-04 loss: 5.509e-01]
latex_v1:  32%|###2      | 974/3000 [22:46<35:48,  1.06s/it, lr: 1.0e-04 loss: 7.909e-02]
latex_v1:  32%|###2      | 974/3000 [22:46<35:48,  1.06s/it, lr: 1.0e-04 loss: 7.909e-02]
latex_v1:  32%|###2      | 975/3000 [22:46<32:50,  1.03it/s, lr: 1.0e-04 loss: 7.909e-02]
latex_v1:  32%|###2      | 975/3000 [22:46<32:50,  1.03it/s, lr: 1.0e-04 loss: 7.909e-02]
latex_v1:  32%|###2      | 975/3000 [22:47<32:50,  1.03it/s, lr: 1.0e-04 loss: 1.447e-01]
latex_v1:  32%|###2      | 975/3000 [22:47<32:50,  1.03it/s, lr: 1.0e-04 loss: 1.447e-01]
latex_v1:  33%|###2      | 976/3000 [22:47<30:41,  1.10it/s, lr: 1.0e-04 loss: 1.447e-01]
latex_v1:  33%|###2      | 976/3000 [22:47<30:41,  1.10it/s, lr: 1.0e-04 loss: 1.447e-01]
latex_v1:  33%|###2      | 976/3000 [22:48<30:41,  1.10it/s, lr: 1.0e-04 loss: 3.228e-01]
latex_v1:  33%|###2      | 976/3000 [22:48<30:41,  1.10it/s, lr: 1.0e-04 loss: 3.228e-01]
latex_v1:  33%|###2      | 977/3000 [22:48<36:40,  1.09s/it, lr: 1.0e-04 loss: 3.228e-01]
latex_v1:  33%|###2      | 977/3000 [22:48<36:40,  1.09s/it, lr: 1.0e-04 loss: 3.228e-01]
latex_v1:  33%|###2      | 977/3000 [22:49<36:40,  1.09s/it, lr: 1.0e-04 loss: 6.424e-01]
latex_v1:  33%|###2      | 977/3000 [22:49<36:40,  1.09s/it, lr: 1.0e-04 loss: 6.424e-01]
latex_v1:  33%|###2      | 978/3000 [22:49<33:20,  1.01it/s, lr: 1.0e-04 loss: 6.424e-01]
latex_v1:  33%|###2      | 978/3000 [22:49<33:20,  1.01it/s, lr: 1.0e-04 loss: 6.424e-01]
latex_v1:  33%|###2      | 978/3000 [22:51<33:20,  1.01it/s, lr: 1.0e-04 loss: 5.401e-01]
latex_v1:  33%|###2      | 978/3000 [22:51<33:20,  1.01it/s, lr: 1.0e-04 loss: 5.401e-01]
latex_v1:  33%|###2      | 979/3000 [22:51<38:31,  1.14s/it, lr: 1.0e-04 loss: 5.401e-01]
latex_v1:  33%|###2      | 979/3000 [22:51<38:31,  1.14s/it, lr: 1.0e-04 loss: 5.401e-01]
latex_v1:  33%|###2      | 979/3000 [22:52<38:31,  1.14s/it, lr: 1.0e-04 loss: 4.459e-01]
latex_v1:  33%|###2      | 979/3000 [22:52<38:31,  1.14s/it, lr: 1.0e-04 loss: 4.459e-01]
latex_v1:  33%|###2      | 980/3000 [22:53<38:30,  1.14s/it, lr: 1.0e-04 loss: 5.630e-01]
latex_v1:  33%|###2      | 980/3000 [22:53<38:30,  1.14s/it, lr: 1.0e-04 loss: 5.630e-01]
latex_v1:  33%|###2      | 981/3000 [22:53<31:44,  1.06it/s, lr: 1.0e-04 loss: 5.630e-01]
latex_v1:  33%|###2      | 981/3000 [22:53<31:44,  1.06it/s, lr: 1.0e-04 loss: 5.630e-01]
latex_v1:  33%|###2      | 981/3000 [22:54<31:44,  1.06it/s, lr: 1.0e-04 loss: 8.234e-02]
latex_v1:  33%|###2      | 981/3000 [22:54<31:44,  1.06it/s, lr: 1.0e-04 loss: 8.234e-02]
latex_v1:  33%|###2      | 982/3000 [22:54<35:53,  1.07s/it, lr: 1.0e-04 loss: 8.234e-02]
latex_v1:  33%|###2      | 982/3000 [22:54<35:53,  1.07s/it, lr: 1.0e-04 loss: 8.234e-02]
latex_v1:  33%|###2      | 982/3000 [22:56<35:53,  1.07s/it, lr: 1.0e-04 loss: 5.695e-01]
latex_v1:  33%|###2      | 982/3000 [22:56<35:53,  1.07s/it, lr: 1.0e-04 loss: 5.695e-01]
latex_v1:  33%|###2      | 983/3000 [22:56<39:55,  1.19s/it, lr: 1.0e-04 loss: 5.695e-01]
latex_v1:  33%|###2      | 983/3000 [22:56<39:55,  1.19s/it, lr: 1.0e-04 loss: 5.695e-01]
latex_v1:  33%|###2      | 983/3000 [22:57<39:55,  1.19s/it, lr: 1.0e-04 loss: 7.267e-01]
latex_v1:  33%|###2      | 983/3000 [22:57<39:55,  1.19s/it, lr: 1.0e-04 loss: 7.267e-01]
latex_v1:  33%|###2      | 984/3000 [22:57<41:02,  1.22s/it, lr: 1.0e-04 loss: 7.267e-01]
latex_v1:  33%|###2      | 984/3000 [22:57<41:02,  1.22s/it, lr: 1.0e-04 loss: 7.267e-01]
latex_v1:  33%|###2      | 984/3000 [22:59<41:02,  1.22s/it, lr: 1.0e-04 loss: 2.957e-01]
latex_v1:  33%|###2      | 984/3000 [22:59<41:02,  1.22s/it, lr: 1.0e-04 loss: 2.957e-01]
latex_v1:  33%|###2      | 985/3000 [22:59<49:56,  1.49s/it, lr: 1.0e-04 loss: 2.957e-01]
latex_v1:  33%|###2      | 985/3000 [22:59<49:56,  1.49s/it, lr: 1.0e-04 loss: 2.957e-01]
latex_v1:  33%|###2      | 985/3000 [23:02<49:56,  1.49s/it, lr: 1.0e-04 loss: 8.314e-02]
latex_v1:  33%|###2      | 985/3000 [23:02<49:56,  1.49s/it, lr: 1.0e-04 loss: 8.314e-02]
latex_v1:  33%|###2      | 986/3000 [23:02<1:02:46,  1.87s/it, lr: 1.0e-04 loss: 8.314e-02]
latex_v1:  33%|###2      | 986/3000 [23:02<1:02:46,  1.87s/it, lr: 1.0e-04 loss: 8.314e-02]
latex_v1:  33%|###2      | 986/3000 [23:03<1:02:46,  1.87s/it, lr: 1.0e-04 loss: 6.642e-01]
latex_v1:  33%|###2      | 986/3000 [23:03<1:02:46,  1.87s/it, lr: 1.0e-04 loss: 6.642e-01]
latex_v1:  33%|###2      | 987/3000 [23:03<51:49,  1.54s/it, lr: 1.0e-04 loss: 6.642e-01]  
latex_v1:  33%|###2      | 987/3000 [23:03<51:49,  1.54s/it, lr: 1.0e-04 loss: 6.642e-01]  
latex_v1:  33%|###2      | 987/3000 [23:06<51:49,  1.54s/it, lr: 1.0e-04 loss: 1.572e-01]
latex_v1:  33%|###2      | 987/3000 [23:06<51:49,  1.54s/it, lr: 1.0e-04 loss: 1.572e-01]
latex_v1:  33%|###2      | 988/3000 [23:06<1:04:04,  1.91s/it, lr: 1.0e-04 loss: 1.572e-01]
latex_v1:  33%|###2      | 988/3000 [23:06<1:04:04,  1.91s/it, lr: 1.0e-04 loss: 1.572e-01]
latex_v1:  33%|###2      | 988/3000 [23:07<1:04:04,  1.91s/it, lr: 1.0e-04 loss: 1.004e-01]
latex_v1:  33%|###2      | 988/3000 [23:07<1:04:04,  1.91s/it, lr: 1.0e-04 loss: 1.004e-01]
latex_v1:  33%|###2      | 989/3000 [23:07<59:10,  1.77s/it, lr: 1.0e-04 loss: 1.004e-01]  
latex_v1:  33%|###2      | 989/3000 [23:07<59:10,  1.77s/it, lr: 1.0e-04 loss: 1.004e-01]  
latex_v1:  33%|###2      | 989/3000 [23:09<59:10,  1.77s/it, lr: 1.0e-04 loss: 2.311e-01]
latex_v1:  33%|###2      | 989/3000 [23:09<59:10,  1.77s/it, lr: 1.0e-04 loss: 2.311e-01]
latex_v1:  33%|###3      | 990/3000 [23:09<59:08,  1.77s/it, lr: 1.0e-04 loss: 5.794e-01]
latex_v1:  33%|###3      | 990/3000 [23:09<59:08,  1.77s/it, lr: 1.0e-04 loss: 5.794e-01]
latex_v1:  33%|###3      | 991/3000 [23:09<37:49,  1.13s/it, lr: 1.0e-04 loss: 5.794e-01]
latex_v1:  33%|###3      | 991/3000 [23:09<37:49,  1.13s/it, lr: 1.0e-04 loss: 5.794e-01]
latex_v1:  33%|###3      | 991/3000 [23:10<37:49,  1.13s/it, lr: 1.0e-04 loss: 3.255e-01]
latex_v1:  33%|###3      | 991/3000 [23:10<37:49,  1.13s/it, lr: 1.0e-04 loss: 3.255e-01]
latex_v1:  33%|###3      | 992/3000 [23:10<34:36,  1.03s/it, lr: 1.0e-04 loss: 3.255e-01]
latex_v1:  33%|###3      | 992/3000 [23:10<34:36,  1.03s/it, lr: 1.0e-04 loss: 3.255e-01]
latex_v1:  33%|###3      | 992/3000 [23:11<34:36,  1.03s/it, lr: 1.0e-04 loss: 4.098e-01]
latex_v1:  33%|###3      | 992/3000 [23:11<34:36,  1.03s/it, lr: 1.0e-04 loss: 4.098e-01]
latex_v1:  33%|###3      | 993/3000 [23:11<35:47,  1.07s/it, lr: 1.0e-04 loss: 4.098e-01]
latex_v1:  33%|###3      | 993/3000 [23:11<35:47,  1.07s/it, lr: 1.0e-04 loss: 4.098e-01]
latex_v1:  33%|###3      | 993/3000 [23:14<35:47,  1.07s/it, lr: 1.0e-04 loss: 4.911e-02]
latex_v1:  33%|###3      | 993/3000 [23:14<35:47,  1.07s/it, lr: 1.0e-04 loss: 4.911e-02]
latex_v1:  33%|###3      | 994/3000 [23:14<51:30,  1.54s/it, lr: 1.0e-04 loss: 4.911e-02]
latex_v1:  33%|###3      | 994/3000 [23:14<51:30,  1.54s/it, lr: 1.0e-04 loss: 4.911e-02]
latex_v1:  33%|###3      | 994/3000 [23:15<51:30,  1.54s/it, lr: 1.0e-04 loss: 3.153e-01]
latex_v1:  33%|###3      | 994/3000 [23:15<51:30,  1.54s/it, lr: 1.0e-04 loss: 3.153e-01]
latex_v1:  33%|###3      | 995/3000 [23:15<49:39,  1.49s/it, lr: 1.0e-04 loss: 3.153e-01]
latex_v1:  33%|###3      | 995/3000 [23:15<49:39,  1.49s/it, lr: 1.0e-04 loss: 3.153e-01]
latex_v1:  33%|###3      | 995/3000 [23:17<49:39,  1.49s/it, lr: 1.0e-04 loss: 7.300e-01]
latex_v1:  33%|###3      | 995/3000 [23:17<49:39,  1.49s/it, lr: 1.0e-04 loss: 7.300e-01]
latex_v1:  33%|###3      | 996/3000 [23:17<46:38,  1.40s/it, lr: 1.0e-04 loss: 7.300e-01]
latex_v1:  33%|###3      | 996/3000 [23:17<46:38,  1.40s/it, lr: 1.0e-04 loss: 7.300e-01]
latex_v1:  33%|###3      | 996/3000 [23:17<46:38,  1.40s/it, lr: 1.0e-04 loss: 6.201e-02]
latex_v1:  33%|###3      | 996/3000 [23:17<46:38,  1.40s/it, lr: 1.0e-04 loss: 6.201e-02]
latex_v1:  33%|###3      | 997/3000 [23:17<40:20,  1.21s/it, lr: 1.0e-04 loss: 6.201e-02]
latex_v1:  33%|###3      | 997/3000 [23:17<40:20,  1.21s/it, lr: 1.0e-04 loss: 6.201e-02]
latex_v1:  33%|###3      | 997/3000 [23:19<40:20,  1.21s/it, lr: 1.0e-04 loss: 3.413e-01]
latex_v1:  33%|###3      | 997/3000 [23:19<40:20,  1.21s/it, lr: 1.0e-04 loss: 3.413e-01]
latex_v1:  33%|###3      | 998/3000 [23:19<41:14,  1.24s/it, lr: 1.0e-04 loss: 3.413e-01]
latex_v1:  33%|###3      | 998/3000 [23:19<41:14,  1.24s/it, lr: 1.0e-04 loss: 3.413e-01]
latex_v1:  33%|###3      | 998/3000 [23:20<41:14,  1.24s/it, lr: 1.0e-04 loss: 4.111e-01]
latex_v1:  33%|###3      | 998/3000 [23:20<41:14,  1.24s/it, lr: 1.0e-04 loss: 4.111e-01]
latex_v1:  33%|###3      | 999/3000 [23:20<44:02,  1.32s/it, lr: 1.0e-04 loss: 4.111e-01]
latex_v1:  33%|###3      | 999/3000 [23:20<44:02,  1.32s/it, lr: 1.0e-04 loss: 4.111e-01]
latex_v1:  33%|###3      | 999/3000 [23:23<44:02,  1.32s/it, lr: 1.0e-04 loss: 2.478e-02]
latex_v1:  33%|###3      | 999/3000 [23:23<44:02,  1.32s/it, lr: 1.0e-04 loss: 2.478e-02]
Saving at step 1000
Saved checkpoint to /data/app/output/latex_v1/latex_v1_000001000.safetensors
Saved optimizer to /data/app/output/latex_v1/optimizer.pt

latex_v1:  33%|###3      | 1000/3000 [23:26<44:00,  1.32s/it, lr: 1.0e-04 loss: 7.638e-01]
latex_v1:  33%|###3      | 1000/3000 [23:26<44:00,  1.32s/it, lr: 1.0e-04 loss: 7.638e-01]
latex_v1:  33%|###3      | 1001/3000 [23:26<47:06,  1.41s/it, lr: 1.0e-04 loss: 7.638e-01]
latex_v1:  33%|###3      | 1001/3000 [23:26<47:06,  1.41s/it, lr: 1.0e-04 loss: 7.638e-01]
latex_v1:  33%|###3      | 1001/3000 [23:27<47:06,  1.41s/it, lr: 1.0e-04 loss: 5.515e-01]
latex_v1:  33%|###3      | 1001/3000 [23:27<47:06,  1.41s/it, lr: 1.0e-04 loss: 5.515e-01]
latex_v1:  33%|###3      | 1002/3000 [23:27<41:30,  1.25s/it, lr: 1.0e-04 loss: 5.515e-01]
latex_v1:  33%|###3      | 1002/3000 [23:27<41:30,  1.25s/it, lr: 1.0e-04 loss: 5.515e-01]
latex_v1:  33%|###3      | 1002/3000 [23:28<41:30,  1.25s/it, lr: 1.0e-04 loss: 6.250e-01]
latex_v1:  33%|###3      | 1002/3000 [23:28<41:30,  1.25s/it, lr: 1.0e-04 loss: 6.250e-01]
latex_v1:  33%|###3      | 1003/3000 [23:28<37:03,  1.11s/it, lr: 1.0e-04 loss: 6.250e-01]
latex_v1:  33%|###3      | 1003/3000 [23:28<37:03,  1.11s/it, lr: 1.0e-04 loss: 6.250e-01]
latex_v1:  33%|###3      | 1003/3000 [23:28<37:03,  1.11s/it, lr: 1.0e-04 loss: 4.136e-01]
latex_v1:  33%|###3      | 1003/3000 [23:28<37:03,  1.11s/it, lr: 1.0e-04 loss: 4.136e-01]
latex_v1:  33%|###3      | 1004/3000 [23:28<33:51,  1.02s/it, lr: 1.0e-04 loss: 4.136e-01]
latex_v1:  33%|###3      | 1004/3000 [23:28<33:51,  1.02s/it, lr: 1.0e-04 loss: 4.136e-01]
latex_v1:  33%|###3      | 1004/3000 [23:29<33:51,  1.02s/it, lr: 1.0e-04 loss: 1.688e-01]
latex_v1:  33%|###3      | 1004/3000 [23:29<33:51,  1.02s/it, lr: 1.0e-04 loss: 1.688e-01]
latex_v1:  34%|###3      | 1005/3000 [23:29<33:58,  1.02s/it, lr: 1.0e-04 loss: 1.688e-01]
latex_v1:  34%|###3      | 1005/3000 [23:29<33:58,  1.02s/it, lr: 1.0e-04 loss: 1.688e-01]
latex_v1:  34%|###3      | 1005/3000 [23:31<33:58,  1.02s/it, lr: 1.0e-04 loss: 3.748e-01]
latex_v1:  34%|###3      | 1005/3000 [23:31<33:58,  1.02s/it, lr: 1.0e-04 loss: 3.748e-01]
latex_v1:  34%|###3      | 1006/3000 [23:31<37:57,  1.14s/it, lr: 1.0e-04 loss: 3.748e-01]
latex_v1:  34%|###3      | 1006/3000 [23:31<37:57,  1.14s/it, lr: 1.0e-04 loss: 3.748e-01]
latex_v1:  34%|###3      | 1006/3000 [23:32<37:57,  1.14s/it, lr: 1.0e-04 loss: 7.251e-01]
latex_v1:  34%|###3      | 1006/3000 [23:32<37:57,  1.14s/it, lr: 1.0e-04 loss: 7.251e-01]
latex_v1:  34%|###3      | 1007/3000 [23:32<40:30,  1.22s/it, lr: 1.0e-04 loss: 7.251e-01]
latex_v1:  34%|###3      | 1007/3000 [23:32<40:30,  1.22s/it, lr: 1.0e-04 loss: 7.251e-01]
latex_v1:  34%|###3      | 1007/3000 [23:33<40:30,  1.22s/it, lr: 1.0e-04 loss: 2.992e-01]
latex_v1:  34%|###3      | 1007/3000 [23:33<40:30,  1.22s/it, lr: 1.0e-04 loss: 2.992e-01]
latex_v1:  34%|###3      | 1008/3000 [23:33<39:50,  1.20s/it, lr: 1.0e-04 loss: 2.992e-01]
latex_v1:  34%|###3      | 1008/3000 [23:33<39:50,  1.20s/it, lr: 1.0e-04 loss: 2.992e-01]
latex_v1:  34%|###3      | 1008/3000 [23:35<39:50,  1.20s/it, lr: 1.0e-04 loss: 8.511e-02]
latex_v1:  34%|###3      | 1008/3000 [23:35<39:50,  1.20s/it, lr: 1.0e-04 loss: 8.511e-02]
latex_v1:  34%|###3      | 1009/3000 [23:35<41:17,  1.24s/it, lr: 1.0e-04 loss: 8.511e-02]
latex_v1:  34%|###3      | 1009/3000 [23:35<41:17,  1.24s/it, lr: 1.0e-04 loss: 8.511e-02]
latex_v1:  34%|###3      | 1009/3000 [23:37<41:17,  1.24s/it, lr: 1.0e-04 loss: 4.005e-01]
latex_v1:  34%|###3      | 1009/3000 [23:37<41:17,  1.24s/it, lr: 1.0e-04 loss: 4.005e-01]
latex_v1:  34%|###3      | 1010/3000 [23:38<41:15,  1.24s/it, lr: 1.0e-04 loss: 5.251e-01]
latex_v1:  34%|###3      | 1010/3000 [23:38<41:15,  1.24s/it, lr: 1.0e-04 loss: 5.251e-01]
latex_v1:  34%|###3      | 1011/3000 [23:38<32:19,  1.03it/s, lr: 1.0e-04 loss: 5.251e-01]
latex_v1:  34%|###3      | 1011/3000 [23:38<32:19,  1.03it/s, lr: 1.0e-04 loss: 5.251e-01]
latex_v1:  34%|###3      | 1011/3000 [23:39<32:19,  1.03it/s, lr: 1.0e-04 loss: 4.700e-01]
latex_v1:  34%|###3      | 1011/3000 [23:39<32:19,  1.03it/s, lr: 1.0e-04 loss: 4.700e-01]
latex_v1:  34%|###3      | 1012/3000 [23:39<30:31,  1.09it/s, lr: 1.0e-04 loss: 4.700e-01]
latex_v1:  34%|###3      | 1012/3000 [23:39<30:31,  1.09it/s, lr: 1.0e-04 loss: 4.700e-01]
latex_v1:  34%|###3      | 1012/3000 [23:40<30:31,  1.09it/s, lr: 1.0e-04 loss: 5.940e-01]
latex_v1:  34%|###3      | 1012/3000 [23:40<30:31,  1.09it/s, lr: 1.0e-04 loss: 5.940e-01]
latex_v1:  34%|###3      | 1013/3000 [23:40<37:04,  1.12s/it, lr: 1.0e-04 loss: 5.940e-01]
latex_v1:  34%|###3      | 1013/3000 [23:40<37:04,  1.12s/it, lr: 1.0e-04 loss: 5.940e-01]
latex_v1:  34%|###3      | 1013/3000 [23:41<37:04,  1.12s/it, lr: 1.0e-04 loss: 9.340e-02]
latex_v1:  34%|###3      | 1013/3000 [23:41<37:04,  1.12s/it, lr: 1.0e-04 loss: 9.340e-02]
latex_v1:  34%|###3      | 1014/3000 [23:41<33:47,  1.02s/it, lr: 1.0e-04 loss: 9.340e-02]
latex_v1:  34%|###3      | 1014/3000 [23:41<33:47,  1.02s/it, lr: 1.0e-04 loss: 9.340e-02]
latex_v1:  34%|###3      | 1014/3000 [23:43<33:47,  1.02s/it, lr: 1.0e-04 loss: 1.326e-01]
latex_v1:  34%|###3      | 1014/3000 [23:43<33:47,  1.02s/it, lr: 1.0e-04 loss: 1.326e-01]
latex_v1:  34%|###3      | 1015/3000 [23:43<39:20,  1.19s/it, lr: 1.0e-04 loss: 1.326e-01]
latex_v1:  34%|###3      | 1015/3000 [23:43<39:20,  1.19s/it, lr: 1.0e-04 loss: 1.326e-01]
latex_v1:  34%|###3      | 1015/3000 [23:43<39:20,  1.19s/it, lr: 1.0e-04 loss: 6.144e-01]
latex_v1:  34%|###3      | 1015/3000 [23:43<39:20,  1.19s/it, lr: 1.0e-04 loss: 6.144e-01]
latex_v1:  34%|###3      | 1016/3000 [23:43<34:56,  1.06s/it, lr: 1.0e-04 loss: 6.144e-01]
latex_v1:  34%|###3      | 1016/3000 [23:43<34:56,  1.06s/it, lr: 1.0e-04 loss: 6.144e-01]
latex_v1:  34%|###3      | 1016/3000 [23:44<34:56,  1.06s/it, lr: 1.0e-04 loss: 5.587e-01]
latex_v1:  34%|###3      | 1016/3000 [23:44<34:56,  1.06s/it, lr: 1.0e-04 loss: 5.587e-01]
latex_v1:  34%|###3      | 1017/3000 [23:44<32:00,  1.03it/s, lr: 1.0e-04 loss: 5.587e-01]
latex_v1:  34%|###3      | 1017/3000 [23:44<32:00,  1.03it/s, lr: 1.0e-04 loss: 5.587e-01]
latex_v1:  34%|###3      | 1017/3000 [23:45<32:00,  1.03it/s, lr: 1.0e-04 loss: 2.370e-01]
latex_v1:  34%|###3      | 1017/3000 [23:45<32:00,  1.03it/s, lr: 1.0e-04 loss: 2.370e-01]
latex_v1:  34%|###3      | 1018/3000 [23:45<29:45,  1.11it/s, lr: 1.0e-04 loss: 2.370e-01]
latex_v1:  34%|###3      | 1018/3000 [23:45<29:45,  1.11it/s, lr: 1.0e-04 loss: 2.370e-01]
latex_v1:  34%|###3      | 1018/3000 [23:46<29:45,  1.11it/s, lr: 1.0e-04 loss: 4.957e-01]
latex_v1:  34%|###3      | 1018/3000 [23:46<29:45,  1.11it/s, lr: 1.0e-04 loss: 4.957e-01]
latex_v1:  34%|###3      | 1019/3000 [23:46<34:47,  1.05s/it, lr: 1.0e-04 loss: 4.957e-01]
latex_v1:  34%|###3      | 1019/3000 [23:46<34:47,  1.05s/it, lr: 1.0e-04 loss: 4.957e-01]
latex_v1:  34%|###3      | 1019/3000 [23:48<34:47,  1.05s/it, lr: 1.0e-04 loss: 3.713e-02]
latex_v1:  34%|###3      | 1019/3000 [23:48<34:47,  1.05s/it, lr: 1.0e-04 loss: 3.713e-02]
latex_v1:  34%|###4      | 1020/3000 [23:48<34:46,  1.05s/it, lr: 1.0e-04 loss: 4.617e-01]
latex_v1:  34%|###4      | 1020/3000 [23:48<34:46,  1.05s/it, lr: 1.0e-04 loss: 4.617e-01]
latex_v1:  34%|###4      | 1021/3000 [23:48<24:33,  1.34it/s, lr: 1.0e-04 loss: 4.617e-01]
latex_v1:  34%|###4      | 1021/3000 [23:48<24:33,  1.34it/s, lr: 1.0e-04 loss: 4.617e-01]
latex_v1:  34%|###4      | 1021/3000 [23:50<24:33,  1.34it/s, lr: 1.0e-04 loss: 5.350e-01]
latex_v1:  34%|###4      | 1021/3000 [23:50<24:33,  1.34it/s, lr: 1.0e-04 loss: 5.350e-01]
latex_v1:  34%|###4      | 1022/3000 [23:50<33:35,  1.02s/it, lr: 1.0e-04 loss: 5.350e-01]
latex_v1:  34%|###4      | 1022/3000 [23:50<33:35,  1.02s/it, lr: 1.0e-04 loss: 5.350e-01]
latex_v1:  34%|###4      | 1022/3000 [23:51<33:35,  1.02s/it, lr: 1.0e-04 loss: 3.466e-01]
latex_v1:  34%|###4      | 1022/3000 [23:51<33:35,  1.02s/it, lr: 1.0e-04 loss: 3.466e-01]
latex_v1:  34%|###4      | 1023/3000 [23:51<31:44,  1.04it/s, lr: 1.0e-04 loss: 3.466e-01]
latex_v1:  34%|###4      | 1023/3000 [23:51<31:44,  1.04it/s, lr: 1.0e-04 loss: 3.466e-01]
latex_v1:  34%|###4      | 1023/3000 [23:52<31:44,  1.04it/s, lr: 1.0e-04 loss: 1.867e-01]
latex_v1:  34%|###4      | 1023/3000 [23:52<31:44,  1.04it/s, lr: 1.0e-04 loss: 1.867e-01]
latex_v1:  34%|###4      | 1024/3000 [23:52<29:46,  1.11it/s, lr: 1.0e-04 loss: 1.867e-01]
latex_v1:  34%|###4      | 1024/3000 [23:52<29:46,  1.11it/s, lr: 1.0e-04 loss: 1.867e-01]
latex_v1:  34%|###4      | 1024/3000 [23:53<29:46,  1.11it/s, lr: 1.0e-04 loss: 1.516e-01]
latex_v1:  34%|###4      | 1024/3000 [23:53<29:46,  1.11it/s, lr: 1.0e-04 loss: 1.516e-01]
latex_v1:  34%|###4      | 1025/3000 [23:53<31:07,  1.06it/s, lr: 1.0e-04 loss: 1.516e-01]
latex_v1:  34%|###4      | 1025/3000 [23:53<31:07,  1.06it/s, lr: 1.0e-04 loss: 1.516e-01]
latex_v1:  34%|###4      | 1025/3000 [23:54<31:07,  1.06it/s, lr: 1.0e-04 loss: 4.301e-01]
latex_v1:  34%|###4      | 1025/3000 [23:54<31:07,  1.06it/s, lr: 1.0e-04 loss: 4.301e-01]
latex_v1:  34%|###4      | 1026/3000 [23:54<29:16,  1.12it/s, lr: 1.0e-04 loss: 4.301e-01]
latex_v1:  34%|###4      | 1026/3000 [23:54<29:16,  1.12it/s, lr: 1.0e-04 loss: 4.301e-01]
latex_v1:  34%|###4      | 1026/3000 [23:55<29:16,  1.12it/s, lr: 1.0e-04 loss: 5.895e-01]
latex_v1:  34%|###4      | 1026/3000 [23:55<29:16,  1.12it/s, lr: 1.0e-04 loss: 5.895e-01]
latex_v1:  34%|###4      | 1027/3000 [23:55<30:43,  1.07it/s, lr: 1.0e-04 loss: 5.895e-01]
latex_v1:  34%|###4      | 1027/3000 [23:55<30:43,  1.07it/s, lr: 1.0e-04 loss: 5.895e-01]
latex_v1:  34%|###4      | 1027/3000 [23:56<30:43,  1.07it/s, lr: 1.0e-04 loss: 1.513e-01]
latex_v1:  34%|###4      | 1027/3000 [23:56<30:43,  1.07it/s, lr: 1.0e-04 loss: 1.513e-01]
latex_v1:  34%|###4      | 1028/3000 [23:56<35:01,  1.07s/it, lr: 1.0e-04 loss: 1.513e-01]
latex_v1:  34%|###4      | 1028/3000 [23:56<35:01,  1.07s/it, lr: 1.0e-04 loss: 1.513e-01]
latex_v1:  34%|###4      | 1028/3000 [23:58<35:01,  1.07s/it, lr: 1.0e-04 loss: 4.131e-01]
latex_v1:  34%|###4      | 1028/3000 [23:58<35:01,  1.07s/it, lr: 1.0e-04 loss: 4.131e-01]
latex_v1:  34%|###4      | 1029/3000 [23:58<37:25,  1.14s/it, lr: 1.0e-04 loss: 4.131e-01]
latex_v1:  34%|###4      | 1029/3000 [23:58<37:25,  1.14s/it, lr: 1.0e-04 loss: 4.131e-01]
latex_v1:  34%|###4      | 1029/3000 [24:00<37:25,  1.14s/it, lr: 1.0e-04 loss: 3.499e-01]
latex_v1:  34%|###4      | 1029/3000 [24:00<37:25,  1.14s/it, lr: 1.0e-04 loss: 3.499e-01]
latex_v1:  34%|###4      | 1030/3000 [24:00<37:24,  1.14s/it, lr: 1.0e-04 loss: 5.517e-01]
latex_v1:  34%|###4      | 1030/3000 [24:00<37:24,  1.14s/it, lr: 1.0e-04 loss: 5.517e-01]
latex_v1:  34%|###4      | 1031/3000 [24:00<25:51,  1.27it/s, lr: 1.0e-04 loss: 5.517e-01]
latex_v1:  34%|###4      | 1031/3000 [24:00<25:51,  1.27it/s, lr: 1.0e-04 loss: 5.517e-01]
latex_v1:  34%|###4      | 1031/3000 [24:02<25:51,  1.27it/s, lr: 1.0e-04 loss: 6.728e-02]
latex_v1:  34%|###4      | 1031/3000 [24:02<25:51,  1.27it/s, lr: 1.0e-04 loss: 6.728e-02]
latex_v1:  34%|###4      | 1032/3000 [24:02<35:17,  1.08s/it, lr: 1.0e-04 loss: 6.728e-02]
latex_v1:  34%|###4      | 1032/3000 [24:02<35:17,  1.08s/it, lr: 1.0e-04 loss: 6.728e-02]
latex_v1:  34%|###4      | 1032/3000 [24:05<35:17,  1.08s/it, lr: 1.0e-04 loss: 1.990e-02]
latex_v1:  34%|###4      | 1032/3000 [24:05<35:17,  1.08s/it, lr: 1.0e-04 loss: 1.990e-02]
latex_v1:  34%|###4      | 1033/3000 [24:05<49:53,  1.52s/it, lr: 1.0e-04 loss: 1.990e-02]
latex_v1:  34%|###4      | 1033/3000 [24:05<49:53,  1.52s/it, lr: 1.0e-04 loss: 1.990e-02]
latex_v1:  34%|###4      | 1033/3000 [24:06<49:53,  1.52s/it, lr: 1.0e-04 loss: 3.469e-01]
latex_v1:  34%|###4      | 1033/3000 [24:06<49:53,  1.52s/it, lr: 1.0e-04 loss: 3.469e-01]
latex_v1:  34%|###4      | 1034/3000 [24:06<42:59,  1.31s/it, lr: 1.0e-04 loss: 3.469e-01]
latex_v1:  34%|###4      | 1034/3000 [24:06<42:59,  1.31s/it, lr: 1.0e-04 loss: 3.469e-01]
latex_v1:  34%|###4      | 1034/3000 [24:09<42:59,  1.31s/it, lr: 1.0e-04 loss: 1.782e-01]
latex_v1:  34%|###4      | 1034/3000 [24:09<42:59,  1.31s/it, lr: 1.0e-04 loss: 1.782e-01]
latex_v1:  34%|###4      | 1035/3000 [24:09<56:33,  1.73s/it, lr: 1.0e-04 loss: 1.782e-01]
latex_v1:  34%|###4      | 1035/3000 [24:09<56:33,  1.73s/it, lr: 1.0e-04 loss: 1.782e-01]
latex_v1:  34%|###4      | 1035/3000 [24:11<56:33,  1.73s/it, lr: 1.0e-04 loss: 4.707e-01]
latex_v1:  34%|###4      | 1035/3000 [24:11<56:33,  1.73s/it, lr: 1.0e-04 loss: 4.707e-01]
latex_v1:  35%|###4      | 1036/3000 [24:11<1:06:37,  2.04s/it, lr: 1.0e-04 loss: 4.707e-01]
latex_v1:  35%|###4      | 1036/3000 [24:11<1:06:37,  2.04s/it, lr: 1.0e-04 loss: 4.707e-01]
latex_v1:  35%|###4      | 1036/3000 [24:12<1:06:37,  2.04s/it, lr: 1.0e-04 loss: 3.782e-01]
latex_v1:  35%|###4      | 1036/3000 [24:12<1:06:37,  2.04s/it, lr: 1.0e-04 loss: 3.782e-01]
latex_v1:  35%|###4      | 1037/3000 [24:12<54:00,  1.65s/it, lr: 1.0e-04 loss: 3.782e-01]  
latex_v1:  35%|###4      | 1037/3000 [24:12<54:00,  1.65s/it, lr: 1.0e-04 loss: 3.782e-01]  
latex_v1:  35%|###4      | 1037/3000 [24:13<54:00,  1.65s/it, lr: 1.0e-04 loss: 1.423e-01]
latex_v1:  35%|###4      | 1037/3000 [24:13<54:00,  1.65s/it, lr: 1.0e-04 loss: 1.423e-01]
latex_v1:  35%|###4      | 1038/3000 [24:13<45:15,  1.38s/it, lr: 1.0e-04 loss: 1.423e-01]
latex_v1:  35%|###4      | 1038/3000 [24:13<45:15,  1.38s/it, lr: 1.0e-04 loss: 1.423e-01]
latex_v1:  35%|###4      | 1038/3000 [24:14<45:15,  1.38s/it, lr: 1.0e-04 loss: 3.641e-01]
latex_v1:  35%|###4      | 1038/3000 [24:14<45:15,  1.38s/it, lr: 1.0e-04 loss: 3.641e-01]
latex_v1:  35%|###4      | 1039/3000 [24:14<43:05,  1.32s/it, lr: 1.0e-04 loss: 3.641e-01]
latex_v1:  35%|###4      | 1039/3000 [24:14<43:05,  1.32s/it, lr: 1.0e-04 loss: 3.641e-01]
latex_v1:  35%|###4      | 1039/3000 [24:15<43:05,  1.32s/it, lr: 1.0e-04 loss: 3.715e-01]
latex_v1:  35%|###4      | 1039/3000 [24:15<43:05,  1.32s/it, lr: 1.0e-04 loss: 3.715e-01]
latex_v1:  35%|###4      | 1040/3000 [24:16<43:04,  1.32s/it, lr: 1.0e-04 loss: 3.078e-01]
latex_v1:  35%|###4      | 1040/3000 [24:16<43:04,  1.32s/it, lr: 1.0e-04 loss: 3.078e-01]
latex_v1:  35%|###4      | 1041/3000 [24:16<30:42,  1.06it/s, lr: 1.0e-04 loss: 3.078e-01]
latex_v1:  35%|###4      | 1041/3000 [24:16<30:42,  1.06it/s, lr: 1.0e-04 loss: 3.078e-01]
latex_v1:  35%|###4      | 1041/3000 [24:17<30:42,  1.06it/s, lr: 1.0e-04 loss: 7.966e-01]
latex_v1:  35%|###4      | 1041/3000 [24:17<30:42,  1.06it/s, lr: 1.0e-04 loss: 7.966e-01]
latex_v1:  35%|###4      | 1042/3000 [24:17<30:40,  1.06it/s, lr: 1.0e-04 loss: 7.966e-01]
latex_v1:  35%|###4      | 1042/3000 [24:17<30:40,  1.06it/s, lr: 1.0e-04 loss: 7.966e-01]
latex_v1:  35%|###4      | 1042/3000 [24:20<30:40,  1.06it/s, lr: 1.0e-04 loss: 8.479e-02]
latex_v1:  35%|###4      | 1042/3000 [24:20<30:40,  1.06it/s, lr: 1.0e-04 loss: 8.479e-02]
latex_v1:  35%|###4      | 1043/3000 [24:20<46:39,  1.43s/it, lr: 1.0e-04 loss: 8.479e-02]
latex_v1:  35%|###4      | 1043/3000 [24:20<46:39,  1.43s/it, lr: 1.0e-04 loss: 8.479e-02]
latex_v1:  35%|###4      | 1043/3000 [24:21<46:39,  1.43s/it, lr: 1.0e-04 loss: 5.337e-01]
latex_v1:  35%|###4      | 1043/3000 [24:21<46:39,  1.43s/it, lr: 1.0e-04 loss: 5.337e-01]
latex_v1:  35%|###4      | 1044/3000 [24:21<46:30,  1.43s/it, lr: 1.0e-04 loss: 5.337e-01]
latex_v1:  35%|###4      | 1044/3000 [24:21<46:30,  1.43s/it, lr: 1.0e-04 loss: 5.337e-01]
latex_v1:  35%|###4      | 1044/3000 [24:22<46:30,  1.43s/it, lr: 1.0e-04 loss: 5.333e-01]
latex_v1:  35%|###4      | 1044/3000 [24:22<46:30,  1.43s/it, lr: 1.0e-04 loss: 5.333e-01]
latex_v1:  35%|###4      | 1045/3000 [24:22<45:27,  1.40s/it, lr: 1.0e-04 loss: 5.333e-01]
latex_v1:  35%|###4      | 1045/3000 [24:22<45:27,  1.40s/it, lr: 1.0e-04 loss: 5.333e-01]
latex_v1:  35%|###4      | 1045/3000 [24:23<45:27,  1.40s/it, lr: 1.0e-04 loss: 4.219e-01]
latex_v1:  35%|###4      | 1045/3000 [24:23<45:27,  1.40s/it, lr: 1.0e-04 loss: 4.219e-01]
latex_v1:  35%|###4      | 1046/3000 [24:23<39:24,  1.21s/it, lr: 1.0e-04 loss: 4.219e-01]
latex_v1:  35%|###4      | 1046/3000 [24:23<39:24,  1.21s/it, lr: 1.0e-04 loss: 4.219e-01]
latex_v1:  35%|###4      | 1046/3000 [24:24<39:24,  1.21s/it, lr: 1.0e-04 loss: 1.895e-01]
latex_v1:  35%|###4      | 1046/3000 [24:24<39:24,  1.21s/it, lr: 1.0e-04 loss: 1.895e-01]
latex_v1:  35%|###4      | 1047/3000 [24:24<35:11,  1.08s/it, lr: 1.0e-04 loss: 1.895e-01]
latex_v1:  35%|###4      | 1047/3000 [24:24<35:11,  1.08s/it, lr: 1.0e-04 loss: 1.895e-01]
latex_v1:  35%|###4      | 1047/3000 [24:25<35:11,  1.08s/it, lr: 1.0e-04 loss: 7.867e-02]
latex_v1:  35%|###4      | 1047/3000 [24:25<35:11,  1.08s/it, lr: 1.0e-04 loss: 7.867e-02]
latex_v1:  35%|###4      | 1048/3000 [24:25<37:29,  1.15s/it, lr: 1.0e-04 loss: 7.867e-02]
latex_v1:  35%|###4      | 1048/3000 [24:25<37:29,  1.15s/it, lr: 1.0e-04 loss: 7.867e-02]
latex_v1:  35%|###4      | 1048/3000 [24:27<37:29,  1.15s/it, lr: 1.0e-04 loss: 2.558e-01]
latex_v1:  35%|###4      | 1048/3000 [24:27<37:29,  1.15s/it, lr: 1.0e-04 loss: 2.558e-01]
latex_v1:  35%|###4      | 1049/3000 [24:27<41:04,  1.26s/it, lr: 1.0e-04 loss: 2.558e-01]
latex_v1:  35%|###4      | 1049/3000 [24:27<41:04,  1.26s/it, lr: 1.0e-04 loss: 2.558e-01]
latex_v1:  35%|###4      | 1049/3000 [24:28<41:04,  1.26s/it, lr: 1.0e-04 loss: 2.470e-02]
latex_v1:  35%|###4      | 1049/3000 [24:28<41:04,  1.26s/it, lr: 1.0e-04 loss: 2.470e-02]
latex_v1:  35%|###5      | 1050/3000 [24:30<41:03,  1.26s/it, lr: 1.0e-04 loss: 1.723e-01]
latex_v1:  35%|###5      | 1050/3000 [24:30<41:03,  1.26s/it, lr: 1.0e-04 loss: 1.723e-01]
latex_v1:  35%|###5      | 1051/3000 [24:30<36:06,  1.11s/it, lr: 1.0e-04 loss: 1.723e-01]
latex_v1:  35%|###5      | 1051/3000 [24:30<36:06,  1.11s/it, lr: 1.0e-04 loss: 1.723e-01]
latex_v1:  35%|###5      | 1051/3000 [24:31<36:06,  1.11s/it, lr: 1.0e-04 loss: 3.402e-01]
latex_v1:  35%|###5      | 1051/3000 [24:31<36:06,  1.11s/it, lr: 1.0e-04 loss: 3.402e-01]
latex_v1:  35%|###5      | 1052/3000 [24:32<38:55,  1.20s/it, lr: 1.0e-04 loss: 3.402e-01]
latex_v1:  35%|###5      | 1052/3000 [24:32<38:55,  1.20s/it, lr: 1.0e-04 loss: 3.402e-01]
latex_v1:  35%|###5      | 1052/3000 [24:33<38:55,  1.20s/it, lr: 1.0e-04 loss: 1.888e-01]
latex_v1:  35%|###5      | 1052/3000 [24:33<38:55,  1.20s/it, lr: 1.0e-04 loss: 1.888e-01]
latex_v1:  35%|###5      | 1053/3000 [24:33<37:37,  1.16s/it, lr: 1.0e-04 loss: 1.888e-01]
latex_v1:  35%|###5      | 1053/3000 [24:33<37:37,  1.16s/it, lr: 1.0e-04 loss: 1.888e-01]
latex_v1:  35%|###5      | 1053/3000 [24:34<37:37,  1.16s/it, lr: 1.0e-04 loss: 4.838e-01]
latex_v1:  35%|###5      | 1053/3000 [24:34<37:37,  1.16s/it, lr: 1.0e-04 loss: 4.838e-01]
latex_v1:  35%|###5      | 1054/3000 [24:34<35:54,  1.11s/it, lr: 1.0e-04 loss: 4.838e-01]
latex_v1:  35%|###5      | 1054/3000 [24:34<35:54,  1.11s/it, lr: 1.0e-04 loss: 4.838e-01]
latex_v1:  35%|###5      | 1054/3000 [24:34<35:54,  1.11s/it, lr: 1.0e-04 loss: 7.476e-01]
latex_v1:  35%|###5      | 1054/3000 [24:34<35:54,  1.11s/it, lr: 1.0e-04 loss: 7.476e-01]
latex_v1:  35%|###5      | 1055/3000 [24:34<32:53,  1.01s/it, lr: 1.0e-04 loss: 7.476e-01]
latex_v1:  35%|###5      | 1055/3000 [24:34<32:53,  1.01s/it, lr: 1.0e-04 loss: 7.476e-01]
latex_v1:  35%|###5      | 1055/3000 [24:36<32:53,  1.01s/it, lr: 1.0e-04 loss: 6.933e-01]
latex_v1:  35%|###5      | 1055/3000 [24:36<32:53,  1.01s/it, lr: 1.0e-04 loss: 6.933e-01]
latex_v1:  35%|###5      | 1056/3000 [24:36<36:31,  1.13s/it, lr: 1.0e-04 loss: 6.933e-01]
latex_v1:  35%|###5      | 1056/3000 [24:36<36:31,  1.13s/it, lr: 1.0e-04 loss: 6.933e-01]
latex_v1:  35%|###5      | 1056/3000 [24:39<36:31,  1.13s/it, lr: 1.0e-04 loss: 1.241e-01]
latex_v1:  35%|###5      | 1056/3000 [24:39<36:31,  1.13s/it, lr: 1.0e-04 loss: 1.241e-01]
latex_v1:  35%|###5      | 1057/3000 [24:39<52:30,  1.62s/it, lr: 1.0e-04 loss: 1.241e-01]
latex_v1:  35%|###5      | 1057/3000 [24:39<52:30,  1.62s/it, lr: 1.0e-04 loss: 1.241e-01]
latex_v1:  35%|###5      | 1057/3000 [24:40<52:30,  1.62s/it, lr: 1.0e-04 loss: 5.404e-01]
latex_v1:  35%|###5      | 1057/3000 [24:40<52:30,  1.62s/it, lr: 1.0e-04 loss: 5.404e-01]
latex_v1:  35%|###5      | 1058/3000 [24:40<54:53,  1.70s/it, lr: 1.0e-04 loss: 5.404e-01]
latex_v1:  35%|###5      | 1058/3000 [24:40<54:53,  1.70s/it, lr: 1.0e-04 loss: 5.404e-01]
latex_v1:  35%|###5      | 1058/3000 [24:42<54:53,  1.70s/it, lr: 1.0e-04 loss: 5.964e-01]
latex_v1:  35%|###5      | 1058/3000 [24:42<54:53,  1.70s/it, lr: 1.0e-04 loss: 5.964e-01]
latex_v1:  35%|###5      | 1059/3000 [24:42<56:27,  1.75s/it, lr: 1.0e-04 loss: 5.964e-01]
latex_v1:  35%|###5      | 1059/3000 [24:42<56:27,  1.75s/it, lr: 1.0e-04 loss: 5.964e-01]
latex_v1:  35%|###5      | 1059/3000 [24:43<56:27,  1.75s/it, lr: 1.0e-04 loss: 1.485e-01]
latex_v1:  35%|###5      | 1059/3000 [24:43<56:27,  1.75s/it, lr: 1.0e-04 loss: 1.485e-01]
latex_v1:  35%|###5      | 1060/3000 [24:44<56:25,  1.75s/it, lr: 1.0e-04 loss: 6.718e-01]
latex_v1:  35%|###5      | 1060/3000 [24:44<56:25,  1.75s/it, lr: 1.0e-04 loss: 6.718e-01]
latex_v1:  35%|###5      | 1061/3000 [24:44<40:40,  1.26s/it, lr: 1.0e-04 loss: 6.718e-01]
latex_v1:  35%|###5      | 1061/3000 [24:44<40:40,  1.26s/it, lr: 1.0e-04 loss: 6.718e-01]
latex_v1:  35%|###5      | 1061/3000 [24:47<40:40,  1.26s/it, lr: 1.0e-04 loss: 4.745e-01]
latex_v1:  35%|###5      | 1061/3000 [24:47<40:40,  1.26s/it, lr: 1.0e-04 loss: 4.745e-01]
latex_v1:  35%|###5      | 1062/3000 [24:47<51:59,  1.61s/it, lr: 1.0e-04 loss: 4.745e-01]
latex_v1:  35%|###5      | 1062/3000 [24:47<51:59,  1.61s/it, lr: 1.0e-04 loss: 4.745e-01]
latex_v1:  35%|###5      | 1062/3000 [24:49<51:59,  1.61s/it, lr: 1.0e-04 loss: 8.288e-02]
latex_v1:  35%|###5      | 1062/3000 [24:49<51:59,  1.61s/it, lr: 1.0e-04 loss: 8.288e-02]
latex_v1:  35%|###5      | 1063/3000 [24:49<51:09,  1.58s/it, lr: 1.0e-04 loss: 8.288e-02]
latex_v1:  35%|###5      | 1063/3000 [24:49<51:09,  1.58s/it, lr: 1.0e-04 loss: 8.288e-02]
latex_v1:  35%|###5      | 1063/3000 [24:50<51:09,  1.58s/it, lr: 1.0e-04 loss: 2.460e-01]
latex_v1:  35%|###5      | 1063/3000 [24:50<51:09,  1.58s/it, lr: 1.0e-04 loss: 2.460e-01]
latex_v1:  35%|###5      | 1064/3000 [24:50<50:55,  1.58s/it, lr: 1.0e-04 loss: 2.460e-01]
latex_v1:  35%|###5      | 1064/3000 [24:50<50:55,  1.58s/it, lr: 1.0e-04 loss: 2.460e-01]
latex_v1:  35%|###5      | 1064/3000 [24:52<50:55,  1.58s/it, lr: 1.0e-04 loss: 5.184e-01]
latex_v1:  35%|###5      | 1064/3000 [24:52<50:55,  1.58s/it, lr: 1.0e-04 loss: 5.184e-01]
latex_v1:  36%|###5      | 1065/3000 [24:52<50:24,  1.56s/it, lr: 1.0e-04 loss: 5.184e-01]
latex_v1:  36%|###5      | 1065/3000 [24:52<50:24,  1.56s/it, lr: 1.0e-04 loss: 5.184e-01]
latex_v1:  36%|###5      | 1065/3000 [24:53<50:24,  1.56s/it, lr: 1.0e-04 loss: 4.894e-01]
latex_v1:  36%|###5      | 1065/3000 [24:53<50:24,  1.56s/it, lr: 1.0e-04 loss: 4.894e-01]
latex_v1:  36%|###5      | 1066/3000 [24:53<50:59,  1.58s/it, lr: 1.0e-04 loss: 4.894e-01]
latex_v1:  36%|###5      | 1066/3000 [24:53<50:59,  1.58s/it, lr: 1.0e-04 loss: 4.894e-01]
latex_v1:  36%|###5      | 1066/3000 [24:55<50:59,  1.58s/it, lr: 1.0e-04 loss: 2.021e-01]
latex_v1:  36%|###5      | 1066/3000 [24:55<50:59,  1.58s/it, lr: 1.0e-04 loss: 2.021e-01]
latex_v1:  36%|###5      | 1067/3000 [24:55<51:51,  1.61s/it, lr: 1.0e-04 loss: 2.021e-01]
latex_v1:  36%|###5      | 1067/3000 [24:55<51:51,  1.61s/it, lr: 1.0e-04 loss: 2.021e-01]
latex_v1:  36%|###5      | 1067/3000 [24:57<51:51,  1.61s/it, lr: 1.0e-04 loss: 1.105e-01]
latex_v1:  36%|###5      | 1067/3000 [24:57<51:51,  1.61s/it, lr: 1.0e-04 loss: 1.105e-01]
latex_v1:  36%|###5      | 1068/3000 [24:57<54:10,  1.68s/it, lr: 1.0e-04 loss: 1.105e-01]
latex_v1:  36%|###5      | 1068/3000 [24:57<54:10,  1.68s/it, lr: 1.0e-04 loss: 1.105e-01]
latex_v1:  36%|###5      | 1068/3000 [24:58<54:10,  1.68s/it, lr: 1.0e-04 loss: 2.509e-01]
latex_v1:  36%|###5      | 1068/3000 [24:58<54:10,  1.68s/it, lr: 1.0e-04 loss: 2.509e-01]
latex_v1:  36%|###5      | 1069/3000 [24:58<48:51,  1.52s/it, lr: 1.0e-04 loss: 2.509e-01]
latex_v1:  36%|###5      | 1069/3000 [24:58<48:51,  1.52s/it, lr: 1.0e-04 loss: 2.509e-01]
latex_v1:  36%|###5      | 1069/3000 [24:59<48:51,  1.52s/it, lr: 1.0e-04 loss: 5.682e-01]
latex_v1:  36%|###5      | 1069/3000 [24:59<48:51,  1.52s/it, lr: 1.0e-04 loss: 5.682e-01]
latex_v1:  36%|###5      | 1070/3000 [25:01<48:49,  1.52s/it, lr: 1.0e-04 loss: 3.727e-01]
latex_v1:  36%|###5      | 1070/3000 [25:01<48:49,  1.52s/it, lr: 1.0e-04 loss: 3.727e-01]
latex_v1:  36%|###5      | 1071/3000 [25:01<37:00,  1.15s/it, lr: 1.0e-04 loss: 3.727e-01]
latex_v1:  36%|###5      | 1071/3000 [25:01<37:00,  1.15s/it, lr: 1.0e-04 loss: 3.727e-01]
latex_v1:  36%|###5      | 1071/3000 [25:01<37:00,  1.15s/it, lr: 1.0e-04 loss: 3.973e-01]
latex_v1:  36%|###5      | 1071/3000 [25:01<37:00,  1.15s/it, lr: 1.0e-04 loss: 3.973e-01]
latex_v1:  36%|###5      | 1072/3000 [25:01<33:38,  1.05s/it, lr: 1.0e-04 loss: 3.973e-01]
latex_v1:  36%|###5      | 1072/3000 [25:01<33:38,  1.05s/it, lr: 1.0e-04 loss: 3.973e-01]
latex_v1:  36%|###5      | 1072/3000 [25:03<33:38,  1.05s/it, lr: 1.0e-04 loss: 1.251e-01]
latex_v1:  36%|###5      | 1072/3000 [25:03<33:38,  1.05s/it, lr: 1.0e-04 loss: 1.251e-01]
latex_v1:  36%|###5      | 1073/3000 [25:03<37:30,  1.17s/it, lr: 1.0e-04 loss: 1.251e-01]
latex_v1:  36%|###5      | 1073/3000 [25:03<37:30,  1.17s/it, lr: 1.0e-04 loss: 1.251e-01]
latex_v1:  36%|###5      | 1073/3000 [25:04<37:30,  1.17s/it, lr: 1.0e-04 loss: 3.642e-01]
latex_v1:  36%|###5      | 1073/3000 [25:04<37:30,  1.17s/it, lr: 1.0e-04 loss: 3.642e-01]
latex_v1:  36%|###5      | 1074/3000 [25:04<39:07,  1.22s/it, lr: 1.0e-04 loss: 3.642e-01]
latex_v1:  36%|###5      | 1074/3000 [25:04<39:07,  1.22s/it, lr: 1.0e-04 loss: 3.642e-01]
latex_v1:  36%|###5      | 1074/3000 [25:06<39:07,  1.22s/it, lr: 1.0e-04 loss: 5.562e-01]
latex_v1:  36%|###5      | 1074/3000 [25:06<39:07,  1.22s/it, lr: 1.0e-04 loss: 5.562e-01]
latex_v1:  36%|###5      | 1075/3000 [25:06<47:27,  1.48s/it, lr: 1.0e-04 loss: 5.562e-01]
latex_v1:  36%|###5      | 1075/3000 [25:06<47:27,  1.48s/it, lr: 1.0e-04 loss: 5.562e-01]
latex_v1:  36%|###5      | 1075/3000 [25:08<47:27,  1.48s/it, lr: 1.0e-04 loss: 4.841e-01]
latex_v1:  36%|###5      | 1075/3000 [25:08<47:27,  1.48s/it, lr: 1.0e-04 loss: 4.841e-01]
latex_v1:  36%|###5      | 1076/3000 [25:08<48:00,  1.50s/it, lr: 1.0e-04 loss: 4.841e-01]
latex_v1:  36%|###5      | 1076/3000 [25:08<48:00,  1.50s/it, lr: 1.0e-04 loss: 4.841e-01]
latex_v1:  36%|###5      | 1076/3000 [25:10<48:00,  1.50s/it, lr: 1.0e-04 loss: 6.629e-01]
latex_v1:  36%|###5      | 1076/3000 [25:10<48:00,  1.50s/it, lr: 1.0e-04 loss: 6.629e-01]
latex_v1:  36%|###5      | 1077/3000 [25:10<51:02,  1.59s/it, lr: 1.0e-04 loss: 6.629e-01]
latex_v1:  36%|###5      | 1077/3000 [25:10<51:02,  1.59s/it, lr: 1.0e-04 loss: 6.629e-01]
latex_v1:  36%|###5      | 1077/3000 [25:10<51:02,  1.59s/it, lr: 1.0e-04 loss: 2.413e-01]
latex_v1:  36%|###5      | 1077/3000 [25:10<51:02,  1.59s/it, lr: 1.0e-04 loss: 2.413e-01]
latex_v1:  36%|###5      | 1078/3000 [25:10<43:08,  1.35s/it, lr: 1.0e-04 loss: 2.413e-01]
latex_v1:  36%|###5      | 1078/3000 [25:10<43:08,  1.35s/it, lr: 1.0e-04 loss: 2.413e-01]
latex_v1:  36%|###5      | 1078/3000 [25:12<43:08,  1.35s/it, lr: 1.0e-04 loss: 2.375e-01]
latex_v1:  36%|###5      | 1078/3000 [25:12<43:08,  1.35s/it, lr: 1.0e-04 loss: 2.375e-01]
latex_v1:  36%|###5      | 1079/3000 [25:12<46:35,  1.46s/it, lr: 1.0e-04 loss: 2.375e-01]
latex_v1:  36%|###5      | 1079/3000 [25:12<46:35,  1.46s/it, lr: 1.0e-04 loss: 2.375e-01]
latex_v1:  36%|###5      | 1079/3000 [25:14<46:35,  1.46s/it, lr: 1.0e-04 loss: 7.439e-01]
latex_v1:  36%|###5      | 1079/3000 [25:14<46:35,  1.46s/it, lr: 1.0e-04 loss: 7.439e-01]
latex_v1:  36%|###6      | 1080/3000 [25:15<46:33,  1.46s/it, lr: 1.0e-04 loss: 4.317e-01]
latex_v1:  36%|###6      | 1080/3000 [25:15<46:33,  1.46s/it, lr: 1.0e-04 loss: 4.317e-01]
latex_v1:  36%|###6      | 1081/3000 [25:15<36:29,  1.14s/it, lr: 1.0e-04 loss: 4.317e-01]
latex_v1:  36%|###6      | 1081/3000 [25:15<36:29,  1.14s/it, lr: 1.0e-04 loss: 4.317e-01]
latex_v1:  36%|###6      | 1081/3000 [25:17<36:29,  1.14s/it, lr: 1.0e-04 loss: 1.760e-01]
latex_v1:  36%|###6      | 1081/3000 [25:17<36:29,  1.14s/it, lr: 1.0e-04 loss: 1.760e-01]
latex_v1:  36%|###6      | 1082/3000 [25:17<39:30,  1.24s/it, lr: 1.0e-04 loss: 1.760e-01]
latex_v1:  36%|###6      | 1082/3000 [25:17<39:30,  1.24s/it, lr: 1.0e-04 loss: 1.760e-01]
latex_v1:  36%|###6      | 1082/3000 [25:18<39:30,  1.24s/it, lr: 1.0e-04 loss: 6.126e-01]
latex_v1:  36%|###6      | 1082/3000 [25:18<39:30,  1.24s/it, lr: 1.0e-04 loss: 6.126e-01]
latex_v1:  36%|###6      | 1083/3000 [25:18<35:28,  1.11s/it, lr: 1.0e-04 loss: 6.126e-01]
latex_v1:  36%|###6      | 1083/3000 [25:18<35:28,  1.11s/it, lr: 1.0e-04 loss: 6.126e-01]
latex_v1:  36%|###6      | 1083/3000 [25:20<35:28,  1.11s/it, lr: 1.0e-04 loss: 1.766e-01]
latex_v1:  36%|###6      | 1083/3000 [25:20<35:28,  1.11s/it, lr: 1.0e-04 loss: 1.766e-01]
latex_v1:  36%|###6      | 1084/3000 [25:20<50:31,  1.58s/it, lr: 1.0e-04 loss: 1.766e-01]
latex_v1:  36%|###6      | 1084/3000 [25:20<50:31,  1.58s/it, lr: 1.0e-04 loss: 1.766e-01]
latex_v1:  36%|###6      | 1084/3000 [25:21<50:31,  1.58s/it, lr: 1.0e-04 loss: 1.125e-01]
latex_v1:  36%|###6      | 1084/3000 [25:21<50:31,  1.58s/it, lr: 1.0e-04 loss: 1.125e-01]
latex_v1:  36%|###6      | 1085/3000 [25:21<43:13,  1.35s/it, lr: 1.0e-04 loss: 1.125e-01]
latex_v1:  36%|###6      | 1085/3000 [25:21<43:13,  1.35s/it, lr: 1.0e-04 loss: 1.125e-01]
latex_v1:  36%|###6      | 1085/3000 [25:23<43:13,  1.35s/it, lr: 1.0e-04 loss: 1.515e-01]
latex_v1:  36%|###6      | 1085/3000 [25:23<43:13,  1.35s/it, lr: 1.0e-04 loss: 1.515e-01]
latex_v1:  36%|###6      | 1086/3000 [25:23<43:44,  1.37s/it, lr: 1.0e-04 loss: 1.515e-01]
latex_v1:  36%|###6      | 1086/3000 [25:23<43:44,  1.37s/it, lr: 1.0e-04 loss: 1.515e-01]
latex_v1:  36%|###6      | 1086/3000 [25:24<43:44,  1.37s/it, lr: 1.0e-04 loss: 8.642e-01]
latex_v1:  36%|###6      | 1086/3000 [25:24<43:44,  1.37s/it, lr: 1.0e-04 loss: 8.642e-01]
latex_v1:  36%|###6      | 1087/3000 [25:24<42:19,  1.33s/it, lr: 1.0e-04 loss: 8.642e-01]
latex_v1:  36%|###6      | 1087/3000 [25:24<42:19,  1.33s/it, lr: 1.0e-04 loss: 8.642e-01]
latex_v1:  36%|###6      | 1087/3000 [25:25<42:19,  1.33s/it, lr: 1.0e-04 loss: 6.547e-01]
latex_v1:  36%|###6      | 1087/3000 [25:25<42:19,  1.33s/it, lr: 1.0e-04 loss: 6.547e-01]
latex_v1:  36%|###6      | 1088/3000 [25:25<44:16,  1.39s/it, lr: 1.0e-04 loss: 6.547e-01]
latex_v1:  36%|###6      | 1088/3000 [25:25<44:16,  1.39s/it, lr: 1.0e-04 loss: 6.547e-01]
latex_v1:  36%|###6      | 1088/3000 [25:26<44:16,  1.39s/it, lr: 1.0e-04 loss: 7.211e-01]
latex_v1:  36%|###6      | 1088/3000 [25:26<44:16,  1.39s/it, lr: 1.0e-04 loss: 7.211e-01]
latex_v1:  36%|###6      | 1089/3000 [25:26<38:16,  1.20s/it, lr: 1.0e-04 loss: 7.211e-01]
latex_v1:  36%|###6      | 1089/3000 [25:26<38:16,  1.20s/it, lr: 1.0e-04 loss: 7.211e-01]
latex_v1:  36%|###6      | 1089/3000 [25:29<38:16,  1.20s/it, lr: 1.0e-04 loss: 3.165e-01]
latex_v1:  36%|###6      | 1089/3000 [25:29<38:16,  1.20s/it, lr: 1.0e-04 loss: 3.165e-01]
latex_v1:  36%|###6      | 1090/3000 [25:30<38:15,  1.20s/it, lr: 1.0e-04 loss: 6.237e-01]
latex_v1:  36%|###6      | 1090/3000 [25:30<38:15,  1.20s/it, lr: 1.0e-04 loss: 6.237e-01]
latex_v1:  36%|###6      | 1091/3000 [25:30<26:06,  1.22it/s, lr: 1.0e-04 loss: 6.237e-01]
latex_v1:  36%|###6      | 1091/3000 [25:30<26:06,  1.22it/s, lr: 1.0e-04 loss: 6.237e-01]
latex_v1:  36%|###6      | 1091/3000 [25:31<26:06,  1.22it/s, lr: 1.0e-04 loss: 1.053e-02]
latex_v1:  36%|###6      | 1091/3000 [25:31<26:06,  1.22it/s, lr: 1.0e-04 loss: 1.053e-02]
latex_v1:  36%|###6      | 1092/3000 [25:31<27:04,  1.17it/s, lr: 1.0e-04 loss: 1.053e-02]
latex_v1:  36%|###6      | 1092/3000 [25:31<27:04,  1.17it/s, lr: 1.0e-04 loss: 1.053e-02]
latex_v1:  36%|###6      | 1092/3000 [25:32<27:04,  1.17it/s, lr: 1.0e-04 loss: 4.046e-01]
latex_v1:  36%|###6      | 1092/3000 [25:32<27:04,  1.17it/s, lr: 1.0e-04 loss: 4.046e-01]
latex_v1:  36%|###6      | 1093/3000 [25:32<32:03,  1.01s/it, lr: 1.0e-04 loss: 4.046e-01]
latex_v1:  36%|###6      | 1093/3000 [25:32<32:03,  1.01s/it, lr: 1.0e-04 loss: 4.046e-01]
latex_v1:  36%|###6      | 1093/3000 [25:33<32:03,  1.01s/it, lr: 1.0e-04 loss: 3.133e-01]
latex_v1:  36%|###6      | 1093/3000 [25:33<32:03,  1.01s/it, lr: 1.0e-04 loss: 3.133e-01]
latex_v1:  36%|###6      | 1094/3000 [25:33<34:44,  1.09s/it, lr: 1.0e-04 loss: 3.133e-01]
latex_v1:  36%|###6      | 1094/3000 [25:33<34:44,  1.09s/it, lr: 1.0e-04 loss: 3.133e-01]
latex_v1:  36%|###6      | 1094/3000 [25:35<34:44,  1.09s/it, lr: 1.0e-04 loss: 5.889e-01]
latex_v1:  36%|###6      | 1094/3000 [25:35<34:44,  1.09s/it, lr: 1.0e-04 loss: 5.889e-01]
latex_v1:  36%|###6      | 1095/3000 [25:35<39:11,  1.23s/it, lr: 1.0e-04 loss: 5.889e-01]
latex_v1:  36%|###6      | 1095/3000 [25:35<39:11,  1.23s/it, lr: 1.0e-04 loss: 5.889e-01]
latex_v1:  36%|###6      | 1095/3000 [25:36<39:11,  1.23s/it, lr: 1.0e-04 loss: 6.742e-01]
latex_v1:  36%|###6      | 1095/3000 [25:36<39:11,  1.23s/it, lr: 1.0e-04 loss: 6.742e-01]
latex_v1:  37%|###6      | 1096/3000 [25:36<34:53,  1.10s/it, lr: 1.0e-04 loss: 6.742e-01]
latex_v1:  37%|###6      | 1096/3000 [25:36<34:53,  1.10s/it, lr: 1.0e-04 loss: 6.742e-01]
latex_v1:  37%|###6      | 1096/3000 [25:37<34:53,  1.10s/it, lr: 1.0e-04 loss: 1.849e-01]
latex_v1:  37%|###6      | 1096/3000 [25:37<34:53,  1.10s/it, lr: 1.0e-04 loss: 1.849e-01]
latex_v1:  37%|###6      | 1097/3000 [25:37<39:07,  1.23s/it, lr: 1.0e-04 loss: 1.849e-01]
latex_v1:  37%|###6      | 1097/3000 [25:37<39:07,  1.23s/it, lr: 1.0e-04 loss: 1.849e-01]
latex_v1:  37%|###6      | 1097/3000 [25:38<39:07,  1.23s/it, lr: 1.0e-04 loss: 2.272e-02]
latex_v1:  37%|###6      | 1097/3000 [25:38<39:07,  1.23s/it, lr: 1.0e-04 loss: 2.272e-02]
latex_v1:  37%|###6      | 1098/3000 [25:38<34:40,  1.09s/it, lr: 1.0e-04 loss: 2.272e-02]
latex_v1:  37%|###6      | 1098/3000 [25:38<34:40,  1.09s/it, lr: 1.0e-04 loss: 2.272e-02]
latex_v1:  37%|###6      | 1098/3000 [25:39<34:40,  1.09s/it, lr: 1.0e-04 loss: 5.904e-02]
latex_v1:  37%|###6      | 1098/3000 [25:39<34:40,  1.09s/it, lr: 1.0e-04 loss: 5.904e-02]
latex_v1:  37%|###6      | 1099/3000 [25:39<31:28,  1.01it/s, lr: 1.0e-04 loss: 5.904e-02]
latex_v1:  37%|###6      | 1099/3000 [25:39<31:28,  1.01it/s, lr: 1.0e-04 loss: 5.904e-02]
latex_v1:  37%|###6      | 1099/3000 [25:40<31:28,  1.01it/s, lr: 1.0e-04 loss: 6.770e-01]
latex_v1:  37%|###6      | 1099/3000 [25:40<31:28,  1.01it/s, lr: 1.0e-04 loss: 6.770e-01]
latex_v1:  37%|###6      | 1100/3000 [25:40<31:27,  1.01it/s, lr: 1.0e-04 loss: 3.574e-01]
latex_v1:  37%|###6      | 1100/3000 [25:40<31:27,  1.01it/s, lr: 1.0e-04 loss: 3.574e-01]
latex_v1:  37%|###6      | 1101/3000 [25:40<22:29,  1.41it/s, lr: 1.0e-04 loss: 3.574e-01]
latex_v1:  37%|###6      | 1101/3000 [25:40<22:29,  1.41it/s, lr: 1.0e-04 loss: 3.574e-01]
latex_v1:  37%|###6      | 1101/3000 [25:42<22:29,  1.41it/s, lr: 1.0e-04 loss: 5.997e-01]
latex_v1:  37%|###6      | 1101/3000 [25:42<22:29,  1.41it/s, lr: 1.0e-04 loss: 5.997e-01]
latex_v1:  37%|###6      | 1102/3000 [25:42<26:00,  1.22it/s, lr: 1.0e-04 loss: 5.997e-01]
latex_v1:  37%|###6      | 1102/3000 [25:42<26:00,  1.22it/s, lr: 1.0e-04 loss: 5.997e-01]
latex_v1:  37%|###6      | 1102/3000 [25:43<26:00,  1.22it/s, lr: 1.0e-04 loss: 2.989e-01]
latex_v1:  37%|###6      | 1102/3000 [25:43<26:00,  1.22it/s, lr: 1.0e-04 loss: 2.989e-01]
latex_v1:  37%|###6      | 1103/3000 [25:43<31:53,  1.01s/it, lr: 1.0e-04 loss: 2.989e-01]
latex_v1:  37%|###6      | 1103/3000 [25:43<31:53,  1.01s/it, lr: 1.0e-04 loss: 2.989e-01]
latex_v1:  37%|###6      | 1103/3000 [25:44<31:53,  1.01s/it, lr: 1.0e-04 loss: 4.310e-01]
latex_v1:  37%|###6      | 1103/3000 [25:44<31:53,  1.01s/it, lr: 1.0e-04 loss: 4.310e-01]
latex_v1:  37%|###6      | 1104/3000 [25:45<35:32,  1.12s/it, lr: 1.0e-04 loss: 4.310e-01]
latex_v1:  37%|###6      | 1104/3000 [25:45<35:32,  1.12s/it, lr: 1.0e-04 loss: 4.310e-01]
latex_v1:  37%|###6      | 1104/3000 [25:45<35:32,  1.12s/it, lr: 1.0e-04 loss: 8.229e-01]
latex_v1:  37%|###6      | 1104/3000 [25:45<35:32,  1.12s/it, lr: 1.0e-04 loss: 8.229e-01]
latex_v1:  37%|###6      | 1105/3000 [25:45<32:18,  1.02s/it, lr: 1.0e-04 loss: 8.229e-01]
latex_v1:  37%|###6      | 1105/3000 [25:45<32:18,  1.02s/it, lr: 1.0e-04 loss: 8.229e-01]
latex_v1:  37%|###6      | 1105/3000 [25:46<32:18,  1.02s/it, lr: 1.0e-04 loss: 5.768e-01]
latex_v1:  37%|###6      | 1105/3000 [25:46<32:18,  1.02s/it, lr: 1.0e-04 loss: 5.768e-01]
latex_v1:  37%|###6      | 1106/3000 [25:46<29:47,  1.06it/s, lr: 1.0e-04 loss: 5.768e-01]
latex_v1:  37%|###6      | 1106/3000 [25:46<29:47,  1.06it/s, lr: 1.0e-04 loss: 5.768e-01]
latex_v1:  37%|###6      | 1106/3000 [25:47<29:47,  1.06it/s, lr: 1.0e-04 loss: 4.689e-01]
latex_v1:  37%|###6      | 1106/3000 [25:47<29:47,  1.06it/s, lr: 1.0e-04 loss: 4.689e-01]
latex_v1:  37%|###6      | 1107/3000 [25:47<34:29,  1.09s/it, lr: 1.0e-04 loss: 4.689e-01]
latex_v1:  37%|###6      | 1107/3000 [25:47<34:29,  1.09s/it, lr: 1.0e-04 loss: 4.689e-01]
latex_v1:  37%|###6      | 1107/3000 [25:48<34:29,  1.09s/it, lr: 1.0e-04 loss: 5.325e-01]
latex_v1:  37%|###6      | 1107/3000 [25:48<34:29,  1.09s/it, lr: 1.0e-04 loss: 5.325e-01]
latex_v1:  37%|###6      | 1108/3000 [25:48<31:17,  1.01it/s, lr: 1.0e-04 loss: 5.325e-01]
latex_v1:  37%|###6      | 1108/3000 [25:48<31:17,  1.01it/s, lr: 1.0e-04 loss: 5.325e-01]
latex_v1:  37%|###6      | 1108/3000 [25:51<31:17,  1.01it/s, lr: 1.0e-04 loss: 7.036e-02]
latex_v1:  37%|###6      | 1108/3000 [25:51<31:17,  1.01it/s, lr: 1.0e-04 loss: 7.036e-02]
latex_v1:  37%|###6      | 1109/3000 [25:51<50:01,  1.59s/it, lr: 1.0e-04 loss: 7.036e-02]
latex_v1:  37%|###6      | 1109/3000 [25:51<50:01,  1.59s/it, lr: 1.0e-04 loss: 7.036e-02]
latex_v1:  37%|###6      | 1109/3000 [25:52<50:01,  1.59s/it, lr: 1.0e-04 loss: 3.420e-01]
latex_v1:  37%|###6      | 1109/3000 [25:52<50:01,  1.59s/it, lr: 1.0e-04 loss: 3.420e-01]
latex_v1:  37%|###7      | 1110/3000 [25:53<50:00,  1.59s/it, lr: 1.0e-04 loss: 2.828e-01]
latex_v1:  37%|###7      | 1110/3000 [25:53<50:00,  1.59s/it, lr: 1.0e-04 loss: 2.828e-01]
latex_v1:  37%|###7      | 1111/3000 [25:53<32:31,  1.03s/it, lr: 1.0e-04 loss: 2.828e-01]
latex_v1:  37%|###7      | 1111/3000 [25:53<32:31,  1.03s/it, lr: 1.0e-04 loss: 2.828e-01]
latex_v1:  37%|###7      | 1111/3000 [25:54<32:31,  1.03s/it, lr: 1.0e-04 loss: 2.764e-01]
latex_v1:  37%|###7      | 1111/3000 [25:54<32:31,  1.03s/it, lr: 1.0e-04 loss: 2.764e-01]
latex_v1:  37%|###7      | 1112/3000 [25:54<33:41,  1.07s/it, lr: 1.0e-04 loss: 2.764e-01]
latex_v1:  37%|###7      | 1112/3000 [25:54<33:41,  1.07s/it, lr: 1.0e-04 loss: 2.764e-01]
latex_v1:  37%|###7      | 1112/3000 [25:55<33:41,  1.07s/it, lr: 1.0e-04 loss: 5.450e-01]
latex_v1:  37%|###7      | 1112/3000 [25:55<33:41,  1.07s/it, lr: 1.0e-04 loss: 5.450e-01]
latex_v1:  37%|###7      | 1113/3000 [25:55<37:34,  1.19s/it, lr: 1.0e-04 loss: 5.450e-01]
latex_v1:  37%|###7      | 1113/3000 [25:55<37:34,  1.19s/it, lr: 1.0e-04 loss: 5.450e-01]
latex_v1:  37%|###7      | 1113/3000 [25:57<37:34,  1.19s/it, lr: 1.0e-04 loss: 1.634e-01]
latex_v1:  37%|###7      | 1113/3000 [25:57<37:34,  1.19s/it, lr: 1.0e-04 loss: 1.634e-01]
latex_v1:  37%|###7      | 1114/3000 [25:57<40:21,  1.28s/it, lr: 1.0e-04 loss: 1.634e-01]
latex_v1:  37%|###7      | 1114/3000 [25:57<40:21,  1.28s/it, lr: 1.0e-04 loss: 1.634e-01]
latex_v1:  37%|###7      | 1114/3000 [26:00<40:21,  1.28s/it, lr: 1.0e-04 loss: 8.363e-02]
latex_v1:  37%|###7      | 1114/3000 [26:00<40:21,  1.28s/it, lr: 1.0e-04 loss: 8.363e-02]
latex_v1:  37%|###7      | 1115/3000 [26:00<52:09,  1.66s/it, lr: 1.0e-04 loss: 8.363e-02]
latex_v1:  37%|###7      | 1115/3000 [26:00<52:09,  1.66s/it, lr: 1.0e-04 loss: 8.363e-02]
latex_v1:  37%|###7      | 1115/3000 [26:02<52:09,  1.66s/it, lr: 1.0e-04 loss: 5.315e-01]
latex_v1:  37%|###7      | 1115/3000 [26:02<52:09,  1.66s/it, lr: 1.0e-04 loss: 5.315e-01]
latex_v1:  37%|###7      | 1116/3000 [26:02<51:37,  1.64s/it, lr: 1.0e-04 loss: 5.315e-01]
latex_v1:  37%|###7      | 1116/3000 [26:02<51:37,  1.64s/it, lr: 1.0e-04 loss: 5.315e-01]
latex_v1:  37%|###7      | 1116/3000 [26:03<51:37,  1.64s/it, lr: 1.0e-04 loss: 1.947e-01]
latex_v1:  37%|###7      | 1116/3000 [26:03<51:37,  1.64s/it, lr: 1.0e-04 loss: 1.947e-01]
latex_v1:  37%|###7      | 1117/3000 [26:03<50:50,  1.62s/it, lr: 1.0e-04 loss: 1.947e-01]
latex_v1:  37%|###7      | 1117/3000 [26:03<50:50,  1.62s/it, lr: 1.0e-04 loss: 1.947e-01]
latex_v1:  37%|###7      | 1117/3000 [26:05<50:50,  1.62s/it, lr: 1.0e-04 loss: 7.080e-02]
latex_v1:  37%|###7      | 1117/3000 [26:05<50:50,  1.62s/it, lr: 1.0e-04 loss: 7.080e-02]
latex_v1:  37%|###7      | 1118/3000 [26:05<50:06,  1.60s/it, lr: 1.0e-04 loss: 7.080e-02]
latex_v1:  37%|###7      | 1118/3000 [26:05<50:06,  1.60s/it, lr: 1.0e-04 loss: 7.080e-02]
latex_v1:  37%|###7      | 1118/3000 [26:06<50:06,  1.60s/it, lr: 1.0e-04 loss: 1.872e-01]
latex_v1:  37%|###7      | 1118/3000 [26:06<50:06,  1.60s/it, lr: 1.0e-04 loss: 1.872e-01]
latex_v1:  37%|###7      | 1119/3000 [26:06<49:35,  1.58s/it, lr: 1.0e-04 loss: 1.872e-01]
latex_v1:  37%|###7      | 1119/3000 [26:06<49:35,  1.58s/it, lr: 1.0e-04 loss: 1.872e-01]
latex_v1:  37%|###7      | 1119/3000 [26:08<49:35,  1.58s/it, lr: 1.0e-04 loss: 1.208e-01]
latex_v1:  37%|###7      | 1119/3000 [26:08<49:35,  1.58s/it, lr: 1.0e-04 loss: 1.208e-01]
latex_v1:  37%|###7      | 1120/3000 [26:09<49:34,  1.58s/it, lr: 1.0e-04 loss: 2.772e-01]
latex_v1:  37%|###7      | 1120/3000 [26:09<49:34,  1.58s/it, lr: 1.0e-04 loss: 2.772e-01]
latex_v1:  37%|###7      | 1121/3000 [26:09<37:25,  1.19s/it, lr: 1.0e-04 loss: 2.772e-01]
latex_v1:  37%|###7      | 1121/3000 [26:09<37:25,  1.19s/it, lr: 1.0e-04 loss: 2.772e-01]
latex_v1:  37%|###7      | 1121/3000 [26:11<37:25,  1.19s/it, lr: 1.0e-04 loss: 3.869e-01]
latex_v1:  37%|###7      | 1121/3000 [26:11<37:25,  1.19s/it, lr: 1.0e-04 loss: 3.869e-01]
latex_v1:  37%|###7      | 1122/3000 [26:11<44:26,  1.42s/it, lr: 1.0e-04 loss: 3.869e-01]
latex_v1:  37%|###7      | 1122/3000 [26:11<44:26,  1.42s/it, lr: 1.0e-04 loss: 3.869e-01]
latex_v1:  37%|###7      | 1122/3000 [26:12<44:26,  1.42s/it, lr: 1.0e-04 loss: 6.654e-01]
latex_v1:  37%|###7      | 1122/3000 [26:12<44:26,  1.42s/it, lr: 1.0e-04 loss: 6.654e-01]
latex_v1:  37%|###7      | 1123/3000 [26:12<42:26,  1.36s/it, lr: 1.0e-04 loss: 6.654e-01]
latex_v1:  37%|###7      | 1123/3000 [26:12<42:26,  1.36s/it, lr: 1.0e-04 loss: 6.654e-01]
latex_v1:  37%|###7      | 1123/3000 [26:13<42:26,  1.36s/it, lr: 1.0e-04 loss: 4.094e-01]
latex_v1:  37%|###7      | 1123/3000 [26:13<42:26,  1.36s/it, lr: 1.0e-04 loss: 4.094e-01]
latex_v1:  37%|###7      | 1124/3000 [26:13<37:27,  1.20s/it, lr: 1.0e-04 loss: 4.094e-01]
latex_v1:  37%|###7      | 1124/3000 [26:13<37:27,  1.20s/it, lr: 1.0e-04 loss: 4.094e-01]
latex_v1:  37%|###7      | 1124/3000 [26:14<37:27,  1.20s/it, lr: 1.0e-04 loss: 5.574e-01]
latex_v1:  37%|###7      | 1124/3000 [26:14<37:27,  1.20s/it, lr: 1.0e-04 loss: 5.574e-01]
latex_v1:  38%|###7      | 1125/3000 [26:14<36:21,  1.16s/it, lr: 1.0e-04 loss: 5.574e-01]
latex_v1:  38%|###7      | 1125/3000 [26:14<36:21,  1.16s/it, lr: 1.0e-04 loss: 5.574e-01]
latex_v1:  38%|###7      | 1125/3000 [26:16<36:21,  1.16s/it, lr: 1.0e-04 loss: 6.025e-01]
latex_v1:  38%|###7      | 1125/3000 [26:16<36:21,  1.16s/it, lr: 1.0e-04 loss: 6.025e-01]
latex_v1:  38%|###7      | 1126/3000 [26:16<42:45,  1.37s/it, lr: 1.0e-04 loss: 6.025e-01]
latex_v1:  38%|###7      | 1126/3000 [26:16<42:45,  1.37s/it, lr: 1.0e-04 loss: 6.025e-01]
latex_v1:  38%|###7      | 1126/3000 [26:18<42:45,  1.37s/it, lr: 1.0e-04 loss: 4.653e-01]
latex_v1:  38%|###7      | 1126/3000 [26:18<42:45,  1.37s/it, lr: 1.0e-04 loss: 4.653e-01]
latex_v1:  38%|###7      | 1127/3000 [26:18<43:08,  1.38s/it, lr: 1.0e-04 loss: 4.653e-01]
latex_v1:  38%|###7      | 1127/3000 [26:18<43:08,  1.38s/it, lr: 1.0e-04 loss: 4.653e-01]
latex_v1:  38%|###7      | 1127/3000 [26:19<43:08,  1.38s/it, lr: 1.0e-04 loss: 5.728e-01]
latex_v1:  38%|###7      | 1127/3000 [26:19<43:08,  1.38s/it, lr: 1.0e-04 loss: 5.728e-01]
latex_v1:  38%|###7      | 1128/3000 [26:19<41:15,  1.32s/it, lr: 1.0e-04 loss: 5.728e-01]
latex_v1:  38%|###7      | 1128/3000 [26:19<41:15,  1.32s/it, lr: 1.0e-04 loss: 5.728e-01]
latex_v1:  38%|###7      | 1128/3000 [26:19<41:15,  1.32s/it, lr: 1.0e-04 loss: 6.729e-01]
latex_v1:  38%|###7      | 1128/3000 [26:19<41:15,  1.32s/it, lr: 1.0e-04 loss: 6.729e-01]
latex_v1:  38%|###7      | 1129/3000 [26:19<36:03,  1.16s/it, lr: 1.0e-04 loss: 6.729e-01]
latex_v1:  38%|###7      | 1129/3000 [26:19<36:03,  1.16s/it, lr: 1.0e-04 loss: 6.729e-01]
latex_v1:  38%|###7      | 1129/3000 [26:21<36:03,  1.16s/it, lr: 1.0e-04 loss: 4.218e-01]
latex_v1:  38%|###7      | 1129/3000 [26:21<36:03,  1.16s/it, lr: 1.0e-04 loss: 4.218e-01]
latex_v1:  38%|###7      | 1130/3000 [26:22<36:02,  1.16s/it, lr: 1.0e-04 loss: 1.193e-01]
latex_v1:  38%|###7      | 1130/3000 [26:22<36:02,  1.16s/it, lr: 1.0e-04 loss: 1.193e-01]
latex_v1:  38%|###7      | 1131/3000 [26:22<25:02,  1.24it/s, lr: 1.0e-04 loss: 1.193e-01]
latex_v1:  38%|###7      | 1131/3000 [26:22<25:02,  1.24it/s, lr: 1.0e-04 loss: 1.193e-01]
latex_v1:  38%|###7      | 1131/3000 [26:24<25:02,  1.24it/s, lr: 1.0e-04 loss: 4.610e-01]
latex_v1:  38%|###7      | 1131/3000 [26:24<25:02,  1.24it/s, lr: 1.0e-04 loss: 4.610e-01]
latex_v1:  38%|###7      | 1132/3000 [26:24<29:52,  1.04it/s, lr: 1.0e-04 loss: 4.610e-01]
latex_v1:  38%|###7      | 1132/3000 [26:24<29:52,  1.04it/s, lr: 1.0e-04 loss: 4.610e-01]
latex_v1:  38%|###7      | 1132/3000 [26:25<29:52,  1.04it/s, lr: 1.0e-04 loss: 4.322e-01]
latex_v1:  38%|###7      | 1132/3000 [26:25<29:52,  1.04it/s, lr: 1.0e-04 loss: 4.322e-01]
latex_v1:  38%|###7      | 1133/3000 [26:25<34:36,  1.11s/it, lr: 1.0e-04 loss: 4.322e-01]
latex_v1:  38%|###7      | 1133/3000 [26:25<34:36,  1.11s/it, lr: 1.0e-04 loss: 4.322e-01]
latex_v1:  38%|###7      | 1133/3000 [26:27<34:36,  1.11s/it, lr: 1.0e-04 loss: 7.042e-02]
latex_v1:  38%|###7      | 1133/3000 [26:27<34:36,  1.11s/it, lr: 1.0e-04 loss: 7.042e-02]
latex_v1:  38%|###7      | 1134/3000 [26:27<38:07,  1.23s/it, lr: 1.0e-04 loss: 7.042e-02]
latex_v1:  38%|###7      | 1134/3000 [26:27<38:07,  1.23s/it, lr: 1.0e-04 loss: 7.042e-02]
latex_v1:  38%|###7      | 1134/3000 [26:28<38:07,  1.23s/it, lr: 1.0e-04 loss: 5.889e-01]
latex_v1:  38%|###7      | 1134/3000 [26:28<38:07,  1.23s/it, lr: 1.0e-04 loss: 5.889e-01]
latex_v1:  38%|###7      | 1135/3000 [26:28<36:09,  1.16s/it, lr: 1.0e-04 loss: 5.889e-01]
latex_v1:  38%|###7      | 1135/3000 [26:28<36:09,  1.16s/it, lr: 1.0e-04 loss: 5.889e-01]
latex_v1:  38%|###7      | 1135/3000 [26:29<36:09,  1.16s/it, lr: 1.0e-04 loss: 5.347e-01]
latex_v1:  38%|###7      | 1135/3000 [26:29<36:09,  1.16s/it, lr: 1.0e-04 loss: 5.347e-01]
latex_v1:  38%|###7      | 1136/3000 [26:29<36:17,  1.17s/it, lr: 1.0e-04 loss: 5.347e-01]
latex_v1:  38%|###7      | 1136/3000 [26:29<36:17,  1.17s/it, lr: 1.0e-04 loss: 5.347e-01]
latex_v1:  38%|###7      | 1136/3000 [26:32<36:17,  1.17s/it, lr: 1.0e-04 loss: 3.856e-01]
latex_v1:  38%|###7      | 1136/3000 [26:32<36:17,  1.17s/it, lr: 1.0e-04 loss: 3.856e-01]
latex_v1:  38%|###7      | 1137/3000 [26:32<51:35,  1.66s/it, lr: 1.0e-04 loss: 3.856e-01]
latex_v1:  38%|###7      | 1137/3000 [26:32<51:35,  1.66s/it, lr: 1.0e-04 loss: 3.856e-01]
latex_v1:  38%|###7      | 1137/3000 [26:32<51:35,  1.66s/it, lr: 1.0e-04 loss: 6.283e-01]
latex_v1:  38%|###7      | 1137/3000 [26:32<51:35,  1.66s/it, lr: 1.0e-04 loss: 6.283e-01]
latex_v1:  38%|###7      | 1138/3000 [26:32<43:21,  1.40s/it, lr: 1.0e-04 loss: 6.283e-01]
latex_v1:  38%|###7      | 1138/3000 [26:32<43:21,  1.40s/it, lr: 1.0e-04 loss: 6.283e-01]
latex_v1:  38%|###7      | 1138/3000 [26:34<43:21,  1.40s/it, lr: 1.0e-04 loss: 5.177e-01]
latex_v1:  38%|###7      | 1138/3000 [26:34<43:21,  1.40s/it, lr: 1.0e-04 loss: 5.177e-01]
latex_v1:  38%|###7      | 1139/3000 [26:34<41:25,  1.34s/it, lr: 1.0e-04 loss: 5.177e-01]
latex_v1:  38%|###7      | 1139/3000 [26:34<41:25,  1.34s/it, lr: 1.0e-04 loss: 5.177e-01]
latex_v1:  38%|###7      | 1139/3000 [26:35<41:25,  1.34s/it, lr: 1.0e-04 loss: 7.330e-01]
latex_v1:  38%|###7      | 1139/3000 [26:35<41:25,  1.34s/it, lr: 1.0e-04 loss: 7.330e-01]
latex_v1:  38%|###8      | 1140/3000 [26:38<41:24,  1.34s/it, lr: 1.0e-04 loss: 1.301e-01]
latex_v1:  38%|###8      | 1140/3000 [26:38<41:24,  1.34s/it, lr: 1.0e-04 loss: 1.301e-01]
latex_v1:  38%|###8      | 1141/3000 [26:38<42:48,  1.38s/it, lr: 1.0e-04 loss: 1.301e-01]
latex_v1:  38%|###8      | 1141/3000 [26:38<42:48,  1.38s/it, lr: 1.0e-04 loss: 1.301e-01]
latex_v1:  38%|###8      | 1141/3000 [26:39<42:48,  1.38s/it, lr: 1.0e-04 loss: 5.951e-02]
latex_v1:  38%|###8      | 1141/3000 [26:39<42:48,  1.38s/it, lr: 1.0e-04 loss: 5.951e-02]
latex_v1:  38%|###8      | 1142/3000 [26:39<40:29,  1.31s/it, lr: 1.0e-04 loss: 5.951e-02]
latex_v1:  38%|###8      | 1142/3000 [26:39<40:29,  1.31s/it, lr: 1.0e-04 loss: 5.951e-02]
latex_v1:  38%|###8      | 1142/3000 [26:40<40:29,  1.31s/it, lr: 1.0e-04 loss: 1.487e-01]
latex_v1:  38%|###8      | 1142/3000 [26:40<40:29,  1.31s/it, lr: 1.0e-04 loss: 1.487e-01]
latex_v1:  38%|###8      | 1143/3000 [26:40<36:01,  1.16s/it, lr: 1.0e-04 loss: 1.487e-01]
latex_v1:  38%|###8      | 1143/3000 [26:40<36:01,  1.16s/it, lr: 1.0e-04 loss: 1.487e-01]
latex_v1:  38%|###8      | 1143/3000 [26:43<36:01,  1.16s/it, lr: 1.0e-04 loss: 1.914e-01]
latex_v1:  38%|###8      | 1143/3000 [26:43<36:01,  1.16s/it, lr: 1.0e-04 loss: 1.914e-01]
latex_v1:  38%|###8      | 1144/3000 [26:43<50:12,  1.62s/it, lr: 1.0e-04 loss: 1.914e-01]
latex_v1:  38%|###8      | 1144/3000 [26:43<50:12,  1.62s/it, lr: 1.0e-04 loss: 1.914e-01]
latex_v1:  38%|###8      | 1144/3000 [26:45<50:12,  1.62s/it, lr: 1.0e-04 loss: 4.442e-01]
latex_v1:  38%|###8      | 1144/3000 [26:45<50:12,  1.62s/it, lr: 1.0e-04 loss: 4.442e-01]
latex_v1:  38%|###8      | 1145/3000 [26:45<59:33,  1.93s/it, lr: 1.0e-04 loss: 4.442e-01]
latex_v1:  38%|###8      | 1145/3000 [26:45<59:33,  1.93s/it, lr: 1.0e-04 loss: 4.442e-01]
latex_v1:  38%|###8      | 1145/3000 [26:48<59:33,  1.93s/it, lr: 1.0e-04 loss: 2.995e-01]
latex_v1:  38%|###8      | 1145/3000 [26:48<59:33,  1.93s/it, lr: 1.0e-04 loss: 2.995e-01]
latex_v1:  38%|###8      | 1146/3000 [26:48<1:07:49,  2.19s/it, lr: 1.0e-04 loss: 2.995e-01]
latex_v1:  38%|###8      | 1146/3000 [26:48<1:07:49,  2.19s/it, lr: 1.0e-04 loss: 2.995e-01]
latex_v1:  38%|###8      | 1146/3000 [26:49<1:07:49,  2.19s/it, lr: 1.0e-04 loss: 5.988e-01]
latex_v1:  38%|###8      | 1146/3000 [26:49<1:07:49,  2.19s/it, lr: 1.0e-04 loss: 5.988e-01]
latex_v1:  38%|###8      | 1147/3000 [26:49<54:46,  1.77s/it, lr: 1.0e-04 loss: 5.988e-01]  
latex_v1:  38%|###8      | 1147/3000 [26:49<54:46,  1.77s/it, lr: 1.0e-04 loss: 5.988e-01]  
latex_v1:  38%|###8      | 1147/3000 [26:50<54:46,  1.77s/it, lr: 1.0e-04 loss: 4.399e-01]
latex_v1:  38%|###8      | 1147/3000 [26:50<54:46,  1.77s/it, lr: 1.0e-04 loss: 4.399e-01]
latex_v1:  38%|###8      | 1148/3000 [26:50<50:42,  1.64s/it, lr: 1.0e-04 loss: 4.399e-01]
latex_v1:  38%|###8      | 1148/3000 [26:50<50:42,  1.64s/it, lr: 1.0e-04 loss: 4.399e-01]
latex_v1:  38%|###8      | 1148/3000 [26:52<50:42,  1.64s/it, lr: 1.0e-04 loss: 8.635e-01]
latex_v1:  38%|###8      | 1148/3000 [26:52<50:42,  1.64s/it, lr: 1.0e-04 loss: 8.635e-01]
latex_v1:  38%|###8      | 1149/3000 [26:52<48:00,  1.56s/it, lr: 1.0e-04 loss: 8.635e-01]
latex_v1:  38%|###8      | 1149/3000 [26:52<48:00,  1.56s/it, lr: 1.0e-04 loss: 8.635e-01]
latex_v1:  38%|###8      | 1149/3000 [26:52<48:00,  1.56s/it, lr: 1.0e-04 loss: 5.895e-01]
latex_v1:  38%|###8      | 1149/3000 [26:52<48:00,  1.56s/it, lr: 1.0e-04 loss: 5.895e-01]
latex_v1:  38%|###8      | 1150/3000 [26:54<47:59,  1.56s/it, lr: 1.0e-04 loss: 2.960e-01]
latex_v1:  38%|###8      | 1150/3000 [26:54<47:59,  1.56s/it, lr: 1.0e-04 loss: 2.960e-01]
latex_v1:  38%|###8      | 1151/3000 [26:54<36:57,  1.20s/it, lr: 1.0e-04 loss: 2.960e-01]
latex_v1:  38%|###8      | 1151/3000 [26:54<36:57,  1.20s/it, lr: 1.0e-04 loss: 2.960e-01]
latex_v1:  38%|###8      | 1151/3000 [26:55<36:57,  1.20s/it, lr: 1.0e-04 loss: 1.757e-01]
latex_v1:  38%|###8      | 1151/3000 [26:55<36:57,  1.20s/it, lr: 1.0e-04 loss: 1.757e-01]
latex_v1:  38%|###8      | 1152/3000 [26:55<33:26,  1.09s/it, lr: 1.0e-04 loss: 1.757e-01]
latex_v1:  38%|###8      | 1152/3000 [26:55<33:26,  1.09s/it, lr: 1.0e-04 loss: 1.757e-01]
latex_v1:  38%|###8      | 1152/3000 [26:55<33:26,  1.09s/it, lr: 1.0e-04 loss: 2.667e-01]
latex_v1:  38%|###8      | 1152/3000 [26:55<33:26,  1.09s/it, lr: 1.0e-04 loss: 2.667e-01]
latex_v1:  38%|###8      | 1153/3000 [26:55<30:53,  1.00s/it, lr: 1.0e-04 loss: 2.667e-01]
latex_v1:  38%|###8      | 1153/3000 [26:55<30:53,  1.00s/it, lr: 1.0e-04 loss: 2.667e-01]
latex_v1:  38%|###8      | 1153/3000 [26:56<30:53,  1.00s/it, lr: 1.0e-04 loss: 2.301e-01]
latex_v1:  38%|###8      | 1153/3000 [26:56<30:53,  1.00s/it, lr: 1.0e-04 loss: 2.301e-01]
latex_v1:  38%|###8      | 1154/3000 [26:56<28:45,  1.07it/s, lr: 1.0e-04 loss: 2.301e-01]
latex_v1:  38%|###8      | 1154/3000 [26:56<28:45,  1.07it/s, lr: 1.0e-04 loss: 2.301e-01]
latex_v1:  38%|###8      | 1154/3000 [26:57<28:45,  1.07it/s, lr: 1.0e-04 loss: 1.251e-01]
latex_v1:  38%|###8      | 1154/3000 [26:57<28:45,  1.07it/s, lr: 1.0e-04 loss: 1.251e-01]
latex_v1:  38%|###8      | 1155/3000 [26:57<27:08,  1.13it/s, lr: 1.0e-04 loss: 1.251e-01]
latex_v1:  38%|###8      | 1155/3000 [26:57<27:08,  1.13it/s, lr: 1.0e-04 loss: 1.251e-01]
latex_v1:  38%|###8      | 1155/3000 [26:58<27:08,  1.13it/s, lr: 1.0e-04 loss: 3.388e-01]
latex_v1:  38%|###8      | 1155/3000 [26:58<27:08,  1.13it/s, lr: 1.0e-04 loss: 3.388e-01]
latex_v1:  39%|###8      | 1156/3000 [26:58<25:58,  1.18it/s, lr: 1.0e-04 loss: 3.388e-01]
latex_v1:  39%|###8      | 1156/3000 [26:58<25:58,  1.18it/s, lr: 1.0e-04 loss: 3.388e-01]
latex_v1:  39%|###8      | 1156/3000 [26:59<25:58,  1.18it/s, lr: 1.0e-04 loss: 5.828e-01]
latex_v1:  39%|###8      | 1156/3000 [26:59<25:58,  1.18it/s, lr: 1.0e-04 loss: 5.828e-01]
latex_v1:  39%|###8      | 1157/3000 [26:59<28:58,  1.06it/s, lr: 1.0e-04 loss: 5.828e-01]
latex_v1:  39%|###8      | 1157/3000 [26:59<28:58,  1.06it/s, lr: 1.0e-04 loss: 5.828e-01]
latex_v1:  39%|###8      | 1157/3000 [27:00<28:58,  1.06it/s, lr: 1.0e-04 loss: 5.233e-01]
latex_v1:  39%|###8      | 1157/3000 [27:00<28:58,  1.06it/s, lr: 1.0e-04 loss: 5.233e-01]
latex_v1:  39%|###8      | 1158/3000 [27:00<33:12,  1.08s/it, lr: 1.0e-04 loss: 5.233e-01]
latex_v1:  39%|###8      | 1158/3000 [27:00<33:12,  1.08s/it, lr: 1.0e-04 loss: 5.233e-01]
latex_v1:  39%|###8      | 1158/3000 [27:01<33:12,  1.08s/it, lr: 1.0e-04 loss: 2.038e-01]
latex_v1:  39%|###8      | 1158/3000 [27:01<33:12,  1.08s/it, lr: 1.0e-04 loss: 2.038e-01]
latex_v1:  39%|###8      | 1159/3000 [27:01<30:13,  1.02it/s, lr: 1.0e-04 loss: 2.038e-01]
latex_v1:  39%|###8      | 1159/3000 [27:01<30:13,  1.02it/s, lr: 1.0e-04 loss: 2.038e-01]
latex_v1:  39%|###8      | 1159/3000 [27:02<30:13,  1.02it/s, lr: 1.0e-04 loss: 2.127e-01]
latex_v1:  39%|###8      | 1159/3000 [27:02<30:13,  1.02it/s, lr: 1.0e-04 loss: 2.127e-01]
latex_v1:  39%|###8      | 1160/3000 [27:04<30:12,  1.02it/s, lr: 1.0e-04 loss: 2.690e-01]
latex_v1:  39%|###8      | 1160/3000 [27:04<30:12,  1.02it/s, lr: 1.0e-04 loss: 2.690e-01]
latex_v1:  39%|###8      | 1161/3000 [27:04<27:12,  1.13it/s, lr: 1.0e-04 loss: 2.690e-01]
latex_v1:  39%|###8      | 1161/3000 [27:04<27:12,  1.13it/s, lr: 1.0e-04 loss: 2.690e-01]
latex_v1:  39%|###8      | 1161/3000 [27:05<27:12,  1.13it/s, lr: 1.0e-04 loss: 6.339e-02]
latex_v1:  39%|###8      | 1161/3000 [27:05<27:12,  1.13it/s, lr: 1.0e-04 loss: 6.339e-02]
latex_v1:  39%|###8      | 1162/3000 [27:05<26:07,  1.17it/s, lr: 1.0e-04 loss: 6.339e-02]
latex_v1:  39%|###8      | 1162/3000 [27:05<26:07,  1.17it/s, lr: 1.0e-04 loss: 6.339e-02]
latex_v1:  39%|###8      | 1162/3000 [27:06<26:07,  1.17it/s, lr: 1.0e-04 loss: 5.452e-01]
latex_v1:  39%|###8      | 1162/3000 [27:06<26:07,  1.17it/s, lr: 1.0e-04 loss: 5.452e-01]
latex_v1:  39%|###8      | 1163/3000 [27:06<27:01,  1.13it/s, lr: 1.0e-04 loss: 5.452e-01]
latex_v1:  39%|###8      | 1163/3000 [27:06<27:01,  1.13it/s, lr: 1.0e-04 loss: 5.452e-01]
latex_v1:  39%|###8      | 1163/3000 [27:07<27:01,  1.13it/s, lr: 1.0e-04 loss: 5.633e-01]
latex_v1:  39%|###8      | 1163/3000 [27:07<27:01,  1.13it/s, lr: 1.0e-04 loss: 5.633e-01]
latex_v1:  39%|###8      | 1164/3000 [27:07<33:27,  1.09s/it, lr: 1.0e-04 loss: 5.633e-01]
latex_v1:  39%|###8      | 1164/3000 [27:07<33:27,  1.09s/it, lr: 1.0e-04 loss: 5.633e-01]
latex_v1:  39%|###8      | 1164/3000 [27:09<33:27,  1.09s/it, lr: 1.0e-04 loss: 3.643e-01]
latex_v1:  39%|###8      | 1164/3000 [27:09<33:27,  1.09s/it, lr: 1.0e-04 loss: 3.643e-01]
latex_v1:  39%|###8      | 1165/3000 [27:09<36:25,  1.19s/it, lr: 1.0e-04 loss: 3.643e-01]
latex_v1:  39%|###8      | 1165/3000 [27:09<36:25,  1.19s/it, lr: 1.0e-04 loss: 3.643e-01]
latex_v1:  39%|###8      | 1165/3000 [27:09<36:25,  1.19s/it, lr: 1.0e-04 loss: 1.904e-01]
latex_v1:  39%|###8      | 1165/3000 [27:09<36:25,  1.19s/it, lr: 1.0e-04 loss: 1.904e-01]
latex_v1:  39%|###8      | 1166/3000 [27:09<32:42,  1.07s/it, lr: 1.0e-04 loss: 1.904e-01]
latex_v1:  39%|###8      | 1166/3000 [27:09<32:42,  1.07s/it, lr: 1.0e-04 loss: 1.904e-01]
latex_v1:  39%|###8      | 1166/3000 [27:11<32:42,  1.07s/it, lr: 1.0e-04 loss: 3.941e-01]
latex_v1:  39%|###8      | 1166/3000 [27:11<32:42,  1.07s/it, lr: 1.0e-04 loss: 3.941e-01]
latex_v1:  39%|###8      | 1167/3000 [27:11<34:53,  1.14s/it, lr: 1.0e-04 loss: 3.941e-01]
latex_v1:  39%|###8      | 1167/3000 [27:11<34:53,  1.14s/it, lr: 1.0e-04 loss: 3.941e-01]
latex_v1:  39%|###8      | 1167/3000 [27:14<34:53,  1.14s/it, lr: 1.0e-04 loss: 7.271e-01]
latex_v1:  39%|###8      | 1167/3000 [27:14<34:53,  1.14s/it, lr: 1.0e-04 loss: 7.271e-01]
latex_v1:  39%|###8      | 1168/3000 [27:14<49:55,  1.63s/it, lr: 1.0e-04 loss: 7.271e-01]
latex_v1:  39%|###8      | 1168/3000 [27:14<49:55,  1.63s/it, lr: 1.0e-04 loss: 7.271e-01]
latex_v1:  39%|###8      | 1168/3000 [27:15<49:55,  1.63s/it, lr: 1.0e-04 loss: 2.198e-01]
latex_v1:  39%|###8      | 1168/3000 [27:15<49:55,  1.63s/it, lr: 1.0e-04 loss: 2.198e-01]
latex_v1:  39%|###8      | 1169/3000 [27:15<48:03,  1.58s/it, lr: 1.0e-04 loss: 2.198e-01]
latex_v1:  39%|###8      | 1169/3000 [27:15<48:03,  1.58s/it, lr: 1.0e-04 loss: 2.198e-01]
latex_v1:  39%|###8      | 1169/3000 [27:16<48:03,  1.58s/it, lr: 1.0e-04 loss: 7.703e-02]
latex_v1:  39%|###8      | 1169/3000 [27:16<48:03,  1.58s/it, lr: 1.0e-04 loss: 7.703e-02]
latex_v1:  39%|###9      | 1170/3000 [27:17<48:02,  1.58s/it, lr: 1.0e-04 loss: 4.941e-01]
latex_v1:  39%|###9      | 1170/3000 [27:17<48:02,  1.58s/it, lr: 1.0e-04 loss: 4.941e-01]
latex_v1:  39%|###9      | 1171/3000 [27:17<35:17,  1.16s/it, lr: 1.0e-04 loss: 4.941e-01]
latex_v1:  39%|###9      | 1171/3000 [27:17<35:17,  1.16s/it, lr: 1.0e-04 loss: 4.941e-01]
latex_v1:  39%|###9      | 1171/3000 [27:18<35:17,  1.16s/it, lr: 1.0e-04 loss: 1.854e-01]
latex_v1:  39%|###9      | 1171/3000 [27:18<35:17,  1.16s/it, lr: 1.0e-04 loss: 1.854e-01]
latex_v1:  39%|###9      | 1172/3000 [27:18<32:19,  1.06s/it, lr: 1.0e-04 loss: 1.854e-01]
latex_v1:  39%|###9      | 1172/3000 [27:18<32:19,  1.06s/it, lr: 1.0e-04 loss: 1.854e-01]
latex_v1:  39%|###9      | 1172/3000 [27:19<32:19,  1.06s/it, lr: 1.0e-04 loss: 4.859e-01]
latex_v1:  39%|###9      | 1172/3000 [27:19<32:19,  1.06s/it, lr: 1.0e-04 loss: 4.859e-01]
latex_v1:  39%|###9      | 1173/3000 [27:19<36:05,  1.19s/it, lr: 1.0e-04 loss: 4.859e-01]
latex_v1:  39%|###9      | 1173/3000 [27:19<36:05,  1.19s/it, lr: 1.0e-04 loss: 4.859e-01]
latex_v1:  39%|###9      | 1173/3000 [27:21<36:05,  1.19s/it, lr: 1.0e-04 loss: 4.055e-01]
latex_v1:  39%|###9      | 1173/3000 [27:21<36:05,  1.19s/it, lr: 1.0e-04 loss: 4.055e-01]
latex_v1:  39%|###9      | 1174/3000 [27:21<42:03,  1.38s/it, lr: 1.0e-04 loss: 4.055e-01]
latex_v1:  39%|###9      | 1174/3000 [27:21<42:03,  1.38s/it, lr: 1.0e-04 loss: 4.055e-01]
latex_v1:  39%|###9      | 1174/3000 [27:23<42:03,  1.38s/it, lr: 1.0e-04 loss: 5.868e-01]
latex_v1:  39%|###9      | 1174/3000 [27:23<42:03,  1.38s/it, lr: 1.0e-04 loss: 5.868e-01]
latex_v1:  39%|###9      | 1175/3000 [27:23<42:13,  1.39s/it, lr: 1.0e-04 loss: 5.868e-01]
latex_v1:  39%|###9      | 1175/3000 [27:23<42:13,  1.39s/it, lr: 1.0e-04 loss: 5.868e-01]
latex_v1:  39%|###9      | 1175/3000 [27:24<42:13,  1.39s/it, lr: 1.0e-04 loss: 1.825e-01]
latex_v1:  39%|###9      | 1175/3000 [27:24<42:13,  1.39s/it, lr: 1.0e-04 loss: 1.825e-01]
latex_v1:  39%|###9      | 1176/3000 [27:24<44:45,  1.47s/it, lr: 1.0e-04 loss: 1.825e-01]
latex_v1:  39%|###9      | 1176/3000 [27:24<44:45,  1.47s/it, lr: 1.0e-04 loss: 1.825e-01]
latex_v1:  39%|###9      | 1176/3000 [27:25<44:45,  1.47s/it, lr: 1.0e-04 loss: 3.572e-01]
latex_v1:  39%|###9      | 1176/3000 [27:25<44:45,  1.47s/it, lr: 1.0e-04 loss: 3.572e-01]
latex_v1:  39%|###9      | 1177/3000 [27:25<38:22,  1.26s/it, lr: 1.0e-04 loss: 3.572e-01]
latex_v1:  39%|###9      | 1177/3000 [27:25<38:22,  1.26s/it, lr: 1.0e-04 loss: 3.572e-01]
latex_v1:  39%|###9      | 1177/3000 [27:26<38:22,  1.26s/it, lr: 1.0e-04 loss: 5.434e-01]
latex_v1:  39%|###9      | 1177/3000 [27:26<38:22,  1.26s/it, lr: 1.0e-04 loss: 5.434e-01]
latex_v1:  39%|###9      | 1178/3000 [27:26<33:56,  1.12s/it, lr: 1.0e-04 loss: 5.434e-01]
latex_v1:  39%|###9      | 1178/3000 [27:26<33:56,  1.12s/it, lr: 1.0e-04 loss: 5.434e-01]
latex_v1:  39%|###9      | 1178/3000 [27:27<33:56,  1.12s/it, lr: 1.0e-04 loss: 1.402e-01]
latex_v1:  39%|###9      | 1178/3000 [27:27<33:56,  1.12s/it, lr: 1.0e-04 loss: 1.402e-01]
latex_v1:  39%|###9      | 1179/3000 [27:27<36:13,  1.19s/it, lr: 1.0e-04 loss: 1.402e-01]
latex_v1:  39%|###9      | 1179/3000 [27:27<36:13,  1.19s/it, lr: 1.0e-04 loss: 1.402e-01]
latex_v1:  39%|###9      | 1179/3000 [27:28<36:13,  1.19s/it, lr: 1.0e-04 loss: 3.469e-01]
latex_v1:  39%|###9      | 1179/3000 [27:28<36:13,  1.19s/it, lr: 1.0e-04 loss: 3.469e-01]
latex_v1:  39%|###9      | 1180/3000 [27:31<36:11,  1.19s/it, lr: 1.0e-04 loss: 1.882e-01]
latex_v1:  39%|###9      | 1180/3000 [27:31<36:11,  1.19s/it, lr: 1.0e-04 loss: 1.882e-01]
latex_v1:  39%|###9      | 1181/3000 [27:31<39:15,  1.30s/it, lr: 1.0e-04 loss: 1.882e-01]
latex_v1:  39%|###9      | 1181/3000 [27:31<39:15,  1.30s/it, lr: 1.0e-04 loss: 1.882e-01]
latex_v1:  39%|###9      | 1181/3000 [27:32<39:15,  1.30s/it, lr: 1.0e-04 loss: 7.976e-01]
latex_v1:  39%|###9      | 1181/3000 [27:32<39:15,  1.30s/it, lr: 1.0e-04 loss: 7.976e-01]
latex_v1:  39%|###9      | 1182/3000 [27:32<36:46,  1.21s/it, lr: 1.0e-04 loss: 7.976e-01]
latex_v1:  39%|###9      | 1182/3000 [27:32<36:46,  1.21s/it, lr: 1.0e-04 loss: 7.976e-01]
latex_v1:  39%|###9      | 1182/3000 [27:33<36:46,  1.21s/it, lr: 1.0e-04 loss: 2.834e-01]
latex_v1:  39%|###9      | 1182/3000 [27:33<36:46,  1.21s/it, lr: 1.0e-04 loss: 2.834e-01]
latex_v1:  39%|###9      | 1183/3000 [27:33<39:41,  1.31s/it, lr: 1.0e-04 loss: 2.834e-01]
latex_v1:  39%|###9      | 1183/3000 [27:33<39:41,  1.31s/it, lr: 1.0e-04 loss: 2.834e-01]
latex_v1:  39%|###9      | 1183/3000 [27:35<39:41,  1.31s/it, lr: 1.0e-04 loss: 3.387e-01]
latex_v1:  39%|###9      | 1183/3000 [27:35<39:41,  1.31s/it, lr: 1.0e-04 loss: 3.387e-01]
latex_v1:  39%|###9      | 1184/3000 [27:35<41:29,  1.37s/it, lr: 1.0e-04 loss: 3.387e-01]
latex_v1:  39%|###9      | 1184/3000 [27:35<41:29,  1.37s/it, lr: 1.0e-04 loss: 3.387e-01]
latex_v1:  39%|###9      | 1184/3000 [27:37<41:29,  1.37s/it, lr: 1.0e-04 loss: 1.087e-01]
latex_v1:  39%|###9      | 1184/3000 [27:37<41:29,  1.37s/it, lr: 1.0e-04 loss: 1.087e-01]
latex_v1:  40%|###9      | 1185/3000 [27:37<45:40,  1.51s/it, lr: 1.0e-04 loss: 1.087e-01]
latex_v1:  40%|###9      | 1185/3000 [27:37<45:40,  1.51s/it, lr: 1.0e-04 loss: 1.087e-01]
latex_v1:  40%|###9      | 1185/3000 [27:38<45:40,  1.51s/it, lr: 1.0e-04 loss: 5.836e-01]
latex_v1:  40%|###9      | 1185/3000 [27:38<45:40,  1.51s/it, lr: 1.0e-04 loss: 5.836e-01]
latex_v1:  40%|###9      | 1186/3000 [27:38<45:18,  1.50s/it, lr: 1.0e-04 loss: 5.836e-01]
latex_v1:  40%|###9      | 1186/3000 [27:38<45:18,  1.50s/it, lr: 1.0e-04 loss: 5.836e-01]
latex_v1:  40%|###9      | 1186/3000 [27:40<45:18,  1.50s/it, lr: 1.0e-04 loss: 3.597e-01]
latex_v1:  40%|###9      | 1186/3000 [27:40<45:18,  1.50s/it, lr: 1.0e-04 loss: 3.597e-01]
latex_v1:  40%|###9      | 1187/3000 [27:40<49:37,  1.64s/it, lr: 1.0e-04 loss: 3.597e-01]
latex_v1:  40%|###9      | 1187/3000 [27:40<49:37,  1.64s/it, lr: 1.0e-04 loss: 3.597e-01]
latex_v1:  40%|###9      | 1187/3000 [27:42<49:37,  1.64s/it, lr: 1.0e-04 loss: 9.854e-02]
latex_v1:  40%|###9      | 1187/3000 [27:42<49:37,  1.64s/it, lr: 1.0e-04 loss: 9.854e-02]
latex_v1:  40%|###9      | 1188/3000 [27:42<48:52,  1.62s/it, lr: 1.0e-04 loss: 9.854e-02]
latex_v1:  40%|###9      | 1188/3000 [27:42<48:52,  1.62s/it, lr: 1.0e-04 loss: 9.854e-02]
latex_v1:  40%|###9      | 1188/3000 [27:43<48:52,  1.62s/it, lr: 1.0e-04 loss: 3.636e-01]
latex_v1:  40%|###9      | 1188/3000 [27:43<48:52,  1.62s/it, lr: 1.0e-04 loss: 3.636e-01]
latex_v1:  40%|###9      | 1189/3000 [27:43<42:55,  1.42s/it, lr: 1.0e-04 loss: 3.636e-01]
latex_v1:  40%|###9      | 1189/3000 [27:43<42:55,  1.42s/it, lr: 1.0e-04 loss: 3.636e-01]
latex_v1:  40%|###9      | 1189/3000 [27:44<42:55,  1.42s/it, lr: 1.0e-04 loss: 5.588e-02]
latex_v1:  40%|###9      | 1189/3000 [27:44<42:55,  1.42s/it, lr: 1.0e-04 loss: 5.588e-02]
latex_v1:  40%|###9      | 1190/3000 [27:46<42:54,  1.42s/it, lr: 1.0e-04 loss: 3.142e-01]
latex_v1:  40%|###9      | 1190/3000 [27:46<42:54,  1.42s/it, lr: 1.0e-04 loss: 3.142e-01]
latex_v1:  40%|###9      | 1191/3000 [27:46<43:20,  1.44s/it, lr: 1.0e-04 loss: 3.142e-01]
latex_v1:  40%|###9      | 1191/3000 [27:46<43:20,  1.44s/it, lr: 1.0e-04 loss: 3.142e-01]
latex_v1:  40%|###9      | 1191/3000 [27:48<43:20,  1.44s/it, lr: 1.0e-04 loss: 4.508e-01]
latex_v1:  40%|###9      | 1191/3000 [27:48<43:20,  1.44s/it, lr: 1.0e-04 loss: 4.508e-01]
latex_v1:  40%|###9      | 1192/3000 [27:48<43:24,  1.44s/it, lr: 1.0e-04 loss: 4.508e-01]
latex_v1:  40%|###9      | 1192/3000 [27:48<43:24,  1.44s/it, lr: 1.0e-04 loss: 4.508e-01]
latex_v1:  40%|###9      | 1192/3000 [27:51<43:24,  1.44s/it, lr: 1.0e-04 loss: 6.359e-02]
latex_v1:  40%|###9      | 1192/3000 [27:51<43:24,  1.44s/it, lr: 1.0e-04 loss: 6.359e-02]
latex_v1:  40%|###9      | 1193/3000 [27:51<52:56,  1.76s/it, lr: 1.0e-04 loss: 6.359e-02]
latex_v1:  40%|###9      | 1193/3000 [27:51<52:56,  1.76s/it, lr: 1.0e-04 loss: 6.359e-02]
latex_v1:  40%|###9      | 1193/3000 [27:51<52:56,  1.76s/it, lr: 1.0e-04 loss: 6.175e-01]
latex_v1:  40%|###9      | 1193/3000 [27:51<52:56,  1.76s/it, lr: 1.0e-04 loss: 6.175e-01]
latex_v1:  40%|###9      | 1194/3000 [27:51<44:42,  1.49s/it, lr: 1.0e-04 loss: 6.175e-01]
latex_v1:  40%|###9      | 1194/3000 [27:51<44:42,  1.49s/it, lr: 1.0e-04 loss: 6.175e-01]
latex_v1:  40%|###9      | 1194/3000 [27:52<44:42,  1.49s/it, lr: 1.0e-04 loss: 9.034e-02]
latex_v1:  40%|###9      | 1194/3000 [27:52<44:42,  1.49s/it, lr: 1.0e-04 loss: 9.034e-02]
latex_v1:  40%|###9      | 1195/3000 [27:52<38:25,  1.28s/it, lr: 1.0e-04 loss: 9.034e-02]
latex_v1:  40%|###9      | 1195/3000 [27:52<38:25,  1.28s/it, lr: 1.0e-04 loss: 9.034e-02]
latex_v1:  40%|###9      | 1195/3000 [27:53<38:25,  1.28s/it, lr: 1.0e-04 loss: 6.600e-01]
latex_v1:  40%|###9      | 1195/3000 [27:53<38:25,  1.28s/it, lr: 1.0e-04 loss: 6.600e-01]
latex_v1:  40%|###9      | 1196/3000 [27:53<33:49,  1.13s/it, lr: 1.0e-04 loss: 6.600e-01]
latex_v1:  40%|###9      | 1196/3000 [27:53<33:49,  1.13s/it, lr: 1.0e-04 loss: 6.600e-01]
latex_v1:  40%|###9      | 1196/3000 [27:54<33:49,  1.13s/it, lr: 1.0e-04 loss: 3.959e-01]
latex_v1:  40%|###9      | 1196/3000 [27:54<33:49,  1.13s/it, lr: 1.0e-04 loss: 3.959e-01]
latex_v1:  40%|###9      | 1197/3000 [27:54<30:31,  1.02s/it, lr: 1.0e-04 loss: 3.959e-01]
latex_v1:  40%|###9      | 1197/3000 [27:54<30:31,  1.02s/it, lr: 1.0e-04 loss: 3.959e-01]
latex_v1:  40%|###9      | 1197/3000 [27:54<30:31,  1.02s/it, lr: 1.0e-04 loss: 3.433e-01]
latex_v1:  40%|###9      | 1197/3000 [27:54<30:31,  1.02s/it, lr: 1.0e-04 loss: 3.433e-01]
latex_v1:  40%|###9      | 1198/3000 [27:54<28:26,  1.06it/s, lr: 1.0e-04 loss: 3.433e-01]
latex_v1:  40%|###9      | 1198/3000 [27:54<28:26,  1.06it/s, lr: 1.0e-04 loss: 3.433e-01]
latex_v1:  40%|###9      | 1198/3000 [27:56<28:26,  1.06it/s, lr: 1.0e-04 loss: 1.386e-01]
latex_v1:  40%|###9      | 1198/3000 [27:56<28:26,  1.06it/s, lr: 1.0e-04 loss: 1.386e-01]
latex_v1:  40%|###9      | 1199/3000 [27:56<33:56,  1.13s/it, lr: 1.0e-04 loss: 1.386e-01]
latex_v1:  40%|###9      | 1199/3000 [27:56<33:56,  1.13s/it, lr: 1.0e-04 loss: 1.386e-01]
latex_v1:  40%|###9      | 1199/3000 [27:59<33:56,  1.13s/it, lr: 1.0e-04 loss: 1.437e-01]
latex_v1:  40%|###9      | 1199/3000 [27:59<33:56,  1.13s/it, lr: 1.0e-04 loss: 1.437e-01]Unloading assistant lora



Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]


Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.40s/it]
Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.40s/it]


Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.40s/it]
Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.40s/it]


Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.40s/it]
Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.40s/it]


Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.40s/it]
Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.40s/it]


Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.40s/it]
Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.40s/it]


Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.40s/it]
Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.40s/it]


Generating Images: 100%|##########| 7/7 [00:16<00:00,  2.40s/it]
Generating Images: 100%|##########| 7/7 [00:16<00:00,  2.40s/it]


                                                                
                                                                Loading assistant lora

latex_v1:  40%|####      | 1200/3000 [28:01<33:55,  1.13s/it, lr: 1.0e-04 loss: 2.817e-01]
latex_v1:  40%|####      | 1200/3000 [28:01<33:55,  1.13s/it, lr: 1.0e-04 loss: 2.817e-01]
latex_v1:  40%|####      | 1201/3000 [28:01<33:31,  1.12s/it, lr: 1.0e-04 loss: 2.817e-01]
latex_v1:  40%|####      | 1201/3000 [28:01<33:31,  1.12s/it, lr: 1.0e-04 loss: 2.817e-01]
latex_v1:  40%|####      | 1201/3000 [28:02<33:31,  1.12s/it, lr: 1.0e-04 loss: 8.591e-01]
latex_v1:  40%|####      | 1201/3000 [28:02<33:31,  1.12s/it, lr: 1.0e-04 loss: 8.591e-01]
latex_v1:  40%|####      | 1202/3000 [28:02<32:20,  1.08s/it, lr: 1.0e-04 loss: 8.591e-01]
latex_v1:  40%|####      | 1202/3000 [28:02<32:20,  1.08s/it, lr: 1.0e-04 loss: 8.591e-01]
latex_v1:  40%|####      | 1202/3000 [28:03<32:20,  1.08s/it, lr: 1.0e-04 loss: 1.136e-01]
latex_v1:  40%|####      | 1202/3000 [28:03<32:20,  1.08s/it, lr: 1.0e-04 loss: 1.136e-01]
latex_v1:  40%|####      | 1203/3000 [28:03<35:06,  1.17s/it, lr: 1.0e-04 loss: 1.136e-01]
latex_v1:  40%|####      | 1203/3000 [28:03<35:06,  1.17s/it, lr: 1.0e-04 loss: 1.136e-01]
latex_v1:  40%|####      | 1203/3000 [28:05<35:06,  1.17s/it, lr: 1.0e-04 loss: 8.646e-02]
latex_v1:  40%|####      | 1203/3000 [28:05<35:06,  1.17s/it, lr: 1.0e-04 loss: 8.646e-02]
latex_v1:  40%|####      | 1204/3000 [28:05<40:49,  1.36s/it, lr: 1.0e-04 loss: 8.646e-02]
latex_v1:  40%|####      | 1204/3000 [28:05<40:49,  1.36s/it, lr: 1.0e-04 loss: 8.646e-02]
latex_v1:  40%|####      | 1204/3000 [28:06<40:49,  1.36s/it, lr: 1.0e-04 loss: 1.273e-01]
latex_v1:  40%|####      | 1204/3000 [28:06<40:49,  1.36s/it, lr: 1.0e-04 loss: 1.273e-01]
latex_v1:  40%|####      | 1205/3000 [28:06<35:39,  1.19s/it, lr: 1.0e-04 loss: 1.273e-01]
latex_v1:  40%|####      | 1205/3000 [28:06<35:39,  1.19s/it, lr: 1.0e-04 loss: 1.273e-01]
latex_v1:  40%|####      | 1205/3000 [28:07<35:39,  1.19s/it, lr: 1.0e-04 loss: 1.382e-01]
latex_v1:  40%|####      | 1205/3000 [28:07<35:39,  1.19s/it, lr: 1.0e-04 loss: 1.382e-01]
latex_v1:  40%|####      | 1206/3000 [28:07<31:52,  1.07s/it, lr: 1.0e-04 loss: 1.382e-01]
latex_v1:  40%|####      | 1206/3000 [28:07<31:52,  1.07s/it, lr: 1.0e-04 loss: 1.382e-01]
latex_v1:  40%|####      | 1206/3000 [28:08<31:52,  1.07s/it, lr: 1.0e-04 loss: 5.265e-01]
latex_v1:  40%|####      | 1206/3000 [28:08<31:52,  1.07s/it, lr: 1.0e-04 loss: 5.265e-01]
latex_v1:  40%|####      | 1207/3000 [28:08<37:39,  1.26s/it, lr: 1.0e-04 loss: 5.265e-01]
latex_v1:  40%|####      | 1207/3000 [28:08<37:39,  1.26s/it, lr: 1.0e-04 loss: 5.265e-01]
latex_v1:  40%|####      | 1207/3000 [28:10<37:39,  1.26s/it, lr: 1.0e-04 loss: 4.412e-01]
latex_v1:  40%|####      | 1207/3000 [28:10<37:39,  1.26s/it, lr: 1.0e-04 loss: 4.412e-01]
latex_v1:  40%|####      | 1208/3000 [28:10<39:25,  1.32s/it, lr: 1.0e-04 loss: 4.412e-01]
latex_v1:  40%|####      | 1208/3000 [28:10<39:25,  1.32s/it, lr: 1.0e-04 loss: 4.412e-01]
latex_v1:  40%|####      | 1208/3000 [28:12<39:25,  1.32s/it, lr: 1.0e-04 loss: 6.201e-02]
latex_v1:  40%|####      | 1208/3000 [28:12<39:25,  1.32s/it, lr: 1.0e-04 loss: 6.201e-02]
latex_v1:  40%|####      | 1209/3000 [28:12<41:35,  1.39s/it, lr: 1.0e-04 loss: 6.201e-02]
latex_v1:  40%|####      | 1209/3000 [28:12<41:35,  1.39s/it, lr: 1.0e-04 loss: 6.201e-02]
latex_v1:  40%|####      | 1209/3000 [28:14<41:35,  1.39s/it, lr: 1.0e-04 loss: 2.295e-01]
latex_v1:  40%|####      | 1209/3000 [28:14<41:35,  1.39s/it, lr: 1.0e-04 loss: 2.295e-01]
latex_v1:  40%|####      | 1210/3000 [28:15<41:34,  1.39s/it, lr: 1.0e-04 loss: 2.912e-01]
latex_v1:  40%|####      | 1210/3000 [28:15<41:34,  1.39s/it, lr: 1.0e-04 loss: 2.912e-01]
latex_v1:  40%|####      | 1211/3000 [28:15<32:32,  1.09s/it, lr: 1.0e-04 loss: 2.912e-01]
latex_v1:  40%|####      | 1211/3000 [28:15<32:32,  1.09s/it, lr: 1.0e-04 loss: 2.912e-01]
latex_v1:  40%|####      | 1211/3000 [28:18<32:32,  1.09s/it, lr: 1.0e-04 loss: 2.322e-01]
latex_v1:  40%|####      | 1211/3000 [28:18<32:32,  1.09s/it, lr: 1.0e-04 loss: 2.322e-01]
latex_v1:  40%|####      | 1212/3000 [28:18<45:20,  1.52s/it, lr: 1.0e-04 loss: 2.322e-01]
latex_v1:  40%|####      | 1212/3000 [28:18<45:20,  1.52s/it, lr: 1.0e-04 loss: 2.322e-01]
latex_v1:  40%|####      | 1212/3000 [28:20<45:20,  1.52s/it, lr: 1.0e-04 loss: 3.179e-01]
latex_v1:  40%|####      | 1212/3000 [28:20<45:20,  1.52s/it, lr: 1.0e-04 loss: 3.179e-01]
latex_v1:  40%|####      | 1213/3000 [28:20<44:41,  1.50s/it, lr: 1.0e-04 loss: 3.179e-01]
latex_v1:  40%|####      | 1213/3000 [28:20<44:41,  1.50s/it, lr: 1.0e-04 loss: 3.179e-01]
latex_v1:  40%|####      | 1213/3000 [28:20<44:41,  1.50s/it, lr: 1.0e-04 loss: 2.214e-01]
latex_v1:  40%|####      | 1213/3000 [28:20<44:41,  1.50s/it, lr: 1.0e-04 loss: 2.214e-01]
latex_v1:  40%|####      | 1214/3000 [28:20<38:34,  1.30s/it, lr: 1.0e-04 loss: 2.214e-01]
latex_v1:  40%|####      | 1214/3000 [28:20<38:34,  1.30s/it, lr: 1.0e-04 loss: 2.214e-01]
latex_v1:  40%|####      | 1214/3000 [28:22<38:34,  1.30s/it, lr: 1.0e-04 loss: 5.322e-01]
latex_v1:  40%|####      | 1214/3000 [28:22<38:34,  1.30s/it, lr: 1.0e-04 loss: 5.322e-01]
latex_v1:  40%|####      | 1215/3000 [28:22<39:06,  1.31s/it, lr: 1.0e-04 loss: 5.322e-01]
latex_v1:  40%|####      | 1215/3000 [28:22<39:06,  1.31s/it, lr: 1.0e-04 loss: 5.322e-01]
latex_v1:  40%|####      | 1215/3000 [28:23<39:06,  1.31s/it, lr: 1.0e-04 loss: 1.781e-02]
latex_v1:  40%|####      | 1215/3000 [28:23<39:06,  1.31s/it, lr: 1.0e-04 loss: 1.781e-02]
latex_v1:  41%|####      | 1216/3000 [28:23<39:53,  1.34s/it, lr: 1.0e-04 loss: 1.781e-02]
latex_v1:  41%|####      | 1216/3000 [28:23<39:53,  1.34s/it, lr: 1.0e-04 loss: 1.781e-02]
latex_v1:  41%|####      | 1216/3000 [28:24<39:53,  1.34s/it, lr: 1.0e-04 loss: 5.822e-01]
latex_v1:  41%|####      | 1216/3000 [28:24<39:53,  1.34s/it, lr: 1.0e-04 loss: 5.822e-01]
latex_v1:  41%|####      | 1217/3000 [28:24<34:53,  1.17s/it, lr: 1.0e-04 loss: 5.822e-01]
latex_v1:  41%|####      | 1217/3000 [28:24<34:53,  1.17s/it, lr: 1.0e-04 loss: 5.822e-01]
latex_v1:  41%|####      | 1217/3000 [28:25<34:53,  1.17s/it, lr: 1.0e-04 loss: 3.789e-01]
latex_v1:  41%|####      | 1217/3000 [28:25<34:53,  1.17s/it, lr: 1.0e-04 loss: 3.789e-01]
latex_v1:  41%|####      | 1218/3000 [28:25<31:23,  1.06s/it, lr: 1.0e-04 loss: 3.789e-01]
latex_v1:  41%|####      | 1218/3000 [28:25<31:23,  1.06s/it, lr: 1.0e-04 loss: 3.789e-01]
latex_v1:  41%|####      | 1218/3000 [28:25<31:23,  1.06s/it, lr: 1.0e-04 loss: 1.671e-01]
latex_v1:  41%|####      | 1218/3000 [28:25<31:23,  1.06s/it, lr: 1.0e-04 loss: 1.671e-01]
latex_v1:  41%|####      | 1219/3000 [28:25<28:59,  1.02it/s, lr: 1.0e-04 loss: 1.671e-01]
latex_v1:  41%|####      | 1219/3000 [28:25<28:59,  1.02it/s, lr: 1.0e-04 loss: 1.671e-01]
latex_v1:  41%|####      | 1219/3000 [28:26<28:59,  1.02it/s, lr: 1.0e-04 loss: 6.138e-01]
latex_v1:  41%|####      | 1219/3000 [28:26<28:59,  1.02it/s, lr: 1.0e-04 loss: 6.138e-01]
latex_v1:  41%|####      | 1220/3000 [28:28<28:58,  1.02it/s, lr: 1.0e-04 loss: 1.079e-01]
latex_v1:  41%|####      | 1220/3000 [28:28<28:58,  1.02it/s, lr: 1.0e-04 loss: 1.079e-01]
latex_v1:  41%|####      | 1221/3000 [28:28<26:03,  1.14it/s, lr: 1.0e-04 loss: 1.079e-01]
latex_v1:  41%|####      | 1221/3000 [28:28<26:03,  1.14it/s, lr: 1.0e-04 loss: 1.079e-01]
latex_v1:  41%|####      | 1221/3000 [28:30<26:03,  1.14it/s, lr: 1.0e-04 loss: 3.010e-01]
latex_v1:  41%|####      | 1221/3000 [28:30<26:03,  1.14it/s, lr: 1.0e-04 loss: 3.010e-01]
latex_v1:  41%|####      | 1222/3000 [28:30<40:13,  1.36s/it, lr: 1.0e-04 loss: 3.010e-01]
latex_v1:  41%|####      | 1222/3000 [28:30<40:13,  1.36s/it, lr: 1.0e-04 loss: 3.010e-01]
latex_v1:  41%|####      | 1222/3000 [28:32<40:13,  1.36s/it, lr: 1.0e-04 loss: 1.677e-01]
latex_v1:  41%|####      | 1222/3000 [28:32<40:13,  1.36s/it, lr: 1.0e-04 loss: 1.677e-01]
latex_v1:  41%|####      | 1223/3000 [28:32<40:53,  1.38s/it, lr: 1.0e-04 loss: 1.677e-01]
latex_v1:  41%|####      | 1223/3000 [28:32<40:53,  1.38s/it, lr: 1.0e-04 loss: 1.677e-01]
latex_v1:  41%|####      | 1223/3000 [28:34<40:53,  1.38s/it, lr: 1.0e-04 loss: 1.165e-01]
latex_v1:  41%|####      | 1223/3000 [28:34<40:53,  1.38s/it, lr: 1.0e-04 loss: 1.165e-01]
latex_v1:  41%|####      | 1224/3000 [28:34<44:49,  1.51s/it, lr: 1.0e-04 loss: 1.165e-01]
latex_v1:  41%|####      | 1224/3000 [28:34<44:49,  1.51s/it, lr: 1.0e-04 loss: 1.165e-01]
latex_v1:  41%|####      | 1224/3000 [28:35<44:49,  1.51s/it, lr: 1.0e-04 loss: 1.831e-01]
latex_v1:  41%|####      | 1224/3000 [28:35<44:49,  1.51s/it, lr: 1.0e-04 loss: 1.831e-01]
latex_v1:  41%|####      | 1225/3000 [28:35<38:26,  1.30s/it, lr: 1.0e-04 loss: 1.831e-01]
latex_v1:  41%|####      | 1225/3000 [28:35<38:26,  1.30s/it, lr: 1.0e-04 loss: 1.831e-01]
latex_v1:  41%|####      | 1225/3000 [28:35<38:26,  1.30s/it, lr: 1.0e-04 loss: 2.585e-01]
latex_v1:  41%|####      | 1225/3000 [28:35<38:26,  1.30s/it, lr: 1.0e-04 loss: 2.585e-01]
latex_v1:  41%|####      | 1226/3000 [28:35<33:54,  1.15s/it, lr: 1.0e-04 loss: 2.585e-01]
latex_v1:  41%|####      | 1226/3000 [28:35<33:54,  1.15s/it, lr: 1.0e-04 loss: 2.585e-01]
latex_v1:  41%|####      | 1226/3000 [28:38<33:54,  1.15s/it, lr: 1.0e-04 loss: 4.217e-02]
latex_v1:  41%|####      | 1226/3000 [28:38<33:54,  1.15s/it, lr: 1.0e-04 loss: 4.217e-02]
latex_v1:  41%|####      | 1227/3000 [28:38<47:37,  1.61s/it, lr: 1.0e-04 loss: 4.217e-02]
latex_v1:  41%|####      | 1227/3000 [28:38<47:37,  1.61s/it, lr: 1.0e-04 loss: 4.217e-02]
latex_v1:  41%|####      | 1227/3000 [28:39<47:37,  1.61s/it, lr: 1.0e-04 loss: 2.647e-01]
latex_v1:  41%|####      | 1227/3000 [28:39<47:37,  1.61s/it, lr: 1.0e-04 loss: 2.647e-01]
latex_v1:  41%|####      | 1228/3000 [28:39<40:07,  1.36s/it, lr: 1.0e-04 loss: 2.647e-01]
latex_v1:  41%|####      | 1228/3000 [28:39<40:07,  1.36s/it, lr: 1.0e-04 loss: 2.647e-01]
latex_v1:  41%|####      | 1228/3000 [28:40<40:07,  1.36s/it, lr: 1.0e-04 loss: 5.056e-01]
latex_v1:  41%|####      | 1228/3000 [28:40<40:07,  1.36s/it, lr: 1.0e-04 loss: 5.056e-01]
latex_v1:  41%|####      | 1229/3000 [28:40<34:51,  1.18s/it, lr: 1.0e-04 loss: 5.056e-01]
latex_v1:  41%|####      | 1229/3000 [28:40<34:51,  1.18s/it, lr: 1.0e-04 loss: 5.056e-01]
latex_v1:  41%|####      | 1229/3000 [28:41<34:51,  1.18s/it, lr: 1.0e-04 loss: 8.154e-01]
latex_v1:  41%|####      | 1229/3000 [28:41<34:51,  1.18s/it, lr: 1.0e-04 loss: 8.154e-01]
latex_v1:  41%|####1     | 1230/3000 [28:41<34:50,  1.18s/it, lr: 1.0e-04 loss: 7.427e-02]
latex_v1:  41%|####1     | 1230/3000 [28:41<34:50,  1.18s/it, lr: 1.0e-04 loss: 7.427e-02]
latex_v1:  41%|####1     | 1231/3000 [28:41<25:21,  1.16it/s, lr: 1.0e-04 loss: 7.427e-02]
latex_v1:  41%|####1     | 1231/3000 [28:41<25:21,  1.16it/s, lr: 1.0e-04 loss: 7.427e-02]
latex_v1:  41%|####1     | 1231/3000 [28:43<25:21,  1.16it/s, lr: 1.0e-04 loss: 6.764e-01]
latex_v1:  41%|####1     | 1231/3000 [28:43<25:21,  1.16it/s, lr: 1.0e-04 loss: 6.764e-01]
latex_v1:  41%|####1     | 1232/3000 [28:43<29:13,  1.01it/s, lr: 1.0e-04 loss: 6.764e-01]
latex_v1:  41%|####1     | 1232/3000 [28:43<29:13,  1.01it/s, lr: 1.0e-04 loss: 6.764e-01]
latex_v1:  41%|####1     | 1232/3000 [28:44<29:13,  1.01it/s, lr: 1.0e-04 loss: 2.736e-02]
latex_v1:  41%|####1     | 1232/3000 [28:44<29:13,  1.01it/s, lr: 1.0e-04 loss: 2.736e-02]
latex_v1:  41%|####1     | 1233/3000 [28:44<33:37,  1.14s/it, lr: 1.0e-04 loss: 2.736e-02]
latex_v1:  41%|####1     | 1233/3000 [28:44<33:37,  1.14s/it, lr: 1.0e-04 loss: 2.736e-02]
latex_v1:  41%|####1     | 1233/3000 [28:46<33:37,  1.14s/it, lr: 1.0e-04 loss: 5.073e-01]
latex_v1:  41%|####1     | 1233/3000 [28:46<33:37,  1.14s/it, lr: 1.0e-04 loss: 5.073e-01]
latex_v1:  41%|####1     | 1234/3000 [28:46<36:41,  1.25s/it, lr: 1.0e-04 loss: 5.073e-01]
latex_v1:  41%|####1     | 1234/3000 [28:46<36:41,  1.25s/it, lr: 1.0e-04 loss: 5.073e-01]
latex_v1:  41%|####1     | 1234/3000 [28:47<36:41,  1.25s/it, lr: 1.0e-04 loss: 3.896e-01]
latex_v1:  41%|####1     | 1234/3000 [28:47<36:41,  1.25s/it, lr: 1.0e-04 loss: 3.896e-01]
latex_v1:  41%|####1     | 1235/3000 [28:47<32:29,  1.10s/it, lr: 1.0e-04 loss: 3.896e-01]
latex_v1:  41%|####1     | 1235/3000 [28:47<32:29,  1.10s/it, lr: 1.0e-04 loss: 3.896e-01]
latex_v1:  41%|####1     | 1235/3000 [28:48<32:29,  1.10s/it, lr: 1.0e-04 loss: 7.060e-01]
latex_v1:  41%|####1     | 1235/3000 [28:48<32:29,  1.10s/it, lr: 1.0e-04 loss: 7.060e-01]
latex_v1:  41%|####1     | 1236/3000 [28:48<35:08,  1.20s/it, lr: 1.0e-04 loss: 7.060e-01]
latex_v1:  41%|####1     | 1236/3000 [28:48<35:08,  1.20s/it, lr: 1.0e-04 loss: 7.060e-01]
latex_v1:  41%|####1     | 1236/3000 [28:49<35:08,  1.20s/it, lr: 1.0e-04 loss: 6.823e-01]
latex_v1:  41%|####1     | 1236/3000 [28:49<35:08,  1.20s/it, lr: 1.0e-04 loss: 6.823e-01]
latex_v1:  41%|####1     | 1237/3000 [28:49<35:01,  1.19s/it, lr: 1.0e-04 loss: 6.823e-01]
latex_v1:  41%|####1     | 1237/3000 [28:49<35:01,  1.19s/it, lr: 1.0e-04 loss: 6.823e-01]
latex_v1:  41%|####1     | 1237/3000 [28:51<35:01,  1.19s/it, lr: 1.0e-04 loss: 3.005e-01]
latex_v1:  41%|####1     | 1237/3000 [28:51<35:01,  1.19s/it, lr: 1.0e-04 loss: 3.005e-01]
latex_v1:  41%|####1     | 1238/3000 [28:51<37:53,  1.29s/it, lr: 1.0e-04 loss: 3.005e-01]
latex_v1:  41%|####1     | 1238/3000 [28:51<37:53,  1.29s/it, lr: 1.0e-04 loss: 3.005e-01]
latex_v1:  41%|####1     | 1238/3000 [28:52<37:53,  1.29s/it, lr: 1.0e-04 loss: 5.233e-01]
latex_v1:  41%|####1     | 1238/3000 [28:52<37:53,  1.29s/it, lr: 1.0e-04 loss: 5.233e-01]
latex_v1:  41%|####1     | 1239/3000 [28:52<33:12,  1.13s/it, lr: 1.0e-04 loss: 5.233e-01]
latex_v1:  41%|####1     | 1239/3000 [28:52<33:12,  1.13s/it, lr: 1.0e-04 loss: 5.233e-01]
latex_v1:  41%|####1     | 1239/3000 [28:53<33:12,  1.13s/it, lr: 1.0e-04 loss: 5.671e-01]
latex_v1:  41%|####1     | 1239/3000 [28:53<33:12,  1.13s/it, lr: 1.0e-04 loss: 5.671e-01]
latex_v1:  41%|####1     | 1240/3000 [28:55<33:11,  1.13s/it, lr: 1.0e-04 loss: 6.388e-01]
latex_v1:  41%|####1     | 1240/3000 [28:55<33:11,  1.13s/it, lr: 1.0e-04 loss: 6.388e-01]
latex_v1:  41%|####1     | 1241/3000 [28:55<29:22,  1.00s/it, lr: 1.0e-04 loss: 6.388e-01]
latex_v1:  41%|####1     | 1241/3000 [28:55<29:22,  1.00s/it, lr: 1.0e-04 loss: 6.388e-01]
latex_v1:  41%|####1     | 1241/3000 [28:56<29:22,  1.00s/it, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  41%|####1     | 1241/3000 [28:56<29:22,  1.00s/it, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  41%|####1     | 1242/3000 [28:56<27:33,  1.06it/s, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  41%|####1     | 1242/3000 [28:56<27:33,  1.06it/s, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  41%|####1     | 1242/3000 [28:58<27:33,  1.06it/s, lr: 1.0e-04 loss: 5.150e-01]
latex_v1:  41%|####1     | 1242/3000 [28:58<27:33,  1.06it/s, lr: 1.0e-04 loss: 5.150e-01]
latex_v1:  41%|####1     | 1243/3000 [28:58<42:17,  1.44s/it, lr: 1.0e-04 loss: 5.150e-01]
latex_v1:  41%|####1     | 1243/3000 [28:58<42:17,  1.44s/it, lr: 1.0e-04 loss: 5.150e-01]
latex_v1:  41%|####1     | 1243/3000 [29:01<42:17,  1.44s/it, lr: 1.0e-04 loss: 1.318e-01]
latex_v1:  41%|####1     | 1243/3000 [29:01<42:17,  1.44s/it, lr: 1.0e-04 loss: 1.318e-01]
latex_v1:  41%|####1     | 1244/3000 [29:01<53:34,  1.83s/it, lr: 1.0e-04 loss: 1.318e-01]
latex_v1:  41%|####1     | 1244/3000 [29:01<53:34,  1.83s/it, lr: 1.0e-04 loss: 1.318e-01]
latex_v1:  41%|####1     | 1244/3000 [29:02<53:34,  1.83s/it, lr: 1.0e-04 loss: 6.155e-01]
latex_v1:  41%|####1     | 1244/3000 [29:02<53:34,  1.83s/it, lr: 1.0e-04 loss: 6.155e-01]
latex_v1:  42%|####1     | 1245/3000 [29:02<48:05,  1.64s/it, lr: 1.0e-04 loss: 6.155e-01]
latex_v1:  42%|####1     | 1245/3000 [29:02<48:05,  1.64s/it, lr: 1.0e-04 loss: 6.155e-01]
latex_v1:  42%|####1     | 1245/3000 [29:03<48:05,  1.64s/it, lr: 1.0e-04 loss: 2.430e-01]
latex_v1:  42%|####1     | 1245/3000 [29:03<48:05,  1.64s/it, lr: 1.0e-04 loss: 2.430e-01]
latex_v1:  42%|####1     | 1246/3000 [29:03<40:34,  1.39s/it, lr: 1.0e-04 loss: 2.430e-01]
latex_v1:  42%|####1     | 1246/3000 [29:03<40:34,  1.39s/it, lr: 1.0e-04 loss: 2.430e-01]
latex_v1:  42%|####1     | 1246/3000 [29:04<40:34,  1.39s/it, lr: 1.0e-04 loss: 3.839e-01]
latex_v1:  42%|####1     | 1246/3000 [29:04<40:34,  1.39s/it, lr: 1.0e-04 loss: 3.839e-01]
latex_v1:  42%|####1     | 1247/3000 [29:04<38:46,  1.33s/it, lr: 1.0e-04 loss: 3.839e-01]
latex_v1:  42%|####1     | 1247/3000 [29:04<38:46,  1.33s/it, lr: 1.0e-04 loss: 3.839e-01]
latex_v1:  42%|####1     | 1247/3000 [29:05<38:46,  1.33s/it, lr: 1.0e-04 loss: 5.257e-01]
latex_v1:  42%|####1     | 1247/3000 [29:05<38:46,  1.33s/it, lr: 1.0e-04 loss: 5.257e-01]
latex_v1:  42%|####1     | 1248/3000 [29:05<33:53,  1.16s/it, lr: 1.0e-04 loss: 5.257e-01]
latex_v1:  42%|####1     | 1248/3000 [29:05<33:53,  1.16s/it, lr: 1.0e-04 loss: 5.257e-01]
latex_v1:  42%|####1     | 1248/3000 [29:06<33:53,  1.16s/it, lr: 1.0e-04 loss: 2.757e-01]
latex_v1:  42%|####1     | 1248/3000 [29:06<33:53,  1.16s/it, lr: 1.0e-04 loss: 2.757e-01]
latex_v1:  42%|####1     | 1249/3000 [29:06<30:17,  1.04s/it, lr: 1.0e-04 loss: 2.757e-01]
latex_v1:  42%|####1     | 1249/3000 [29:06<30:17,  1.04s/it, lr: 1.0e-04 loss: 2.757e-01]
latex_v1:  42%|####1     | 1249/3000 [29:07<30:17,  1.04s/it, lr: 1.0e-04 loss: 2.032e-01]
latex_v1:  42%|####1     | 1249/3000 [29:07<30:17,  1.04s/it, lr: 1.0e-04 loss: 2.032e-01]
Saving at step 1250
Saved checkpoint to /data/app/output/latex_v1/latex_v1_000001250.safetensors
Saved optimizer to /data/app/output/latex_v1/optimizer.pt
Removing old save: /data/app/output/latex_v1/latex_v1_000000250.safetensors

latex_v1:  42%|####1     | 1250/3000 [29:08<30:16,  1.04s/it, lr: 1.0e-04 loss: 4.709e-01]
latex_v1:  42%|####1     | 1250/3000 [29:08<30:16,  1.04s/it, lr: 1.0e-04 loss: 4.709e-01]
latex_v1:  42%|####1     | 1251/3000 [29:08<28:20,  1.03it/s, lr: 1.0e-04 loss: 4.709e-01]
latex_v1:  42%|####1     | 1251/3000 [29:08<28:20,  1.03it/s, lr: 1.0e-04 loss: 4.709e-01]
latex_v1:  42%|####1     | 1251/3000 [29:10<28:20,  1.03it/s, lr: 1.0e-04 loss: 4.296e-01]
latex_v1:  42%|####1     | 1251/3000 [29:10<28:20,  1.03it/s, lr: 1.0e-04 loss: 4.296e-01]
latex_v1:  42%|####1     | 1252/3000 [29:10<33:15,  1.14s/it, lr: 1.0e-04 loss: 4.296e-01]
latex_v1:  42%|####1     | 1252/3000 [29:10<33:15,  1.14s/it, lr: 1.0e-04 loss: 4.296e-01]
latex_v1:  42%|####1     | 1252/3000 [29:12<33:15,  1.14s/it, lr: 1.0e-04 loss: 2.261e-01]
latex_v1:  42%|####1     | 1252/3000 [29:12<33:15,  1.14s/it, lr: 1.0e-04 loss: 2.261e-01]
latex_v1:  42%|####1     | 1253/3000 [29:12<35:34,  1.22s/it, lr: 1.0e-04 loss: 2.261e-01]
latex_v1:  42%|####1     | 1253/3000 [29:12<35:34,  1.22s/it, lr: 1.0e-04 loss: 2.261e-01]
latex_v1:  42%|####1     | 1253/3000 [29:14<35:34,  1.22s/it, lr: 1.0e-04 loss: 2.323e-01]
latex_v1:  42%|####1     | 1253/3000 [29:14<35:34,  1.22s/it, lr: 1.0e-04 loss: 2.323e-01]
latex_v1:  42%|####1     | 1254/3000 [29:14<48:56,  1.68s/it, lr: 1.0e-04 loss: 2.323e-01]
latex_v1:  42%|####1     | 1254/3000 [29:14<48:56,  1.68s/it, lr: 1.0e-04 loss: 2.323e-01]
latex_v1:  42%|####1     | 1254/3000 [29:15<48:56,  1.68s/it, lr: 1.0e-04 loss: 1.641e-01]
latex_v1:  42%|####1     | 1254/3000 [29:15<48:56,  1.68s/it, lr: 1.0e-04 loss: 1.641e-01]
latex_v1:  42%|####1     | 1255/3000 [29:15<41:22,  1.42s/it, lr: 1.0e-04 loss: 1.641e-01]
latex_v1:  42%|####1     | 1255/3000 [29:15<41:22,  1.42s/it, lr: 1.0e-04 loss: 1.641e-01]
latex_v1:  42%|####1     | 1255/3000 [29:16<41:22,  1.42s/it, lr: 1.0e-04 loss: 5.927e-01]
latex_v1:  42%|####1     | 1255/3000 [29:16<41:22,  1.42s/it, lr: 1.0e-04 loss: 5.927e-01]
latex_v1:  42%|####1     | 1256/3000 [29:16<35:51,  1.23s/it, lr: 1.0e-04 loss: 5.927e-01]
latex_v1:  42%|####1     | 1256/3000 [29:16<35:51,  1.23s/it, lr: 1.0e-04 loss: 5.927e-01]
latex_v1:  42%|####1     | 1256/3000 [29:17<35:51,  1.23s/it, lr: 1.0e-04 loss: 8.708e-01]
latex_v1:  42%|####1     | 1256/3000 [29:17<35:51,  1.23s/it, lr: 1.0e-04 loss: 8.708e-01]
latex_v1:  42%|####1     | 1257/3000 [29:17<35:24,  1.22s/it, lr: 1.0e-04 loss: 8.708e-01]
latex_v1:  42%|####1     | 1257/3000 [29:17<35:24,  1.22s/it, lr: 1.0e-04 loss: 8.708e-01]
latex_v1:  42%|####1     | 1257/3000 [29:19<35:24,  1.22s/it, lr: 1.0e-04 loss: 4.269e-01]
latex_v1:  42%|####1     | 1257/3000 [29:19<35:24,  1.22s/it, lr: 1.0e-04 loss: 4.269e-01]
latex_v1:  42%|####1     | 1258/3000 [29:19<38:08,  1.31s/it, lr: 1.0e-04 loss: 4.269e-01]
latex_v1:  42%|####1     | 1258/3000 [29:19<38:08,  1.31s/it, lr: 1.0e-04 loss: 4.269e-01]
latex_v1:  42%|####1     | 1258/3000 [29:19<38:08,  1.31s/it, lr: 1.0e-04 loss: 6.874e-01]
latex_v1:  42%|####1     | 1258/3000 [29:19<38:08,  1.31s/it, lr: 1.0e-04 loss: 6.874e-01]
latex_v1:  42%|####1     | 1259/3000 [29:19<33:33,  1.16s/it, lr: 1.0e-04 loss: 6.874e-01]
latex_v1:  42%|####1     | 1259/3000 [29:19<33:33,  1.16s/it, lr: 1.0e-04 loss: 6.874e-01]
latex_v1:  42%|####1     | 1259/3000 [29:20<33:33,  1.16s/it, lr: 1.0e-04 loss: 9.221e-02]
latex_v1:  42%|####1     | 1259/3000 [29:20<33:33,  1.16s/it, lr: 1.0e-04 loss: 9.221e-02]
latex_v1:  42%|####2     | 1260/3000 [29:21<33:32,  1.16s/it, lr: 1.0e-04 loss: 4.183e-01]
latex_v1:  42%|####2     | 1260/3000 [29:21<33:32,  1.16s/it, lr: 1.0e-04 loss: 4.183e-01]
latex_v1:  42%|####2     | 1261/3000 [29:21<23:13,  1.25it/s, lr: 1.0e-04 loss: 4.183e-01]
latex_v1:  42%|####2     | 1261/3000 [29:21<23:13,  1.25it/s, lr: 1.0e-04 loss: 4.183e-01]
latex_v1:  42%|####2     | 1261/3000 [29:22<23:13,  1.25it/s, lr: 1.0e-04 loss: 2.342e-01]
latex_v1:  42%|####2     | 1261/3000 [29:22<23:13,  1.25it/s, lr: 1.0e-04 loss: 2.342e-01]
latex_v1:  42%|####2     | 1262/3000 [29:22<22:51,  1.27it/s, lr: 1.0e-04 loss: 2.342e-01]
latex_v1:  42%|####2     | 1262/3000 [29:22<22:51,  1.27it/s, lr: 1.0e-04 loss: 2.342e-01]
latex_v1:  42%|####2     | 1262/3000 [29:24<22:51,  1.27it/s, lr: 1.0e-04 loss: 3.704e-01]
latex_v1:  42%|####2     | 1262/3000 [29:24<22:51,  1.27it/s, lr: 1.0e-04 loss: 3.704e-01]
latex_v1:  42%|####2     | 1263/3000 [29:24<31:12,  1.08s/it, lr: 1.0e-04 loss: 3.704e-01]
latex_v1:  42%|####2     | 1263/3000 [29:24<31:12,  1.08s/it, lr: 1.0e-04 loss: 3.704e-01]
latex_v1:  42%|####2     | 1263/3000 [29:25<31:12,  1.08s/it, lr: 1.0e-04 loss: 2.114e-01]
latex_v1:  42%|####2     | 1263/3000 [29:25<31:12,  1.08s/it, lr: 1.0e-04 loss: 2.114e-01]
latex_v1:  42%|####2     | 1264/3000 [29:25<31:59,  1.11s/it, lr: 1.0e-04 loss: 2.114e-01]
latex_v1:  42%|####2     | 1264/3000 [29:25<31:59,  1.11s/it, lr: 1.0e-04 loss: 2.114e-01]
latex_v1:  42%|####2     | 1264/3000 [29:26<31:59,  1.11s/it, lr: 1.0e-04 loss: 6.016e-01]
latex_v1:  42%|####2     | 1264/3000 [29:26<31:59,  1.11s/it, lr: 1.0e-04 loss: 6.016e-01]
latex_v1:  42%|####2     | 1265/3000 [29:26<31:18,  1.08s/it, lr: 1.0e-04 loss: 6.016e-01]
latex_v1:  42%|####2     | 1265/3000 [29:26<31:18,  1.08s/it, lr: 1.0e-04 loss: 6.016e-01]
latex_v1:  42%|####2     | 1265/3000 [29:27<31:18,  1.08s/it, lr: 1.0e-04 loss: 3.200e-01]
latex_v1:  42%|####2     | 1265/3000 [29:27<31:18,  1.08s/it, lr: 1.0e-04 loss: 3.200e-01]
latex_v1:  42%|####2     | 1266/3000 [29:27<34:00,  1.18s/it, lr: 1.0e-04 loss: 3.200e-01]
latex_v1:  42%|####2     | 1266/3000 [29:27<34:00,  1.18s/it, lr: 1.0e-04 loss: 3.200e-01]
latex_v1:  42%|####2     | 1266/3000 [29:29<34:00,  1.18s/it, lr: 1.0e-04 loss: 1.521e-01]
latex_v1:  42%|####2     | 1266/3000 [29:29<34:00,  1.18s/it, lr: 1.0e-04 loss: 1.521e-01]
latex_v1:  42%|####2     | 1267/3000 [29:29<40:01,  1.39s/it, lr: 1.0e-04 loss: 1.521e-01]
latex_v1:  42%|####2     | 1267/3000 [29:29<40:01,  1.39s/it, lr: 1.0e-04 loss: 1.521e-01]
latex_v1:  42%|####2     | 1267/3000 [29:31<40:01,  1.39s/it, lr: 1.0e-04 loss: 5.172e-01]
latex_v1:  42%|####2     | 1267/3000 [29:31<40:01,  1.39s/it, lr: 1.0e-04 loss: 5.172e-01]
latex_v1:  42%|####2     | 1268/3000 [29:31<46:44,  1.62s/it, lr: 1.0e-04 loss: 5.172e-01]
latex_v1:  42%|####2     | 1268/3000 [29:31<46:44,  1.62s/it, lr: 1.0e-04 loss: 5.172e-01]
latex_v1:  42%|####2     | 1268/3000 [29:34<46:44,  1.62s/it, lr: 1.0e-04 loss: 3.803e-01]
latex_v1:  42%|####2     | 1268/3000 [29:34<46:44,  1.62s/it, lr: 1.0e-04 loss: 3.803e-01]
latex_v1:  42%|####2     | 1269/3000 [29:34<56:04,  1.94s/it, lr: 1.0e-04 loss: 3.803e-01]
latex_v1:  42%|####2     | 1269/3000 [29:34<56:04,  1.94s/it, lr: 1.0e-04 loss: 3.803e-01]
latex_v1:  42%|####2     | 1269/3000 [29:36<56:04,  1.94s/it, lr: 1.0e-04 loss: 3.206e-01]
latex_v1:  42%|####2     | 1269/3000 [29:36<56:04,  1.94s/it, lr: 1.0e-04 loss: 3.206e-01]
latex_v1:  42%|####2     | 1270/3000 [29:37<56:02,  1.94s/it, lr: 1.0e-04 loss: 3.087e-01]
latex_v1:  42%|####2     | 1270/3000 [29:37<56:02,  1.94s/it, lr: 1.0e-04 loss: 3.087e-01]
latex_v1:  42%|####2     | 1271/3000 [29:37<42:48,  1.49s/it, lr: 1.0e-04 loss: 3.087e-01]
latex_v1:  42%|####2     | 1271/3000 [29:37<42:48,  1.49s/it, lr: 1.0e-04 loss: 3.087e-01]
latex_v1:  42%|####2     | 1271/3000 [29:39<42:48,  1.49s/it, lr: 1.0e-04 loss: 2.042e-01]
latex_v1:  42%|####2     | 1271/3000 [29:39<42:48,  1.49s/it, lr: 1.0e-04 loss: 2.042e-01]
latex_v1:  42%|####2     | 1272/3000 [29:39<42:36,  1.48s/it, lr: 1.0e-04 loss: 2.042e-01]
latex_v1:  42%|####2     | 1272/3000 [29:39<42:36,  1.48s/it, lr: 1.0e-04 loss: 2.042e-01]
latex_v1:  42%|####2     | 1272/3000 [29:40<42:36,  1.48s/it, lr: 1.0e-04 loss: 6.617e-01]
latex_v1:  42%|####2     | 1272/3000 [29:40<42:36,  1.48s/it, lr: 1.0e-04 loss: 6.617e-01]
latex_v1:  42%|####2     | 1273/3000 [29:40<42:52,  1.49s/it, lr: 1.0e-04 loss: 6.617e-01]
latex_v1:  42%|####2     | 1273/3000 [29:40<42:52,  1.49s/it, lr: 1.0e-04 loss: 6.617e-01]
latex_v1:  42%|####2     | 1273/3000 [29:43<42:52,  1.49s/it, lr: 1.0e-04 loss: 5.648e-02]
latex_v1:  42%|####2     | 1273/3000 [29:43<42:52,  1.49s/it, lr: 1.0e-04 loss: 5.648e-02]
latex_v1:  42%|####2     | 1274/3000 [29:43<53:26,  1.86s/it, lr: 1.0e-04 loss: 5.648e-02]
latex_v1:  42%|####2     | 1274/3000 [29:43<53:26,  1.86s/it, lr: 1.0e-04 loss: 5.648e-02]
latex_v1:  42%|####2     | 1274/3000 [29:45<53:26,  1.86s/it, lr: 1.0e-04 loss: 6.997e-01]
latex_v1:  42%|####2     | 1274/3000 [29:45<53:26,  1.86s/it, lr: 1.0e-04 loss: 6.997e-01]
latex_v1:  42%|####2     | 1275/3000 [29:45<49:04,  1.71s/it, lr: 1.0e-04 loss: 6.997e-01]
latex_v1:  42%|####2     | 1275/3000 [29:45<49:04,  1.71s/it, lr: 1.0e-04 loss: 6.997e-01]
latex_v1:  42%|####2     | 1275/3000 [29:46<49:04,  1.71s/it, lr: 1.0e-04 loss: 1.577e-01]
latex_v1:  42%|####2     | 1275/3000 [29:46<49:04,  1.71s/it, lr: 1.0e-04 loss: 1.577e-01]
latex_v1:  43%|####2     | 1276/3000 [29:46<47:50,  1.66s/it, lr: 1.0e-04 loss: 1.577e-01]
latex_v1:  43%|####2     | 1276/3000 [29:46<47:50,  1.66s/it, lr: 1.0e-04 loss: 1.577e-01]
latex_v1:  43%|####2     | 1276/3000 [29:48<47:50,  1.66s/it, lr: 1.0e-04 loss: 7.671e-02]
latex_v1:  43%|####2     | 1276/3000 [29:48<47:50,  1.66s/it, lr: 1.0e-04 loss: 7.671e-02]
latex_v1:  43%|####2     | 1277/3000 [29:48<45:06,  1.57s/it, lr: 1.0e-04 loss: 7.671e-02]
latex_v1:  43%|####2     | 1277/3000 [29:48<45:06,  1.57s/it, lr: 1.0e-04 loss: 7.671e-02]
latex_v1:  43%|####2     | 1277/3000 [29:50<45:06,  1.57s/it, lr: 1.0e-04 loss: 6.009e-01]
latex_v1:  43%|####2     | 1277/3000 [29:50<45:06,  1.57s/it, lr: 1.0e-04 loss: 6.009e-01]
latex_v1:  43%|####2     | 1278/3000 [29:50<56:42,  1.98s/it, lr: 1.0e-04 loss: 6.009e-01]
latex_v1:  43%|####2     | 1278/3000 [29:50<56:42,  1.98s/it, lr: 1.0e-04 loss: 6.009e-01]
latex_v1:  43%|####2     | 1278/3000 [29:51<56:42,  1.98s/it, lr: 1.0e-04 loss: 4.371e-01]
latex_v1:  43%|####2     | 1278/3000 [29:51<56:42,  1.98s/it, lr: 1.0e-04 loss: 4.371e-01]
latex_v1:  43%|####2     | 1279/3000 [29:51<46:29,  1.62s/it, lr: 1.0e-04 loss: 4.371e-01]
latex_v1:  43%|####2     | 1279/3000 [29:51<46:29,  1.62s/it, lr: 1.0e-04 loss: 4.371e-01]
latex_v1:  43%|####2     | 1279/3000 [29:54<46:29,  1.62s/it, lr: 1.0e-04 loss: 1.837e-01]
latex_v1:  43%|####2     | 1279/3000 [29:54<46:29,  1.62s/it, lr: 1.0e-04 loss: 1.837e-01]
latex_v1:  43%|####2     | 1280/3000 [29:55<46:27,  1.62s/it, lr: 1.0e-04 loss: 3.241e-01]
latex_v1:  43%|####2     | 1280/3000 [29:55<46:27,  1.62s/it, lr: 1.0e-04 loss: 3.241e-01]
latex_v1:  43%|####2     | 1281/3000 [29:55<30:04,  1.05s/it, lr: 1.0e-04 loss: 3.241e-01]
latex_v1:  43%|####2     | 1281/3000 [29:55<30:04,  1.05s/it, lr: 1.0e-04 loss: 3.241e-01]
latex_v1:  43%|####2     | 1281/3000 [29:56<30:04,  1.05s/it, lr: 1.0e-04 loss: 1.961e-01]
latex_v1:  43%|####2     | 1281/3000 [29:56<30:04,  1.05s/it, lr: 1.0e-04 loss: 1.961e-01]
latex_v1:  43%|####2     | 1282/3000 [29:56<32:47,  1.15s/it, lr: 1.0e-04 loss: 1.961e-01]
latex_v1:  43%|####2     | 1282/3000 [29:56<32:47,  1.15s/it, lr: 1.0e-04 loss: 1.961e-01]
latex_v1:  43%|####2     | 1282/3000 [29:58<32:47,  1.15s/it, lr: 1.0e-04 loss: 4.747e-01]
latex_v1:  43%|####2     | 1282/3000 [29:58<32:47,  1.15s/it, lr: 1.0e-04 loss: 4.747e-01]
latex_v1:  43%|####2     | 1283/3000 [29:58<35:48,  1.25s/it, lr: 1.0e-04 loss: 4.747e-01]
latex_v1:  43%|####2     | 1283/3000 [29:58<35:48,  1.25s/it, lr: 1.0e-04 loss: 4.747e-01]
latex_v1:  43%|####2     | 1283/3000 [29:59<35:48,  1.25s/it, lr: 1.0e-04 loss: 6.123e-01]
latex_v1:  43%|####2     | 1283/3000 [29:59<35:48,  1.25s/it, lr: 1.0e-04 loss: 6.123e-01]
latex_v1:  43%|####2     | 1284/3000 [29:59<31:52,  1.11s/it, lr: 1.0e-04 loss: 6.123e-01]
latex_v1:  43%|####2     | 1284/3000 [29:59<31:52,  1.11s/it, lr: 1.0e-04 loss: 6.123e-01]
latex_v1:  43%|####2     | 1284/3000 [30:00<31:52,  1.11s/it, lr: 1.0e-04 loss: 5.910e-01]
latex_v1:  43%|####2     | 1284/3000 [30:00<31:52,  1.11s/it, lr: 1.0e-04 loss: 5.910e-01]
latex_v1:  43%|####2     | 1285/3000 [30:00<34:26,  1.20s/it, lr: 1.0e-04 loss: 5.910e-01]
latex_v1:  43%|####2     | 1285/3000 [30:00<34:26,  1.20s/it, lr: 1.0e-04 loss: 5.910e-01]
latex_v1:  43%|####2     | 1285/3000 [30:02<34:26,  1.20s/it, lr: 1.0e-04 loss: 3.449e-01]
latex_v1:  43%|####2     | 1285/3000 [30:02<34:26,  1.20s/it, lr: 1.0e-04 loss: 3.449e-01]
latex_v1:  43%|####2     | 1286/3000 [30:02<39:54,  1.40s/it, lr: 1.0e-04 loss: 3.449e-01]
latex_v1:  43%|####2     | 1286/3000 [30:02<39:54,  1.40s/it, lr: 1.0e-04 loss: 3.449e-01]
latex_v1:  43%|####2     | 1286/3000 [30:03<39:54,  1.40s/it, lr: 1.0e-04 loss: 7.378e-01]
latex_v1:  43%|####2     | 1286/3000 [30:03<39:54,  1.40s/it, lr: 1.0e-04 loss: 7.378e-01]
latex_v1:  43%|####2     | 1287/3000 [30:03<34:32,  1.21s/it, lr: 1.0e-04 loss: 7.378e-01]
latex_v1:  43%|####2     | 1287/3000 [30:03<34:32,  1.21s/it, lr: 1.0e-04 loss: 7.378e-01]
latex_v1:  43%|####2     | 1287/3000 [30:05<34:32,  1.21s/it, lr: 1.0e-04 loss: 2.894e-01]
latex_v1:  43%|####2     | 1287/3000 [30:05<34:32,  1.21s/it, lr: 1.0e-04 loss: 2.894e-01]
latex_v1:  43%|####2     | 1288/3000 [30:05<40:04,  1.40s/it, lr: 1.0e-04 loss: 2.894e-01]
latex_v1:  43%|####2     | 1288/3000 [30:05<40:04,  1.40s/it, lr: 1.0e-04 loss: 2.894e-01]
latex_v1:  43%|####2     | 1288/3000 [30:06<40:04,  1.40s/it, lr: 1.0e-04 loss: 7.715e-02]
latex_v1:  43%|####2     | 1288/3000 [30:06<40:04,  1.40s/it, lr: 1.0e-04 loss: 7.715e-02]
latex_v1:  43%|####2     | 1289/3000 [30:06<40:41,  1.43s/it, lr: 1.0e-04 loss: 7.715e-02]
latex_v1:  43%|####2     | 1289/3000 [30:06<40:41,  1.43s/it, lr: 1.0e-04 loss: 7.715e-02]
latex_v1:  43%|####2     | 1289/3000 [30:08<40:41,  1.43s/it, lr: 1.0e-04 loss: 1.423e-01]
latex_v1:  43%|####2     | 1289/3000 [30:08<40:41,  1.43s/it, lr: 1.0e-04 loss: 1.423e-01]
latex_v1:  43%|####3     | 1290/3000 [30:09<40:40,  1.43s/it, lr: 1.0e-04 loss: 5.188e-01]
latex_v1:  43%|####3     | 1290/3000 [30:09<40:40,  1.43s/it, lr: 1.0e-04 loss: 5.188e-01]
latex_v1:  43%|####3     | 1291/3000 [30:09<34:14,  1.20s/it, lr: 1.0e-04 loss: 5.188e-01]
latex_v1:  43%|####3     | 1291/3000 [30:09<34:14,  1.20s/it, lr: 1.0e-04 loss: 5.188e-01]
latex_v1:  43%|####3     | 1291/3000 [30:11<34:14,  1.20s/it, lr: 1.0e-04 loss: 1.755e-01]
latex_v1:  43%|####3     | 1291/3000 [30:11<34:14,  1.20s/it, lr: 1.0e-04 loss: 1.755e-01]
latex_v1:  43%|####3     | 1292/3000 [30:11<36:27,  1.28s/it, lr: 1.0e-04 loss: 1.755e-01]
latex_v1:  43%|####3     | 1292/3000 [30:11<36:27,  1.28s/it, lr: 1.0e-04 loss: 1.755e-01]
latex_v1:  43%|####3     | 1292/3000 [30:12<36:27,  1.28s/it, lr: 1.0e-04 loss: 1.165e-01]
latex_v1:  43%|####3     | 1292/3000 [30:12<36:27,  1.28s/it, lr: 1.0e-04 loss: 1.165e-01]
latex_v1:  43%|####3     | 1293/3000 [30:12<32:33,  1.14s/it, lr: 1.0e-04 loss: 1.165e-01]
latex_v1:  43%|####3     | 1293/3000 [30:12<32:33,  1.14s/it, lr: 1.0e-04 loss: 1.165e-01]
latex_v1:  43%|####3     | 1293/3000 [30:13<32:33,  1.14s/it, lr: 1.0e-04 loss: 3.973e-01]
latex_v1:  43%|####3     | 1293/3000 [30:13<32:33,  1.14s/it, lr: 1.0e-04 loss: 3.973e-01]
latex_v1:  43%|####3     | 1294/3000 [30:13<35:31,  1.25s/it, lr: 1.0e-04 loss: 3.973e-01]
latex_v1:  43%|####3     | 1294/3000 [30:13<35:31,  1.25s/it, lr: 1.0e-04 loss: 3.973e-01]
latex_v1:  43%|####3     | 1294/3000 [30:14<35:31,  1.25s/it, lr: 1.0e-04 loss: 1.304e-01]
latex_v1:  43%|####3     | 1294/3000 [30:14<35:31,  1.25s/it, lr: 1.0e-04 loss: 1.304e-01]
latex_v1:  43%|####3     | 1295/3000 [30:14<31:32,  1.11s/it, lr: 1.0e-04 loss: 1.304e-01]
latex_v1:  43%|####3     | 1295/3000 [30:14<31:32,  1.11s/it, lr: 1.0e-04 loss: 1.304e-01]
latex_v1:  43%|####3     | 1295/3000 [30:15<31:32,  1.11s/it, lr: 1.0e-04 loss: 1.091e-01]
latex_v1:  43%|####3     | 1295/3000 [30:15<31:32,  1.11s/it, lr: 1.0e-04 loss: 1.091e-01]
latex_v1:  43%|####3     | 1296/3000 [30:15<33:14,  1.17s/it, lr: 1.0e-04 loss: 1.091e-01]
latex_v1:  43%|####3     | 1296/3000 [30:15<33:14,  1.17s/it, lr: 1.0e-04 loss: 1.091e-01]
latex_v1:  43%|####3     | 1296/3000 [30:16<33:14,  1.17s/it, lr: 1.0e-04 loss: 7.917e-01]
latex_v1:  43%|####3     | 1296/3000 [30:16<33:14,  1.17s/it, lr: 1.0e-04 loss: 7.917e-01]
latex_v1:  43%|####3     | 1297/3000 [30:16<29:49,  1.05s/it, lr: 1.0e-04 loss: 7.917e-01]
latex_v1:  43%|####3     | 1297/3000 [30:16<29:49,  1.05s/it, lr: 1.0e-04 loss: 7.917e-01]
latex_v1:  43%|####3     | 1297/3000 [30:17<29:49,  1.05s/it, lr: 1.0e-04 loss: 3.916e-01]
latex_v1:  43%|####3     | 1297/3000 [30:17<29:49,  1.05s/it, lr: 1.0e-04 loss: 3.916e-01]
latex_v1:  43%|####3     | 1298/3000 [30:17<27:14,  1.04it/s, lr: 1.0e-04 loss: 3.916e-01]
latex_v1:  43%|####3     | 1298/3000 [30:17<27:14,  1.04it/s, lr: 1.0e-04 loss: 3.916e-01]
latex_v1:  43%|####3     | 1298/3000 [30:18<27:14,  1.04it/s, lr: 1.0e-04 loss: 4.578e-01]
latex_v1:  43%|####3     | 1298/3000 [30:18<27:14,  1.04it/s, lr: 1.0e-04 loss: 4.578e-01]
latex_v1:  43%|####3     | 1299/3000 [30:18<28:06,  1.01it/s, lr: 1.0e-04 loss: 4.578e-01]
latex_v1:  43%|####3     | 1299/3000 [30:18<28:06,  1.01it/s, lr: 1.0e-04 loss: 4.578e-01]
latex_v1:  43%|####3     | 1299/3000 [30:19<28:06,  1.01it/s, lr: 1.0e-04 loss: 3.840e-01]
latex_v1:  43%|####3     | 1299/3000 [30:19<28:06,  1.01it/s, lr: 1.0e-04 loss: 3.840e-01]
latex_v1:  43%|####3     | 1300/3000 [30:20<28:05,  1.01it/s, lr: 1.0e-04 loss: 1.549e-01]
latex_v1:  43%|####3     | 1300/3000 [30:20<28:05,  1.01it/s, lr: 1.0e-04 loss: 1.549e-01]
latex_v1:  43%|####3     | 1301/3000 [30:20<20:05,  1.41it/s, lr: 1.0e-04 loss: 1.549e-01]
latex_v1:  43%|####3     | 1301/3000 [30:20<20:05,  1.41it/s, lr: 1.0e-04 loss: 1.549e-01]
latex_v1:  43%|####3     | 1301/3000 [30:21<20:05,  1.41it/s, lr: 1.0e-04 loss: 2.936e-01]
latex_v1:  43%|####3     | 1301/3000 [30:21<20:05,  1.41it/s, lr: 1.0e-04 loss: 2.936e-01]
latex_v1:  43%|####3     | 1302/3000 [30:21<20:52,  1.36it/s, lr: 1.0e-04 loss: 2.936e-01]
latex_v1:  43%|####3     | 1302/3000 [30:21<20:52,  1.36it/s, lr: 1.0e-04 loss: 2.936e-01]
latex_v1:  43%|####3     | 1302/3000 [30:22<20:52,  1.36it/s, lr: 1.0e-04 loss: 3.315e-01]
latex_v1:  43%|####3     | 1302/3000 [30:22<20:52,  1.36it/s, lr: 1.0e-04 loss: 3.315e-01]
latex_v1:  43%|####3     | 1303/3000 [30:22<22:32,  1.25it/s, lr: 1.0e-04 loss: 3.315e-01]
latex_v1:  43%|####3     | 1303/3000 [30:22<22:32,  1.25it/s, lr: 1.0e-04 loss: 3.315e-01]
latex_v1:  43%|####3     | 1303/3000 [30:23<22:32,  1.25it/s, lr: 1.0e-04 loss: 4.216e-01]
latex_v1:  43%|####3     | 1303/3000 [30:23<22:32,  1.25it/s, lr: 1.0e-04 loss: 4.216e-01]
latex_v1:  43%|####3     | 1304/3000 [30:23<23:49,  1.19it/s, lr: 1.0e-04 loss: 4.216e-01]
latex_v1:  43%|####3     | 1304/3000 [30:23<23:49,  1.19it/s, lr: 1.0e-04 loss: 4.216e-01]
latex_v1:  43%|####3     | 1304/3000 [30:24<23:49,  1.19it/s, lr: 1.0e-04 loss: 1.943e-01]
latex_v1:  43%|####3     | 1304/3000 [30:24<23:49,  1.19it/s, lr: 1.0e-04 loss: 1.943e-01]
latex_v1:  44%|####3     | 1305/3000 [30:24<25:33,  1.11it/s, lr: 1.0e-04 loss: 1.943e-01]
latex_v1:  44%|####3     | 1305/3000 [30:24<25:33,  1.11it/s, lr: 1.0e-04 loss: 1.943e-01]
latex_v1:  44%|####3     | 1305/3000 [30:25<25:33,  1.11it/s, lr: 1.0e-04 loss: 1.763e-01]
latex_v1:  44%|####3     | 1305/3000 [30:25<25:33,  1.11it/s, lr: 1.0e-04 loss: 1.763e-01]
latex_v1:  44%|####3     | 1306/3000 [30:25<24:12,  1.17it/s, lr: 1.0e-04 loss: 1.763e-01]
latex_v1:  44%|####3     | 1306/3000 [30:25<24:12,  1.17it/s, lr: 1.0e-04 loss: 1.763e-01]
latex_v1:  44%|####3     | 1306/3000 [30:28<24:12,  1.17it/s, lr: 1.0e-04 loss: 7.345e-01]
latex_v1:  44%|####3     | 1306/3000 [30:28<24:12,  1.17it/s, lr: 1.0e-04 loss: 7.345e-01]
latex_v1:  44%|####3     | 1307/3000 [30:28<40:18,  1.43s/it, lr: 1.0e-04 loss: 7.345e-01]
latex_v1:  44%|####3     | 1307/3000 [30:28<40:18,  1.43s/it, lr: 1.0e-04 loss: 7.345e-01]
latex_v1:  44%|####3     | 1307/3000 [30:29<40:18,  1.43s/it, lr: 1.0e-04 loss: 3.715e-01]
latex_v1:  44%|####3     | 1307/3000 [30:29<40:18,  1.43s/it, lr: 1.0e-04 loss: 3.715e-01]
latex_v1:  44%|####3     | 1308/3000 [30:29<34:51,  1.24s/it, lr: 1.0e-04 loss: 3.715e-01]
latex_v1:  44%|####3     | 1308/3000 [30:29<34:51,  1.24s/it, lr: 1.0e-04 loss: 3.715e-01]
latex_v1:  44%|####3     | 1308/3000 [30:30<34:51,  1.24s/it, lr: 1.0e-04 loss: 4.056e-01]
latex_v1:  44%|####3     | 1308/3000 [30:30<34:51,  1.24s/it, lr: 1.0e-04 loss: 4.056e-01]
latex_v1:  44%|####3     | 1309/3000 [30:30<36:07,  1.28s/it, lr: 1.0e-04 loss: 4.056e-01]
latex_v1:  44%|####3     | 1309/3000 [30:30<36:07,  1.28s/it, lr: 1.0e-04 loss: 4.056e-01]
latex_v1:  44%|####3     | 1309/3000 [30:32<36:07,  1.28s/it, lr: 1.0e-04 loss: 5.262e-01]
latex_v1:  44%|####3     | 1309/3000 [30:32<36:07,  1.28s/it, lr: 1.0e-04 loss: 5.262e-01]
latex_v1:  44%|####3     | 1310/3000 [30:35<36:06,  1.28s/it, lr: 1.0e-04 loss: 1.536e-01]
latex_v1:  44%|####3     | 1310/3000 [30:35<36:06,  1.28s/it, lr: 1.0e-04 loss: 1.536e-01]
latex_v1:  44%|####3     | 1311/3000 [30:35<37:58,  1.35s/it, lr: 1.0e-04 loss: 1.536e-01]
latex_v1:  44%|####3     | 1311/3000 [30:35<37:58,  1.35s/it, lr: 1.0e-04 loss: 1.536e-01]
latex_v1:  44%|####3     | 1311/3000 [30:36<37:58,  1.35s/it, lr: 1.0e-04 loss: 2.372e-03]
latex_v1:  44%|####3     | 1311/3000 [30:36<37:58,  1.35s/it, lr: 1.0e-04 loss: 2.372e-03]
latex_v1:  44%|####3     | 1312/3000 [30:36<38:19,  1.36s/it, lr: 1.0e-04 loss: 2.372e-03]
latex_v1:  44%|####3     | 1312/3000 [30:36<38:19,  1.36s/it, lr: 1.0e-04 loss: 2.372e-03]
latex_v1:  44%|####3     | 1312/3000 [30:39<38:19,  1.36s/it, lr: 1.0e-04 loss: 5.933e-01]
latex_v1:  44%|####3     | 1312/3000 [30:39<38:19,  1.36s/it, lr: 1.0e-04 loss: 5.933e-01]
latex_v1:  44%|####3     | 1313/3000 [30:39<47:37,  1.69s/it, lr: 1.0e-04 loss: 5.933e-01]
latex_v1:  44%|####3     | 1313/3000 [30:39<47:37,  1.69s/it, lr: 1.0e-04 loss: 5.933e-01]
latex_v1:  44%|####3     | 1313/3000 [30:40<47:37,  1.69s/it, lr: 1.0e-04 loss: 7.809e-02]
latex_v1:  44%|####3     | 1313/3000 [30:40<47:37,  1.69s/it, lr: 1.0e-04 loss: 7.809e-02]
latex_v1:  44%|####3     | 1314/3000 [30:40<45:33,  1.62s/it, lr: 1.0e-04 loss: 7.809e-02]
latex_v1:  44%|####3     | 1314/3000 [30:40<45:33,  1.62s/it, lr: 1.0e-04 loss: 7.809e-02]
latex_v1:  44%|####3     | 1314/3000 [30:43<45:33,  1.62s/it, lr: 1.0e-04 loss: 5.404e-02]
latex_v1:  44%|####3     | 1314/3000 [30:43<45:33,  1.62s/it, lr: 1.0e-04 loss: 5.404e-02]
latex_v1:  44%|####3     | 1315/3000 [30:43<55:27,  1.97s/it, lr: 1.0e-04 loss: 5.404e-02]
latex_v1:  44%|####3     | 1315/3000 [30:43<55:27,  1.97s/it, lr: 1.0e-04 loss: 5.404e-02]
latex_v1:  44%|####3     | 1315/3000 [30:46<55:27,  1.97s/it, lr: 1.0e-04 loss: 1.873e-01]
latex_v1:  44%|####3     | 1315/3000 [30:46<55:27,  1.97s/it, lr: 1.0e-04 loss: 1.873e-01]
latex_v1:  44%|####3     | 1316/3000 [30:46<1:01:25,  2.19s/it, lr: 1.0e-04 loss: 1.873e-01]
latex_v1:  44%|####3     | 1316/3000 [30:46<1:01:25,  2.19s/it, lr: 1.0e-04 loss: 1.873e-01]
latex_v1:  44%|####3     | 1316/3000 [30:47<1:01:25,  2.19s/it, lr: 1.0e-04 loss: 4.582e-02]
latex_v1:  44%|####3     | 1316/3000 [30:47<1:01:25,  2.19s/it, lr: 1.0e-04 loss: 4.582e-02]
latex_v1:  44%|####3     | 1317/3000 [30:47<56:09,  2.00s/it, lr: 1.0e-04 loss: 4.582e-02]  
latex_v1:  44%|####3     | 1317/3000 [30:47<56:09,  2.00s/it, lr: 1.0e-04 loss: 4.582e-02]  
latex_v1:  44%|####3     | 1317/3000 [30:49<56:09,  2.00s/it, lr: 1.0e-04 loss: 2.726e-01]
latex_v1:  44%|####3     | 1317/3000 [30:49<56:09,  2.00s/it, lr: 1.0e-04 loss: 2.726e-01]
latex_v1:  44%|####3     | 1318/3000 [30:49<49:57,  1.78s/it, lr: 1.0e-04 loss: 2.726e-01]
latex_v1:  44%|####3     | 1318/3000 [30:49<49:57,  1.78s/it, lr: 1.0e-04 loss: 2.726e-01]
latex_v1:  44%|####3     | 1318/3000 [30:50<49:57,  1.78s/it, lr: 1.0e-04 loss: 3.382e-01]
latex_v1:  44%|####3     | 1318/3000 [30:50<49:57,  1.78s/it, lr: 1.0e-04 loss: 3.382e-01]
latex_v1:  44%|####3     | 1319/3000 [30:50<47:05,  1.68s/it, lr: 1.0e-04 loss: 3.382e-01]
latex_v1:  44%|####3     | 1319/3000 [30:50<47:05,  1.68s/it, lr: 1.0e-04 loss: 3.382e-01]
latex_v1:  44%|####3     | 1319/3000 [30:52<47:05,  1.68s/it, lr: 1.0e-04 loss: 3.568e-01]
latex_v1:  44%|####3     | 1319/3000 [30:52<47:05,  1.68s/it, lr: 1.0e-04 loss: 3.568e-01]
latex_v1:  44%|####4     | 1320/3000 [30:52<47:03,  1.68s/it, lr: 1.0e-04 loss: 2.269e-01]
latex_v1:  44%|####4     | 1320/3000 [30:52<47:03,  1.68s/it, lr: 1.0e-04 loss: 2.269e-01]
latex_v1:  44%|####4     | 1321/3000 [30:52<30:20,  1.08s/it, lr: 1.0e-04 loss: 2.269e-01]
latex_v1:  44%|####4     | 1321/3000 [30:52<30:20,  1.08s/it, lr: 1.0e-04 loss: 2.269e-01]
latex_v1:  44%|####4     | 1321/3000 [30:53<30:20,  1.08s/it, lr: 1.0e-04 loss: 1.295e-01]
latex_v1:  44%|####4     | 1321/3000 [30:53<30:20,  1.08s/it, lr: 1.0e-04 loss: 1.295e-01]
latex_v1:  44%|####4     | 1322/3000 [30:53<28:06,  1.01s/it, lr: 1.0e-04 loss: 1.295e-01]
latex_v1:  44%|####4     | 1322/3000 [30:53<28:06,  1.01s/it, lr: 1.0e-04 loss: 1.295e-01]
latex_v1:  44%|####4     | 1322/3000 [30:54<28:06,  1.01s/it, lr: 1.0e-04 loss: 4.022e-01]
latex_v1:  44%|####4     | 1322/3000 [30:54<28:06,  1.01s/it, lr: 1.0e-04 loss: 4.022e-01]
latex_v1:  44%|####4     | 1323/3000 [30:54<26:15,  1.06it/s, lr: 1.0e-04 loss: 4.022e-01]
latex_v1:  44%|####4     | 1323/3000 [30:54<26:15,  1.06it/s, lr: 1.0e-04 loss: 4.022e-01]
latex_v1:  44%|####4     | 1323/3000 [30:57<26:15,  1.06it/s, lr: 1.0e-04 loss: 1.814e-01]
latex_v1:  44%|####4     | 1323/3000 [30:57<26:15,  1.06it/s, lr: 1.0e-04 loss: 1.814e-01]
latex_v1:  44%|####4     | 1324/3000 [30:57<40:35,  1.45s/it, lr: 1.0e-04 loss: 1.814e-01]
latex_v1:  44%|####4     | 1324/3000 [30:57<40:35,  1.45s/it, lr: 1.0e-04 loss: 1.814e-01]
latex_v1:  44%|####4     | 1324/3000 [30:58<40:35,  1.45s/it, lr: 1.0e-04 loss: 4.690e-01]
latex_v1:  44%|####4     | 1324/3000 [30:58<40:35,  1.45s/it, lr: 1.0e-04 loss: 4.690e-01]
latex_v1:  44%|####4     | 1325/3000 [30:58<38:25,  1.38s/it, lr: 1.0e-04 loss: 4.690e-01]
latex_v1:  44%|####4     | 1325/3000 [30:58<38:25,  1.38s/it, lr: 1.0e-04 loss: 4.690e-01]
latex_v1:  44%|####4     | 1325/3000 [30:59<38:25,  1.38s/it, lr: 1.0e-04 loss: 4.026e-02]
latex_v1:  44%|####4     | 1325/3000 [30:59<38:25,  1.38s/it, lr: 1.0e-04 loss: 4.026e-02]
latex_v1:  44%|####4     | 1326/3000 [30:59<33:37,  1.21s/it, lr: 1.0e-04 loss: 4.026e-02]
latex_v1:  44%|####4     | 1326/3000 [30:59<33:37,  1.21s/it, lr: 1.0e-04 loss: 4.026e-02]
latex_v1:  44%|####4     | 1326/3000 [31:00<33:37,  1.21s/it, lr: 1.0e-04 loss: 3.300e-01]
latex_v1:  44%|####4     | 1326/3000 [31:00<33:37,  1.21s/it, lr: 1.0e-04 loss: 3.300e-01]
latex_v1:  44%|####4     | 1327/3000 [31:00<34:44,  1.25s/it, lr: 1.0e-04 loss: 3.300e-01]
latex_v1:  44%|####4     | 1327/3000 [31:00<34:44,  1.25s/it, lr: 1.0e-04 loss: 3.300e-01]
latex_v1:  44%|####4     | 1327/3000 [31:02<34:44,  1.25s/it, lr: 1.0e-04 loss: 4.362e-01]
latex_v1:  44%|####4     | 1327/3000 [31:02<34:44,  1.25s/it, lr: 1.0e-04 loss: 4.362e-01]
latex_v1:  44%|####4     | 1328/3000 [31:02<37:01,  1.33s/it, lr: 1.0e-04 loss: 4.362e-01]
latex_v1:  44%|####4     | 1328/3000 [31:02<37:01,  1.33s/it, lr: 1.0e-04 loss: 4.362e-01]
latex_v1:  44%|####4     | 1328/3000 [31:03<37:01,  1.33s/it, lr: 1.0e-04 loss: 3.706e-01]
latex_v1:  44%|####4     | 1328/3000 [31:03<37:01,  1.33s/it, lr: 1.0e-04 loss: 3.706e-01]
latex_v1:  44%|####4     | 1329/3000 [31:03<41:37,  1.49s/it, lr: 1.0e-04 loss: 3.706e-01]
latex_v1:  44%|####4     | 1329/3000 [31:03<41:37,  1.49s/it, lr: 1.0e-04 loss: 3.706e-01]
latex_v1:  44%|####4     | 1329/3000 [31:05<41:37,  1.49s/it, lr: 1.0e-04 loss: 1.349e-01]
latex_v1:  44%|####4     | 1329/3000 [31:05<41:37,  1.49s/it, lr: 1.0e-04 loss: 1.349e-01]
latex_v1:  44%|####4     | 1330/3000 [31:07<41:35,  1.49s/it, lr: 1.0e-04 loss: 8.160e-02]
latex_v1:  44%|####4     | 1330/3000 [31:07<41:35,  1.49s/it, lr: 1.0e-04 loss: 8.160e-02]
latex_v1:  44%|####4     | 1331/3000 [31:07<32:22,  1.16s/it, lr: 1.0e-04 loss: 8.160e-02]
latex_v1:  44%|####4     | 1331/3000 [31:07<32:22,  1.16s/it, lr: 1.0e-04 loss: 8.160e-02]
latex_v1:  44%|####4     | 1331/3000 [31:08<32:22,  1.16s/it, lr: 1.0e-04 loss: 3.186e-02]
latex_v1:  44%|####4     | 1331/3000 [31:08<32:22,  1.16s/it, lr: 1.0e-04 loss: 3.186e-02]
latex_v1:  44%|####4     | 1332/3000 [31:08<36:10,  1.30s/it, lr: 1.0e-04 loss: 3.186e-02]
latex_v1:  44%|####4     | 1332/3000 [31:08<36:10,  1.30s/it, lr: 1.0e-04 loss: 3.186e-02]
latex_v1:  44%|####4     | 1332/3000 [31:10<36:10,  1.30s/it, lr: 1.0e-04 loss: 4.190e-01]
latex_v1:  44%|####4     | 1332/3000 [31:10<36:10,  1.30s/it, lr: 1.0e-04 loss: 4.190e-01]
latex_v1:  44%|####4     | 1333/3000 [31:10<40:21,  1.45s/it, lr: 1.0e-04 loss: 4.190e-01]
latex_v1:  44%|####4     | 1333/3000 [31:10<40:21,  1.45s/it, lr: 1.0e-04 loss: 4.190e-01]
latex_v1:  44%|####4     | 1333/3000 [31:11<40:21,  1.45s/it, lr: 1.0e-04 loss: 2.879e-02]
latex_v1:  44%|####4     | 1333/3000 [31:11<40:21,  1.45s/it, lr: 1.0e-04 loss: 2.879e-02]
latex_v1:  44%|####4     | 1334/3000 [31:11<34:57,  1.26s/it, lr: 1.0e-04 loss: 2.879e-02]
latex_v1:  44%|####4     | 1334/3000 [31:11<34:57,  1.26s/it, lr: 1.0e-04 loss: 2.879e-02]
latex_v1:  44%|####4     | 1334/3000 [31:13<34:57,  1.26s/it, lr: 1.0e-04 loss: 3.718e-01]
latex_v1:  44%|####4     | 1334/3000 [31:13<34:57,  1.26s/it, lr: 1.0e-04 loss: 3.718e-01]
latex_v1:  44%|####4     | 1335/3000 [31:13<37:58,  1.37s/it, lr: 1.0e-04 loss: 3.718e-01]
latex_v1:  44%|####4     | 1335/3000 [31:13<37:58,  1.37s/it, lr: 1.0e-04 loss: 3.718e-01]
latex_v1:  44%|####4     | 1335/3000 [31:14<37:58,  1.37s/it, lr: 1.0e-04 loss: 1.521e-01]
latex_v1:  44%|####4     | 1335/3000 [31:14<37:58,  1.37s/it, lr: 1.0e-04 loss: 1.521e-01]
latex_v1:  45%|####4     | 1336/3000 [31:14<38:48,  1.40s/it, lr: 1.0e-04 loss: 1.521e-01]
latex_v1:  45%|####4     | 1336/3000 [31:14<38:48,  1.40s/it, lr: 1.0e-04 loss: 1.521e-01]
latex_v1:  45%|####4     | 1336/3000 [31:17<38:48,  1.40s/it, lr: 1.0e-04 loss: 1.474e-01]
latex_v1:  45%|####4     | 1336/3000 [31:17<38:48,  1.40s/it, lr: 1.0e-04 loss: 1.474e-01]
latex_v1:  45%|####4     | 1337/3000 [31:17<50:31,  1.82s/it, lr: 1.0e-04 loss: 1.474e-01]
latex_v1:  45%|####4     | 1337/3000 [31:17<50:31,  1.82s/it, lr: 1.0e-04 loss: 1.474e-01]
latex_v1:  45%|####4     | 1337/3000 [31:18<50:31,  1.82s/it, lr: 1.0e-04 loss: 4.088e-01]
latex_v1:  45%|####4     | 1337/3000 [31:18<50:31,  1.82s/it, lr: 1.0e-04 loss: 4.088e-01]
latex_v1:  45%|####4     | 1338/3000 [31:18<41:47,  1.51s/it, lr: 1.0e-04 loss: 4.088e-01]
latex_v1:  45%|####4     | 1338/3000 [31:18<41:47,  1.51s/it, lr: 1.0e-04 loss: 4.088e-01]
latex_v1:  45%|####4     | 1338/3000 [31:19<41:47,  1.51s/it, lr: 1.0e-04 loss: 1.666e-01]
latex_v1:  45%|####4     | 1338/3000 [31:19<41:47,  1.51s/it, lr: 1.0e-04 loss: 1.666e-01]
latex_v1:  45%|####4     | 1339/3000 [31:19<44:30,  1.61s/it, lr: 1.0e-04 loss: 1.666e-01]
latex_v1:  45%|####4     | 1339/3000 [31:19<44:30,  1.61s/it, lr: 1.0e-04 loss: 1.666e-01]
latex_v1:  45%|####4     | 1339/3000 [31:22<44:30,  1.61s/it, lr: 1.0e-04 loss: 4.311e-01]
latex_v1:  45%|####4     | 1339/3000 [31:22<44:30,  1.61s/it, lr: 1.0e-04 loss: 4.311e-01]
latex_v1:  45%|####4     | 1340/3000 [31:24<44:28,  1.61s/it, lr: 1.0e-04 loss: 1.144e-01]
latex_v1:  45%|####4     | 1340/3000 [31:24<44:28,  1.61s/it, lr: 1.0e-04 loss: 1.144e-01]
latex_v1:  45%|####4     | 1341/3000 [31:24<33:20,  1.21s/it, lr: 1.0e-04 loss: 1.144e-01]
latex_v1:  45%|####4     | 1341/3000 [31:24<33:20,  1.21s/it, lr: 1.0e-04 loss: 1.144e-01]
latex_v1:  45%|####4     | 1341/3000 [31:25<33:20,  1.21s/it, lr: 1.0e-04 loss: 4.202e-02]
latex_v1:  45%|####4     | 1341/3000 [31:25<33:20,  1.21s/it, lr: 1.0e-04 loss: 4.202e-02]
latex_v1:  45%|####4     | 1342/3000 [31:25<30:12,  1.09s/it, lr: 1.0e-04 loss: 4.202e-02]
latex_v1:  45%|####4     | 1342/3000 [31:25<30:12,  1.09s/it, lr: 1.0e-04 loss: 4.202e-02]
latex_v1:  45%|####4     | 1342/3000 [31:26<30:12,  1.09s/it, lr: 1.0e-04 loss: 5.667e-01]
latex_v1:  45%|####4     | 1342/3000 [31:26<30:12,  1.09s/it, lr: 1.0e-04 loss: 5.667e-01]
latex_v1:  45%|####4     | 1343/3000 [31:26<33:24,  1.21s/it, lr: 1.0e-04 loss: 5.667e-01]
latex_v1:  45%|####4     | 1343/3000 [31:26<33:24,  1.21s/it, lr: 1.0e-04 loss: 5.667e-01]
latex_v1:  45%|####4     | 1343/3000 [31:27<33:24,  1.21s/it, lr: 1.0e-04 loss: 3.821e-01]
latex_v1:  45%|####4     | 1343/3000 [31:27<33:24,  1.21s/it, lr: 1.0e-04 loss: 3.821e-01]
latex_v1:  45%|####4     | 1344/3000 [31:27<33:07,  1.20s/it, lr: 1.0e-04 loss: 3.821e-01]
latex_v1:  45%|####4     | 1344/3000 [31:27<33:07,  1.20s/it, lr: 1.0e-04 loss: 3.821e-01]
latex_v1:  45%|####4     | 1344/3000 [31:29<33:07,  1.20s/it, lr: 1.0e-04 loss: 1.399e-01]
latex_v1:  45%|####4     | 1344/3000 [31:29<33:07,  1.20s/it, lr: 1.0e-04 loss: 1.399e-01]
latex_v1:  45%|####4     | 1345/3000 [31:29<34:22,  1.25s/it, lr: 1.0e-04 loss: 1.399e-01]
latex_v1:  45%|####4     | 1345/3000 [31:29<34:22,  1.25s/it, lr: 1.0e-04 loss: 1.399e-01]
latex_v1:  45%|####4     | 1345/3000 [31:30<34:22,  1.25s/it, lr: 1.0e-04 loss: 1.029e-01]
latex_v1:  45%|####4     | 1345/3000 [31:30<34:22,  1.25s/it, lr: 1.0e-04 loss: 1.029e-01]
latex_v1:  45%|####4     | 1346/3000 [31:30<32:11,  1.17s/it, lr: 1.0e-04 loss: 1.029e-01]
latex_v1:  45%|####4     | 1346/3000 [31:30<32:11,  1.17s/it, lr: 1.0e-04 loss: 1.029e-01]
latex_v1:  45%|####4     | 1346/3000 [31:31<32:11,  1.17s/it, lr: 1.0e-04 loss: 2.991e-01]
latex_v1:  45%|####4     | 1346/3000 [31:31<32:11,  1.17s/it, lr: 1.0e-04 loss: 2.991e-01]
latex_v1:  45%|####4     | 1347/3000 [31:31<33:40,  1.22s/it, lr: 1.0e-04 loss: 2.991e-01]
latex_v1:  45%|####4     | 1347/3000 [31:31<33:40,  1.22s/it, lr: 1.0e-04 loss: 2.991e-01]
latex_v1:  45%|####4     | 1347/3000 [31:32<33:40,  1.22s/it, lr: 1.0e-04 loss: 2.288e-01]
latex_v1:  45%|####4     | 1347/3000 [31:32<33:40,  1.22s/it, lr: 1.0e-04 loss: 2.288e-01]
latex_v1:  45%|####4     | 1348/3000 [31:32<30:05,  1.09s/it, lr: 1.0e-04 loss: 2.288e-01]
latex_v1:  45%|####4     | 1348/3000 [31:32<30:05,  1.09s/it, lr: 1.0e-04 loss: 2.288e-01]
latex_v1:  45%|####4     | 1348/3000 [31:33<30:05,  1.09s/it, lr: 1.0e-04 loss: 1.442e-01]
latex_v1:  45%|####4     | 1348/3000 [31:33<30:05,  1.09s/it, lr: 1.0e-04 loss: 1.442e-01]
latex_v1:  45%|####4     | 1349/3000 [31:33<30:48,  1.12s/it, lr: 1.0e-04 loss: 1.442e-01]
latex_v1:  45%|####4     | 1349/3000 [31:33<30:48,  1.12s/it, lr: 1.0e-04 loss: 1.442e-01]
latex_v1:  45%|####4     | 1349/3000 [31:35<30:48,  1.12s/it, lr: 1.0e-04 loss: 2.123e-01]
latex_v1:  45%|####4     | 1349/3000 [31:35<30:48,  1.12s/it, lr: 1.0e-04 loss: 2.123e-01]
latex_v1:  45%|####5     | 1350/3000 [31:36<30:47,  1.12s/it, lr: 1.0e-04 loss: 6.183e-01]
latex_v1:  45%|####5     | 1350/3000 [31:36<30:47,  1.12s/it, lr: 1.0e-04 loss: 6.183e-01]
latex_v1:  45%|####5     | 1351/3000 [31:36<21:17,  1.29it/s, lr: 1.0e-04 loss: 6.183e-01]
latex_v1:  45%|####5     | 1351/3000 [31:36<21:17,  1.29it/s, lr: 1.0e-04 loss: 6.183e-01]
latex_v1:  45%|####5     | 1351/3000 [31:39<21:17,  1.29it/s, lr: 1.0e-04 loss: 5.913e-01]
latex_v1:  45%|####5     | 1351/3000 [31:39<21:17,  1.29it/s, lr: 1.0e-04 loss: 5.913e-01]
latex_v1:  45%|####5     | 1352/3000 [31:39<35:28,  1.29s/it, lr: 1.0e-04 loss: 5.913e-01]
latex_v1:  45%|####5     | 1352/3000 [31:39<35:28,  1.29s/it, lr: 1.0e-04 loss: 5.913e-01]
latex_v1:  45%|####5     | 1352/3000 [31:40<35:28,  1.29s/it, lr: 1.0e-04 loss: 9.774e-02]
latex_v1:  45%|####5     | 1352/3000 [31:40<35:28,  1.29s/it, lr: 1.0e-04 loss: 9.774e-02]
latex_v1:  45%|####5     | 1353/3000 [31:40<37:06,  1.35s/it, lr: 1.0e-04 loss: 9.774e-02]
latex_v1:  45%|####5     | 1353/3000 [31:40<37:06,  1.35s/it, lr: 1.0e-04 loss: 9.774e-02]
latex_v1:  45%|####5     | 1353/3000 [31:41<37:06,  1.35s/it, lr: 1.0e-04 loss: 3.442e-01]
latex_v1:  45%|####5     | 1353/3000 [31:41<37:06,  1.35s/it, lr: 1.0e-04 loss: 3.442e-01]
latex_v1:  45%|####5     | 1354/3000 [31:41<32:37,  1.19s/it, lr: 1.0e-04 loss: 3.442e-01]
latex_v1:  45%|####5     | 1354/3000 [31:41<32:37,  1.19s/it, lr: 1.0e-04 loss: 3.442e-01]
latex_v1:  45%|####5     | 1354/3000 [31:42<32:37,  1.19s/it, lr: 1.0e-04 loss: 4.796e-01]
latex_v1:  45%|####5     | 1354/3000 [31:42<32:37,  1.19s/it, lr: 1.0e-04 loss: 4.796e-01]
latex_v1:  45%|####5     | 1355/3000 [31:42<29:18,  1.07s/it, lr: 1.0e-04 loss: 4.796e-01]
latex_v1:  45%|####5     | 1355/3000 [31:42<29:18,  1.07s/it, lr: 1.0e-04 loss: 4.796e-01]
latex_v1:  45%|####5     | 1355/3000 [31:43<29:18,  1.07s/it, lr: 1.0e-04 loss: 4.754e-01]
latex_v1:  45%|####5     | 1355/3000 [31:43<29:18,  1.07s/it, lr: 1.0e-04 loss: 4.754e-01]
latex_v1:  45%|####5     | 1356/3000 [31:43<26:47,  1.02it/s, lr: 1.0e-04 loss: 4.754e-01]
latex_v1:  45%|####5     | 1356/3000 [31:43<26:47,  1.02it/s, lr: 1.0e-04 loss: 4.754e-01]
latex_v1:  45%|####5     | 1356/3000 [31:43<26:47,  1.02it/s, lr: 1.0e-04 loss: 4.402e-01]
latex_v1:  45%|####5     | 1356/3000 [31:43<26:47,  1.02it/s, lr: 1.0e-04 loss: 4.402e-01]
latex_v1:  45%|####5     | 1357/3000 [31:43<24:59,  1.10it/s, lr: 1.0e-04 loss: 4.402e-01]
latex_v1:  45%|####5     | 1357/3000 [31:43<24:59,  1.10it/s, lr: 1.0e-04 loss: 4.402e-01]
latex_v1:  45%|####5     | 1357/3000 [31:44<24:59,  1.10it/s, lr: 1.0e-04 loss: 4.332e-01]
latex_v1:  45%|####5     | 1357/3000 [31:44<24:59,  1.10it/s, lr: 1.0e-04 loss: 4.332e-01]
latex_v1:  45%|####5     | 1358/3000 [31:44<23:44,  1.15it/s, lr: 1.0e-04 loss: 4.332e-01]
latex_v1:  45%|####5     | 1358/3000 [31:44<23:44,  1.15it/s, lr: 1.0e-04 loss: 4.332e-01]
latex_v1:  45%|####5     | 1358/3000 [31:45<23:44,  1.15it/s, lr: 1.0e-04 loss: 6.335e-01]
latex_v1:  45%|####5     | 1358/3000 [31:45<23:44,  1.15it/s, lr: 1.0e-04 loss: 6.335e-01]
latex_v1:  45%|####5     | 1359/3000 [31:45<24:32,  1.11it/s, lr: 1.0e-04 loss: 6.335e-01]
latex_v1:  45%|####5     | 1359/3000 [31:45<24:32,  1.11it/s, lr: 1.0e-04 loss: 6.335e-01]
latex_v1:  45%|####5     | 1359/3000 [31:46<24:32,  1.11it/s, lr: 1.0e-04 loss: 3.421e-01]
latex_v1:  45%|####5     | 1359/3000 [31:46<24:32,  1.11it/s, lr: 1.0e-04 loss: 3.421e-01]
latex_v1:  45%|####5     | 1360/3000 [31:47<24:31,  1.11it/s, lr: 1.0e-04 loss: 3.224e-01]
latex_v1:  45%|####5     | 1360/3000 [31:47<24:31,  1.11it/s, lr: 1.0e-04 loss: 3.224e-01]
latex_v1:  45%|####5     | 1361/3000 [31:47<24:10,  1.13it/s, lr: 1.0e-04 loss: 3.224e-01]
latex_v1:  45%|####5     | 1361/3000 [31:47<24:10,  1.13it/s, lr: 1.0e-04 loss: 3.224e-01]
latex_v1:  45%|####5     | 1361/3000 [31:49<24:10,  1.13it/s, lr: 1.0e-04 loss: 4.344e-01]
latex_v1:  45%|####5     | 1361/3000 [31:49<24:10,  1.13it/s, lr: 1.0e-04 loss: 4.344e-01]
latex_v1:  45%|####5     | 1362/3000 [31:49<31:02,  1.14s/it, lr: 1.0e-04 loss: 4.344e-01]
latex_v1:  45%|####5     | 1362/3000 [31:49<31:02,  1.14s/it, lr: 1.0e-04 loss: 4.344e-01]
latex_v1:  45%|####5     | 1362/3000 [31:51<31:02,  1.14s/it, lr: 1.0e-04 loss: 3.971e-01]
latex_v1:  45%|####5     | 1362/3000 [31:51<31:02,  1.14s/it, lr: 1.0e-04 loss: 3.971e-01]
latex_v1:  45%|####5     | 1363/3000 [31:51<31:19,  1.15s/it, lr: 1.0e-04 loss: 3.971e-01]
latex_v1:  45%|####5     | 1363/3000 [31:51<31:19,  1.15s/it, lr: 1.0e-04 loss: 3.971e-01]
latex_v1:  45%|####5     | 1363/3000 [31:51<31:19,  1.15s/it, lr: 1.0e-04 loss: 1.973e-01]
latex_v1:  45%|####5     | 1363/3000 [31:51<31:19,  1.15s/it, lr: 1.0e-04 loss: 1.973e-01]
latex_v1:  45%|####5     | 1364/3000 [31:51<28:22,  1.04s/it, lr: 1.0e-04 loss: 1.973e-01]
latex_v1:  45%|####5     | 1364/3000 [31:51<28:22,  1.04s/it, lr: 1.0e-04 loss: 1.973e-01]
latex_v1:  45%|####5     | 1364/3000 [31:52<28:22,  1.04s/it, lr: 1.0e-04 loss: 8.795e-01]
latex_v1:  45%|####5     | 1364/3000 [31:52<28:22,  1.04s/it, lr: 1.0e-04 loss: 8.795e-01]
latex_v1:  46%|####5     | 1365/3000 [31:52<29:20,  1.08s/it, lr: 1.0e-04 loss: 8.795e-01]
latex_v1:  46%|####5     | 1365/3000 [31:52<29:20,  1.08s/it, lr: 1.0e-04 loss: 8.795e-01]
latex_v1:  46%|####5     | 1365/3000 [31:53<29:20,  1.08s/it, lr: 1.0e-04 loss: 5.408e-01]
latex_v1:  46%|####5     | 1365/3000 [31:53<29:20,  1.08s/it, lr: 1.0e-04 loss: 5.408e-01]
latex_v1:  46%|####5     | 1366/3000 [31:53<26:53,  1.01it/s, lr: 1.0e-04 loss: 5.408e-01]
latex_v1:  46%|####5     | 1366/3000 [31:53<26:53,  1.01it/s, lr: 1.0e-04 loss: 5.408e-01]
latex_v1:  46%|####5     | 1366/3000 [31:54<26:53,  1.01it/s, lr: 1.0e-04 loss: 3.614e-01]
latex_v1:  46%|####5     | 1366/3000 [31:54<26:53,  1.01it/s, lr: 1.0e-04 loss: 3.614e-01]
latex_v1:  46%|####5     | 1367/3000 [31:54<24:57,  1.09it/s, lr: 1.0e-04 loss: 3.614e-01]
latex_v1:  46%|####5     | 1367/3000 [31:54<24:57,  1.09it/s, lr: 1.0e-04 loss: 3.614e-01]
latex_v1:  46%|####5     | 1367/3000 [31:55<24:57,  1.09it/s, lr: 1.0e-04 loss: 6.097e-01]
latex_v1:  46%|####5     | 1367/3000 [31:55<24:57,  1.09it/s, lr: 1.0e-04 loss: 6.097e-01]
latex_v1:  46%|####5     | 1368/3000 [31:55<23:41,  1.15it/s, lr: 1.0e-04 loss: 6.097e-01]
latex_v1:  46%|####5     | 1368/3000 [31:55<23:41,  1.15it/s, lr: 1.0e-04 loss: 6.097e-01]
latex_v1:  46%|####5     | 1368/3000 [31:56<23:41,  1.15it/s, lr: 1.0e-04 loss: 1.509e-01]
latex_v1:  46%|####5     | 1368/3000 [31:56<23:41,  1.15it/s, lr: 1.0e-04 loss: 1.509e-01]
latex_v1:  46%|####5     | 1369/3000 [31:56<22:49,  1.19it/s, lr: 1.0e-04 loss: 1.509e-01]
latex_v1:  46%|####5     | 1369/3000 [31:56<22:49,  1.19it/s, lr: 1.0e-04 loss: 1.509e-01]
latex_v1:  46%|####5     | 1369/3000 [31:57<22:49,  1.19it/s, lr: 1.0e-04 loss: 1.976e-01]
latex_v1:  46%|####5     | 1369/3000 [31:57<22:49,  1.19it/s, lr: 1.0e-04 loss: 1.976e-01]
latex_v1:  46%|####5     | 1370/3000 [31:58<22:48,  1.19it/s, lr: 1.0e-04 loss: 5.314e-01]
latex_v1:  46%|####5     | 1370/3000 [31:58<22:48,  1.19it/s, lr: 1.0e-04 loss: 5.314e-01]
latex_v1:  46%|####5     | 1371/3000 [31:58<20:38,  1.32it/s, lr: 1.0e-04 loss: 5.314e-01]
latex_v1:  46%|####5     | 1371/3000 [31:58<20:38,  1.32it/s, lr: 1.0e-04 loss: 5.314e-01]
latex_v1:  46%|####5     | 1371/3000 [32:00<20:38,  1.32it/s, lr: 1.0e-04 loss: 8.052e-02]
latex_v1:  46%|####5     | 1371/3000 [32:00<20:38,  1.32it/s, lr: 1.0e-04 loss: 8.052e-02]
latex_v1:  46%|####5     | 1372/3000 [32:00<25:37,  1.06it/s, lr: 1.0e-04 loss: 8.052e-02]
latex_v1:  46%|####5     | 1372/3000 [32:00<25:37,  1.06it/s, lr: 1.0e-04 loss: 8.052e-02]
latex_v1:  46%|####5     | 1372/3000 [32:01<25:37,  1.06it/s, lr: 1.0e-04 loss: 3.254e-01]
latex_v1:  46%|####5     | 1372/3000 [32:01<25:37,  1.06it/s, lr: 1.0e-04 loss: 3.254e-01]
latex_v1:  46%|####5     | 1373/3000 [32:01<28:34,  1.05s/it, lr: 1.0e-04 loss: 3.254e-01]
latex_v1:  46%|####5     | 1373/3000 [32:01<28:34,  1.05s/it, lr: 1.0e-04 loss: 3.254e-01]
latex_v1:  46%|####5     | 1373/3000 [32:02<28:34,  1.05s/it, lr: 1.0e-04 loss: 2.844e-01]
latex_v1:  46%|####5     | 1373/3000 [32:02<28:34,  1.05s/it, lr: 1.0e-04 loss: 2.844e-01]
latex_v1:  46%|####5     | 1374/3000 [32:02<26:27,  1.02it/s, lr: 1.0e-04 loss: 2.844e-01]
latex_v1:  46%|####5     | 1374/3000 [32:02<26:27,  1.02it/s, lr: 1.0e-04 loss: 2.844e-01]
latex_v1:  46%|####5     | 1374/3000 [32:03<26:27,  1.02it/s, lr: 1.0e-04 loss: 1.221e-01]
latex_v1:  46%|####5     | 1374/3000 [32:03<26:27,  1.02it/s, lr: 1.0e-04 loss: 1.221e-01]
latex_v1:  46%|####5     | 1375/3000 [32:03<30:09,  1.11s/it, lr: 1.0e-04 loss: 1.221e-01]
latex_v1:  46%|####5     | 1375/3000 [32:03<30:09,  1.11s/it, lr: 1.0e-04 loss: 1.221e-01]
latex_v1:  46%|####5     | 1375/3000 [32:05<30:09,  1.11s/it, lr: 1.0e-04 loss: 3.006e-01]
latex_v1:  46%|####5     | 1375/3000 [32:05<30:09,  1.11s/it, lr: 1.0e-04 loss: 3.006e-01]
latex_v1:  46%|####5     | 1376/3000 [32:05<31:53,  1.18s/it, lr: 1.0e-04 loss: 3.006e-01]
latex_v1:  46%|####5     | 1376/3000 [32:05<31:53,  1.18s/it, lr: 1.0e-04 loss: 3.006e-01]
latex_v1:  46%|####5     | 1376/3000 [32:06<31:53,  1.18s/it, lr: 1.0e-04 loss: 3.291e-01]
latex_v1:  46%|####5     | 1376/3000 [32:06<31:53,  1.18s/it, lr: 1.0e-04 loss: 3.291e-01]
latex_v1:  46%|####5     | 1377/3000 [32:06<34:03,  1.26s/it, lr: 1.0e-04 loss: 3.291e-01]
latex_v1:  46%|####5     | 1377/3000 [32:06<34:03,  1.26s/it, lr: 1.0e-04 loss: 3.291e-01]
latex_v1:  46%|####5     | 1377/3000 [32:08<34:03,  1.26s/it, lr: 1.0e-04 loss: 4.506e-01]
latex_v1:  46%|####5     | 1377/3000 [32:08<34:03,  1.26s/it, lr: 1.0e-04 loss: 4.506e-01]
latex_v1:  46%|####5     | 1378/3000 [32:08<36:49,  1.36s/it, lr: 1.0e-04 loss: 4.506e-01]
latex_v1:  46%|####5     | 1378/3000 [32:08<36:49,  1.36s/it, lr: 1.0e-04 loss: 4.506e-01]
latex_v1:  46%|####5     | 1378/3000 [32:09<36:49,  1.36s/it, lr: 1.0e-04 loss: 2.354e-01]
latex_v1:  46%|####5     | 1378/3000 [32:09<36:49,  1.36s/it, lr: 1.0e-04 loss: 2.354e-01]
latex_v1:  46%|####5     | 1379/3000 [32:09<31:47,  1.18s/it, lr: 1.0e-04 loss: 2.354e-01]
latex_v1:  46%|####5     | 1379/3000 [32:09<31:47,  1.18s/it, lr: 1.0e-04 loss: 2.354e-01]
latex_v1:  46%|####5     | 1379/3000 [32:10<31:47,  1.18s/it, lr: 1.0e-04 loss: 6.033e-01]
latex_v1:  46%|####5     | 1379/3000 [32:10<31:47,  1.18s/it, lr: 1.0e-04 loss: 6.033e-01]
latex_v1:  46%|####6     | 1380/3000 [32:13<31:46,  1.18s/it, lr: 1.0e-04 loss: 3.228e-02]
latex_v1:  46%|####6     | 1380/3000 [32:13<31:46,  1.18s/it, lr: 1.0e-04 loss: 3.228e-02]
latex_v1:  46%|####6     | 1381/3000 [32:13<35:02,  1.30s/it, lr: 1.0e-04 loss: 3.228e-02]
latex_v1:  46%|####6     | 1381/3000 [32:13<35:02,  1.30s/it, lr: 1.0e-04 loss: 3.228e-02]
latex_v1:  46%|####6     | 1381/3000 [32:15<35:02,  1.30s/it, lr: 1.0e-04 loss: 2.204e-01]
latex_v1:  46%|####6     | 1381/3000 [32:15<35:02,  1.30s/it, lr: 1.0e-04 loss: 2.204e-01]
latex_v1:  46%|####6     | 1382/3000 [32:15<39:36,  1.47s/it, lr: 1.0e-04 loss: 2.204e-01]
latex_v1:  46%|####6     | 1382/3000 [32:15<39:36,  1.47s/it, lr: 1.0e-04 loss: 2.204e-01]
latex_v1:  46%|####6     | 1382/3000 [32:17<39:36,  1.47s/it, lr: 1.0e-04 loss: 3.798e-01]
latex_v1:  46%|####6     | 1382/3000 [32:17<39:36,  1.47s/it, lr: 1.0e-04 loss: 3.798e-01]
latex_v1:  46%|####6     | 1383/3000 [32:17<40:07,  1.49s/it, lr: 1.0e-04 loss: 3.798e-01]
latex_v1:  46%|####6     | 1383/3000 [32:17<40:07,  1.49s/it, lr: 1.0e-04 loss: 3.798e-01]
latex_v1:  46%|####6     | 1383/3000 [32:18<40:07,  1.49s/it, lr: 1.0e-04 loss: 1.223e-01]
latex_v1:  46%|####6     | 1383/3000 [32:18<40:07,  1.49s/it, lr: 1.0e-04 loss: 1.223e-01]
latex_v1:  46%|####6     | 1384/3000 [32:18<39:52,  1.48s/it, lr: 1.0e-04 loss: 1.223e-01]
latex_v1:  46%|####6     | 1384/3000 [32:18<39:52,  1.48s/it, lr: 1.0e-04 loss: 1.223e-01]
latex_v1:  46%|####6     | 1384/3000 [32:20<39:52,  1.48s/it, lr: 1.0e-04 loss: 1.678e-02]
latex_v1:  46%|####6     | 1384/3000 [32:20<39:52,  1.48s/it, lr: 1.0e-04 loss: 1.678e-02]
latex_v1:  46%|####6     | 1385/3000 [32:20<40:45,  1.51s/it, lr: 1.0e-04 loss: 1.678e-02]
latex_v1:  46%|####6     | 1385/3000 [32:20<40:45,  1.51s/it, lr: 1.0e-04 loss: 1.678e-02]
latex_v1:  46%|####6     | 1385/3000 [32:22<40:45,  1.51s/it, lr: 1.0e-04 loss: 9.885e-02]
latex_v1:  46%|####6     | 1385/3000 [32:22<40:45,  1.51s/it, lr: 1.0e-04 loss: 9.885e-02]
latex_v1:  46%|####6     | 1386/3000 [32:22<43:34,  1.62s/it, lr: 1.0e-04 loss: 9.885e-02]
latex_v1:  46%|####6     | 1386/3000 [32:22<43:34,  1.62s/it, lr: 1.0e-04 loss: 9.885e-02]
latex_v1:  46%|####6     | 1386/3000 [32:23<43:34,  1.62s/it, lr: 1.0e-04 loss: 5.550e-01]
latex_v1:  46%|####6     | 1386/3000 [32:23<43:34,  1.62s/it, lr: 1.0e-04 loss: 5.550e-01]
latex_v1:  46%|####6     | 1387/3000 [32:23<42:21,  1.58s/it, lr: 1.0e-04 loss: 5.550e-01]
latex_v1:  46%|####6     | 1387/3000 [32:23<42:21,  1.58s/it, lr: 1.0e-04 loss: 5.550e-01]
latex_v1:  46%|####6     | 1387/3000 [32:25<42:21,  1.58s/it, lr: 1.0e-04 loss: 2.697e-01]
latex_v1:  46%|####6     | 1387/3000 [32:25<42:21,  1.58s/it, lr: 1.0e-04 loss: 2.697e-01]
latex_v1:  46%|####6     | 1388/3000 [32:25<42:12,  1.57s/it, lr: 1.0e-04 loss: 2.697e-01]
latex_v1:  46%|####6     | 1388/3000 [32:25<42:12,  1.57s/it, lr: 1.0e-04 loss: 2.697e-01]
latex_v1:  46%|####6     | 1388/3000 [32:26<42:12,  1.57s/it, lr: 1.0e-04 loss: 5.832e-01]
latex_v1:  46%|####6     | 1388/3000 [32:26<42:12,  1.57s/it, lr: 1.0e-04 loss: 5.832e-01]
latex_v1:  46%|####6     | 1389/3000 [32:26<38:08,  1.42s/it, lr: 1.0e-04 loss: 5.832e-01]
latex_v1:  46%|####6     | 1389/3000 [32:26<38:08,  1.42s/it, lr: 1.0e-04 loss: 5.832e-01]
latex_v1:  46%|####6     | 1389/3000 [32:27<38:08,  1.42s/it, lr: 1.0e-04 loss: 3.390e-01]
latex_v1:  46%|####6     | 1389/3000 [32:27<38:08,  1.42s/it, lr: 1.0e-04 loss: 3.390e-01]
latex_v1:  46%|####6     | 1390/3000 [32:28<38:06,  1.42s/it, lr: 1.0e-04 loss: 4.560e-01]
latex_v1:  46%|####6     | 1390/3000 [32:28<38:06,  1.42s/it, lr: 1.0e-04 loss: 4.560e-01]
latex_v1:  46%|####6     | 1391/3000 [32:28<27:56,  1.04s/it, lr: 1.0e-04 loss: 4.560e-01]
latex_v1:  46%|####6     | 1391/3000 [32:28<27:56,  1.04s/it, lr: 1.0e-04 loss: 4.560e-01]
latex_v1:  46%|####6     | 1391/3000 [32:29<27:56,  1.04s/it, lr: 1.0e-04 loss: 2.260e-01]
latex_v1:  46%|####6     | 1391/3000 [32:29<27:56,  1.04s/it, lr: 1.0e-04 loss: 2.260e-01]
latex_v1:  46%|####6     | 1392/3000 [32:29<26:02,  1.03it/s, lr: 1.0e-04 loss: 2.260e-01]
latex_v1:  46%|####6     | 1392/3000 [32:29<26:02,  1.03it/s, lr: 1.0e-04 loss: 2.260e-01]
latex_v1:  46%|####6     | 1392/3000 [32:30<26:02,  1.03it/s, lr: 1.0e-04 loss: 2.770e-01]
latex_v1:  46%|####6     | 1392/3000 [32:30<26:02,  1.03it/s, lr: 1.0e-04 loss: 2.770e-01]
latex_v1:  46%|####6     | 1393/3000 [32:30<24:34,  1.09it/s, lr: 1.0e-04 loss: 2.770e-01]
latex_v1:  46%|####6     | 1393/3000 [32:30<24:34,  1.09it/s, lr: 1.0e-04 loss: 2.770e-01]
latex_v1:  46%|####6     | 1393/3000 [32:31<24:34,  1.09it/s, lr: 1.0e-04 loss: 1.640e-01]
latex_v1:  46%|####6     | 1393/3000 [32:31<24:34,  1.09it/s, lr: 1.0e-04 loss: 1.640e-01]
latex_v1:  46%|####6     | 1394/3000 [32:31<23:24,  1.14it/s, lr: 1.0e-04 loss: 1.640e-01]
latex_v1:  46%|####6     | 1394/3000 [32:31<23:24,  1.14it/s, lr: 1.0e-04 loss: 1.640e-01]
latex_v1:  46%|####6     | 1394/3000 [32:33<23:24,  1.14it/s, lr: 1.0e-04 loss: 3.708e-01]
latex_v1:  46%|####6     | 1394/3000 [32:33<23:24,  1.14it/s, lr: 1.0e-04 loss: 3.708e-01]
latex_v1:  46%|####6     | 1395/3000 [32:33<31:20,  1.17s/it, lr: 1.0e-04 loss: 3.708e-01]
latex_v1:  46%|####6     | 1395/3000 [32:33<31:20,  1.17s/it, lr: 1.0e-04 loss: 3.708e-01]
latex_v1:  46%|####6     | 1395/3000 [32:34<31:20,  1.17s/it, lr: 1.0e-04 loss: 2.817e-01]
latex_v1:  46%|####6     | 1395/3000 [32:34<31:20,  1.17s/it, lr: 1.0e-04 loss: 2.817e-01]
latex_v1:  47%|####6     | 1396/3000 [32:34<28:17,  1.06s/it, lr: 1.0e-04 loss: 2.817e-01]
latex_v1:  47%|####6     | 1396/3000 [32:34<28:17,  1.06s/it, lr: 1.0e-04 loss: 2.817e-01]
latex_v1:  47%|####6     | 1396/3000 [32:34<28:17,  1.06s/it, lr: 1.0e-04 loss: 3.000e-01]
latex_v1:  47%|####6     | 1396/3000 [32:34<28:17,  1.06s/it, lr: 1.0e-04 loss: 3.000e-01]
latex_v1:  47%|####6     | 1397/3000 [32:34<26:01,  1.03it/s, lr: 1.0e-04 loss: 3.000e-01]
latex_v1:  47%|####6     | 1397/3000 [32:34<26:01,  1.03it/s, lr: 1.0e-04 loss: 3.000e-01]
latex_v1:  47%|####6     | 1397/3000 [32:36<26:01,  1.03it/s, lr: 1.0e-04 loss: 5.609e-01]
latex_v1:  47%|####6     | 1397/3000 [32:36<26:01,  1.03it/s, lr: 1.0e-04 loss: 5.609e-01]
latex_v1:  47%|####6     | 1398/3000 [32:36<30:30,  1.14s/it, lr: 1.0e-04 loss: 5.609e-01]
latex_v1:  47%|####6     | 1398/3000 [32:36<30:30,  1.14s/it, lr: 1.0e-04 loss: 5.609e-01]
latex_v1:  47%|####6     | 1398/3000 [32:38<30:30,  1.14s/it, lr: 1.0e-04 loss: 5.619e-01]
latex_v1:  47%|####6     | 1398/3000 [32:38<30:30,  1.14s/it, lr: 1.0e-04 loss: 5.619e-01]
latex_v1:  47%|####6     | 1399/3000 [32:38<33:45,  1.27s/it, lr: 1.0e-04 loss: 5.619e-01]
latex_v1:  47%|####6     | 1399/3000 [32:38<33:45,  1.27s/it, lr: 1.0e-04 loss: 5.619e-01]
latex_v1:  47%|####6     | 1399/3000 [32:39<33:45,  1.27s/it, lr: 1.0e-04 loss: 4.013e-01]
latex_v1:  47%|####6     | 1399/3000 [32:39<33:45,  1.27s/it, lr: 1.0e-04 loss: 4.013e-01]
latex_v1:  47%|####6     | 1400/3000 [32:40<33:44,  1.27s/it, lr: 1.0e-04 loss: 4.648e-02]
latex_v1:  47%|####6     | 1400/3000 [32:40<33:44,  1.27s/it, lr: 1.0e-04 loss: 4.648e-02]
latex_v1:  47%|####6     | 1401/3000 [32:40<27:14,  1.02s/it, lr: 1.0e-04 loss: 4.648e-02]
latex_v1:  47%|####6     | 1401/3000 [32:40<27:14,  1.02s/it, lr: 1.0e-04 loss: 4.648e-02]
latex_v1:  47%|####6     | 1401/3000 [32:43<27:14,  1.02s/it, lr: 1.0e-04 loss: 1.957e-01]
latex_v1:  47%|####6     | 1401/3000 [32:43<27:14,  1.02s/it, lr: 1.0e-04 loss: 1.957e-01]
latex_v1:  47%|####6     | 1402/3000 [32:43<39:14,  1.47s/it, lr: 1.0e-04 loss: 1.957e-01]
latex_v1:  47%|####6     | 1402/3000 [32:43<39:14,  1.47s/it, lr: 1.0e-04 loss: 1.957e-01]
latex_v1:  47%|####6     | 1402/3000 [32:45<39:14,  1.47s/it, lr: 1.0e-04 loss: 4.878e-01]
latex_v1:  47%|####6     | 1402/3000 [32:45<39:14,  1.47s/it, lr: 1.0e-04 loss: 4.878e-01]
latex_v1:  47%|####6     | 1403/3000 [32:45<41:04,  1.54s/it, lr: 1.0e-04 loss: 4.878e-01]
latex_v1:  47%|####6     | 1403/3000 [32:45<41:04,  1.54s/it, lr: 1.0e-04 loss: 4.878e-01]
latex_v1:  47%|####6     | 1403/3000 [32:46<41:04,  1.54s/it, lr: 1.0e-04 loss: 1.589e-01]
latex_v1:  47%|####6     | 1403/3000 [32:46<41:04,  1.54s/it, lr: 1.0e-04 loss: 1.589e-01]
latex_v1:  47%|####6     | 1404/3000 [32:46<41:06,  1.55s/it, lr: 1.0e-04 loss: 1.589e-01]
latex_v1:  47%|####6     | 1404/3000 [32:46<41:06,  1.55s/it, lr: 1.0e-04 loss: 1.589e-01]
latex_v1:  47%|####6     | 1404/3000 [32:48<41:06,  1.55s/it, lr: 1.0e-04 loss: 5.690e-01]
latex_v1:  47%|####6     | 1404/3000 [32:48<41:06,  1.55s/it, lr: 1.0e-04 loss: 5.690e-01]
latex_v1:  47%|####6     | 1405/3000 [32:48<40:56,  1.54s/it, lr: 1.0e-04 loss: 5.690e-01]
latex_v1:  47%|####6     | 1405/3000 [32:48<40:56,  1.54s/it, lr: 1.0e-04 loss: 5.690e-01]
latex_v1:  47%|####6     | 1405/3000 [32:49<40:56,  1.54s/it, lr: 1.0e-04 loss: 1.650e-01]
latex_v1:  47%|####6     | 1405/3000 [32:49<40:56,  1.54s/it, lr: 1.0e-04 loss: 1.650e-01]
latex_v1:  47%|####6     | 1406/3000 [32:49<34:53,  1.31s/it, lr: 1.0e-04 loss: 1.650e-01]
latex_v1:  47%|####6     | 1406/3000 [32:49<34:53,  1.31s/it, lr: 1.0e-04 loss: 1.650e-01]
latex_v1:  47%|####6     | 1406/3000 [32:50<34:53,  1.31s/it, lr: 1.0e-04 loss: 5.266e-01]
latex_v1:  47%|####6     | 1406/3000 [32:50<34:53,  1.31s/it, lr: 1.0e-04 loss: 5.266e-01]
latex_v1:  47%|####6     | 1407/3000 [32:50<32:57,  1.24s/it, lr: 1.0e-04 loss: 5.266e-01]
latex_v1:  47%|####6     | 1407/3000 [32:50<32:57,  1.24s/it, lr: 1.0e-04 loss: 5.266e-01]
latex_v1:  47%|####6     | 1407/3000 [32:50<32:57,  1.24s/it, lr: 1.0e-04 loss: 5.250e-01]
latex_v1:  47%|####6     | 1407/3000 [32:50<32:57,  1.24s/it, lr: 1.0e-04 loss: 5.250e-01]
latex_v1:  47%|####6     | 1408/3000 [32:50<28:55,  1.09s/it, lr: 1.0e-04 loss: 5.250e-01]
latex_v1:  47%|####6     | 1408/3000 [32:50<28:55,  1.09s/it, lr: 1.0e-04 loss: 5.250e-01]
latex_v1:  47%|####6     | 1408/3000 [32:53<28:55,  1.09s/it, lr: 1.0e-04 loss: 9.558e-02]
latex_v1:  47%|####6     | 1408/3000 [32:53<28:55,  1.09s/it, lr: 1.0e-04 loss: 9.558e-02]
latex_v1:  47%|####6     | 1409/3000 [32:53<41:35,  1.57s/it, lr: 1.0e-04 loss: 9.558e-02]
latex_v1:  47%|####6     | 1409/3000 [32:53<41:35,  1.57s/it, lr: 1.0e-04 loss: 9.558e-02]
latex_v1:  47%|####6     | 1409/3000 [32:55<41:35,  1.57s/it, lr: 1.0e-04 loss: 6.007e-01]
latex_v1:  47%|####6     | 1409/3000 [32:55<41:35,  1.57s/it, lr: 1.0e-04 loss: 6.007e-01]
latex_v1:  47%|####6     | 1410/3000 [32:56<41:33,  1.57s/it, lr: 1.0e-04 loss: 7.518e-02]
latex_v1:  47%|####6     | 1410/3000 [32:56<41:33,  1.57s/it, lr: 1.0e-04 loss: 7.518e-02]
latex_v1:  47%|####7     | 1411/3000 [32:56<31:54,  1.20s/it, lr: 1.0e-04 loss: 7.518e-02]
latex_v1:  47%|####7     | 1411/3000 [32:56<31:54,  1.20s/it, lr: 1.0e-04 loss: 7.518e-02]
latex_v1:  47%|####7     | 1411/3000 [32:59<31:54,  1.20s/it, lr: 1.0e-04 loss: 6.549e-01]
latex_v1:  47%|####7     | 1411/3000 [32:59<31:54,  1.20s/it, lr: 1.0e-04 loss: 6.549e-01]
latex_v1:  47%|####7     | 1412/3000 [32:59<42:25,  1.60s/it, lr: 1.0e-04 loss: 6.549e-01]
latex_v1:  47%|####7     | 1412/3000 [32:59<42:25,  1.60s/it, lr: 1.0e-04 loss: 6.549e-01]
latex_v1:  47%|####7     | 1412/3000 [33:01<42:25,  1.60s/it, lr: 1.0e-04 loss: 2.167e-01]
latex_v1:  47%|####7     | 1412/3000 [33:01<42:25,  1.60s/it, lr: 1.0e-04 loss: 2.167e-01]
latex_v1:  47%|####7     | 1413/3000 [33:01<41:58,  1.59s/it, lr: 1.0e-04 loss: 2.167e-01]
latex_v1:  47%|####7     | 1413/3000 [33:01<41:58,  1.59s/it, lr: 1.0e-04 loss: 2.167e-01]
latex_v1:  47%|####7     | 1413/3000 [33:04<41:58,  1.59s/it, lr: 1.0e-04 loss: 1.552e-01]
latex_v1:  47%|####7     | 1413/3000 [33:04<41:58,  1.59s/it, lr: 1.0e-04 loss: 1.552e-01]
latex_v1:  47%|####7     | 1414/3000 [33:04<52:20,  1.98s/it, lr: 1.0e-04 loss: 1.552e-01]
latex_v1:  47%|####7     | 1414/3000 [33:04<52:20,  1.98s/it, lr: 1.0e-04 loss: 1.552e-01]
latex_v1:  47%|####7     | 1414/3000 [33:05<52:20,  1.98s/it, lr: 1.0e-04 loss: 1.293e-01]
latex_v1:  47%|####7     | 1414/3000 [33:05<52:20,  1.98s/it, lr: 1.0e-04 loss: 1.293e-01]
latex_v1:  47%|####7     | 1415/3000 [33:05<43:10,  1.63s/it, lr: 1.0e-04 loss: 1.293e-01]
latex_v1:  47%|####7     | 1415/3000 [33:05<43:10,  1.63s/it, lr: 1.0e-04 loss: 1.293e-01]
latex_v1:  47%|####7     | 1415/3000 [33:06<43:10,  1.63s/it, lr: 1.0e-04 loss: 5.767e-01]
latex_v1:  47%|####7     | 1415/3000 [33:06<43:10,  1.63s/it, lr: 1.0e-04 loss: 5.767e-01]
latex_v1:  47%|####7     | 1416/3000 [33:06<44:54,  1.70s/it, lr: 1.0e-04 loss: 5.767e-01]
latex_v1:  47%|####7     | 1416/3000 [33:06<44:54,  1.70s/it, lr: 1.0e-04 loss: 5.767e-01]
latex_v1:  47%|####7     | 1416/3000 [33:07<44:54,  1.70s/it, lr: 1.0e-04 loss: 1.988e-01]
latex_v1:  47%|####7     | 1416/3000 [33:07<44:54,  1.70s/it, lr: 1.0e-04 loss: 1.988e-01]
latex_v1:  47%|####7     | 1417/3000 [33:07<37:45,  1.43s/it, lr: 1.0e-04 loss: 1.988e-01]
latex_v1:  47%|####7     | 1417/3000 [33:07<37:45,  1.43s/it, lr: 1.0e-04 loss: 1.988e-01]
latex_v1:  47%|####7     | 1417/3000 [33:09<37:45,  1.43s/it, lr: 1.0e-04 loss: 1.563e-01]
latex_v1:  47%|####7     | 1417/3000 [33:09<37:45,  1.43s/it, lr: 1.0e-04 loss: 1.563e-01]
latex_v1:  47%|####7     | 1418/3000 [33:09<38:40,  1.47s/it, lr: 1.0e-04 loss: 1.563e-01]
latex_v1:  47%|####7     | 1418/3000 [33:09<38:40,  1.47s/it, lr: 1.0e-04 loss: 1.563e-01]
latex_v1:  47%|####7     | 1418/3000 [33:10<38:40,  1.47s/it, lr: 1.0e-04 loss: 6.240e-01]
latex_v1:  47%|####7     | 1418/3000 [33:10<38:40,  1.47s/it, lr: 1.0e-04 loss: 6.240e-01]
latex_v1:  47%|####7     | 1419/3000 [33:10<38:37,  1.47s/it, lr: 1.0e-04 loss: 6.240e-01]
latex_v1:  47%|####7     | 1419/3000 [33:10<38:37,  1.47s/it, lr: 1.0e-04 loss: 6.240e-01]
latex_v1:  47%|####7     | 1419/3000 [33:11<38:37,  1.47s/it, lr: 1.0e-04 loss: 7.073e-01]
latex_v1:  47%|####7     | 1419/3000 [33:11<38:37,  1.47s/it, lr: 1.0e-04 loss: 7.073e-01]
latex_v1:  47%|####7     | 1420/3000 [33:14<38:36,  1.47s/it, lr: 1.0e-04 loss: 2.715e-01]
latex_v1:  47%|####7     | 1420/3000 [33:14<38:36,  1.47s/it, lr: 1.0e-04 loss: 2.715e-01]
latex_v1:  47%|####7     | 1421/3000 [33:14<38:09,  1.45s/it, lr: 1.0e-04 loss: 2.715e-01]
latex_v1:  47%|####7     | 1421/3000 [33:14<38:09,  1.45s/it, lr: 1.0e-04 loss: 2.715e-01]
latex_v1:  47%|####7     | 1421/3000 [33:16<38:09,  1.45s/it, lr: 1.0e-04 loss: 9.124e-02]
latex_v1:  47%|####7     | 1421/3000 [33:16<38:09,  1.45s/it, lr: 1.0e-04 loss: 9.124e-02]
latex_v1:  47%|####7     | 1422/3000 [33:16<41:03,  1.56s/it, lr: 1.0e-04 loss: 9.124e-02]
latex_v1:  47%|####7     | 1422/3000 [33:16<41:03,  1.56s/it, lr: 1.0e-04 loss: 9.124e-02]
latex_v1:  47%|####7     | 1422/3000 [33:17<41:03,  1.56s/it, lr: 1.0e-04 loss: 1.672e-01]
latex_v1:  47%|####7     | 1422/3000 [33:17<41:03,  1.56s/it, lr: 1.0e-04 loss: 1.672e-01]
latex_v1:  47%|####7     | 1423/3000 [33:17<35:36,  1.35s/it, lr: 1.0e-04 loss: 1.672e-01]
latex_v1:  47%|####7     | 1423/3000 [33:17<35:36,  1.35s/it, lr: 1.0e-04 loss: 1.672e-01]
latex_v1:  47%|####7     | 1423/3000 [33:18<35:36,  1.35s/it, lr: 1.0e-04 loss: 6.214e-02]
latex_v1:  47%|####7     | 1423/3000 [33:18<35:36,  1.35s/it, lr: 1.0e-04 loss: 6.214e-02]
latex_v1:  47%|####7     | 1424/3000 [33:18<36:46,  1.40s/it, lr: 1.0e-04 loss: 6.214e-02]
latex_v1:  47%|####7     | 1424/3000 [33:18<36:46,  1.40s/it, lr: 1.0e-04 loss: 6.214e-02]
latex_v1:  47%|####7     | 1424/3000 [33:21<36:46,  1.40s/it, lr: 1.0e-04 loss: 3.895e-01]
latex_v1:  47%|####7     | 1424/3000 [33:21<36:46,  1.40s/it, lr: 1.0e-04 loss: 3.895e-01]
latex_v1:  48%|####7     | 1425/3000 [33:21<45:46,  1.74s/it, lr: 1.0e-04 loss: 3.895e-01]
latex_v1:  48%|####7     | 1425/3000 [33:21<45:46,  1.74s/it, lr: 1.0e-04 loss: 3.895e-01]
latex_v1:  48%|####7     | 1425/3000 [33:21<45:46,  1.74s/it, lr: 1.0e-04 loss: 5.196e-01]
latex_v1:  48%|####7     | 1425/3000 [33:21<45:46,  1.74s/it, lr: 1.0e-04 loss: 5.196e-01]
latex_v1:  48%|####7     | 1426/3000 [33:21<38:28,  1.47s/it, lr: 1.0e-04 loss: 5.196e-01]
latex_v1:  48%|####7     | 1426/3000 [33:21<38:28,  1.47s/it, lr: 1.0e-04 loss: 5.196e-01]
latex_v1:  48%|####7     | 1426/3000 [33:24<38:28,  1.47s/it, lr: 1.0e-04 loss: 5.978e-01]
latex_v1:  48%|####7     | 1426/3000 [33:24<38:28,  1.47s/it, lr: 1.0e-04 loss: 5.978e-01]
latex_v1:  48%|####7     | 1427/3000 [33:24<43:19,  1.65s/it, lr: 1.0e-04 loss: 5.978e-01]
latex_v1:  48%|####7     | 1427/3000 [33:24<43:19,  1.65s/it, lr: 1.0e-04 loss: 5.978e-01]
latex_v1:  48%|####7     | 1427/3000 [33:24<43:19,  1.65s/it, lr: 1.0e-04 loss: 1.638e-01]
latex_v1:  48%|####7     | 1427/3000 [33:24<43:19,  1.65s/it, lr: 1.0e-04 loss: 1.638e-01]
latex_v1:  48%|####7     | 1428/3000 [33:24<36:26,  1.39s/it, lr: 1.0e-04 loss: 1.638e-01]
latex_v1:  48%|####7     | 1428/3000 [33:24<36:26,  1.39s/it, lr: 1.0e-04 loss: 1.638e-01]
latex_v1:  48%|####7     | 1428/3000 [33:27<36:26,  1.39s/it, lr: 1.0e-04 loss: 9.404e-02]
latex_v1:  48%|####7     | 1428/3000 [33:27<36:26,  1.39s/it, lr: 1.0e-04 loss: 9.404e-02]
latex_v1:  48%|####7     | 1429/3000 [33:27<47:51,  1.83s/it, lr: 1.0e-04 loss: 9.404e-02]
latex_v1:  48%|####7     | 1429/3000 [33:27<47:51,  1.83s/it, lr: 1.0e-04 loss: 9.404e-02]
latex_v1:  48%|####7     | 1429/3000 [33:29<47:51,  1.83s/it, lr: 1.0e-04 loss: 5.658e-02]
latex_v1:  48%|####7     | 1429/3000 [33:29<47:51,  1.83s/it, lr: 1.0e-04 loss: 5.658e-02]
latex_v1:  48%|####7     | 1430/3000 [33:30<47:50,  1.83s/it, lr: 1.0e-04 loss: 1.936e-01]
latex_v1:  48%|####7     | 1430/3000 [33:30<47:50,  1.83s/it, lr: 1.0e-04 loss: 1.936e-01]
latex_v1:  48%|####7     | 1431/3000 [33:30<30:26,  1.16s/it, lr: 1.0e-04 loss: 1.936e-01]
latex_v1:  48%|####7     | 1431/3000 [33:30<30:26,  1.16s/it, lr: 1.0e-04 loss: 1.936e-01]
latex_v1:  48%|####7     | 1431/3000 [33:31<30:26,  1.16s/it, lr: 1.0e-04 loss: 2.360e-01]
latex_v1:  48%|####7     | 1431/3000 [33:31<30:26,  1.16s/it, lr: 1.0e-04 loss: 2.360e-01]
latex_v1:  48%|####7     | 1432/3000 [33:31<32:05,  1.23s/it, lr: 1.0e-04 loss: 2.360e-01]
latex_v1:  48%|####7     | 1432/3000 [33:31<32:05,  1.23s/it, lr: 1.0e-04 loss: 2.360e-01]
latex_v1:  48%|####7     | 1432/3000 [33:32<32:05,  1.23s/it, lr: 1.0e-04 loss: 1.956e-01]
latex_v1:  48%|####7     | 1432/3000 [33:32<32:05,  1.23s/it, lr: 1.0e-04 loss: 1.956e-01]
latex_v1:  48%|####7     | 1433/3000 [33:32<28:53,  1.11s/it, lr: 1.0e-04 loss: 1.956e-01]
latex_v1:  48%|####7     | 1433/3000 [33:32<28:53,  1.11s/it, lr: 1.0e-04 loss: 1.956e-01]
latex_v1:  48%|####7     | 1433/3000 [33:33<28:53,  1.11s/it, lr: 1.0e-04 loss: 6.111e-01]
latex_v1:  48%|####7     | 1433/3000 [33:33<28:53,  1.11s/it, lr: 1.0e-04 loss: 6.111e-01]
latex_v1:  48%|####7     | 1434/3000 [33:33<26:25,  1.01s/it, lr: 1.0e-04 loss: 6.111e-01]
latex_v1:  48%|####7     | 1434/3000 [33:33<26:25,  1.01s/it, lr: 1.0e-04 loss: 6.111e-01]
latex_v1:  48%|####7     | 1434/3000 [33:34<26:25,  1.01s/it, lr: 1.0e-04 loss: 1.759e-01]
latex_v1:  48%|####7     | 1434/3000 [33:34<26:25,  1.01s/it, lr: 1.0e-04 loss: 1.759e-01]
latex_v1:  48%|####7     | 1435/3000 [33:34<29:34,  1.13s/it, lr: 1.0e-04 loss: 1.759e-01]
latex_v1:  48%|####7     | 1435/3000 [33:34<29:34,  1.13s/it, lr: 1.0e-04 loss: 1.759e-01]
latex_v1:  48%|####7     | 1435/3000 [33:35<29:34,  1.13s/it, lr: 1.0e-04 loss: 3.157e-01]
latex_v1:  48%|####7     | 1435/3000 [33:35<29:34,  1.13s/it, lr: 1.0e-04 loss: 3.157e-01]
latex_v1:  48%|####7     | 1436/3000 [33:35<26:50,  1.03s/it, lr: 1.0e-04 loss: 3.157e-01]
latex_v1:  48%|####7     | 1436/3000 [33:35<26:50,  1.03s/it, lr: 1.0e-04 loss: 3.157e-01]
latex_v1:  48%|####7     | 1436/3000 [33:36<26:50,  1.03s/it, lr: 1.0e-04 loss: 1.085e-01]
latex_v1:  48%|####7     | 1436/3000 [33:36<26:50,  1.03s/it, lr: 1.0e-04 loss: 1.085e-01]
latex_v1:  48%|####7     | 1437/3000 [33:36<29:42,  1.14s/it, lr: 1.0e-04 loss: 1.085e-01]
latex_v1:  48%|####7     | 1437/3000 [33:36<29:42,  1.14s/it, lr: 1.0e-04 loss: 1.085e-01]
latex_v1:  48%|####7     | 1437/3000 [33:39<29:42,  1.14s/it, lr: 1.0e-04 loss: 1.687e-01]
latex_v1:  48%|####7     | 1437/3000 [33:39<29:42,  1.14s/it, lr: 1.0e-04 loss: 1.687e-01]
latex_v1:  48%|####7     | 1438/3000 [33:39<42:29,  1.63s/it, lr: 1.0e-04 loss: 1.687e-01]
latex_v1:  48%|####7     | 1438/3000 [33:39<42:29,  1.63s/it, lr: 1.0e-04 loss: 1.687e-01]
latex_v1:  48%|####7     | 1438/3000 [33:41<42:29,  1.63s/it, lr: 1.0e-04 loss: 1.537e-01]
latex_v1:  48%|####7     | 1438/3000 [33:41<42:29,  1.63s/it, lr: 1.0e-04 loss: 1.537e-01]
latex_v1:  48%|####7     | 1439/3000 [33:41<46:37,  1.79s/it, lr: 1.0e-04 loss: 1.537e-01]
latex_v1:  48%|####7     | 1439/3000 [33:41<46:37,  1.79s/it, lr: 1.0e-04 loss: 1.537e-01]
latex_v1:  48%|####7     | 1439/3000 [33:43<46:37,  1.79s/it, lr: 1.0e-04 loss: 6.055e-01]
latex_v1:  48%|####7     | 1439/3000 [33:43<46:37,  1.79s/it, lr: 1.0e-04 loss: 6.055e-01]
latex_v1:  48%|####8     | 1440/3000 [33:44<46:35,  1.79s/it, lr: 1.0e-04 loss: 5.520e-02]
latex_v1:  48%|####8     | 1440/3000 [33:44<46:35,  1.79s/it, lr: 1.0e-04 loss: 5.520e-02]
latex_v1:  48%|####8     | 1441/3000 [33:44<33:21,  1.28s/it, lr: 1.0e-04 loss: 5.520e-02]
latex_v1:  48%|####8     | 1441/3000 [33:44<33:21,  1.28s/it, lr: 1.0e-04 loss: 5.520e-02]
latex_v1:  48%|####8     | 1441/3000 [33:46<33:21,  1.28s/it, lr: 1.0e-04 loss: 1.528e-01]
latex_v1:  48%|####8     | 1441/3000 [33:46<33:21,  1.28s/it, lr: 1.0e-04 loss: 1.528e-01]
latex_v1:  48%|####8     | 1442/3000 [33:46<34:11,  1.32s/it, lr: 1.0e-04 loss: 1.528e-01]
latex_v1:  48%|####8     | 1442/3000 [33:46<34:11,  1.32s/it, lr: 1.0e-04 loss: 1.528e-01]
latex_v1:  48%|####8     | 1442/3000 [33:47<34:11,  1.32s/it, lr: 1.0e-04 loss: 7.254e-01]
latex_v1:  48%|####8     | 1442/3000 [33:47<34:11,  1.32s/it, lr: 1.0e-04 loss: 7.254e-01]
latex_v1:  48%|####8     | 1443/3000 [33:47<34:14,  1.32s/it, lr: 1.0e-04 loss: 7.254e-01]
latex_v1:  48%|####8     | 1443/3000 [33:47<34:14,  1.32s/it, lr: 1.0e-04 loss: 7.254e-01]
latex_v1:  48%|####8     | 1443/3000 [33:48<34:14,  1.32s/it, lr: 1.0e-04 loss: 8.628e-02]
latex_v1:  48%|####8     | 1443/3000 [33:48<34:14,  1.32s/it, lr: 1.0e-04 loss: 8.628e-02]
latex_v1:  48%|####8     | 1444/3000 [33:48<35:43,  1.38s/it, lr: 1.0e-04 loss: 8.628e-02]
latex_v1:  48%|####8     | 1444/3000 [33:48<35:43,  1.38s/it, lr: 1.0e-04 loss: 8.628e-02]
latex_v1:  48%|####8     | 1444/3000 [33:49<35:43,  1.38s/it, lr: 1.0e-04 loss: 7.293e-01]
latex_v1:  48%|####8     | 1444/3000 [33:49<35:43,  1.38s/it, lr: 1.0e-04 loss: 7.293e-01]
latex_v1:  48%|####8     | 1445/3000 [33:49<31:06,  1.20s/it, lr: 1.0e-04 loss: 7.293e-01]
latex_v1:  48%|####8     | 1445/3000 [33:49<31:06,  1.20s/it, lr: 1.0e-04 loss: 7.293e-01]
latex_v1:  48%|####8     | 1445/3000 [33:50<31:06,  1.20s/it, lr: 1.0e-04 loss: 6.197e-02]
latex_v1:  48%|####8     | 1445/3000 [33:50<31:06,  1.20s/it, lr: 1.0e-04 loss: 6.197e-02]
latex_v1:  48%|####8     | 1446/3000 [33:50<30:49,  1.19s/it, lr: 1.0e-04 loss: 6.197e-02]
latex_v1:  48%|####8     | 1446/3000 [33:50<30:49,  1.19s/it, lr: 1.0e-04 loss: 6.197e-02]
latex_v1:  48%|####8     | 1446/3000 [33:52<30:49,  1.19s/it, lr: 1.0e-04 loss: 3.440e-01]
latex_v1:  48%|####8     | 1446/3000 [33:52<30:49,  1.19s/it, lr: 1.0e-04 loss: 3.440e-01]
latex_v1:  48%|####8     | 1447/3000 [33:52<33:17,  1.29s/it, lr: 1.0e-04 loss: 3.440e-01]
latex_v1:  48%|####8     | 1447/3000 [33:52<33:17,  1.29s/it, lr: 1.0e-04 loss: 3.440e-01]
latex_v1:  48%|####8     | 1447/3000 [33:53<33:17,  1.29s/it, lr: 1.0e-04 loss: 4.003e-01]
latex_v1:  48%|####8     | 1447/3000 [33:53<33:17,  1.29s/it, lr: 1.0e-04 loss: 4.003e-01]
latex_v1:  48%|####8     | 1448/3000 [33:53<32:25,  1.25s/it, lr: 1.0e-04 loss: 4.003e-01]
latex_v1:  48%|####8     | 1448/3000 [33:53<32:25,  1.25s/it, lr: 1.0e-04 loss: 4.003e-01]
latex_v1:  48%|####8     | 1448/3000 [33:54<32:25,  1.25s/it, lr: 1.0e-04 loss: 4.834e-01]
latex_v1:  48%|####8     | 1448/3000 [33:54<32:25,  1.25s/it, lr: 1.0e-04 loss: 4.834e-01]
latex_v1:  48%|####8     | 1449/3000 [33:54<28:29,  1.10s/it, lr: 1.0e-04 loss: 4.834e-01]
latex_v1:  48%|####8     | 1449/3000 [33:54<28:29,  1.10s/it, lr: 1.0e-04 loss: 4.834e-01]
latex_v1:  48%|####8     | 1449/3000 [33:56<28:29,  1.10s/it, lr: 1.0e-04 loss: 4.241e-02]
latex_v1:  48%|####8     | 1449/3000 [33:56<28:29,  1.10s/it, lr: 1.0e-04 loss: 4.241e-02]
latex_v1:  48%|####8     | 1450/3000 [33:56<28:28,  1.10s/it, lr: 1.0e-04 loss: 5.854e-01]
latex_v1:  48%|####8     | 1450/3000 [33:56<28:28,  1.10s/it, lr: 1.0e-04 loss: 5.854e-01]
latex_v1:  48%|####8     | 1451/3000 [33:56<19:48,  1.30it/s, lr: 1.0e-04 loss: 5.854e-01]
latex_v1:  48%|####8     | 1451/3000 [33:56<19:48,  1.30it/s, lr: 1.0e-04 loss: 5.854e-01]
latex_v1:  48%|####8     | 1451/3000 [33:58<19:48,  1.30it/s, lr: 1.0e-04 loss: 7.023e-01]
latex_v1:  48%|####8     | 1451/3000 [33:58<19:48,  1.30it/s, lr: 1.0e-04 loss: 7.023e-01]
latex_v1:  48%|####8     | 1452/3000 [33:58<23:31,  1.10it/s, lr: 1.0e-04 loss: 7.023e-01]
latex_v1:  48%|####8     | 1452/3000 [33:58<23:31,  1.10it/s, lr: 1.0e-04 loss: 7.023e-01]
latex_v1:  48%|####8     | 1452/3000 [33:59<23:31,  1.10it/s, lr: 1.0e-04 loss: 7.400e-01]
latex_v1:  48%|####8     | 1452/3000 [33:59<23:31,  1.10it/s, lr: 1.0e-04 loss: 7.400e-01]
latex_v1:  48%|####8     | 1453/3000 [33:59<25:16,  1.02it/s, lr: 1.0e-04 loss: 7.400e-01]
latex_v1:  48%|####8     | 1453/3000 [33:59<25:16,  1.02it/s, lr: 1.0e-04 loss: 7.400e-01]
latex_v1:  48%|####8     | 1453/3000 [34:02<25:16,  1.02it/s, lr: 1.0e-04 loss: 3.996e-01]
latex_v1:  48%|####8     | 1453/3000 [34:02<25:16,  1.02it/s, lr: 1.0e-04 loss: 3.996e-01]
latex_v1:  48%|####8     | 1454/3000 [34:02<38:19,  1.49s/it, lr: 1.0e-04 loss: 3.996e-01]
latex_v1:  48%|####8     | 1454/3000 [34:02<38:19,  1.49s/it, lr: 1.0e-04 loss: 3.996e-01]
latex_v1:  48%|####8     | 1454/3000 [34:04<38:19,  1.49s/it, lr: 1.0e-04 loss: 1.430e-01]
latex_v1:  48%|####8     | 1454/3000 [34:04<38:19,  1.49s/it, lr: 1.0e-04 loss: 1.430e-01]
latex_v1:  48%|####8     | 1455/3000 [34:04<39:56,  1.55s/it, lr: 1.0e-04 loss: 1.430e-01]
latex_v1:  48%|####8     | 1455/3000 [34:04<39:56,  1.55s/it, lr: 1.0e-04 loss: 1.430e-01]
latex_v1:  48%|####8     | 1455/3000 [34:05<39:56,  1.55s/it, lr: 1.0e-04 loss: 4.123e-01]
latex_v1:  48%|####8     | 1455/3000 [34:05<39:56,  1.55s/it, lr: 1.0e-04 loss: 4.123e-01]
latex_v1:  49%|####8     | 1456/3000 [34:05<39:47,  1.55s/it, lr: 1.0e-04 loss: 4.123e-01]
latex_v1:  49%|####8     | 1456/3000 [34:05<39:47,  1.55s/it, lr: 1.0e-04 loss: 4.123e-01]
latex_v1:  49%|####8     | 1456/3000 [34:07<39:47,  1.55s/it, lr: 1.0e-04 loss: 5.876e-01]
latex_v1:  49%|####8     | 1456/3000 [34:07<39:47,  1.55s/it, lr: 1.0e-04 loss: 5.876e-01]
latex_v1:  49%|####8     | 1457/3000 [34:07<39:13,  1.53s/it, lr: 1.0e-04 loss: 5.876e-01]
latex_v1:  49%|####8     | 1457/3000 [34:07<39:13,  1.53s/it, lr: 1.0e-04 loss: 5.876e-01]
latex_v1:  49%|####8     | 1457/3000 [34:07<39:13,  1.53s/it, lr: 1.0e-04 loss: 2.520e-01]
latex_v1:  49%|####8     | 1457/3000 [34:07<39:13,  1.53s/it, lr: 1.0e-04 loss: 2.520e-01]
latex_v1:  49%|####8     | 1458/3000 [34:07<33:30,  1.30s/it, lr: 1.0e-04 loss: 2.520e-01]
latex_v1:  49%|####8     | 1458/3000 [34:07<33:30,  1.30s/it, lr: 1.0e-04 loss: 2.520e-01]
latex_v1:  49%|####8     | 1458/3000 [34:08<33:30,  1.30s/it, lr: 1.0e-04 loss: 3.903e-01]
latex_v1:  49%|####8     | 1458/3000 [34:08<33:30,  1.30s/it, lr: 1.0e-04 loss: 3.903e-01]
latex_v1:  49%|####8     | 1459/3000 [34:08<29:21,  1.14s/it, lr: 1.0e-04 loss: 3.903e-01]
latex_v1:  49%|####8     | 1459/3000 [34:08<29:21,  1.14s/it, lr: 1.0e-04 loss: 3.903e-01]
latex_v1:  49%|####8     | 1459/3000 [34:10<29:21,  1.14s/it, lr: 1.0e-04 loss: 5.306e-01]
latex_v1:  49%|####8     | 1459/3000 [34:10<29:21,  1.14s/it, lr: 1.0e-04 loss: 5.306e-01]
latex_v1:  49%|####8     | 1460/3000 [34:11<29:20,  1.14s/it, lr: 1.0e-04 loss: 4.424e-01]
latex_v1:  49%|####8     | 1460/3000 [34:11<29:20,  1.14s/it, lr: 1.0e-04 loss: 4.424e-01]
latex_v1:  49%|####8     | 1461/3000 [34:11<24:54,  1.03it/s, lr: 1.0e-04 loss: 4.424e-01]
latex_v1:  49%|####8     | 1461/3000 [34:11<24:54,  1.03it/s, lr: 1.0e-04 loss: 4.424e-01]
latex_v1:  49%|####8     | 1461/3000 [34:12<24:54,  1.03it/s, lr: 1.0e-04 loss: 4.415e-02]
latex_v1:  49%|####8     | 1461/3000 [34:12<24:54,  1.03it/s, lr: 1.0e-04 loss: 4.415e-02]
latex_v1:  49%|####8     | 1462/3000 [34:12<26:13,  1.02s/it, lr: 1.0e-04 loss: 4.415e-02]
latex_v1:  49%|####8     | 1462/3000 [34:12<26:13,  1.02s/it, lr: 1.0e-04 loss: 4.415e-02]
latex_v1:  49%|####8     | 1462/3000 [34:15<26:13,  1.02s/it, lr: 1.0e-04 loss: 4.604e-02]
latex_v1:  49%|####8     | 1462/3000 [34:15<26:13,  1.02s/it, lr: 1.0e-04 loss: 4.604e-02]
latex_v1:  49%|####8     | 1463/3000 [34:15<38:31,  1.50s/it, lr: 1.0e-04 loss: 4.604e-02]
latex_v1:  49%|####8     | 1463/3000 [34:15<38:31,  1.50s/it, lr: 1.0e-04 loss: 4.604e-02]
latex_v1:  49%|####8     | 1463/3000 [34:17<38:31,  1.50s/it, lr: 1.0e-04 loss: 4.943e-01]
latex_v1:  49%|####8     | 1463/3000 [34:17<38:31,  1.50s/it, lr: 1.0e-04 loss: 4.943e-01]
latex_v1:  49%|####8     | 1464/3000 [34:17<38:12,  1.49s/it, lr: 1.0e-04 loss: 4.943e-01]
latex_v1:  49%|####8     | 1464/3000 [34:17<38:12,  1.49s/it, lr: 1.0e-04 loss: 4.943e-01]
latex_v1:  49%|####8     | 1464/3000 [34:17<38:12,  1.49s/it, lr: 1.0e-04 loss: 6.175e-01]
latex_v1:  49%|####8     | 1464/3000 [34:17<38:12,  1.49s/it, lr: 1.0e-04 loss: 6.175e-01]
latex_v1:  49%|####8     | 1465/3000 [34:17<32:56,  1.29s/it, lr: 1.0e-04 loss: 6.175e-01]
latex_v1:  49%|####8     | 1465/3000 [34:17<32:56,  1.29s/it, lr: 1.0e-04 loss: 6.175e-01]
latex_v1:  49%|####8     | 1465/3000 [34:19<32:56,  1.29s/it, lr: 1.0e-04 loss: 3.035e-01]
latex_v1:  49%|####8     | 1465/3000 [34:19<32:56,  1.29s/it, lr: 1.0e-04 loss: 3.035e-01]
latex_v1:  49%|####8     | 1466/3000 [34:19<32:10,  1.26s/it, lr: 1.0e-04 loss: 3.035e-01]
latex_v1:  49%|####8     | 1466/3000 [34:19<32:10,  1.26s/it, lr: 1.0e-04 loss: 3.035e-01]
latex_v1:  49%|####8     | 1466/3000 [34:20<32:10,  1.26s/it, lr: 1.0e-04 loss: 3.862e-01]
latex_v1:  49%|####8     | 1466/3000 [34:20<32:10,  1.26s/it, lr: 1.0e-04 loss: 3.862e-01]
latex_v1:  49%|####8     | 1467/3000 [34:20<29:58,  1.17s/it, lr: 1.0e-04 loss: 3.862e-01]
latex_v1:  49%|####8     | 1467/3000 [34:20<29:58,  1.17s/it, lr: 1.0e-04 loss: 3.862e-01]
latex_v1:  49%|####8     | 1467/3000 [34:21<29:58,  1.17s/it, lr: 1.0e-04 loss: 4.993e-01]
latex_v1:  49%|####8     | 1467/3000 [34:21<29:58,  1.17s/it, lr: 1.0e-04 loss: 4.993e-01]
latex_v1:  49%|####8     | 1468/3000 [34:21<31:40,  1.24s/it, lr: 1.0e-04 loss: 4.993e-01]
latex_v1:  49%|####8     | 1468/3000 [34:21<31:40,  1.24s/it, lr: 1.0e-04 loss: 4.993e-01]
latex_v1:  49%|####8     | 1468/3000 [34:22<31:40,  1.24s/it, lr: 1.0e-04 loss: 1.821e-01]
latex_v1:  49%|####8     | 1468/3000 [34:22<31:40,  1.24s/it, lr: 1.0e-04 loss: 1.821e-01]
latex_v1:  49%|####8     | 1469/3000 [34:22<31:55,  1.25s/it, lr: 1.0e-04 loss: 1.821e-01]
latex_v1:  49%|####8     | 1469/3000 [34:22<31:55,  1.25s/it, lr: 1.0e-04 loss: 1.821e-01]
latex_v1:  49%|####8     | 1469/3000 [34:23<31:55,  1.25s/it, lr: 1.0e-04 loss: 8.177e-01]
latex_v1:  49%|####8     | 1469/3000 [34:23<31:55,  1.25s/it, lr: 1.0e-04 loss: 8.177e-01]
latex_v1:  49%|####9     | 1470/3000 [34:25<31:54,  1.25s/it, lr: 1.0e-04 loss: 9.768e-02]
latex_v1:  49%|####9     | 1470/3000 [34:25<31:54,  1.25s/it, lr: 1.0e-04 loss: 9.768e-02]
latex_v1:  49%|####9     | 1471/3000 [34:25<25:03,  1.02it/s, lr: 1.0e-04 loss: 9.768e-02]
latex_v1:  49%|####9     | 1471/3000 [34:25<25:03,  1.02it/s, lr: 1.0e-04 loss: 9.768e-02]
latex_v1:  49%|####9     | 1471/3000 [34:25<25:03,  1.02it/s, lr: 1.0e-04 loss: 5.515e-01]
latex_v1:  49%|####9     | 1471/3000 [34:25<25:03,  1.02it/s, lr: 1.0e-04 loss: 5.515e-01]
latex_v1:  49%|####9     | 1472/3000 [34:25<23:38,  1.08it/s, lr: 1.0e-04 loss: 5.515e-01]
latex_v1:  49%|####9     | 1472/3000 [34:25<23:38,  1.08it/s, lr: 1.0e-04 loss: 5.515e-01]
latex_v1:  49%|####9     | 1472/3000 [34:26<23:38,  1.08it/s, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:  49%|####9     | 1472/3000 [34:26<23:38,  1.08it/s, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:  49%|####9     | 1473/3000 [34:26<22:23,  1.14it/s, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:  49%|####9     | 1473/3000 [34:26<22:23,  1.14it/s, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:  49%|####9     | 1473/3000 [34:27<22:23,  1.14it/s, lr: 1.0e-04 loss: 7.277e-02]
latex_v1:  49%|####9     | 1473/3000 [34:27<22:23,  1.14it/s, lr: 1.0e-04 loss: 7.277e-02]
latex_v1:  49%|####9     | 1474/3000 [34:27<21:25,  1.19it/s, lr: 1.0e-04 loss: 7.277e-02]
latex_v1:  49%|####9     | 1474/3000 [34:27<21:25,  1.19it/s, lr: 1.0e-04 loss: 7.277e-02]
latex_v1:  49%|####9     | 1474/3000 [34:29<21:25,  1.19it/s, lr: 1.0e-04 loss: 1.133e-01]
latex_v1:  49%|####9     | 1474/3000 [34:29<21:25,  1.19it/s, lr: 1.0e-04 loss: 1.133e-01]
latex_v1:  49%|####9     | 1475/3000 [34:29<28:31,  1.12s/it, lr: 1.0e-04 loss: 1.133e-01]
latex_v1:  49%|####9     | 1475/3000 [34:29<28:31,  1.12s/it, lr: 1.0e-04 loss: 1.133e-01]
latex_v1:  49%|####9     | 1475/3000 [34:30<28:31,  1.12s/it, lr: 1.0e-04 loss: 1.883e-01]
latex_v1:  49%|####9     | 1475/3000 [34:30<28:31,  1.12s/it, lr: 1.0e-04 loss: 1.883e-01]
latex_v1:  49%|####9     | 1476/3000 [34:30<31:48,  1.25s/it, lr: 1.0e-04 loss: 1.883e-01]
latex_v1:  49%|####9     | 1476/3000 [34:30<31:48,  1.25s/it, lr: 1.0e-04 loss: 1.883e-01]
latex_v1:  49%|####9     | 1476/3000 [34:31<31:48,  1.25s/it, lr: 1.0e-04 loss: 2.805e-02]
latex_v1:  49%|####9     | 1476/3000 [34:31<31:48,  1.25s/it, lr: 1.0e-04 loss: 2.805e-02]
latex_v1:  49%|####9     | 1477/3000 [34:31<28:06,  1.11s/it, lr: 1.0e-04 loss: 2.805e-02]
latex_v1:  49%|####9     | 1477/3000 [34:31<28:06,  1.11s/it, lr: 1.0e-04 loss: 2.805e-02]
latex_v1:  49%|####9     | 1477/3000 [34:32<28:06,  1.11s/it, lr: 1.0e-04 loss: 1.439e-01]
latex_v1:  49%|####9     | 1477/3000 [34:32<28:06,  1.11s/it, lr: 1.0e-04 loss: 1.439e-01]
latex_v1:  49%|####9     | 1478/3000 [34:32<30:27,  1.20s/it, lr: 1.0e-04 loss: 1.439e-01]
latex_v1:  49%|####9     | 1478/3000 [34:32<30:27,  1.20s/it, lr: 1.0e-04 loss: 1.439e-01]
latex_v1:  49%|####9     | 1478/3000 [34:33<30:27,  1.20s/it, lr: 1.0e-04 loss: 4.387e-01]
latex_v1:  49%|####9     | 1478/3000 [34:33<30:27,  1.20s/it, lr: 1.0e-04 loss: 4.387e-01]
latex_v1:  49%|####9     | 1479/3000 [34:33<27:05,  1.07s/it, lr: 1.0e-04 loss: 4.387e-01]
latex_v1:  49%|####9     | 1479/3000 [34:33<27:05,  1.07s/it, lr: 1.0e-04 loss: 4.387e-01]
latex_v1:  49%|####9     | 1479/3000 [34:34<27:05,  1.07s/it, lr: 1.0e-04 loss: 5.015e-01]
latex_v1:  49%|####9     | 1479/3000 [34:34<27:05,  1.07s/it, lr: 1.0e-04 loss: 5.015e-01]
latex_v1:  49%|####9     | 1480/3000 [34:35<27:04,  1.07s/it, lr: 1.0e-04 loss: 9.429e-02]
latex_v1:  49%|####9     | 1480/3000 [34:35<27:04,  1.07s/it, lr: 1.0e-04 loss: 9.429e-02]
latex_v1:  49%|####9     | 1481/3000 [34:35<22:26,  1.13it/s, lr: 1.0e-04 loss: 9.429e-02]
latex_v1:  49%|####9     | 1481/3000 [34:35<22:26,  1.13it/s, lr: 1.0e-04 loss: 9.429e-02]
latex_v1:  49%|####9     | 1481/3000 [34:36<22:26,  1.13it/s, lr: 1.0e-04 loss: 2.465e-01]
latex_v1:  49%|####9     | 1481/3000 [34:36<22:26,  1.13it/s, lr: 1.0e-04 loss: 2.465e-01]
latex_v1:  49%|####9     | 1482/3000 [34:36<23:02,  1.10it/s, lr: 1.0e-04 loss: 2.465e-01]
latex_v1:  49%|####9     | 1482/3000 [34:36<23:02,  1.10it/s, lr: 1.0e-04 loss: 2.465e-01]
latex_v1:  49%|####9     | 1482/3000 [34:37<23:02,  1.10it/s, lr: 1.0e-04 loss: 6.176e-01]
latex_v1:  49%|####9     | 1482/3000 [34:37<23:02,  1.10it/s, lr: 1.0e-04 loss: 6.176e-01]
latex_v1:  49%|####9     | 1483/3000 [34:37<22:06,  1.14it/s, lr: 1.0e-04 loss: 6.176e-01]
latex_v1:  49%|####9     | 1483/3000 [34:37<22:06,  1.14it/s, lr: 1.0e-04 loss: 6.176e-01]
latex_v1:  49%|####9     | 1483/3000 [34:38<22:06,  1.14it/s, lr: 1.0e-04 loss: 3.092e-01]
latex_v1:  49%|####9     | 1483/3000 [34:38<22:06,  1.14it/s, lr: 1.0e-04 loss: 3.092e-01]
latex_v1:  49%|####9     | 1484/3000 [34:38<25:17,  1.00s/it, lr: 1.0e-04 loss: 3.092e-01]
latex_v1:  49%|####9     | 1484/3000 [34:38<25:17,  1.00s/it, lr: 1.0e-04 loss: 3.092e-01]
latex_v1:  49%|####9     | 1484/3000 [34:39<25:17,  1.00s/it, lr: 1.0e-04 loss: 2.071e-01]
latex_v1:  49%|####9     | 1484/3000 [34:39<25:17,  1.00s/it, lr: 1.0e-04 loss: 2.071e-01]
latex_v1:  50%|####9     | 1485/3000 [34:39<23:28,  1.08it/s, lr: 1.0e-04 loss: 2.071e-01]
latex_v1:  50%|####9     | 1485/3000 [34:39<23:28,  1.08it/s, lr: 1.0e-04 loss: 2.071e-01]
latex_v1:  50%|####9     | 1485/3000 [34:40<23:28,  1.08it/s, lr: 1.0e-04 loss: 7.352e-01]
latex_v1:  50%|####9     | 1485/3000 [34:40<23:28,  1.08it/s, lr: 1.0e-04 loss: 7.352e-01]
latex_v1:  50%|####9     | 1486/3000 [34:40<25:11,  1.00it/s, lr: 1.0e-04 loss: 7.352e-01]
latex_v1:  50%|####9     | 1486/3000 [34:40<25:11,  1.00it/s, lr: 1.0e-04 loss: 7.352e-01]
latex_v1:  50%|####9     | 1486/3000 [34:41<25:11,  1.00it/s, lr: 1.0e-04 loss: 6.034e-01]
latex_v1:  50%|####9     | 1486/3000 [34:41<25:11,  1.00it/s, lr: 1.0e-04 loss: 6.034e-01]
latex_v1:  50%|####9     | 1487/3000 [34:41<23:19,  1.08it/s, lr: 1.0e-04 loss: 6.034e-01]
latex_v1:  50%|####9     | 1487/3000 [34:41<23:19,  1.08it/s, lr: 1.0e-04 loss: 6.034e-01]
latex_v1:  50%|####9     | 1487/3000 [34:43<23:19,  1.08it/s, lr: 1.0e-04 loss: 3.644e-01]
latex_v1:  50%|####9     | 1487/3000 [34:43<23:19,  1.08it/s, lr: 1.0e-04 loss: 3.644e-01]
latex_v1:  50%|####9     | 1488/3000 [34:43<27:25,  1.09s/it, lr: 1.0e-04 loss: 3.644e-01]
latex_v1:  50%|####9     | 1488/3000 [34:43<27:25,  1.09s/it, lr: 1.0e-04 loss: 3.644e-01]
latex_v1:  50%|####9     | 1488/3000 [34:44<27:25,  1.09s/it, lr: 1.0e-04 loss: 6.330e-01]
latex_v1:  50%|####9     | 1488/3000 [34:44<27:25,  1.09s/it, lr: 1.0e-04 loss: 6.330e-01]
latex_v1:  50%|####9     | 1489/3000 [34:44<24:53,  1.01it/s, lr: 1.0e-04 loss: 6.330e-01]
latex_v1:  50%|####9     | 1489/3000 [34:44<24:53,  1.01it/s, lr: 1.0e-04 loss: 6.330e-01]
latex_v1:  50%|####9     | 1489/3000 [34:45<24:53,  1.01it/s, lr: 1.0e-04 loss: 1.438e-01]
latex_v1:  50%|####9     | 1489/3000 [34:45<24:53,  1.01it/s, lr: 1.0e-04 loss: 1.438e-01]
latex_v1:  50%|####9     | 1490/3000 [34:47<24:52,  1.01it/s, lr: 1.0e-04 loss: 5.927e-01]
latex_v1:  50%|####9     | 1490/3000 [34:47<24:52,  1.01it/s, lr: 1.0e-04 loss: 5.927e-01]
latex_v1:  50%|####9     | 1491/3000 [34:47<24:20,  1.03it/s, lr: 1.0e-04 loss: 5.927e-01]
latex_v1:  50%|####9     | 1491/3000 [34:47<24:20,  1.03it/s, lr: 1.0e-04 loss: 5.927e-01]
latex_v1:  50%|####9     | 1491/3000 [34:48<24:20,  1.03it/s, lr: 1.0e-04 loss: 7.001e-01]
latex_v1:  50%|####9     | 1491/3000 [34:48<24:20,  1.03it/s, lr: 1.0e-04 loss: 7.001e-01]
latex_v1:  50%|####9     | 1492/3000 [34:48<22:58,  1.09it/s, lr: 1.0e-04 loss: 7.001e-01]
latex_v1:  50%|####9     | 1492/3000 [34:48<22:58,  1.09it/s, lr: 1.0e-04 loss: 7.001e-01]
latex_v1:  50%|####9     | 1492/3000 [34:49<22:58,  1.09it/s, lr: 1.0e-04 loss: 1.483e-01]
latex_v1:  50%|####9     | 1492/3000 [34:49<22:58,  1.09it/s, lr: 1.0e-04 loss: 1.483e-01]
latex_v1:  50%|####9     | 1493/3000 [34:49<27:06,  1.08s/it, lr: 1.0e-04 loss: 1.483e-01]
latex_v1:  50%|####9     | 1493/3000 [34:49<27:06,  1.08s/it, lr: 1.0e-04 loss: 1.483e-01]
latex_v1:  50%|####9     | 1493/3000 [34:51<27:06,  1.08s/it, lr: 1.0e-04 loss: 2.172e-01]
latex_v1:  50%|####9     | 1493/3000 [34:51<27:06,  1.08s/it, lr: 1.0e-04 loss: 2.172e-01]
latex_v1:  50%|####9     | 1494/3000 [34:51<28:46,  1.15s/it, lr: 1.0e-04 loss: 2.172e-01]
latex_v1:  50%|####9     | 1494/3000 [34:51<28:46,  1.15s/it, lr: 1.0e-04 loss: 2.172e-01]
latex_v1:  50%|####9     | 1494/3000 [34:52<28:46,  1.15s/it, lr: 1.0e-04 loss: 1.046e-02]
latex_v1:  50%|####9     | 1494/3000 [34:52<28:46,  1.15s/it, lr: 1.0e-04 loss: 1.046e-02]
latex_v1:  50%|####9     | 1495/3000 [34:52<33:25,  1.33s/it, lr: 1.0e-04 loss: 1.046e-02]
latex_v1:  50%|####9     | 1495/3000 [34:52<33:25,  1.33s/it, lr: 1.0e-04 loss: 1.046e-02]
latex_v1:  50%|####9     | 1495/3000 [34:54<33:25,  1.33s/it, lr: 1.0e-04 loss: 4.690e-01]
latex_v1:  50%|####9     | 1495/3000 [34:54<33:25,  1.33s/it, lr: 1.0e-04 loss: 4.690e-01]
latex_v1:  50%|####9     | 1496/3000 [34:54<32:17,  1.29s/it, lr: 1.0e-04 loss: 4.690e-01]
latex_v1:  50%|####9     | 1496/3000 [34:54<32:17,  1.29s/it, lr: 1.0e-04 loss: 4.690e-01]
latex_v1:  50%|####9     | 1496/3000 [34:56<32:17,  1.29s/it, lr: 1.0e-04 loss: 7.520e-02]
latex_v1:  50%|####9     | 1496/3000 [34:56<32:17,  1.29s/it, lr: 1.0e-04 loss: 7.520e-02]
latex_v1:  50%|####9     | 1497/3000 [34:56<43:22,  1.73s/it, lr: 1.0e-04 loss: 7.520e-02]
latex_v1:  50%|####9     | 1497/3000 [34:56<43:22,  1.73s/it, lr: 1.0e-04 loss: 7.520e-02]
latex_v1:  50%|####9     | 1497/3000 [34:58<43:22,  1.73s/it, lr: 1.0e-04 loss: 3.758e-01]
latex_v1:  50%|####9     | 1497/3000 [34:58<43:22,  1.73s/it, lr: 1.0e-04 loss: 3.758e-01]
latex_v1:  50%|####9     | 1498/3000 [34:58<42:00,  1.68s/it, lr: 1.0e-04 loss: 3.758e-01]
latex_v1:  50%|####9     | 1498/3000 [34:58<42:00,  1.68s/it, lr: 1.0e-04 loss: 3.758e-01]
latex_v1:  50%|####9     | 1498/3000 [34:59<42:00,  1.68s/it, lr: 1.0e-04 loss: 3.867e-01]
latex_v1:  50%|####9     | 1498/3000 [34:59<42:00,  1.68s/it, lr: 1.0e-04 loss: 3.867e-01]
latex_v1:  50%|####9     | 1499/3000 [34:59<39:36,  1.58s/it, lr: 1.0e-04 loss: 3.867e-01]
latex_v1:  50%|####9     | 1499/3000 [34:59<39:36,  1.58s/it, lr: 1.0e-04 loss: 3.867e-01]
latex_v1:  50%|####9     | 1499/3000 [35:00<39:36,  1.58s/it, lr: 1.0e-04 loss: 7.063e-01]
latex_v1:  50%|####9     | 1499/3000 [35:00<39:36,  1.58s/it, lr: 1.0e-04 loss: 7.063e-01]
Saving at step 1500
Saved checkpoint to /data/app/output/latex_v1/latex_v1_000001500.safetensors
Saved optimizer to /data/app/output/latex_v1/optimizer.pt
Removing old save: /data/app/output/latex_v1/latex_v1_000000500.safetensors
Unloading assistant lora



Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]


Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.42s/it]
Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.42s/it]


Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.42s/it]
Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.42s/it]


Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.42s/it]
Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.42s/it]


Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.42s/it]
Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.42s/it]


Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.42s/it]
Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.42s/it]


Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.42s/it]
Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.42s/it]


Generating Images: 100%|##########| 7/7 [00:16<00:00,  2.42s/it]
Generating Images: 100%|##########| 7/7 [00:16<00:00,  2.42s/it]


                                                                
                                                                Loading assistant lora

latex_v1:  50%|#####     | 1500/3000 [35:02<39:34,  1.58s/it, lr: 1.0e-04 loss: 5.686e-02]
latex_v1:  50%|#####     | 1500/3000 [35:02<39:34,  1.58s/it, lr: 1.0e-04 loss: 5.686e-02]
latex_v1:  50%|#####     | 1501/3000 [35:02<30:16,  1.21s/it, lr: 1.0e-04 loss: 5.686e-02]
latex_v1:  50%|#####     | 1501/3000 [35:02<30:16,  1.21s/it, lr: 1.0e-04 loss: 5.686e-02]
latex_v1:  50%|#####     | 1501/3000 [35:02<30:16,  1.21s/it, lr: 1.0e-04 loss: 2.421e-01]
latex_v1:  50%|#####     | 1501/3000 [35:02<30:16,  1.21s/it, lr: 1.0e-04 loss: 2.421e-01]
latex_v1:  50%|#####     | 1502/3000 [35:02<27:29,  1.10s/it, lr: 1.0e-04 loss: 2.421e-01]
latex_v1:  50%|#####     | 1502/3000 [35:02<27:29,  1.10s/it, lr: 1.0e-04 loss: 2.421e-01]
latex_v1:  50%|#####     | 1502/3000 [35:03<27:29,  1.10s/it, lr: 1.0e-04 loss: 5.230e-02]
latex_v1:  50%|#####     | 1502/3000 [35:03<27:29,  1.10s/it, lr: 1.0e-04 loss: 5.230e-02]
latex_v1:  50%|#####     | 1503/3000 [35:03<25:09,  1.01s/it, lr: 1.0e-04 loss: 5.230e-02]
latex_v1:  50%|#####     | 1503/3000 [35:03<25:09,  1.01s/it, lr: 1.0e-04 loss: 5.230e-02]
latex_v1:  50%|#####     | 1503/3000 [35:04<25:09,  1.01s/it, lr: 1.0e-04 loss: 8.610e-02]
latex_v1:  50%|#####     | 1503/3000 [35:04<25:09,  1.01s/it, lr: 1.0e-04 loss: 8.610e-02]
latex_v1:  50%|#####     | 1504/3000 [35:04<23:23,  1.07it/s, lr: 1.0e-04 loss: 8.610e-02]
latex_v1:  50%|#####     | 1504/3000 [35:04<23:23,  1.07it/s, lr: 1.0e-04 loss: 8.610e-02]
latex_v1:  50%|#####     | 1504/3000 [35:05<23:23,  1.07it/s, lr: 1.0e-04 loss: 5.470e-01]
latex_v1:  50%|#####     | 1504/3000 [35:05<23:23,  1.07it/s, lr: 1.0e-04 loss: 5.470e-01]
latex_v1:  50%|#####     | 1505/3000 [35:05<27:32,  1.11s/it, lr: 1.0e-04 loss: 5.470e-01]
latex_v1:  50%|#####     | 1505/3000 [35:05<27:32,  1.11s/it, lr: 1.0e-04 loss: 5.470e-01]
latex_v1:  50%|#####     | 1505/3000 [35:07<27:32,  1.11s/it, lr: 1.0e-04 loss: 4.994e-01]
latex_v1:  50%|#####     | 1505/3000 [35:07<27:32,  1.11s/it, lr: 1.0e-04 loss: 4.994e-01]
latex_v1:  50%|#####     | 1506/3000 [35:07<27:57,  1.12s/it, lr: 1.0e-04 loss: 4.994e-01]
latex_v1:  50%|#####     | 1506/3000 [35:07<27:57,  1.12s/it, lr: 1.0e-04 loss: 4.994e-01]
latex_v1:  50%|#####     | 1506/3000 [35:07<27:57,  1.12s/it, lr: 1.0e-04 loss: 5.965e-01]
latex_v1:  50%|#####     | 1506/3000 [35:07<27:57,  1.12s/it, lr: 1.0e-04 loss: 5.965e-01]
latex_v1:  50%|#####     | 1507/3000 [35:07<25:27,  1.02s/it, lr: 1.0e-04 loss: 5.965e-01]
latex_v1:  50%|#####     | 1507/3000 [35:07<25:27,  1.02s/it, lr: 1.0e-04 loss: 5.965e-01]
latex_v1:  50%|#####     | 1507/3000 [35:09<25:27,  1.02s/it, lr: 1.0e-04 loss: 4.517e-01]
latex_v1:  50%|#####     | 1507/3000 [35:09<25:27,  1.02s/it, lr: 1.0e-04 loss: 4.517e-01]
latex_v1:  50%|#####     | 1508/3000 [35:09<29:06,  1.17s/it, lr: 1.0e-04 loss: 4.517e-01]
latex_v1:  50%|#####     | 1508/3000 [35:09<29:06,  1.17s/it, lr: 1.0e-04 loss: 4.517e-01]
latex_v1:  50%|#####     | 1508/3000 [35:10<29:06,  1.17s/it, lr: 1.0e-04 loss: 4.898e-01]
latex_v1:  50%|#####     | 1508/3000 [35:10<29:06,  1.17s/it, lr: 1.0e-04 loss: 4.898e-01]
latex_v1:  50%|#####     | 1509/3000 [35:10<31:09,  1.25s/it, lr: 1.0e-04 loss: 4.898e-01]
latex_v1:  50%|#####     | 1509/3000 [35:10<31:09,  1.25s/it, lr: 1.0e-04 loss: 4.898e-01]
latex_v1:  50%|#####     | 1509/3000 [35:12<31:09,  1.25s/it, lr: 1.0e-04 loss: 5.286e-01]
latex_v1:  50%|#####     | 1509/3000 [35:12<31:09,  1.25s/it, lr: 1.0e-04 loss: 5.286e-01]
latex_v1:  50%|#####     | 1510/3000 [35:13<31:08,  1.25s/it, lr: 1.0e-04 loss: 3.515e-01]
latex_v1:  50%|#####     | 1510/3000 [35:13<31:08,  1.25s/it, lr: 1.0e-04 loss: 3.515e-01]
latex_v1:  50%|#####     | 1511/3000 [35:13<21:06,  1.18it/s, lr: 1.0e-04 loss: 3.515e-01]
latex_v1:  50%|#####     | 1511/3000 [35:13<21:06,  1.18it/s, lr: 1.0e-04 loss: 3.515e-01]
latex_v1:  50%|#####     | 1511/3000 [35:14<21:06,  1.18it/s, lr: 1.0e-04 loss: 1.589e-01]
latex_v1:  50%|#####     | 1511/3000 [35:14<21:06,  1.18it/s, lr: 1.0e-04 loss: 1.589e-01]
latex_v1:  50%|#####     | 1512/3000 [35:14<20:29,  1.21it/s, lr: 1.0e-04 loss: 1.589e-01]
latex_v1:  50%|#####     | 1512/3000 [35:14<20:29,  1.21it/s, lr: 1.0e-04 loss: 1.589e-01]
latex_v1:  50%|#####     | 1512/3000 [35:15<20:29,  1.21it/s, lr: 1.0e-04 loss: 1.873e-01]
latex_v1:  50%|#####     | 1512/3000 [35:15<20:29,  1.21it/s, lr: 1.0e-04 loss: 1.873e-01]
latex_v1:  50%|#####     | 1513/3000 [35:15<23:08,  1.07it/s, lr: 1.0e-04 loss: 1.873e-01]
latex_v1:  50%|#####     | 1513/3000 [35:15<23:08,  1.07it/s, lr: 1.0e-04 loss: 1.873e-01]
latex_v1:  50%|#####     | 1513/3000 [35:16<23:08,  1.07it/s, lr: 1.0e-04 loss: 7.363e-01]
latex_v1:  50%|#####     | 1513/3000 [35:16<23:08,  1.07it/s, lr: 1.0e-04 loss: 7.363e-01]
latex_v1:  50%|#####     | 1514/3000 [35:16<21:51,  1.13it/s, lr: 1.0e-04 loss: 7.363e-01]
latex_v1:  50%|#####     | 1514/3000 [35:16<21:51,  1.13it/s, lr: 1.0e-04 loss: 7.363e-01]
latex_v1:  50%|#####     | 1514/3000 [35:18<21:51,  1.13it/s, lr: 1.0e-04 loss: 5.127e-02]
latex_v1:  50%|#####     | 1514/3000 [35:18<21:51,  1.13it/s, lr: 1.0e-04 loss: 5.127e-02]
latex_v1:  50%|#####     | 1515/3000 [35:18<35:13,  1.42s/it, lr: 1.0e-04 loss: 5.127e-02]
latex_v1:  50%|#####     | 1515/3000 [35:18<35:13,  1.42s/it, lr: 1.0e-04 loss: 5.127e-02]
latex_v1:  50%|#####     | 1515/3000 [35:21<35:13,  1.42s/it, lr: 1.0e-04 loss: 3.436e-01]
latex_v1:  50%|#####     | 1515/3000 [35:21<35:13,  1.42s/it, lr: 1.0e-04 loss: 3.436e-01]
latex_v1:  51%|#####     | 1516/3000 [35:21<45:19,  1.83s/it, lr: 1.0e-04 loss: 3.436e-01]
latex_v1:  51%|#####     | 1516/3000 [35:21<45:19,  1.83s/it, lr: 1.0e-04 loss: 3.436e-01]
latex_v1:  51%|#####     | 1516/3000 [35:23<45:19,  1.83s/it, lr: 1.0e-04 loss: 2.964e-01]
latex_v1:  51%|#####     | 1516/3000 [35:23<45:19,  1.83s/it, lr: 1.0e-04 loss: 2.964e-01]
latex_v1:  51%|#####     | 1517/3000 [35:23<41:39,  1.69s/it, lr: 1.0e-04 loss: 2.964e-01]
latex_v1:  51%|#####     | 1517/3000 [35:23<41:39,  1.69s/it, lr: 1.0e-04 loss: 2.964e-01]
latex_v1:  51%|#####     | 1517/3000 [35:23<41:39,  1.69s/it, lr: 1.0e-04 loss: 1.248e-01]
latex_v1:  51%|#####     | 1517/3000 [35:23<41:39,  1.69s/it, lr: 1.0e-04 loss: 1.248e-01]
latex_v1:  51%|#####     | 1518/3000 [35:23<34:45,  1.41s/it, lr: 1.0e-04 loss: 1.248e-01]
latex_v1:  51%|#####     | 1518/3000 [35:23<34:45,  1.41s/it, lr: 1.0e-04 loss: 1.248e-01]
latex_v1:  51%|#####     | 1518/3000 [35:25<34:45,  1.41s/it, lr: 1.0e-04 loss: 5.336e-01]
latex_v1:  51%|#####     | 1518/3000 [35:25<34:45,  1.41s/it, lr: 1.0e-04 loss: 5.336e-01]
latex_v1:  51%|#####     | 1519/3000 [35:25<38:09,  1.55s/it, lr: 1.0e-04 loss: 5.336e-01]
latex_v1:  51%|#####     | 1519/3000 [35:25<38:09,  1.55s/it, lr: 1.0e-04 loss: 5.336e-01]
latex_v1:  51%|#####     | 1519/3000 [35:26<38:09,  1.55s/it, lr: 1.0e-04 loss: 3.242e-01]
latex_v1:  51%|#####     | 1519/3000 [35:26<38:09,  1.55s/it, lr: 1.0e-04 loss: 3.242e-01]
latex_v1:  51%|#####     | 1520/3000 [35:27<38:07,  1.55s/it, lr: 1.0e-04 loss: 6.659e-02]
latex_v1:  51%|#####     | 1520/3000 [35:27<38:07,  1.55s/it, lr: 1.0e-04 loss: 6.659e-02]
latex_v1:  51%|#####     | 1521/3000 [35:27<24:53,  1.01s/it, lr: 1.0e-04 loss: 6.659e-02]
latex_v1:  51%|#####     | 1521/3000 [35:27<24:53,  1.01s/it, lr: 1.0e-04 loss: 6.659e-02]
latex_v1:  51%|#####     | 1521/3000 [35:30<24:53,  1.01s/it, lr: 1.0e-04 loss: 3.394e-01]
latex_v1:  51%|#####     | 1521/3000 [35:30<24:53,  1.01s/it, lr: 1.0e-04 loss: 3.394e-01]
latex_v1:  51%|#####     | 1522/3000 [35:30<36:20,  1.48s/it, lr: 1.0e-04 loss: 3.394e-01]
latex_v1:  51%|#####     | 1522/3000 [35:30<36:20,  1.48s/it, lr: 1.0e-04 loss: 3.394e-01]
latex_v1:  51%|#####     | 1522/3000 [35:31<36:20,  1.48s/it, lr: 1.0e-04 loss: 5.925e-01]
latex_v1:  51%|#####     | 1522/3000 [35:31<36:20,  1.48s/it, lr: 1.0e-04 loss: 5.925e-01]
latex_v1:  51%|#####     | 1523/3000 [35:31<36:09,  1.47s/it, lr: 1.0e-04 loss: 5.925e-01]
latex_v1:  51%|#####     | 1523/3000 [35:31<36:09,  1.47s/it, lr: 1.0e-04 loss: 5.925e-01]
latex_v1:  51%|#####     | 1523/3000 [35:33<36:09,  1.47s/it, lr: 1.0e-04 loss: 1.316e-01]
latex_v1:  51%|#####     | 1523/3000 [35:33<36:09,  1.47s/it, lr: 1.0e-04 loss: 1.316e-01]
latex_v1:  51%|#####     | 1524/3000 [35:33<38:49,  1.58s/it, lr: 1.0e-04 loss: 1.316e-01]
latex_v1:  51%|#####     | 1524/3000 [35:33<38:49,  1.58s/it, lr: 1.0e-04 loss: 1.316e-01]
latex_v1:  51%|#####     | 1524/3000 [35:35<38:49,  1.58s/it, lr: 1.0e-04 loss: 1.332e-01]
latex_v1:  51%|#####     | 1524/3000 [35:35<38:49,  1.58s/it, lr: 1.0e-04 loss: 1.332e-01]
latex_v1:  51%|#####     | 1525/3000 [35:35<38:41,  1.57s/it, lr: 1.0e-04 loss: 1.332e-01]
latex_v1:  51%|#####     | 1525/3000 [35:35<38:41,  1.57s/it, lr: 1.0e-04 loss: 1.332e-01]
latex_v1:  51%|#####     | 1525/3000 [35:37<38:41,  1.57s/it, lr: 1.0e-04 loss: 3.924e-01]
latex_v1:  51%|#####     | 1525/3000 [35:37<38:41,  1.57s/it, lr: 1.0e-04 loss: 3.924e-01]
latex_v1:  51%|#####     | 1526/3000 [35:37<40:55,  1.67s/it, lr: 1.0e-04 loss: 3.924e-01]
latex_v1:  51%|#####     | 1526/3000 [35:37<40:55,  1.67s/it, lr: 1.0e-04 loss: 3.924e-01]
latex_v1:  51%|#####     | 1526/3000 [35:38<40:55,  1.67s/it, lr: 1.0e-04 loss: 1.743e-01]
latex_v1:  51%|#####     | 1526/3000 [35:38<40:55,  1.67s/it, lr: 1.0e-04 loss: 1.743e-01]
latex_v1:  51%|#####     | 1527/3000 [35:38<39:05,  1.59s/it, lr: 1.0e-04 loss: 1.743e-01]
latex_v1:  51%|#####     | 1527/3000 [35:38<39:05,  1.59s/it, lr: 1.0e-04 loss: 1.743e-01]
latex_v1:  51%|#####     | 1527/3000 [35:40<39:05,  1.59s/it, lr: 1.0e-04 loss: 1.408e-01]
latex_v1:  51%|#####     | 1527/3000 [35:40<39:05,  1.59s/it, lr: 1.0e-04 loss: 1.408e-01]
latex_v1:  51%|#####     | 1528/3000 [35:40<41:07,  1.68s/it, lr: 1.0e-04 loss: 1.408e-01]
latex_v1:  51%|#####     | 1528/3000 [35:40<41:07,  1.68s/it, lr: 1.0e-04 loss: 1.408e-01]
latex_v1:  51%|#####     | 1528/3000 [35:41<41:07,  1.68s/it, lr: 1.0e-04 loss: 4.549e-01]
latex_v1:  51%|#####     | 1528/3000 [35:41<41:07,  1.68s/it, lr: 1.0e-04 loss: 4.549e-01]
latex_v1:  51%|#####     | 1529/3000 [35:41<34:26,  1.41s/it, lr: 1.0e-04 loss: 4.549e-01]
latex_v1:  51%|#####     | 1529/3000 [35:41<34:26,  1.41s/it, lr: 1.0e-04 loss: 4.549e-01]
latex_v1:  51%|#####     | 1529/3000 [35:41<34:26,  1.41s/it, lr: 1.0e-04 loss: 2.319e-01]
latex_v1:  51%|#####     | 1529/3000 [35:41<34:26,  1.41s/it, lr: 1.0e-04 loss: 2.319e-01]
latex_v1:  51%|#####1    | 1530/3000 [35:44<34:25,  1.41s/it, lr: 1.0e-04 loss: 5.868e-02]
latex_v1:  51%|#####1    | 1530/3000 [35:44<34:25,  1.41s/it, lr: 1.0e-04 loss: 5.868e-02]
latex_v1:  51%|#####1    | 1531/3000 [35:44<34:46,  1.42s/it, lr: 1.0e-04 loss: 5.868e-02]
latex_v1:  51%|#####1    | 1531/3000 [35:44<34:46,  1.42s/it, lr: 1.0e-04 loss: 5.868e-02]
latex_v1:  51%|#####1    | 1531/3000 [35:46<34:46,  1.42s/it, lr: 1.0e-04 loss: 6.095e-01]
latex_v1:  51%|#####1    | 1531/3000 [35:46<34:46,  1.42s/it, lr: 1.0e-04 loss: 6.095e-01]
latex_v1:  51%|#####1    | 1532/3000 [35:46<35:31,  1.45s/it, lr: 1.0e-04 loss: 6.095e-01]
latex_v1:  51%|#####1    | 1532/3000 [35:46<35:31,  1.45s/it, lr: 1.0e-04 loss: 6.095e-01]
latex_v1:  51%|#####1    | 1532/3000 [35:48<35:31,  1.45s/it, lr: 1.0e-04 loss: 4.226e-01]
latex_v1:  51%|#####1    | 1532/3000 [35:48<35:31,  1.45s/it, lr: 1.0e-04 loss: 4.226e-01]
latex_v1:  51%|#####1    | 1533/3000 [35:48<40:13,  1.65s/it, lr: 1.0e-04 loss: 4.226e-01]
latex_v1:  51%|#####1    | 1533/3000 [35:48<40:13,  1.65s/it, lr: 1.0e-04 loss: 4.226e-01]
latex_v1:  51%|#####1    | 1533/3000 [35:50<40:13,  1.65s/it, lr: 1.0e-04 loss: 5.031e-01]
latex_v1:  51%|#####1    | 1533/3000 [35:50<40:13,  1.65s/it, lr: 1.0e-04 loss: 5.031e-01]
latex_v1:  51%|#####1    | 1534/3000 [35:50<39:31,  1.62s/it, lr: 1.0e-04 loss: 5.031e-01]
latex_v1:  51%|#####1    | 1534/3000 [35:50<39:31,  1.62s/it, lr: 1.0e-04 loss: 5.031e-01]
latex_v1:  51%|#####1    | 1534/3000 [35:50<39:31,  1.62s/it, lr: 1.0e-04 loss: 4.519e-01]
latex_v1:  51%|#####1    | 1534/3000 [35:50<39:31,  1.62s/it, lr: 1.0e-04 loss: 4.519e-01]
latex_v1:  51%|#####1    | 1535/3000 [35:50<33:35,  1.38s/it, lr: 1.0e-04 loss: 4.519e-01]
latex_v1:  51%|#####1    | 1535/3000 [35:50<33:35,  1.38s/it, lr: 1.0e-04 loss: 4.519e-01]
latex_v1:  51%|#####1    | 1535/3000 [35:52<33:35,  1.38s/it, lr: 1.0e-04 loss: 1.661e-01]
latex_v1:  51%|#####1    | 1535/3000 [35:52<33:35,  1.38s/it, lr: 1.0e-04 loss: 1.661e-01]
latex_v1:  51%|#####1    | 1536/3000 [35:52<35:32,  1.46s/it, lr: 1.0e-04 loss: 1.661e-01]
latex_v1:  51%|#####1    | 1536/3000 [35:52<35:32,  1.46s/it, lr: 1.0e-04 loss: 1.661e-01]
latex_v1:  51%|#####1    | 1536/3000 [35:53<35:32,  1.46s/it, lr: 1.0e-04 loss: 5.270e-01]
latex_v1:  51%|#####1    | 1536/3000 [35:53<35:32,  1.46s/it, lr: 1.0e-04 loss: 5.270e-01]
latex_v1:  51%|#####1    | 1537/3000 [35:53<35:31,  1.46s/it, lr: 1.0e-04 loss: 5.270e-01]
latex_v1:  51%|#####1    | 1537/3000 [35:53<35:31,  1.46s/it, lr: 1.0e-04 loss: 5.270e-01]
latex_v1:  51%|#####1    | 1537/3000 [35:54<35:31,  1.46s/it, lr: 1.0e-04 loss: 1.686e-01]
latex_v1:  51%|#####1    | 1537/3000 [35:54<35:31,  1.46s/it, lr: 1.0e-04 loss: 1.686e-01]
latex_v1:  51%|#####1    | 1538/3000 [35:54<30:24,  1.25s/it, lr: 1.0e-04 loss: 1.686e-01]
latex_v1:  51%|#####1    | 1538/3000 [35:54<30:24,  1.25s/it, lr: 1.0e-04 loss: 1.686e-01]
latex_v1:  51%|#####1    | 1538/3000 [35:56<30:24,  1.25s/it, lr: 1.0e-04 loss: 1.828e-01]
latex_v1:  51%|#####1    | 1538/3000 [35:56<30:24,  1.25s/it, lr: 1.0e-04 loss: 1.828e-01]
latex_v1:  51%|#####1    | 1539/3000 [35:56<32:26,  1.33s/it, lr: 1.0e-04 loss: 1.828e-01]
latex_v1:  51%|#####1    | 1539/3000 [35:56<32:26,  1.33s/it, lr: 1.0e-04 loss: 1.828e-01]
latex_v1:  51%|#####1    | 1539/3000 [35:57<32:26,  1.33s/it, lr: 1.0e-04 loss: 9.145e-02]
latex_v1:  51%|#####1    | 1539/3000 [35:57<32:26,  1.33s/it, lr: 1.0e-04 loss: 9.145e-02]
latex_v1:  51%|#####1    | 1540/3000 [36:00<32:24,  1.33s/it, lr: 1.0e-04 loss: 3.756e-02]
latex_v1:  51%|#####1    | 1540/3000 [36:00<32:24,  1.33s/it, lr: 1.0e-04 loss: 3.756e-02]
latex_v1:  51%|#####1    | 1541/3000 [36:00<33:32,  1.38s/it, lr: 1.0e-04 loss: 3.756e-02]
latex_v1:  51%|#####1    | 1541/3000 [36:00<33:32,  1.38s/it, lr: 1.0e-04 loss: 3.756e-02]
latex_v1:  51%|#####1    | 1541/3000 [36:01<33:32,  1.38s/it, lr: 1.0e-04 loss: 4.242e-01]
latex_v1:  51%|#####1    | 1541/3000 [36:01<33:32,  1.38s/it, lr: 1.0e-04 loss: 4.242e-01]
latex_v1:  51%|#####1    | 1542/3000 [36:01<31:07,  1.28s/it, lr: 1.0e-04 loss: 4.242e-01]
latex_v1:  51%|#####1    | 1542/3000 [36:01<31:07,  1.28s/it, lr: 1.0e-04 loss: 4.242e-01]
latex_v1:  51%|#####1    | 1542/3000 [36:02<31:07,  1.28s/it, lr: 1.0e-04 loss: 7.306e-01]
latex_v1:  51%|#####1    | 1542/3000 [36:02<31:07,  1.28s/it, lr: 1.0e-04 loss: 7.306e-01]
latex_v1:  51%|#####1    | 1543/3000 [36:02<30:25,  1.25s/it, lr: 1.0e-04 loss: 7.306e-01]
latex_v1:  51%|#####1    | 1543/3000 [36:02<30:25,  1.25s/it, lr: 1.0e-04 loss: 7.306e-01]
latex_v1:  51%|#####1    | 1543/3000 [36:03<30:25,  1.25s/it, lr: 1.0e-04 loss: 6.826e-01]
latex_v1:  51%|#####1    | 1543/3000 [36:03<30:25,  1.25s/it, lr: 1.0e-04 loss: 6.826e-01]
latex_v1:  51%|#####1    | 1544/3000 [36:03<28:29,  1.17s/it, lr: 1.0e-04 loss: 6.826e-01]
latex_v1:  51%|#####1    | 1544/3000 [36:03<28:29,  1.17s/it, lr: 1.0e-04 loss: 6.826e-01]
latex_v1:  51%|#####1    | 1544/3000 [36:04<28:29,  1.17s/it, lr: 1.0e-04 loss: 1.436e-01]
latex_v1:  51%|#####1    | 1544/3000 [36:04<28:29,  1.17s/it, lr: 1.0e-04 loss: 1.436e-01]
latex_v1:  52%|#####1    | 1545/3000 [36:04<25:35,  1.06s/it, lr: 1.0e-04 loss: 1.436e-01]
latex_v1:  52%|#####1    | 1545/3000 [36:04<25:35,  1.06s/it, lr: 1.0e-04 loss: 1.436e-01]
latex_v1:  52%|#####1    | 1545/3000 [36:05<25:35,  1.06s/it, lr: 1.0e-04 loss: 3.501e-01]
latex_v1:  52%|#####1    | 1545/3000 [36:05<25:35,  1.06s/it, lr: 1.0e-04 loss: 3.501e-01]
latex_v1:  52%|#####1    | 1546/3000 [36:05<23:36,  1.03it/s, lr: 1.0e-04 loss: 3.501e-01]
latex_v1:  52%|#####1    | 1546/3000 [36:05<23:36,  1.03it/s, lr: 1.0e-04 loss: 3.501e-01]
latex_v1:  52%|#####1    | 1546/3000 [36:06<23:36,  1.03it/s, lr: 1.0e-04 loss: 4.532e-01]
latex_v1:  52%|#####1    | 1546/3000 [36:06<23:36,  1.03it/s, lr: 1.0e-04 loss: 4.532e-01]
latex_v1:  52%|#####1    | 1547/3000 [36:06<26:18,  1.09s/it, lr: 1.0e-04 loss: 4.532e-01]
latex_v1:  52%|#####1    | 1547/3000 [36:06<26:18,  1.09s/it, lr: 1.0e-04 loss: 4.532e-01]
latex_v1:  52%|#####1    | 1547/3000 [36:07<26:18,  1.09s/it, lr: 1.0e-04 loss: 7.782e-02]
latex_v1:  52%|#####1    | 1547/3000 [36:07<26:18,  1.09s/it, lr: 1.0e-04 loss: 7.782e-02]
latex_v1:  52%|#####1    | 1548/3000 [36:07<23:43,  1.02it/s, lr: 1.0e-04 loss: 7.782e-02]
latex_v1:  52%|#####1    | 1548/3000 [36:07<23:43,  1.02it/s, lr: 1.0e-04 loss: 7.782e-02]
latex_v1:  52%|#####1    | 1548/3000 [36:08<23:43,  1.02it/s, lr: 1.0e-04 loss: 1.096e-01]
latex_v1:  52%|#####1    | 1548/3000 [36:08<23:43,  1.02it/s, lr: 1.0e-04 loss: 1.096e-01]
latex_v1:  52%|#####1    | 1549/3000 [36:08<27:43,  1.15s/it, lr: 1.0e-04 loss: 1.096e-01]
latex_v1:  52%|#####1    | 1549/3000 [36:08<27:43,  1.15s/it, lr: 1.0e-04 loss: 1.096e-01]
latex_v1:  52%|#####1    | 1549/3000 [36:11<27:43,  1.15s/it, lr: 1.0e-04 loss: 3.692e-01]
latex_v1:  52%|#####1    | 1549/3000 [36:11<27:43,  1.15s/it, lr: 1.0e-04 loss: 3.692e-01]
latex_v1:  52%|#####1    | 1550/3000 [36:14<27:42,  1.15s/it, lr: 1.0e-04 loss: 3.459e-01]
latex_v1:  52%|#####1    | 1550/3000 [36:14<27:42,  1.15s/it, lr: 1.0e-04 loss: 3.459e-01]
latex_v1:  52%|#####1    | 1551/3000 [36:14<30:49,  1.28s/it, lr: 1.0e-04 loss: 3.459e-01]
latex_v1:  52%|#####1    | 1551/3000 [36:14<30:49,  1.28s/it, lr: 1.0e-04 loss: 3.459e-01]
latex_v1:  52%|#####1    | 1551/3000 [36:16<30:49,  1.28s/it, lr: 1.0e-04 loss: 3.946e-01]
latex_v1:  52%|#####1    | 1551/3000 [36:16<30:49,  1.28s/it, lr: 1.0e-04 loss: 3.946e-01]
latex_v1:  52%|#####1    | 1552/3000 [36:16<32:22,  1.34s/it, lr: 1.0e-04 loss: 3.946e-01]
latex_v1:  52%|#####1    | 1552/3000 [36:16<32:22,  1.34s/it, lr: 1.0e-04 loss: 3.946e-01]
latex_v1:  52%|#####1    | 1552/3000 [36:18<32:22,  1.34s/it, lr: 1.0e-04 loss: 4.465e-01]
latex_v1:  52%|#####1    | 1552/3000 [36:18<32:22,  1.34s/it, lr: 1.0e-04 loss: 4.465e-01]
latex_v1:  52%|#####1    | 1553/3000 [36:18<36:30,  1.51s/it, lr: 1.0e-04 loss: 4.465e-01]
latex_v1:  52%|#####1    | 1553/3000 [36:18<36:30,  1.51s/it, lr: 1.0e-04 loss: 4.465e-01]
latex_v1:  52%|#####1    | 1553/3000 [36:19<36:30,  1.51s/it, lr: 1.0e-04 loss: 5.258e-01]
latex_v1:  52%|#####1    | 1553/3000 [36:19<36:30,  1.51s/it, lr: 1.0e-04 loss: 5.258e-01]
latex_v1:  52%|#####1    | 1554/3000 [36:19<33:34,  1.39s/it, lr: 1.0e-04 loss: 5.258e-01]
latex_v1:  52%|#####1    | 1554/3000 [36:19<33:34,  1.39s/it, lr: 1.0e-04 loss: 5.258e-01]
latex_v1:  52%|#####1    | 1554/3000 [36:20<33:34,  1.39s/it, lr: 1.0e-04 loss: 1.041e-01]
latex_v1:  52%|#####1    | 1554/3000 [36:20<33:34,  1.39s/it, lr: 1.0e-04 loss: 1.041e-01]
latex_v1:  52%|#####1    | 1555/3000 [36:20<30:45,  1.28s/it, lr: 1.0e-04 loss: 1.041e-01]
latex_v1:  52%|#####1    | 1555/3000 [36:20<30:45,  1.28s/it, lr: 1.0e-04 loss: 1.041e-01]
latex_v1:  52%|#####1    | 1555/3000 [36:20<30:45,  1.28s/it, lr: 1.0e-04 loss: 9.279e-02]
latex_v1:  52%|#####1    | 1555/3000 [36:20<30:45,  1.28s/it, lr: 1.0e-04 loss: 9.279e-02]
latex_v1:  52%|#####1    | 1556/3000 [36:20<27:07,  1.13s/it, lr: 1.0e-04 loss: 9.279e-02]
latex_v1:  52%|#####1    | 1556/3000 [36:20<27:07,  1.13s/it, lr: 1.0e-04 loss: 9.279e-02]
latex_v1:  52%|#####1    | 1556/3000 [36:23<27:07,  1.13s/it, lr: 1.0e-04 loss: 1.363e-01]
latex_v1:  52%|#####1    | 1556/3000 [36:23<27:07,  1.13s/it, lr: 1.0e-04 loss: 1.363e-01]
latex_v1:  52%|#####1    | 1557/3000 [36:23<37:37,  1.56s/it, lr: 1.0e-04 loss: 1.363e-01]
latex_v1:  52%|#####1    | 1557/3000 [36:23<37:37,  1.56s/it, lr: 1.0e-04 loss: 1.363e-01]
latex_v1:  52%|#####1    | 1557/3000 [36:24<37:37,  1.56s/it, lr: 1.0e-04 loss: 4.980e-01]
latex_v1:  52%|#####1    | 1557/3000 [36:24<37:37,  1.56s/it, lr: 1.0e-04 loss: 4.980e-01]
latex_v1:  52%|#####1    | 1558/3000 [36:24<36:51,  1.53s/it, lr: 1.0e-04 loss: 4.980e-01]
latex_v1:  52%|#####1    | 1558/3000 [36:24<36:51,  1.53s/it, lr: 1.0e-04 loss: 4.980e-01]
latex_v1:  52%|#####1    | 1558/3000 [36:26<36:51,  1.53s/it, lr: 1.0e-04 loss: 0.000e+00]
latex_v1:  52%|#####1    | 1558/3000 [36:26<36:51,  1.53s/it, lr: 1.0e-04 loss: 0.000e+00]
latex_v1:  52%|#####1    | 1559/3000 [36:26<33:47,  1.41s/it, lr: 1.0e-04 loss: 0.000e+00]
latex_v1:  52%|#####1    | 1559/3000 [36:26<33:47,  1.41s/it, lr: 1.0e-04 loss: 0.000e+00]
latex_v1:  52%|#####1    | 1559/3000 [36:27<33:47,  1.41s/it, lr: 1.0e-04 loss: 8.163e-01]
latex_v1:  52%|#####1    | 1559/3000 [36:27<33:47,  1.41s/it, lr: 1.0e-04 loss: 8.163e-01]
latex_v1:  52%|#####2    | 1560/3000 [36:28<33:46,  1.41s/it, lr: 1.0e-04 loss: 2.437e-01]
latex_v1:  52%|#####2    | 1560/3000 [36:28<33:46,  1.41s/it, lr: 1.0e-04 loss: 2.437e-01]
latex_v1:  52%|#####2    | 1561/3000 [36:28<26:15,  1.09s/it, lr: 1.0e-04 loss: 2.437e-01]
latex_v1:  52%|#####2    | 1561/3000 [36:28<26:15,  1.09s/it, lr: 1.0e-04 loss: 2.437e-01]
latex_v1:  52%|#####2    | 1561/3000 [36:30<26:15,  1.09s/it, lr: 1.0e-04 loss: 1.351e-01]
latex_v1:  52%|#####2    | 1561/3000 [36:30<26:15,  1.09s/it, lr: 1.0e-04 loss: 1.351e-01]
latex_v1:  52%|#####2    | 1562/3000 [36:30<30:48,  1.29s/it, lr: 1.0e-04 loss: 1.351e-01]
latex_v1:  52%|#####2    | 1562/3000 [36:30<30:48,  1.29s/it, lr: 1.0e-04 loss: 1.351e-01]
latex_v1:  52%|#####2    | 1562/3000 [36:31<30:48,  1.29s/it, lr: 1.0e-04 loss: 5.338e-01]
latex_v1:  52%|#####2    | 1562/3000 [36:31<30:48,  1.29s/it, lr: 1.0e-04 loss: 5.338e-01]
latex_v1:  52%|#####2    | 1563/3000 [36:31<32:14,  1.35s/it, lr: 1.0e-04 loss: 5.338e-01]
latex_v1:  52%|#####2    | 1563/3000 [36:31<32:14,  1.35s/it, lr: 1.0e-04 loss: 5.338e-01]
latex_v1:  52%|#####2    | 1563/3000 [36:32<32:14,  1.35s/it, lr: 1.0e-04 loss: 6.187e-01]
latex_v1:  52%|#####2    | 1563/3000 [36:32<32:14,  1.35s/it, lr: 1.0e-04 loss: 6.187e-01]
latex_v1:  52%|#####2    | 1564/3000 [36:32<28:20,  1.18s/it, lr: 1.0e-04 loss: 6.187e-01]
latex_v1:  52%|#####2    | 1564/3000 [36:32<28:20,  1.18s/it, lr: 1.0e-04 loss: 6.187e-01]
latex_v1:  52%|#####2    | 1564/3000 [36:34<28:20,  1.18s/it, lr: 1.0e-04 loss: 5.409e-01]
latex_v1:  52%|#####2    | 1564/3000 [36:34<28:20,  1.18s/it, lr: 1.0e-04 loss: 5.409e-01]
latex_v1:  52%|#####2    | 1565/3000 [36:34<30:05,  1.26s/it, lr: 1.0e-04 loss: 5.409e-01]
latex_v1:  52%|#####2    | 1565/3000 [36:34<30:05,  1.26s/it, lr: 1.0e-04 loss: 5.409e-01]
latex_v1:  52%|#####2    | 1565/3000 [36:35<30:05,  1.26s/it, lr: 1.0e-04 loss: 2.796e-01]
latex_v1:  52%|#####2    | 1565/3000 [36:35<30:05,  1.26s/it, lr: 1.0e-04 loss: 2.796e-01]
latex_v1:  52%|#####2    | 1566/3000 [36:35<31:03,  1.30s/it, lr: 1.0e-04 loss: 2.796e-01]
latex_v1:  52%|#####2    | 1566/3000 [36:35<31:03,  1.30s/it, lr: 1.0e-04 loss: 2.796e-01]
latex_v1:  52%|#####2    | 1566/3000 [36:36<31:03,  1.30s/it, lr: 1.0e-04 loss: 1.239e-01]
latex_v1:  52%|#####2    | 1566/3000 [36:36<31:03,  1.30s/it, lr: 1.0e-04 loss: 1.239e-01]
latex_v1:  52%|#####2    | 1567/3000 [36:36<27:11,  1.14s/it, lr: 1.0e-04 loss: 1.239e-01]
latex_v1:  52%|#####2    | 1567/3000 [36:36<27:11,  1.14s/it, lr: 1.0e-04 loss: 1.239e-01]
latex_v1:  52%|#####2    | 1567/3000 [36:37<27:11,  1.14s/it, lr: 1.0e-04 loss: 4.918e-01]
latex_v1:  52%|#####2    | 1567/3000 [36:37<27:11,  1.14s/it, lr: 1.0e-04 loss: 4.918e-01]
latex_v1:  52%|#####2    | 1568/3000 [36:37<26:04,  1.09s/it, lr: 1.0e-04 loss: 4.918e-01]
latex_v1:  52%|#####2    | 1568/3000 [36:37<26:04,  1.09s/it, lr: 1.0e-04 loss: 4.918e-01]
latex_v1:  52%|#####2    | 1568/3000 [36:40<26:04,  1.09s/it, lr: 1.0e-04 loss: 2.175e-01]
latex_v1:  52%|#####2    | 1568/3000 [36:40<26:04,  1.09s/it, lr: 1.0e-04 loss: 2.175e-01]
latex_v1:  52%|#####2    | 1569/3000 [36:40<38:22,  1.61s/it, lr: 1.0e-04 loss: 2.175e-01]
latex_v1:  52%|#####2    | 1569/3000 [36:40<38:22,  1.61s/it, lr: 1.0e-04 loss: 2.175e-01]
latex_v1:  52%|#####2    | 1569/3000 [36:41<38:22,  1.61s/it, lr: 1.0e-04 loss: 3.326e-01]
latex_v1:  52%|#####2    | 1569/3000 [36:41<38:22,  1.61s/it, lr: 1.0e-04 loss: 3.326e-01]
latex_v1:  52%|#####2    | 1570/3000 [36:42<38:20,  1.61s/it, lr: 1.0e-04 loss: 1.270e-01]
latex_v1:  52%|#####2    | 1570/3000 [36:42<38:20,  1.61s/it, lr: 1.0e-04 loss: 1.270e-01]
latex_v1:  52%|#####2    | 1571/3000 [36:42<28:27,  1.19s/it, lr: 1.0e-04 loss: 1.270e-01]
latex_v1:  52%|#####2    | 1571/3000 [36:42<28:27,  1.19s/it, lr: 1.0e-04 loss: 1.270e-01]
latex_v1:  52%|#####2    | 1571/3000 [36:43<28:27,  1.19s/it, lr: 1.0e-04 loss: 1.303e-01]
latex_v1:  52%|#####2    | 1571/3000 [36:43<28:27,  1.19s/it, lr: 1.0e-04 loss: 1.303e-01]
latex_v1:  52%|#####2    | 1572/3000 [36:43<25:47,  1.08s/it, lr: 1.0e-04 loss: 1.303e-01]
latex_v1:  52%|#####2    | 1572/3000 [36:43<25:47,  1.08s/it, lr: 1.0e-04 loss: 1.303e-01]
latex_v1:  52%|#####2    | 1572/3000 [36:44<25:47,  1.08s/it, lr: 1.0e-04 loss: 8.862e-01]
latex_v1:  52%|#####2    | 1572/3000 [36:44<25:47,  1.08s/it, lr: 1.0e-04 loss: 8.862e-01]
latex_v1:  52%|#####2    | 1573/3000 [36:44<23:41,  1.00it/s, lr: 1.0e-04 loss: 8.862e-01]
latex_v1:  52%|#####2    | 1573/3000 [36:44<23:41,  1.00it/s, lr: 1.0e-04 loss: 8.862e-01]
latex_v1:  52%|#####2    | 1573/3000 [36:45<23:41,  1.00it/s, lr: 1.0e-04 loss: 1.740e-01]
latex_v1:  52%|#####2    | 1573/3000 [36:45<23:41,  1.00it/s, lr: 1.0e-04 loss: 1.740e-01]
latex_v1:  52%|#####2    | 1574/3000 [36:45<22:07,  1.07it/s, lr: 1.0e-04 loss: 1.740e-01]
latex_v1:  52%|#####2    | 1574/3000 [36:45<22:07,  1.07it/s, lr: 1.0e-04 loss: 1.740e-01]
latex_v1:  52%|#####2    | 1574/3000 [36:45<22:07,  1.07it/s, lr: 1.0e-04 loss: 1.732e-01]
latex_v1:  52%|#####2    | 1574/3000 [36:45<22:07,  1.07it/s, lr: 1.0e-04 loss: 1.732e-01]
latex_v1:  52%|#####2    | 1575/3000 [36:45<20:51,  1.14it/s, lr: 1.0e-04 loss: 1.732e-01]
latex_v1:  52%|#####2    | 1575/3000 [36:45<20:51,  1.14it/s, lr: 1.0e-04 loss: 1.732e-01]
latex_v1:  52%|#####2    | 1575/3000 [36:46<20:51,  1.14it/s, lr: 1.0e-04 loss: 2.689e-01]
latex_v1:  52%|#####2    | 1575/3000 [36:46<20:51,  1.14it/s, lr: 1.0e-04 loss: 2.689e-01]
latex_v1:  53%|#####2    | 1576/3000 [36:46<20:05,  1.18it/s, lr: 1.0e-04 loss: 2.689e-01]
latex_v1:  53%|#####2    | 1576/3000 [36:46<20:05,  1.18it/s, lr: 1.0e-04 loss: 2.689e-01]
latex_v1:  53%|#####2    | 1576/3000 [36:48<20:05,  1.18it/s, lr: 1.0e-04 loss: 1.720e-01]
latex_v1:  53%|#####2    | 1576/3000 [36:48<20:05,  1.18it/s, lr: 1.0e-04 loss: 1.720e-01]
latex_v1:  53%|#####2    | 1577/3000 [36:48<23:15,  1.02it/s, lr: 1.0e-04 loss: 1.720e-01]
latex_v1:  53%|#####2    | 1577/3000 [36:48<23:15,  1.02it/s, lr: 1.0e-04 loss: 1.720e-01]
latex_v1:  53%|#####2    | 1577/3000 [36:49<23:15,  1.02it/s, lr: 1.0e-04 loss: 2.790e-01]
latex_v1:  53%|#####2    | 1577/3000 [36:49<23:15,  1.02it/s, lr: 1.0e-04 loss: 2.790e-01]
latex_v1:  53%|#####2    | 1578/3000 [36:49<24:36,  1.04s/it, lr: 1.0e-04 loss: 2.790e-01]
latex_v1:  53%|#####2    | 1578/3000 [36:49<24:36,  1.04s/it, lr: 1.0e-04 loss: 2.790e-01]
latex_v1:  53%|#####2    | 1578/3000 [36:50<24:36,  1.04s/it, lr: 1.0e-04 loss: 2.945e-01]
latex_v1:  53%|#####2    | 1578/3000 [36:50<24:36,  1.04s/it, lr: 1.0e-04 loss: 2.945e-01]
latex_v1:  53%|#####2    | 1579/3000 [36:50<27:59,  1.18s/it, lr: 1.0e-04 loss: 2.945e-01]
latex_v1:  53%|#####2    | 1579/3000 [36:50<27:59,  1.18s/it, lr: 1.0e-04 loss: 2.945e-01]
latex_v1:  53%|#####2    | 1579/3000 [36:51<27:59,  1.18s/it, lr: 1.0e-04 loss: 2.078e-01]
latex_v1:  53%|#####2    | 1579/3000 [36:51<27:59,  1.18s/it, lr: 1.0e-04 loss: 2.078e-01]
latex_v1:  53%|#####2    | 1580/3000 [36:52<27:57,  1.18s/it, lr: 1.0e-04 loss: 5.154e-01]
latex_v1:  53%|#####2    | 1580/3000 [36:52<27:57,  1.18s/it, lr: 1.0e-04 loss: 5.154e-01]
latex_v1:  53%|#####2    | 1581/3000 [36:52<21:06,  1.12it/s, lr: 1.0e-04 loss: 5.154e-01]
latex_v1:  53%|#####2    | 1581/3000 [36:52<21:06,  1.12it/s, lr: 1.0e-04 loss: 5.154e-01]
latex_v1:  53%|#####2    | 1581/3000 [36:53<21:06,  1.12it/s, lr: 1.0e-04 loss: 9.716e-02]
latex_v1:  53%|#####2    | 1581/3000 [36:53<21:06,  1.12it/s, lr: 1.0e-04 loss: 9.716e-02]
latex_v1:  53%|#####2    | 1582/3000 [36:53<20:18,  1.16it/s, lr: 1.0e-04 loss: 9.716e-02]
latex_v1:  53%|#####2    | 1582/3000 [36:53<20:18,  1.16it/s, lr: 1.0e-04 loss: 9.716e-02]
latex_v1:  53%|#####2    | 1582/3000 [36:55<20:18,  1.16it/s, lr: 1.0e-04 loss: 1.834e-01]
latex_v1:  53%|#####2    | 1582/3000 [36:55<20:18,  1.16it/s, lr: 1.0e-04 loss: 1.834e-01]
latex_v1:  53%|#####2    | 1583/3000 [36:55<25:11,  1.07s/it, lr: 1.0e-04 loss: 1.834e-01]
latex_v1:  53%|#####2    | 1583/3000 [36:55<25:11,  1.07s/it, lr: 1.0e-04 loss: 1.834e-01]
latex_v1:  53%|#####2    | 1583/3000 [36:56<25:11,  1.07s/it, lr: 1.0e-04 loss: 5.562e-01]
latex_v1:  53%|#####2    | 1583/3000 [36:56<25:11,  1.07s/it, lr: 1.0e-04 loss: 5.562e-01]
latex_v1:  53%|#####2    | 1584/3000 [36:56<25:49,  1.09s/it, lr: 1.0e-04 loss: 5.562e-01]
latex_v1:  53%|#####2    | 1584/3000 [36:56<25:49,  1.09s/it, lr: 1.0e-04 loss: 5.562e-01]
latex_v1:  53%|#####2    | 1584/3000 [36:57<25:49,  1.09s/it, lr: 1.0e-04 loss: 6.663e-01]
latex_v1:  53%|#####2    | 1584/3000 [36:57<25:49,  1.09s/it, lr: 1.0e-04 loss: 6.663e-01]
latex_v1:  53%|#####2    | 1585/3000 [36:57<26:13,  1.11s/it, lr: 1.0e-04 loss: 6.663e-01]
latex_v1:  53%|#####2    | 1585/3000 [36:57<26:13,  1.11s/it, lr: 1.0e-04 loss: 6.663e-01]
latex_v1:  53%|#####2    | 1585/3000 [36:58<26:13,  1.11s/it, lr: 1.0e-04 loss: 4.915e-01]
latex_v1:  53%|#####2    | 1585/3000 [36:58<26:13,  1.11s/it, lr: 1.0e-04 loss: 4.915e-01]
latex_v1:  53%|#####2    | 1586/3000 [36:58<23:41,  1.01s/it, lr: 1.0e-04 loss: 4.915e-01]
latex_v1:  53%|#####2    | 1586/3000 [36:58<23:41,  1.01s/it, lr: 1.0e-04 loss: 4.915e-01]
latex_v1:  53%|#####2    | 1586/3000 [36:59<23:41,  1.01s/it, lr: 1.0e-04 loss: 6.158e-01]
latex_v1:  53%|#####2    | 1586/3000 [36:59<23:41,  1.01s/it, lr: 1.0e-04 loss: 6.158e-01]
latex_v1:  53%|#####2    | 1587/3000 [36:59<21:54,  1.07it/s, lr: 1.0e-04 loss: 6.158e-01]
latex_v1:  53%|#####2    | 1587/3000 [36:59<21:54,  1.07it/s, lr: 1.0e-04 loss: 6.158e-01]
latex_v1:  53%|#####2    | 1587/3000 [37:00<21:54,  1.07it/s, lr: 1.0e-04 loss: 2.549e-01]
latex_v1:  53%|#####2    | 1587/3000 [37:00<21:54,  1.07it/s, lr: 1.0e-04 loss: 2.549e-01]
latex_v1:  53%|#####2    | 1588/3000 [37:00<24:36,  1.05s/it, lr: 1.0e-04 loss: 2.549e-01]
latex_v1:  53%|#####2    | 1588/3000 [37:00<24:36,  1.05s/it, lr: 1.0e-04 loss: 2.549e-01]
latex_v1:  53%|#####2    | 1588/3000 [37:01<24:36,  1.05s/it, lr: 1.0e-04 loss: 7.253e-01]
latex_v1:  53%|#####2    | 1588/3000 [37:01<24:36,  1.05s/it, lr: 1.0e-04 loss: 7.253e-01]
latex_v1:  53%|#####2    | 1589/3000 [37:01<25:22,  1.08s/it, lr: 1.0e-04 loss: 7.253e-01]
latex_v1:  53%|#####2    | 1589/3000 [37:01<25:22,  1.08s/it, lr: 1.0e-04 loss: 7.253e-01]
latex_v1:  53%|#####2    | 1589/3000 [37:04<25:22,  1.08s/it, lr: 1.0e-04 loss: 1.646e-01]
latex_v1:  53%|#####2    | 1589/3000 [37:04<25:22,  1.08s/it, lr: 1.0e-04 loss: 1.646e-01]
latex_v1:  53%|#####3    | 1590/3000 [37:05<25:21,  1.08s/it, lr: 1.0e-04 loss: 2.059e-02]
latex_v1:  53%|#####3    | 1590/3000 [37:05<25:21,  1.08s/it, lr: 1.0e-04 loss: 2.059e-02]
latex_v1:  53%|#####3    | 1591/3000 [37:05<20:59,  1.12it/s, lr: 1.0e-04 loss: 2.059e-02]
latex_v1:  53%|#####3    | 1591/3000 [37:05<20:59,  1.12it/s, lr: 1.0e-04 loss: 2.059e-02]
latex_v1:  53%|#####3    | 1591/3000 [37:07<20:59,  1.12it/s, lr: 1.0e-04 loss: 4.945e-01]
latex_v1:  53%|#####3    | 1591/3000 [37:07<20:59,  1.12it/s, lr: 1.0e-04 loss: 4.945e-01]
latex_v1:  53%|#####3    | 1592/3000 [37:07<23:31,  1.00s/it, lr: 1.0e-04 loss: 4.945e-01]
latex_v1:  53%|#####3    | 1592/3000 [37:07<23:31,  1.00s/it, lr: 1.0e-04 loss: 4.945e-01]
latex_v1:  53%|#####3    | 1592/3000 [37:08<23:31,  1.00s/it, lr: 1.0e-04 loss: 7.682e-02]
latex_v1:  53%|#####3    | 1592/3000 [37:08<23:31,  1.00s/it, lr: 1.0e-04 loss: 7.682e-02]
latex_v1:  53%|#####3    | 1593/3000 [37:08<24:34,  1.05s/it, lr: 1.0e-04 loss: 7.682e-02]
latex_v1:  53%|#####3    | 1593/3000 [37:08<24:34,  1.05s/it, lr: 1.0e-04 loss: 7.682e-02]
latex_v1:  53%|#####3    | 1593/3000 [37:09<24:34,  1.05s/it, lr: 1.0e-04 loss: 9.684e-02]
latex_v1:  53%|#####3    | 1593/3000 [37:09<24:34,  1.05s/it, lr: 1.0e-04 loss: 9.684e-02]
latex_v1:  53%|#####3    | 1594/3000 [37:09<26:56,  1.15s/it, lr: 1.0e-04 loss: 9.684e-02]
latex_v1:  53%|#####3    | 1594/3000 [37:09<26:56,  1.15s/it, lr: 1.0e-04 loss: 9.684e-02]
latex_v1:  53%|#####3    | 1594/3000 [37:10<26:56,  1.15s/it, lr: 1.0e-04 loss: 5.161e-01]
latex_v1:  53%|#####3    | 1594/3000 [37:10<26:56,  1.15s/it, lr: 1.0e-04 loss: 5.161e-01]
latex_v1:  53%|#####3    | 1595/3000 [37:10<24:11,  1.03s/it, lr: 1.0e-04 loss: 5.161e-01]
latex_v1:  53%|#####3    | 1595/3000 [37:10<24:11,  1.03s/it, lr: 1.0e-04 loss: 5.161e-01]
latex_v1:  53%|#####3    | 1595/3000 [37:12<24:11,  1.03s/it, lr: 1.0e-04 loss: 3.896e-01]
latex_v1:  53%|#####3    | 1595/3000 [37:12<24:11,  1.03s/it, lr: 1.0e-04 loss: 3.896e-01]
latex_v1:  53%|#####3    | 1596/3000 [37:12<27:32,  1.18s/it, lr: 1.0e-04 loss: 3.896e-01]
latex_v1:  53%|#####3    | 1596/3000 [37:12<27:32,  1.18s/it, lr: 1.0e-04 loss: 3.896e-01]
latex_v1:  53%|#####3    | 1596/3000 [37:13<27:32,  1.18s/it, lr: 1.0e-04 loss: 5.533e-01]
latex_v1:  53%|#####3    | 1596/3000 [37:13<27:32,  1.18s/it, lr: 1.0e-04 loss: 5.533e-01]
latex_v1:  53%|#####3    | 1597/3000 [37:13<26:12,  1.12s/it, lr: 1.0e-04 loss: 5.533e-01]
latex_v1:  53%|#####3    | 1597/3000 [37:13<26:12,  1.12s/it, lr: 1.0e-04 loss: 5.533e-01]
latex_v1:  53%|#####3    | 1597/3000 [37:13<26:12,  1.12s/it, lr: 1.0e-04 loss: 1.131e-01]
latex_v1:  53%|#####3    | 1597/3000 [37:13<26:12,  1.12s/it, lr: 1.0e-04 loss: 1.131e-01]
latex_v1:  53%|#####3    | 1598/3000 [37:13<23:35,  1.01s/it, lr: 1.0e-04 loss: 1.131e-01]
latex_v1:  53%|#####3    | 1598/3000 [37:13<23:35,  1.01s/it, lr: 1.0e-04 loss: 1.131e-01]
latex_v1:  53%|#####3    | 1598/3000 [37:16<23:35,  1.01s/it, lr: 1.0e-04 loss: 7.315e-01]
latex_v1:  53%|#####3    | 1598/3000 [37:16<23:35,  1.01s/it, lr: 1.0e-04 loss: 7.315e-01]
latex_v1:  53%|#####3    | 1599/3000 [37:16<35:54,  1.54s/it, lr: 1.0e-04 loss: 7.315e-01]
latex_v1:  53%|#####3    | 1599/3000 [37:16<35:54,  1.54s/it, lr: 1.0e-04 loss: 7.315e-01]
latex_v1:  53%|#####3    | 1599/3000 [37:17<35:54,  1.54s/it, lr: 1.0e-04 loss: 6.417e-01]
latex_v1:  53%|#####3    | 1599/3000 [37:17<35:54,  1.54s/it, lr: 1.0e-04 loss: 6.417e-01]
latex_v1:  53%|#####3    | 1600/3000 [37:18<35:53,  1.54s/it, lr: 1.0e-04 loss: 1.507e-01]
latex_v1:  53%|#####3    | 1600/3000 [37:18<35:53,  1.54s/it, lr: 1.0e-04 loss: 1.507e-01]
latex_v1:  53%|#####3    | 1601/3000 [37:18<26:34,  1.14s/it, lr: 1.0e-04 loss: 1.507e-01]
latex_v1:  53%|#####3    | 1601/3000 [37:18<26:34,  1.14s/it, lr: 1.0e-04 loss: 1.507e-01]
latex_v1:  53%|#####3    | 1601/3000 [37:19<26:34,  1.14s/it, lr: 1.0e-04 loss: 2.442e-01]
latex_v1:  53%|#####3    | 1601/3000 [37:19<26:34,  1.14s/it, lr: 1.0e-04 loss: 2.442e-01]
latex_v1:  53%|#####3    | 1602/3000 [37:19<24:19,  1.04s/it, lr: 1.0e-04 loss: 2.442e-01]
latex_v1:  53%|#####3    | 1602/3000 [37:19<24:19,  1.04s/it, lr: 1.0e-04 loss: 2.442e-01]
latex_v1:  53%|#####3    | 1602/3000 [37:21<24:19,  1.04s/it, lr: 1.0e-04 loss: 3.905e-01]
latex_v1:  53%|#####3    | 1602/3000 [37:21<24:19,  1.04s/it, lr: 1.0e-04 loss: 3.905e-01]
latex_v1:  53%|#####3    | 1603/3000 [37:21<27:56,  1.20s/it, lr: 1.0e-04 loss: 3.905e-01]
latex_v1:  53%|#####3    | 1603/3000 [37:21<27:56,  1.20s/it, lr: 1.0e-04 loss: 3.905e-01]
latex_v1:  53%|#####3    | 1603/3000 [37:23<27:56,  1.20s/it, lr: 1.0e-04 loss: 6.846e-01]
latex_v1:  53%|#####3    | 1603/3000 [37:23<27:56,  1.20s/it, lr: 1.0e-04 loss: 6.846e-01]
latex_v1:  53%|#####3    | 1604/3000 [37:23<37:23,  1.61s/it, lr: 1.0e-04 loss: 6.846e-01]
latex_v1:  53%|#####3    | 1604/3000 [37:23<37:23,  1.61s/it, lr: 1.0e-04 loss: 6.846e-01]
latex_v1:  53%|#####3    | 1604/3000 [37:25<37:23,  1.61s/it, lr: 1.0e-04 loss: 4.484e-01]
latex_v1:  53%|#####3    | 1604/3000 [37:25<37:23,  1.61s/it, lr: 1.0e-04 loss: 4.484e-01]
latex_v1:  54%|#####3    | 1605/3000 [37:25<36:49,  1.58s/it, lr: 1.0e-04 loss: 4.484e-01]
latex_v1:  54%|#####3    | 1605/3000 [37:25<36:49,  1.58s/it, lr: 1.0e-04 loss: 4.484e-01]
latex_v1:  54%|#####3    | 1605/3000 [37:26<36:49,  1.58s/it, lr: 1.0e-04 loss: 5.963e-01]
latex_v1:  54%|#####3    | 1605/3000 [37:26<36:49,  1.58s/it, lr: 1.0e-04 loss: 5.963e-01]
latex_v1:  54%|#####3    | 1606/3000 [37:26<33:21,  1.44s/it, lr: 1.0e-04 loss: 5.963e-01]
latex_v1:  54%|#####3    | 1606/3000 [37:26<33:21,  1.44s/it, lr: 1.0e-04 loss: 5.963e-01]
latex_v1:  54%|#####3    | 1606/3000 [37:27<33:21,  1.44s/it, lr: 1.0e-04 loss: 6.113e-01]
latex_v1:  54%|#####3    | 1606/3000 [37:27<33:21,  1.44s/it, lr: 1.0e-04 loss: 6.113e-01]
latex_v1:  54%|#####3    | 1607/3000 [37:27<33:07,  1.43s/it, lr: 1.0e-04 loss: 6.113e-01]
latex_v1:  54%|#####3    | 1607/3000 [37:27<33:07,  1.43s/it, lr: 1.0e-04 loss: 6.113e-01]
latex_v1:  54%|#####3    | 1607/3000 [37:28<33:07,  1.43s/it, lr: 1.0e-04 loss: 1.693e-01]
latex_v1:  54%|#####3    | 1607/3000 [37:28<33:07,  1.43s/it, lr: 1.0e-04 loss: 1.693e-01]
latex_v1:  54%|#####3    | 1608/3000 [37:28<28:27,  1.23s/it, lr: 1.0e-04 loss: 1.693e-01]
latex_v1:  54%|#####3    | 1608/3000 [37:28<28:27,  1.23s/it, lr: 1.0e-04 loss: 1.693e-01]
latex_v1:  54%|#####3    | 1608/3000 [37:30<28:27,  1.23s/it, lr: 1.0e-04 loss: 1.268e-01]
latex_v1:  54%|#####3    | 1608/3000 [37:30<28:27,  1.23s/it, lr: 1.0e-04 loss: 1.268e-01]
latex_v1:  54%|#####3    | 1609/3000 [37:30<29:56,  1.29s/it, lr: 1.0e-04 loss: 1.268e-01]
latex_v1:  54%|#####3    | 1609/3000 [37:30<29:56,  1.29s/it, lr: 1.0e-04 loss: 1.268e-01]
latex_v1:  54%|#####3    | 1609/3000 [37:31<29:56,  1.29s/it, lr: 1.0e-04 loss: 1.571e-01]
latex_v1:  54%|#####3    | 1609/3000 [37:31<29:56,  1.29s/it, lr: 1.0e-04 loss: 1.571e-01]
latex_v1:  54%|#####3    | 1610/3000 [37:32<29:55,  1.29s/it, lr: 1.0e-04 loss: 6.507e-01]
latex_v1:  54%|#####3    | 1610/3000 [37:32<29:55,  1.29s/it, lr: 1.0e-04 loss: 6.507e-01]
latex_v1:  54%|#####3    | 1611/3000 [37:32<23:35,  1.02s/it, lr: 1.0e-04 loss: 6.507e-01]
latex_v1:  54%|#####3    | 1611/3000 [37:32<23:35,  1.02s/it, lr: 1.0e-04 loss: 6.507e-01]
latex_v1:  54%|#####3    | 1611/3000 [37:33<23:35,  1.02s/it, lr: 1.0e-04 loss: 5.280e-02]
latex_v1:  54%|#####3    | 1611/3000 [37:33<23:35,  1.02s/it, lr: 1.0e-04 loss: 5.280e-02]
latex_v1:  54%|#####3    | 1612/3000 [37:33<21:58,  1.05it/s, lr: 1.0e-04 loss: 5.280e-02]
latex_v1:  54%|#####3    | 1612/3000 [37:33<21:58,  1.05it/s, lr: 1.0e-04 loss: 5.280e-02]
latex_v1:  54%|#####3    | 1612/3000 [37:34<21:58,  1.05it/s, lr: 1.0e-04 loss: 9.643e-02]
latex_v1:  54%|#####3    | 1612/3000 [37:34<21:58,  1.05it/s, lr: 1.0e-04 loss: 9.643e-02]
latex_v1:  54%|#####3    | 1613/3000 [37:34<24:53,  1.08s/it, lr: 1.0e-04 loss: 9.643e-02]
latex_v1:  54%|#####3    | 1613/3000 [37:34<24:53,  1.08s/it, lr: 1.0e-04 loss: 9.643e-02]
latex_v1:  54%|#####3    | 1613/3000 [37:36<24:53,  1.08s/it, lr: 1.0e-04 loss: 5.316e-01]
latex_v1:  54%|#####3    | 1613/3000 [37:36<24:53,  1.08s/it, lr: 1.0e-04 loss: 5.316e-01]
latex_v1:  54%|#####3    | 1614/3000 [37:36<27:42,  1.20s/it, lr: 1.0e-04 loss: 5.316e-01]
latex_v1:  54%|#####3    | 1614/3000 [37:36<27:42,  1.20s/it, lr: 1.0e-04 loss: 5.316e-01]
latex_v1:  54%|#####3    | 1614/3000 [37:37<27:42,  1.20s/it, lr: 1.0e-04 loss: 5.748e-01]
latex_v1:  54%|#####3    | 1614/3000 [37:37<27:42,  1.20s/it, lr: 1.0e-04 loss: 5.748e-01]
latex_v1:  54%|#####3    | 1615/3000 [37:37<29:21,  1.27s/it, lr: 1.0e-04 loss: 5.748e-01]
latex_v1:  54%|#####3    | 1615/3000 [37:37<29:21,  1.27s/it, lr: 1.0e-04 loss: 5.748e-01]
latex_v1:  54%|#####3    | 1615/3000 [37:39<29:21,  1.27s/it, lr: 1.0e-04 loss: 4.265e-01]
latex_v1:  54%|#####3    | 1615/3000 [37:39<29:21,  1.27s/it, lr: 1.0e-04 loss: 4.265e-01]
latex_v1:  54%|#####3    | 1616/3000 [37:39<33:21,  1.45s/it, lr: 1.0e-04 loss: 4.265e-01]
latex_v1:  54%|#####3    | 1616/3000 [37:39<33:21,  1.45s/it, lr: 1.0e-04 loss: 4.265e-01]
latex_v1:  54%|#####3    | 1616/3000 [37:40<33:21,  1.45s/it, lr: 1.0e-04 loss: 1.397e-01]
latex_v1:  54%|#####3    | 1616/3000 [37:40<33:21,  1.45s/it, lr: 1.0e-04 loss: 1.397e-01]
latex_v1:  54%|#####3    | 1617/3000 [37:40<28:41,  1.24s/it, lr: 1.0e-04 loss: 1.397e-01]
latex_v1:  54%|#####3    | 1617/3000 [37:40<28:41,  1.24s/it, lr: 1.0e-04 loss: 1.397e-01]
latex_v1:  54%|#####3    | 1617/3000 [37:41<28:41,  1.24s/it, lr: 1.0e-04 loss: 8.756e-02]
latex_v1:  54%|#####3    | 1617/3000 [37:41<28:41,  1.24s/it, lr: 1.0e-04 loss: 8.756e-02]
latex_v1:  54%|#####3    | 1618/3000 [37:41<25:24,  1.10s/it, lr: 1.0e-04 loss: 8.756e-02]
latex_v1:  54%|#####3    | 1618/3000 [37:41<25:24,  1.10s/it, lr: 1.0e-04 loss: 8.756e-02]
latex_v1:  54%|#####3    | 1618/3000 [37:42<25:24,  1.10s/it, lr: 1.0e-04 loss: 6.704e-01]
latex_v1:  54%|#####3    | 1618/3000 [37:42<25:24,  1.10s/it, lr: 1.0e-04 loss: 6.704e-01]
latex_v1:  54%|#####3    | 1619/3000 [37:42<26:55,  1.17s/it, lr: 1.0e-04 loss: 6.704e-01]
latex_v1:  54%|#####3    | 1619/3000 [37:42<26:55,  1.17s/it, lr: 1.0e-04 loss: 6.704e-01]
latex_v1:  54%|#####3    | 1619/3000 [37:43<26:55,  1.17s/it, lr: 1.0e-04 loss: 1.550e-01]
latex_v1:  54%|#####3    | 1619/3000 [37:43<26:55,  1.17s/it, lr: 1.0e-04 loss: 1.550e-01]
latex_v1:  54%|#####4    | 1620/3000 [37:44<26:54,  1.17s/it, lr: 1.0e-04 loss: 7.529e-02]
latex_v1:  54%|#####4    | 1620/3000 [37:44<26:54,  1.17s/it, lr: 1.0e-04 loss: 7.529e-02]
latex_v1:  54%|#####4    | 1621/3000 [37:44<18:36,  1.24it/s, lr: 1.0e-04 loss: 7.529e-02]
latex_v1:  54%|#####4    | 1621/3000 [37:44<18:36,  1.24it/s, lr: 1.0e-04 loss: 7.529e-02]
latex_v1:  54%|#####4    | 1621/3000 [37:46<18:36,  1.24it/s, lr: 1.0e-04 loss: 4.316e-01]
latex_v1:  54%|#####4    | 1621/3000 [37:46<18:36,  1.24it/s, lr: 1.0e-04 loss: 4.316e-01]
latex_v1:  54%|#####4    | 1622/3000 [37:46<22:48,  1.01it/s, lr: 1.0e-04 loss: 4.316e-01]
latex_v1:  54%|#####4    | 1622/3000 [37:46<22:48,  1.01it/s, lr: 1.0e-04 loss: 4.316e-01]
latex_v1:  54%|#####4    | 1622/3000 [37:49<22:48,  1.01it/s, lr: 1.0e-04 loss: 2.421e-01]
latex_v1:  54%|#####4    | 1622/3000 [37:49<22:48,  1.01it/s, lr: 1.0e-04 loss: 2.421e-01]
latex_v1:  54%|#####4    | 1623/3000 [37:49<34:23,  1.50s/it, lr: 1.0e-04 loss: 2.421e-01]
latex_v1:  54%|#####4    | 1623/3000 [37:49<34:23,  1.50s/it, lr: 1.0e-04 loss: 2.421e-01]
latex_v1:  54%|#####4    | 1623/3000 [37:50<34:23,  1.50s/it, lr: 1.0e-04 loss: 2.704e-01]
latex_v1:  54%|#####4    | 1623/3000 [37:50<34:23,  1.50s/it, lr: 1.0e-04 loss: 2.704e-01]
latex_v1:  54%|#####4    | 1624/3000 [37:50<34:11,  1.49s/it, lr: 1.0e-04 loss: 2.704e-01]
latex_v1:  54%|#####4    | 1624/3000 [37:50<34:11,  1.49s/it, lr: 1.0e-04 loss: 2.704e-01]
latex_v1:  54%|#####4    | 1624/3000 [37:52<34:11,  1.49s/it, lr: 1.0e-04 loss: 3.305e-01]
latex_v1:  54%|#####4    | 1624/3000 [37:52<34:11,  1.49s/it, lr: 1.0e-04 loss: 3.305e-01]
latex_v1:  54%|#####4    | 1625/3000 [37:52<33:45,  1.47s/it, lr: 1.0e-04 loss: 3.305e-01]
latex_v1:  54%|#####4    | 1625/3000 [37:52<33:45,  1.47s/it, lr: 1.0e-04 loss: 3.305e-01]
latex_v1:  54%|#####4    | 1625/3000 [37:52<33:45,  1.47s/it, lr: 1.0e-04 loss: 2.025e-01]
latex_v1:  54%|#####4    | 1625/3000 [37:52<33:45,  1.47s/it, lr: 1.0e-04 loss: 2.025e-01]
latex_v1:  54%|#####4    | 1626/3000 [37:52<28:59,  1.27s/it, lr: 1.0e-04 loss: 2.025e-01]
latex_v1:  54%|#####4    | 1626/3000 [37:52<28:59,  1.27s/it, lr: 1.0e-04 loss: 2.025e-01]
latex_v1:  54%|#####4    | 1626/3000 [37:54<28:59,  1.27s/it, lr: 1.0e-04 loss: 5.737e-01]
latex_v1:  54%|#####4    | 1626/3000 [37:54<28:59,  1.27s/it, lr: 1.0e-04 loss: 5.737e-01]
latex_v1:  54%|#####4    | 1627/3000 [37:54<33:09,  1.45s/it, lr: 1.0e-04 loss: 5.737e-01]
latex_v1:  54%|#####4    | 1627/3000 [37:54<33:09,  1.45s/it, lr: 1.0e-04 loss: 5.737e-01]
latex_v1:  54%|#####4    | 1627/3000 [37:56<33:09,  1.45s/it, lr: 1.0e-04 loss: 8.987e-02]
latex_v1:  54%|#####4    | 1627/3000 [37:56<33:09,  1.45s/it, lr: 1.0e-04 loss: 8.987e-02]
latex_v1:  54%|#####4    | 1628/3000 [37:56<33:57,  1.48s/it, lr: 1.0e-04 loss: 8.987e-02]
latex_v1:  54%|#####4    | 1628/3000 [37:56<33:57,  1.48s/it, lr: 1.0e-04 loss: 8.987e-02]
latex_v1:  54%|#####4    | 1628/3000 [37:57<33:57,  1.48s/it, lr: 1.0e-04 loss: 7.291e-01]
latex_v1:  54%|#####4    | 1628/3000 [37:57<33:57,  1.48s/it, lr: 1.0e-04 loss: 7.291e-01]
latex_v1:  54%|#####4    | 1629/3000 [37:57<30:21,  1.33s/it, lr: 1.0e-04 loss: 7.291e-01]
latex_v1:  54%|#####4    | 1629/3000 [37:57<30:21,  1.33s/it, lr: 1.0e-04 loss: 7.291e-01]
latex_v1:  54%|#####4    | 1629/3000 [37:58<30:21,  1.33s/it, lr: 1.0e-04 loss: 4.606e-01]
latex_v1:  54%|#####4    | 1629/3000 [37:58<30:21,  1.33s/it, lr: 1.0e-04 loss: 4.606e-01]
latex_v1:  54%|#####4    | 1630/3000 [37:58<30:20,  1.33s/it, lr: 1.0e-04 loss: 3.163e-01]
latex_v1:  54%|#####4    | 1630/3000 [37:58<30:20,  1.33s/it, lr: 1.0e-04 loss: 3.163e-01]
latex_v1:  54%|#####4    | 1631/3000 [37:58<20:26,  1.12it/s, lr: 1.0e-04 loss: 3.163e-01]
latex_v1:  54%|#####4    | 1631/3000 [37:58<20:26,  1.12it/s, lr: 1.0e-04 loss: 3.163e-01]
latex_v1:  54%|#####4    | 1631/3000 [38:00<20:26,  1.12it/s, lr: 1.0e-04 loss: 4.107e-01]
latex_v1:  54%|#####4    | 1631/3000 [38:00<20:26,  1.12it/s, lr: 1.0e-04 loss: 4.107e-01]
latex_v1:  54%|#####4    | 1632/3000 [38:00<24:07,  1.06s/it, lr: 1.0e-04 loss: 4.107e-01]
latex_v1:  54%|#####4    | 1632/3000 [38:00<24:07,  1.06s/it, lr: 1.0e-04 loss: 4.107e-01]
latex_v1:  54%|#####4    | 1632/3000 [38:01<24:07,  1.06s/it, lr: 1.0e-04 loss: 2.390e-01]
latex_v1:  54%|#####4    | 1632/3000 [38:01<24:07,  1.06s/it, lr: 1.0e-04 loss: 2.390e-01]
latex_v1:  54%|#####4    | 1633/3000 [38:01<22:13,  1.02it/s, lr: 1.0e-04 loss: 2.390e-01]
latex_v1:  54%|#####4    | 1633/3000 [38:01<22:13,  1.02it/s, lr: 1.0e-04 loss: 2.390e-01]
latex_v1:  54%|#####4    | 1633/3000 [38:03<22:13,  1.02it/s, lr: 1.0e-04 loss: 4.463e-01]
latex_v1:  54%|#####4    | 1633/3000 [38:03<22:13,  1.02it/s, lr: 1.0e-04 loss: 4.463e-01]
latex_v1:  54%|#####4    | 1634/3000 [38:03<29:39,  1.30s/it, lr: 1.0e-04 loss: 4.463e-01]
latex_v1:  54%|#####4    | 1634/3000 [38:03<29:39,  1.30s/it, lr: 1.0e-04 loss: 4.463e-01]
latex_v1:  54%|#####4    | 1634/3000 [38:04<29:39,  1.30s/it, lr: 1.0e-04 loss: 2.946e-01]
latex_v1:  54%|#####4    | 1634/3000 [38:04<29:39,  1.30s/it, lr: 1.0e-04 loss: 2.946e-01]
latex_v1:  55%|#####4    | 1635/3000 [38:04<31:08,  1.37s/it, lr: 1.0e-04 loss: 2.946e-01]
latex_v1:  55%|#####4    | 1635/3000 [38:04<31:08,  1.37s/it, lr: 1.0e-04 loss: 2.946e-01]
latex_v1:  55%|#####4    | 1635/3000 [38:07<31:08,  1.37s/it, lr: 1.0e-04 loss: 6.852e-01]
latex_v1:  55%|#####4    | 1635/3000 [38:07<31:08,  1.37s/it, lr: 1.0e-04 loss: 6.852e-01]
latex_v1:  55%|#####4    | 1636/3000 [38:07<40:46,  1.79s/it, lr: 1.0e-04 loss: 6.852e-01]
latex_v1:  55%|#####4    | 1636/3000 [38:07<40:46,  1.79s/it, lr: 1.0e-04 loss: 6.852e-01]
latex_v1:  55%|#####4    | 1636/3000 [38:08<40:46,  1.79s/it, lr: 1.0e-04 loss: 3.794e-01]
latex_v1:  55%|#####4    | 1636/3000 [38:08<40:46,  1.79s/it, lr: 1.0e-04 loss: 3.794e-01]
latex_v1:  55%|#####4    | 1637/3000 [38:08<33:58,  1.50s/it, lr: 1.0e-04 loss: 3.794e-01]
latex_v1:  55%|#####4    | 1637/3000 [38:08<33:58,  1.50s/it, lr: 1.0e-04 loss: 3.794e-01]
latex_v1:  55%|#####4    | 1637/3000 [38:10<33:58,  1.50s/it, lr: 1.0e-04 loss: 1.754e-01]
latex_v1:  55%|#####4    | 1637/3000 [38:10<33:58,  1.50s/it, lr: 1.0e-04 loss: 1.754e-01]
latex_v1:  55%|#####4    | 1638/3000 [38:10<35:14,  1.55s/it, lr: 1.0e-04 loss: 1.754e-01]
latex_v1:  55%|#####4    | 1638/3000 [38:10<35:14,  1.55s/it, lr: 1.0e-04 loss: 1.754e-01]
latex_v1:  55%|#####4    | 1638/3000 [38:13<35:14,  1.55s/it, lr: 1.0e-04 loss: 1.445e-01]
latex_v1:  55%|#####4    | 1638/3000 [38:13<35:14,  1.55s/it, lr: 1.0e-04 loss: 1.445e-01]
latex_v1:  55%|#####4    | 1639/3000 [38:13<44:21,  1.96s/it, lr: 1.0e-04 loss: 1.445e-01]
latex_v1:  55%|#####4    | 1639/3000 [38:13<44:21,  1.96s/it, lr: 1.0e-04 loss: 1.445e-01]
latex_v1:  55%|#####4    | 1639/3000 [38:14<44:21,  1.96s/it, lr: 1.0e-04 loss: 4.155e-01]
latex_v1:  55%|#####4    | 1639/3000 [38:14<44:21,  1.96s/it, lr: 1.0e-04 loss: 4.155e-01]
latex_v1:  55%|#####4    | 1640/3000 [38:15<44:19,  1.96s/it, lr: 1.0e-04 loss: 6.475e-01]
latex_v1:  55%|#####4    | 1640/3000 [38:15<44:19,  1.96s/it, lr: 1.0e-04 loss: 6.475e-01]
latex_v1:  55%|#####4    | 1641/3000 [38:15<27:59,  1.24s/it, lr: 1.0e-04 loss: 6.475e-01]
latex_v1:  55%|#####4    | 1641/3000 [38:15<27:59,  1.24s/it, lr: 1.0e-04 loss: 6.475e-01]
latex_v1:  55%|#####4    | 1641/3000 [38:16<27:59,  1.24s/it, lr: 1.0e-04 loss: 1.161e-01]
latex_v1:  55%|#####4    | 1641/3000 [38:16<27:59,  1.24s/it, lr: 1.0e-04 loss: 1.161e-01]
latex_v1:  55%|#####4    | 1642/3000 [38:16<25:16,  1.12s/it, lr: 1.0e-04 loss: 1.161e-01]
latex_v1:  55%|#####4    | 1642/3000 [38:16<25:16,  1.12s/it, lr: 1.0e-04 loss: 1.161e-01]
latex_v1:  55%|#####4    | 1642/3000 [38:16<25:16,  1.12s/it, lr: 1.0e-04 loss: 3.924e-01]
latex_v1:  55%|#####4    | 1642/3000 [38:16<25:16,  1.12s/it, lr: 1.0e-04 loss: 3.924e-01]
latex_v1:  55%|#####4    | 1643/3000 [38:16<23:07,  1.02s/it, lr: 1.0e-04 loss: 3.924e-01]
latex_v1:  55%|#####4    | 1643/3000 [38:16<23:07,  1.02s/it, lr: 1.0e-04 loss: 3.924e-01]
latex_v1:  55%|#####4    | 1643/3000 [38:18<23:07,  1.02s/it, lr: 1.0e-04 loss: 3.719e-01]
latex_v1:  55%|#####4    | 1643/3000 [38:18<23:07,  1.02s/it, lr: 1.0e-04 loss: 3.719e-01]
latex_v1:  55%|#####4    | 1644/3000 [38:18<24:05,  1.07s/it, lr: 1.0e-04 loss: 3.719e-01]
latex_v1:  55%|#####4    | 1644/3000 [38:18<24:05,  1.07s/it, lr: 1.0e-04 loss: 3.719e-01]
latex_v1:  55%|#####4    | 1644/3000 [38:20<24:05,  1.07s/it, lr: 1.0e-04 loss: 4.659e-01]
latex_v1:  55%|#####4    | 1644/3000 [38:20<24:05,  1.07s/it, lr: 1.0e-04 loss: 4.659e-01]
latex_v1:  55%|#####4    | 1645/3000 [38:20<35:26,  1.57s/it, lr: 1.0e-04 loss: 4.659e-01]
latex_v1:  55%|#####4    | 1645/3000 [38:20<35:26,  1.57s/it, lr: 1.0e-04 loss: 4.659e-01]
latex_v1:  55%|#####4    | 1645/3000 [38:22<35:26,  1.57s/it, lr: 1.0e-04 loss: 3.990e-02]
latex_v1:  55%|#####4    | 1645/3000 [38:22<35:26,  1.57s/it, lr: 1.0e-04 loss: 3.990e-02]
latex_v1:  55%|#####4    | 1646/3000 [38:22<36:31,  1.62s/it, lr: 1.0e-04 loss: 3.990e-02]
latex_v1:  55%|#####4    | 1646/3000 [38:22<36:31,  1.62s/it, lr: 1.0e-04 loss: 3.990e-02]
latex_v1:  55%|#####4    | 1646/3000 [38:24<36:31,  1.62s/it, lr: 1.0e-04 loss: 5.565e-01]
latex_v1:  55%|#####4    | 1646/3000 [38:24<36:31,  1.62s/it, lr: 1.0e-04 loss: 5.565e-01]
latex_v1:  55%|#####4    | 1647/3000 [38:24<36:00,  1.60s/it, lr: 1.0e-04 loss: 5.565e-01]
latex_v1:  55%|#####4    | 1647/3000 [38:24<36:00,  1.60s/it, lr: 1.0e-04 loss: 5.565e-01]
latex_v1:  55%|#####4    | 1647/3000 [38:25<36:00,  1.60s/it, lr: 1.0e-04 loss: 8.421e-02]
latex_v1:  55%|#####4    | 1647/3000 [38:25<36:00,  1.60s/it, lr: 1.0e-04 loss: 8.421e-02]
latex_v1:  55%|#####4    | 1648/3000 [38:25<35:33,  1.58s/it, lr: 1.0e-04 loss: 8.421e-02]
latex_v1:  55%|#####4    | 1648/3000 [38:25<35:33,  1.58s/it, lr: 1.0e-04 loss: 8.421e-02]
latex_v1:  55%|#####4    | 1648/3000 [38:28<35:33,  1.58s/it, lr: 1.0e-04 loss: 1.577e-01]
latex_v1:  55%|#####4    | 1648/3000 [38:28<35:33,  1.58s/it, lr: 1.0e-04 loss: 1.577e-01]
latex_v1:  55%|#####4    | 1649/3000 [38:28<44:06,  1.96s/it, lr: 1.0e-04 loss: 1.577e-01]
latex_v1:  55%|#####4    | 1649/3000 [38:28<44:06,  1.96s/it, lr: 1.0e-04 loss: 1.577e-01]
latex_v1:  55%|#####4    | 1649/3000 [38:29<44:06,  1.96s/it, lr: 1.0e-04 loss: 1.206e-01]
latex_v1:  55%|#####4    | 1649/3000 [38:29<44:06,  1.96s/it, lr: 1.0e-04 loss: 1.206e-01]
latex_v1:  55%|#####5    | 1650/3000 [38:30<44:05,  1.96s/it, lr: 1.0e-04 loss: 1.290e-01]
latex_v1:  55%|#####5    | 1650/3000 [38:30<44:05,  1.96s/it, lr: 1.0e-04 loss: 1.290e-01]
latex_v1:  55%|#####5    | 1651/3000 [38:30<27:47,  1.24s/it, lr: 1.0e-04 loss: 1.290e-01]
latex_v1:  55%|#####5    | 1651/3000 [38:30<27:47,  1.24s/it, lr: 1.0e-04 loss: 1.290e-01]
latex_v1:  55%|#####5    | 1651/3000 [38:32<27:47,  1.24s/it, lr: 1.0e-04 loss: 2.966e-01]
latex_v1:  55%|#####5    | 1651/3000 [38:32<27:47,  1.24s/it, lr: 1.0e-04 loss: 2.966e-01]
latex_v1:  55%|#####5    | 1652/3000 [38:32<32:17,  1.44s/it, lr: 1.0e-04 loss: 2.966e-01]
latex_v1:  55%|#####5    | 1652/3000 [38:32<32:17,  1.44s/it, lr: 1.0e-04 loss: 2.966e-01]
latex_v1:  55%|#####5    | 1652/3000 [38:32<32:17,  1.44s/it, lr: 1.0e-04 loss: 2.207e-01]
latex_v1:  55%|#####5    | 1652/3000 [38:32<32:17,  1.44s/it, lr: 1.0e-04 loss: 2.207e-01]
latex_v1:  55%|#####5    | 1653/3000 [38:32<28:16,  1.26s/it, lr: 1.0e-04 loss: 2.207e-01]
latex_v1:  55%|#####5    | 1653/3000 [38:32<28:16,  1.26s/it, lr: 1.0e-04 loss: 2.207e-01]
latex_v1:  55%|#####5    | 1653/3000 [38:33<28:16,  1.26s/it, lr: 1.0e-04 loss: 2.679e-01]
latex_v1:  55%|#####5    | 1653/3000 [38:33<28:16,  1.26s/it, lr: 1.0e-04 loss: 2.679e-01]
latex_v1:  55%|#####5    | 1654/3000 [38:33<25:17,  1.13s/it, lr: 1.0e-04 loss: 2.679e-01]
latex_v1:  55%|#####5    | 1654/3000 [38:33<25:17,  1.13s/it, lr: 1.0e-04 loss: 2.679e-01]
latex_v1:  55%|#####5    | 1654/3000 [38:36<25:17,  1.13s/it, lr: 1.0e-04 loss: 6.022e-01]
latex_v1:  55%|#####5    | 1654/3000 [38:36<25:17,  1.13s/it, lr: 1.0e-04 loss: 6.022e-01]
latex_v1:  55%|#####5    | 1655/3000 [38:36<34:45,  1.55s/it, lr: 1.0e-04 loss: 6.022e-01]
latex_v1:  55%|#####5    | 1655/3000 [38:36<34:45,  1.55s/it, lr: 1.0e-04 loss: 6.022e-01]
latex_v1:  55%|#####5    | 1655/3000 [38:38<34:45,  1.55s/it, lr: 1.0e-04 loss: 5.913e-01]
latex_v1:  55%|#####5    | 1655/3000 [38:38<34:45,  1.55s/it, lr: 1.0e-04 loss: 5.913e-01]
latex_v1:  55%|#####5    | 1656/3000 [38:38<36:50,  1.64s/it, lr: 1.0e-04 loss: 5.913e-01]
latex_v1:  55%|#####5    | 1656/3000 [38:38<36:50,  1.64s/it, lr: 1.0e-04 loss: 5.913e-01]
latex_v1:  55%|#####5    | 1656/3000 [38:39<36:50,  1.64s/it, lr: 1.0e-04 loss: 6.957e-01]
latex_v1:  55%|#####5    | 1656/3000 [38:39<36:50,  1.64s/it, lr: 1.0e-04 loss: 6.957e-01]
latex_v1:  55%|#####5    | 1657/3000 [38:39<35:04,  1.57s/it, lr: 1.0e-04 loss: 6.957e-01]
latex_v1:  55%|#####5    | 1657/3000 [38:39<35:04,  1.57s/it, lr: 1.0e-04 loss: 6.957e-01]
latex_v1:  55%|#####5    | 1657/3000 [38:40<35:04,  1.57s/it, lr: 1.0e-04 loss: 1.107e-01]
latex_v1:  55%|#####5    | 1657/3000 [38:40<35:04,  1.57s/it, lr: 1.0e-04 loss: 1.107e-01]
latex_v1:  55%|#####5    | 1658/3000 [38:40<29:39,  1.33s/it, lr: 1.0e-04 loss: 1.107e-01]
latex_v1:  55%|#####5    | 1658/3000 [38:40<29:39,  1.33s/it, lr: 1.0e-04 loss: 1.107e-01]
latex_v1:  55%|#####5    | 1658/3000 [38:41<29:39,  1.33s/it, lr: 1.0e-04 loss: 1.791e-01]
latex_v1:  55%|#####5    | 1658/3000 [38:41<29:39,  1.33s/it, lr: 1.0e-04 loss: 1.791e-01]
latex_v1:  55%|#####5    | 1659/3000 [38:41<25:52,  1.16s/it, lr: 1.0e-04 loss: 1.791e-01]
latex_v1:  55%|#####5    | 1659/3000 [38:41<25:52,  1.16s/it, lr: 1.0e-04 loss: 1.791e-01]
latex_v1:  55%|#####5    | 1659/3000 [38:42<25:52,  1.16s/it, lr: 1.0e-04 loss: 1.896e-01]
latex_v1:  55%|#####5    | 1659/3000 [38:42<25:52,  1.16s/it, lr: 1.0e-04 loss: 1.896e-01]
latex_v1:  55%|#####5    | 1660/3000 [38:45<25:51,  1.16s/it, lr: 1.0e-04 loss: 2.117e-01]
latex_v1:  55%|#####5    | 1660/3000 [38:45<25:51,  1.16s/it, lr: 1.0e-04 loss: 2.117e-01]
latex_v1:  55%|#####5    | 1661/3000 [38:45<28:31,  1.28s/it, lr: 1.0e-04 loss: 2.117e-01]
latex_v1:  55%|#####5    | 1661/3000 [38:45<28:31,  1.28s/it, lr: 1.0e-04 loss: 2.117e-01]
latex_v1:  55%|#####5    | 1661/3000 [38:46<28:31,  1.28s/it, lr: 1.0e-04 loss: 5.960e-01]
latex_v1:  55%|#####5    | 1661/3000 [38:46<28:31,  1.28s/it, lr: 1.0e-04 loss: 5.960e-01]
latex_v1:  55%|#####5    | 1662/3000 [38:46<25:35,  1.15s/it, lr: 1.0e-04 loss: 5.960e-01]
latex_v1:  55%|#####5    | 1662/3000 [38:46<25:35,  1.15s/it, lr: 1.0e-04 loss: 5.960e-01]
latex_v1:  55%|#####5    | 1662/3000 [38:48<25:35,  1.15s/it, lr: 1.0e-04 loss: 5.264e-02]
latex_v1:  55%|#####5    | 1662/3000 [38:48<25:35,  1.15s/it, lr: 1.0e-04 loss: 5.264e-02]
latex_v1:  55%|#####5    | 1663/3000 [38:48<29:47,  1.34s/it, lr: 1.0e-04 loss: 5.264e-02]
latex_v1:  55%|#####5    | 1663/3000 [38:48<29:47,  1.34s/it, lr: 1.0e-04 loss: 5.264e-02]
latex_v1:  55%|#####5    | 1663/3000 [38:48<29:47,  1.34s/it, lr: 1.0e-04 loss: 5.169e-01]
latex_v1:  55%|#####5    | 1663/3000 [38:48<29:47,  1.34s/it, lr: 1.0e-04 loss: 5.169e-01]
latex_v1:  55%|#####5    | 1664/3000 [38:48<26:24,  1.19s/it, lr: 1.0e-04 loss: 5.169e-01]
latex_v1:  55%|#####5    | 1664/3000 [38:48<26:24,  1.19s/it, lr: 1.0e-04 loss: 5.169e-01]
latex_v1:  55%|#####5    | 1664/3000 [38:50<26:24,  1.19s/it, lr: 1.0e-04 loss: 4.394e-01]
latex_v1:  55%|#####5    | 1664/3000 [38:50<26:24,  1.19s/it, lr: 1.0e-04 loss: 4.394e-01]
latex_v1:  56%|#####5    | 1665/3000 [38:50<27:55,  1.25s/it, lr: 1.0e-04 loss: 4.394e-01]
latex_v1:  56%|#####5    | 1665/3000 [38:50<27:55,  1.25s/it, lr: 1.0e-04 loss: 4.394e-01]
latex_v1:  56%|#####5    | 1665/3000 [38:51<27:55,  1.25s/it, lr: 1.0e-04 loss: 5.720e-01]
latex_v1:  56%|#####5    | 1665/3000 [38:51<27:55,  1.25s/it, lr: 1.0e-04 loss: 5.720e-01]
latex_v1:  56%|#####5    | 1666/3000 [38:51<24:45,  1.11s/it, lr: 1.0e-04 loss: 5.720e-01]
latex_v1:  56%|#####5    | 1666/3000 [38:51<24:45,  1.11s/it, lr: 1.0e-04 loss: 5.720e-01]
latex_v1:  56%|#####5    | 1666/3000 [38:51<24:45,  1.11s/it, lr: 1.0e-04 loss: 1.416e-01]
latex_v1:  56%|#####5    | 1666/3000 [38:51<24:45,  1.11s/it, lr: 1.0e-04 loss: 1.416e-01]
latex_v1:  56%|#####5    | 1667/3000 [38:51<22:26,  1.01s/it, lr: 1.0e-04 loss: 1.416e-01]
latex_v1:  56%|#####5    | 1667/3000 [38:51<22:26,  1.01s/it, lr: 1.0e-04 loss: 1.416e-01]
latex_v1:  56%|#####5    | 1667/3000 [38:53<22:26,  1.01s/it, lr: 1.0e-04 loss: 4.036e-01]
latex_v1:  56%|#####5    | 1667/3000 [38:53<22:26,  1.01s/it, lr: 1.0e-04 loss: 4.036e-01]
latex_v1:  56%|#####5    | 1668/3000 [38:53<25:56,  1.17s/it, lr: 1.0e-04 loss: 4.036e-01]
latex_v1:  56%|#####5    | 1668/3000 [38:53<25:56,  1.17s/it, lr: 1.0e-04 loss: 4.036e-01]
latex_v1:  56%|#####5    | 1668/3000 [38:54<25:56,  1.17s/it, lr: 1.0e-04 loss: 6.557e-02]
latex_v1:  56%|#####5    | 1668/3000 [38:54<25:56,  1.17s/it, lr: 1.0e-04 loss: 6.557e-02]
latex_v1:  56%|#####5    | 1669/3000 [38:54<27:34,  1.24s/it, lr: 1.0e-04 loss: 6.557e-02]
latex_v1:  56%|#####5    | 1669/3000 [38:54<27:34,  1.24s/it, lr: 1.0e-04 loss: 6.557e-02]
latex_v1:  56%|#####5    | 1669/3000 [38:56<27:34,  1.24s/it, lr: 1.0e-04 loss: 7.045e-01]
latex_v1:  56%|#####5    | 1669/3000 [38:56<27:34,  1.24s/it, lr: 1.0e-04 loss: 7.045e-01]
latex_v1:  56%|#####5    | 1670/3000 [38:57<27:33,  1.24s/it, lr: 1.0e-04 loss: 0.000e+00]
latex_v1:  56%|#####5    | 1670/3000 [38:57<27:33,  1.24s/it, lr: 1.0e-04 loss: 0.000e+00]
latex_v1:  56%|#####5    | 1671/3000 [38:57<22:43,  1.03s/it, lr: 1.0e-04 loss: 0.000e+00]
latex_v1:  56%|#####5    | 1671/3000 [38:57<22:43,  1.03s/it, lr: 1.0e-04 loss: 0.000e+00]
latex_v1:  56%|#####5    | 1671/3000 [38:59<22:43,  1.03s/it, lr: 1.0e-04 loss: 5.716e-01]
latex_v1:  56%|#####5    | 1671/3000 [38:59<22:43,  1.03s/it, lr: 1.0e-04 loss: 5.716e-01]
latex_v1:  56%|#####5    | 1672/3000 [38:59<27:21,  1.24s/it, lr: 1.0e-04 loss: 5.716e-01]
latex_v1:  56%|#####5    | 1672/3000 [38:59<27:21,  1.24s/it, lr: 1.0e-04 loss: 5.716e-01]
latex_v1:  56%|#####5    | 1672/3000 [39:01<27:21,  1.24s/it, lr: 1.0e-04 loss: 6.056e-01]
latex_v1:  56%|#####5    | 1672/3000 [39:01<27:21,  1.24s/it, lr: 1.0e-04 loss: 6.056e-01]
latex_v1:  56%|#####5    | 1673/3000 [39:01<31:31,  1.43s/it, lr: 1.0e-04 loss: 6.056e-01]
latex_v1:  56%|#####5    | 1673/3000 [39:01<31:31,  1.43s/it, lr: 1.0e-04 loss: 6.056e-01]
latex_v1:  56%|#####5    | 1673/3000 [39:02<31:31,  1.43s/it, lr: 1.0e-04 loss: 2.559e-01]
latex_v1:  56%|#####5    | 1673/3000 [39:02<31:31,  1.43s/it, lr: 1.0e-04 loss: 2.559e-01]
latex_v1:  56%|#####5    | 1674/3000 [39:02<27:50,  1.26s/it, lr: 1.0e-04 loss: 2.559e-01]
latex_v1:  56%|#####5    | 1674/3000 [39:02<27:50,  1.26s/it, lr: 1.0e-04 loss: 2.559e-01]
latex_v1:  56%|#####5    | 1674/3000 [39:03<27:50,  1.26s/it, lr: 1.0e-04 loss: 2.089e-01]
latex_v1:  56%|#####5    | 1674/3000 [39:03<27:50,  1.26s/it, lr: 1.0e-04 loss: 2.089e-01]
latex_v1:  56%|#####5    | 1675/3000 [39:03<24:43,  1.12s/it, lr: 1.0e-04 loss: 2.089e-01]
latex_v1:  56%|#####5    | 1675/3000 [39:03<24:43,  1.12s/it, lr: 1.0e-04 loss: 2.089e-01]
latex_v1:  56%|#####5    | 1675/3000 [39:05<24:43,  1.12s/it, lr: 1.0e-04 loss: 1.689e-01]
latex_v1:  56%|#####5    | 1675/3000 [39:05<24:43,  1.12s/it, lr: 1.0e-04 loss: 1.689e-01]
latex_v1:  56%|#####5    | 1676/3000 [39:05<28:31,  1.29s/it, lr: 1.0e-04 loss: 1.689e-01]
latex_v1:  56%|#####5    | 1676/3000 [39:05<28:31,  1.29s/it, lr: 1.0e-04 loss: 1.689e-01]
latex_v1:  56%|#####5    | 1676/3000 [39:07<28:31,  1.29s/it, lr: 1.0e-04 loss: 2.113e-01]
latex_v1:  56%|#####5    | 1676/3000 [39:07<28:31,  1.29s/it, lr: 1.0e-04 loss: 2.113e-01]
latex_v1:  56%|#####5    | 1677/3000 [39:07<34:14,  1.55s/it, lr: 1.0e-04 loss: 2.113e-01]
latex_v1:  56%|#####5    | 1677/3000 [39:07<34:14,  1.55s/it, lr: 1.0e-04 loss: 2.113e-01]
latex_v1:  56%|#####5    | 1677/3000 [39:08<34:14,  1.55s/it, lr: 1.0e-04 loss: 1.059e-01]
latex_v1:  56%|#####5    | 1677/3000 [39:08<34:14,  1.55s/it, lr: 1.0e-04 loss: 1.059e-01]
latex_v1:  56%|#####5    | 1678/3000 [39:08<34:17,  1.56s/it, lr: 1.0e-04 loss: 1.059e-01]
latex_v1:  56%|#####5    | 1678/3000 [39:08<34:17,  1.56s/it, lr: 1.0e-04 loss: 1.059e-01]
latex_v1:  56%|#####5    | 1678/3000 [39:09<34:17,  1.56s/it, lr: 1.0e-04 loss: 3.824e-01]
latex_v1:  56%|#####5    | 1678/3000 [39:09<34:17,  1.56s/it, lr: 1.0e-04 loss: 3.824e-01]
latex_v1:  56%|#####5    | 1679/3000 [39:10<31:02,  1.41s/it, lr: 1.0e-04 loss: 3.824e-01]
latex_v1:  56%|#####5    | 1679/3000 [39:10<31:02,  1.41s/it, lr: 1.0e-04 loss: 3.824e-01]
latex_v1:  56%|#####5    | 1679/3000 [39:10<31:02,  1.41s/it, lr: 1.0e-04 loss: 4.481e-01]
latex_v1:  56%|#####5    | 1679/3000 [39:10<31:02,  1.41s/it, lr: 1.0e-04 loss: 4.481e-01]
latex_v1:  56%|#####6    | 1680/3000 [39:11<31:00,  1.41s/it, lr: 1.0e-04 loss: 2.205e-01]
latex_v1:  56%|#####6    | 1680/3000 [39:11<31:00,  1.41s/it, lr: 1.0e-04 loss: 2.205e-01]
latex_v1:  56%|#####6    | 1681/3000 [39:11<20:39,  1.06it/s, lr: 1.0e-04 loss: 2.205e-01]
latex_v1:  56%|#####6    | 1681/3000 [39:11<20:39,  1.06it/s, lr: 1.0e-04 loss: 2.205e-01]
latex_v1:  56%|#####6    | 1681/3000 [39:12<20:39,  1.06it/s, lr: 1.0e-04 loss: 6.569e-01]
latex_v1:  56%|#####6    | 1681/3000 [39:12<20:39,  1.06it/s, lr: 1.0e-04 loss: 6.569e-01]
latex_v1:  56%|#####6    | 1682/3000 [39:12<21:55,  1.00it/s, lr: 1.0e-04 loss: 6.569e-01]
latex_v1:  56%|#####6    | 1682/3000 [39:12<21:55,  1.00it/s, lr: 1.0e-04 loss: 6.569e-01]
latex_v1:  56%|#####6    | 1682/3000 [39:14<21:55,  1.00it/s, lr: 1.0e-04 loss: 3.929e-01]
latex_v1:  56%|#####6    | 1682/3000 [39:14<21:55,  1.00it/s, lr: 1.0e-04 loss: 3.929e-01]
latex_v1:  56%|#####6    | 1683/3000 [39:14<25:03,  1.14s/it, lr: 1.0e-04 loss: 3.929e-01]
latex_v1:  56%|#####6    | 1683/3000 [39:14<25:03,  1.14s/it, lr: 1.0e-04 loss: 3.929e-01]
latex_v1:  56%|#####6    | 1683/3000 [39:15<25:03,  1.14s/it, lr: 1.0e-04 loss: 1.689e-01]
latex_v1:  56%|#####6    | 1683/3000 [39:15<25:03,  1.14s/it, lr: 1.0e-04 loss: 1.689e-01]
latex_v1:  56%|#####6    | 1684/3000 [39:15<23:57,  1.09s/it, lr: 1.0e-04 loss: 1.689e-01]
latex_v1:  56%|#####6    | 1684/3000 [39:15<23:57,  1.09s/it, lr: 1.0e-04 loss: 1.689e-01]
latex_v1:  56%|#####6    | 1684/3000 [39:15<23:57,  1.09s/it, lr: 1.0e-04 loss: 4.862e-01]
latex_v1:  56%|#####6    | 1684/3000 [39:15<23:57,  1.09s/it, lr: 1.0e-04 loss: 4.862e-01]
latex_v1:  56%|#####6    | 1685/3000 [39:15<21:53,  1.00it/s, lr: 1.0e-04 loss: 4.862e-01]
latex_v1:  56%|#####6    | 1685/3000 [39:15<21:53,  1.00it/s, lr: 1.0e-04 loss: 4.862e-01]
latex_v1:  56%|#####6    | 1685/3000 [39:17<21:53,  1.00it/s, lr: 1.0e-04 loss: 6.085e-01]
latex_v1:  56%|#####6    | 1685/3000 [39:17<21:53,  1.00it/s, lr: 1.0e-04 loss: 6.085e-01]
latex_v1:  56%|#####6    | 1686/3000 [39:17<27:57,  1.28s/it, lr: 1.0e-04 loss: 6.085e-01]
latex_v1:  56%|#####6    | 1686/3000 [39:17<27:57,  1.28s/it, lr: 1.0e-04 loss: 6.085e-01]
latex_v1:  56%|#####6    | 1686/3000 [39:19<27:57,  1.28s/it, lr: 1.0e-04 loss: 4.217e-01]
latex_v1:  56%|#####6    | 1686/3000 [39:19<27:57,  1.28s/it, lr: 1.0e-04 loss: 4.217e-01]
latex_v1:  56%|#####6    | 1687/3000 [39:19<28:53,  1.32s/it, lr: 1.0e-04 loss: 4.217e-01]
latex_v1:  56%|#####6    | 1687/3000 [39:19<28:53,  1.32s/it, lr: 1.0e-04 loss: 4.217e-01]
latex_v1:  56%|#####6    | 1687/3000 [39:20<28:53,  1.32s/it, lr: 1.0e-04 loss: 9.949e-02]
latex_v1:  56%|#####6    | 1687/3000 [39:20<28:53,  1.32s/it, lr: 1.0e-04 loss: 9.949e-02]
latex_v1:  56%|#####6    | 1688/3000 [39:20<30:09,  1.38s/it, lr: 1.0e-04 loss: 9.949e-02]
latex_v1:  56%|#####6    | 1688/3000 [39:20<30:09,  1.38s/it, lr: 1.0e-04 loss: 9.949e-02]
latex_v1:  56%|#####6    | 1688/3000 [39:21<30:09,  1.38s/it, lr: 1.0e-04 loss: 8.172e-02]
latex_v1:  56%|#####6    | 1688/3000 [39:21<30:09,  1.38s/it, lr: 1.0e-04 loss: 8.172e-02]
latex_v1:  56%|#####6    | 1689/3000 [39:21<26:04,  1.19s/it, lr: 1.0e-04 loss: 8.172e-02]
latex_v1:  56%|#####6    | 1689/3000 [39:21<26:04,  1.19s/it, lr: 1.0e-04 loss: 8.172e-02]
latex_v1:  56%|#####6    | 1689/3000 [39:23<26:04,  1.19s/it, lr: 1.0e-04 loss: 5.271e-01]
latex_v1:  56%|#####6    | 1689/3000 [39:23<26:04,  1.19s/it, lr: 1.0e-04 loss: 5.271e-01]
latex_v1:  56%|#####6    | 1690/3000 [39:23<26:02,  1.19s/it, lr: 1.0e-04 loss: 2.666e-01]
latex_v1:  56%|#####6    | 1690/3000 [39:23<26:02,  1.19s/it, lr: 1.0e-04 loss: 2.666e-01]
latex_v1:  56%|#####6    | 1691/3000 [39:23<17:59,  1.21it/s, lr: 1.0e-04 loss: 2.666e-01]
latex_v1:  56%|#####6    | 1691/3000 [39:23<17:59,  1.21it/s, lr: 1.0e-04 loss: 2.666e-01]
latex_v1:  56%|#####6    | 1691/3000 [39:25<17:59,  1.21it/s, lr: 1.0e-04 loss: 2.139e-01]
latex_v1:  56%|#####6    | 1691/3000 [39:25<17:59,  1.21it/s, lr: 1.0e-04 loss: 2.139e-01]
latex_v1:  56%|#####6    | 1692/3000 [39:25<20:51,  1.04it/s, lr: 1.0e-04 loss: 2.139e-01]
latex_v1:  56%|#####6    | 1692/3000 [39:25<20:51,  1.04it/s, lr: 1.0e-04 loss: 2.139e-01]
latex_v1:  56%|#####6    | 1692/3000 [39:26<20:51,  1.04it/s, lr: 1.0e-04 loss: 6.043e-01]
latex_v1:  56%|#####6    | 1692/3000 [39:26<20:51,  1.04it/s, lr: 1.0e-04 loss: 6.043e-01]
latex_v1:  56%|#####6    | 1693/3000 [39:26<21:02,  1.04it/s, lr: 1.0e-04 loss: 6.043e-01]
latex_v1:  56%|#####6    | 1693/3000 [39:26<21:02,  1.04it/s, lr: 1.0e-04 loss: 6.043e-01]
latex_v1:  56%|#####6    | 1693/3000 [39:28<21:02,  1.04it/s, lr: 1.0e-04 loss: 4.470e-01]
latex_v1:  56%|#####6    | 1693/3000 [39:28<21:02,  1.04it/s, lr: 1.0e-04 loss: 4.470e-01]
latex_v1:  56%|#####6    | 1694/3000 [39:28<26:20,  1.21s/it, lr: 1.0e-04 loss: 4.470e-01]
latex_v1:  56%|#####6    | 1694/3000 [39:28<26:20,  1.21s/it, lr: 1.0e-04 loss: 4.470e-01]
latex_v1:  56%|#####6    | 1694/3000 [39:29<26:20,  1.21s/it, lr: 1.0e-04 loss: 4.291e-01]
latex_v1:  56%|#####6    | 1694/3000 [39:29<26:20,  1.21s/it, lr: 1.0e-04 loss: 4.291e-01]
latex_v1:  56%|#####6    | 1695/3000 [39:29<28:18,  1.30s/it, lr: 1.0e-04 loss: 4.291e-01]
latex_v1:  56%|#####6    | 1695/3000 [39:29<28:18,  1.30s/it, lr: 1.0e-04 loss: 4.291e-01]
latex_v1:  56%|#####6    | 1695/3000 [39:31<28:18,  1.30s/it, lr: 1.0e-04 loss: 1.577e-01]
latex_v1:  56%|#####6    | 1695/3000 [39:31<28:18,  1.30s/it, lr: 1.0e-04 loss: 1.577e-01]
latex_v1:  57%|#####6    | 1696/3000 [39:31<29:39,  1.36s/it, lr: 1.0e-04 loss: 1.577e-01]
latex_v1:  57%|#####6    | 1696/3000 [39:31<29:39,  1.36s/it, lr: 1.0e-04 loss: 1.577e-01]
latex_v1:  57%|#####6    | 1696/3000 [39:33<29:39,  1.36s/it, lr: 1.0e-04 loss: 3.533e-01]
latex_v1:  57%|#####6    | 1696/3000 [39:33<29:39,  1.36s/it, lr: 1.0e-04 loss: 3.533e-01]
latex_v1:  57%|#####6    | 1697/3000 [39:33<38:03,  1.75s/it, lr: 1.0e-04 loss: 3.533e-01]
latex_v1:  57%|#####6    | 1697/3000 [39:33<38:03,  1.75s/it, lr: 1.0e-04 loss: 3.533e-01]
latex_v1:  57%|#####6    | 1697/3000 [39:34<38:03,  1.75s/it, lr: 1.0e-04 loss: 6.157e-01]
latex_v1:  57%|#####6    | 1697/3000 [39:34<38:03,  1.75s/it, lr: 1.0e-04 loss: 6.157e-01]
latex_v1:  57%|#####6    | 1698/3000 [39:34<31:29,  1.45s/it, lr: 1.0e-04 loss: 6.157e-01]
latex_v1:  57%|#####6    | 1698/3000 [39:34<31:29,  1.45s/it, lr: 1.0e-04 loss: 6.157e-01]
latex_v1:  57%|#####6    | 1698/3000 [39:35<31:29,  1.45s/it, lr: 1.0e-04 loss: 4.653e-01]
latex_v1:  57%|#####6    | 1698/3000 [39:35<31:29,  1.45s/it, lr: 1.0e-04 loss: 4.653e-01]
latex_v1:  57%|#####6    | 1699/3000 [39:35<29:36,  1.37s/it, lr: 1.0e-04 loss: 4.653e-01]
latex_v1:  57%|#####6    | 1699/3000 [39:35<29:36,  1.37s/it, lr: 1.0e-04 loss: 4.653e-01]
latex_v1:  57%|#####6    | 1699/3000 [39:37<29:36,  1.37s/it, lr: 1.0e-04 loss: 6.743e-01]
latex_v1:  57%|#####6    | 1699/3000 [39:37<29:36,  1.37s/it, lr: 1.0e-04 loss: 6.743e-01]
latex_v1:  57%|#####6    | 1700/3000 [39:38<29:34,  1.37s/it, lr: 1.0e-04 loss: 2.840e-01]
latex_v1:  57%|#####6    | 1700/3000 [39:38<29:34,  1.37s/it, lr: 1.0e-04 loss: 2.840e-01]
latex_v1:  57%|#####6    | 1701/3000 [39:38<23:40,  1.09s/it, lr: 1.0e-04 loss: 2.840e-01]
latex_v1:  57%|#####6    | 1701/3000 [39:38<23:40,  1.09s/it, lr: 1.0e-04 loss: 2.840e-01]
latex_v1:  57%|#####6    | 1701/3000 [39:39<23:40,  1.09s/it, lr: 1.0e-04 loss: 2.418e-01]
latex_v1:  57%|#####6    | 1701/3000 [39:39<23:40,  1.09s/it, lr: 1.0e-04 loss: 2.418e-01]
latex_v1:  57%|#####6    | 1702/3000 [39:39<21:43,  1.00s/it, lr: 1.0e-04 loss: 2.418e-01]
latex_v1:  57%|#####6    | 1702/3000 [39:39<21:43,  1.00s/it, lr: 1.0e-04 loss: 2.418e-01]
latex_v1:  57%|#####6    | 1702/3000 [39:40<21:43,  1.00s/it, lr: 1.0e-04 loss: 5.667e-01]
latex_v1:  57%|#####6    | 1702/3000 [39:40<21:43,  1.00s/it, lr: 1.0e-04 loss: 5.667e-01]
latex_v1:  57%|#####6    | 1703/3000 [39:40<24:41,  1.14s/it, lr: 1.0e-04 loss: 5.667e-01]
latex_v1:  57%|#####6    | 1703/3000 [39:40<24:41,  1.14s/it, lr: 1.0e-04 loss: 5.667e-01]
latex_v1:  57%|#####6    | 1703/3000 [39:43<24:41,  1.14s/it, lr: 1.0e-04 loss: 1.336e-01]
latex_v1:  57%|#####6    | 1703/3000 [39:43<24:41,  1.14s/it, lr: 1.0e-04 loss: 1.336e-01]
latex_v1:  57%|#####6    | 1704/3000 [39:43<34:41,  1.61s/it, lr: 1.0e-04 loss: 1.336e-01]
latex_v1:  57%|#####6    | 1704/3000 [39:43<34:41,  1.61s/it, lr: 1.0e-04 loss: 1.336e-01]
latex_v1:  57%|#####6    | 1704/3000 [39:46<34:41,  1.61s/it, lr: 1.0e-04 loss: 2.438e-01]
latex_v1:  57%|#####6    | 1704/3000 [39:46<34:41,  1.61s/it, lr: 1.0e-04 loss: 2.438e-01]
latex_v1:  57%|#####6    | 1705/3000 [39:46<42:14,  1.96s/it, lr: 1.0e-04 loss: 2.438e-01]
latex_v1:  57%|#####6    | 1705/3000 [39:46<42:14,  1.96s/it, lr: 1.0e-04 loss: 2.438e-01]
latex_v1:  57%|#####6    | 1705/3000 [39:47<42:14,  1.96s/it, lr: 1.0e-04 loss: 1.160e-01]
latex_v1:  57%|#####6    | 1705/3000 [39:47<42:14,  1.96s/it, lr: 1.0e-04 loss: 1.160e-01]
latex_v1:  57%|#####6    | 1706/3000 [39:47<34:45,  1.61s/it, lr: 1.0e-04 loss: 1.160e-01]
latex_v1:  57%|#####6    | 1706/3000 [39:47<34:45,  1.61s/it, lr: 1.0e-04 loss: 1.160e-01]
latex_v1:  57%|#####6    | 1706/3000 [39:48<34:45,  1.61s/it, lr: 1.0e-04 loss: 4.035e-01]
latex_v1:  57%|#####6    | 1706/3000 [39:48<34:45,  1.61s/it, lr: 1.0e-04 loss: 4.035e-01]
latex_v1:  57%|#####6    | 1707/3000 [39:48<32:37,  1.51s/it, lr: 1.0e-04 loss: 4.035e-01]
latex_v1:  57%|#####6    | 1707/3000 [39:48<32:37,  1.51s/it, lr: 1.0e-04 loss: 4.035e-01]
latex_v1:  57%|#####6    | 1707/3000 [39:50<32:37,  1.51s/it, lr: 1.0e-04 loss: 1.772e-01]
latex_v1:  57%|#####6    | 1707/3000 [39:50<32:37,  1.51s/it, lr: 1.0e-04 loss: 1.772e-01]
latex_v1:  57%|#####6    | 1708/3000 [39:50<34:58,  1.62s/it, lr: 1.0e-04 loss: 1.772e-01]
latex_v1:  57%|#####6    | 1708/3000 [39:50<34:58,  1.62s/it, lr: 1.0e-04 loss: 1.772e-01]
latex_v1:  57%|#####6    | 1708/3000 [39:51<34:58,  1.62s/it, lr: 1.0e-04 loss: 3.620e-01]
latex_v1:  57%|#####6    | 1708/3000 [39:51<34:58,  1.62s/it, lr: 1.0e-04 loss: 3.620e-01]
latex_v1:  57%|#####6    | 1709/3000 [39:51<33:52,  1.57s/it, lr: 1.0e-04 loss: 3.620e-01]
latex_v1:  57%|#####6    | 1709/3000 [39:51<33:52,  1.57s/it, lr: 1.0e-04 loss: 3.620e-01]
latex_v1:  57%|#####6    | 1709/3000 [39:53<33:52,  1.57s/it, lr: 1.0e-04 loss: 3.961e-01]
latex_v1:  57%|#####6    | 1709/3000 [39:53<33:52,  1.57s/it, lr: 1.0e-04 loss: 3.961e-01]
latex_v1:  57%|#####6    | 1710/3000 [39:54<33:50,  1.57s/it, lr: 1.0e-04 loss: 2.192e-01]
latex_v1:  57%|#####6    | 1710/3000 [39:54<33:50,  1.57s/it, lr: 1.0e-04 loss: 2.192e-01]
latex_v1:  57%|#####7    | 1711/3000 [39:54<25:56,  1.21s/it, lr: 1.0e-04 loss: 2.192e-01]
latex_v1:  57%|#####7    | 1711/3000 [39:54<25:56,  1.21s/it, lr: 1.0e-04 loss: 2.192e-01]
latex_v1:  57%|#####7    | 1711/3000 [39:56<25:56,  1.21s/it, lr: 1.0e-04 loss: 4.112e-01]
latex_v1:  57%|#####7    | 1711/3000 [39:56<25:56,  1.21s/it, lr: 1.0e-04 loss: 4.112e-01]
latex_v1:  57%|#####7    | 1712/3000 [39:56<27:43,  1.29s/it, lr: 1.0e-04 loss: 4.112e-01]
latex_v1:  57%|#####7    | 1712/3000 [39:56<27:43,  1.29s/it, lr: 1.0e-04 loss: 4.112e-01]
latex_v1:  57%|#####7    | 1712/3000 [39:57<27:43,  1.29s/it, lr: 1.0e-04 loss: 2.821e-02]
latex_v1:  57%|#####7    | 1712/3000 [39:57<27:43,  1.29s/it, lr: 1.0e-04 loss: 2.821e-02]
latex_v1:  57%|#####7    | 1713/3000 [39:57<24:30,  1.14s/it, lr: 1.0e-04 loss: 2.821e-02]
latex_v1:  57%|#####7    | 1713/3000 [39:57<24:30,  1.14s/it, lr: 1.0e-04 loss: 2.821e-02]
latex_v1:  57%|#####7    | 1713/3000 [39:58<24:30,  1.14s/it, lr: 1.0e-04 loss: 3.906e-01]
latex_v1:  57%|#####7    | 1713/3000 [39:58<24:30,  1.14s/it, lr: 1.0e-04 loss: 3.906e-01]
latex_v1:  57%|#####7    | 1714/3000 [39:58<25:58,  1.21s/it, lr: 1.0e-04 loss: 3.906e-01]
latex_v1:  57%|#####7    | 1714/3000 [39:58<25:58,  1.21s/it, lr: 1.0e-04 loss: 3.906e-01]
latex_v1:  57%|#####7    | 1714/3000 [40:01<25:58,  1.21s/it, lr: 1.0e-04 loss: 1.195e-01]
latex_v1:  57%|#####7    | 1714/3000 [40:01<25:58,  1.21s/it, lr: 1.0e-04 loss: 1.195e-01]
latex_v1:  57%|#####7    | 1715/3000 [40:01<35:43,  1.67s/it, lr: 1.0e-04 loss: 1.195e-01]
latex_v1:  57%|#####7    | 1715/3000 [40:01<35:43,  1.67s/it, lr: 1.0e-04 loss: 1.195e-01]
latex_v1:  57%|#####7    | 1715/3000 [40:04<35:43,  1.67s/it, lr: 1.0e-04 loss: 4.849e-01]
latex_v1:  57%|#####7    | 1715/3000 [40:04<35:43,  1.67s/it, lr: 1.0e-04 loss: 4.849e-01]
latex_v1:  57%|#####7    | 1716/3000 [40:04<42:52,  2.00s/it, lr: 1.0e-04 loss: 4.849e-01]
latex_v1:  57%|#####7    | 1716/3000 [40:04<42:52,  2.00s/it, lr: 1.0e-04 loss: 4.849e-01]
latex_v1:  57%|#####7    | 1716/3000 [40:05<42:52,  2.00s/it, lr: 1.0e-04 loss: 1.858e-01]
latex_v1:  57%|#####7    | 1716/3000 [40:05<42:52,  2.00s/it, lr: 1.0e-04 loss: 1.858e-01]
latex_v1:  57%|#####7    | 1717/3000 [40:05<39:03,  1.83s/it, lr: 1.0e-04 loss: 1.858e-01]
latex_v1:  57%|#####7    | 1717/3000 [40:05<39:03,  1.83s/it, lr: 1.0e-04 loss: 1.858e-01]
latex_v1:  57%|#####7    | 1717/3000 [40:07<39:03,  1.83s/it, lr: 1.0e-04 loss: 3.270e-02]
latex_v1:  57%|#####7    | 1717/3000 [40:07<39:03,  1.83s/it, lr: 1.0e-04 loss: 3.270e-02]
latex_v1:  57%|#####7    | 1718/3000 [40:07<37:17,  1.74s/it, lr: 1.0e-04 loss: 3.270e-02]
latex_v1:  57%|#####7    | 1718/3000 [40:07<37:17,  1.74s/it, lr: 1.0e-04 loss: 3.270e-02]
latex_v1:  57%|#####7    | 1718/3000 [40:07<37:17,  1.74s/it, lr: 1.0e-04 loss: 7.878e-01]
latex_v1:  57%|#####7    | 1718/3000 [40:07<37:17,  1.74s/it, lr: 1.0e-04 loss: 7.878e-01]
latex_v1:  57%|#####7    | 1719/3000 [40:07<30:54,  1.45s/it, lr: 1.0e-04 loss: 7.878e-01]
latex_v1:  57%|#####7    | 1719/3000 [40:07<30:54,  1.45s/it, lr: 1.0e-04 loss: 7.878e-01]
latex_v1:  57%|#####7    | 1719/3000 [40:08<30:54,  1.45s/it, lr: 1.0e-04 loss: 5.174e-01]
latex_v1:  57%|#####7    | 1719/3000 [40:08<30:54,  1.45s/it, lr: 1.0e-04 loss: 5.174e-01]
latex_v1:  57%|#####7    | 1720/3000 [40:09<30:52,  1.45s/it, lr: 1.0e-04 loss: 3.800e-01]
latex_v1:  57%|#####7    | 1720/3000 [40:09<30:52,  1.45s/it, lr: 1.0e-04 loss: 3.800e-01]
latex_v1:  57%|#####7    | 1721/3000 [40:09<20:26,  1.04it/s, lr: 1.0e-04 loss: 3.800e-01]
latex_v1:  57%|#####7    | 1721/3000 [40:09<20:26,  1.04it/s, lr: 1.0e-04 loss: 3.800e-01]
latex_v1:  57%|#####7    | 1721/3000 [40:11<20:26,  1.04it/s, lr: 1.0e-04 loss: 6.901e-01]
latex_v1:  57%|#####7    | 1721/3000 [40:11<20:26,  1.04it/s, lr: 1.0e-04 loss: 6.901e-01]
latex_v1:  57%|#####7    | 1722/3000 [40:11<22:53,  1.07s/it, lr: 1.0e-04 loss: 6.901e-01]
latex_v1:  57%|#####7    | 1722/3000 [40:11<22:53,  1.07s/it, lr: 1.0e-04 loss: 6.901e-01]
latex_v1:  57%|#####7    | 1722/3000 [40:11<22:53,  1.07s/it, lr: 1.0e-04 loss: 1.106e-01]
latex_v1:  57%|#####7    | 1722/3000 [40:11<22:53,  1.07s/it, lr: 1.0e-04 loss: 1.106e-01]
latex_v1:  57%|#####7    | 1723/3000 [40:11<21:05,  1.01it/s, lr: 1.0e-04 loss: 1.106e-01]
latex_v1:  57%|#####7    | 1723/3000 [40:11<21:05,  1.01it/s, lr: 1.0e-04 loss: 1.106e-01]
latex_v1:  57%|#####7    | 1723/3000 [40:12<21:05,  1.01it/s, lr: 1.0e-04 loss: 7.203e-01]
latex_v1:  57%|#####7    | 1723/3000 [40:12<21:05,  1.01it/s, lr: 1.0e-04 loss: 7.203e-01]
latex_v1:  57%|#####7    | 1724/3000 [40:12<19:50,  1.07it/s, lr: 1.0e-04 loss: 7.203e-01]
latex_v1:  57%|#####7    | 1724/3000 [40:12<19:50,  1.07it/s, lr: 1.0e-04 loss: 7.203e-01]
latex_v1:  57%|#####7    | 1724/3000 [40:15<19:50,  1.07it/s, lr: 1.0e-04 loss: 1.163e-01]
latex_v1:  57%|#####7    | 1724/3000 [40:15<19:50,  1.07it/s, lr: 1.0e-04 loss: 1.163e-01]
latex_v1:  57%|#####7    | 1725/3000 [40:15<31:12,  1.47s/it, lr: 1.0e-04 loss: 1.163e-01]
latex_v1:  57%|#####7    | 1725/3000 [40:15<31:12,  1.47s/it, lr: 1.0e-04 loss: 1.163e-01]
latex_v1:  57%|#####7    | 1725/3000 [40:16<31:12,  1.47s/it, lr: 1.0e-04 loss: 1.045e-01]
latex_v1:  57%|#####7    | 1725/3000 [40:16<31:12,  1.47s/it, lr: 1.0e-04 loss: 1.045e-01]
latex_v1:  58%|#####7    | 1726/3000 [40:16<26:44,  1.26s/it, lr: 1.0e-04 loss: 1.045e-01]
latex_v1:  58%|#####7    | 1726/3000 [40:16<26:44,  1.26s/it, lr: 1.0e-04 loss: 1.045e-01]
latex_v1:  58%|#####7    | 1726/3000 [40:16<26:44,  1.26s/it, lr: 1.0e-04 loss: 4.599e-01]
latex_v1:  58%|#####7    | 1726/3000 [40:16<26:44,  1.26s/it, lr: 1.0e-04 loss: 4.599e-01]
latex_v1:  58%|#####7    | 1727/3000 [40:16<23:36,  1.11s/it, lr: 1.0e-04 loss: 4.599e-01]
latex_v1:  58%|#####7    | 1727/3000 [40:16<23:36,  1.11s/it, lr: 1.0e-04 loss: 4.599e-01]
latex_v1:  58%|#####7    | 1727/3000 [40:18<23:36,  1.11s/it, lr: 1.0e-04 loss: 5.801e-01]
latex_v1:  58%|#####7    | 1727/3000 [40:18<23:36,  1.11s/it, lr: 1.0e-04 loss: 5.801e-01]
latex_v1:  58%|#####7    | 1728/3000 [40:18<25:43,  1.21s/it, lr: 1.0e-04 loss: 5.801e-01]
latex_v1:  58%|#####7    | 1728/3000 [40:18<25:43,  1.21s/it, lr: 1.0e-04 loss: 5.801e-01]
latex_v1:  58%|#####7    | 1728/3000 [40:19<25:43,  1.21s/it, lr: 1.0e-04 loss: 6.883e-01]
latex_v1:  58%|#####7    | 1728/3000 [40:19<25:43,  1.21s/it, lr: 1.0e-04 loss: 6.883e-01]
latex_v1:  58%|#####7    | 1729/3000 [40:19<25:30,  1.20s/it, lr: 1.0e-04 loss: 6.883e-01]
latex_v1:  58%|#####7    | 1729/3000 [40:19<25:30,  1.20s/it, lr: 1.0e-04 loss: 6.883e-01]
latex_v1:  58%|#####7    | 1729/3000 [40:20<25:30,  1.20s/it, lr: 1.0e-04 loss: 1.459e-01]
latex_v1:  58%|#####7    | 1729/3000 [40:20<25:30,  1.20s/it, lr: 1.0e-04 loss: 1.459e-01]
latex_v1:  58%|#####7    | 1730/3000 [40:21<25:29,  1.20s/it, lr: 1.0e-04 loss: 7.450e-01]
latex_v1:  58%|#####7    | 1730/3000 [40:21<25:29,  1.20s/it, lr: 1.0e-04 loss: 7.450e-01]
latex_v1:  58%|#####7    | 1731/3000 [40:21<17:24,  1.22it/s, lr: 1.0e-04 loss: 7.450e-01]
latex_v1:  58%|#####7    | 1731/3000 [40:21<17:24,  1.22it/s, lr: 1.0e-04 loss: 7.450e-01]
latex_v1:  58%|#####7    | 1731/3000 [40:22<17:24,  1.22it/s, lr: 1.0e-04 loss: 3.579e-01]
latex_v1:  58%|#####7    | 1731/3000 [40:22<17:24,  1.22it/s, lr: 1.0e-04 loss: 3.579e-01]
latex_v1:  58%|#####7    | 1732/3000 [40:22<22:56,  1.09s/it, lr: 1.0e-04 loss: 3.579e-01]
latex_v1:  58%|#####7    | 1732/3000 [40:22<22:56,  1.09s/it, lr: 1.0e-04 loss: 3.579e-01]
latex_v1:  58%|#####7    | 1732/3000 [40:24<22:56,  1.09s/it, lr: 1.0e-04 loss: 6.161e-01]
latex_v1:  58%|#####7    | 1732/3000 [40:24<22:56,  1.09s/it, lr: 1.0e-04 loss: 6.161e-01]
latex_v1:  58%|#####7    | 1733/3000 [40:24<24:27,  1.16s/it, lr: 1.0e-04 loss: 6.161e-01]
latex_v1:  58%|#####7    | 1733/3000 [40:24<24:27,  1.16s/it, lr: 1.0e-04 loss: 6.161e-01]
latex_v1:  58%|#####7    | 1733/3000 [40:27<24:27,  1.16s/it, lr: 1.0e-04 loss: 4.132e-01]
latex_v1:  58%|#####7    | 1733/3000 [40:27<24:27,  1.16s/it, lr: 1.0e-04 loss: 4.132e-01]
latex_v1:  58%|#####7    | 1734/3000 [40:27<34:20,  1.63s/it, lr: 1.0e-04 loss: 4.132e-01]
latex_v1:  58%|#####7    | 1734/3000 [40:27<34:20,  1.63s/it, lr: 1.0e-04 loss: 4.132e-01]
latex_v1:  58%|#####7    | 1734/3000 [40:28<34:20,  1.63s/it, lr: 1.0e-04 loss: 4.907e-01]
latex_v1:  58%|#####7    | 1734/3000 [40:28<34:20,  1.63s/it, lr: 1.0e-04 loss: 4.907e-01]
latex_v1:  58%|#####7    | 1735/3000 [40:28<34:22,  1.63s/it, lr: 1.0e-04 loss: 4.907e-01]
latex_v1:  58%|#####7    | 1735/3000 [40:28<34:22,  1.63s/it, lr: 1.0e-04 loss: 4.907e-01]
latex_v1:  58%|#####7    | 1735/3000 [40:29<34:22,  1.63s/it, lr: 1.0e-04 loss: 5.457e-01]
latex_v1:  58%|#####7    | 1735/3000 [40:29<34:22,  1.63s/it, lr: 1.0e-04 loss: 5.457e-01]
latex_v1:  58%|#####7    | 1736/3000 [40:29<30:18,  1.44s/it, lr: 1.0e-04 loss: 5.457e-01]
latex_v1:  58%|#####7    | 1736/3000 [40:29<30:18,  1.44s/it, lr: 1.0e-04 loss: 5.457e-01]
latex_v1:  58%|#####7    | 1736/3000 [40:30<30:18,  1.44s/it, lr: 1.0e-04 loss: 2.588e-01]
latex_v1:  58%|#####7    | 1736/3000 [40:30<30:18,  1.44s/it, lr: 1.0e-04 loss: 2.588e-01]
latex_v1:  58%|#####7    | 1737/3000 [40:30<26:00,  1.24s/it, lr: 1.0e-04 loss: 2.588e-01]
latex_v1:  58%|#####7    | 1737/3000 [40:30<26:00,  1.24s/it, lr: 1.0e-04 loss: 2.588e-01]
latex_v1:  58%|#####7    | 1737/3000 [40:31<26:00,  1.24s/it, lr: 1.0e-04 loss: 1.486e-01]
latex_v1:  58%|#####7    | 1737/3000 [40:31<26:00,  1.24s/it, lr: 1.0e-04 loss: 1.486e-01]
latex_v1:  58%|#####7    | 1738/3000 [40:31<27:14,  1.30s/it, lr: 1.0e-04 loss: 1.486e-01]
latex_v1:  58%|#####7    | 1738/3000 [40:31<27:14,  1.30s/it, lr: 1.0e-04 loss: 1.486e-01]
latex_v1:  58%|#####7    | 1738/3000 [40:33<27:14,  1.30s/it, lr: 1.0e-04 loss: 6.151e-01]
latex_v1:  58%|#####7    | 1738/3000 [40:33<27:14,  1.30s/it, lr: 1.0e-04 loss: 6.151e-01]
latex_v1:  58%|#####7    | 1739/3000 [40:33<28:36,  1.36s/it, lr: 1.0e-04 loss: 6.151e-01]
latex_v1:  58%|#####7    | 1739/3000 [40:33<28:36,  1.36s/it, lr: 1.0e-04 loss: 6.151e-01]
latex_v1:  58%|#####7    | 1739/3000 [40:34<28:36,  1.36s/it, lr: 1.0e-04 loss: 4.115e-01]
latex_v1:  58%|#####7    | 1739/3000 [40:34<28:36,  1.36s/it, lr: 1.0e-04 loss: 4.115e-01]
latex_v1:  58%|#####8    | 1740/3000 [40:34<28:35,  1.36s/it, lr: 1.0e-04 loss: 1.318e-01]
latex_v1:  58%|#####8    | 1740/3000 [40:34<28:35,  1.36s/it, lr: 1.0e-04 loss: 1.318e-01]
latex_v1:  58%|#####8    | 1741/3000 [40:34<19:03,  1.10it/s, lr: 1.0e-04 loss: 1.318e-01]
latex_v1:  58%|#####8    | 1741/3000 [40:34<19:03,  1.10it/s, lr: 1.0e-04 loss: 1.318e-01]
latex_v1:  58%|#####8    | 1741/3000 [40:36<19:03,  1.10it/s, lr: 1.0e-04 loss: 5.254e-01]
latex_v1:  58%|#####8    | 1741/3000 [40:36<19:03,  1.10it/s, lr: 1.0e-04 loss: 5.254e-01]
latex_v1:  58%|#####8    | 1742/3000 [40:36<21:09,  1.01s/it, lr: 1.0e-04 loss: 5.254e-01]
latex_v1:  58%|#####8    | 1742/3000 [40:36<21:09,  1.01s/it, lr: 1.0e-04 loss: 5.254e-01]
latex_v1:  58%|#####8    | 1742/3000 [40:37<21:09,  1.01s/it, lr: 1.0e-04 loss: 5.435e-01]
latex_v1:  58%|#####8    | 1742/3000 [40:37<21:09,  1.01s/it, lr: 1.0e-04 loss: 5.435e-01]
latex_v1:  58%|#####8    | 1743/3000 [40:37<22:00,  1.05s/it, lr: 1.0e-04 loss: 5.435e-01]
latex_v1:  58%|#####8    | 1743/3000 [40:37<22:00,  1.05s/it, lr: 1.0e-04 loss: 5.435e-01]
latex_v1:  58%|#####8    | 1743/3000 [40:38<22:00,  1.05s/it, lr: 1.0e-04 loss: 3.963e-01]
latex_v1:  58%|#####8    | 1743/3000 [40:38<22:00,  1.05s/it, lr: 1.0e-04 loss: 3.963e-01]
latex_v1:  58%|#####8    | 1744/3000 [40:38<24:15,  1.16s/it, lr: 1.0e-04 loss: 3.963e-01]
latex_v1:  58%|#####8    | 1744/3000 [40:38<24:15,  1.16s/it, lr: 1.0e-04 loss: 3.963e-01]
latex_v1:  58%|#####8    | 1744/3000 [40:40<24:15,  1.16s/it, lr: 1.0e-04 loss: 1.020e-01]
latex_v1:  58%|#####8    | 1744/3000 [40:40<24:15,  1.16s/it, lr: 1.0e-04 loss: 1.020e-01]
latex_v1:  58%|#####8    | 1745/3000 [40:40<25:38,  1.23s/it, lr: 1.0e-04 loss: 1.020e-01]
latex_v1:  58%|#####8    | 1745/3000 [40:40<25:38,  1.23s/it, lr: 1.0e-04 loss: 1.020e-01]
latex_v1:  58%|#####8    | 1745/3000 [40:40<25:38,  1.23s/it, lr: 1.0e-04 loss: 1.737e-01]
latex_v1:  58%|#####8    | 1745/3000 [40:40<25:38,  1.23s/it, lr: 1.0e-04 loss: 1.737e-01]
latex_v1:  58%|#####8    | 1746/3000 [40:40<22:46,  1.09s/it, lr: 1.0e-04 loss: 1.737e-01]
latex_v1:  58%|#####8    | 1746/3000 [40:40<22:46,  1.09s/it, lr: 1.0e-04 loss: 1.737e-01]
latex_v1:  58%|#####8    | 1746/3000 [40:42<22:46,  1.09s/it, lr: 1.0e-04 loss: 6.850e-01]
latex_v1:  58%|#####8    | 1746/3000 [40:42<22:46,  1.09s/it, lr: 1.0e-04 loss: 6.850e-01]
latex_v1:  58%|#####8    | 1747/3000 [40:42<23:12,  1.11s/it, lr: 1.0e-04 loss: 6.850e-01]
latex_v1:  58%|#####8    | 1747/3000 [40:42<23:12,  1.11s/it, lr: 1.0e-04 loss: 6.850e-01]
latex_v1:  58%|#####8    | 1747/3000 [40:43<23:12,  1.11s/it, lr: 1.0e-04 loss: 1.722e-01]
latex_v1:  58%|#####8    | 1747/3000 [40:43<23:12,  1.11s/it, lr: 1.0e-04 loss: 1.722e-01]
latex_v1:  58%|#####8    | 1748/3000 [40:43<26:02,  1.25s/it, lr: 1.0e-04 loss: 1.722e-01]
latex_v1:  58%|#####8    | 1748/3000 [40:43<26:02,  1.25s/it, lr: 1.0e-04 loss: 1.722e-01]
latex_v1:  58%|#####8    | 1748/3000 [40:45<26:02,  1.25s/it, lr: 1.0e-04 loss: 5.308e-01]
latex_v1:  58%|#####8    | 1748/3000 [40:45<26:02,  1.25s/it, lr: 1.0e-04 loss: 5.308e-01]
latex_v1:  58%|#####8    | 1749/3000 [40:45<27:48,  1.33s/it, lr: 1.0e-04 loss: 5.308e-01]
latex_v1:  58%|#####8    | 1749/3000 [40:45<27:48,  1.33s/it, lr: 1.0e-04 loss: 5.308e-01]
latex_v1:  58%|#####8    | 1749/3000 [40:46<27:48,  1.33s/it, lr: 1.0e-04 loss: 6.453e-01]
latex_v1:  58%|#####8    | 1749/3000 [40:46<27:48,  1.33s/it, lr: 1.0e-04 loss: 6.453e-01]
Saving at step 1750
Saved checkpoint to /data/app/output/latex_v1/latex_v1_000001750.safetensors
Saved optimizer to /data/app/output/latex_v1/optimizer.pt
Removing old save: /data/app/output/latex_v1/latex_v1_000000750.safetensors

latex_v1:  58%|#####8    | 1750/3000 [40:47<27:47,  1.33s/it, lr: 1.0e-04 loss: 7.200e-01]
latex_v1:  58%|#####8    | 1750/3000 [40:47<27:47,  1.33s/it, lr: 1.0e-04 loss: 7.200e-01]
latex_v1:  58%|#####8    | 1751/3000 [40:47<22:37,  1.09s/it, lr: 1.0e-04 loss: 7.200e-01]
latex_v1:  58%|#####8    | 1751/3000 [40:47<22:37,  1.09s/it, lr: 1.0e-04 loss: 7.200e-01]
latex_v1:  58%|#####8    | 1751/3000 [40:49<22:37,  1.09s/it, lr: 1.0e-04 loss: 1.916e-01]
latex_v1:  58%|#####8    | 1751/3000 [40:49<22:37,  1.09s/it, lr: 1.0e-04 loss: 1.916e-01]
latex_v1:  58%|#####8    | 1752/3000 [40:49<24:52,  1.20s/it, lr: 1.0e-04 loss: 1.916e-01]
latex_v1:  58%|#####8    | 1752/3000 [40:49<24:52,  1.20s/it, lr: 1.0e-04 loss: 1.916e-01]
latex_v1:  58%|#####8    | 1752/3000 [40:51<24:52,  1.20s/it, lr: 1.0e-04 loss: 4.836e-01]
latex_v1:  58%|#####8    | 1752/3000 [40:51<24:52,  1.20s/it, lr: 1.0e-04 loss: 4.836e-01]
latex_v1:  58%|#####8    | 1753/3000 [40:51<28:29,  1.37s/it, lr: 1.0e-04 loss: 4.836e-01]
latex_v1:  58%|#####8    | 1753/3000 [40:51<28:29,  1.37s/it, lr: 1.0e-04 loss: 4.836e-01]
latex_v1:  58%|#####8    | 1753/3000 [40:51<28:29,  1.37s/it, lr: 1.0e-04 loss: 5.951e-01]
latex_v1:  58%|#####8    | 1753/3000 [40:51<28:29,  1.37s/it, lr: 1.0e-04 loss: 5.951e-01]
latex_v1:  58%|#####8    | 1754/3000 [40:51<24:54,  1.20s/it, lr: 1.0e-04 loss: 5.951e-01]
latex_v1:  58%|#####8    | 1754/3000 [40:51<24:54,  1.20s/it, lr: 1.0e-04 loss: 5.951e-01]
latex_v1:  58%|#####8    | 1754/3000 [40:52<24:54,  1.20s/it, lr: 1.0e-04 loss: 1.548e-01]
latex_v1:  58%|#####8    | 1754/3000 [40:52<24:54,  1.20s/it, lr: 1.0e-04 loss: 1.548e-01]
latex_v1:  58%|#####8    | 1755/3000 [40:52<22:20,  1.08s/it, lr: 1.0e-04 loss: 1.548e-01]
latex_v1:  58%|#####8    | 1755/3000 [40:52<22:20,  1.08s/it, lr: 1.0e-04 loss: 1.548e-01]
latex_v1:  58%|#####8    | 1755/3000 [40:55<22:20,  1.08s/it, lr: 1.0e-04 loss: 4.729e-01]
latex_v1:  58%|#####8    | 1755/3000 [40:55<22:20,  1.08s/it, lr: 1.0e-04 loss: 4.729e-01]
latex_v1:  59%|#####8    | 1756/3000 [40:55<31:34,  1.52s/it, lr: 1.0e-04 loss: 4.729e-01]
latex_v1:  59%|#####8    | 1756/3000 [40:55<31:34,  1.52s/it, lr: 1.0e-04 loss: 4.729e-01]
latex_v1:  59%|#####8    | 1756/3000 [40:55<31:34,  1.52s/it, lr: 1.0e-04 loss: 2.764e-01]
latex_v1:  59%|#####8    | 1756/3000 [40:55<31:34,  1.52s/it, lr: 1.0e-04 loss: 2.764e-01]
latex_v1:  59%|#####8    | 1757/3000 [40:55<26:57,  1.30s/it, lr: 1.0e-04 loss: 2.764e-01]
latex_v1:  59%|#####8    | 1757/3000 [40:55<26:57,  1.30s/it, lr: 1.0e-04 loss: 2.764e-01]
latex_v1:  59%|#####8    | 1757/3000 [40:57<26:57,  1.30s/it, lr: 1.0e-04 loss: 5.982e-01]
latex_v1:  59%|#####8    | 1757/3000 [40:57<26:57,  1.30s/it, lr: 1.0e-04 loss: 5.982e-01]
latex_v1:  59%|#####8    | 1758/3000 [40:57<30:26,  1.47s/it, lr: 1.0e-04 loss: 5.982e-01]
latex_v1:  59%|#####8    | 1758/3000 [40:57<30:26,  1.47s/it, lr: 1.0e-04 loss: 5.982e-01]
latex_v1:  59%|#####8    | 1758/3000 [40:59<30:26,  1.47s/it, lr: 1.0e-04 loss: 5.208e-01]
latex_v1:  59%|#####8    | 1758/3000 [40:59<30:26,  1.47s/it, lr: 1.0e-04 loss: 5.208e-01]
latex_v1:  59%|#####8    | 1759/3000 [40:59<32:35,  1.58s/it, lr: 1.0e-04 loss: 5.208e-01]
latex_v1:  59%|#####8    | 1759/3000 [40:59<32:35,  1.58s/it, lr: 1.0e-04 loss: 5.208e-01]
latex_v1:  59%|#####8    | 1759/3000 [41:01<32:35,  1.58s/it, lr: 1.0e-04 loss: 1.234e-01]
latex_v1:  59%|#####8    | 1759/3000 [41:01<32:35,  1.58s/it, lr: 1.0e-04 loss: 1.234e-01]
latex_v1:  59%|#####8    | 1760/3000 [41:02<32:33,  1.58s/it, lr: 1.0e-04 loss: 3.545e-01]
latex_v1:  59%|#####8    | 1760/3000 [41:02<32:33,  1.58s/it, lr: 1.0e-04 loss: 3.545e-01]
latex_v1:  59%|#####8    | 1761/3000 [41:02<24:57,  1.21s/it, lr: 1.0e-04 loss: 3.545e-01]
latex_v1:  59%|#####8    | 1761/3000 [41:02<24:57,  1.21s/it, lr: 1.0e-04 loss: 3.545e-01]
latex_v1:  59%|#####8    | 1761/3000 [41:05<24:57,  1.21s/it, lr: 1.0e-04 loss: 1.223e-01]
latex_v1:  59%|#####8    | 1761/3000 [41:05<24:57,  1.21s/it, lr: 1.0e-04 loss: 1.223e-01]
latex_v1:  59%|#####8    | 1762/3000 [41:05<33:11,  1.61s/it, lr: 1.0e-04 loss: 1.223e-01]
latex_v1:  59%|#####8    | 1762/3000 [41:05<33:11,  1.61s/it, lr: 1.0e-04 loss: 1.223e-01]
latex_v1:  59%|#####8    | 1762/3000 [41:07<33:11,  1.61s/it, lr: 1.0e-04 loss: 4.646e-01]
latex_v1:  59%|#####8    | 1762/3000 [41:07<33:11,  1.61s/it, lr: 1.0e-04 loss: 4.646e-01]
latex_v1:  59%|#####8    | 1763/3000 [41:07<33:46,  1.64s/it, lr: 1.0e-04 loss: 4.646e-01]
latex_v1:  59%|#####8    | 1763/3000 [41:07<33:46,  1.64s/it, lr: 1.0e-04 loss: 4.646e-01]
latex_v1:  59%|#####8    | 1763/3000 [41:07<33:46,  1.64s/it, lr: 1.0e-04 loss: 2.346e-01]
latex_v1:  59%|#####8    | 1763/3000 [41:07<33:46,  1.64s/it, lr: 1.0e-04 loss: 2.346e-01]
latex_v1:  59%|#####8    | 1764/3000 [41:07<28:43,  1.39s/it, lr: 1.0e-04 loss: 2.346e-01]
latex_v1:  59%|#####8    | 1764/3000 [41:07<28:43,  1.39s/it, lr: 1.0e-04 loss: 2.346e-01]
latex_v1:  59%|#####8    | 1764/3000 [41:08<28:43,  1.39s/it, lr: 1.0e-04 loss: 8.137e-02]
latex_v1:  59%|#####8    | 1764/3000 [41:08<28:43,  1.39s/it, lr: 1.0e-04 loss: 8.137e-02]
latex_v1:  59%|#####8    | 1765/3000 [41:08<24:58,  1.21s/it, lr: 1.0e-04 loss: 8.137e-02]
latex_v1:  59%|#####8    | 1765/3000 [41:08<24:58,  1.21s/it, lr: 1.0e-04 loss: 8.137e-02]
latex_v1:  59%|#####8    | 1765/3000 [41:11<24:58,  1.21s/it, lr: 1.0e-04 loss: 2.707e-01]
latex_v1:  59%|#####8    | 1765/3000 [41:11<24:58,  1.21s/it, lr: 1.0e-04 loss: 2.707e-01]
latex_v1:  59%|#####8    | 1766/3000 [41:11<34:27,  1.68s/it, lr: 1.0e-04 loss: 2.707e-01]
latex_v1:  59%|#####8    | 1766/3000 [41:11<34:27,  1.68s/it, lr: 1.0e-04 loss: 2.707e-01]
latex_v1:  59%|#####8    | 1766/3000 [41:14<34:27,  1.68s/it, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:  59%|#####8    | 1766/3000 [41:14<34:27,  1.68s/it, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:  59%|#####8    | 1767/3000 [41:14<41:33,  2.02s/it, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:  59%|#####8    | 1767/3000 [41:14<41:33,  2.02s/it, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:  59%|#####8    | 1767/3000 [41:16<41:33,  2.02s/it, lr: 1.0e-04 loss: 3.399e-01]
latex_v1:  59%|#####8    | 1767/3000 [41:16<41:33,  2.02s/it, lr: 1.0e-04 loss: 3.399e-01]
latex_v1:  59%|#####8    | 1768/3000 [41:16<38:35,  1.88s/it, lr: 1.0e-04 loss: 3.399e-01]
latex_v1:  59%|#####8    | 1768/3000 [41:16<38:35,  1.88s/it, lr: 1.0e-04 loss: 3.399e-01]
latex_v1:  59%|#####8    | 1768/3000 [41:18<38:35,  1.88s/it, lr: 1.0e-04 loss: 2.912e-01]
latex_v1:  59%|#####8    | 1768/3000 [41:18<38:35,  1.88s/it, lr: 1.0e-04 loss: 2.912e-01]
latex_v1:  59%|#####8    | 1769/3000 [41:18<40:35,  1.98s/it, lr: 1.0e-04 loss: 2.912e-01]
latex_v1:  59%|#####8    | 1769/3000 [41:18<40:35,  1.98s/it, lr: 1.0e-04 loss: 2.912e-01]
latex_v1:  59%|#####8    | 1769/3000 [41:19<40:35,  1.98s/it, lr: 1.0e-04 loss: 1.805e-01]
latex_v1:  59%|#####8    | 1769/3000 [41:19<40:35,  1.98s/it, lr: 1.0e-04 loss: 1.805e-01]
latex_v1:  59%|#####8    | 1770/3000 [41:20<40:33,  1.98s/it, lr: 1.0e-04 loss: 3.968e-01]
latex_v1:  59%|#####8    | 1770/3000 [41:20<40:33,  1.98s/it, lr: 1.0e-04 loss: 3.968e-01]
latex_v1:  59%|#####9    | 1771/3000 [41:20<28:19,  1.38s/it, lr: 1.0e-04 loss: 3.968e-01]
latex_v1:  59%|#####9    | 1771/3000 [41:20<28:19,  1.38s/it, lr: 1.0e-04 loss: 3.968e-01]
latex_v1:  59%|#####9    | 1771/3000 [41:21<28:19,  1.38s/it, lr: 1.0e-04 loss: 4.051e-01]
latex_v1:  59%|#####9    | 1771/3000 [41:21<28:19,  1.38s/it, lr: 1.0e-04 loss: 4.051e-01]
latex_v1:  59%|#####9    | 1772/3000 [41:21<25:07,  1.23s/it, lr: 1.0e-04 loss: 4.051e-01]
latex_v1:  59%|#####9    | 1772/3000 [41:21<25:07,  1.23s/it, lr: 1.0e-04 loss: 4.051e-01]
latex_v1:  59%|#####9    | 1772/3000 [41:23<25:07,  1.23s/it, lr: 1.0e-04 loss: 1.808e-01]
latex_v1:  59%|#####9    | 1772/3000 [41:23<25:07,  1.23s/it, lr: 1.0e-04 loss: 1.808e-01]
latex_v1:  59%|#####9    | 1773/3000 [41:23<26:42,  1.31s/it, lr: 1.0e-04 loss: 1.808e-01]
latex_v1:  59%|#####9    | 1773/3000 [41:23<26:42,  1.31s/it, lr: 1.0e-04 loss: 1.808e-01]
latex_v1:  59%|#####9    | 1773/3000 [41:24<26:42,  1.31s/it, lr: 1.0e-04 loss: 7.820e-01]
latex_v1:  59%|#####9    | 1773/3000 [41:24<26:42,  1.31s/it, lr: 1.0e-04 loss: 7.820e-01]
latex_v1:  59%|#####9    | 1774/3000 [41:24<24:46,  1.21s/it, lr: 1.0e-04 loss: 7.820e-01]
latex_v1:  59%|#####9    | 1774/3000 [41:24<24:46,  1.21s/it, lr: 1.0e-04 loss: 7.820e-01]
latex_v1:  59%|#####9    | 1774/3000 [41:24<24:46,  1.21s/it, lr: 1.0e-04 loss: 4.442e-01]
latex_v1:  59%|#####9    | 1774/3000 [41:24<24:46,  1.21s/it, lr: 1.0e-04 loss: 4.442e-01]
latex_v1:  59%|#####9    | 1775/3000 [41:24<22:03,  1.08s/it, lr: 1.0e-04 loss: 4.442e-01]
latex_v1:  59%|#####9    | 1775/3000 [41:24<22:03,  1.08s/it, lr: 1.0e-04 loss: 4.442e-01]
latex_v1:  59%|#####9    | 1775/3000 [41:26<22:03,  1.08s/it, lr: 1.0e-04 loss: 3.293e-01]
latex_v1:  59%|#####9    | 1775/3000 [41:26<22:03,  1.08s/it, lr: 1.0e-04 loss: 3.293e-01]
latex_v1:  59%|#####9    | 1776/3000 [41:26<25:45,  1.26s/it, lr: 1.0e-04 loss: 3.293e-01]
latex_v1:  59%|#####9    | 1776/3000 [41:26<25:45,  1.26s/it, lr: 1.0e-04 loss: 3.293e-01]
latex_v1:  59%|#####9    | 1776/3000 [41:27<25:45,  1.26s/it, lr: 1.0e-04 loss: 3.177e-01]
latex_v1:  59%|#####9    | 1776/3000 [41:27<25:45,  1.26s/it, lr: 1.0e-04 loss: 3.177e-01]
latex_v1:  59%|#####9    | 1777/3000 [41:27<25:08,  1.23s/it, lr: 1.0e-04 loss: 3.177e-01]
latex_v1:  59%|#####9    | 1777/3000 [41:27<25:08,  1.23s/it, lr: 1.0e-04 loss: 3.177e-01]
latex_v1:  59%|#####9    | 1777/3000 [41:30<25:08,  1.23s/it, lr: 1.0e-04 loss: 3.253e-01]
latex_v1:  59%|#####9    | 1777/3000 [41:30<25:08,  1.23s/it, lr: 1.0e-04 loss: 3.253e-01]
latex_v1:  59%|#####9    | 1778/3000 [41:30<35:56,  1.76s/it, lr: 1.0e-04 loss: 3.253e-01]
latex_v1:  59%|#####9    | 1778/3000 [41:30<35:56,  1.76s/it, lr: 1.0e-04 loss: 3.253e-01]
latex_v1:  59%|#####9    | 1778/3000 [41:31<35:56,  1.76s/it, lr: 1.0e-04 loss: 2.961e-01]
latex_v1:  59%|#####9    | 1778/3000 [41:31<35:56,  1.76s/it, lr: 1.0e-04 loss: 2.961e-01]
latex_v1:  59%|#####9    | 1779/3000 [41:31<29:52,  1.47s/it, lr: 1.0e-04 loss: 2.961e-01]
latex_v1:  59%|#####9    | 1779/3000 [41:31<29:52,  1.47s/it, lr: 1.0e-04 loss: 2.961e-01]
latex_v1:  59%|#####9    | 1779/3000 [41:32<29:52,  1.47s/it, lr: 1.0e-04 loss: 3.399e-01]
latex_v1:  59%|#####9    | 1779/3000 [41:32<29:52,  1.47s/it, lr: 1.0e-04 loss: 3.399e-01]
latex_v1:  59%|#####9    | 1780/3000 [41:33<29:50,  1.47s/it, lr: 1.0e-04 loss: 5.465e-01]
latex_v1:  59%|#####9    | 1780/3000 [41:33<29:50,  1.47s/it, lr: 1.0e-04 loss: 5.465e-01]
latex_v1:  59%|#####9    | 1781/3000 [41:33<23:18,  1.15s/it, lr: 1.0e-04 loss: 5.465e-01]
latex_v1:  59%|#####9    | 1781/3000 [41:33<23:18,  1.15s/it, lr: 1.0e-04 loss: 5.465e-01]
latex_v1:  59%|#####9    | 1781/3000 [41:34<23:18,  1.15s/it, lr: 1.0e-04 loss: 2.232e-01]
latex_v1:  59%|#####9    | 1781/3000 [41:34<23:18,  1.15s/it, lr: 1.0e-04 loss: 2.232e-01]
latex_v1:  59%|#####9    | 1782/3000 [41:34<21:14,  1.05s/it, lr: 1.0e-04 loss: 2.232e-01]
latex_v1:  59%|#####9    | 1782/3000 [41:34<21:14,  1.05s/it, lr: 1.0e-04 loss: 2.232e-01]
latex_v1:  59%|#####9    | 1782/3000 [41:36<21:14,  1.05s/it, lr: 1.0e-04 loss: 4.478e-01]
latex_v1:  59%|#####9    | 1782/3000 [41:36<21:14,  1.05s/it, lr: 1.0e-04 loss: 4.478e-01]
latex_v1:  59%|#####9    | 1783/3000 [41:36<23:46,  1.17s/it, lr: 1.0e-04 loss: 4.478e-01]
latex_v1:  59%|#####9    | 1783/3000 [41:36<23:46,  1.17s/it, lr: 1.0e-04 loss: 4.478e-01]
latex_v1:  59%|#####9    | 1783/3000 [41:37<23:46,  1.17s/it, lr: 1.0e-04 loss: 5.859e-01]
latex_v1:  59%|#####9    | 1783/3000 [41:37<23:46,  1.17s/it, lr: 1.0e-04 loss: 5.859e-01]
latex_v1:  59%|#####9    | 1784/3000 [41:37<25:11,  1.24s/it, lr: 1.0e-04 loss: 5.859e-01]
latex_v1:  59%|#####9    | 1784/3000 [41:37<25:11,  1.24s/it, lr: 1.0e-04 loss: 5.859e-01]
latex_v1:  59%|#####9    | 1784/3000 [41:40<25:11,  1.24s/it, lr: 1.0e-04 loss: 5.613e-02]
latex_v1:  59%|#####9    | 1784/3000 [41:40<25:11,  1.24s/it, lr: 1.0e-04 loss: 5.613e-02]
latex_v1:  60%|#####9    | 1785/3000 [41:40<34:22,  1.70s/it, lr: 1.0e-04 loss: 5.613e-02]
latex_v1:  60%|#####9    | 1785/3000 [41:40<34:22,  1.70s/it, lr: 1.0e-04 loss: 5.613e-02]
latex_v1:  60%|#####9    | 1785/3000 [41:42<34:22,  1.70s/it, lr: 1.0e-04 loss: 8.583e-02]
latex_v1:  60%|#####9    | 1785/3000 [41:42<34:22,  1.70s/it, lr: 1.0e-04 loss: 8.583e-02]
latex_v1:  60%|#####9    | 1786/3000 [41:42<33:28,  1.65s/it, lr: 1.0e-04 loss: 8.583e-02]
latex_v1:  60%|#####9    | 1786/3000 [41:42<33:28,  1.65s/it, lr: 1.0e-04 loss: 8.583e-02]
latex_v1:  60%|#####9    | 1786/3000 [41:43<33:28,  1.65s/it, lr: 1.0e-04 loss: 5.035e-01]
latex_v1:  60%|#####9    | 1786/3000 [41:43<33:28,  1.65s/it, lr: 1.0e-04 loss: 5.035e-01]
latex_v1:  60%|#####9    | 1787/3000 [41:43<34:42,  1.72s/it, lr: 1.0e-04 loss: 5.035e-01]
latex_v1:  60%|#####9    | 1787/3000 [41:43<34:42,  1.72s/it, lr: 1.0e-04 loss: 5.035e-01]
latex_v1:  60%|#####9    | 1787/3000 [41:44<34:42,  1.72s/it, lr: 1.0e-04 loss: 3.882e-01]
latex_v1:  60%|#####9    | 1787/3000 [41:44<34:42,  1.72s/it, lr: 1.0e-04 loss: 3.882e-01]
latex_v1:  60%|#####9    | 1788/3000 [41:44<29:04,  1.44s/it, lr: 1.0e-04 loss: 3.882e-01]
latex_v1:  60%|#####9    | 1788/3000 [41:44<29:04,  1.44s/it, lr: 1.0e-04 loss: 3.882e-01]
latex_v1:  60%|#####9    | 1788/3000 [41:45<29:04,  1.44s/it, lr: 1.0e-04 loss: 2.184e-01]
latex_v1:  60%|#####9    | 1788/3000 [41:45<29:04,  1.44s/it, lr: 1.0e-04 loss: 2.184e-01]
latex_v1:  60%|#####9    | 1789/3000 [41:45<25:05,  1.24s/it, lr: 1.0e-04 loss: 2.184e-01]
latex_v1:  60%|#####9    | 1789/3000 [41:45<25:05,  1.24s/it, lr: 1.0e-04 loss: 2.184e-01]
latex_v1:  60%|#####9    | 1789/3000 [41:46<25:05,  1.24s/it, lr: 1.0e-04 loss: 2.689e-01]
latex_v1:  60%|#####9    | 1789/3000 [41:46<25:05,  1.24s/it, lr: 1.0e-04 loss: 2.689e-01]
latex_v1:  60%|#####9    | 1790/3000 [41:48<25:04,  1.24s/it, lr: 1.0e-04 loss: 1.171e-01]
latex_v1:  60%|#####9    | 1790/3000 [41:48<25:04,  1.24s/it, lr: 1.0e-04 loss: 1.171e-01]
latex_v1:  60%|#####9    | 1791/3000 [41:48<22:17,  1.11s/it, lr: 1.0e-04 loss: 1.171e-01]
latex_v1:  60%|#####9    | 1791/3000 [41:48<22:17,  1.11s/it, lr: 1.0e-04 loss: 1.171e-01]
latex_v1:  60%|#####9    | 1791/3000 [41:50<22:17,  1.11s/it, lr: 1.0e-04 loss: 2.272e-01]
latex_v1:  60%|#####9    | 1791/3000 [41:50<22:17,  1.11s/it, lr: 1.0e-04 loss: 2.272e-01]
latex_v1:  60%|#####9    | 1792/3000 [41:50<30:27,  1.51s/it, lr: 1.0e-04 loss: 2.272e-01]
latex_v1:  60%|#####9    | 1792/3000 [41:50<30:27,  1.51s/it, lr: 1.0e-04 loss: 2.272e-01]
latex_v1:  60%|#####9    | 1792/3000 [41:52<30:27,  1.51s/it, lr: 1.0e-04 loss: 1.564e-01]
latex_v1:  60%|#####9    | 1792/3000 [41:52<30:27,  1.51s/it, lr: 1.0e-04 loss: 1.564e-01]
latex_v1:  60%|#####9    | 1793/3000 [41:52<30:32,  1.52s/it, lr: 1.0e-04 loss: 1.564e-01]
latex_v1:  60%|#####9    | 1793/3000 [41:52<30:32,  1.52s/it, lr: 1.0e-04 loss: 1.564e-01]
latex_v1:  60%|#####9    | 1793/3000 [41:53<30:32,  1.52s/it, lr: 1.0e-04 loss: 5.790e-01]
latex_v1:  60%|#####9    | 1793/3000 [41:53<30:32,  1.52s/it, lr: 1.0e-04 loss: 5.790e-01]
latex_v1:  60%|#####9    | 1794/3000 [41:53<30:04,  1.50s/it, lr: 1.0e-04 loss: 5.790e-01]
latex_v1:  60%|#####9    | 1794/3000 [41:53<30:04,  1.50s/it, lr: 1.0e-04 loss: 5.790e-01]
latex_v1:  60%|#####9    | 1794/3000 [41:56<30:04,  1.50s/it, lr: 1.0e-04 loss: 4.347e-01]
latex_v1:  60%|#####9    | 1794/3000 [41:56<30:04,  1.50s/it, lr: 1.0e-04 loss: 4.347e-01]
latex_v1:  60%|#####9    | 1795/3000 [41:56<37:44,  1.88s/it, lr: 1.0e-04 loss: 4.347e-01]
latex_v1:  60%|#####9    | 1795/3000 [41:56<37:44,  1.88s/it, lr: 1.0e-04 loss: 4.347e-01]
latex_v1:  60%|#####9    | 1795/3000 [41:57<37:44,  1.88s/it, lr: 1.0e-04 loss: 3.003e-01]
latex_v1:  60%|#####9    | 1795/3000 [41:57<37:44,  1.88s/it, lr: 1.0e-04 loss: 3.003e-01]
latex_v1:  60%|#####9    | 1796/3000 [41:57<33:34,  1.67s/it, lr: 1.0e-04 loss: 3.003e-01]
latex_v1:  60%|#####9    | 1796/3000 [41:57<33:34,  1.67s/it, lr: 1.0e-04 loss: 3.003e-01]
latex_v1:  60%|#####9    | 1796/3000 [41:59<33:34,  1.67s/it, lr: 1.0e-04 loss: 1.791e-01]
latex_v1:  60%|#####9    | 1796/3000 [41:59<33:34,  1.67s/it, lr: 1.0e-04 loss: 1.791e-01]
latex_v1:  60%|#####9    | 1797/3000 [41:59<32:10,  1.60s/it, lr: 1.0e-04 loss: 1.791e-01]
latex_v1:  60%|#####9    | 1797/3000 [41:59<32:10,  1.60s/it, lr: 1.0e-04 loss: 1.791e-01]
latex_v1:  60%|#####9    | 1797/3000 [42:02<32:10,  1.60s/it, lr: 1.0e-04 loss: 4.955e-01]
latex_v1:  60%|#####9    | 1797/3000 [42:02<32:10,  1.60s/it, lr: 1.0e-04 loss: 4.955e-01]
latex_v1:  60%|#####9    | 1798/3000 [42:02<39:13,  1.96s/it, lr: 1.0e-04 loss: 4.955e-01]
latex_v1:  60%|#####9    | 1798/3000 [42:02<39:13,  1.96s/it, lr: 1.0e-04 loss: 4.955e-01]
latex_v1:  60%|#####9    | 1798/3000 [42:03<39:13,  1.96s/it, lr: 1.0e-04 loss: 4.100e-01]
latex_v1:  60%|#####9    | 1798/3000 [42:03<39:13,  1.96s/it, lr: 1.0e-04 loss: 4.100e-01]
latex_v1:  60%|#####9    | 1799/3000 [42:03<35:26,  1.77s/it, lr: 1.0e-04 loss: 4.100e-01]
latex_v1:  60%|#####9    | 1799/3000 [42:03<35:26,  1.77s/it, lr: 1.0e-04 loss: 4.100e-01]
latex_v1:  60%|#####9    | 1799/3000 [42:04<35:26,  1.77s/it, lr: 1.0e-04 loss: 4.644e-01]
latex_v1:  60%|#####9    | 1799/3000 [42:04<35:26,  1.77s/it, lr: 1.0e-04 loss: 4.644e-01]Unloading assistant lora



Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]


Generating Images:  14%|#4        | 1/7 [00:02<00:15,  2.50s/it]
Generating Images:  14%|#4        | 1/7 [00:02<00:15,  2.50s/it]


Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.46s/it]
Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.46s/it]


Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.47s/it]
Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.47s/it]


Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.44s/it]
Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.44s/it]


Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.43s/it]
Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.43s/it]


Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.43s/it]
Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.43s/it]


Generating Images: 100%|##########| 7/7 [00:17<00:00,  2.43s/it]
Generating Images: 100%|##########| 7/7 [00:17<00:00,  2.43s/it]


                                                                
                                                                Loading assistant lora

latex_v1:  60%|######    | 1800/3000 [42:06<35:24,  1.77s/it, lr: 1.0e-04 loss: 4.563e-01]
latex_v1:  60%|######    | 1800/3000 [42:06<35:24,  1.77s/it, lr: 1.0e-04 loss: 4.563e-01]
latex_v1:  60%|######    | 1801/3000 [42:06<25:48,  1.29s/it, lr: 1.0e-04 loss: 4.563e-01]
latex_v1:  60%|######    | 1801/3000 [42:06<25:48,  1.29s/it, lr: 1.0e-04 loss: 4.563e-01]
latex_v1:  60%|######    | 1801/3000 [42:07<25:48,  1.29s/it, lr: 1.0e-04 loss: 3.023e-01]
latex_v1:  60%|######    | 1801/3000 [42:07<25:48,  1.29s/it, lr: 1.0e-04 loss: 3.023e-01]
latex_v1:  60%|######    | 1802/3000 [42:07<23:08,  1.16s/it, lr: 1.0e-04 loss: 3.023e-01]
latex_v1:  60%|######    | 1802/3000 [42:07<23:08,  1.16s/it, lr: 1.0e-04 loss: 3.023e-01]
latex_v1:  60%|######    | 1802/3000 [42:07<23:08,  1.16s/it, lr: 1.0e-04 loss: 2.648e-01]
latex_v1:  60%|######    | 1802/3000 [42:07<23:08,  1.16s/it, lr: 1.0e-04 loss: 2.648e-01]
latex_v1:  60%|######    | 1803/3000 [42:07<20:59,  1.05s/it, lr: 1.0e-04 loss: 2.648e-01]
latex_v1:  60%|######    | 1803/3000 [42:07<20:59,  1.05s/it, lr: 1.0e-04 loss: 2.648e-01]
latex_v1:  60%|######    | 1803/3000 [42:09<20:59,  1.05s/it, lr: 1.0e-04 loss: 2.603e-01]
latex_v1:  60%|######    | 1803/3000 [42:09<20:59,  1.05s/it, lr: 1.0e-04 loss: 2.603e-01]
latex_v1:  60%|######    | 1804/3000 [42:09<22:49,  1.14s/it, lr: 1.0e-04 loss: 2.603e-01]
latex_v1:  60%|######    | 1804/3000 [42:09<22:49,  1.14s/it, lr: 1.0e-04 loss: 2.603e-01]
latex_v1:  60%|######    | 1804/3000 [42:09<22:49,  1.14s/it, lr: 1.0e-04 loss: 3.226e-01]
latex_v1:  60%|######    | 1804/3000 [42:09<22:49,  1.14s/it, lr: 1.0e-04 loss: 3.226e-01]
latex_v1:  60%|######    | 1805/3000 [42:09<20:39,  1.04s/it, lr: 1.0e-04 loss: 3.226e-01]
latex_v1:  60%|######    | 1805/3000 [42:09<20:39,  1.04s/it, lr: 1.0e-04 loss: 3.226e-01]
latex_v1:  60%|######    | 1805/3000 [42:11<20:39,  1.04s/it, lr: 1.0e-04 loss: 4.769e-01]
latex_v1:  60%|######    | 1805/3000 [42:11<20:39,  1.04s/it, lr: 1.0e-04 loss: 4.769e-01]
latex_v1:  60%|######    | 1806/3000 [42:11<25:19,  1.27s/it, lr: 1.0e-04 loss: 4.769e-01]
latex_v1:  60%|######    | 1806/3000 [42:11<25:19,  1.27s/it, lr: 1.0e-04 loss: 4.769e-01]
latex_v1:  60%|######    | 1806/3000 [42:13<25:19,  1.27s/it, lr: 1.0e-04 loss: 7.006e-02]
latex_v1:  60%|######    | 1806/3000 [42:13<25:19,  1.27s/it, lr: 1.0e-04 loss: 7.006e-02]
latex_v1:  60%|######    | 1807/3000 [42:13<28:39,  1.44s/it, lr: 1.0e-04 loss: 7.006e-02]
latex_v1:  60%|######    | 1807/3000 [42:13<28:39,  1.44s/it, lr: 1.0e-04 loss: 7.006e-02]
latex_v1:  60%|######    | 1807/3000 [42:16<28:39,  1.44s/it, lr: 1.0e-04 loss: 7.523e-01]
latex_v1:  60%|######    | 1807/3000 [42:16<28:39,  1.44s/it, lr: 1.0e-04 loss: 7.523e-01]
latex_v1:  60%|######    | 1808/3000 [42:16<36:42,  1.85s/it, lr: 1.0e-04 loss: 7.523e-01]
latex_v1:  60%|######    | 1808/3000 [42:16<36:42,  1.85s/it, lr: 1.0e-04 loss: 7.523e-01]
latex_v1:  60%|######    | 1808/3000 [42:19<36:42,  1.85s/it, lr: 1.0e-04 loss: 1.171e-01]
latex_v1:  60%|######    | 1808/3000 [42:19<36:42,  1.85s/it, lr: 1.0e-04 loss: 1.171e-01]
latex_v1:  60%|######    | 1809/3000 [42:19<42:42,  2.15s/it, lr: 1.0e-04 loss: 1.171e-01]
latex_v1:  60%|######    | 1809/3000 [42:19<42:42,  2.15s/it, lr: 1.0e-04 loss: 1.171e-01]
latex_v1:  60%|######    | 1809/3000 [42:20<42:42,  2.15s/it, lr: 1.0e-04 loss: 5.947e-01]
latex_v1:  60%|######    | 1809/3000 [42:20<42:42,  2.15s/it, lr: 1.0e-04 loss: 5.947e-01]
latex_v1:  60%|######    | 1810/3000 [42:21<42:39,  2.15s/it, lr: 1.0e-04 loss: 1.840e-01]
latex_v1:  60%|######    | 1810/3000 [42:21<42:39,  2.15s/it, lr: 1.0e-04 loss: 1.840e-01]
latex_v1:  60%|######    | 1811/3000 [42:21<26:30,  1.34s/it, lr: 1.0e-04 loss: 1.840e-01]
latex_v1:  60%|######    | 1811/3000 [42:21<26:30,  1.34s/it, lr: 1.0e-04 loss: 1.840e-01]
latex_v1:  60%|######    | 1811/3000 [42:23<26:30,  1.34s/it, lr: 1.0e-04 loss: 4.551e-01]
latex_v1:  60%|######    | 1811/3000 [42:23<26:30,  1.34s/it, lr: 1.0e-04 loss: 4.551e-01]
latex_v1:  60%|######    | 1812/3000 [42:23<27:30,  1.39s/it, lr: 1.0e-04 loss: 4.551e-01]
latex_v1:  60%|######    | 1812/3000 [42:23<27:30,  1.39s/it, lr: 1.0e-04 loss: 4.551e-01]
latex_v1:  60%|######    | 1812/3000 [42:23<27:30,  1.39s/it, lr: 1.0e-04 loss: 2.667e-01]
latex_v1:  60%|######    | 1812/3000 [42:23<27:30,  1.39s/it, lr: 1.0e-04 loss: 2.667e-01]
latex_v1:  60%|######    | 1813/3000 [42:23<25:19,  1.28s/it, lr: 1.0e-04 loss: 2.667e-01]
latex_v1:  60%|######    | 1813/3000 [42:23<25:19,  1.28s/it, lr: 1.0e-04 loss: 2.667e-01]
latex_v1:  60%|######    | 1813/3000 [42:25<25:19,  1.28s/it, lr: 1.0e-04 loss: 4.949e-01]
latex_v1:  60%|######    | 1813/3000 [42:25<25:19,  1.28s/it, lr: 1.0e-04 loss: 4.949e-01]
latex_v1:  60%|######    | 1814/3000 [42:25<26:07,  1.32s/it, lr: 1.0e-04 loss: 4.949e-01]
latex_v1:  60%|######    | 1814/3000 [42:25<26:07,  1.32s/it, lr: 1.0e-04 loss: 4.949e-01]
latex_v1:  60%|######    | 1814/3000 [42:26<26:07,  1.32s/it, lr: 1.0e-04 loss: 7.495e-01]
latex_v1:  60%|######    | 1814/3000 [42:26<26:07,  1.32s/it, lr: 1.0e-04 loss: 7.495e-01]
latex_v1:  60%|######    | 1815/3000 [42:26<26:29,  1.34s/it, lr: 1.0e-04 loss: 7.495e-01]
latex_v1:  60%|######    | 1815/3000 [42:26<26:29,  1.34s/it, lr: 1.0e-04 loss: 7.495e-01]
latex_v1:  60%|######    | 1815/3000 [42:28<26:29,  1.34s/it, lr: 1.0e-04 loss: 5.746e-02]
latex_v1:  60%|######    | 1815/3000 [42:28<26:29,  1.34s/it, lr: 1.0e-04 loss: 5.746e-02]
latex_v1:  61%|######    | 1816/3000 [42:28<29:22,  1.49s/it, lr: 1.0e-04 loss: 5.746e-02]
latex_v1:  61%|######    | 1816/3000 [42:28<29:22,  1.49s/it, lr: 1.0e-04 loss: 5.746e-02]
latex_v1:  61%|######    | 1816/3000 [42:29<29:22,  1.49s/it, lr: 1.0e-04 loss: 3.227e-01]
latex_v1:  61%|######    | 1816/3000 [42:29<29:22,  1.49s/it, lr: 1.0e-04 loss: 3.227e-01]
latex_v1:  61%|######    | 1817/3000 [42:29<28:22,  1.44s/it, lr: 1.0e-04 loss: 3.227e-01]
latex_v1:  61%|######    | 1817/3000 [42:29<28:22,  1.44s/it, lr: 1.0e-04 loss: 3.227e-01]
latex_v1:  61%|######    | 1817/3000 [42:30<28:22,  1.44s/it, lr: 1.0e-04 loss: 8.605e-01]
latex_v1:  61%|######    | 1817/3000 [42:30<28:22,  1.44s/it, lr: 1.0e-04 loss: 8.605e-01]
latex_v1:  61%|######    | 1818/3000 [42:30<24:19,  1.24s/it, lr: 1.0e-04 loss: 8.605e-01]
latex_v1:  61%|######    | 1818/3000 [42:30<24:19,  1.24s/it, lr: 1.0e-04 loss: 8.605e-01]
latex_v1:  61%|######    | 1818/3000 [42:32<24:19,  1.24s/it, lr: 1.0e-04 loss: 4.195e-01]
latex_v1:  61%|######    | 1818/3000 [42:32<24:19,  1.24s/it, lr: 1.0e-04 loss: 4.195e-01]
latex_v1:  61%|######    | 1819/3000 [42:32<25:18,  1.29s/it, lr: 1.0e-04 loss: 4.195e-01]
latex_v1:  61%|######    | 1819/3000 [42:32<25:18,  1.29s/it, lr: 1.0e-04 loss: 4.195e-01]
latex_v1:  61%|######    | 1819/3000 [42:32<25:18,  1.29s/it, lr: 1.0e-04 loss: 6.069e-01]
latex_v1:  61%|######    | 1819/3000 [42:32<25:18,  1.29s/it, lr: 1.0e-04 loss: 6.069e-01]
latex_v1:  61%|######    | 1820/3000 [42:33<25:16,  1.29s/it, lr: 1.0e-04 loss: 5.299e-01]
latex_v1:  61%|######    | 1820/3000 [42:33<25:16,  1.29s/it, lr: 1.0e-04 loss: 5.299e-01]
latex_v1:  61%|######    | 1821/3000 [42:33<17:03,  1.15it/s, lr: 1.0e-04 loss: 5.299e-01]
latex_v1:  61%|######    | 1821/3000 [42:33<17:03,  1.15it/s, lr: 1.0e-04 loss: 5.299e-01]
latex_v1:  61%|######    | 1821/3000 [42:34<17:03,  1.15it/s, lr: 1.0e-04 loss: 2.555e-01]
latex_v1:  61%|######    | 1821/3000 [42:34<17:03,  1.15it/s, lr: 1.0e-04 loss: 2.555e-01]
latex_v1:  61%|######    | 1822/3000 [42:34<18:29,  1.06it/s, lr: 1.0e-04 loss: 2.555e-01]
latex_v1:  61%|######    | 1822/3000 [42:34<18:29,  1.06it/s, lr: 1.0e-04 loss: 2.555e-01]
latex_v1:  61%|######    | 1822/3000 [42:35<18:29,  1.06it/s, lr: 1.0e-04 loss: 1.000e-01]
latex_v1:  61%|######    | 1822/3000 [42:35<18:29,  1.06it/s, lr: 1.0e-04 loss: 1.000e-01]
latex_v1:  61%|######    | 1823/3000 [42:35<17:25,  1.13it/s, lr: 1.0e-04 loss: 1.000e-01]
latex_v1:  61%|######    | 1823/3000 [42:35<17:25,  1.13it/s, lr: 1.0e-04 loss: 1.000e-01]
latex_v1:  61%|######    | 1823/3000 [42:36<17:25,  1.13it/s, lr: 1.0e-04 loss: 3.598e-01]
latex_v1:  61%|######    | 1823/3000 [42:36<17:25,  1.13it/s, lr: 1.0e-04 loss: 3.598e-01]
latex_v1:  61%|######    | 1824/3000 [42:36<18:51,  1.04it/s, lr: 1.0e-04 loss: 3.598e-01]
latex_v1:  61%|######    | 1824/3000 [42:36<18:51,  1.04it/s, lr: 1.0e-04 loss: 3.598e-01]
latex_v1:  61%|######    | 1824/3000 [42:37<18:51,  1.04it/s, lr: 1.0e-04 loss: 8.876e-01]
latex_v1:  61%|######    | 1824/3000 [42:37<18:51,  1.04it/s, lr: 1.0e-04 loss: 8.876e-01]
latex_v1:  61%|######    | 1825/3000 [42:37<19:56,  1.02s/it, lr: 1.0e-04 loss: 8.876e-01]
latex_v1:  61%|######    | 1825/3000 [42:37<19:56,  1.02s/it, lr: 1.0e-04 loss: 8.876e-01]
latex_v1:  61%|######    | 1825/3000 [42:38<19:56,  1.02s/it, lr: 1.0e-04 loss: 2.590e-01]
latex_v1:  61%|######    | 1825/3000 [42:38<19:56,  1.02s/it, lr: 1.0e-04 loss: 2.590e-01]
latex_v1:  61%|######    | 1826/3000 [42:38<18:25,  1.06it/s, lr: 1.0e-04 loss: 2.590e-01]
latex_v1:  61%|######    | 1826/3000 [42:38<18:25,  1.06it/s, lr: 1.0e-04 loss: 2.590e-01]
latex_v1:  61%|######    | 1826/3000 [42:39<18:25,  1.06it/s, lr: 1.0e-04 loss: 2.100e-01]
latex_v1:  61%|######    | 1826/3000 [42:39<18:25,  1.06it/s, lr: 1.0e-04 loss: 2.100e-01]
latex_v1:  61%|######    | 1827/3000 [42:39<17:22,  1.13it/s, lr: 1.0e-04 loss: 2.100e-01]
latex_v1:  61%|######    | 1827/3000 [42:39<17:22,  1.13it/s, lr: 1.0e-04 loss: 2.100e-01]
latex_v1:  61%|######    | 1827/3000 [42:42<17:22,  1.13it/s, lr: 1.0e-04 loss: 1.116e-01]
latex_v1:  61%|######    | 1827/3000 [42:42<17:22,  1.13it/s, lr: 1.0e-04 loss: 1.116e-01]
latex_v1:  61%|######    | 1828/3000 [42:42<29:17,  1.50s/it, lr: 1.0e-04 loss: 1.116e-01]
latex_v1:  61%|######    | 1828/3000 [42:42<29:17,  1.50s/it, lr: 1.0e-04 loss: 1.116e-01]
latex_v1:  61%|######    | 1828/3000 [42:43<29:17,  1.50s/it, lr: 1.0e-04 loss: 5.361e-01]
latex_v1:  61%|######    | 1828/3000 [42:43<29:17,  1.50s/it, lr: 1.0e-04 loss: 5.361e-01]
latex_v1:  61%|######    | 1829/3000 [42:43<29:25,  1.51s/it, lr: 1.0e-04 loss: 5.361e-01]
latex_v1:  61%|######    | 1829/3000 [42:43<29:25,  1.51s/it, lr: 1.0e-04 loss: 5.361e-01]
latex_v1:  61%|######    | 1829/3000 [42:45<29:25,  1.51s/it, lr: 1.0e-04 loss: 4.517e-01]
latex_v1:  61%|######    | 1829/3000 [42:45<29:25,  1.51s/it, lr: 1.0e-04 loss: 4.517e-01]
latex_v1:  61%|######1   | 1830/3000 [42:46<29:23,  1.51s/it, lr: 1.0e-04 loss: 5.014e-01]
latex_v1:  61%|######1   | 1830/3000 [42:46<29:23,  1.51s/it, lr: 1.0e-04 loss: 5.014e-01]
latex_v1:  61%|######1   | 1831/3000 [42:46<22:53,  1.18s/it, lr: 1.0e-04 loss: 5.014e-01]
latex_v1:  61%|######1   | 1831/3000 [42:46<22:53,  1.18s/it, lr: 1.0e-04 loss: 5.014e-01]
latex_v1:  61%|######1   | 1831/3000 [42:49<22:53,  1.18s/it, lr: 1.0e-04 loss: 6.882e-01]
latex_v1:  61%|######1   | 1831/3000 [42:49<22:53,  1.18s/it, lr: 1.0e-04 loss: 6.882e-01]
latex_v1:  61%|######1   | 1832/3000 [42:49<30:09,  1.55s/it, lr: 1.0e-04 loss: 6.882e-01]
latex_v1:  61%|######1   | 1832/3000 [42:49<30:09,  1.55s/it, lr: 1.0e-04 loss: 6.882e-01]
latex_v1:  61%|######1   | 1832/3000 [42:51<30:09,  1.55s/it, lr: 1.0e-04 loss: 1.279e-01]
latex_v1:  61%|######1   | 1832/3000 [42:51<30:09,  1.55s/it, lr: 1.0e-04 loss: 1.279e-01]
latex_v1:  61%|######1   | 1833/3000 [42:51<30:03,  1.55s/it, lr: 1.0e-04 loss: 1.279e-01]
latex_v1:  61%|######1   | 1833/3000 [42:51<30:03,  1.55s/it, lr: 1.0e-04 loss: 1.279e-01]
latex_v1:  61%|######1   | 1833/3000 [42:51<30:03,  1.55s/it, lr: 1.0e-04 loss: 3.901e-01]
latex_v1:  61%|######1   | 1833/3000 [42:51<30:03,  1.55s/it, lr: 1.0e-04 loss: 3.901e-01]
latex_v1:  61%|######1   | 1834/3000 [42:51<25:45,  1.33s/it, lr: 1.0e-04 loss: 3.901e-01]
latex_v1:  61%|######1   | 1834/3000 [42:51<25:45,  1.33s/it, lr: 1.0e-04 loss: 3.901e-01]
latex_v1:  61%|######1   | 1834/3000 [42:52<25:45,  1.33s/it, lr: 1.0e-04 loss: 1.352e-01]
latex_v1:  61%|######1   | 1834/3000 [42:52<25:45,  1.33s/it, lr: 1.0e-04 loss: 1.352e-01]
latex_v1:  61%|######1   | 1835/3000 [42:52<22:43,  1.17s/it, lr: 1.0e-04 loss: 1.352e-01]
latex_v1:  61%|######1   | 1835/3000 [42:52<22:43,  1.17s/it, lr: 1.0e-04 loss: 1.352e-01]
latex_v1:  61%|######1   | 1835/3000 [42:53<22:43,  1.17s/it, lr: 1.0e-04 loss: 3.708e-01]
latex_v1:  61%|######1   | 1835/3000 [42:53<22:43,  1.17s/it, lr: 1.0e-04 loss: 3.708e-01]
latex_v1:  61%|######1   | 1836/3000 [42:53<20:21,  1.05s/it, lr: 1.0e-04 loss: 3.708e-01]
latex_v1:  61%|######1   | 1836/3000 [42:53<20:21,  1.05s/it, lr: 1.0e-04 loss: 3.708e-01]
latex_v1:  61%|######1   | 1836/3000 [42:54<20:21,  1.05s/it, lr: 1.0e-04 loss: 1.192e-01]
latex_v1:  61%|######1   | 1836/3000 [42:54<20:21,  1.05s/it, lr: 1.0e-04 loss: 1.192e-01]
latex_v1:  61%|######1   | 1837/3000 [42:54<18:40,  1.04it/s, lr: 1.0e-04 loss: 1.192e-01]
latex_v1:  61%|######1   | 1837/3000 [42:54<18:40,  1.04it/s, lr: 1.0e-04 loss: 1.192e-01]
latex_v1:  61%|######1   | 1837/3000 [42:56<18:40,  1.04it/s, lr: 1.0e-04 loss: 6.208e-01]
latex_v1:  61%|######1   | 1837/3000 [42:56<18:40,  1.04it/s, lr: 1.0e-04 loss: 6.208e-01]
latex_v1:  61%|######1   | 1838/3000 [42:56<23:53,  1.23s/it, lr: 1.0e-04 loss: 6.208e-01]
latex_v1:  61%|######1   | 1838/3000 [42:56<23:53,  1.23s/it, lr: 1.0e-04 loss: 6.208e-01]
latex_v1:  61%|######1   | 1838/3000 [42:56<23:53,  1.23s/it, lr: 1.0e-04 loss: 6.693e-01]
latex_v1:  61%|######1   | 1838/3000 [42:56<23:53,  1.23s/it, lr: 1.0e-04 loss: 6.693e-01]
latex_v1:  61%|######1   | 1839/3000 [42:56<21:05,  1.09s/it, lr: 1.0e-04 loss: 6.693e-01]
latex_v1:  61%|######1   | 1839/3000 [42:56<21:05,  1.09s/it, lr: 1.0e-04 loss: 6.693e-01]
latex_v1:  61%|######1   | 1839/3000 [42:58<21:05,  1.09s/it, lr: 1.0e-04 loss: 2.654e-01]
latex_v1:  61%|######1   | 1839/3000 [42:58<21:05,  1.09s/it, lr: 1.0e-04 loss: 2.654e-01]
latex_v1:  61%|######1   | 1840/3000 [43:00<21:04,  1.09s/it, lr: 1.0e-04 loss: 5.238e-01]
latex_v1:  61%|######1   | 1840/3000 [43:00<21:04,  1.09s/it, lr: 1.0e-04 loss: 5.238e-01]
latex_v1:  61%|######1   | 1841/3000 [43:00<18:12,  1.06it/s, lr: 1.0e-04 loss: 5.238e-01]
latex_v1:  61%|######1   | 1841/3000 [43:00<18:12,  1.06it/s, lr: 1.0e-04 loss: 5.238e-01]
latex_v1:  61%|######1   | 1841/3000 [43:01<18:12,  1.06it/s, lr: 1.0e-04 loss: 3.191e-01]
latex_v1:  61%|######1   | 1841/3000 [43:01<18:12,  1.06it/s, lr: 1.0e-04 loss: 3.191e-01]
latex_v1:  61%|######1   | 1842/3000 [43:01<18:22,  1.05it/s, lr: 1.0e-04 loss: 3.191e-01]
latex_v1:  61%|######1   | 1842/3000 [43:01<18:22,  1.05it/s, lr: 1.0e-04 loss: 3.191e-01]
latex_v1:  61%|######1   | 1842/3000 [43:02<18:22,  1.05it/s, lr: 1.0e-04 loss: 1.803e-01]
latex_v1:  61%|######1   | 1842/3000 [43:02<18:22,  1.05it/s, lr: 1.0e-04 loss: 1.803e-01]
latex_v1:  61%|######1   | 1843/3000 [43:02<19:27,  1.01s/it, lr: 1.0e-04 loss: 1.803e-01]
latex_v1:  61%|######1   | 1843/3000 [43:02<19:27,  1.01s/it, lr: 1.0e-04 loss: 1.803e-01]
latex_v1:  61%|######1   | 1843/3000 [43:03<19:27,  1.01s/it, lr: 1.0e-04 loss: 5.096e-01]
latex_v1:  61%|######1   | 1843/3000 [43:03<19:27,  1.01s/it, lr: 1.0e-04 loss: 5.096e-01]
latex_v1:  61%|######1   | 1844/3000 [43:03<22:07,  1.15s/it, lr: 1.0e-04 loss: 5.096e-01]
latex_v1:  61%|######1   | 1844/3000 [43:03<22:07,  1.15s/it, lr: 1.0e-04 loss: 5.096e-01]
latex_v1:  61%|######1   | 1844/3000 [43:05<22:07,  1.15s/it, lr: 1.0e-04 loss: 6.581e-01]
latex_v1:  61%|######1   | 1844/3000 [43:05<22:07,  1.15s/it, lr: 1.0e-04 loss: 6.581e-01]
latex_v1:  62%|######1   | 1845/3000 [43:05<23:37,  1.23s/it, lr: 1.0e-04 loss: 6.581e-01]
latex_v1:  62%|######1   | 1845/3000 [43:05<23:37,  1.23s/it, lr: 1.0e-04 loss: 6.581e-01]
latex_v1:  62%|######1   | 1845/3000 [43:07<23:37,  1.23s/it, lr: 1.0e-04 loss: 2.340e-02]
latex_v1:  62%|######1   | 1845/3000 [43:07<23:37,  1.23s/it, lr: 1.0e-04 loss: 2.340e-02]
latex_v1:  62%|######1   | 1846/3000 [43:07<25:54,  1.35s/it, lr: 1.0e-04 loss: 2.340e-02]
latex_v1:  62%|######1   | 1846/3000 [43:07<25:54,  1.35s/it, lr: 1.0e-04 loss: 2.340e-02]
latex_v1:  62%|######1   | 1846/3000 [43:07<25:54,  1.35s/it, lr: 1.0e-04 loss: 2.868e-01]
latex_v1:  62%|######1   | 1846/3000 [43:07<25:54,  1.35s/it, lr: 1.0e-04 loss: 2.868e-01]
latex_v1:  62%|######1   | 1847/3000 [43:07<22:30,  1.17s/it, lr: 1.0e-04 loss: 2.868e-01]
latex_v1:  62%|######1   | 1847/3000 [43:07<22:30,  1.17s/it, lr: 1.0e-04 loss: 2.868e-01]
latex_v1:  62%|######1   | 1847/3000 [43:08<22:30,  1.17s/it, lr: 1.0e-04 loss: 5.475e-01]
latex_v1:  62%|######1   | 1847/3000 [43:08<22:30,  1.17s/it, lr: 1.0e-04 loss: 5.475e-01]
latex_v1:  62%|######1   | 1848/3000 [43:08<20:12,  1.05s/it, lr: 1.0e-04 loss: 5.475e-01]
latex_v1:  62%|######1   | 1848/3000 [43:08<20:12,  1.05s/it, lr: 1.0e-04 loss: 5.475e-01]
latex_v1:  62%|######1   | 1848/3000 [43:09<20:12,  1.05s/it, lr: 1.0e-04 loss: 2.427e-01]
latex_v1:  62%|######1   | 1848/3000 [43:09<20:12,  1.05s/it, lr: 1.0e-04 loss: 2.427e-01]
latex_v1:  62%|######1   | 1849/3000 [43:09<20:10,  1.05s/it, lr: 1.0e-04 loss: 2.427e-01]
latex_v1:  62%|######1   | 1849/3000 [43:09<20:10,  1.05s/it, lr: 1.0e-04 loss: 2.427e-01]
latex_v1:  62%|######1   | 1849/3000 [43:10<20:10,  1.05s/it, lr: 1.0e-04 loss: 1.490e-01]
latex_v1:  62%|######1   | 1849/3000 [43:10<20:10,  1.05s/it, lr: 1.0e-04 loss: 1.490e-01]
latex_v1:  62%|######1   | 1850/3000 [43:11<20:08,  1.05s/it, lr: 1.0e-04 loss: 2.211e-01]
latex_v1:  62%|######1   | 1850/3000 [43:11<20:08,  1.05s/it, lr: 1.0e-04 loss: 2.211e-01]
latex_v1:  62%|######1   | 1851/3000 [43:11<17:06,  1.12it/s, lr: 1.0e-04 loss: 2.211e-01]
latex_v1:  62%|######1   | 1851/3000 [43:11<17:06,  1.12it/s, lr: 1.0e-04 loss: 2.211e-01]
latex_v1:  62%|######1   | 1851/3000 [43:12<17:06,  1.12it/s, lr: 1.0e-04 loss: 2.779e-01]
latex_v1:  62%|######1   | 1851/3000 [43:12<17:06,  1.12it/s, lr: 1.0e-04 loss: 2.779e-01]
latex_v1:  62%|######1   | 1852/3000 [43:12<16:21,  1.17it/s, lr: 1.0e-04 loss: 2.779e-01]
latex_v1:  62%|######1   | 1852/3000 [43:12<16:21,  1.17it/s, lr: 1.0e-04 loss: 2.779e-01]
latex_v1:  62%|######1   | 1852/3000 [43:13<16:21,  1.17it/s, lr: 1.0e-04 loss: 5.460e-01]
latex_v1:  62%|######1   | 1852/3000 [43:13<16:21,  1.17it/s, lr: 1.0e-04 loss: 5.460e-01]
latex_v1:  62%|######1   | 1853/3000 [43:13<15:50,  1.21it/s, lr: 1.0e-04 loss: 5.460e-01]
latex_v1:  62%|######1   | 1853/3000 [43:13<15:50,  1.21it/s, lr: 1.0e-04 loss: 5.460e-01]
latex_v1:  62%|######1   | 1853/3000 [43:14<15:50,  1.21it/s, lr: 1.0e-04 loss: 3.123e-01]
latex_v1:  62%|######1   | 1853/3000 [43:14<15:50,  1.21it/s, lr: 1.0e-04 loss: 3.123e-01]
latex_v1:  62%|######1   | 1854/3000 [43:14<18:37,  1.03it/s, lr: 1.0e-04 loss: 3.123e-01]
latex_v1:  62%|######1   | 1854/3000 [43:14<18:37,  1.03it/s, lr: 1.0e-04 loss: 3.123e-01]
latex_v1:  62%|######1   | 1854/3000 [43:16<18:37,  1.03it/s, lr: 1.0e-04 loss: 5.203e-01]
latex_v1:  62%|######1   | 1854/3000 [43:16<18:37,  1.03it/s, lr: 1.0e-04 loss: 5.203e-01]
latex_v1:  62%|######1   | 1855/3000 [43:16<22:45,  1.19s/it, lr: 1.0e-04 loss: 5.203e-01]
latex_v1:  62%|######1   | 1855/3000 [43:16<22:45,  1.19s/it, lr: 1.0e-04 loss: 5.203e-01]
latex_v1:  62%|######1   | 1855/3000 [43:17<22:45,  1.19s/it, lr: 1.0e-04 loss: 8.501e-01]
latex_v1:  62%|######1   | 1855/3000 [43:17<22:45,  1.19s/it, lr: 1.0e-04 loss: 8.501e-01]
latex_v1:  62%|######1   | 1856/3000 [43:17<21:27,  1.13s/it, lr: 1.0e-04 loss: 8.501e-01]
latex_v1:  62%|######1   | 1856/3000 [43:17<21:27,  1.13s/it, lr: 1.0e-04 loss: 8.501e-01]
latex_v1:  62%|######1   | 1856/3000 [43:18<21:27,  1.13s/it, lr: 1.0e-04 loss: 1.497e-01]
latex_v1:  62%|######1   | 1856/3000 [43:18<21:27,  1.13s/it, lr: 1.0e-04 loss: 1.497e-01]
latex_v1:  62%|######1   | 1857/3000 [43:18<23:42,  1.24s/it, lr: 1.0e-04 loss: 1.497e-01]
latex_v1:  62%|######1   | 1857/3000 [43:18<23:42,  1.24s/it, lr: 1.0e-04 loss: 1.497e-01]
latex_v1:  62%|######1   | 1857/3000 [43:20<23:42,  1.24s/it, lr: 1.0e-04 loss: 4.030e-01]
latex_v1:  62%|######1   | 1857/3000 [43:20<23:42,  1.24s/it, lr: 1.0e-04 loss: 4.030e-01]
latex_v1:  62%|######1   | 1858/3000 [43:20<24:04,  1.26s/it, lr: 1.0e-04 loss: 4.030e-01]
latex_v1:  62%|######1   | 1858/3000 [43:20<24:04,  1.26s/it, lr: 1.0e-04 loss: 4.030e-01]
latex_v1:  62%|######1   | 1858/3000 [43:20<24:04,  1.26s/it, lr: 1.0e-04 loss: 1.348e-01]
latex_v1:  62%|######1   | 1858/3000 [43:20<24:04,  1.26s/it, lr: 1.0e-04 loss: 1.348e-01]
latex_v1:  62%|######1   | 1859/3000 [43:20<21:10,  1.11s/it, lr: 1.0e-04 loss: 1.348e-01]
latex_v1:  62%|######1   | 1859/3000 [43:20<21:10,  1.11s/it, lr: 1.0e-04 loss: 1.348e-01]
latex_v1:  62%|######1   | 1859/3000 [43:23<21:10,  1.11s/it, lr: 1.0e-04 loss: 5.793e-01]
latex_v1:  62%|######1   | 1859/3000 [43:23<21:10,  1.11s/it, lr: 1.0e-04 loss: 5.793e-01]
latex_v1:  62%|######2   | 1860/3000 [43:24<21:09,  1.11s/it, lr: 1.0e-04 loss: 6.744e-01]
latex_v1:  62%|######2   | 1860/3000 [43:24<21:09,  1.11s/it, lr: 1.0e-04 loss: 6.744e-01]
latex_v1:  62%|######2   | 1861/3000 [43:24<18:05,  1.05it/s, lr: 1.0e-04 loss: 6.744e-01]
latex_v1:  62%|######2   | 1861/3000 [43:24<18:05,  1.05it/s, lr: 1.0e-04 loss: 6.744e-01]
latex_v1:  62%|######2   | 1861/3000 [43:27<18:05,  1.05it/s, lr: 1.0e-04 loss: 1.347e-01]
latex_v1:  62%|######2   | 1861/3000 [43:27<18:05,  1.05it/s, lr: 1.0e-04 loss: 1.347e-01]
latex_v1:  62%|######2   | 1862/3000 [43:27<26:51,  1.42s/it, lr: 1.0e-04 loss: 1.347e-01]
latex_v1:  62%|######2   | 1862/3000 [43:27<26:51,  1.42s/it, lr: 1.0e-04 loss: 1.347e-01]
latex_v1:  62%|######2   | 1862/3000 [43:28<26:51,  1.42s/it, lr: 1.0e-04 loss: 6.071e-01]
latex_v1:  62%|######2   | 1862/3000 [43:28<26:51,  1.42s/it, lr: 1.0e-04 loss: 6.071e-01]
latex_v1:  62%|######2   | 1863/3000 [43:28<25:06,  1.32s/it, lr: 1.0e-04 loss: 6.071e-01]
latex_v1:  62%|######2   | 1863/3000 [43:28<25:06,  1.32s/it, lr: 1.0e-04 loss: 6.071e-01]
latex_v1:  62%|######2   | 1863/3000 [43:29<25:06,  1.32s/it, lr: 1.0e-04 loss: 1.605e-01]
latex_v1:  62%|######2   | 1863/3000 [43:29<25:06,  1.32s/it, lr: 1.0e-04 loss: 1.605e-01]
latex_v1:  62%|######2   | 1864/3000 [43:29<22:10,  1.17s/it, lr: 1.0e-04 loss: 1.605e-01]
latex_v1:  62%|######2   | 1864/3000 [43:29<22:10,  1.17s/it, lr: 1.0e-04 loss: 1.605e-01]
latex_v1:  62%|######2   | 1864/3000 [43:29<22:10,  1.17s/it, lr: 1.0e-04 loss: 2.634e-01]
latex_v1:  62%|######2   | 1864/3000 [43:29<22:10,  1.17s/it, lr: 1.0e-04 loss: 2.634e-01]
latex_v1:  62%|######2   | 1865/3000 [43:29<19:59,  1.06s/it, lr: 1.0e-04 loss: 2.634e-01]
latex_v1:  62%|######2   | 1865/3000 [43:29<19:59,  1.06s/it, lr: 1.0e-04 loss: 2.634e-01]
latex_v1:  62%|######2   | 1865/3000 [43:30<19:59,  1.06s/it, lr: 1.0e-04 loss: 3.037e-01]
latex_v1:  62%|######2   | 1865/3000 [43:30<19:59,  1.06s/it, lr: 1.0e-04 loss: 3.037e-01]
latex_v1:  62%|######2   | 1866/3000 [43:30<18:20,  1.03it/s, lr: 1.0e-04 loss: 3.037e-01]
latex_v1:  62%|######2   | 1866/3000 [43:30<18:20,  1.03it/s, lr: 1.0e-04 loss: 3.037e-01]
latex_v1:  62%|######2   | 1866/3000 [43:32<18:20,  1.03it/s, lr: 1.0e-04 loss: 3.610e-01]
latex_v1:  62%|######2   | 1866/3000 [43:32<18:20,  1.03it/s, lr: 1.0e-04 loss: 3.610e-01]
latex_v1:  62%|######2   | 1867/3000 [43:32<20:55,  1.11s/it, lr: 1.0e-04 loss: 3.610e-01]
latex_v1:  62%|######2   | 1867/3000 [43:32<20:55,  1.11s/it, lr: 1.0e-04 loss: 3.610e-01]
latex_v1:  62%|######2   | 1867/3000 [43:33<20:55,  1.11s/it, lr: 1.0e-04 loss: 5.920e-02]
latex_v1:  62%|######2   | 1867/3000 [43:33<20:55,  1.11s/it, lr: 1.0e-04 loss: 5.920e-02]
latex_v1:  62%|######2   | 1868/3000 [43:33<24:40,  1.31s/it, lr: 1.0e-04 loss: 5.920e-02]
latex_v1:  62%|######2   | 1868/3000 [43:33<24:40,  1.31s/it, lr: 1.0e-04 loss: 5.920e-02]
latex_v1:  62%|######2   | 1868/3000 [43:35<24:40,  1.31s/it, lr: 1.0e-04 loss: 6.734e-01]
latex_v1:  62%|######2   | 1868/3000 [43:35<24:40,  1.31s/it, lr: 1.0e-04 loss: 6.734e-01]
latex_v1:  62%|######2   | 1869/3000 [43:35<27:55,  1.48s/it, lr: 1.0e-04 loss: 6.734e-01]
latex_v1:  62%|######2   | 1869/3000 [43:35<27:55,  1.48s/it, lr: 1.0e-04 loss: 6.734e-01]
latex_v1:  62%|######2   | 1869/3000 [43:37<27:55,  1.48s/it, lr: 1.0e-04 loss: 2.483e-01]
latex_v1:  62%|######2   | 1869/3000 [43:37<27:55,  1.48s/it, lr: 1.0e-04 loss: 2.483e-01]
latex_v1:  62%|######2   | 1870/3000 [43:38<27:54,  1.48s/it, lr: 1.0e-04 loss: 4.557e-01]
latex_v1:  62%|######2   | 1870/3000 [43:38<27:54,  1.48s/it, lr: 1.0e-04 loss: 4.557e-01]
latex_v1:  62%|######2   | 1871/3000 [43:38<18:23,  1.02it/s, lr: 1.0e-04 loss: 4.557e-01]
latex_v1:  62%|######2   | 1871/3000 [43:38<18:23,  1.02it/s, lr: 1.0e-04 loss: 4.557e-01]
latex_v1:  62%|######2   | 1871/3000 [43:39<18:23,  1.02it/s, lr: 1.0e-04 loss: 6.133e-01]
latex_v1:  62%|######2   | 1871/3000 [43:39<18:23,  1.02it/s, lr: 1.0e-04 loss: 6.133e-01]
latex_v1:  62%|######2   | 1872/3000 [43:39<20:58,  1.12s/it, lr: 1.0e-04 loss: 6.133e-01]
latex_v1:  62%|######2   | 1872/3000 [43:39<20:58,  1.12s/it, lr: 1.0e-04 loss: 6.133e-01]
latex_v1:  62%|######2   | 1872/3000 [43:41<20:58,  1.12s/it, lr: 1.0e-04 loss: 6.956e-02]
latex_v1:  62%|######2   | 1872/3000 [43:41<20:58,  1.12s/it, lr: 1.0e-04 loss: 6.956e-02]
latex_v1:  62%|######2   | 1873/3000 [43:41<21:12,  1.13s/it, lr: 1.0e-04 loss: 6.956e-02]
latex_v1:  62%|######2   | 1873/3000 [43:41<21:12,  1.13s/it, lr: 1.0e-04 loss: 6.956e-02]
latex_v1:  62%|######2   | 1873/3000 [43:41<21:12,  1.13s/it, lr: 1.0e-04 loss: 5.963e-01]
latex_v1:  62%|######2   | 1873/3000 [43:41<21:12,  1.13s/it, lr: 1.0e-04 loss: 5.963e-01]
latex_v1:  62%|######2   | 1874/3000 [43:41<19:14,  1.03s/it, lr: 1.0e-04 loss: 5.963e-01]
latex_v1:  62%|######2   | 1874/3000 [43:41<19:14,  1.03s/it, lr: 1.0e-04 loss: 5.963e-01]
latex_v1:  62%|######2   | 1874/3000 [43:42<19:14,  1.03s/it, lr: 1.0e-04 loss: 6.847e-01]
latex_v1:  62%|######2   | 1874/3000 [43:42<19:14,  1.03s/it, lr: 1.0e-04 loss: 6.847e-01]
latex_v1:  62%|######2   | 1875/3000 [43:42<17:49,  1.05it/s, lr: 1.0e-04 loss: 6.847e-01]
latex_v1:  62%|######2   | 1875/3000 [43:42<17:49,  1.05it/s, lr: 1.0e-04 loss: 6.847e-01]
latex_v1:  62%|######2   | 1875/3000 [43:43<17:49,  1.05it/s, lr: 1.0e-04 loss: 5.339e-01]
latex_v1:  62%|######2   | 1875/3000 [43:43<17:49,  1.05it/s, lr: 1.0e-04 loss: 5.339e-01]
latex_v1:  63%|######2   | 1876/3000 [43:43<20:17,  1.08s/it, lr: 1.0e-04 loss: 5.339e-01]
latex_v1:  63%|######2   | 1876/3000 [43:43<20:17,  1.08s/it, lr: 1.0e-04 loss: 5.339e-01]
latex_v1:  63%|######2   | 1876/3000 [43:45<20:17,  1.08s/it, lr: 1.0e-04 loss: 1.738e-01]
latex_v1:  63%|######2   | 1876/3000 [43:45<20:17,  1.08s/it, lr: 1.0e-04 loss: 1.738e-01]
latex_v1:  63%|######2   | 1877/3000 [43:45<22:42,  1.21s/it, lr: 1.0e-04 loss: 1.738e-01]
latex_v1:  63%|######2   | 1877/3000 [43:45<22:42,  1.21s/it, lr: 1.0e-04 loss: 1.738e-01]
latex_v1:  63%|######2   | 1877/3000 [43:46<22:42,  1.21s/it, lr: 1.0e-04 loss: 6.198e-01]
latex_v1:  63%|######2   | 1877/3000 [43:46<22:42,  1.21s/it, lr: 1.0e-04 loss: 6.198e-01]
latex_v1:  63%|######2   | 1878/3000 [43:46<20:10,  1.08s/it, lr: 1.0e-04 loss: 6.198e-01]
latex_v1:  63%|######2   | 1878/3000 [43:46<20:10,  1.08s/it, lr: 1.0e-04 loss: 6.198e-01]
latex_v1:  63%|######2   | 1878/3000 [43:47<20:10,  1.08s/it, lr: 1.0e-04 loss: 3.227e-01]
latex_v1:  63%|######2   | 1878/3000 [43:47<20:10,  1.08s/it, lr: 1.0e-04 loss: 3.227e-01]
latex_v1:  63%|######2   | 1879/3000 [43:47<22:09,  1.19s/it, lr: 1.0e-04 loss: 3.227e-01]
latex_v1:  63%|######2   | 1879/3000 [43:47<22:09,  1.19s/it, lr: 1.0e-04 loss: 3.227e-01]
latex_v1:  63%|######2   | 1879/3000 [43:48<22:09,  1.19s/it, lr: 1.0e-04 loss: 1.046e-01]
latex_v1:  63%|######2   | 1879/3000 [43:48<22:09,  1.19s/it, lr: 1.0e-04 loss: 1.046e-01]
latex_v1:  63%|######2   | 1880/3000 [43:50<22:08,  1.19s/it, lr: 1.0e-04 loss: 7.133e-01]
latex_v1:  63%|######2   | 1880/3000 [43:50<22:08,  1.19s/it, lr: 1.0e-04 loss: 7.133e-01]
latex_v1:  63%|######2   | 1881/3000 [43:50<17:42,  1.05it/s, lr: 1.0e-04 loss: 7.133e-01]
latex_v1:  63%|######2   | 1881/3000 [43:50<17:42,  1.05it/s, lr: 1.0e-04 loss: 7.133e-01]
latex_v1:  63%|######2   | 1881/3000 [43:53<17:42,  1.05it/s, lr: 1.0e-04 loss: 2.436e-01]
latex_v1:  63%|######2   | 1881/3000 [43:53<17:42,  1.05it/s, lr: 1.0e-04 loss: 2.436e-01]
latex_v1:  63%|######2   | 1882/3000 [43:53<26:43,  1.43s/it, lr: 1.0e-04 loss: 2.436e-01]
latex_v1:  63%|######2   | 1882/3000 [43:53<26:43,  1.43s/it, lr: 1.0e-04 loss: 2.436e-01]
latex_v1:  63%|######2   | 1882/3000 [43:54<26:43,  1.43s/it, lr: 1.0e-04 loss: 6.362e-01]
latex_v1:  63%|######2   | 1882/3000 [43:54<26:43,  1.43s/it, lr: 1.0e-04 loss: 6.362e-01]
latex_v1:  63%|######2   | 1883/3000 [43:54<27:09,  1.46s/it, lr: 1.0e-04 loss: 6.362e-01]
latex_v1:  63%|######2   | 1883/3000 [43:54<27:09,  1.46s/it, lr: 1.0e-04 loss: 6.362e-01]
latex_v1:  63%|######2   | 1883/3000 [43:56<27:09,  1.46s/it, lr: 1.0e-04 loss: 4.303e-01]
latex_v1:  63%|######2   | 1883/3000 [43:56<27:09,  1.46s/it, lr: 1.0e-04 loss: 4.303e-01]
latex_v1:  63%|######2   | 1884/3000 [43:56<27:36,  1.48s/it, lr: 1.0e-04 loss: 4.303e-01]
latex_v1:  63%|######2   | 1884/3000 [43:56<27:36,  1.48s/it, lr: 1.0e-04 loss: 4.303e-01]
latex_v1:  63%|######2   | 1884/3000 [43:57<27:36,  1.48s/it, lr: 1.0e-04 loss: 1.043e-01]
latex_v1:  63%|######2   | 1884/3000 [43:57<27:36,  1.48s/it, lr: 1.0e-04 loss: 1.043e-01]
latex_v1:  63%|######2   | 1885/3000 [43:57<27:51,  1.50s/it, lr: 1.0e-04 loss: 1.043e-01]
latex_v1:  63%|######2   | 1885/3000 [43:57<27:51,  1.50s/it, lr: 1.0e-04 loss: 1.043e-01]
latex_v1:  63%|######2   | 1885/3000 [43:59<27:51,  1.50s/it, lr: 1.0e-04 loss: 1.111e-01]
latex_v1:  63%|######2   | 1885/3000 [43:59<27:51,  1.50s/it, lr: 1.0e-04 loss: 1.111e-01]
latex_v1:  63%|######2   | 1886/3000 [43:59<27:15,  1.47s/it, lr: 1.0e-04 loss: 1.111e-01]
latex_v1:  63%|######2   | 1886/3000 [43:59<27:15,  1.47s/it, lr: 1.0e-04 loss: 1.111e-01]
latex_v1:  63%|######2   | 1886/3000 [43:59<27:15,  1.47s/it, lr: 1.0e-04 loss: 5.703e-01]
latex_v1:  63%|######2   | 1886/3000 [43:59<27:15,  1.47s/it, lr: 1.0e-04 loss: 5.703e-01]
latex_v1:  63%|######2   | 1887/3000 [43:59<23:24,  1.26s/it, lr: 1.0e-04 loss: 5.703e-01]
latex_v1:  63%|######2   | 1887/3000 [43:59<23:24,  1.26s/it, lr: 1.0e-04 loss: 5.703e-01]
latex_v1:  63%|######2   | 1887/3000 [44:01<23:24,  1.26s/it, lr: 1.0e-04 loss: 5.319e-01]
latex_v1:  63%|######2   | 1887/3000 [44:01<23:24,  1.26s/it, lr: 1.0e-04 loss: 5.319e-01]
latex_v1:  63%|######2   | 1888/3000 [44:01<26:44,  1.44s/it, lr: 1.0e-04 loss: 5.319e-01]
latex_v1:  63%|######2   | 1888/3000 [44:01<26:44,  1.44s/it, lr: 1.0e-04 loss: 5.319e-01]
latex_v1:  63%|######2   | 1888/3000 [44:02<26:44,  1.44s/it, lr: 1.0e-04 loss: 6.205e-01]
latex_v1:  63%|######2   | 1888/3000 [44:02<26:44,  1.44s/it, lr: 1.0e-04 loss: 6.205e-01]
latex_v1:  63%|######2   | 1889/3000 [44:02<22:49,  1.23s/it, lr: 1.0e-04 loss: 6.205e-01]
latex_v1:  63%|######2   | 1889/3000 [44:02<22:49,  1.23s/it, lr: 1.0e-04 loss: 6.205e-01]
latex_v1:  63%|######2   | 1889/3000 [44:03<22:49,  1.23s/it, lr: 1.0e-04 loss: 5.664e-01]
latex_v1:  63%|######2   | 1889/3000 [44:03<22:49,  1.23s/it, lr: 1.0e-04 loss: 5.664e-01]
latex_v1:  63%|######3   | 1890/3000 [44:05<22:48,  1.23s/it, lr: 1.0e-04 loss: 1.017e-01]
latex_v1:  63%|######3   | 1890/3000 [44:05<22:48,  1.23s/it, lr: 1.0e-04 loss: 1.017e-01]
latex_v1:  63%|######3   | 1891/3000 [44:05<17:56,  1.03it/s, lr: 1.0e-04 loss: 1.017e-01]
latex_v1:  63%|######3   | 1891/3000 [44:05<17:56,  1.03it/s, lr: 1.0e-04 loss: 1.017e-01]
latex_v1:  63%|######3   | 1891/3000 [44:06<17:56,  1.03it/s, lr: 1.0e-04 loss: 1.960e-01]
latex_v1:  63%|######3   | 1891/3000 [44:06<17:56,  1.03it/s, lr: 1.0e-04 loss: 1.960e-01]
latex_v1:  63%|######3   | 1892/3000 [44:06<16:57,  1.09it/s, lr: 1.0e-04 loss: 1.960e-01]
latex_v1:  63%|######3   | 1892/3000 [44:06<16:57,  1.09it/s, lr: 1.0e-04 loss: 1.960e-01]
latex_v1:  63%|######3   | 1892/3000 [44:07<16:57,  1.09it/s, lr: 1.0e-04 loss: 4.634e-02]
latex_v1:  63%|######3   | 1892/3000 [44:07<16:57,  1.09it/s, lr: 1.0e-04 loss: 4.634e-02]
latex_v1:  63%|######3   | 1893/3000 [44:07<18:14,  1.01it/s, lr: 1.0e-04 loss: 4.634e-02]
latex_v1:  63%|######3   | 1893/3000 [44:07<18:14,  1.01it/s, lr: 1.0e-04 loss: 4.634e-02]
latex_v1:  63%|######3   | 1893/3000 [44:07<18:14,  1.01it/s, lr: 1.0e-04 loss: 1.949e-01]
latex_v1:  63%|######3   | 1893/3000 [44:07<18:14,  1.01it/s, lr: 1.0e-04 loss: 1.949e-01]
latex_v1:  63%|######3   | 1894/3000 [44:07<17:04,  1.08it/s, lr: 1.0e-04 loss: 1.949e-01]
latex_v1:  63%|######3   | 1894/3000 [44:07<17:04,  1.08it/s, lr: 1.0e-04 loss: 1.949e-01]
latex_v1:  63%|######3   | 1894/3000 [44:08<17:04,  1.08it/s, lr: 1.0e-04 loss: 1.222e-01]
latex_v1:  63%|######3   | 1894/3000 [44:08<17:04,  1.08it/s, lr: 1.0e-04 loss: 1.222e-01]
latex_v1:  63%|######3   | 1895/3000 [44:08<16:14,  1.13it/s, lr: 1.0e-04 loss: 1.222e-01]
latex_v1:  63%|######3   | 1895/3000 [44:08<16:14,  1.13it/s, lr: 1.0e-04 loss: 1.222e-01]
latex_v1:  63%|######3   | 1895/3000 [44:10<16:14,  1.13it/s, lr: 1.0e-04 loss: 2.145e-01]
latex_v1:  63%|######3   | 1895/3000 [44:10<16:14,  1.13it/s, lr: 1.0e-04 loss: 2.145e-01]
latex_v1:  63%|######3   | 1896/3000 [44:10<22:00,  1.20s/it, lr: 1.0e-04 loss: 2.145e-01]
latex_v1:  63%|######3   | 1896/3000 [44:10<22:00,  1.20s/it, lr: 1.0e-04 loss: 2.145e-01]
latex_v1:  63%|######3   | 1896/3000 [44:12<22:00,  1.20s/it, lr: 1.0e-04 loss: 4.481e-01]
latex_v1:  63%|######3   | 1896/3000 [44:12<22:00,  1.20s/it, lr: 1.0e-04 loss: 4.481e-01]
latex_v1:  63%|######3   | 1897/3000 [44:12<24:50,  1.35s/it, lr: 1.0e-04 loss: 4.481e-01]
latex_v1:  63%|######3   | 1897/3000 [44:12<24:50,  1.35s/it, lr: 1.0e-04 loss: 4.481e-01]
latex_v1:  63%|######3   | 1897/3000 [44:15<24:50,  1.35s/it, lr: 1.0e-04 loss: 1.143e-01]
latex_v1:  63%|######3   | 1897/3000 [44:15<24:50,  1.35s/it, lr: 1.0e-04 loss: 1.143e-01]
latex_v1:  63%|######3   | 1898/3000 [44:15<32:57,  1.79s/it, lr: 1.0e-04 loss: 1.143e-01]
latex_v1:  63%|######3   | 1898/3000 [44:15<32:57,  1.79s/it, lr: 1.0e-04 loss: 1.143e-01]
latex_v1:  63%|######3   | 1898/3000 [44:16<32:57,  1.79s/it, lr: 1.0e-04 loss: 5.343e-01]
latex_v1:  63%|######3   | 1898/3000 [44:16<32:57,  1.79s/it, lr: 1.0e-04 loss: 5.343e-01]
latex_v1:  63%|######3   | 1899/3000 [44:16<31:06,  1.70s/it, lr: 1.0e-04 loss: 5.343e-01]
latex_v1:  63%|######3   | 1899/3000 [44:16<31:06,  1.70s/it, lr: 1.0e-04 loss: 5.343e-01]
latex_v1:  63%|######3   | 1899/3000 [44:17<31:06,  1.70s/it, lr: 1.0e-04 loss: 5.364e-01]
latex_v1:  63%|######3   | 1899/3000 [44:17<31:06,  1.70s/it, lr: 1.0e-04 loss: 5.364e-01]
latex_v1:  63%|######3   | 1900/3000 [44:19<31:05,  1.70s/it, lr: 1.0e-04 loss: 4.814e-01]
latex_v1:  63%|######3   | 1900/3000 [44:19<31:05,  1.70s/it, lr: 1.0e-04 loss: 4.814e-01]
latex_v1:  63%|######3   | 1901/3000 [44:19<22:28,  1.23s/it, lr: 1.0e-04 loss: 4.814e-01]
latex_v1:  63%|######3   | 1901/3000 [44:19<22:28,  1.23s/it, lr: 1.0e-04 loss: 4.814e-01]
latex_v1:  63%|######3   | 1901/3000 [44:19<22:28,  1.23s/it, lr: 1.0e-04 loss: 4.137e-01]
latex_v1:  63%|######3   | 1901/3000 [44:19<22:28,  1.23s/it, lr: 1.0e-04 loss: 4.137e-01]
latex_v1:  63%|######3   | 1902/3000 [44:19<20:18,  1.11s/it, lr: 1.0e-04 loss: 4.137e-01]
latex_v1:  63%|######3   | 1902/3000 [44:19<20:18,  1.11s/it, lr: 1.0e-04 loss: 4.137e-01]
latex_v1:  63%|######3   | 1902/3000 [44:21<20:18,  1.11s/it, lr: 1.0e-04 loss: 2.723e-02]
latex_v1:  63%|######3   | 1902/3000 [44:21<20:18,  1.11s/it, lr: 1.0e-04 loss: 2.723e-02]
latex_v1:  63%|######3   | 1903/3000 [44:21<22:25,  1.23s/it, lr: 1.0e-04 loss: 2.723e-02]
latex_v1:  63%|######3   | 1903/3000 [44:21<22:25,  1.23s/it, lr: 1.0e-04 loss: 2.723e-02]
latex_v1:  63%|######3   | 1903/3000 [44:24<22:25,  1.23s/it, lr: 1.0e-04 loss: 5.229e-02]
latex_v1:  63%|######3   | 1903/3000 [44:24<22:25,  1.23s/it, lr: 1.0e-04 loss: 5.229e-02]
latex_v1:  63%|######3   | 1904/3000 [44:24<29:47,  1.63s/it, lr: 1.0e-04 loss: 5.229e-02]
latex_v1:  63%|######3   | 1904/3000 [44:24<29:47,  1.63s/it, lr: 1.0e-04 loss: 5.229e-02]
latex_v1:  63%|######3   | 1904/3000 [44:25<29:47,  1.63s/it, lr: 1.0e-04 loss: 2.217e-01]
latex_v1:  63%|######3   | 1904/3000 [44:25<29:47,  1.63s/it, lr: 1.0e-04 loss: 2.217e-01]
latex_v1:  64%|######3   | 1905/3000 [44:25<28:23,  1.56s/it, lr: 1.0e-04 loss: 2.217e-01]
latex_v1:  64%|######3   | 1905/3000 [44:25<28:23,  1.56s/it, lr: 1.0e-04 loss: 2.217e-01]
latex_v1:  64%|######3   | 1905/3000 [44:28<28:23,  1.56s/it, lr: 1.0e-04 loss: 3.977e-01]
latex_v1:  64%|######3   | 1905/3000 [44:28<28:23,  1.56s/it, lr: 1.0e-04 loss: 3.977e-01]
latex_v1:  64%|######3   | 1906/3000 [44:28<35:23,  1.94s/it, lr: 1.0e-04 loss: 3.977e-01]
latex_v1:  64%|######3   | 1906/3000 [44:28<35:23,  1.94s/it, lr: 1.0e-04 loss: 3.977e-01]
latex_v1:  64%|######3   | 1906/3000 [44:31<35:23,  1.94s/it, lr: 1.0e-04 loss: 6.154e-01]
latex_v1:  64%|######3   | 1906/3000 [44:31<35:23,  1.94s/it, lr: 1.0e-04 loss: 6.154e-01]
latex_v1:  64%|######3   | 1907/3000 [44:31<40:03,  2.20s/it, lr: 1.0e-04 loss: 6.154e-01]
latex_v1:  64%|######3   | 1907/3000 [44:31<40:03,  2.20s/it, lr: 1.0e-04 loss: 6.154e-01]
latex_v1:  64%|######3   | 1907/3000 [44:32<40:03,  2.20s/it, lr: 1.0e-04 loss: 8.389e-02]
latex_v1:  64%|######3   | 1907/3000 [44:32<40:03,  2.20s/it, lr: 1.0e-04 loss: 8.389e-02]
latex_v1:  64%|######3   | 1908/3000 [44:32<36:34,  2.01s/it, lr: 1.0e-04 loss: 8.389e-02]
latex_v1:  64%|######3   | 1908/3000 [44:32<36:34,  2.01s/it, lr: 1.0e-04 loss: 8.389e-02]
latex_v1:  64%|######3   | 1908/3000 [44:33<36:34,  2.01s/it, lr: 1.0e-04 loss: 6.734e-01]
latex_v1:  64%|######3   | 1908/3000 [44:33<36:34,  2.01s/it, lr: 1.0e-04 loss: 6.734e-01]
latex_v1:  64%|######3   | 1909/3000 [44:33<31:52,  1.75s/it, lr: 1.0e-04 loss: 6.734e-01]
latex_v1:  64%|######3   | 1909/3000 [44:33<31:52,  1.75s/it, lr: 1.0e-04 loss: 6.734e-01]
latex_v1:  64%|######3   | 1909/3000 [44:34<31:52,  1.75s/it, lr: 1.0e-04 loss: 3.140e-01]
latex_v1:  64%|######3   | 1909/3000 [44:34<31:52,  1.75s/it, lr: 1.0e-04 loss: 3.140e-01]
latex_v1:  64%|######3   | 1910/3000 [44:35<31:50,  1.75s/it, lr: 1.0e-04 loss: 5.936e-01]
latex_v1:  64%|######3   | 1910/3000 [44:35<31:50,  1.75s/it, lr: 1.0e-04 loss: 5.936e-01]
latex_v1:  64%|######3   | 1911/3000 [44:35<20:25,  1.13s/it, lr: 1.0e-04 loss: 5.936e-01]
latex_v1:  64%|######3   | 1911/3000 [44:35<20:25,  1.13s/it, lr: 1.0e-04 loss: 5.936e-01]
latex_v1:  64%|######3   | 1911/3000 [44:37<20:25,  1.13s/it, lr: 1.0e-04 loss: 2.084e-01]
latex_v1:  64%|######3   | 1911/3000 [44:37<20:25,  1.13s/it, lr: 1.0e-04 loss: 2.084e-01]
latex_v1:  64%|######3   | 1912/3000 [44:37<23:50,  1.31s/it, lr: 1.0e-04 loss: 2.084e-01]
latex_v1:  64%|######3   | 1912/3000 [44:37<23:50,  1.31s/it, lr: 1.0e-04 loss: 2.084e-01]
latex_v1:  64%|######3   | 1912/3000 [44:39<23:50,  1.31s/it, lr: 1.0e-04 loss: 4.501e-01]
latex_v1:  64%|######3   | 1912/3000 [44:39<23:50,  1.31s/it, lr: 1.0e-04 loss: 4.501e-01]
latex_v1:  64%|######3   | 1913/3000 [44:39<26:33,  1.47s/it, lr: 1.0e-04 loss: 4.501e-01]
latex_v1:  64%|######3   | 1913/3000 [44:39<26:33,  1.47s/it, lr: 1.0e-04 loss: 4.501e-01]
latex_v1:  64%|######3   | 1913/3000 [44:40<26:33,  1.47s/it, lr: 1.0e-04 loss: 3.576e-01]
latex_v1:  64%|######3   | 1913/3000 [44:40<26:33,  1.47s/it, lr: 1.0e-04 loss: 3.576e-01]
latex_v1:  64%|######3   | 1914/3000 [44:40<24:38,  1.36s/it, lr: 1.0e-04 loss: 3.576e-01]
latex_v1:  64%|######3   | 1914/3000 [44:40<24:38,  1.36s/it, lr: 1.0e-04 loss: 3.576e-01]
latex_v1:  64%|######3   | 1914/3000 [44:41<24:38,  1.36s/it, lr: 1.0e-04 loss: 1.424e-01]
latex_v1:  64%|######3   | 1914/3000 [44:41<24:38,  1.36s/it, lr: 1.0e-04 loss: 1.424e-01]
latex_v1:  64%|######3   | 1915/3000 [44:41<21:31,  1.19s/it, lr: 1.0e-04 loss: 1.424e-01]
latex_v1:  64%|######3   | 1915/3000 [44:41<21:31,  1.19s/it, lr: 1.0e-04 loss: 1.424e-01]
latex_v1:  64%|######3   | 1915/3000 [44:42<21:31,  1.19s/it, lr: 1.0e-04 loss: 1.867e-01]
latex_v1:  64%|######3   | 1915/3000 [44:42<21:31,  1.19s/it, lr: 1.0e-04 loss: 1.867e-01]
latex_v1:  64%|######3   | 1916/3000 [44:42<21:27,  1.19s/it, lr: 1.0e-04 loss: 1.867e-01]
latex_v1:  64%|######3   | 1916/3000 [44:42<21:27,  1.19s/it, lr: 1.0e-04 loss: 1.867e-01]
latex_v1:  64%|######3   | 1916/3000 [44:43<21:27,  1.19s/it, lr: 1.0e-04 loss: 1.186e-01]
latex_v1:  64%|######3   | 1916/3000 [44:43<21:27,  1.19s/it, lr: 1.0e-04 loss: 1.186e-01]
latex_v1:  64%|######3   | 1917/3000 [44:43<19:07,  1.06s/it, lr: 1.0e-04 loss: 1.186e-01]
latex_v1:  64%|######3   | 1917/3000 [44:43<19:07,  1.06s/it, lr: 1.0e-04 loss: 1.186e-01]
latex_v1:  64%|######3   | 1917/3000 [44:44<19:07,  1.06s/it, lr: 1.0e-04 loss: 1.799e-01]
latex_v1:  64%|######3   | 1917/3000 [44:44<19:07,  1.06s/it, lr: 1.0e-04 loss: 1.799e-01]
latex_v1:  64%|######3   | 1918/3000 [44:44<21:03,  1.17s/it, lr: 1.0e-04 loss: 1.799e-01]
latex_v1:  64%|######3   | 1918/3000 [44:44<21:03,  1.17s/it, lr: 1.0e-04 loss: 1.799e-01]
latex_v1:  64%|######3   | 1918/3000 [44:45<21:03,  1.17s/it, lr: 1.0e-04 loss: 6.278e-01]
latex_v1:  64%|######3   | 1918/3000 [44:45<21:03,  1.17s/it, lr: 1.0e-04 loss: 6.278e-01]
latex_v1:  64%|######3   | 1919/3000 [44:45<18:53,  1.05s/it, lr: 1.0e-04 loss: 6.278e-01]
latex_v1:  64%|######3   | 1919/3000 [44:45<18:53,  1.05s/it, lr: 1.0e-04 loss: 6.278e-01]
latex_v1:  64%|######3   | 1919/3000 [44:46<18:53,  1.05s/it, lr: 1.0e-04 loss: 1.683e-01]
latex_v1:  64%|######3   | 1919/3000 [44:46<18:53,  1.05s/it, lr: 1.0e-04 loss: 1.683e-01]
latex_v1:  64%|######4   | 1920/3000 [44:46<18:52,  1.05s/it, lr: 1.0e-04 loss: 6.693e-01]
latex_v1:  64%|######4   | 1920/3000 [44:46<18:52,  1.05s/it, lr: 1.0e-04 loss: 6.693e-01]
latex_v1:  64%|######4   | 1921/3000 [44:46<13:19,  1.35it/s, lr: 1.0e-04 loss: 6.693e-01]
latex_v1:  64%|######4   | 1921/3000 [44:46<13:19,  1.35it/s, lr: 1.0e-04 loss: 6.693e-01]
latex_v1:  64%|######4   | 1921/3000 [44:49<13:19,  1.35it/s, lr: 1.0e-04 loss: 5.409e-01]
latex_v1:  64%|######4   | 1921/3000 [44:49<13:19,  1.35it/s, lr: 1.0e-04 loss: 5.409e-01]
latex_v1:  64%|######4   | 1922/3000 [44:49<22:47,  1.27s/it, lr: 1.0e-04 loss: 5.409e-01]
latex_v1:  64%|######4   | 1922/3000 [44:49<22:47,  1.27s/it, lr: 1.0e-04 loss: 5.409e-01]
latex_v1:  64%|######4   | 1922/3000 [44:51<22:47,  1.27s/it, lr: 1.0e-04 loss: 1.988e-01]
latex_v1:  64%|######4   | 1922/3000 [44:51<22:47,  1.27s/it, lr: 1.0e-04 loss: 1.988e-01]
latex_v1:  64%|######4   | 1923/3000 [44:51<25:19,  1.41s/it, lr: 1.0e-04 loss: 1.988e-01]
latex_v1:  64%|######4   | 1923/3000 [44:51<25:19,  1.41s/it, lr: 1.0e-04 loss: 1.988e-01]
latex_v1:  64%|######4   | 1923/3000 [44:53<25:19,  1.41s/it, lr: 1.0e-04 loss: 3.974e-01]
latex_v1:  64%|######4   | 1923/3000 [44:53<25:19,  1.41s/it, lr: 1.0e-04 loss: 3.974e-01]
latex_v1:  64%|######4   | 1924/3000 [44:53<25:25,  1.42s/it, lr: 1.0e-04 loss: 3.974e-01]
latex_v1:  64%|######4   | 1924/3000 [44:53<25:25,  1.42s/it, lr: 1.0e-04 loss: 3.974e-01]
latex_v1:  64%|######4   | 1924/3000 [44:54<25:25,  1.42s/it, lr: 1.0e-04 loss: 3.855e-01]
latex_v1:  64%|######4   | 1924/3000 [44:54<25:25,  1.42s/it, lr: 1.0e-04 loss: 3.855e-01]
latex_v1:  64%|######4   | 1925/3000 [44:54<27:43,  1.55s/it, lr: 1.0e-04 loss: 3.855e-01]
latex_v1:  64%|######4   | 1925/3000 [44:54<27:43,  1.55s/it, lr: 1.0e-04 loss: 3.855e-01]
latex_v1:  64%|######4   | 1925/3000 [44:55<27:43,  1.55s/it, lr: 1.0e-04 loss: 1.874e-01]
latex_v1:  64%|######4   | 1925/3000 [44:55<27:43,  1.55s/it, lr: 1.0e-04 loss: 1.874e-01]
latex_v1:  64%|######4   | 1926/3000 [44:55<23:37,  1.32s/it, lr: 1.0e-04 loss: 1.874e-01]
latex_v1:  64%|######4   | 1926/3000 [44:55<23:37,  1.32s/it, lr: 1.0e-04 loss: 1.874e-01]
latex_v1:  64%|######4   | 1926/3000 [44:57<23:37,  1.32s/it, lr: 1.0e-04 loss: 5.976e-01]
latex_v1:  64%|######4   | 1926/3000 [44:57<23:37,  1.32s/it, lr: 1.0e-04 loss: 5.976e-01]
latex_v1:  64%|######4   | 1927/3000 [44:57<24:51,  1.39s/it, lr: 1.0e-04 loss: 5.976e-01]
latex_v1:  64%|######4   | 1927/3000 [44:57<24:51,  1.39s/it, lr: 1.0e-04 loss: 5.976e-01]
latex_v1:  64%|######4   | 1927/3000 [44:58<24:51,  1.39s/it, lr: 1.0e-04 loss: 2.801e-01]
latex_v1:  64%|######4   | 1927/3000 [44:58<24:51,  1.39s/it, lr: 1.0e-04 loss: 2.801e-01]
latex_v1:  64%|######4   | 1928/3000 [44:58<24:35,  1.38s/it, lr: 1.0e-04 loss: 2.801e-01]
latex_v1:  64%|######4   | 1928/3000 [44:58<24:35,  1.38s/it, lr: 1.0e-04 loss: 2.801e-01]
latex_v1:  64%|######4   | 1928/3000 [45:00<24:35,  1.38s/it, lr: 1.0e-04 loss: 2.551e-01]
latex_v1:  64%|######4   | 1928/3000 [45:00<24:35,  1.38s/it, lr: 1.0e-04 loss: 2.551e-01]
latex_v1:  64%|######4   | 1929/3000 [45:00<25:00,  1.40s/it, lr: 1.0e-04 loss: 2.551e-01]
latex_v1:  64%|######4   | 1929/3000 [45:00<25:00,  1.40s/it, lr: 1.0e-04 loss: 2.551e-01]
latex_v1:  64%|######4   | 1929/3000 [45:02<25:00,  1.40s/it, lr: 1.0e-04 loss: 3.418e-01]
latex_v1:  64%|######4   | 1929/3000 [45:02<25:00,  1.40s/it, lr: 1.0e-04 loss: 3.418e-01]
latex_v1:  64%|######4   | 1930/3000 [45:03<24:59,  1.40s/it, lr: 1.0e-04 loss: 1.237e-01]
latex_v1:  64%|######4   | 1930/3000 [45:03<24:59,  1.40s/it, lr: 1.0e-04 loss: 1.237e-01]
latex_v1:  64%|######4   | 1931/3000 [45:03<18:23,  1.03s/it, lr: 1.0e-04 loss: 1.237e-01]
latex_v1:  64%|######4   | 1931/3000 [45:03<18:23,  1.03s/it, lr: 1.0e-04 loss: 1.237e-01]
latex_v1:  64%|######4   | 1931/3000 [45:04<18:23,  1.03s/it, lr: 1.0e-04 loss: 2.215e-01]
latex_v1:  64%|######4   | 1931/3000 [45:04<18:23,  1.03s/it, lr: 1.0e-04 loss: 2.215e-01]
latex_v1:  64%|######4   | 1932/3000 [45:04<17:09,  1.04it/s, lr: 1.0e-04 loss: 2.215e-01]
latex_v1:  64%|######4   | 1932/3000 [45:04<17:09,  1.04it/s, lr: 1.0e-04 loss: 2.215e-01]
latex_v1:  64%|######4   | 1932/3000 [45:06<17:09,  1.04it/s, lr: 1.0e-04 loss: 7.285e-02]
latex_v1:  64%|######4   | 1932/3000 [45:06<17:09,  1.04it/s, lr: 1.0e-04 loss: 7.285e-02]
latex_v1:  64%|######4   | 1933/3000 [45:06<21:24,  1.20s/it, lr: 1.0e-04 loss: 7.285e-02]
latex_v1:  64%|######4   | 1933/3000 [45:06<21:24,  1.20s/it, lr: 1.0e-04 loss: 7.285e-02]
latex_v1:  64%|######4   | 1933/3000 [45:07<21:24,  1.20s/it, lr: 1.0e-04 loss: 6.987e-01]
latex_v1:  64%|######4   | 1933/3000 [45:07<21:24,  1.20s/it, lr: 1.0e-04 loss: 6.987e-01]
latex_v1:  64%|######4   | 1934/3000 [45:07<19:21,  1.09s/it, lr: 1.0e-04 loss: 6.987e-01]
latex_v1:  64%|######4   | 1934/3000 [45:07<19:21,  1.09s/it, lr: 1.0e-04 loss: 6.987e-01]
latex_v1:  64%|######4   | 1934/3000 [45:08<19:21,  1.09s/it, lr: 1.0e-04 loss: 2.864e-01]
latex_v1:  64%|######4   | 1934/3000 [45:08<19:21,  1.09s/it, lr: 1.0e-04 loss: 2.864e-01]
latex_v1:  64%|######4   | 1935/3000 [45:08<21:14,  1.20s/it, lr: 1.0e-04 loss: 2.864e-01]
latex_v1:  64%|######4   | 1935/3000 [45:08<21:14,  1.20s/it, lr: 1.0e-04 loss: 2.864e-01]
latex_v1:  64%|######4   | 1935/3000 [45:09<21:14,  1.20s/it, lr: 1.0e-04 loss: 3.606e-01]
latex_v1:  64%|######4   | 1935/3000 [45:09<21:14,  1.20s/it, lr: 1.0e-04 loss: 3.606e-01]
latex_v1:  65%|######4   | 1936/3000 [45:09<19:01,  1.07s/it, lr: 1.0e-04 loss: 3.606e-01]
latex_v1:  65%|######4   | 1936/3000 [45:09<19:01,  1.07s/it, lr: 1.0e-04 loss: 3.606e-01]
latex_v1:  65%|######4   | 1936/3000 [45:10<19:01,  1.07s/it, lr: 1.0e-04 loss: 5.548e-01]
latex_v1:  65%|######4   | 1936/3000 [45:10<19:01,  1.07s/it, lr: 1.0e-04 loss: 5.548e-01]
latex_v1:  65%|######4   | 1937/3000 [45:10<17:27,  1.01it/s, lr: 1.0e-04 loss: 5.548e-01]
latex_v1:  65%|######4   | 1937/3000 [45:10<17:27,  1.01it/s, lr: 1.0e-04 loss: 5.548e-01]
latex_v1:  65%|######4   | 1937/3000 [45:12<17:27,  1.01it/s, lr: 1.0e-04 loss: 3.850e-01]
latex_v1:  65%|######4   | 1937/3000 [45:12<17:27,  1.01it/s, lr: 1.0e-04 loss: 3.850e-01]
latex_v1:  65%|######4   | 1938/3000 [45:12<21:11,  1.20s/it, lr: 1.0e-04 loss: 3.850e-01]
latex_v1:  65%|######4   | 1938/3000 [45:12<21:11,  1.20s/it, lr: 1.0e-04 loss: 3.850e-01]
latex_v1:  65%|######4   | 1938/3000 [45:12<21:11,  1.20s/it, lr: 1.0e-04 loss: 1.519e-01]
latex_v1:  65%|######4   | 1938/3000 [45:12<21:11,  1.20s/it, lr: 1.0e-04 loss: 1.519e-01]
latex_v1:  65%|######4   | 1939/3000 [45:12<18:54,  1.07s/it, lr: 1.0e-04 loss: 1.519e-01]
latex_v1:  65%|######4   | 1939/3000 [45:12<18:54,  1.07s/it, lr: 1.0e-04 loss: 1.519e-01]
latex_v1:  65%|######4   | 1939/3000 [45:13<18:54,  1.07s/it, lr: 1.0e-04 loss: 2.832e-01]
latex_v1:  65%|######4   | 1939/3000 [45:13<18:54,  1.07s/it, lr: 1.0e-04 loss: 2.832e-01]
latex_v1:  65%|######4   | 1940/3000 [45:15<18:53,  1.07s/it, lr: 1.0e-04 loss: 2.581e-01]
latex_v1:  65%|######4   | 1940/3000 [45:15<18:53,  1.07s/it, lr: 1.0e-04 loss: 2.581e-01]
latex_v1:  65%|######4   | 1941/3000 [45:15<16:38,  1.06it/s, lr: 1.0e-04 loss: 2.581e-01]
latex_v1:  65%|######4   | 1941/3000 [45:15<16:38,  1.06it/s, lr: 1.0e-04 loss: 2.581e-01]
latex_v1:  65%|######4   | 1941/3000 [45:16<16:38,  1.06it/s, lr: 1.0e-04 loss: 1.258e-01]
latex_v1:  65%|######4   | 1941/3000 [45:16<16:38,  1.06it/s, lr: 1.0e-04 loss: 1.258e-01]
latex_v1:  65%|######4   | 1942/3000 [45:16<15:41,  1.12it/s, lr: 1.0e-04 loss: 1.258e-01]
latex_v1:  65%|######4   | 1942/3000 [45:16<15:41,  1.12it/s, lr: 1.0e-04 loss: 1.258e-01]
latex_v1:  65%|######4   | 1942/3000 [45:16<15:41,  1.12it/s, lr: 1.0e-04 loss: 6.812e-01]
latex_v1:  65%|######4   | 1942/3000 [45:16<15:41,  1.12it/s, lr: 1.0e-04 loss: 6.812e-01]
latex_v1:  65%|######4   | 1943/3000 [45:16<15:05,  1.17it/s, lr: 1.0e-04 loss: 6.812e-01]
latex_v1:  65%|######4   | 1943/3000 [45:16<15:05,  1.17it/s, lr: 1.0e-04 loss: 6.812e-01]
latex_v1:  65%|######4   | 1943/3000 [45:18<15:05,  1.17it/s, lr: 1.0e-04 loss: 6.595e-01]
latex_v1:  65%|######4   | 1943/3000 [45:18<15:05,  1.17it/s, lr: 1.0e-04 loss: 6.595e-01]
latex_v1:  65%|######4   | 1944/3000 [45:18<18:29,  1.05s/it, lr: 1.0e-04 loss: 6.595e-01]
latex_v1:  65%|######4   | 1944/3000 [45:18<18:29,  1.05s/it, lr: 1.0e-04 loss: 6.595e-01]
latex_v1:  65%|######4   | 1944/3000 [45:21<18:29,  1.05s/it, lr: 1.0e-04 loss: 7.430e-02]
latex_v1:  65%|######4   | 1944/3000 [45:21<18:29,  1.05s/it, lr: 1.0e-04 loss: 7.430e-02]
latex_v1:  65%|######4   | 1945/3000 [45:21<27:26,  1.56s/it, lr: 1.0e-04 loss: 7.430e-02]
latex_v1:  65%|######4   | 1945/3000 [45:21<27:26,  1.56s/it, lr: 1.0e-04 loss: 7.430e-02]
latex_v1:  65%|######4   | 1945/3000 [45:24<27:26,  1.56s/it, lr: 1.0e-04 loss: 6.017e-01]
latex_v1:  65%|######4   | 1945/3000 [45:24<27:26,  1.56s/it, lr: 1.0e-04 loss: 6.017e-01]
latex_v1:  65%|######4   | 1946/3000 [45:24<34:00,  1.94s/it, lr: 1.0e-04 loss: 6.017e-01]
latex_v1:  65%|######4   | 1946/3000 [45:24<34:00,  1.94s/it, lr: 1.0e-04 loss: 6.017e-01]
latex_v1:  65%|######4   | 1946/3000 [45:24<34:00,  1.94s/it, lr: 1.0e-04 loss: 5.188e-01]
latex_v1:  65%|######4   | 1946/3000 [45:24<34:00,  1.94s/it, lr: 1.0e-04 loss: 5.188e-01]
latex_v1:  65%|######4   | 1947/3000 [45:24<27:55,  1.59s/it, lr: 1.0e-04 loss: 5.188e-01]
latex_v1:  65%|######4   | 1947/3000 [45:24<27:55,  1.59s/it, lr: 1.0e-04 loss: 5.188e-01]
latex_v1:  65%|######4   | 1947/3000 [45:25<27:55,  1.59s/it, lr: 1.0e-04 loss: 3.536e-01]
latex_v1:  65%|######4   | 1947/3000 [45:25<27:55,  1.59s/it, lr: 1.0e-04 loss: 3.536e-01]
latex_v1:  65%|######4   | 1948/3000 [45:25<23:41,  1.35s/it, lr: 1.0e-04 loss: 3.536e-01]
latex_v1:  65%|######4   | 1948/3000 [45:25<23:41,  1.35s/it, lr: 1.0e-04 loss: 3.536e-01]
latex_v1:  65%|######4   | 1948/3000 [45:26<23:41,  1.35s/it, lr: 1.0e-04 loss: 6.111e-01]
latex_v1:  65%|######4   | 1948/3000 [45:26<23:41,  1.35s/it, lr: 1.0e-04 loss: 6.111e-01]
latex_v1:  65%|######4   | 1949/3000 [45:26<20:35,  1.18s/it, lr: 1.0e-04 loss: 6.111e-01]
latex_v1:  65%|######4   | 1949/3000 [45:26<20:35,  1.18s/it, lr: 1.0e-04 loss: 6.111e-01]
latex_v1:  65%|######4   | 1949/3000 [45:27<20:35,  1.18s/it, lr: 1.0e-04 loss: 5.594e-01]
latex_v1:  65%|######4   | 1949/3000 [45:27<20:35,  1.18s/it, lr: 1.0e-04 loss: 5.594e-01]
latex_v1:  65%|######5   | 1950/3000 [45:30<20:34,  1.18s/it, lr: 1.0e-04 loss: 1.609e-01]
latex_v1:  65%|######5   | 1950/3000 [45:30<20:34,  1.18s/it, lr: 1.0e-04 loss: 1.609e-01]
latex_v1:  65%|######5   | 1951/3000 [45:30<19:56,  1.14s/it, lr: 1.0e-04 loss: 1.609e-01]
latex_v1:  65%|######5   | 1951/3000 [45:30<19:56,  1.14s/it, lr: 1.0e-04 loss: 1.609e-01]
latex_v1:  65%|######5   | 1951/3000 [45:31<19:56,  1.14s/it, lr: 1.0e-04 loss: 1.490e-01]
latex_v1:  65%|######5   | 1951/3000 [45:31<19:56,  1.14s/it, lr: 1.0e-04 loss: 1.490e-01]
latex_v1:  65%|######5   | 1952/3000 [45:31<21:55,  1.26s/it, lr: 1.0e-04 loss: 1.490e-01]
latex_v1:  65%|######5   | 1952/3000 [45:31<21:55,  1.26s/it, lr: 1.0e-04 loss: 1.490e-01]
latex_v1:  65%|######5   | 1952/3000 [45:33<21:55,  1.26s/it, lr: 1.0e-04 loss: 5.259e-01]
latex_v1:  65%|######5   | 1952/3000 [45:33<21:55,  1.26s/it, lr: 1.0e-04 loss: 5.259e-01]
latex_v1:  65%|######5   | 1953/3000 [45:33<22:49,  1.31s/it, lr: 1.0e-04 loss: 5.259e-01]
latex_v1:  65%|######5   | 1953/3000 [45:33<22:49,  1.31s/it, lr: 1.0e-04 loss: 5.259e-01]
latex_v1:  65%|######5   | 1953/3000 [45:35<22:49,  1.31s/it, lr: 1.0e-04 loss: 1.300e-01]
latex_v1:  65%|######5   | 1953/3000 [45:35<22:49,  1.31s/it, lr: 1.0e-04 loss: 1.300e-01]
latex_v1:  65%|######5   | 1954/3000 [45:35<24:04,  1.38s/it, lr: 1.0e-04 loss: 1.300e-01]
latex_v1:  65%|######5   | 1954/3000 [45:35<24:04,  1.38s/it, lr: 1.0e-04 loss: 1.300e-01]
latex_v1:  65%|######5   | 1954/3000 [45:35<24:04,  1.38s/it, lr: 1.0e-04 loss: 3.652e-01]
latex_v1:  65%|######5   | 1954/3000 [45:35<24:04,  1.38s/it, lr: 1.0e-04 loss: 3.652e-01]
latex_v1:  65%|######5   | 1955/3000 [45:35<20:59,  1.21s/it, lr: 1.0e-04 loss: 3.652e-01]
latex_v1:  65%|######5   | 1955/3000 [45:35<20:59,  1.21s/it, lr: 1.0e-04 loss: 3.652e-01]
latex_v1:  65%|######5   | 1955/3000 [45:38<20:59,  1.21s/it, lr: 1.0e-04 loss: 1.309e-01]
latex_v1:  65%|######5   | 1955/3000 [45:38<20:59,  1.21s/it, lr: 1.0e-04 loss: 1.309e-01]
latex_v1:  65%|######5   | 1956/3000 [45:38<29:08,  1.67s/it, lr: 1.0e-04 loss: 1.309e-01]
latex_v1:  65%|######5   | 1956/3000 [45:38<29:08,  1.67s/it, lr: 1.0e-04 loss: 1.309e-01]
latex_v1:  65%|######5   | 1956/3000 [45:40<29:08,  1.67s/it, lr: 1.0e-04 loss: 4.018e-01]
latex_v1:  65%|######5   | 1956/3000 [45:40<29:08,  1.67s/it, lr: 1.0e-04 loss: 4.018e-01]
latex_v1:  65%|######5   | 1957/3000 [45:40<28:03,  1.61s/it, lr: 1.0e-04 loss: 4.018e-01]
latex_v1:  65%|######5   | 1957/3000 [45:40<28:03,  1.61s/it, lr: 1.0e-04 loss: 4.018e-01]
latex_v1:  65%|######5   | 1957/3000 [45:40<28:03,  1.61s/it, lr: 1.0e-04 loss: 1.357e-01]
latex_v1:  65%|######5   | 1957/3000 [45:40<28:03,  1.61s/it, lr: 1.0e-04 loss: 1.357e-01]
latex_v1:  65%|######5   | 1958/3000 [45:40<23:39,  1.36s/it, lr: 1.0e-04 loss: 1.357e-01]
latex_v1:  65%|######5   | 1958/3000 [45:40<23:39,  1.36s/it, lr: 1.0e-04 loss: 1.357e-01]
latex_v1:  65%|######5   | 1958/3000 [45:42<23:39,  1.36s/it, lr: 1.0e-04 loss: 1.088e-01]
latex_v1:  65%|######5   | 1958/3000 [45:42<23:39,  1.36s/it, lr: 1.0e-04 loss: 1.088e-01]
latex_v1:  65%|######5   | 1959/3000 [45:42<26:21,  1.52s/it, lr: 1.0e-04 loss: 1.088e-01]
latex_v1:  65%|######5   | 1959/3000 [45:42<26:21,  1.52s/it, lr: 1.0e-04 loss: 1.088e-01]
latex_v1:  65%|######5   | 1959/3000 [45:43<26:21,  1.52s/it, lr: 1.0e-04 loss: 9.812e-02]
latex_v1:  65%|######5   | 1959/3000 [45:43<26:21,  1.52s/it, lr: 1.0e-04 loss: 9.812e-02]
latex_v1:  65%|######5   | 1960/3000 [45:44<26:20,  1.52s/it, lr: 1.0e-04 loss: 6.023e-01]
latex_v1:  65%|######5   | 1960/3000 [45:44<26:20,  1.52s/it, lr: 1.0e-04 loss: 6.023e-01]
latex_v1:  65%|######5   | 1961/3000 [45:44<17:15,  1.00it/s, lr: 1.0e-04 loss: 6.023e-01]
latex_v1:  65%|######5   | 1961/3000 [45:44<17:15,  1.00it/s, lr: 1.0e-04 loss: 6.023e-01]
latex_v1:  65%|######5   | 1961/3000 [45:46<17:15,  1.00it/s, lr: 1.0e-04 loss: 3.956e-01]
latex_v1:  65%|######5   | 1961/3000 [45:46<17:15,  1.00it/s, lr: 1.0e-04 loss: 3.956e-01]
latex_v1:  65%|######5   | 1962/3000 [45:46<22:23,  1.29s/it, lr: 1.0e-04 loss: 3.956e-01]
latex_v1:  65%|######5   | 1962/3000 [45:46<22:23,  1.29s/it, lr: 1.0e-04 loss: 3.956e-01]
latex_v1:  65%|######5   | 1962/3000 [45:47<22:23,  1.29s/it, lr: 1.0e-04 loss: 4.801e-01]
latex_v1:  65%|######5   | 1962/3000 [45:47<22:23,  1.29s/it, lr: 1.0e-04 loss: 4.801e-01]
latex_v1:  65%|######5   | 1963/3000 [45:47<20:01,  1.16s/it, lr: 1.0e-04 loss: 4.801e-01]
latex_v1:  65%|######5   | 1963/3000 [45:47<20:01,  1.16s/it, lr: 1.0e-04 loss: 4.801e-01]
latex_v1:  65%|######5   | 1963/3000 [45:48<20:01,  1.16s/it, lr: 1.0e-04 loss: 4.390e-01]
latex_v1:  65%|######5   | 1963/3000 [45:48<20:01,  1.16s/it, lr: 1.0e-04 loss: 4.390e-01]
latex_v1:  65%|######5   | 1964/3000 [45:48<18:10,  1.05s/it, lr: 1.0e-04 loss: 4.390e-01]
latex_v1:  65%|######5   | 1964/3000 [45:48<18:10,  1.05s/it, lr: 1.0e-04 loss: 4.390e-01]
latex_v1:  65%|######5   | 1964/3000 [45:49<18:10,  1.05s/it, lr: 1.0e-04 loss: 5.498e-01]
latex_v1:  65%|######5   | 1964/3000 [45:49<18:10,  1.05s/it, lr: 1.0e-04 loss: 5.498e-01]
latex_v1:  66%|######5   | 1965/3000 [45:49<21:31,  1.25s/it, lr: 1.0e-04 loss: 5.498e-01]
latex_v1:  66%|######5   | 1965/3000 [45:49<21:31,  1.25s/it, lr: 1.0e-04 loss: 5.498e-01]
latex_v1:  66%|######5   | 1965/3000 [45:51<21:31,  1.25s/it, lr: 1.0e-04 loss: 2.469e-01]
latex_v1:  66%|######5   | 1965/3000 [45:51<21:31,  1.25s/it, lr: 1.0e-04 loss: 2.469e-01]
latex_v1:  66%|######5   | 1966/3000 [45:51<22:53,  1.33s/it, lr: 1.0e-04 loss: 2.469e-01]
latex_v1:  66%|######5   | 1966/3000 [45:51<22:53,  1.33s/it, lr: 1.0e-04 loss: 2.469e-01]
latex_v1:  66%|######5   | 1966/3000 [45:52<22:53,  1.33s/it, lr: 1.0e-04 loss: 4.956e-01]
latex_v1:  66%|######5   | 1966/3000 [45:52<22:53,  1.33s/it, lr: 1.0e-04 loss: 4.956e-01]
latex_v1:  66%|######5   | 1967/3000 [45:52<20:07,  1.17s/it, lr: 1.0e-04 loss: 4.956e-01]
latex_v1:  66%|######5   | 1967/3000 [45:52<20:07,  1.17s/it, lr: 1.0e-04 loss: 4.956e-01]
latex_v1:  66%|######5   | 1967/3000 [45:52<20:07,  1.17s/it, lr: 1.0e-04 loss: 2.606e-01]
latex_v1:  66%|######5   | 1967/3000 [45:52<20:07,  1.17s/it, lr: 1.0e-04 loss: 2.606e-01]
latex_v1:  66%|######5   | 1968/3000 [45:52<18:05,  1.05s/it, lr: 1.0e-04 loss: 2.606e-01]
latex_v1:  66%|######5   | 1968/3000 [45:52<18:05,  1.05s/it, lr: 1.0e-04 loss: 2.606e-01]
latex_v1:  66%|######5   | 1968/3000 [45:55<18:05,  1.05s/it, lr: 1.0e-04 loss: 3.731e-01]
latex_v1:  66%|######5   | 1968/3000 [45:55<18:05,  1.05s/it, lr: 1.0e-04 loss: 3.731e-01]
latex_v1:  66%|######5   | 1969/3000 [45:55<27:03,  1.57s/it, lr: 1.0e-04 loss: 3.731e-01]
latex_v1:  66%|######5   | 1969/3000 [45:55<27:03,  1.57s/it, lr: 1.0e-04 loss: 3.731e-01]
latex_v1:  66%|######5   | 1969/3000 [45:57<27:03,  1.57s/it, lr: 1.0e-04 loss: 5.926e-02]
latex_v1:  66%|######5   | 1969/3000 [45:57<27:03,  1.57s/it, lr: 1.0e-04 loss: 5.926e-02]
latex_v1:  66%|######5   | 1970/3000 [45:59<27:01,  1.57s/it, lr: 1.0e-04 loss: 2.262e-01]
latex_v1:  66%|######5   | 1970/3000 [45:59<27:01,  1.57s/it, lr: 1.0e-04 loss: 2.262e-01]
latex_v1:  66%|######5   | 1971/3000 [45:59<25:00,  1.46s/it, lr: 1.0e-04 loss: 2.262e-01]
latex_v1:  66%|######5   | 1971/3000 [45:59<25:00,  1.46s/it, lr: 1.0e-04 loss: 2.262e-01]
latex_v1:  66%|######5   | 1971/3000 [46:00<25:00,  1.46s/it, lr: 1.0e-04 loss: 3.707e-01]
latex_v1:  66%|######5   | 1971/3000 [46:00<25:00,  1.46s/it, lr: 1.0e-04 loss: 3.707e-01]
latex_v1:  66%|######5   | 1972/3000 [46:00<22:28,  1.31s/it, lr: 1.0e-04 loss: 3.707e-01]
latex_v1:  66%|######5   | 1972/3000 [46:00<22:28,  1.31s/it, lr: 1.0e-04 loss: 3.707e-01]
latex_v1:  66%|######5   | 1972/3000 [46:02<22:28,  1.31s/it, lr: 1.0e-04 loss: 3.227e-01]
latex_v1:  66%|######5   | 1972/3000 [46:02<22:28,  1.31s/it, lr: 1.0e-04 loss: 3.227e-01]
latex_v1:  66%|######5   | 1973/3000 [46:02<23:32,  1.38s/it, lr: 1.0e-04 loss: 3.227e-01]
latex_v1:  66%|######5   | 1973/3000 [46:02<23:32,  1.38s/it, lr: 1.0e-04 loss: 3.227e-01]
latex_v1:  66%|######5   | 1973/3000 [46:03<23:32,  1.38s/it, lr: 1.0e-04 loss: 5.832e-01]
latex_v1:  66%|######5   | 1973/3000 [46:03<23:32,  1.38s/it, lr: 1.0e-04 loss: 5.832e-01]
latex_v1:  66%|######5   | 1974/3000 [46:03<24:20,  1.42s/it, lr: 1.0e-04 loss: 5.832e-01]
latex_v1:  66%|######5   | 1974/3000 [46:03<24:20,  1.42s/it, lr: 1.0e-04 loss: 5.832e-01]
latex_v1:  66%|######5   | 1974/3000 [46:06<24:20,  1.42s/it, lr: 1.0e-04 loss: 4.758e-01]
latex_v1:  66%|######5   | 1974/3000 [46:06<24:20,  1.42s/it, lr: 1.0e-04 loss: 4.758e-01]
latex_v1:  66%|######5   | 1975/3000 [46:06<31:13,  1.83s/it, lr: 1.0e-04 loss: 4.758e-01]
latex_v1:  66%|######5   | 1975/3000 [46:06<31:13,  1.83s/it, lr: 1.0e-04 loss: 4.758e-01]
latex_v1:  66%|######5   | 1975/3000 [46:07<31:13,  1.83s/it, lr: 1.0e-04 loss: 2.445e-02]
latex_v1:  66%|######5   | 1975/3000 [46:07<31:13,  1.83s/it, lr: 1.0e-04 loss: 2.445e-02]
latex_v1:  66%|######5   | 1976/3000 [46:07<25:56,  1.52s/it, lr: 1.0e-04 loss: 2.445e-02]
latex_v1:  66%|######5   | 1976/3000 [46:07<25:56,  1.52s/it, lr: 1.0e-04 loss: 2.445e-02]
latex_v1:  66%|######5   | 1976/3000 [46:09<25:56,  1.52s/it, lr: 1.0e-04 loss: 3.398e-02]
latex_v1:  66%|######5   | 1976/3000 [46:09<25:56,  1.52s/it, lr: 1.0e-04 loss: 3.398e-02]
latex_v1:  66%|######5   | 1977/3000 [46:09<25:59,  1.52s/it, lr: 1.0e-04 loss: 3.398e-02]
latex_v1:  66%|######5   | 1977/3000 [46:09<25:59,  1.52s/it, lr: 1.0e-04 loss: 3.398e-02]
latex_v1:  66%|######5   | 1977/3000 [46:10<25:59,  1.52s/it, lr: 1.0e-04 loss: 6.187e-01]
latex_v1:  66%|######5   | 1977/3000 [46:10<25:59,  1.52s/it, lr: 1.0e-04 loss: 6.187e-01]
latex_v1:  66%|######5   | 1978/3000 [46:10<23:16,  1.37s/it, lr: 1.0e-04 loss: 6.187e-01]
latex_v1:  66%|######5   | 1978/3000 [46:10<23:16,  1.37s/it, lr: 1.0e-04 loss: 6.187e-01]
latex_v1:  66%|######5   | 1978/3000 [46:12<23:16,  1.37s/it, lr: 1.0e-04 loss: 2.663e-01]
latex_v1:  66%|######5   | 1978/3000 [46:12<23:16,  1.37s/it, lr: 1.0e-04 loss: 2.663e-01]
latex_v1:  66%|######5   | 1979/3000 [46:12<30:00,  1.76s/it, lr: 1.0e-04 loss: 2.663e-01]
latex_v1:  66%|######5   | 1979/3000 [46:12<30:00,  1.76s/it, lr: 1.0e-04 loss: 2.663e-01]
latex_v1:  66%|######5   | 1979/3000 [46:14<30:00,  1.76s/it, lr: 1.0e-04 loss: 1.950e-01]
latex_v1:  66%|######5   | 1979/3000 [46:14<30:00,  1.76s/it, lr: 1.0e-04 loss: 1.950e-01]
latex_v1:  66%|######6   | 1980/3000 [46:15<29:58,  1.76s/it, lr: 1.0e-04 loss: 5.579e-02]
latex_v1:  66%|######6   | 1980/3000 [46:15<29:58,  1.76s/it, lr: 1.0e-04 loss: 5.579e-02]
latex_v1:  66%|######6   | 1981/3000 [46:15<22:12,  1.31s/it, lr: 1.0e-04 loss: 5.579e-02]
latex_v1:  66%|######6   | 1981/3000 [46:15<22:12,  1.31s/it, lr: 1.0e-04 loss: 5.579e-02]
latex_v1:  66%|######6   | 1981/3000 [46:17<22:12,  1.31s/it, lr: 1.0e-04 loss: 1.027e-01]
latex_v1:  66%|######6   | 1981/3000 [46:17<22:12,  1.31s/it, lr: 1.0e-04 loss: 1.027e-01]
latex_v1:  66%|######6   | 1982/3000 [46:17<22:32,  1.33s/it, lr: 1.0e-04 loss: 1.027e-01]
latex_v1:  66%|######6   | 1982/3000 [46:17<22:32,  1.33s/it, lr: 1.0e-04 loss: 1.027e-01]
latex_v1:  66%|######6   | 1982/3000 [46:18<22:32,  1.33s/it, lr: 1.0e-04 loss: 2.497e-01]
latex_v1:  66%|######6   | 1982/3000 [46:18<22:32,  1.33s/it, lr: 1.0e-04 loss: 2.497e-01]
latex_v1:  66%|######6   | 1983/3000 [46:18<21:49,  1.29s/it, lr: 1.0e-04 loss: 2.497e-01]
latex_v1:  66%|######6   | 1983/3000 [46:18<21:49,  1.29s/it, lr: 1.0e-04 loss: 2.497e-01]
latex_v1:  66%|######6   | 1983/3000 [46:19<21:49,  1.29s/it, lr: 1.0e-04 loss: 1.615e-01]
latex_v1:  66%|######6   | 1983/3000 [46:19<21:49,  1.29s/it, lr: 1.0e-04 loss: 1.615e-01]
latex_v1:  66%|######6   | 1984/3000 [46:19<23:00,  1.36s/it, lr: 1.0e-04 loss: 1.615e-01]
latex_v1:  66%|######6   | 1984/3000 [46:19<23:00,  1.36s/it, lr: 1.0e-04 loss: 1.615e-01]
latex_v1:  66%|######6   | 1984/3000 [46:20<23:00,  1.36s/it, lr: 1.0e-04 loss: 6.960e-01]
latex_v1:  66%|######6   | 1984/3000 [46:20<23:00,  1.36s/it, lr: 1.0e-04 loss: 6.960e-01]
latex_v1:  66%|######6   | 1985/3000 [46:20<21:05,  1.25s/it, lr: 1.0e-04 loss: 6.960e-01]
latex_v1:  66%|######6   | 1985/3000 [46:20<21:05,  1.25s/it, lr: 1.0e-04 loss: 6.960e-01]
latex_v1:  66%|######6   | 1985/3000 [46:22<21:05,  1.25s/it, lr: 1.0e-04 loss: 4.827e-01]
latex_v1:  66%|######6   | 1985/3000 [46:22<21:05,  1.25s/it, lr: 1.0e-04 loss: 4.827e-01]
latex_v1:  66%|######6   | 1986/3000 [46:22<22:32,  1.33s/it, lr: 1.0e-04 loss: 4.827e-01]
latex_v1:  66%|######6   | 1986/3000 [46:22<22:32,  1.33s/it, lr: 1.0e-04 loss: 4.827e-01]
latex_v1:  66%|######6   | 1986/3000 [46:25<22:32,  1.33s/it, lr: 1.0e-04 loss: 1.464e-01]
latex_v1:  66%|######6   | 1986/3000 [46:25<22:32,  1.33s/it, lr: 1.0e-04 loss: 1.464e-01]
latex_v1:  66%|######6   | 1987/3000 [46:25<30:01,  1.78s/it, lr: 1.0e-04 loss: 1.464e-01]
latex_v1:  66%|######6   | 1987/3000 [46:25<30:01,  1.78s/it, lr: 1.0e-04 loss: 1.464e-01]
latex_v1:  66%|######6   | 1987/3000 [46:27<30:01,  1.78s/it, lr: 1.0e-04 loss: 1.398e-01]
latex_v1:  66%|######6   | 1987/3000 [46:27<30:01,  1.78s/it, lr: 1.0e-04 loss: 1.398e-01]
latex_v1:  66%|######6   | 1988/3000 [46:27<30:28,  1.81s/it, lr: 1.0e-04 loss: 1.398e-01]
latex_v1:  66%|######6   | 1988/3000 [46:27<30:28,  1.81s/it, lr: 1.0e-04 loss: 1.398e-01]
latex_v1:  66%|######6   | 1988/3000 [46:30<30:28,  1.81s/it, lr: 1.0e-04 loss: 3.434e-01]
latex_v1:  66%|######6   | 1988/3000 [46:30<30:28,  1.81s/it, lr: 1.0e-04 loss: 3.434e-01]
latex_v1:  66%|######6   | 1989/3000 [46:30<35:51,  2.13s/it, lr: 1.0e-04 loss: 3.434e-01]
latex_v1:  66%|######6   | 1989/3000 [46:30<35:51,  2.13s/it, lr: 1.0e-04 loss: 3.434e-01]
latex_v1:  66%|######6   | 1989/3000 [46:31<35:51,  2.13s/it, lr: 1.0e-04 loss: 2.120e-01]
latex_v1:  66%|######6   | 1989/3000 [46:31<35:51,  2.13s/it, lr: 1.0e-04 loss: 2.120e-01]
latex_v1:  66%|######6   | 1990/3000 [46:34<35:48,  2.13s/it, lr: 1.0e-04 loss: 1.715e-01]
latex_v1:  66%|######6   | 1990/3000 [46:34<35:48,  2.13s/it, lr: 1.0e-04 loss: 1.715e-01]
latex_v1:  66%|######6   | 1991/3000 [46:34<30:24,  1.81s/it, lr: 1.0e-04 loss: 1.715e-01]
latex_v1:  66%|######6   | 1991/3000 [46:34<30:24,  1.81s/it, lr: 1.0e-04 loss: 1.715e-01]
latex_v1:  66%|######6   | 1991/3000 [46:36<30:24,  1.81s/it, lr: 1.0e-04 loss: 5.657e-01]
latex_v1:  66%|######6   | 1991/3000 [46:36<30:24,  1.81s/it, lr: 1.0e-04 loss: 5.657e-01]
latex_v1:  66%|######6   | 1992/3000 [46:36<30:48,  1.83s/it, lr: 1.0e-04 loss: 5.657e-01]
latex_v1:  66%|######6   | 1992/3000 [46:36<30:48,  1.83s/it, lr: 1.0e-04 loss: 5.657e-01]
latex_v1:  66%|######6   | 1992/3000 [46:37<30:48,  1.83s/it, lr: 1.0e-04 loss: 2.243e-01]
latex_v1:  66%|######6   | 1992/3000 [46:37<30:48,  1.83s/it, lr: 1.0e-04 loss: 2.243e-01]
latex_v1:  66%|######6   | 1993/3000 [46:37<27:01,  1.61s/it, lr: 1.0e-04 loss: 2.243e-01]
latex_v1:  66%|######6   | 1993/3000 [46:37<27:01,  1.61s/it, lr: 1.0e-04 loss: 2.243e-01]
latex_v1:  66%|######6   | 1993/3000 [46:38<27:01,  1.61s/it, lr: 1.0e-04 loss: 1.764e-01]
latex_v1:  66%|######6   | 1993/3000 [46:38<27:01,  1.61s/it, lr: 1.0e-04 loss: 1.764e-01]
latex_v1:  66%|######6   | 1994/3000 [46:38<23:07,  1.38s/it, lr: 1.0e-04 loss: 1.764e-01]
latex_v1:  66%|######6   | 1994/3000 [46:38<23:07,  1.38s/it, lr: 1.0e-04 loss: 1.764e-01]
latex_v1:  66%|######6   | 1994/3000 [46:41<23:07,  1.38s/it, lr: 1.0e-04 loss: 3.795e-01]
latex_v1:  66%|######6   | 1994/3000 [46:41<23:07,  1.38s/it, lr: 1.0e-04 loss: 3.795e-01]
latex_v1:  66%|######6   | 1995/3000 [46:41<30:01,  1.79s/it, lr: 1.0e-04 loss: 3.795e-01]
latex_v1:  66%|######6   | 1995/3000 [46:41<30:01,  1.79s/it, lr: 1.0e-04 loss: 3.795e-01]
latex_v1:  66%|######6   | 1995/3000 [46:41<30:01,  1.79s/it, lr: 1.0e-04 loss: 3.705e-01]
latex_v1:  66%|######6   | 1995/3000 [46:41<30:01,  1.79s/it, lr: 1.0e-04 loss: 3.705e-01]
latex_v1:  67%|######6   | 1996/3000 [46:41<25:02,  1.50s/it, lr: 1.0e-04 loss: 3.705e-01]
latex_v1:  67%|######6   | 1996/3000 [46:41<25:02,  1.50s/it, lr: 1.0e-04 loss: 3.705e-01]
latex_v1:  67%|######6   | 1996/3000 [46:42<25:02,  1.50s/it, lr: 1.0e-04 loss: 6.127e-01]
latex_v1:  67%|######6   | 1996/3000 [46:42<25:02,  1.50s/it, lr: 1.0e-04 loss: 6.127e-01]
latex_v1:  67%|######6   | 1997/3000 [46:42<23:13,  1.39s/it, lr: 1.0e-04 loss: 6.127e-01]
latex_v1:  67%|######6   | 1997/3000 [46:42<23:13,  1.39s/it, lr: 1.0e-04 loss: 6.127e-01]
latex_v1:  67%|######6   | 1997/3000 [46:43<23:13,  1.39s/it, lr: 1.0e-04 loss: 1.737e-01]
latex_v1:  67%|######6   | 1997/3000 [46:43<23:13,  1.39s/it, lr: 1.0e-04 loss: 1.737e-01]
latex_v1:  67%|######6   | 1998/3000 [46:43<20:02,  1.20s/it, lr: 1.0e-04 loss: 1.737e-01]
latex_v1:  67%|######6   | 1998/3000 [46:43<20:02,  1.20s/it, lr: 1.0e-04 loss: 1.737e-01]
latex_v1:  67%|######6   | 1998/3000 [46:44<20:02,  1.20s/it, lr: 1.0e-04 loss: 8.834e-01]
latex_v1:  67%|######6   | 1998/3000 [46:44<20:02,  1.20s/it, lr: 1.0e-04 loss: 8.834e-01]
latex_v1:  67%|######6   | 1999/3000 [46:44<17:50,  1.07s/it, lr: 1.0e-04 loss: 8.834e-01]
latex_v1:  67%|######6   | 1999/3000 [46:44<17:50,  1.07s/it, lr: 1.0e-04 loss: 8.834e-01]
latex_v1:  67%|######6   | 1999/3000 [46:45<17:50,  1.07s/it, lr: 1.0e-04 loss: 5.314e-01]
latex_v1:  67%|######6   | 1999/3000 [46:45<17:50,  1.07s/it, lr: 1.0e-04 loss: 5.314e-01]
Saving at step 2000
Saved checkpoint to /data/app/output/latex_v1/latex_v1_000002000.safetensors
Saved optimizer to /data/app/output/latex_v1/optimizer.pt
Removing old save: /data/app/output/latex_v1/latex_v1_000001000.safetensors

latex_v1:  67%|######6   | 2000/3000 [46:46<17:49,  1.07s/it, lr: 1.0e-04 loss: 1.933e-01]
latex_v1:  67%|######6   | 2000/3000 [46:46<17:49,  1.07s/it, lr: 1.0e-04 loss: 1.933e-01]
latex_v1:  67%|######6   | 2001/3000 [46:46<13:22,  1.25it/s, lr: 1.0e-04 loss: 1.933e-01]
latex_v1:  67%|######6   | 2001/3000 [46:46<13:22,  1.25it/s, lr: 1.0e-04 loss: 1.933e-01]
latex_v1:  67%|######6   | 2001/3000 [46:47<13:22,  1.25it/s, lr: 1.0e-04 loss: 4.798e-01]
latex_v1:  67%|######6   | 2001/3000 [46:47<13:22,  1.25it/s, lr: 1.0e-04 loss: 4.798e-01]
latex_v1:  67%|######6   | 2002/3000 [46:47<13:07,  1.27it/s, lr: 1.0e-04 loss: 4.798e-01]
latex_v1:  67%|######6   | 2002/3000 [46:47<13:07,  1.27it/s, lr: 1.0e-04 loss: 4.798e-01]
latex_v1:  67%|######6   | 2002/3000 [46:49<13:07,  1.27it/s, lr: 1.0e-04 loss: 2.117e-01]
latex_v1:  67%|######6   | 2002/3000 [46:49<13:07,  1.27it/s, lr: 1.0e-04 loss: 2.117e-01]
latex_v1:  67%|######6   | 2003/3000 [46:49<16:21,  1.02it/s, lr: 1.0e-04 loss: 2.117e-01]
latex_v1:  67%|######6   | 2003/3000 [46:49<16:21,  1.02it/s, lr: 1.0e-04 loss: 2.117e-01]
latex_v1:  67%|######6   | 2003/3000 [46:50<16:21,  1.02it/s, lr: 1.0e-04 loss: 8.376e-01]
latex_v1:  67%|######6   | 2003/3000 [46:50<16:21,  1.02it/s, lr: 1.0e-04 loss: 8.376e-01]
latex_v1:  67%|######6   | 2004/3000 [46:50<16:13,  1.02it/s, lr: 1.0e-04 loss: 8.376e-01]
latex_v1:  67%|######6   | 2004/3000 [46:50<16:13,  1.02it/s, lr: 1.0e-04 loss: 8.376e-01]
latex_v1:  67%|######6   | 2004/3000 [46:51<16:13,  1.02it/s, lr: 1.0e-04 loss: 6.832e-01]
latex_v1:  67%|######6   | 2004/3000 [46:51<16:13,  1.02it/s, lr: 1.0e-04 loss: 6.832e-01]
latex_v1:  67%|######6   | 2005/3000 [46:51<18:47,  1.13s/it, lr: 1.0e-04 loss: 6.832e-01]
latex_v1:  67%|######6   | 2005/3000 [46:51<18:47,  1.13s/it, lr: 1.0e-04 loss: 6.832e-01]
latex_v1:  67%|######6   | 2005/3000 [46:52<18:47,  1.13s/it, lr: 1.0e-04 loss: 3.039e-01]
latex_v1:  67%|######6   | 2005/3000 [46:52<18:47,  1.13s/it, lr: 1.0e-04 loss: 3.039e-01]
latex_v1:  67%|######6   | 2006/3000 [46:52<19:31,  1.18s/it, lr: 1.0e-04 loss: 3.039e-01]
latex_v1:  67%|######6   | 2006/3000 [46:52<19:31,  1.18s/it, lr: 1.0e-04 loss: 3.039e-01]
latex_v1:  67%|######6   | 2006/3000 [46:53<19:31,  1.18s/it, lr: 1.0e-04 loss: 4.241e-01]
latex_v1:  67%|######6   | 2006/3000 [46:53<19:31,  1.18s/it, lr: 1.0e-04 loss: 4.241e-01]
latex_v1:  67%|######6   | 2007/3000 [46:53<17:28,  1.06s/it, lr: 1.0e-04 loss: 4.241e-01]
latex_v1:  67%|######6   | 2007/3000 [46:53<17:28,  1.06s/it, lr: 1.0e-04 loss: 4.241e-01]
latex_v1:  67%|######6   | 2007/3000 [46:55<17:28,  1.06s/it, lr: 1.0e-04 loss: 3.149e-01]
latex_v1:  67%|######6   | 2007/3000 [46:55<17:28,  1.06s/it, lr: 1.0e-04 loss: 3.149e-01]
latex_v1:  67%|######6   | 2008/3000 [46:55<20:40,  1.25s/it, lr: 1.0e-04 loss: 3.149e-01]
latex_v1:  67%|######6   | 2008/3000 [46:55<20:40,  1.25s/it, lr: 1.0e-04 loss: 3.149e-01]
latex_v1:  67%|######6   | 2008/3000 [46:56<20:40,  1.25s/it, lr: 1.0e-04 loss: 8.777e-02]
latex_v1:  67%|######6   | 2008/3000 [46:56<20:40,  1.25s/it, lr: 1.0e-04 loss: 8.777e-02]
latex_v1:  67%|######6   | 2009/3000 [46:56<18:14,  1.10s/it, lr: 1.0e-04 loss: 8.777e-02]
latex_v1:  67%|######6   | 2009/3000 [46:56<18:14,  1.10s/it, lr: 1.0e-04 loss: 8.777e-02]
latex_v1:  67%|######6   | 2009/3000 [46:57<18:14,  1.10s/it, lr: 1.0e-04 loss: 3.093e-01]
latex_v1:  67%|######6   | 2009/3000 [46:57<18:14,  1.10s/it, lr: 1.0e-04 loss: 3.093e-01]
latex_v1:  67%|######7   | 2010/3000 [46:58<18:13,  1.10s/it, lr: 1.0e-04 loss: 7.152e-01]
latex_v1:  67%|######7   | 2010/3000 [46:58<18:13,  1.10s/it, lr: 1.0e-04 loss: 7.152e-01]
latex_v1:  67%|######7   | 2011/3000 [46:58<12:46,  1.29it/s, lr: 1.0e-04 loss: 7.152e-01]
latex_v1:  67%|######7   | 2011/3000 [46:58<12:46,  1.29it/s, lr: 1.0e-04 loss: 7.152e-01]
latex_v1:  67%|######7   | 2011/3000 [46:59<12:46,  1.29it/s, lr: 1.0e-04 loss: 4.097e-01]
latex_v1:  67%|######7   | 2011/3000 [46:59<12:46,  1.29it/s, lr: 1.0e-04 loss: 4.097e-01]
latex_v1:  67%|######7   | 2012/3000 [46:59<12:34,  1.31it/s, lr: 1.0e-04 loss: 4.097e-01]
latex_v1:  67%|######7   | 2012/3000 [46:59<12:34,  1.31it/s, lr: 1.0e-04 loss: 4.097e-01]
latex_v1:  67%|######7   | 2012/3000 [47:00<12:34,  1.31it/s, lr: 1.0e-04 loss: 5.795e-01]
latex_v1:  67%|######7   | 2012/3000 [47:00<12:34,  1.31it/s, lr: 1.0e-04 loss: 5.795e-01]
latex_v1:  67%|######7   | 2013/3000 [47:00<14:52,  1.11it/s, lr: 1.0e-04 loss: 5.795e-01]
latex_v1:  67%|######7   | 2013/3000 [47:00<14:52,  1.11it/s, lr: 1.0e-04 loss: 5.795e-01]
latex_v1:  67%|######7   | 2013/3000 [47:02<14:52,  1.11it/s, lr: 1.0e-04 loss: 2.431e-01]
latex_v1:  67%|######7   | 2013/3000 [47:02<14:52,  1.11it/s, lr: 1.0e-04 loss: 2.431e-01]
latex_v1:  67%|######7   | 2014/3000 [47:02<19:13,  1.17s/it, lr: 1.0e-04 loss: 2.431e-01]
latex_v1:  67%|######7   | 2014/3000 [47:02<19:13,  1.17s/it, lr: 1.0e-04 loss: 2.431e-01]
latex_v1:  67%|######7   | 2014/3000 [47:03<19:13,  1.17s/it, lr: 1.0e-04 loss: 3.565e-02]
latex_v1:  67%|######7   | 2014/3000 [47:03<19:13,  1.17s/it, lr: 1.0e-04 loss: 3.565e-02]
latex_v1:  67%|######7   | 2015/3000 [47:03<20:32,  1.25s/it, lr: 1.0e-04 loss: 3.565e-02]
latex_v1:  67%|######7   | 2015/3000 [47:03<20:32,  1.25s/it, lr: 1.0e-04 loss: 3.565e-02]
latex_v1:  67%|######7   | 2015/3000 [47:05<20:32,  1.25s/it, lr: 1.0e-04 loss: 5.901e-02]
latex_v1:  67%|######7   | 2015/3000 [47:05<20:32,  1.25s/it, lr: 1.0e-04 loss: 5.901e-02]
latex_v1:  67%|######7   | 2016/3000 [47:05<23:52,  1.46s/it, lr: 1.0e-04 loss: 5.901e-02]
latex_v1:  67%|######7   | 2016/3000 [47:05<23:52,  1.46s/it, lr: 1.0e-04 loss: 5.901e-02]
latex_v1:  67%|######7   | 2016/3000 [47:06<23:52,  1.46s/it, lr: 1.0e-04 loss: 1.889e-01]
latex_v1:  67%|######7   | 2016/3000 [47:06<23:52,  1.46s/it, lr: 1.0e-04 loss: 1.889e-01]
latex_v1:  67%|######7   | 2017/3000 [47:06<23:11,  1.42s/it, lr: 1.0e-04 loss: 1.889e-01]
latex_v1:  67%|######7   | 2017/3000 [47:06<23:11,  1.42s/it, lr: 1.0e-04 loss: 1.889e-01]
latex_v1:  67%|######7   | 2017/3000 [47:08<23:11,  1.42s/it, lr: 1.0e-04 loss: 7.708e-01]
latex_v1:  67%|######7   | 2017/3000 [47:08<23:11,  1.42s/it, lr: 1.0e-04 loss: 7.708e-01]
latex_v1:  67%|######7   | 2018/3000 [47:08<23:13,  1.42s/it, lr: 1.0e-04 loss: 7.708e-01]
latex_v1:  67%|######7   | 2018/3000 [47:08<23:13,  1.42s/it, lr: 1.0e-04 loss: 7.708e-01]
latex_v1:  67%|######7   | 2018/3000 [47:09<23:13,  1.42s/it, lr: 1.0e-04 loss: 1.649e-01]
latex_v1:  67%|######7   | 2018/3000 [47:09<23:13,  1.42s/it, lr: 1.0e-04 loss: 1.649e-01]
latex_v1:  67%|######7   | 2019/3000 [47:09<19:57,  1.22s/it, lr: 1.0e-04 loss: 1.649e-01]
latex_v1:  67%|######7   | 2019/3000 [47:09<19:57,  1.22s/it, lr: 1.0e-04 loss: 1.649e-01]
latex_v1:  67%|######7   | 2019/3000 [47:09<19:57,  1.22s/it, lr: 1.0e-04 loss: 4.347e-01]
latex_v1:  67%|######7   | 2019/3000 [47:09<19:57,  1.22s/it, lr: 1.0e-04 loss: 4.347e-01]
latex_v1:  67%|######7   | 2020/3000 [47:11<19:56,  1.22s/it, lr: 1.0e-04 loss: 1.515e-01]
latex_v1:  67%|######7   | 2020/3000 [47:11<19:56,  1.22s/it, lr: 1.0e-04 loss: 1.515e-01]
latex_v1:  67%|######7   | 2021/3000 [47:11<16:40,  1.02s/it, lr: 1.0e-04 loss: 1.515e-01]
latex_v1:  67%|######7   | 2021/3000 [47:11<16:40,  1.02s/it, lr: 1.0e-04 loss: 1.515e-01]
latex_v1:  67%|######7   | 2021/3000 [47:12<16:40,  1.02s/it, lr: 1.0e-04 loss: 3.912e-01]
latex_v1:  67%|######7   | 2021/3000 [47:12<16:40,  1.02s/it, lr: 1.0e-04 loss: 3.912e-01]
latex_v1:  67%|######7   | 2022/3000 [47:12<15:30,  1.05it/s, lr: 1.0e-04 loss: 3.912e-01]
latex_v1:  67%|######7   | 2022/3000 [47:12<15:30,  1.05it/s, lr: 1.0e-04 loss: 3.912e-01]
latex_v1:  67%|######7   | 2022/3000 [47:14<15:30,  1.05it/s, lr: 1.0e-04 loss: 5.688e-01]
latex_v1:  67%|######7   | 2022/3000 [47:14<15:30,  1.05it/s, lr: 1.0e-04 loss: 5.688e-01]
latex_v1:  67%|######7   | 2023/3000 [47:14<19:14,  1.18s/it, lr: 1.0e-04 loss: 5.688e-01]
latex_v1:  67%|######7   | 2023/3000 [47:14<19:14,  1.18s/it, lr: 1.0e-04 loss: 5.688e-01]
latex_v1:  67%|######7   | 2023/3000 [47:15<19:14,  1.18s/it, lr: 1.0e-04 loss: 2.066e-01]
latex_v1:  67%|######7   | 2023/3000 [47:15<19:14,  1.18s/it, lr: 1.0e-04 loss: 2.066e-01]
latex_v1:  67%|######7   | 2024/3000 [47:15<19:51,  1.22s/it, lr: 1.0e-04 loss: 2.066e-01]
latex_v1:  67%|######7   | 2024/3000 [47:15<19:51,  1.22s/it, lr: 1.0e-04 loss: 2.066e-01]
latex_v1:  67%|######7   | 2024/3000 [47:16<19:51,  1.22s/it, lr: 1.0e-04 loss: 5.490e-01]
latex_v1:  67%|######7   | 2024/3000 [47:16<19:51,  1.22s/it, lr: 1.0e-04 loss: 5.490e-01]
latex_v1:  68%|######7   | 2025/3000 [47:16<18:56,  1.17s/it, lr: 1.0e-04 loss: 5.490e-01]
latex_v1:  68%|######7   | 2025/3000 [47:16<18:56,  1.17s/it, lr: 1.0e-04 loss: 5.490e-01]
latex_v1:  68%|######7   | 2025/3000 [47:17<18:56,  1.17s/it, lr: 1.0e-04 loss: 7.497e-02]
latex_v1:  68%|######7   | 2025/3000 [47:17<18:56,  1.17s/it, lr: 1.0e-04 loss: 7.497e-02]
latex_v1:  68%|######7   | 2026/3000 [47:17<20:38,  1.27s/it, lr: 1.0e-04 loss: 7.497e-02]
latex_v1:  68%|######7   | 2026/3000 [47:17<20:38,  1.27s/it, lr: 1.0e-04 loss: 7.497e-02]
latex_v1:  68%|######7   | 2026/3000 [47:19<20:38,  1.27s/it, lr: 1.0e-04 loss: 5.151e-01]
latex_v1:  68%|######7   | 2026/3000 [47:19<20:38,  1.27s/it, lr: 1.0e-04 loss: 5.151e-01]
latex_v1:  68%|######7   | 2027/3000 [47:19<21:20,  1.32s/it, lr: 1.0e-04 loss: 5.151e-01]
latex_v1:  68%|######7   | 2027/3000 [47:19<21:20,  1.32s/it, lr: 1.0e-04 loss: 5.151e-01]
latex_v1:  68%|######7   | 2027/3000 [47:21<21:20,  1.32s/it, lr: 1.0e-04 loss: 2.001e-01]
latex_v1:  68%|######7   | 2027/3000 [47:21<21:20,  1.32s/it, lr: 1.0e-04 loss: 2.001e-01]
latex_v1:  68%|######7   | 2028/3000 [47:21<24:29,  1.51s/it, lr: 1.0e-04 loss: 2.001e-01]
latex_v1:  68%|######7   | 2028/3000 [47:21<24:29,  1.51s/it, lr: 1.0e-04 loss: 2.001e-01]
latex_v1:  68%|######7   | 2028/3000 [47:22<24:29,  1.51s/it, lr: 1.0e-04 loss: 1.735e-01]
latex_v1:  68%|######7   | 2028/3000 [47:22<24:29,  1.51s/it, lr: 1.0e-04 loss: 1.735e-01]
latex_v1:  68%|######7   | 2029/3000 [47:22<24:31,  1.52s/it, lr: 1.0e-04 loss: 1.735e-01]
latex_v1:  68%|######7   | 2029/3000 [47:22<24:31,  1.52s/it, lr: 1.0e-04 loss: 1.735e-01]
latex_v1:  68%|######7   | 2029/3000 [47:23<24:31,  1.52s/it, lr: 1.0e-04 loss: 1.161e-01]
latex_v1:  68%|######7   | 2029/3000 [47:23<24:31,  1.52s/it, lr: 1.0e-04 loss: 1.161e-01]
latex_v1:  68%|######7   | 2030/3000 [47:24<24:29,  1.52s/it, lr: 1.0e-04 loss: 8.669e-02]
latex_v1:  68%|######7   | 2030/3000 [47:24<24:29,  1.52s/it, lr: 1.0e-04 loss: 8.669e-02]
latex_v1:  68%|######7   | 2031/3000 [47:24<17:25,  1.08s/it, lr: 1.0e-04 loss: 8.669e-02]
latex_v1:  68%|######7   | 2031/3000 [47:24<17:25,  1.08s/it, lr: 1.0e-04 loss: 8.669e-02]
latex_v1:  68%|######7   | 2031/3000 [47:26<17:25,  1.08s/it, lr: 1.0e-04 loss: 2.424e-01]
latex_v1:  68%|######7   | 2031/3000 [47:26<17:25,  1.08s/it, lr: 1.0e-04 loss: 2.424e-01]
latex_v1:  68%|######7   | 2032/3000 [47:26<18:52,  1.17s/it, lr: 1.0e-04 loss: 2.424e-01]
latex_v1:  68%|######7   | 2032/3000 [47:26<18:52,  1.17s/it, lr: 1.0e-04 loss: 2.424e-01]
latex_v1:  68%|######7   | 2032/3000 [47:27<18:52,  1.17s/it, lr: 1.0e-04 loss: 6.030e-01]
latex_v1:  68%|######7   | 2032/3000 [47:27<18:52,  1.17s/it, lr: 1.0e-04 loss: 6.030e-01]
latex_v1:  68%|######7   | 2033/3000 [47:27<19:42,  1.22s/it, lr: 1.0e-04 loss: 6.030e-01]
latex_v1:  68%|######7   | 2033/3000 [47:27<19:42,  1.22s/it, lr: 1.0e-04 loss: 6.030e-01]
latex_v1:  68%|######7   | 2033/3000 [47:28<19:42,  1.22s/it, lr: 1.0e-04 loss: 1.034e-01]
latex_v1:  68%|######7   | 2033/3000 [47:28<19:42,  1.22s/it, lr: 1.0e-04 loss: 1.034e-01]
latex_v1:  68%|######7   | 2034/3000 [47:28<18:54,  1.17s/it, lr: 1.0e-04 loss: 1.034e-01]
latex_v1:  68%|######7   | 2034/3000 [47:28<18:54,  1.17s/it, lr: 1.0e-04 loss: 1.034e-01]
latex_v1:  68%|######7   | 2034/3000 [47:29<18:54,  1.17s/it, lr: 1.0e-04 loss: 2.204e-01]
latex_v1:  68%|######7   | 2034/3000 [47:29<18:54,  1.17s/it, lr: 1.0e-04 loss: 2.204e-01]
latex_v1:  68%|######7   | 2035/3000 [47:29<16:50,  1.05s/it, lr: 1.0e-04 loss: 2.204e-01]
latex_v1:  68%|######7   | 2035/3000 [47:29<16:50,  1.05s/it, lr: 1.0e-04 loss: 2.204e-01]
latex_v1:  68%|######7   | 2035/3000 [47:30<16:50,  1.05s/it, lr: 1.0e-04 loss: 4.171e-01]
latex_v1:  68%|######7   | 2035/3000 [47:30<16:50,  1.05s/it, lr: 1.0e-04 loss: 4.171e-01]
latex_v1:  68%|######7   | 2036/3000 [47:30<15:24,  1.04it/s, lr: 1.0e-04 loss: 4.171e-01]
latex_v1:  68%|######7   | 2036/3000 [47:30<15:24,  1.04it/s, lr: 1.0e-04 loss: 4.171e-01]
latex_v1:  68%|######7   | 2036/3000 [47:30<15:24,  1.04it/s, lr: 1.0e-04 loss: 1.469e-01]
latex_v1:  68%|######7   | 2036/3000 [47:30<15:24,  1.04it/s, lr: 1.0e-04 loss: 1.469e-01]
latex_v1:  68%|######7   | 2037/3000 [47:30<14:23,  1.11it/s, lr: 1.0e-04 loss: 1.469e-01]
latex_v1:  68%|######7   | 2037/3000 [47:30<14:23,  1.11it/s, lr: 1.0e-04 loss: 1.469e-01]
latex_v1:  68%|######7   | 2037/3000 [47:31<14:23,  1.11it/s, lr: 1.0e-04 loss: 1.743e-01]
latex_v1:  68%|######7   | 2037/3000 [47:31<14:23,  1.11it/s, lr: 1.0e-04 loss: 1.743e-01]
latex_v1:  68%|######7   | 2038/3000 [47:31<13:39,  1.17it/s, lr: 1.0e-04 loss: 1.743e-01]
latex_v1:  68%|######7   | 2038/3000 [47:31<13:39,  1.17it/s, lr: 1.0e-04 loss: 1.743e-01]
latex_v1:  68%|######7   | 2038/3000 [47:32<13:39,  1.17it/s, lr: 1.0e-04 loss: 8.022e-01]
latex_v1:  68%|######7   | 2038/3000 [47:32<13:39,  1.17it/s, lr: 1.0e-04 loss: 8.022e-01]
latex_v1:  68%|######7   | 2039/3000 [47:32<15:07,  1.06it/s, lr: 1.0e-04 loss: 8.022e-01]
latex_v1:  68%|######7   | 2039/3000 [47:32<15:07,  1.06it/s, lr: 1.0e-04 loss: 8.022e-01]
latex_v1:  68%|######7   | 2039/3000 [47:33<15:07,  1.06it/s, lr: 1.0e-04 loss: 6.713e-01]
latex_v1:  68%|######7   | 2039/3000 [47:33<15:07,  1.06it/s, lr: 1.0e-04 loss: 6.713e-01]
latex_v1:  68%|######8   | 2040/3000 [47:35<15:06,  1.06it/s, lr: 1.0e-04 loss: 4.605e-01]
latex_v1:  68%|######8   | 2040/3000 [47:35<15:06,  1.06it/s, lr: 1.0e-04 loss: 4.605e-01]
latex_v1:  68%|######8   | 2041/3000 [47:35<13:02,  1.23it/s, lr: 1.0e-04 loss: 4.605e-01]
latex_v1:  68%|######8   | 2041/3000 [47:35<13:02,  1.23it/s, lr: 1.0e-04 loss: 4.605e-01]
latex_v1:  68%|######8   | 2041/3000 [47:36<13:02,  1.23it/s, lr: 1.0e-04 loss: 5.125e-01]
latex_v1:  68%|######8   | 2041/3000 [47:36<13:02,  1.23it/s, lr: 1.0e-04 loss: 5.125e-01]
latex_v1:  68%|######8   | 2042/3000 [47:36<16:04,  1.01s/it, lr: 1.0e-04 loss: 5.125e-01]
latex_v1:  68%|######8   | 2042/3000 [47:36<16:04,  1.01s/it, lr: 1.0e-04 loss: 5.125e-01]
latex_v1:  68%|######8   | 2042/3000 [47:39<16:04,  1.01s/it, lr: 1.0e-04 loss: 8.879e-02]
latex_v1:  68%|######8   | 2042/3000 [47:39<16:04,  1.01s/it, lr: 1.0e-04 loss: 8.879e-02]
latex_v1:  68%|######8   | 2043/3000 [47:39<23:44,  1.49s/it, lr: 1.0e-04 loss: 8.879e-02]
latex_v1:  68%|######8   | 2043/3000 [47:39<23:44,  1.49s/it, lr: 1.0e-04 loss: 8.879e-02]
latex_v1:  68%|######8   | 2043/3000 [47:41<23:44,  1.49s/it, lr: 1.0e-04 loss: 3.204e-01]
latex_v1:  68%|######8   | 2043/3000 [47:41<23:44,  1.49s/it, lr: 1.0e-04 loss: 3.204e-01]
latex_v1:  68%|######8   | 2044/3000 [47:41<23:34,  1.48s/it, lr: 1.0e-04 loss: 3.204e-01]
latex_v1:  68%|######8   | 2044/3000 [47:41<23:34,  1.48s/it, lr: 1.0e-04 loss: 3.204e-01]
latex_v1:  68%|######8   | 2044/3000 [47:41<23:34,  1.48s/it, lr: 1.0e-04 loss: 3.239e-01]
latex_v1:  68%|######8   | 2044/3000 [47:41<23:34,  1.48s/it, lr: 1.0e-04 loss: 3.239e-01]
latex_v1:  68%|######8   | 2045/3000 [47:41<20:21,  1.28s/it, lr: 1.0e-04 loss: 3.239e-01]
latex_v1:  68%|######8   | 2045/3000 [47:41<20:21,  1.28s/it, lr: 1.0e-04 loss: 3.239e-01]
latex_v1:  68%|######8   | 2045/3000 [47:45<20:21,  1.28s/it, lr: 1.0e-04 loss: 4.810e-01]
latex_v1:  68%|######8   | 2045/3000 [47:45<20:21,  1.28s/it, lr: 1.0e-04 loss: 4.810e-01]
latex_v1:  68%|######8   | 2046/3000 [47:45<27:43,  1.74s/it, lr: 1.0e-04 loss: 4.810e-01]
latex_v1:  68%|######8   | 2046/3000 [47:45<27:43,  1.74s/it, lr: 1.0e-04 loss: 4.810e-01]
latex_v1:  68%|######8   | 2046/3000 [47:45<27:43,  1.74s/it, lr: 1.0e-04 loss: 1.727e-01]
latex_v1:  68%|######8   | 2046/3000 [47:45<27:43,  1.74s/it, lr: 1.0e-04 loss: 1.727e-01]
latex_v1:  68%|######8   | 2047/3000 [47:45<23:08,  1.46s/it, lr: 1.0e-04 loss: 1.727e-01]
latex_v1:  68%|######8   | 2047/3000 [47:45<23:08,  1.46s/it, lr: 1.0e-04 loss: 1.727e-01]
latex_v1:  68%|######8   | 2047/3000 [47:47<23:08,  1.46s/it, lr: 1.0e-04 loss: 3.110e-01]
latex_v1:  68%|######8   | 2047/3000 [47:47<23:08,  1.46s/it, lr: 1.0e-04 loss: 3.110e-01]
latex_v1:  68%|######8   | 2048/3000 [47:47<23:35,  1.49s/it, lr: 1.0e-04 loss: 3.110e-01]
latex_v1:  68%|######8   | 2048/3000 [47:47<23:35,  1.49s/it, lr: 1.0e-04 loss: 3.110e-01]
latex_v1:  68%|######8   | 2048/3000 [47:48<23:35,  1.49s/it, lr: 1.0e-04 loss: 5.851e-01]
latex_v1:  68%|######8   | 2048/3000 [47:48<23:35,  1.49s/it, lr: 1.0e-04 loss: 5.851e-01]
latex_v1:  68%|######8   | 2049/3000 [47:48<23:40,  1.49s/it, lr: 1.0e-04 loss: 5.851e-01]
latex_v1:  68%|######8   | 2049/3000 [47:48<23:40,  1.49s/it, lr: 1.0e-04 loss: 5.851e-01]
latex_v1:  68%|######8   | 2049/3000 [47:49<23:40,  1.49s/it, lr: 1.0e-04 loss: 8.159e-01]
latex_v1:  68%|######8   | 2049/3000 [47:49<23:40,  1.49s/it, lr: 1.0e-04 loss: 8.159e-01]
latex_v1:  68%|######8   | 2050/3000 [47:51<23:39,  1.49s/it, lr: 1.0e-04 loss: 2.559e-01]
latex_v1:  68%|######8   | 2050/3000 [47:51<23:39,  1.49s/it, lr: 1.0e-04 loss: 2.559e-01]
latex_v1:  68%|######8   | 2051/3000 [47:51<18:32,  1.17s/it, lr: 1.0e-04 loss: 2.559e-01]
latex_v1:  68%|######8   | 2051/3000 [47:51<18:32,  1.17s/it, lr: 1.0e-04 loss: 2.559e-01]
latex_v1:  68%|######8   | 2051/3000 [47:53<18:32,  1.17s/it, lr: 1.0e-04 loss: 1.760e-01]
latex_v1:  68%|######8   | 2051/3000 [47:53<18:32,  1.17s/it, lr: 1.0e-04 loss: 1.760e-01]
latex_v1:  68%|######8   | 2052/3000 [47:53<21:21,  1.35s/it, lr: 1.0e-04 loss: 1.760e-01]
latex_v1:  68%|######8   | 2052/3000 [47:53<21:21,  1.35s/it, lr: 1.0e-04 loss: 1.760e-01]
latex_v1:  68%|######8   | 2052/3000 [47:54<21:21,  1.35s/it, lr: 1.0e-04 loss: 6.873e-02]
latex_v1:  68%|######8   | 2052/3000 [47:54<21:21,  1.35s/it, lr: 1.0e-04 loss: 6.873e-02]
latex_v1:  68%|######8   | 2053/3000 [47:54<21:45,  1.38s/it, lr: 1.0e-04 loss: 6.873e-02]
latex_v1:  68%|######8   | 2053/3000 [47:54<21:45,  1.38s/it, lr: 1.0e-04 loss: 6.873e-02]
latex_v1:  68%|######8   | 2053/3000 [47:55<21:45,  1.38s/it, lr: 1.0e-04 loss: 3.101e-01]
latex_v1:  68%|######8   | 2053/3000 [47:55<21:45,  1.38s/it, lr: 1.0e-04 loss: 3.101e-01]
latex_v1:  68%|######8   | 2054/3000 [47:55<19:06,  1.21s/it, lr: 1.0e-04 loss: 3.101e-01]
latex_v1:  68%|######8   | 2054/3000 [47:55<19:06,  1.21s/it, lr: 1.0e-04 loss: 3.101e-01]
latex_v1:  68%|######8   | 2054/3000 [47:56<19:06,  1.21s/it, lr: 1.0e-04 loss: 1.260e-01]
latex_v1:  68%|######8   | 2054/3000 [47:56<19:06,  1.21s/it, lr: 1.0e-04 loss: 1.260e-01]
latex_v1:  68%|######8   | 2055/3000 [47:56<18:28,  1.17s/it, lr: 1.0e-04 loss: 1.260e-01]
latex_v1:  68%|######8   | 2055/3000 [47:56<18:28,  1.17s/it, lr: 1.0e-04 loss: 1.260e-01]
latex_v1:  68%|######8   | 2055/3000 [47:59<18:28,  1.17s/it, lr: 1.0e-04 loss: 4.255e-01]
latex_v1:  68%|######8   | 2055/3000 [47:59<18:28,  1.17s/it, lr: 1.0e-04 loss: 4.255e-01]
latex_v1:  69%|######8   | 2056/3000 [47:59<26:14,  1.67s/it, lr: 1.0e-04 loss: 4.255e-01]
latex_v1:  69%|######8   | 2056/3000 [47:59<26:14,  1.67s/it, lr: 1.0e-04 loss: 4.255e-01]
latex_v1:  69%|######8   | 2056/3000 [48:01<26:14,  1.67s/it, lr: 1.0e-04 loss: 2.451e-01]
latex_v1:  69%|######8   | 2056/3000 [48:01<26:14,  1.67s/it, lr: 1.0e-04 loss: 2.451e-01]
latex_v1:  69%|######8   | 2057/3000 [48:01<25:41,  1.63s/it, lr: 1.0e-04 loss: 2.451e-01]
latex_v1:  69%|######8   | 2057/3000 [48:01<25:41,  1.63s/it, lr: 1.0e-04 loss: 2.451e-01]
latex_v1:  69%|######8   | 2057/3000 [48:01<25:41,  1.63s/it, lr: 1.0e-04 loss: 4.981e-01]
latex_v1:  69%|######8   | 2057/3000 [48:01<25:41,  1.63s/it, lr: 1.0e-04 loss: 4.981e-01]
latex_v1:  69%|######8   | 2058/3000 [48:01<21:32,  1.37s/it, lr: 1.0e-04 loss: 4.981e-01]
latex_v1:  69%|######8   | 2058/3000 [48:01<21:32,  1.37s/it, lr: 1.0e-04 loss: 4.981e-01]
latex_v1:  69%|######8   | 2058/3000 [48:03<21:32,  1.37s/it, lr: 1.0e-04 loss: 3.448e-02]
latex_v1:  69%|######8   | 2058/3000 [48:03<21:32,  1.37s/it, lr: 1.0e-04 loss: 3.448e-02]
latex_v1:  69%|######8   | 2059/3000 [48:03<21:21,  1.36s/it, lr: 1.0e-04 loss: 3.448e-02]
latex_v1:  69%|######8   | 2059/3000 [48:03<21:21,  1.36s/it, lr: 1.0e-04 loss: 3.448e-02]
latex_v1:  69%|######8   | 2059/3000 [48:04<21:21,  1.36s/it, lr: 1.0e-04 loss: 5.830e-01]
latex_v1:  69%|######8   | 2059/3000 [48:04<21:21,  1.36s/it, lr: 1.0e-04 loss: 5.830e-01]
latex_v1:  69%|######8   | 2060/3000 [48:05<21:19,  1.36s/it, lr: 1.0e-04 loss: 5.372e-01]
latex_v1:  69%|######8   | 2060/3000 [48:05<21:19,  1.36s/it, lr: 1.0e-04 loss: 5.372e-01]
latex_v1:  69%|######8   | 2061/3000 [48:05<15:21,  1.02it/s, lr: 1.0e-04 loss: 5.372e-01]
latex_v1:  69%|######8   | 2061/3000 [48:05<15:21,  1.02it/s, lr: 1.0e-04 loss: 5.372e-01]
latex_v1:  69%|######8   | 2061/3000 [48:06<15:21,  1.02it/s, lr: 1.0e-04 loss: 2.043e-01]
latex_v1:  69%|######8   | 2061/3000 [48:06<15:21,  1.02it/s, lr: 1.0e-04 loss: 2.043e-01]
latex_v1:  69%|######8   | 2062/3000 [48:06<16:51,  1.08s/it, lr: 1.0e-04 loss: 2.043e-01]
latex_v1:  69%|######8   | 2062/3000 [48:06<16:51,  1.08s/it, lr: 1.0e-04 loss: 2.043e-01]
latex_v1:  69%|######8   | 2062/3000 [48:07<16:51,  1.08s/it, lr: 1.0e-04 loss: 5.075e-02]
latex_v1:  69%|######8   | 2062/3000 [48:07<16:51,  1.08s/it, lr: 1.0e-04 loss: 5.075e-02]
latex_v1:  69%|######8   | 2063/3000 [48:07<18:24,  1.18s/it, lr: 1.0e-04 loss: 5.075e-02]
latex_v1:  69%|######8   | 2063/3000 [48:07<18:24,  1.18s/it, lr: 1.0e-04 loss: 5.075e-02]
latex_v1:  69%|######8   | 2063/3000 [48:09<18:24,  1.18s/it, lr: 1.0e-04 loss: 7.847e-02]
latex_v1:  69%|######8   | 2063/3000 [48:09<18:24,  1.18s/it, lr: 1.0e-04 loss: 7.847e-02]
latex_v1:  69%|######8   | 2064/3000 [48:09<19:56,  1.28s/it, lr: 1.0e-04 loss: 7.847e-02]
latex_v1:  69%|######8   | 2064/3000 [48:09<19:56,  1.28s/it, lr: 1.0e-04 loss: 7.847e-02]
latex_v1:  69%|######8   | 2064/3000 [48:10<19:56,  1.28s/it, lr: 1.0e-04 loss: 2.187e-01]
latex_v1:  69%|######8   | 2064/3000 [48:10<19:56,  1.28s/it, lr: 1.0e-04 loss: 2.187e-01]
latex_v1:  69%|######8   | 2065/3000 [48:10<20:09,  1.29s/it, lr: 1.0e-04 loss: 2.187e-01]
latex_v1:  69%|######8   | 2065/3000 [48:10<20:09,  1.29s/it, lr: 1.0e-04 loss: 2.187e-01]
latex_v1:  69%|######8   | 2065/3000 [48:11<20:09,  1.29s/it, lr: 1.0e-04 loss: 9.543e-02]
latex_v1:  69%|######8   | 2065/3000 [48:11<20:09,  1.29s/it, lr: 1.0e-04 loss: 9.543e-02]
latex_v1:  69%|######8   | 2066/3000 [48:11<17:46,  1.14s/it, lr: 1.0e-04 loss: 9.543e-02]
latex_v1:  69%|######8   | 2066/3000 [48:11<17:46,  1.14s/it, lr: 1.0e-04 loss: 9.543e-02]
latex_v1:  69%|######8   | 2066/3000 [48:12<17:46,  1.14s/it, lr: 1.0e-04 loss: 2.567e-01]
latex_v1:  69%|######8   | 2066/3000 [48:12<17:46,  1.14s/it, lr: 1.0e-04 loss: 2.567e-01]
latex_v1:  69%|######8   | 2067/3000 [48:12<15:59,  1.03s/it, lr: 1.0e-04 loss: 2.567e-01]
latex_v1:  69%|######8   | 2067/3000 [48:12<15:59,  1.03s/it, lr: 1.0e-04 loss: 2.567e-01]
latex_v1:  69%|######8   | 2067/3000 [48:13<15:59,  1.03s/it, lr: 1.0e-04 loss: 4.523e-01]
latex_v1:  69%|######8   | 2067/3000 [48:13<15:59,  1.03s/it, lr: 1.0e-04 loss: 4.523e-01]
latex_v1:  69%|######8   | 2068/3000 [48:14<19:05,  1.23s/it, lr: 1.0e-04 loss: 4.523e-01]
latex_v1:  69%|######8   | 2068/3000 [48:14<19:05,  1.23s/it, lr: 1.0e-04 loss: 4.523e-01]
latex_v1:  69%|######8   | 2068/3000 [48:15<19:05,  1.23s/it, lr: 1.0e-04 loss: 1.015e-01]
latex_v1:  69%|######8   | 2068/3000 [48:15<19:05,  1.23s/it, lr: 1.0e-04 loss: 1.015e-01]
latex_v1:  69%|######8   | 2069/3000 [48:15<20:27,  1.32s/it, lr: 1.0e-04 loss: 1.015e-01]
latex_v1:  69%|######8   | 2069/3000 [48:15<20:27,  1.32s/it, lr: 1.0e-04 loss: 1.015e-01]
latex_v1:  69%|######8   | 2069/3000 [48:16<20:27,  1.32s/it, lr: 1.0e-04 loss: 3.033e-01]
latex_v1:  69%|######8   | 2069/3000 [48:16<20:27,  1.32s/it, lr: 1.0e-04 loss: 3.033e-01]
latex_v1:  69%|######9   | 2070/3000 [48:17<20:26,  1.32s/it, lr: 1.0e-04 loss: 5.733e-01]
latex_v1:  69%|######9   | 2070/3000 [48:17<20:26,  1.32s/it, lr: 1.0e-04 loss: 5.733e-01]
latex_v1:  69%|######9   | 2071/3000 [48:17<16:14,  1.05s/it, lr: 1.0e-04 loss: 5.733e-01]
latex_v1:  69%|######9   | 2071/3000 [48:17<16:14,  1.05s/it, lr: 1.0e-04 loss: 5.733e-01]
latex_v1:  69%|######9   | 2071/3000 [48:20<16:14,  1.05s/it, lr: 1.0e-04 loss: 6.849e-01]
latex_v1:  69%|######9   | 2071/3000 [48:20<16:14,  1.05s/it, lr: 1.0e-04 loss: 6.849e-01]
latex_v1:  69%|######9   | 2072/3000 [48:20<23:07,  1.50s/it, lr: 1.0e-04 loss: 6.849e-01]
latex_v1:  69%|######9   | 2072/3000 [48:20<23:07,  1.50s/it, lr: 1.0e-04 loss: 6.849e-01]
latex_v1:  69%|######9   | 2072/3000 [48:21<23:07,  1.50s/it, lr: 1.0e-04 loss: 5.135e-01]
latex_v1:  69%|######9   | 2072/3000 [48:21<23:07,  1.50s/it, lr: 1.0e-04 loss: 5.135e-01]
latex_v1:  69%|######9   | 2073/3000 [48:21<20:04,  1.30s/it, lr: 1.0e-04 loss: 5.135e-01]
latex_v1:  69%|######9   | 2073/3000 [48:21<20:04,  1.30s/it, lr: 1.0e-04 loss: 5.135e-01]
latex_v1:  69%|######9   | 2073/3000 [48:22<20:04,  1.30s/it, lr: 1.0e-04 loss: 6.040e-01]
latex_v1:  69%|######9   | 2073/3000 [48:22<20:04,  1.30s/it, lr: 1.0e-04 loss: 6.040e-01]
latex_v1:  69%|######9   | 2074/3000 [48:22<17:43,  1.15s/it, lr: 1.0e-04 loss: 6.040e-01]
latex_v1:  69%|######9   | 2074/3000 [48:22<17:43,  1.15s/it, lr: 1.0e-04 loss: 6.040e-01]
latex_v1:  69%|######9   | 2074/3000 [48:23<17:43,  1.15s/it, lr: 1.0e-04 loss: 4.053e-01]
latex_v1:  69%|######9   | 2074/3000 [48:23<17:43,  1.15s/it, lr: 1.0e-04 loss: 4.053e-01]
latex_v1:  69%|######9   | 2075/3000 [48:23<19:54,  1.29s/it, lr: 1.0e-04 loss: 4.053e-01]
latex_v1:  69%|######9   | 2075/3000 [48:23<19:54,  1.29s/it, lr: 1.0e-04 loss: 4.053e-01]
latex_v1:  69%|######9   | 2075/3000 [48:25<19:54,  1.29s/it, lr: 1.0e-04 loss: 2.160e-01]
latex_v1:  69%|######9   | 2075/3000 [48:25<19:54,  1.29s/it, lr: 1.0e-04 loss: 2.160e-01]
latex_v1:  69%|######9   | 2076/3000 [48:25<22:35,  1.47s/it, lr: 1.0e-04 loss: 2.160e-01]
latex_v1:  69%|######9   | 2076/3000 [48:25<22:35,  1.47s/it, lr: 1.0e-04 loss: 2.160e-01]
latex_v1:  69%|######9   | 2076/3000 [48:27<22:35,  1.47s/it, lr: 1.0e-04 loss: 4.964e-01]
latex_v1:  69%|######9   | 2076/3000 [48:27<22:35,  1.47s/it, lr: 1.0e-04 loss: 4.964e-01]
latex_v1:  69%|######9   | 2077/3000 [48:27<22:21,  1.45s/it, lr: 1.0e-04 loss: 4.964e-01]
latex_v1:  69%|######9   | 2077/3000 [48:27<22:21,  1.45s/it, lr: 1.0e-04 loss: 4.964e-01]
latex_v1:  69%|######9   | 2077/3000 [48:29<22:21,  1.45s/it, lr: 1.0e-04 loss: 6.064e-01]
latex_v1:  69%|######9   | 2077/3000 [48:29<22:21,  1.45s/it, lr: 1.0e-04 loss: 6.064e-01]
latex_v1:  69%|######9   | 2078/3000 [48:29<28:33,  1.86s/it, lr: 1.0e-04 loss: 6.064e-01]
latex_v1:  69%|######9   | 2078/3000 [48:29<28:33,  1.86s/it, lr: 1.0e-04 loss: 6.064e-01]
latex_v1:  69%|######9   | 2078/3000 [48:31<28:33,  1.86s/it, lr: 1.0e-04 loss: 1.657e-01]
latex_v1:  69%|######9   | 2078/3000 [48:31<28:33,  1.86s/it, lr: 1.0e-04 loss: 1.657e-01]
latex_v1:  69%|######9   | 2079/3000 [48:31<26:29,  1.73s/it, lr: 1.0e-04 loss: 1.657e-01]
latex_v1:  69%|######9   | 2079/3000 [48:31<26:29,  1.73s/it, lr: 1.0e-04 loss: 1.657e-01]
latex_v1:  69%|######9   | 2079/3000 [48:33<26:29,  1.73s/it, lr: 1.0e-04 loss: 4.625e-01]
latex_v1:  69%|######9   | 2079/3000 [48:33<26:29,  1.73s/it, lr: 1.0e-04 loss: 4.625e-01]
latex_v1:  69%|######9   | 2080/3000 [48:34<26:27,  1.73s/it, lr: 1.0e-04 loss: 3.532e-01]
latex_v1:  69%|######9   | 2080/3000 [48:34<26:27,  1.73s/it, lr: 1.0e-04 loss: 3.532e-01]
latex_v1:  69%|######9   | 2081/3000 [48:34<19:03,  1.24s/it, lr: 1.0e-04 loss: 3.532e-01]
latex_v1:  69%|######9   | 2081/3000 [48:34<19:03,  1.24s/it, lr: 1.0e-04 loss: 3.532e-01]
latex_v1:  69%|######9   | 2081/3000 [48:35<19:03,  1.24s/it, lr: 1.0e-04 loss: 6.211e-01]
latex_v1:  69%|######9   | 2081/3000 [48:35<19:03,  1.24s/it, lr: 1.0e-04 loss: 6.211e-01]
latex_v1:  69%|######9   | 2082/3000 [48:35<17:16,  1.13s/it, lr: 1.0e-04 loss: 6.211e-01]
latex_v1:  69%|######9   | 2082/3000 [48:35<17:16,  1.13s/it, lr: 1.0e-04 loss: 6.211e-01]
latex_v1:  69%|######9   | 2082/3000 [48:37<17:16,  1.13s/it, lr: 1.0e-04 loss: 1.802e-01]
latex_v1:  69%|######9   | 2082/3000 [48:37<17:16,  1.13s/it, lr: 1.0e-04 loss: 1.802e-01]
latex_v1:  69%|######9   | 2083/3000 [48:37<20:45,  1.36s/it, lr: 1.0e-04 loss: 1.802e-01]
latex_v1:  69%|######9   | 2083/3000 [48:37<20:45,  1.36s/it, lr: 1.0e-04 loss: 1.802e-01]
latex_v1:  69%|######9   | 2083/3000 [48:39<20:45,  1.36s/it, lr: 1.0e-04 loss: 8.372e-02]
latex_v1:  69%|######9   | 2083/3000 [48:39<20:45,  1.36s/it, lr: 1.0e-04 loss: 8.372e-02]
latex_v1:  69%|######9   | 2084/3000 [48:39<24:04,  1.58s/it, lr: 1.0e-04 loss: 8.372e-02]
latex_v1:  69%|######9   | 2084/3000 [48:39<24:04,  1.58s/it, lr: 1.0e-04 loss: 8.372e-02]
latex_v1:  69%|######9   | 2084/3000 [48:40<24:04,  1.58s/it, lr: 1.0e-04 loss: 3.603e-01]
latex_v1:  69%|######9   | 2084/3000 [48:40<24:04,  1.58s/it, lr: 1.0e-04 loss: 3.603e-01]
latex_v1:  70%|######9   | 2085/3000 [48:40<20:27,  1.34s/it, lr: 1.0e-04 loss: 3.603e-01]
latex_v1:  70%|######9   | 2085/3000 [48:40<20:27,  1.34s/it, lr: 1.0e-04 loss: 3.603e-01]
latex_v1:  70%|######9   | 2085/3000 [48:42<20:27,  1.34s/it, lr: 1.0e-04 loss: 2.155e-01]
latex_v1:  70%|######9   | 2085/3000 [48:42<20:27,  1.34s/it, lr: 1.0e-04 loss: 2.155e-01]
latex_v1:  70%|######9   | 2086/3000 [48:42<22:43,  1.49s/it, lr: 1.0e-04 loss: 2.155e-01]
latex_v1:  70%|######9   | 2086/3000 [48:42<22:43,  1.49s/it, lr: 1.0e-04 loss: 2.155e-01]
latex_v1:  70%|######9   | 2086/3000 [48:43<22:43,  1.49s/it, lr: 1.0e-04 loss: 6.758e-01]
latex_v1:  70%|######9   | 2086/3000 [48:43<22:43,  1.49s/it, lr: 1.0e-04 loss: 6.758e-01]
latex_v1:  70%|######9   | 2087/3000 [48:43<22:50,  1.50s/it, lr: 1.0e-04 loss: 6.758e-01]
latex_v1:  70%|######9   | 2087/3000 [48:43<22:50,  1.50s/it, lr: 1.0e-04 loss: 6.758e-01]
latex_v1:  70%|######9   | 2087/3000 [48:45<22:50,  1.50s/it, lr: 1.0e-04 loss: 3.523e-01]
latex_v1:  70%|######9   | 2087/3000 [48:45<22:50,  1.50s/it, lr: 1.0e-04 loss: 3.523e-01]
latex_v1:  70%|######9   | 2088/3000 [48:45<23:48,  1.57s/it, lr: 1.0e-04 loss: 3.523e-01]
latex_v1:  70%|######9   | 2088/3000 [48:45<23:48,  1.57s/it, lr: 1.0e-04 loss: 3.523e-01]
latex_v1:  70%|######9   | 2088/3000 [48:46<23:48,  1.57s/it, lr: 1.0e-04 loss: 8.168e-02]
latex_v1:  70%|######9   | 2088/3000 [48:46<23:48,  1.57s/it, lr: 1.0e-04 loss: 8.168e-02]
latex_v1:  70%|######9   | 2089/3000 [48:46<20:09,  1.33s/it, lr: 1.0e-04 loss: 8.168e-02]
latex_v1:  70%|######9   | 2089/3000 [48:46<20:09,  1.33s/it, lr: 1.0e-04 loss: 8.168e-02]
latex_v1:  70%|######9   | 2089/3000 [48:48<20:09,  1.33s/it, lr: 1.0e-04 loss: 1.471e-01]
latex_v1:  70%|######9   | 2089/3000 [48:48<20:09,  1.33s/it, lr: 1.0e-04 loss: 1.471e-01]
latex_v1:  70%|######9   | 2090/3000 [48:49<20:08,  1.33s/it, lr: 1.0e-04 loss: 6.199e-01]
latex_v1:  70%|######9   | 2090/3000 [48:49<20:08,  1.33s/it, lr: 1.0e-04 loss: 6.199e-01]
latex_v1:  70%|######9   | 2091/3000 [48:49<13:27,  1.13it/s, lr: 1.0e-04 loss: 6.199e-01]
latex_v1:  70%|######9   | 2091/3000 [48:49<13:27,  1.13it/s, lr: 1.0e-04 loss: 6.199e-01]
latex_v1:  70%|######9   | 2091/3000 [48:50<13:27,  1.13it/s, lr: 1.0e-04 loss: 1.388e-01]
latex_v1:  70%|######9   | 2091/3000 [48:50<13:27,  1.13it/s, lr: 1.0e-04 loss: 1.388e-01]
latex_v1:  70%|######9   | 2092/3000 [48:50<12:55,  1.17it/s, lr: 1.0e-04 loss: 1.388e-01]
latex_v1:  70%|######9   | 2092/3000 [48:50<12:55,  1.17it/s, lr: 1.0e-04 loss: 1.388e-01]
latex_v1:  70%|######9   | 2092/3000 [48:51<12:55,  1.17it/s, lr: 1.0e-04 loss: 5.808e-01]
latex_v1:  70%|######9   | 2092/3000 [48:51<12:55,  1.17it/s, lr: 1.0e-04 loss: 5.808e-01]
latex_v1:  70%|######9   | 2093/3000 [48:51<12:28,  1.21it/s, lr: 1.0e-04 loss: 5.808e-01]
latex_v1:  70%|######9   | 2093/3000 [48:51<12:28,  1.21it/s, lr: 1.0e-04 loss: 5.808e-01]
latex_v1:  70%|######9   | 2093/3000 [48:51<12:28,  1.21it/s, lr: 1.0e-04 loss: 5.313e-01]
latex_v1:  70%|######9   | 2093/3000 [48:51<12:28,  1.21it/s, lr: 1.0e-04 loss: 5.313e-01]
latex_v1:  70%|######9   | 2094/3000 [48:51<12:13,  1.24it/s, lr: 1.0e-04 loss: 5.313e-01]
latex_v1:  70%|######9   | 2094/3000 [48:51<12:13,  1.24it/s, lr: 1.0e-04 loss: 5.313e-01]
latex_v1:  70%|######9   | 2094/3000 [48:52<12:13,  1.24it/s, lr: 1.0e-04 loss: 5.654e-01]
latex_v1:  70%|######9   | 2094/3000 [48:52<12:13,  1.24it/s, lr: 1.0e-04 loss: 5.654e-01]
latex_v1:  70%|######9   | 2095/3000 [48:52<13:14,  1.14it/s, lr: 1.0e-04 loss: 5.654e-01]
latex_v1:  70%|######9   | 2095/3000 [48:52<13:14,  1.14it/s, lr: 1.0e-04 loss: 5.654e-01]
latex_v1:  70%|######9   | 2095/3000 [48:54<13:14,  1.14it/s, lr: 1.0e-04 loss: 3.556e-01]
latex_v1:  70%|######9   | 2095/3000 [48:54<13:14,  1.14it/s, lr: 1.0e-04 loss: 3.556e-01]
latex_v1:  70%|######9   | 2096/3000 [48:54<14:13,  1.06it/s, lr: 1.0e-04 loss: 3.556e-01]
latex_v1:  70%|######9   | 2096/3000 [48:54<14:13,  1.06it/s, lr: 1.0e-04 loss: 3.556e-01]
latex_v1:  70%|######9   | 2096/3000 [48:55<14:13,  1.06it/s, lr: 1.0e-04 loss: 3.151e-02]
latex_v1:  70%|######9   | 2096/3000 [48:55<14:13,  1.06it/s, lr: 1.0e-04 loss: 3.151e-02]
latex_v1:  70%|######9   | 2097/3000 [48:55<14:27,  1.04it/s, lr: 1.0e-04 loss: 3.151e-02]
latex_v1:  70%|######9   | 2097/3000 [48:55<14:27,  1.04it/s, lr: 1.0e-04 loss: 3.151e-02]
latex_v1:  70%|######9   | 2097/3000 [48:55<14:27,  1.04it/s, lr: 1.0e-04 loss: 5.136e-01]
latex_v1:  70%|######9   | 2097/3000 [48:55<14:27,  1.04it/s, lr: 1.0e-04 loss: 5.136e-01]
latex_v1:  70%|######9   | 2098/3000 [48:55<13:34,  1.11it/s, lr: 1.0e-04 loss: 5.136e-01]
latex_v1:  70%|######9   | 2098/3000 [48:55<13:34,  1.11it/s, lr: 1.0e-04 loss: 5.136e-01]
latex_v1:  70%|######9   | 2098/3000 [48:56<13:34,  1.11it/s, lr: 1.0e-04 loss: 1.689e-01]
latex_v1:  70%|######9   | 2098/3000 [48:56<13:34,  1.11it/s, lr: 1.0e-04 loss: 1.689e-01]
latex_v1:  70%|######9   | 2099/3000 [48:56<12:53,  1.16it/s, lr: 1.0e-04 loss: 1.689e-01]
latex_v1:  70%|######9   | 2099/3000 [48:56<12:53,  1.16it/s, lr: 1.0e-04 loss: 1.689e-01]
latex_v1:  70%|######9   | 2099/3000 [48:59<12:53,  1.16it/s, lr: 1.0e-04 loss: 5.592e-01]
latex_v1:  70%|######9   | 2099/3000 [48:59<12:53,  1.16it/s, lr: 1.0e-04 loss: 5.592e-01]Unloading assistant lora



Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]


Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.41s/it]
Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.41s/it]


Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.41s/it]
Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.41s/it]


Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.39s/it]
Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.39s/it]


Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.37s/it]
Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.37s/it]


Generating Images:  71%|#######1  | 5/7 [00:11<00:04,  2.36s/it]
Generating Images:  71%|#######1  | 5/7 [00:11<00:04,  2.36s/it]


Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.39s/it]
Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.39s/it]


Generating Images: 100%|##########| 7/7 [00:16<00:00,  2.39s/it]
Generating Images: 100%|##########| 7/7 [00:16<00:00,  2.39s/it]


                                                                
                                                                Loading assistant lora

latex_v1:  70%|#######   | 2100/3000 [49:00<12:52,  1.16it/s, lr: 1.0e-04 loss: 6.397e-01]
latex_v1:  70%|#######   | 2100/3000 [49:00<12:52,  1.16it/s, lr: 1.0e-04 loss: 6.397e-01]
latex_v1:  70%|#######   | 2101/3000 [49:00<11:38,  1.29it/s, lr: 1.0e-04 loss: 6.397e-01]
latex_v1:  70%|#######   | 2101/3000 [49:00<11:38,  1.29it/s, lr: 1.0e-04 loss: 6.397e-01]
latex_v1:  70%|#######   | 2101/3000 [49:03<11:38,  1.29it/s, lr: 1.0e-04 loss: 1.783e-01]
latex_v1:  70%|#######   | 2101/3000 [49:03<11:38,  1.29it/s, lr: 1.0e-04 loss: 1.783e-01]
latex_v1:  70%|#######   | 2102/3000 [49:03<19:15,  1.29s/it, lr: 1.0e-04 loss: 1.783e-01]
latex_v1:  70%|#######   | 2102/3000 [49:03<19:15,  1.29s/it, lr: 1.0e-04 loss: 1.783e-01]
latex_v1:  70%|#######   | 2102/3000 [49:04<19:15,  1.29s/it, lr: 1.0e-04 loss: 6.461e-01]
latex_v1:  70%|#######   | 2102/3000 [49:04<19:15,  1.29s/it, lr: 1.0e-04 loss: 6.461e-01]
latex_v1:  70%|#######   | 2103/3000 [49:04<19:39,  1.31s/it, lr: 1.0e-04 loss: 6.461e-01]
latex_v1:  70%|#######   | 2103/3000 [49:04<19:39,  1.31s/it, lr: 1.0e-04 loss: 6.461e-01]
latex_v1:  70%|#######   | 2103/3000 [49:05<19:39,  1.31s/it, lr: 1.0e-04 loss: 1.421e-01]
latex_v1:  70%|#######   | 2103/3000 [49:05<19:39,  1.31s/it, lr: 1.0e-04 loss: 1.421e-01]
latex_v1:  70%|#######   | 2104/3000 [49:05<19:04,  1.28s/it, lr: 1.0e-04 loss: 1.421e-01]
latex_v1:  70%|#######   | 2104/3000 [49:05<19:04,  1.28s/it, lr: 1.0e-04 loss: 1.421e-01]
latex_v1:  70%|#######   | 2104/3000 [49:07<19:04,  1.28s/it, lr: 1.0e-04 loss: 6.757e-02]
latex_v1:  70%|#######   | 2104/3000 [49:07<19:04,  1.28s/it, lr: 1.0e-04 loss: 6.757e-02]
latex_v1:  70%|#######   | 2105/3000 [49:07<19:44,  1.32s/it, lr: 1.0e-04 loss: 6.757e-02]
latex_v1:  70%|#######   | 2105/3000 [49:07<19:44,  1.32s/it, lr: 1.0e-04 loss: 6.757e-02]
latex_v1:  70%|#######   | 2105/3000 [49:10<19:44,  1.32s/it, lr: 1.0e-04 loss: 7.367e-01]
latex_v1:  70%|#######   | 2105/3000 [49:10<19:44,  1.32s/it, lr: 1.0e-04 loss: 7.367e-01]
latex_v1:  70%|#######   | 2106/3000 [49:10<25:59,  1.74s/it, lr: 1.0e-04 loss: 7.367e-01]
latex_v1:  70%|#######   | 2106/3000 [49:10<25:59,  1.74s/it, lr: 1.0e-04 loss: 7.367e-01]
latex_v1:  70%|#######   | 2106/3000 [49:11<25:59,  1.74s/it, lr: 1.0e-04 loss: 3.730e-01]
latex_v1:  70%|#######   | 2106/3000 [49:11<25:59,  1.74s/it, lr: 1.0e-04 loss: 3.730e-01]
latex_v1:  70%|#######   | 2107/3000 [49:11<24:07,  1.62s/it, lr: 1.0e-04 loss: 3.730e-01]
latex_v1:  70%|#######   | 2107/3000 [49:11<24:07,  1.62s/it, lr: 1.0e-04 loss: 3.730e-01]
latex_v1:  70%|#######   | 2107/3000 [49:14<24:07,  1.62s/it, lr: 1.0e-04 loss: 3.578e-02]
latex_v1:  70%|#######   | 2107/3000 [49:14<24:07,  1.62s/it, lr: 1.0e-04 loss: 3.578e-02]
latex_v1:  70%|#######   | 2108/3000 [49:14<29:15,  1.97s/it, lr: 1.0e-04 loss: 3.578e-02]
latex_v1:  70%|#######   | 2108/3000 [49:14<29:15,  1.97s/it, lr: 1.0e-04 loss: 3.578e-02]
latex_v1:  70%|#######   | 2108/3000 [49:15<29:15,  1.97s/it, lr: 1.0e-04 loss: 2.411e-01]
latex_v1:  70%|#######   | 2108/3000 [49:15<29:15,  1.97s/it, lr: 1.0e-04 loss: 2.411e-01]
latex_v1:  70%|#######   | 2109/3000 [49:15<23:52,  1.61s/it, lr: 1.0e-04 loss: 2.411e-01]
latex_v1:  70%|#######   | 2109/3000 [49:15<23:52,  1.61s/it, lr: 1.0e-04 loss: 2.411e-01]
latex_v1:  70%|#######   | 2109/3000 [49:16<23:52,  1.61s/it, lr: 1.0e-04 loss: 1.935e-01]
latex_v1:  70%|#######   | 2109/3000 [49:16<23:52,  1.61s/it, lr: 1.0e-04 loss: 1.935e-01]
latex_v1:  70%|#######   | 2110/3000 [49:18<23:50,  1.61s/it, lr: 1.0e-04 loss: 5.808e-01]
latex_v1:  70%|#######   | 2110/3000 [49:18<23:50,  1.61s/it, lr: 1.0e-04 loss: 5.808e-01]
latex_v1:  70%|#######   | 2111/3000 [49:18<19:15,  1.30s/it, lr: 1.0e-04 loss: 5.808e-01]
latex_v1:  70%|#######   | 2111/3000 [49:18<19:15,  1.30s/it, lr: 1.0e-04 loss: 5.808e-01]
latex_v1:  70%|#######   | 2111/3000 [49:19<19:15,  1.30s/it, lr: 1.0e-04 loss: 1.395e-01]
latex_v1:  70%|#######   | 2111/3000 [49:19<19:15,  1.30s/it, lr: 1.0e-04 loss: 1.395e-01]
latex_v1:  70%|#######   | 2112/3000 [49:19<18:44,  1.27s/it, lr: 1.0e-04 loss: 1.395e-01]
latex_v1:  70%|#######   | 2112/3000 [49:19<18:44,  1.27s/it, lr: 1.0e-04 loss: 1.395e-01]
latex_v1:  70%|#######   | 2112/3000 [49:20<18:44,  1.27s/it, lr: 1.0e-04 loss: 3.762e-01]
latex_v1:  70%|#######   | 2112/3000 [49:20<18:44,  1.27s/it, lr: 1.0e-04 loss: 3.762e-01]
latex_v1:  70%|#######   | 2113/3000 [49:20<20:21,  1.38s/it, lr: 1.0e-04 loss: 3.762e-01]
latex_v1:  70%|#######   | 2113/3000 [49:20<20:21,  1.38s/it, lr: 1.0e-04 loss: 3.762e-01]
latex_v1:  70%|#######   | 2113/3000 [49:21<20:21,  1.38s/it, lr: 1.0e-04 loss: 5.636e-01]
latex_v1:  70%|#######   | 2113/3000 [49:21<20:21,  1.38s/it, lr: 1.0e-04 loss: 5.636e-01]
latex_v1:  70%|#######   | 2114/3000 [49:21<17:51,  1.21s/it, lr: 1.0e-04 loss: 5.636e-01]
latex_v1:  70%|#######   | 2114/3000 [49:21<17:51,  1.21s/it, lr: 1.0e-04 loss: 5.636e-01]
latex_v1:  70%|#######   | 2114/3000 [49:23<17:51,  1.21s/it, lr: 1.0e-04 loss: 3.674e-01]
latex_v1:  70%|#######   | 2114/3000 [49:23<17:51,  1.21s/it, lr: 1.0e-04 loss: 3.674e-01]
latex_v1:  70%|#######   | 2115/3000 [49:23<19:12,  1.30s/it, lr: 1.0e-04 loss: 3.674e-01]
latex_v1:  70%|#######   | 2115/3000 [49:23<19:12,  1.30s/it, lr: 1.0e-04 loss: 3.674e-01]
latex_v1:  70%|#######   | 2115/3000 [49:24<19:12,  1.30s/it, lr: 1.0e-04 loss: 8.514e-01]
latex_v1:  70%|#######   | 2115/3000 [49:24<19:12,  1.30s/it, lr: 1.0e-04 loss: 8.514e-01]
latex_v1:  71%|#######   | 2116/3000 [49:24<17:44,  1.20s/it, lr: 1.0e-04 loss: 8.514e-01]
latex_v1:  71%|#######   | 2116/3000 [49:24<17:44,  1.20s/it, lr: 1.0e-04 loss: 8.514e-01]
latex_v1:  71%|#######   | 2116/3000 [49:27<17:44,  1.20s/it, lr: 1.0e-04 loss: 3.680e-02]
latex_v1:  71%|#######   | 2116/3000 [49:27<17:44,  1.20s/it, lr: 1.0e-04 loss: 3.680e-02]
latex_v1:  71%|#######   | 2117/3000 [49:27<24:42,  1.68s/it, lr: 1.0e-04 loss: 3.680e-02]
latex_v1:  71%|#######   | 2117/3000 [49:27<24:42,  1.68s/it, lr: 1.0e-04 loss: 3.680e-02]
latex_v1:  71%|#######   | 2117/3000 [49:28<24:42,  1.68s/it, lr: 1.0e-04 loss: 2.510e-01]
latex_v1:  71%|#######   | 2117/3000 [49:28<24:42,  1.68s/it, lr: 1.0e-04 loss: 2.510e-01]
latex_v1:  71%|#######   | 2118/3000 [49:28<22:32,  1.53s/it, lr: 1.0e-04 loss: 2.510e-01]
latex_v1:  71%|#######   | 2118/3000 [49:28<22:32,  1.53s/it, lr: 1.0e-04 loss: 2.510e-01]
latex_v1:  71%|#######   | 2118/3000 [49:29<22:32,  1.53s/it, lr: 1.0e-04 loss: 6.548e-01]
latex_v1:  71%|#######   | 2118/3000 [49:29<22:32,  1.53s/it, lr: 1.0e-04 loss: 6.548e-01]
latex_v1:  71%|#######   | 2119/3000 [49:29<19:05,  1.30s/it, lr: 1.0e-04 loss: 6.548e-01]
latex_v1:  71%|#######   | 2119/3000 [49:29<19:05,  1.30s/it, lr: 1.0e-04 loss: 6.548e-01]
latex_v1:  71%|#######   | 2119/3000 [49:29<19:05,  1.30s/it, lr: 1.0e-04 loss: 2.967e-01]
latex_v1:  71%|#######   | 2119/3000 [49:29<19:05,  1.30s/it, lr: 1.0e-04 loss: 2.967e-01]
latex_v1:  71%|#######   | 2120/3000 [49:31<19:04,  1.30s/it, lr: 1.0e-04 loss: 1.622e-01]
latex_v1:  71%|#######   | 2120/3000 [49:31<19:04,  1.30s/it, lr: 1.0e-04 loss: 1.622e-01]
latex_v1:  71%|#######   | 2121/3000 [49:31<15:26,  1.05s/it, lr: 1.0e-04 loss: 1.622e-01]
latex_v1:  71%|#######   | 2121/3000 [49:31<15:26,  1.05s/it, lr: 1.0e-04 loss: 1.622e-01]
latex_v1:  71%|#######   | 2121/3000 [49:32<15:26,  1.05s/it, lr: 1.0e-04 loss: 1.840e-01]
latex_v1:  71%|#######   | 2121/3000 [49:32<15:26,  1.05s/it, lr: 1.0e-04 loss: 1.840e-01]
latex_v1:  71%|#######   | 2122/3000 [49:32<16:49,  1.15s/it, lr: 1.0e-04 loss: 1.840e-01]
latex_v1:  71%|#######   | 2122/3000 [49:32<16:49,  1.15s/it, lr: 1.0e-04 loss: 1.840e-01]
latex_v1:  71%|#######   | 2122/3000 [49:33<16:49,  1.15s/it, lr: 1.0e-04 loss: 4.945e-01]
latex_v1:  71%|#######   | 2122/3000 [49:33<16:49,  1.15s/it, lr: 1.0e-04 loss: 4.945e-01]
latex_v1:  71%|#######   | 2123/3000 [49:33<16:41,  1.14s/it, lr: 1.0e-04 loss: 4.945e-01]
latex_v1:  71%|#######   | 2123/3000 [49:33<16:41,  1.14s/it, lr: 1.0e-04 loss: 4.945e-01]
latex_v1:  71%|#######   | 2123/3000 [49:35<16:41,  1.14s/it, lr: 1.0e-04 loss: 5.302e-01]
latex_v1:  71%|#######   | 2123/3000 [49:35<16:41,  1.14s/it, lr: 1.0e-04 loss: 5.302e-01]
latex_v1:  71%|#######   | 2124/3000 [49:35<17:46,  1.22s/it, lr: 1.0e-04 loss: 5.302e-01]
latex_v1:  71%|#######   | 2124/3000 [49:35<17:46,  1.22s/it, lr: 1.0e-04 loss: 5.302e-01]
latex_v1:  71%|#######   | 2124/3000 [49:36<17:46,  1.22s/it, lr: 1.0e-04 loss: 4.109e-01]
latex_v1:  71%|#######   | 2124/3000 [49:36<17:46,  1.22s/it, lr: 1.0e-04 loss: 4.109e-01]
latex_v1:  71%|#######   | 2125/3000 [49:36<18:40,  1.28s/it, lr: 1.0e-04 loss: 4.109e-01]
latex_v1:  71%|#######   | 2125/3000 [49:36<18:40,  1.28s/it, lr: 1.0e-04 loss: 4.109e-01]
latex_v1:  71%|#######   | 2125/3000 [49:38<18:40,  1.28s/it, lr: 1.0e-04 loss: 2.497e-02]
latex_v1:  71%|#######   | 2125/3000 [49:38<18:40,  1.28s/it, lr: 1.0e-04 loss: 2.497e-02]
latex_v1:  71%|#######   | 2126/3000 [49:38<19:10,  1.32s/it, lr: 1.0e-04 loss: 2.497e-02]
latex_v1:  71%|#######   | 2126/3000 [49:38<19:10,  1.32s/it, lr: 1.0e-04 loss: 2.497e-02]
latex_v1:  71%|#######   | 2126/3000 [49:39<19:10,  1.32s/it, lr: 1.0e-04 loss: 5.896e-01]
latex_v1:  71%|#######   | 2126/3000 [49:39<19:10,  1.32s/it, lr: 1.0e-04 loss: 5.896e-01]
latex_v1:  71%|#######   | 2127/3000 [49:39<19:10,  1.32s/it, lr: 1.0e-04 loss: 5.896e-01]
latex_v1:  71%|#######   | 2127/3000 [49:39<19:10,  1.32s/it, lr: 1.0e-04 loss: 5.896e-01]
latex_v1:  71%|#######   | 2127/3000 [49:40<19:10,  1.32s/it, lr: 1.0e-04 loss: 1.011e-01]
latex_v1:  71%|#######   | 2127/3000 [49:40<19:10,  1.32s/it, lr: 1.0e-04 loss: 1.011e-01]
latex_v1:  71%|#######   | 2128/3000 [49:40<17:42,  1.22s/it, lr: 1.0e-04 loss: 1.011e-01]
latex_v1:  71%|#######   | 2128/3000 [49:40<17:42,  1.22s/it, lr: 1.0e-04 loss: 1.011e-01]
latex_v1:  71%|#######   | 2128/3000 [49:41<17:42,  1.22s/it, lr: 1.0e-04 loss: 2.199e-01]
latex_v1:  71%|#######   | 2128/3000 [49:41<17:42,  1.22s/it, lr: 1.0e-04 loss: 2.199e-01]
latex_v1:  71%|#######   | 2129/3000 [49:41<15:43,  1.08s/it, lr: 1.0e-04 loss: 2.199e-01]
latex_v1:  71%|#######   | 2129/3000 [49:41<15:43,  1.08s/it, lr: 1.0e-04 loss: 2.199e-01]
latex_v1:  71%|#######   | 2129/3000 [49:41<15:43,  1.08s/it, lr: 1.0e-04 loss: 5.121e-01]
latex_v1:  71%|#######   | 2129/3000 [49:41<15:43,  1.08s/it, lr: 1.0e-04 loss: 5.121e-01]
latex_v1:  71%|#######1  | 2130/3000 [49:43<15:42,  1.08s/it, lr: 1.0e-04 loss: 6.086e-01]
latex_v1:  71%|#######1  | 2130/3000 [49:43<15:42,  1.08s/it, lr: 1.0e-04 loss: 6.086e-01]
latex_v1:  71%|#######1  | 2131/3000 [49:43<13:35,  1.07it/s, lr: 1.0e-04 loss: 6.086e-01]
latex_v1:  71%|#######1  | 2131/3000 [49:43<13:35,  1.07it/s, lr: 1.0e-04 loss: 6.086e-01]
latex_v1:  71%|#######1  | 2131/3000 [49:44<13:35,  1.07it/s, lr: 1.0e-04 loss: 5.799e-01]
latex_v1:  71%|#######1  | 2131/3000 [49:44<13:35,  1.07it/s, lr: 1.0e-04 loss: 5.799e-01]
latex_v1:  71%|#######1  | 2132/3000 [49:44<12:52,  1.12it/s, lr: 1.0e-04 loss: 5.799e-01]
latex_v1:  71%|#######1  | 2132/3000 [49:44<12:52,  1.12it/s, lr: 1.0e-04 loss: 5.799e-01]
latex_v1:  71%|#######1  | 2132/3000 [49:45<12:52,  1.12it/s, lr: 1.0e-04 loss: 5.653e-02]
latex_v1:  71%|#######1  | 2132/3000 [49:45<12:52,  1.12it/s, lr: 1.0e-04 loss: 5.653e-02]
latex_v1:  71%|#######1  | 2133/3000 [49:45<15:14,  1.05s/it, lr: 1.0e-04 loss: 5.653e-02]
latex_v1:  71%|#######1  | 2133/3000 [49:45<15:14,  1.05s/it, lr: 1.0e-04 loss: 5.653e-02]
latex_v1:  71%|#######1  | 2133/3000 [49:46<15:14,  1.05s/it, lr: 1.0e-04 loss: 7.954e-01]
latex_v1:  71%|#######1  | 2133/3000 [49:46<15:14,  1.05s/it, lr: 1.0e-04 loss: 7.954e-01]
latex_v1:  71%|#######1  | 2134/3000 [49:46<14:01,  1.03it/s, lr: 1.0e-04 loss: 7.954e-01]
latex_v1:  71%|#######1  | 2134/3000 [49:46<14:01,  1.03it/s, lr: 1.0e-04 loss: 7.954e-01]
latex_v1:  71%|#######1  | 2134/3000 [49:47<14:01,  1.03it/s, lr: 1.0e-04 loss: 6.112e-01]
latex_v1:  71%|#######1  | 2134/3000 [49:47<14:01,  1.03it/s, lr: 1.0e-04 loss: 6.112e-01]
latex_v1:  71%|#######1  | 2135/3000 [49:47<13:05,  1.10it/s, lr: 1.0e-04 loss: 6.112e-01]
latex_v1:  71%|#######1  | 2135/3000 [49:47<13:05,  1.10it/s, lr: 1.0e-04 loss: 6.112e-01]
latex_v1:  71%|#######1  | 2135/3000 [49:49<13:05,  1.10it/s, lr: 1.0e-04 loss: 1.430e-01]
latex_v1:  71%|#######1  | 2135/3000 [49:49<13:05,  1.10it/s, lr: 1.0e-04 loss: 1.430e-01]
latex_v1:  71%|#######1  | 2136/3000 [49:49<17:03,  1.18s/it, lr: 1.0e-04 loss: 1.430e-01]
latex_v1:  71%|#######1  | 2136/3000 [49:49<17:03,  1.18s/it, lr: 1.0e-04 loss: 1.430e-01]
latex_v1:  71%|#######1  | 2136/3000 [49:50<17:03,  1.18s/it, lr: 1.0e-04 loss: 1.245e-01]
latex_v1:  71%|#######1  | 2136/3000 [49:50<17:03,  1.18s/it, lr: 1.0e-04 loss: 1.245e-01]
latex_v1:  71%|#######1  | 2137/3000 [49:50<18:29,  1.29s/it, lr: 1.0e-04 loss: 1.245e-01]
latex_v1:  71%|#######1  | 2137/3000 [49:50<18:29,  1.29s/it, lr: 1.0e-04 loss: 1.245e-01]
latex_v1:  71%|#######1  | 2137/3000 [49:51<18:29,  1.29s/it, lr: 1.0e-04 loss: 3.471e-01]
latex_v1:  71%|#######1  | 2137/3000 [49:51<18:29,  1.29s/it, lr: 1.0e-04 loss: 3.471e-01]
latex_v1:  71%|#######1  | 2138/3000 [49:51<16:16,  1.13s/it, lr: 1.0e-04 loss: 3.471e-01]
latex_v1:  71%|#######1  | 2138/3000 [49:51<16:16,  1.13s/it, lr: 1.0e-04 loss: 3.471e-01]
latex_v1:  71%|#######1  | 2138/3000 [49:53<16:16,  1.13s/it, lr: 1.0e-04 loss: 2.558e-01]
latex_v1:  71%|#######1  | 2138/3000 [49:53<16:16,  1.13s/it, lr: 1.0e-04 loss: 2.558e-01]
latex_v1:  71%|#######1  | 2139/3000 [49:53<17:16,  1.20s/it, lr: 1.0e-04 loss: 2.558e-01]
latex_v1:  71%|#######1  | 2139/3000 [49:53<17:16,  1.20s/it, lr: 1.0e-04 loss: 2.558e-01]
latex_v1:  71%|#######1  | 2139/3000 [49:53<17:16,  1.20s/it, lr: 1.0e-04 loss: 5.113e-01]
latex_v1:  71%|#######1  | 2139/3000 [49:53<17:16,  1.20s/it, lr: 1.0e-04 loss: 5.113e-01]
latex_v1:  71%|#######1  | 2140/3000 [49:55<17:14,  1.20s/it, lr: 1.0e-04 loss: 9.260e-02]
latex_v1:  71%|#######1  | 2140/3000 [49:55<17:14,  1.20s/it, lr: 1.0e-04 loss: 9.260e-02]
latex_v1:  71%|#######1  | 2141/3000 [49:55<14:04,  1.02it/s, lr: 1.0e-04 loss: 9.260e-02]
latex_v1:  71%|#######1  | 2141/3000 [49:55<14:04,  1.02it/s, lr: 1.0e-04 loss: 9.260e-02]
latex_v1:  71%|#######1  | 2141/3000 [49:56<14:04,  1.02it/s, lr: 1.0e-04 loss: 5.551e-01]
latex_v1:  71%|#######1  | 2141/3000 [49:56<14:04,  1.02it/s, lr: 1.0e-04 loss: 5.551e-01]
latex_v1:  71%|#######1  | 2142/3000 [49:56<15:45,  1.10s/it, lr: 1.0e-04 loss: 5.551e-01]
latex_v1:  71%|#######1  | 2142/3000 [49:56<15:45,  1.10s/it, lr: 1.0e-04 loss: 5.551e-01]
latex_v1:  71%|#######1  | 2142/3000 [49:58<15:45,  1.10s/it, lr: 1.0e-04 loss: 1.595e-01]
latex_v1:  71%|#######1  | 2142/3000 [49:58<15:45,  1.10s/it, lr: 1.0e-04 loss: 1.595e-01]
latex_v1:  71%|#######1  | 2143/3000 [49:58<17:20,  1.21s/it, lr: 1.0e-04 loss: 1.595e-01]
latex_v1:  71%|#######1  | 2143/3000 [49:58<17:20,  1.21s/it, lr: 1.0e-04 loss: 1.595e-01]
latex_v1:  71%|#######1  | 2143/3000 [50:01<17:20,  1.21s/it, lr: 1.0e-04 loss: 1.499e-01]
latex_v1:  71%|#######1  | 2143/3000 [50:01<17:20,  1.21s/it, lr: 1.0e-04 loss: 1.499e-01]
latex_v1:  71%|#######1  | 2144/3000 [50:01<23:32,  1.65s/it, lr: 1.0e-04 loss: 1.499e-01]
latex_v1:  71%|#######1  | 2144/3000 [50:01<23:32,  1.65s/it, lr: 1.0e-04 loss: 1.499e-01]
latex_v1:  71%|#######1  | 2144/3000 [50:03<23:32,  1.65s/it, lr: 1.0e-04 loss: 2.468e-01]
latex_v1:  71%|#######1  | 2144/3000 [50:03<23:32,  1.65s/it, lr: 1.0e-04 loss: 2.468e-01]
latex_v1:  72%|#######1  | 2145/3000 [50:03<24:24,  1.71s/it, lr: 1.0e-04 loss: 2.468e-01]
latex_v1:  72%|#######1  | 2145/3000 [50:03<24:24,  1.71s/it, lr: 1.0e-04 loss: 2.468e-01]
latex_v1:  72%|#######1  | 2145/3000 [50:04<24:24,  1.71s/it, lr: 1.0e-04 loss: 4.514e-01]
latex_v1:  72%|#######1  | 2145/3000 [50:04<24:24,  1.71s/it, lr: 1.0e-04 loss: 4.514e-01]
latex_v1:  72%|#######1  | 2146/3000 [50:04<23:13,  1.63s/it, lr: 1.0e-04 loss: 4.514e-01]
latex_v1:  72%|#######1  | 2146/3000 [50:04<23:13,  1.63s/it, lr: 1.0e-04 loss: 4.514e-01]
latex_v1:  72%|#######1  | 2146/3000 [50:05<23:13,  1.63s/it, lr: 1.0e-04 loss: 6.276e-02]
latex_v1:  72%|#######1  | 2146/3000 [50:05<23:13,  1.63s/it, lr: 1.0e-04 loss: 6.276e-02]
latex_v1:  72%|#######1  | 2147/3000 [50:05<22:29,  1.58s/it, lr: 1.0e-04 loss: 6.276e-02]
latex_v1:  72%|#######1  | 2147/3000 [50:05<22:29,  1.58s/it, lr: 1.0e-04 loss: 6.276e-02]
latex_v1:  72%|#######1  | 2147/3000 [50:06<22:29,  1.58s/it, lr: 1.0e-04 loss: 1.757e-01]
latex_v1:  72%|#######1  | 2147/3000 [50:06<22:29,  1.58s/it, lr: 1.0e-04 loss: 1.757e-01]
latex_v1:  72%|#######1  | 2148/3000 [50:06<19:04,  1.34s/it, lr: 1.0e-04 loss: 1.757e-01]
latex_v1:  72%|#######1  | 2148/3000 [50:06<19:04,  1.34s/it, lr: 1.0e-04 loss: 1.757e-01]
latex_v1:  72%|#######1  | 2148/3000 [50:07<19:04,  1.34s/it, lr: 1.0e-04 loss: 2.888e-01]
latex_v1:  72%|#######1  | 2148/3000 [50:07<19:04,  1.34s/it, lr: 1.0e-04 loss: 2.888e-01]
latex_v1:  72%|#######1  | 2149/3000 [50:07<16:43,  1.18s/it, lr: 1.0e-04 loss: 2.888e-01]
latex_v1:  72%|#######1  | 2149/3000 [50:07<16:43,  1.18s/it, lr: 1.0e-04 loss: 2.888e-01]
latex_v1:  72%|#######1  | 2149/3000 [50:08<16:43,  1.18s/it, lr: 1.0e-04 loss: 4.824e-01]
latex_v1:  72%|#######1  | 2149/3000 [50:08<16:43,  1.18s/it, lr: 1.0e-04 loss: 4.824e-01]
latex_v1:  72%|#######1  | 2150/3000 [50:10<16:41,  1.18s/it, lr: 1.0e-04 loss: 6.110e-01]
latex_v1:  72%|#######1  | 2150/3000 [50:10<16:41,  1.18s/it, lr: 1.0e-04 loss: 6.110e-01]
latex_v1:  72%|#######1  | 2151/3000 [50:10<14:01,  1.01it/s, lr: 1.0e-04 loss: 6.110e-01]
latex_v1:  72%|#######1  | 2151/3000 [50:10<14:01,  1.01it/s, lr: 1.0e-04 loss: 6.110e-01]
latex_v1:  72%|#######1  | 2151/3000 [50:11<14:01,  1.01it/s, lr: 1.0e-04 loss: 5.782e-01]
latex_v1:  72%|#######1  | 2151/3000 [50:11<14:01,  1.01it/s, lr: 1.0e-04 loss: 5.782e-01]
latex_v1:  72%|#######1  | 2152/3000 [50:11<15:38,  1.11s/it, lr: 1.0e-04 loss: 5.782e-01]
latex_v1:  72%|#######1  | 2152/3000 [50:11<15:38,  1.11s/it, lr: 1.0e-04 loss: 5.782e-01]
latex_v1:  72%|#######1  | 2152/3000 [50:14<15:38,  1.11s/it, lr: 1.0e-04 loss: 3.155e-01]
latex_v1:  72%|#######1  | 2152/3000 [50:14<15:38,  1.11s/it, lr: 1.0e-04 loss: 3.155e-01]
latex_v1:  72%|#######1  | 2153/3000 [50:14<22:18,  1.58s/it, lr: 1.0e-04 loss: 3.155e-01]
latex_v1:  72%|#######1  | 2153/3000 [50:14<22:18,  1.58s/it, lr: 1.0e-04 loss: 3.155e-01]
latex_v1:  72%|#######1  | 2153/3000 [50:16<22:18,  1.58s/it, lr: 1.0e-04 loss: 5.996e-02]
latex_v1:  72%|#######1  | 2153/3000 [50:16<22:18,  1.58s/it, lr: 1.0e-04 loss: 5.996e-02]
latex_v1:  72%|#######1  | 2154/3000 [50:16<22:07,  1.57s/it, lr: 1.0e-04 loss: 5.996e-02]
latex_v1:  72%|#######1  | 2154/3000 [50:16<22:07,  1.57s/it, lr: 1.0e-04 loss: 5.996e-02]
latex_v1:  72%|#######1  | 2154/3000 [50:17<22:07,  1.57s/it, lr: 1.0e-04 loss: 2.167e-01]
latex_v1:  72%|#######1  | 2154/3000 [50:17<22:07,  1.57s/it, lr: 1.0e-04 loss: 2.167e-01]
latex_v1:  72%|#######1  | 2155/3000 [50:17<21:30,  1.53s/it, lr: 1.0e-04 loss: 2.167e-01]
latex_v1:  72%|#######1  | 2155/3000 [50:17<21:30,  1.53s/it, lr: 1.0e-04 loss: 2.167e-01]
latex_v1:  72%|#######1  | 2155/3000 [50:19<21:30,  1.53s/it, lr: 1.0e-04 loss: 1.231e-01]
latex_v1:  72%|#######1  | 2155/3000 [50:19<21:30,  1.53s/it, lr: 1.0e-04 loss: 1.231e-01]
latex_v1:  72%|#######1  | 2156/3000 [50:19<20:39,  1.47s/it, lr: 1.0e-04 loss: 1.231e-01]
latex_v1:  72%|#######1  | 2156/3000 [50:19<20:39,  1.47s/it, lr: 1.0e-04 loss: 1.231e-01]
latex_v1:  72%|#######1  | 2156/3000 [50:20<20:39,  1.47s/it, lr: 1.0e-04 loss: 3.019e-01]
latex_v1:  72%|#######1  | 2156/3000 [50:20<20:39,  1.47s/it, lr: 1.0e-04 loss: 3.019e-01]
latex_v1:  72%|#######1  | 2157/3000 [50:20<20:52,  1.49s/it, lr: 1.0e-04 loss: 3.019e-01]
latex_v1:  72%|#######1  | 2157/3000 [50:20<20:52,  1.49s/it, lr: 1.0e-04 loss: 3.019e-01]
latex_v1:  72%|#######1  | 2157/3000 [50:21<20:52,  1.49s/it, lr: 1.0e-04 loss: 5.943e-01]
latex_v1:  72%|#######1  | 2157/3000 [50:21<20:52,  1.49s/it, lr: 1.0e-04 loss: 5.943e-01]
latex_v1:  72%|#######1  | 2158/3000 [50:21<17:50,  1.27s/it, lr: 1.0e-04 loss: 5.943e-01]
latex_v1:  72%|#######1  | 2158/3000 [50:21<17:50,  1.27s/it, lr: 1.0e-04 loss: 5.943e-01]
latex_v1:  72%|#######1  | 2158/3000 [50:22<17:50,  1.27s/it, lr: 1.0e-04 loss: 6.234e-01]
latex_v1:  72%|#######1  | 2158/3000 [50:22<17:50,  1.27s/it, lr: 1.0e-04 loss: 6.234e-01]
latex_v1:  72%|#######1  | 2159/3000 [50:22<15:46,  1.13s/it, lr: 1.0e-04 loss: 6.234e-01]
latex_v1:  72%|#######1  | 2159/3000 [50:22<15:46,  1.13s/it, lr: 1.0e-04 loss: 6.234e-01]
latex_v1:  72%|#######1  | 2159/3000 [50:23<15:46,  1.13s/it, lr: 1.0e-04 loss: 6.423e-01]
latex_v1:  72%|#######1  | 2159/3000 [50:23<15:46,  1.13s/it, lr: 1.0e-04 loss: 6.423e-01]
latex_v1:  72%|#######2  | 2160/3000 [50:24<15:45,  1.13s/it, lr: 1.0e-04 loss: 5.273e-01]
latex_v1:  72%|#######2  | 2160/3000 [50:24<15:45,  1.13s/it, lr: 1.0e-04 loss: 5.273e-01]
latex_v1:  72%|#######2  | 2161/3000 [50:24<10:57,  1.28it/s, lr: 1.0e-04 loss: 5.273e-01]
latex_v1:  72%|#######2  | 2161/3000 [50:24<10:57,  1.28it/s, lr: 1.0e-04 loss: 5.273e-01]
latex_v1:  72%|#######2  | 2161/3000 [50:26<10:57,  1.28it/s, lr: 1.0e-04 loss: 5.086e-01]
latex_v1:  72%|#######2  | 2161/3000 [50:26<10:57,  1.28it/s, lr: 1.0e-04 loss: 5.086e-01]
latex_v1:  72%|#######2  | 2162/3000 [50:26<14:42,  1.05s/it, lr: 1.0e-04 loss: 5.086e-01]
latex_v1:  72%|#######2  | 2162/3000 [50:26<14:42,  1.05s/it, lr: 1.0e-04 loss: 5.086e-01]
latex_v1:  72%|#######2  | 2162/3000 [50:27<14:42,  1.05s/it, lr: 1.0e-04 loss: 3.934e-01]
latex_v1:  72%|#######2  | 2162/3000 [50:27<14:42,  1.05s/it, lr: 1.0e-04 loss: 3.934e-01]
latex_v1:  72%|#######2  | 2163/3000 [50:27<14:43,  1.06s/it, lr: 1.0e-04 loss: 3.934e-01]
latex_v1:  72%|#######2  | 2163/3000 [50:27<14:43,  1.06s/it, lr: 1.0e-04 loss: 3.934e-01]
latex_v1:  72%|#######2  | 2163/3000 [50:30<14:43,  1.06s/it, lr: 1.0e-04 loss: 5.782e-01]
latex_v1:  72%|#######2  | 2163/3000 [50:30<14:43,  1.06s/it, lr: 1.0e-04 loss: 5.782e-01]
latex_v1:  72%|#######2  | 2164/3000 [50:30<21:30,  1.54s/it, lr: 1.0e-04 loss: 5.782e-01]
latex_v1:  72%|#######2  | 2164/3000 [50:30<21:30,  1.54s/it, lr: 1.0e-04 loss: 5.782e-01]
latex_v1:  72%|#######2  | 2164/3000 [50:33<21:30,  1.54s/it, lr: 1.0e-04 loss: 5.733e-01]
latex_v1:  72%|#######2  | 2164/3000 [50:33<21:30,  1.54s/it, lr: 1.0e-04 loss: 5.733e-01]
latex_v1:  72%|#######2  | 2165/3000 [50:33<26:39,  1.92s/it, lr: 1.0e-04 loss: 5.733e-01]
latex_v1:  72%|#######2  | 2165/3000 [50:33<26:39,  1.92s/it, lr: 1.0e-04 loss: 5.733e-01]
latex_v1:  72%|#######2  | 2165/3000 [50:34<26:39,  1.92s/it, lr: 1.0e-04 loss: 1.738e-01]
latex_v1:  72%|#######2  | 2165/3000 [50:34<26:39,  1.92s/it, lr: 1.0e-04 loss: 1.738e-01]
latex_v1:  72%|#######2  | 2166/3000 [50:34<25:09,  1.81s/it, lr: 1.0e-04 loss: 1.738e-01]
latex_v1:  72%|#######2  | 2166/3000 [50:34<25:09,  1.81s/it, lr: 1.0e-04 loss: 1.738e-01]
latex_v1:  72%|#######2  | 2166/3000 [50:35<25:09,  1.81s/it, lr: 1.0e-04 loss: 6.738e-01]
latex_v1:  72%|#######2  | 2166/3000 [50:35<25:09,  1.81s/it, lr: 1.0e-04 loss: 6.738e-01]
latex_v1:  72%|#######2  | 2167/3000 [50:35<23:11,  1.67s/it, lr: 1.0e-04 loss: 6.738e-01]
latex_v1:  72%|#######2  | 2167/3000 [50:35<23:11,  1.67s/it, lr: 1.0e-04 loss: 6.738e-01]
latex_v1:  72%|#######2  | 2167/3000 [50:37<23:11,  1.67s/it, lr: 1.0e-04 loss: 8.291e-01]
latex_v1:  72%|#######2  | 2167/3000 [50:37<23:11,  1.67s/it, lr: 1.0e-04 loss: 8.291e-01]
latex_v1:  72%|#######2  | 2168/3000 [50:37<21:07,  1.52s/it, lr: 1.0e-04 loss: 8.291e-01]
latex_v1:  72%|#######2  | 2168/3000 [50:37<21:07,  1.52s/it, lr: 1.0e-04 loss: 8.291e-01]
latex_v1:  72%|#######2  | 2168/3000 [50:37<21:07,  1.52s/it, lr: 1.0e-04 loss: 1.996e-01]
latex_v1:  72%|#######2  | 2168/3000 [50:37<21:07,  1.52s/it, lr: 1.0e-04 loss: 1.996e-01]
latex_v1:  72%|#######2  | 2169/3000 [50:37<17:55,  1.29s/it, lr: 1.0e-04 loss: 1.996e-01]
latex_v1:  72%|#######2  | 2169/3000 [50:37<17:55,  1.29s/it, lr: 1.0e-04 loss: 1.996e-01]
latex_v1:  72%|#######2  | 2169/3000 [50:39<17:55,  1.29s/it, lr: 1.0e-04 loss: 5.317e-01]
latex_v1:  72%|#######2  | 2169/3000 [50:39<17:55,  1.29s/it, lr: 1.0e-04 loss: 5.317e-01]
latex_v1:  72%|#######2  | 2170/3000 [50:40<17:54,  1.29s/it, lr: 1.0e-04 loss: 2.874e-02]
latex_v1:  72%|#######2  | 2170/3000 [50:40<17:54,  1.29s/it, lr: 1.0e-04 loss: 2.874e-02]
latex_v1:  72%|#######2  | 2171/3000 [50:40<14:35,  1.06s/it, lr: 1.0e-04 loss: 2.874e-02]
latex_v1:  72%|#######2  | 2171/3000 [50:40<14:35,  1.06s/it, lr: 1.0e-04 loss: 2.874e-02]
latex_v1:  72%|#######2  | 2171/3000 [50:43<14:35,  1.06s/it, lr: 1.0e-04 loss: 5.492e-01]
latex_v1:  72%|#######2  | 2171/3000 [50:43<14:35,  1.06s/it, lr: 1.0e-04 loss: 5.492e-01]
latex_v1:  72%|#######2  | 2172/3000 [50:43<18:33,  1.34s/it, lr: 1.0e-04 loss: 5.492e-01]
latex_v1:  72%|#######2  | 2172/3000 [50:43<18:33,  1.34s/it, lr: 1.0e-04 loss: 5.492e-01]
latex_v1:  72%|#######2  | 2172/3000 [50:44<18:33,  1.34s/it, lr: 1.0e-04 loss: 5.509e-01]
latex_v1:  72%|#######2  | 2172/3000 [50:44<18:33,  1.34s/it, lr: 1.0e-04 loss: 5.509e-01]
latex_v1:  72%|#######2  | 2173/3000 [50:44<19:21,  1.40s/it, lr: 1.0e-04 loss: 5.509e-01]
latex_v1:  72%|#######2  | 2173/3000 [50:44<19:21,  1.40s/it, lr: 1.0e-04 loss: 5.509e-01]
latex_v1:  72%|#######2  | 2173/3000 [50:46<19:21,  1.40s/it, lr: 1.0e-04 loss: 2.052e-01]
latex_v1:  72%|#######2  | 2173/3000 [50:46<19:21,  1.40s/it, lr: 1.0e-04 loss: 2.052e-01]
latex_v1:  72%|#######2  | 2174/3000 [50:46<21:16,  1.55s/it, lr: 1.0e-04 loss: 2.052e-01]
latex_v1:  72%|#######2  | 2174/3000 [50:46<21:16,  1.55s/it, lr: 1.0e-04 loss: 2.052e-01]
latex_v1:  72%|#######2  | 2174/3000 [50:47<21:16,  1.55s/it, lr: 1.0e-04 loss: 1.507e-01]
latex_v1:  72%|#######2  | 2174/3000 [50:47<21:16,  1.55s/it, lr: 1.0e-04 loss: 1.507e-01]
latex_v1:  72%|#######2  | 2175/3000 [50:47<20:53,  1.52s/it, lr: 1.0e-04 loss: 1.507e-01]
latex_v1:  72%|#######2  | 2175/3000 [50:47<20:53,  1.52s/it, lr: 1.0e-04 loss: 1.507e-01]
latex_v1:  72%|#######2  | 2175/3000 [50:49<20:53,  1.52s/it, lr: 1.0e-04 loss: 1.320e-01]
latex_v1:  72%|#######2  | 2175/3000 [50:49<20:53,  1.52s/it, lr: 1.0e-04 loss: 1.320e-01]
latex_v1:  73%|#######2  | 2176/3000 [50:49<21:45,  1.58s/it, lr: 1.0e-04 loss: 1.320e-01]
latex_v1:  73%|#######2  | 2176/3000 [50:49<21:45,  1.58s/it, lr: 1.0e-04 loss: 1.320e-01]
latex_v1:  73%|#######2  | 2176/3000 [50:50<21:45,  1.58s/it, lr: 1.0e-04 loss: 1.802e-01]
latex_v1:  73%|#######2  | 2176/3000 [50:50<21:45,  1.58s/it, lr: 1.0e-04 loss: 1.802e-01]
latex_v1:  73%|#######2  | 2177/3000 [50:50<18:26,  1.34s/it, lr: 1.0e-04 loss: 1.802e-01]
latex_v1:  73%|#######2  | 2177/3000 [50:50<18:26,  1.34s/it, lr: 1.0e-04 loss: 1.802e-01]
latex_v1:  73%|#######2  | 2177/3000 [50:52<18:26,  1.34s/it, lr: 1.0e-04 loss: 3.019e-01]
latex_v1:  73%|#######2  | 2177/3000 [50:52<18:26,  1.34s/it, lr: 1.0e-04 loss: 3.019e-01]
latex_v1:  73%|#######2  | 2178/3000 [50:52<19:13,  1.40s/it, lr: 1.0e-04 loss: 3.019e-01]
latex_v1:  73%|#######2  | 2178/3000 [50:52<19:13,  1.40s/it, lr: 1.0e-04 loss: 3.019e-01]
latex_v1:  73%|#######2  | 2178/3000 [50:53<19:13,  1.40s/it, lr: 1.0e-04 loss: 2.952e-01]
latex_v1:  73%|#######2  | 2178/3000 [50:53<19:13,  1.40s/it, lr: 1.0e-04 loss: 2.952e-01]
latex_v1:  73%|#######2  | 2179/3000 [50:53<19:51,  1.45s/it, lr: 1.0e-04 loss: 2.952e-01]
latex_v1:  73%|#######2  | 2179/3000 [50:53<19:51,  1.45s/it, lr: 1.0e-04 loss: 2.952e-01]
latex_v1:  73%|#######2  | 2179/3000 [50:54<19:51,  1.45s/it, lr: 1.0e-04 loss: 8.983e-02]
latex_v1:  73%|#######2  | 2179/3000 [50:54<19:51,  1.45s/it, lr: 1.0e-04 loss: 8.983e-02]
latex_v1:  73%|#######2  | 2180/3000 [50:56<19:49,  1.45s/it, lr: 1.0e-04 loss: 2.375e-01]
latex_v1:  73%|#######2  | 2180/3000 [50:56<19:49,  1.45s/it, lr: 1.0e-04 loss: 2.375e-01]
latex_v1:  73%|#######2  | 2181/3000 [50:56<15:20,  1.12s/it, lr: 1.0e-04 loss: 2.375e-01]
latex_v1:  73%|#######2  | 2181/3000 [50:56<15:20,  1.12s/it, lr: 1.0e-04 loss: 2.375e-01]
latex_v1:  73%|#######2  | 2181/3000 [50:57<15:20,  1.12s/it, lr: 1.0e-04 loss: 1.009e-01]
latex_v1:  73%|#######2  | 2181/3000 [50:57<15:20,  1.12s/it, lr: 1.0e-04 loss: 1.009e-01]
latex_v1:  73%|#######2  | 2182/3000 [50:57<14:04,  1.03s/it, lr: 1.0e-04 loss: 1.009e-01]
latex_v1:  73%|#######2  | 2182/3000 [50:57<14:04,  1.03s/it, lr: 1.0e-04 loss: 1.009e-01]
latex_v1:  73%|#######2  | 2182/3000 [50:58<14:04,  1.03s/it, lr: 1.0e-04 loss: 6.799e-01]
latex_v1:  73%|#######2  | 2182/3000 [50:58<14:04,  1.03s/it, lr: 1.0e-04 loss: 6.799e-01]
latex_v1:  73%|#######2  | 2183/3000 [50:58<15:55,  1.17s/it, lr: 1.0e-04 loss: 6.799e-01]
latex_v1:  73%|#######2  | 2183/3000 [50:58<15:55,  1.17s/it, lr: 1.0e-04 loss: 6.799e-01]
latex_v1:  73%|#######2  | 2183/3000 [50:59<15:55,  1.17s/it, lr: 1.0e-04 loss: 5.385e-01]
latex_v1:  73%|#######2  | 2183/3000 [50:59<15:55,  1.17s/it, lr: 1.0e-04 loss: 5.385e-01]
latex_v1:  73%|#######2  | 2184/3000 [50:59<14:23,  1.06s/it, lr: 1.0e-04 loss: 5.385e-01]
latex_v1:  73%|#######2  | 2184/3000 [50:59<14:23,  1.06s/it, lr: 1.0e-04 loss: 5.385e-01]
latex_v1:  73%|#######2  | 2184/3000 [51:00<14:23,  1.06s/it, lr: 1.0e-04 loss: 2.189e-01]
latex_v1:  73%|#######2  | 2184/3000 [51:00<14:23,  1.06s/it, lr: 1.0e-04 loss: 2.189e-01]
latex_v1:  73%|#######2  | 2185/3000 [51:00<13:12,  1.03it/s, lr: 1.0e-04 loss: 2.189e-01]
latex_v1:  73%|#######2  | 2185/3000 [51:00<13:12,  1.03it/s, lr: 1.0e-04 loss: 2.189e-01]
latex_v1:  73%|#######2  | 2185/3000 [51:00<13:12,  1.03it/s, lr: 1.0e-04 loss: 1.241e-01]
latex_v1:  73%|#######2  | 2185/3000 [51:00<13:12,  1.03it/s, lr: 1.0e-04 loss: 1.241e-01]
latex_v1:  73%|#######2  | 2186/3000 [51:00<12:20,  1.10it/s, lr: 1.0e-04 loss: 1.241e-01]
latex_v1:  73%|#######2  | 2186/3000 [51:00<12:20,  1.10it/s, lr: 1.0e-04 loss: 1.241e-01]
latex_v1:  73%|#######2  | 2186/3000 [51:02<12:20,  1.10it/s, lr: 1.0e-04 loss: 5.916e-01]
latex_v1:  73%|#######2  | 2186/3000 [51:02<12:20,  1.10it/s, lr: 1.0e-04 loss: 5.916e-01]
latex_v1:  73%|#######2  | 2187/3000 [51:02<16:17,  1.20s/it, lr: 1.0e-04 loss: 5.916e-01]
latex_v1:  73%|#######2  | 2187/3000 [51:02<16:17,  1.20s/it, lr: 1.0e-04 loss: 5.916e-01]
latex_v1:  73%|#######2  | 2187/3000 [51:04<16:17,  1.20s/it, lr: 1.0e-04 loss: 3.137e-01]
latex_v1:  73%|#######2  | 2187/3000 [51:04<16:17,  1.20s/it, lr: 1.0e-04 loss: 3.137e-01]
latex_v1:  73%|#######2  | 2188/3000 [51:04<18:55,  1.40s/it, lr: 1.0e-04 loss: 3.137e-01]
latex_v1:  73%|#######2  | 2188/3000 [51:04<18:55,  1.40s/it, lr: 1.0e-04 loss: 3.137e-01]
latex_v1:  73%|#######2  | 2188/3000 [51:05<18:55,  1.40s/it, lr: 1.0e-04 loss: 6.620e-01]
latex_v1:  73%|#######2  | 2188/3000 [51:05<18:55,  1.40s/it, lr: 1.0e-04 loss: 6.620e-01]
latex_v1:  73%|#######2  | 2189/3000 [51:05<18:03,  1.34s/it, lr: 1.0e-04 loss: 6.620e-01]
latex_v1:  73%|#######2  | 2189/3000 [51:05<18:03,  1.34s/it, lr: 1.0e-04 loss: 6.620e-01]
latex_v1:  73%|#######2  | 2189/3000 [51:07<18:03,  1.34s/it, lr: 1.0e-04 loss: 5.531e-01]
latex_v1:  73%|#######2  | 2189/3000 [51:07<18:03,  1.34s/it, lr: 1.0e-04 loss: 5.531e-01]
latex_v1:  73%|#######3  | 2190/3000 [51:10<18:02,  1.34s/it, lr: 1.0e-04 loss: 1.238e-01]
latex_v1:  73%|#######3  | 2190/3000 [51:10<18:02,  1.34s/it, lr: 1.0e-04 loss: 1.238e-01]
latex_v1:  73%|#######3  | 2191/3000 [51:10<17:54,  1.33s/it, lr: 1.0e-04 loss: 1.238e-01]
latex_v1:  73%|#######3  | 2191/3000 [51:10<17:54,  1.33s/it, lr: 1.0e-04 loss: 1.238e-01]
latex_v1:  73%|#######3  | 2191/3000 [51:10<17:54,  1.33s/it, lr: 1.0e-04 loss: 6.223e-02]
latex_v1:  73%|#######3  | 2191/3000 [51:10<17:54,  1.33s/it, lr: 1.0e-04 loss: 6.223e-02]
latex_v1:  73%|#######3  | 2192/3000 [51:10<15:57,  1.19s/it, lr: 1.0e-04 loss: 6.223e-02]
latex_v1:  73%|#######3  | 2192/3000 [51:10<15:57,  1.19s/it, lr: 1.0e-04 loss: 6.223e-02]
latex_v1:  73%|#######3  | 2192/3000 [51:11<15:57,  1.19s/it, lr: 1.0e-04 loss: 4.316e-01]
latex_v1:  73%|#######3  | 2192/3000 [51:11<15:57,  1.19s/it, lr: 1.0e-04 loss: 4.316e-01]
latex_v1:  73%|#######3  | 2193/3000 [51:11<14:24,  1.07s/it, lr: 1.0e-04 loss: 4.316e-01]
latex_v1:  73%|#######3  | 2193/3000 [51:11<14:24,  1.07s/it, lr: 1.0e-04 loss: 4.316e-01]
latex_v1:  73%|#######3  | 2193/3000 [51:12<14:24,  1.07s/it, lr: 1.0e-04 loss: 7.067e-02]
latex_v1:  73%|#######3  | 2193/3000 [51:12<14:24,  1.07s/it, lr: 1.0e-04 loss: 7.067e-02]
latex_v1:  73%|#######3  | 2194/3000 [51:12<13:13,  1.02it/s, lr: 1.0e-04 loss: 7.067e-02]
latex_v1:  73%|#######3  | 2194/3000 [51:12<13:13,  1.02it/s, lr: 1.0e-04 loss: 7.067e-02]
latex_v1:  73%|#######3  | 2194/3000 [51:13<13:13,  1.02it/s, lr: 1.0e-04 loss: 6.413e-01]
latex_v1:  73%|#######3  | 2194/3000 [51:13<13:13,  1.02it/s, lr: 1.0e-04 loss: 6.413e-01]
latex_v1:  73%|#######3  | 2195/3000 [51:13<12:24,  1.08it/s, lr: 1.0e-04 loss: 6.413e-01]
latex_v1:  73%|#######3  | 2195/3000 [51:13<12:24,  1.08it/s, lr: 1.0e-04 loss: 6.413e-01]
latex_v1:  73%|#######3  | 2195/3000 [51:13<12:24,  1.08it/s, lr: 1.0e-04 loss: 5.634e-01]
latex_v1:  73%|#######3  | 2195/3000 [51:13<12:24,  1.08it/s, lr: 1.0e-04 loss: 5.634e-01]
latex_v1:  73%|#######3  | 2196/3000 [51:13<11:43,  1.14it/s, lr: 1.0e-04 loss: 5.634e-01]
latex_v1:  73%|#######3  | 2196/3000 [51:13<11:43,  1.14it/s, lr: 1.0e-04 loss: 5.634e-01]
latex_v1:  73%|#######3  | 2196/3000 [51:14<11:43,  1.14it/s, lr: 1.0e-04 loss: 3.363e-01]
latex_v1:  73%|#######3  | 2196/3000 [51:14<11:43,  1.14it/s, lr: 1.0e-04 loss: 3.363e-01]
latex_v1:  73%|#######3  | 2197/3000 [51:14<12:07,  1.10it/s, lr: 1.0e-04 loss: 3.363e-01]
latex_v1:  73%|#######3  | 2197/3000 [51:14<12:07,  1.10it/s, lr: 1.0e-04 loss: 3.363e-01]
latex_v1:  73%|#######3  | 2197/3000 [51:15<12:07,  1.10it/s, lr: 1.0e-04 loss: 1.967e-01]
latex_v1:  73%|#######3  | 2197/3000 [51:15<12:07,  1.10it/s, lr: 1.0e-04 loss: 1.967e-01]
latex_v1:  73%|#######3  | 2198/3000 [51:15<11:27,  1.17it/s, lr: 1.0e-04 loss: 1.967e-01]
latex_v1:  73%|#######3  | 2198/3000 [51:15<11:27,  1.17it/s, lr: 1.0e-04 loss: 1.967e-01]
latex_v1:  73%|#######3  | 2198/3000 [51:17<11:27,  1.17it/s, lr: 1.0e-04 loss: 5.313e-01]
latex_v1:  73%|#######3  | 2198/3000 [51:17<11:27,  1.17it/s, lr: 1.0e-04 loss: 5.313e-01]
latex_v1:  73%|#######3  | 2199/3000 [51:17<13:42,  1.03s/it, lr: 1.0e-04 loss: 5.313e-01]
latex_v1:  73%|#######3  | 2199/3000 [51:17<13:42,  1.03s/it, lr: 1.0e-04 loss: 5.313e-01]
latex_v1:  73%|#######3  | 2199/3000 [51:17<13:42,  1.03s/it, lr: 1.0e-04 loss: 6.288e-01]
latex_v1:  73%|#######3  | 2199/3000 [51:17<13:42,  1.03s/it, lr: 1.0e-04 loss: 6.288e-01]
latex_v1:  73%|#######3  | 2200/3000 [51:18<13:41,  1.03s/it, lr: 1.0e-04 loss: 5.709e-01]
latex_v1:  73%|#######3  | 2200/3000 [51:18<13:41,  1.03s/it, lr: 1.0e-04 loss: 5.709e-01]
latex_v1:  73%|#######3  | 2201/3000 [51:18<09:44,  1.37it/s, lr: 1.0e-04 loss: 5.709e-01]
latex_v1:  73%|#######3  | 2201/3000 [51:18<09:44,  1.37it/s, lr: 1.0e-04 loss: 5.709e-01]
latex_v1:  73%|#######3  | 2201/3000 [51:21<09:44,  1.37it/s, lr: 1.0e-04 loss: 3.348e-01]
latex_v1:  73%|#######3  | 2201/3000 [51:21<09:44,  1.37it/s, lr: 1.0e-04 loss: 3.348e-01]
latex_v1:  73%|#######3  | 2202/3000 [51:21<16:36,  1.25s/it, lr: 1.0e-04 loss: 3.348e-01]
latex_v1:  73%|#######3  | 2202/3000 [51:21<16:36,  1.25s/it, lr: 1.0e-04 loss: 3.348e-01]
latex_v1:  73%|#######3  | 2202/3000 [51:22<16:36,  1.25s/it, lr: 1.0e-04 loss: 1.813e-01]
latex_v1:  73%|#######3  | 2202/3000 [51:22<16:36,  1.25s/it, lr: 1.0e-04 loss: 1.813e-01]
latex_v1:  73%|#######3  | 2203/3000 [51:22<17:05,  1.29s/it, lr: 1.0e-04 loss: 1.813e-01]
latex_v1:  73%|#######3  | 2203/3000 [51:22<17:05,  1.29s/it, lr: 1.0e-04 loss: 1.813e-01]
latex_v1:  73%|#######3  | 2203/3000 [51:23<17:05,  1.29s/it, lr: 1.0e-04 loss: 3.509e-01]
latex_v1:  73%|#######3  | 2203/3000 [51:23<17:05,  1.29s/it, lr: 1.0e-04 loss: 3.509e-01]
latex_v1:  73%|#######3  | 2204/3000 [51:23<15:03,  1.13s/it, lr: 1.0e-04 loss: 3.509e-01]
latex_v1:  73%|#######3  | 2204/3000 [51:23<15:03,  1.13s/it, lr: 1.0e-04 loss: 3.509e-01]
latex_v1:  73%|#######3  | 2204/3000 [51:24<15:03,  1.13s/it, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  73%|#######3  | 2204/3000 [51:24<15:03,  1.13s/it, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  74%|#######3  | 2205/3000 [51:24<13:38,  1.03s/it, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  74%|#######3  | 2205/3000 [51:24<13:38,  1.03s/it, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  74%|#######3  | 2205/3000 [51:25<13:38,  1.03s/it, lr: 1.0e-04 loss: 2.307e-01]
latex_v1:  74%|#######3  | 2205/3000 [51:25<13:38,  1.03s/it, lr: 1.0e-04 loss: 2.307e-01]
latex_v1:  74%|#######3  | 2206/3000 [51:25<15:36,  1.18s/it, lr: 1.0e-04 loss: 2.307e-01]
latex_v1:  74%|#######3  | 2206/3000 [51:25<15:36,  1.18s/it, lr: 1.0e-04 loss: 2.307e-01]
latex_v1:  74%|#######3  | 2206/3000 [51:26<15:36,  1.18s/it, lr: 1.0e-04 loss: 7.835e-01]
latex_v1:  74%|#######3  | 2206/3000 [51:26<15:36,  1.18s/it, lr: 1.0e-04 loss: 7.835e-01]
latex_v1:  74%|#######3  | 2207/3000 [51:27<15:34,  1.18s/it, lr: 1.0e-04 loss: 7.835e-01]
latex_v1:  74%|#######3  | 2207/3000 [51:27<15:34,  1.18s/it, lr: 1.0e-04 loss: 7.835e-01]
latex_v1:  74%|#######3  | 2207/3000 [51:28<15:34,  1.18s/it, lr: 1.0e-04 loss: 1.552e-01]
latex_v1:  74%|#######3  | 2207/3000 [51:28<15:34,  1.18s/it, lr: 1.0e-04 loss: 1.552e-01]
latex_v1:  74%|#######3  | 2208/3000 [51:28<16:54,  1.28s/it, lr: 1.0e-04 loss: 1.552e-01]
latex_v1:  74%|#######3  | 2208/3000 [51:28<16:54,  1.28s/it, lr: 1.0e-04 loss: 1.552e-01]
latex_v1:  74%|#######3  | 2208/3000 [51:29<16:54,  1.28s/it, lr: 1.0e-04 loss: 9.405e-02]
latex_v1:  74%|#######3  | 2208/3000 [51:29<16:54,  1.28s/it, lr: 1.0e-04 loss: 9.405e-02]
latex_v1:  74%|#######3  | 2209/3000 [51:29<16:03,  1.22s/it, lr: 1.0e-04 loss: 9.405e-02]
latex_v1:  74%|#######3  | 2209/3000 [51:29<16:03,  1.22s/it, lr: 1.0e-04 loss: 9.405e-02]
latex_v1:  74%|#######3  | 2209/3000 [51:32<16:03,  1.22s/it, lr: 1.0e-04 loss: 1.471e-01]
latex_v1:  74%|#######3  | 2209/3000 [51:32<16:03,  1.22s/it, lr: 1.0e-04 loss: 1.471e-01]
latex_v1:  74%|#######3  | 2210/3000 [51:33<16:02,  1.22s/it, lr: 1.0e-04 loss: 2.686e-01]
latex_v1:  74%|#######3  | 2210/3000 [51:33<16:02,  1.22s/it, lr: 1.0e-04 loss: 2.686e-01]
latex_v1:  74%|#######3  | 2211/3000 [51:33<10:57,  1.20it/s, lr: 1.0e-04 loss: 2.686e-01]
latex_v1:  74%|#######3  | 2211/3000 [51:33<10:57,  1.20it/s, lr: 1.0e-04 loss: 2.686e-01]
latex_v1:  74%|#######3  | 2211/3000 [51:34<10:57,  1.20it/s, lr: 1.0e-04 loss: 4.029e-01]
latex_v1:  74%|#######3  | 2211/3000 [51:34<10:57,  1.20it/s, lr: 1.0e-04 loss: 4.029e-01]
latex_v1:  74%|#######3  | 2212/3000 [51:34<10:41,  1.23it/s, lr: 1.0e-04 loss: 4.029e-01]
latex_v1:  74%|#######3  | 2212/3000 [51:34<10:41,  1.23it/s, lr: 1.0e-04 loss: 4.029e-01]
latex_v1:  74%|#######3  | 2212/3000 [51:34<10:41,  1.23it/s, lr: 1.0e-04 loss: 1.650e-01]
latex_v1:  74%|#######3  | 2212/3000 [51:34<10:41,  1.23it/s, lr: 1.0e-04 loss: 1.650e-01]
latex_v1:  74%|#######3  | 2213/3000 [51:34<10:29,  1.25it/s, lr: 1.0e-04 loss: 1.650e-01]
latex_v1:  74%|#######3  | 2213/3000 [51:34<10:29,  1.25it/s, lr: 1.0e-04 loss: 1.650e-01]
latex_v1:  74%|#######3  | 2213/3000 [51:37<10:29,  1.25it/s, lr: 1.0e-04 loss: 1.138e-01]
latex_v1:  74%|#######3  | 2213/3000 [51:37<10:29,  1.25it/s, lr: 1.0e-04 loss: 1.138e-01]
latex_v1:  74%|#######3  | 2214/3000 [51:37<17:47,  1.36s/it, lr: 1.0e-04 loss: 1.138e-01]
latex_v1:  74%|#######3  | 2214/3000 [51:37<17:47,  1.36s/it, lr: 1.0e-04 loss: 1.138e-01]
latex_v1:  74%|#######3  | 2214/3000 [51:38<17:47,  1.36s/it, lr: 1.0e-04 loss: 5.516e-01]
latex_v1:  74%|#######3  | 2214/3000 [51:38<17:47,  1.36s/it, lr: 1.0e-04 loss: 5.516e-01]
latex_v1:  74%|#######3  | 2215/3000 [51:38<15:39,  1.20s/it, lr: 1.0e-04 loss: 5.516e-01]
latex_v1:  74%|#######3  | 2215/3000 [51:38<15:39,  1.20s/it, lr: 1.0e-04 loss: 5.516e-01]
latex_v1:  74%|#######3  | 2215/3000 [51:39<15:39,  1.20s/it, lr: 1.0e-04 loss: 1.179e-02]
latex_v1:  74%|#######3  | 2215/3000 [51:39<15:39,  1.20s/it, lr: 1.0e-04 loss: 1.179e-02]
latex_v1:  74%|#######3  | 2216/3000 [51:39<14:46,  1.13s/it, lr: 1.0e-04 loss: 1.179e-02]
latex_v1:  74%|#######3  | 2216/3000 [51:39<14:46,  1.13s/it, lr: 1.0e-04 loss: 1.179e-02]
latex_v1:  74%|#######3  | 2216/3000 [51:40<14:46,  1.13s/it, lr: 1.0e-04 loss: 6.336e-01]
latex_v1:  74%|#######3  | 2216/3000 [51:40<14:46,  1.13s/it, lr: 1.0e-04 loss: 6.336e-01]
latex_v1:  74%|#######3  | 2217/3000 [51:40<15:36,  1.20s/it, lr: 1.0e-04 loss: 6.336e-01]
latex_v1:  74%|#######3  | 2217/3000 [51:40<15:36,  1.20s/it, lr: 1.0e-04 loss: 6.336e-01]
latex_v1:  74%|#######3  | 2217/3000 [51:42<15:36,  1.20s/it, lr: 1.0e-04 loss: 1.071e-02]
latex_v1:  74%|#######3  | 2217/3000 [51:42<15:36,  1.20s/it, lr: 1.0e-04 loss: 1.071e-02]
latex_v1:  74%|#######3  | 2218/3000 [51:42<17:20,  1.33s/it, lr: 1.0e-04 loss: 1.071e-02]
latex_v1:  74%|#######3  | 2218/3000 [51:42<17:20,  1.33s/it, lr: 1.0e-04 loss: 1.071e-02]
latex_v1:  74%|#######3  | 2218/3000 [51:43<17:20,  1.33s/it, lr: 1.0e-04 loss: 2.406e-01]
latex_v1:  74%|#######3  | 2218/3000 [51:43<17:20,  1.33s/it, lr: 1.0e-04 loss: 2.406e-01]
latex_v1:  74%|#######3  | 2219/3000 [51:44<17:36,  1.35s/it, lr: 1.0e-04 loss: 2.406e-01]
latex_v1:  74%|#######3  | 2219/3000 [51:44<17:36,  1.35s/it, lr: 1.0e-04 loss: 2.406e-01]
latex_v1:  74%|#######3  | 2219/3000 [51:45<17:36,  1.35s/it, lr: 1.0e-04 loss: 1.982e-01]
latex_v1:  74%|#######3  | 2219/3000 [51:45<17:36,  1.35s/it, lr: 1.0e-04 loss: 1.982e-01]
latex_v1:  74%|#######4  | 2220/3000 [51:48<17:35,  1.35s/it, lr: 1.0e-04 loss: 2.468e-01]
latex_v1:  74%|#######4  | 2220/3000 [51:48<17:35,  1.35s/it, lr: 1.0e-04 loss: 2.468e-01]
latex_v1:  74%|#######4  | 2221/3000 [51:48<18:00,  1.39s/it, lr: 1.0e-04 loss: 2.468e-01]
latex_v1:  74%|#######4  | 2221/3000 [51:48<18:00,  1.39s/it, lr: 1.0e-04 loss: 2.468e-01]
latex_v1:  74%|#######4  | 2221/3000 [51:49<18:00,  1.39s/it, lr: 1.0e-04 loss: 2.147e-01]
latex_v1:  74%|#######4  | 2221/3000 [51:49<18:00,  1.39s/it, lr: 1.0e-04 loss: 2.147e-01]
latex_v1:  74%|#######4  | 2222/3000 [51:49<15:59,  1.23s/it, lr: 1.0e-04 loss: 2.147e-01]
latex_v1:  74%|#######4  | 2222/3000 [51:49<15:59,  1.23s/it, lr: 1.0e-04 loss: 2.147e-01]
latex_v1:  74%|#######4  | 2222/3000 [51:50<15:59,  1.23s/it, lr: 1.0e-04 loss: 2.515e-02]
latex_v1:  74%|#######4  | 2222/3000 [51:50<15:59,  1.23s/it, lr: 1.0e-04 loss: 2.515e-02]
latex_v1:  74%|#######4  | 2223/3000 [51:50<16:22,  1.26s/it, lr: 1.0e-04 loss: 2.515e-02]
latex_v1:  74%|#######4  | 2223/3000 [51:50<16:22,  1.26s/it, lr: 1.0e-04 loss: 2.515e-02]
latex_v1:  74%|#######4  | 2223/3000 [51:52<16:22,  1.26s/it, lr: 1.0e-04 loss: 6.694e-01]
latex_v1:  74%|#######4  | 2223/3000 [51:52<16:22,  1.26s/it, lr: 1.0e-04 loss: 6.694e-01]
latex_v1:  74%|#######4  | 2224/3000 [51:52<17:27,  1.35s/it, lr: 1.0e-04 loss: 6.694e-01]
latex_v1:  74%|#######4  | 2224/3000 [51:52<17:27,  1.35s/it, lr: 1.0e-04 loss: 6.694e-01]
latex_v1:  74%|#######4  | 2224/3000 [51:53<17:27,  1.35s/it, lr: 1.0e-04 loss: 1.590e-01]
latex_v1:  74%|#######4  | 2224/3000 [51:53<17:27,  1.35s/it, lr: 1.0e-04 loss: 1.590e-01]
latex_v1:  74%|#######4  | 2225/3000 [51:53<15:14,  1.18s/it, lr: 1.0e-04 loss: 1.590e-01]
latex_v1:  74%|#######4  | 2225/3000 [51:53<15:14,  1.18s/it, lr: 1.0e-04 loss: 1.590e-01]
latex_v1:  74%|#######4  | 2225/3000 [51:54<15:14,  1.18s/it, lr: 1.0e-04 loss: 3.667e-01]
latex_v1:  74%|#######4  | 2225/3000 [51:54<15:14,  1.18s/it, lr: 1.0e-04 loss: 3.667e-01]
latex_v1:  74%|#######4  | 2226/3000 [51:54<13:42,  1.06s/it, lr: 1.0e-04 loss: 3.667e-01]
latex_v1:  74%|#######4  | 2226/3000 [51:54<13:42,  1.06s/it, lr: 1.0e-04 loss: 3.667e-01]
latex_v1:  74%|#######4  | 2226/3000 [51:55<13:42,  1.06s/it, lr: 1.0e-04 loss: 5.920e-01]
latex_v1:  74%|#######4  | 2226/3000 [51:55<13:42,  1.06s/it, lr: 1.0e-04 loss: 5.920e-01]
latex_v1:  74%|#######4  | 2227/3000 [51:55<14:08,  1.10s/it, lr: 1.0e-04 loss: 5.920e-01]
latex_v1:  74%|#######4  | 2227/3000 [51:55<14:08,  1.10s/it, lr: 1.0e-04 loss: 5.920e-01]
latex_v1:  74%|#######4  | 2227/3000 [51:57<14:08,  1.10s/it, lr: 1.0e-04 loss: 4.317e-01]
latex_v1:  74%|#######4  | 2227/3000 [51:57<14:08,  1.10s/it, lr: 1.0e-04 loss: 4.317e-01]
latex_v1:  74%|#######4  | 2228/3000 [51:57<17:02,  1.32s/it, lr: 1.0e-04 loss: 4.317e-01]
latex_v1:  74%|#######4  | 2228/3000 [51:57<17:02,  1.32s/it, lr: 1.0e-04 loss: 4.317e-01]
latex_v1:  74%|#######4  | 2228/3000 [51:58<17:02,  1.32s/it, lr: 1.0e-04 loss: 1.824e-01]
latex_v1:  74%|#######4  | 2228/3000 [51:58<17:02,  1.32s/it, lr: 1.0e-04 loss: 1.824e-01]
latex_v1:  74%|#######4  | 2229/3000 [51:58<17:55,  1.39s/it, lr: 1.0e-04 loss: 1.824e-01]
latex_v1:  74%|#######4  | 2229/3000 [51:58<17:55,  1.39s/it, lr: 1.0e-04 loss: 1.824e-01]
latex_v1:  74%|#######4  | 2229/3000 [51:59<17:55,  1.39s/it, lr: 1.0e-04 loss: 3.723e-01]
latex_v1:  74%|#######4  | 2229/3000 [51:59<17:55,  1.39s/it, lr: 1.0e-04 loss: 3.723e-01]
latex_v1:  74%|#######4  | 2230/3000 [52:02<17:53,  1.39s/it, lr: 1.0e-04 loss: 2.649e-01]
latex_v1:  74%|#######4  | 2230/3000 [52:02<17:53,  1.39s/it, lr: 1.0e-04 loss: 2.649e-01]
latex_v1:  74%|#######4  | 2231/3000 [52:02<17:38,  1.38s/it, lr: 1.0e-04 loss: 2.649e-01]
latex_v1:  74%|#######4  | 2231/3000 [52:02<17:38,  1.38s/it, lr: 1.0e-04 loss: 2.649e-01]
latex_v1:  74%|#######4  | 2231/3000 [52:03<17:38,  1.38s/it, lr: 1.0e-04 loss: 8.269e-01]
latex_v1:  74%|#######4  | 2231/3000 [52:03<17:38,  1.38s/it, lr: 1.0e-04 loss: 8.269e-01]
latex_v1:  74%|#######4  | 2232/3000 [52:03<16:22,  1.28s/it, lr: 1.0e-04 loss: 8.269e-01]
latex_v1:  74%|#######4  | 2232/3000 [52:03<16:22,  1.28s/it, lr: 1.0e-04 loss: 8.269e-01]
latex_v1:  74%|#######4  | 2232/3000 [52:04<16:22,  1.28s/it, lr: 1.0e-04 loss: 1.265e-01]
latex_v1:  74%|#######4  | 2232/3000 [52:04<16:22,  1.28s/it, lr: 1.0e-04 loss: 1.265e-01]
latex_v1:  74%|#######4  | 2233/3000 [52:04<16:56,  1.32s/it, lr: 1.0e-04 loss: 1.265e-01]
latex_v1:  74%|#######4  | 2233/3000 [52:04<16:56,  1.32s/it, lr: 1.0e-04 loss: 1.265e-01]
latex_v1:  74%|#######4  | 2233/3000 [52:06<16:56,  1.32s/it, lr: 1.0e-04 loss: 2.155e-01]
latex_v1:  74%|#######4  | 2233/3000 [52:06<16:56,  1.32s/it, lr: 1.0e-04 loss: 2.155e-01]
latex_v1:  74%|#######4  | 2234/3000 [52:06<18:48,  1.47s/it, lr: 1.0e-04 loss: 2.155e-01]
latex_v1:  74%|#######4  | 2234/3000 [52:06<18:48,  1.47s/it, lr: 1.0e-04 loss: 2.155e-01]
latex_v1:  74%|#######4  | 2234/3000 [52:07<18:48,  1.47s/it, lr: 1.0e-04 loss: 6.686e-02]
latex_v1:  74%|#######4  | 2234/3000 [52:07<18:48,  1.47s/it, lr: 1.0e-04 loss: 6.686e-02]
latex_v1:  74%|#######4  | 2235/3000 [52:07<16:15,  1.28s/it, lr: 1.0e-04 loss: 6.686e-02]
latex_v1:  74%|#######4  | 2235/3000 [52:07<16:15,  1.28s/it, lr: 1.0e-04 loss: 6.686e-02]
latex_v1:  74%|#######4  | 2235/3000 [52:08<16:15,  1.28s/it, lr: 1.0e-04 loss: 5.577e-01]
latex_v1:  74%|#######4  | 2235/3000 [52:08<16:15,  1.28s/it, lr: 1.0e-04 loss: 5.577e-01]
latex_v1:  75%|#######4  | 2236/3000 [52:08<15:26,  1.21s/it, lr: 1.0e-04 loss: 5.577e-01]
latex_v1:  75%|#######4  | 2236/3000 [52:08<15:26,  1.21s/it, lr: 1.0e-04 loss: 5.577e-01]
latex_v1:  75%|#######4  | 2236/3000 [52:11<15:26,  1.21s/it, lr: 1.0e-04 loss: 1.756e-01]
latex_v1:  75%|#######4  | 2236/3000 [52:11<15:26,  1.21s/it, lr: 1.0e-04 loss: 1.756e-01]
latex_v1:  75%|#######4  | 2237/3000 [52:11<21:34,  1.70s/it, lr: 1.0e-04 loss: 1.756e-01]
latex_v1:  75%|#######4  | 2237/3000 [52:11<21:34,  1.70s/it, lr: 1.0e-04 loss: 1.756e-01]
latex_v1:  75%|#######4  | 2237/3000 [52:12<21:34,  1.70s/it, lr: 1.0e-04 loss: 6.148e-01]
latex_v1:  75%|#######4  | 2237/3000 [52:12<21:34,  1.70s/it, lr: 1.0e-04 loss: 6.148e-01]
latex_v1:  75%|#######4  | 2238/3000 [52:12<19:12,  1.51s/it, lr: 1.0e-04 loss: 6.148e-01]
latex_v1:  75%|#######4  | 2238/3000 [52:12<19:12,  1.51s/it, lr: 1.0e-04 loss: 6.148e-01]
latex_v1:  75%|#######4  | 2238/3000 [52:13<19:12,  1.51s/it, lr: 1.0e-04 loss: 5.290e-02]
latex_v1:  75%|#######4  | 2238/3000 [52:13<19:12,  1.51s/it, lr: 1.0e-04 loss: 5.290e-02]
latex_v1:  75%|#######4  | 2239/3000 [52:13<16:17,  1.28s/it, lr: 1.0e-04 loss: 5.290e-02]
latex_v1:  75%|#######4  | 2239/3000 [52:13<16:17,  1.28s/it, lr: 1.0e-04 loss: 5.290e-02]
latex_v1:  75%|#######4  | 2239/3000 [52:14<16:17,  1.28s/it, lr: 1.0e-04 loss: 4.499e-01]
latex_v1:  75%|#######4  | 2239/3000 [52:14<16:17,  1.28s/it, lr: 1.0e-04 loss: 4.499e-01]
latex_v1:  75%|#######4  | 2240/3000 [52:15<16:16,  1.28s/it, lr: 1.0e-04 loss: 5.681e-01]
latex_v1:  75%|#######4  | 2240/3000 [52:15<16:16,  1.28s/it, lr: 1.0e-04 loss: 5.681e-01]
latex_v1:  75%|#######4  | 2241/3000 [52:15<11:28,  1.10it/s, lr: 1.0e-04 loss: 5.681e-01]
latex_v1:  75%|#######4  | 2241/3000 [52:15<11:28,  1.10it/s, lr: 1.0e-04 loss: 5.681e-01]
latex_v1:  75%|#######4  | 2241/3000 [52:17<11:28,  1.10it/s, lr: 1.0e-04 loss: 6.018e-01]
latex_v1:  75%|#######4  | 2241/3000 [52:17<11:28,  1.10it/s, lr: 1.0e-04 loss: 6.018e-01]
latex_v1:  75%|#######4  | 2242/3000 [52:17<14:30,  1.15s/it, lr: 1.0e-04 loss: 6.018e-01]
latex_v1:  75%|#######4  | 2242/3000 [52:17<14:30,  1.15s/it, lr: 1.0e-04 loss: 6.018e-01]
latex_v1:  75%|#######4  | 2242/3000 [52:19<14:30,  1.15s/it, lr: 1.0e-04 loss: 9.518e-02]
latex_v1:  75%|#######4  | 2242/3000 [52:19<14:30,  1.15s/it, lr: 1.0e-04 loss: 9.518e-02]
latex_v1:  75%|#######4  | 2243/3000 [52:19<15:46,  1.25s/it, lr: 1.0e-04 loss: 9.518e-02]
latex_v1:  75%|#######4  | 2243/3000 [52:19<15:46,  1.25s/it, lr: 1.0e-04 loss: 9.518e-02]
latex_v1:  75%|#######4  | 2243/3000 [52:19<15:46,  1.25s/it, lr: 1.0e-04 loss: 8.019e-02]
latex_v1:  75%|#######4  | 2243/3000 [52:19<15:46,  1.25s/it, lr: 1.0e-04 loss: 8.019e-02]
latex_v1:  75%|#######4  | 2244/3000 [52:19<14:07,  1.12s/it, lr: 1.0e-04 loss: 8.019e-02]
latex_v1:  75%|#######4  | 2244/3000 [52:19<14:07,  1.12s/it, lr: 1.0e-04 loss: 8.019e-02]
latex_v1:  75%|#######4  | 2244/3000 [52:21<14:07,  1.12s/it, lr: 1.0e-04 loss: 1.488e-01]
latex_v1:  75%|#######4  | 2244/3000 [52:21<14:07,  1.12s/it, lr: 1.0e-04 loss: 1.488e-01]
latex_v1:  75%|#######4  | 2245/3000 [52:21<15:02,  1.19s/it, lr: 1.0e-04 loss: 1.488e-01]
latex_v1:  75%|#######4  | 2245/3000 [52:21<15:02,  1.19s/it, lr: 1.0e-04 loss: 1.488e-01]
latex_v1:  75%|#######4  | 2245/3000 [52:22<15:02,  1.19s/it, lr: 1.0e-04 loss: 4.588e-01]
latex_v1:  75%|#######4  | 2245/3000 [52:22<15:02,  1.19s/it, lr: 1.0e-04 loss: 4.588e-01]
latex_v1:  75%|#######4  | 2246/3000 [52:22<14:56,  1.19s/it, lr: 1.0e-04 loss: 4.588e-01]
latex_v1:  75%|#######4  | 2246/3000 [52:22<14:56,  1.19s/it, lr: 1.0e-04 loss: 4.588e-01]
latex_v1:  75%|#######4  | 2246/3000 [52:23<14:56,  1.19s/it, lr: 1.0e-04 loss: 5.606e-01]
latex_v1:  75%|#######4  | 2246/3000 [52:23<14:56,  1.19s/it, lr: 1.0e-04 loss: 5.606e-01]
latex_v1:  75%|#######4  | 2247/3000 [52:23<13:20,  1.06s/it, lr: 1.0e-04 loss: 5.606e-01]
latex_v1:  75%|#######4  | 2247/3000 [52:23<13:20,  1.06s/it, lr: 1.0e-04 loss: 5.606e-01]
latex_v1:  75%|#######4  | 2247/3000 [52:24<13:20,  1.06s/it, lr: 1.0e-04 loss: 6.354e-01]
latex_v1:  75%|#######4  | 2247/3000 [52:24<13:20,  1.06s/it, lr: 1.0e-04 loss: 6.354e-01]
latex_v1:  75%|#######4  | 2248/3000 [52:24<13:44,  1.10s/it, lr: 1.0e-04 loss: 6.354e-01]
latex_v1:  75%|#######4  | 2248/3000 [52:24<13:44,  1.10s/it, lr: 1.0e-04 loss: 6.354e-01]
latex_v1:  75%|#######4  | 2248/3000 [52:25<13:44,  1.10s/it, lr: 1.0e-04 loss: 4.630e-01]
latex_v1:  75%|#######4  | 2248/3000 [52:25<13:44,  1.10s/it, lr: 1.0e-04 loss: 4.630e-01]
latex_v1:  75%|#######4  | 2249/3000 [52:25<12:25,  1.01it/s, lr: 1.0e-04 loss: 4.630e-01]
latex_v1:  75%|#######4  | 2249/3000 [52:25<12:25,  1.01it/s, lr: 1.0e-04 loss: 4.630e-01]
latex_v1:  75%|#######4  | 2249/3000 [52:26<12:25,  1.01it/s, lr: 1.0e-04 loss: 2.626e-01]
latex_v1:  75%|#######4  | 2249/3000 [52:26<12:25,  1.01it/s, lr: 1.0e-04 loss: 2.626e-01]
Saving at step 2250
Saved checkpoint to /data/app/output/latex_v1/latex_v1_000002250.safetensors
Saved optimizer to /data/app/output/latex_v1/optimizer.pt
Removing old save: /data/app/output/latex_v1/latex_v1_000001250.safetensors

latex_v1:  75%|#######5  | 2250/3000 [52:28<12:24,  1.01it/s, lr: 1.0e-04 loss: 6.575e-01]
latex_v1:  75%|#######5  | 2250/3000 [52:28<12:24,  1.01it/s, lr: 1.0e-04 loss: 6.575e-01]
latex_v1:  75%|#######5  | 2251/3000 [52:28<11:43,  1.07it/s, lr: 1.0e-04 loss: 6.575e-01]
latex_v1:  75%|#######5  | 2251/3000 [52:28<11:43,  1.07it/s, lr: 1.0e-04 loss: 6.575e-01]
latex_v1:  75%|#######5  | 2251/3000 [52:29<11:43,  1.07it/s, lr: 1.0e-04 loss: 3.010e-01]
latex_v1:  75%|#######5  | 2251/3000 [52:29<11:43,  1.07it/s, lr: 1.0e-04 loss: 3.010e-01]
latex_v1:  75%|#######5  | 2252/3000 [52:29<12:54,  1.04s/it, lr: 1.0e-04 loss: 3.010e-01]
latex_v1:  75%|#######5  | 2252/3000 [52:29<12:54,  1.04s/it, lr: 1.0e-04 loss: 3.010e-01]
latex_v1:  75%|#######5  | 2252/3000 [52:30<12:54,  1.04s/it, lr: 1.0e-04 loss: 3.044e-01]
latex_v1:  75%|#######5  | 2252/3000 [52:30<12:54,  1.04s/it, lr: 1.0e-04 loss: 3.044e-01]
latex_v1:  75%|#######5  | 2253/3000 [52:30<11:59,  1.04it/s, lr: 1.0e-04 loss: 3.044e-01]
latex_v1:  75%|#######5  | 2253/3000 [52:30<11:59,  1.04it/s, lr: 1.0e-04 loss: 3.044e-01]
latex_v1:  75%|#######5  | 2253/3000 [52:33<11:59,  1.04it/s, lr: 1.0e-04 loss: 4.823e-01]
latex_v1:  75%|#######5  | 2253/3000 [52:33<11:59,  1.04it/s, lr: 1.0e-04 loss: 4.823e-01]
latex_v1:  75%|#######5  | 2254/3000 [52:33<18:23,  1.48s/it, lr: 1.0e-04 loss: 4.823e-01]
latex_v1:  75%|#######5  | 2254/3000 [52:33<18:23,  1.48s/it, lr: 1.0e-04 loss: 4.823e-01]
latex_v1:  75%|#######5  | 2254/3000 [52:34<18:23,  1.48s/it, lr: 1.0e-04 loss: 5.091e-01]
latex_v1:  75%|#######5  | 2254/3000 [52:34<18:23,  1.48s/it, lr: 1.0e-04 loss: 5.091e-01]
latex_v1:  75%|#######5  | 2255/3000 [52:34<17:23,  1.40s/it, lr: 1.0e-04 loss: 5.091e-01]
latex_v1:  75%|#######5  | 2255/3000 [52:34<17:23,  1.40s/it, lr: 1.0e-04 loss: 5.091e-01]
latex_v1:  75%|#######5  | 2255/3000 [52:36<17:23,  1.40s/it, lr: 1.0e-04 loss: 6.836e-01]
latex_v1:  75%|#######5  | 2255/3000 [52:36<17:23,  1.40s/it, lr: 1.0e-04 loss: 6.836e-01]
latex_v1:  75%|#######5  | 2256/3000 [52:36<17:24,  1.40s/it, lr: 1.0e-04 loss: 6.836e-01]
latex_v1:  75%|#######5  | 2256/3000 [52:36<17:24,  1.40s/it, lr: 1.0e-04 loss: 6.836e-01]
latex_v1:  75%|#######5  | 2256/3000 [52:37<17:24,  1.40s/it, lr: 1.0e-04 loss: 5.239e-01]
latex_v1:  75%|#######5  | 2256/3000 [52:37<17:24,  1.40s/it, lr: 1.0e-04 loss: 5.239e-01]
latex_v1:  75%|#######5  | 2257/3000 [52:37<18:19,  1.48s/it, lr: 1.0e-04 loss: 5.239e-01]
latex_v1:  75%|#######5  | 2257/3000 [52:37<18:19,  1.48s/it, lr: 1.0e-04 loss: 5.239e-01]
latex_v1:  75%|#######5  | 2257/3000 [52:39<18:19,  1.48s/it, lr: 1.0e-04 loss: 2.044e-01]
latex_v1:  75%|#######5  | 2257/3000 [52:39<18:19,  1.48s/it, lr: 1.0e-04 loss: 2.044e-01]
latex_v1:  75%|#######5  | 2258/3000 [52:39<18:08,  1.47s/it, lr: 1.0e-04 loss: 2.044e-01]
latex_v1:  75%|#######5  | 2258/3000 [52:39<18:08,  1.47s/it, lr: 1.0e-04 loss: 2.044e-01]
latex_v1:  75%|#######5  | 2258/3000 [52:39<18:08,  1.47s/it, lr: 1.0e-04 loss: 6.198e-01]
latex_v1:  75%|#######5  | 2258/3000 [52:39<18:08,  1.47s/it, lr: 1.0e-04 loss: 6.198e-01]
latex_v1:  75%|#######5  | 2259/3000 [52:39<15:32,  1.26s/it, lr: 1.0e-04 loss: 6.198e-01]
latex_v1:  75%|#######5  | 2259/3000 [52:39<15:32,  1.26s/it, lr: 1.0e-04 loss: 6.198e-01]
latex_v1:  75%|#######5  | 2259/3000 [52:41<15:32,  1.26s/it, lr: 1.0e-04 loss: 3.894e-01]
latex_v1:  75%|#######5  | 2259/3000 [52:41<15:32,  1.26s/it, lr: 1.0e-04 loss: 3.894e-01]
latex_v1:  75%|#######5  | 2260/3000 [52:43<15:31,  1.26s/it, lr: 1.0e-04 loss: 4.656e-01]
latex_v1:  75%|#######5  | 2260/3000 [52:43<15:31,  1.26s/it, lr: 1.0e-04 loss: 4.656e-01]
latex_v1:  75%|#######5  | 2261/3000 [52:43<13:16,  1.08s/it, lr: 1.0e-04 loss: 4.656e-01]
latex_v1:  75%|#######5  | 2261/3000 [52:43<13:16,  1.08s/it, lr: 1.0e-04 loss: 4.656e-01]
latex_v1:  75%|#######5  | 2261/3000 [52:44<13:16,  1.08s/it, lr: 1.0e-04 loss: 4.202e-01]
latex_v1:  75%|#######5  | 2261/3000 [52:44<13:16,  1.08s/it, lr: 1.0e-04 loss: 4.202e-01]
latex_v1:  75%|#######5  | 2262/3000 [52:44<14:02,  1.14s/it, lr: 1.0e-04 loss: 4.202e-01]
latex_v1:  75%|#######5  | 2262/3000 [52:44<14:02,  1.14s/it, lr: 1.0e-04 loss: 4.202e-01]
latex_v1:  75%|#######5  | 2262/3000 [52:45<14:02,  1.14s/it, lr: 1.0e-04 loss: 6.604e-01]
latex_v1:  75%|#######5  | 2262/3000 [52:45<14:02,  1.14s/it, lr: 1.0e-04 loss: 6.604e-01]
latex_v1:  75%|#######5  | 2263/3000 [52:45<14:42,  1.20s/it, lr: 1.0e-04 loss: 6.604e-01]
latex_v1:  75%|#######5  | 2263/3000 [52:45<14:42,  1.20s/it, lr: 1.0e-04 loss: 6.604e-01]
latex_v1:  75%|#######5  | 2263/3000 [52:46<14:42,  1.20s/it, lr: 1.0e-04 loss: 9.134e-02]
latex_v1:  75%|#######5  | 2263/3000 [52:46<14:42,  1.20s/it, lr: 1.0e-04 loss: 9.134e-02]
latex_v1:  75%|#######5  | 2264/3000 [52:46<13:11,  1.08s/it, lr: 1.0e-04 loss: 9.134e-02]
latex_v1:  75%|#######5  | 2264/3000 [52:46<13:11,  1.08s/it, lr: 1.0e-04 loss: 9.134e-02]
latex_v1:  75%|#######5  | 2264/3000 [52:48<13:11,  1.08s/it, lr: 1.0e-04 loss: 9.308e-02]
latex_v1:  75%|#######5  | 2264/3000 [52:48<13:11,  1.08s/it, lr: 1.0e-04 loss: 9.308e-02]
latex_v1:  76%|#######5  | 2265/3000 [52:48<14:45,  1.20s/it, lr: 1.0e-04 loss: 9.308e-02]
latex_v1:  76%|#######5  | 2265/3000 [52:48<14:45,  1.20s/it, lr: 1.0e-04 loss: 9.308e-02]
latex_v1:  76%|#######5  | 2265/3000 [52:50<14:45,  1.20s/it, lr: 1.0e-04 loss: 3.701e-02]
latex_v1:  76%|#######5  | 2265/3000 [52:50<14:45,  1.20s/it, lr: 1.0e-04 loss: 3.701e-02]
latex_v1:  76%|#######5  | 2266/3000 [52:50<20:31,  1.68s/it, lr: 1.0e-04 loss: 3.701e-02]
latex_v1:  76%|#######5  | 2266/3000 [52:50<20:31,  1.68s/it, lr: 1.0e-04 loss: 3.701e-02]
latex_v1:  76%|#######5  | 2266/3000 [52:51<20:31,  1.68s/it, lr: 1.0e-04 loss: 2.578e-01]
latex_v1:  76%|#######5  | 2266/3000 [52:51<20:31,  1.68s/it, lr: 1.0e-04 loss: 2.578e-01]
latex_v1:  76%|#######5  | 2267/3000 [52:51<17:11,  1.41s/it, lr: 1.0e-04 loss: 2.578e-01]
latex_v1:  76%|#######5  | 2267/3000 [52:51<17:11,  1.41s/it, lr: 1.0e-04 loss: 2.578e-01]
latex_v1:  76%|#######5  | 2267/3000 [52:54<17:11,  1.41s/it, lr: 1.0e-04 loss: 2.029e-01]
latex_v1:  76%|#######5  | 2267/3000 [52:54<17:11,  1.41s/it, lr: 1.0e-04 loss: 2.029e-01]
latex_v1:  76%|#######5  | 2268/3000 [52:54<21:45,  1.78s/it, lr: 1.0e-04 loss: 2.029e-01]
latex_v1:  76%|#######5  | 2268/3000 [52:54<21:45,  1.78s/it, lr: 1.0e-04 loss: 2.029e-01]
latex_v1:  76%|#######5  | 2268/3000 [52:55<21:45,  1.78s/it, lr: 1.0e-04 loss: 6.002e-01]
latex_v1:  76%|#######5  | 2268/3000 [52:55<21:45,  1.78s/it, lr: 1.0e-04 loss: 6.002e-01]
latex_v1:  76%|#######5  | 2269/3000 [52:55<18:00,  1.48s/it, lr: 1.0e-04 loss: 6.002e-01]
latex_v1:  76%|#######5  | 2269/3000 [52:55<18:00,  1.48s/it, lr: 1.0e-04 loss: 6.002e-01]
latex_v1:  76%|#######5  | 2269/3000 [52:57<18:00,  1.48s/it, lr: 1.0e-04 loss: 1.947e-01]
latex_v1:  76%|#######5  | 2269/3000 [52:57<18:00,  1.48s/it, lr: 1.0e-04 loss: 1.947e-01]
latex_v1:  76%|#######5  | 2270/3000 [52:58<17:59,  1.48s/it, lr: 1.0e-04 loss: 6.382e-01]
latex_v1:  76%|#######5  | 2270/3000 [52:58<17:59,  1.48s/it, lr: 1.0e-04 loss: 6.382e-01]
latex_v1:  76%|#######5  | 2271/3000 [52:58<13:57,  1.15s/it, lr: 1.0e-04 loss: 6.382e-01]
latex_v1:  76%|#######5  | 2271/3000 [52:58<13:57,  1.15s/it, lr: 1.0e-04 loss: 6.382e-01]
latex_v1:  76%|#######5  | 2271/3000 [53:01<13:57,  1.15s/it, lr: 1.0e-04 loss: 7.272e-02]
latex_v1:  76%|#######5  | 2271/3000 [53:01<13:57,  1.15s/it, lr: 1.0e-04 loss: 7.272e-02]
latex_v1:  76%|#######5  | 2272/3000 [53:01<18:52,  1.56s/it, lr: 1.0e-04 loss: 7.272e-02]
latex_v1:  76%|#######5  | 2272/3000 [53:01<18:52,  1.56s/it, lr: 1.0e-04 loss: 7.272e-02]
latex_v1:  76%|#######5  | 2272/3000 [53:02<18:52,  1.56s/it, lr: 1.0e-04 loss: 6.883e-01]
latex_v1:  76%|#######5  | 2272/3000 [53:02<18:52,  1.56s/it, lr: 1.0e-04 loss: 6.883e-01]
latex_v1:  76%|#######5  | 2273/3000 [53:02<17:34,  1.45s/it, lr: 1.0e-04 loss: 6.883e-01]
latex_v1:  76%|#######5  | 2273/3000 [53:02<17:34,  1.45s/it, lr: 1.0e-04 loss: 6.883e-01]
latex_v1:  76%|#######5  | 2273/3000 [53:05<17:34,  1.45s/it, lr: 1.0e-04 loss: 3.470e-01]
latex_v1:  76%|#######5  | 2273/3000 [53:05<17:34,  1.45s/it, lr: 1.0e-04 loss: 3.470e-01]
latex_v1:  76%|#######5  | 2274/3000 [53:05<22:14,  1.84s/it, lr: 1.0e-04 loss: 3.470e-01]
latex_v1:  76%|#######5  | 2274/3000 [53:05<22:14,  1.84s/it, lr: 1.0e-04 loss: 3.470e-01]
latex_v1:  76%|#######5  | 2274/3000 [53:07<22:14,  1.84s/it, lr: 1.0e-04 loss: 5.558e-01]
latex_v1:  76%|#######5  | 2274/3000 [53:07<22:14,  1.84s/it, lr: 1.0e-04 loss: 5.558e-01]
latex_v1:  76%|#######5  | 2275/3000 [53:07<23:20,  1.93s/it, lr: 1.0e-04 loss: 5.558e-01]
latex_v1:  76%|#######5  | 2275/3000 [53:07<23:20,  1.93s/it, lr: 1.0e-04 loss: 5.558e-01]
latex_v1:  76%|#######5  | 2275/3000 [53:09<23:20,  1.93s/it, lr: 1.0e-04 loss: 4.273e-01]
latex_v1:  76%|#######5  | 2275/3000 [53:09<23:20,  1.93s/it, lr: 1.0e-04 loss: 4.273e-01]
latex_v1:  76%|#######5  | 2276/3000 [53:09<22:00,  1.82s/it, lr: 1.0e-04 loss: 4.273e-01]
latex_v1:  76%|#######5  | 2276/3000 [53:09<22:00,  1.82s/it, lr: 1.0e-04 loss: 4.273e-01]
latex_v1:  76%|#######5  | 2276/3000 [53:09<22:00,  1.82s/it, lr: 1.0e-04 loss: 1.002e-01]
latex_v1:  76%|#######5  | 2276/3000 [53:09<22:00,  1.82s/it, lr: 1.0e-04 loss: 1.002e-01]
latex_v1:  76%|#######5  | 2277/3000 [53:09<18:10,  1.51s/it, lr: 1.0e-04 loss: 1.002e-01]
latex_v1:  76%|#######5  | 2277/3000 [53:09<18:10,  1.51s/it, lr: 1.0e-04 loss: 1.002e-01]
latex_v1:  76%|#######5  | 2277/3000 [53:10<18:10,  1.51s/it, lr: 1.0e-04 loss: 5.279e-01]
latex_v1:  76%|#######5  | 2277/3000 [53:10<18:10,  1.51s/it, lr: 1.0e-04 loss: 5.279e-01]
latex_v1:  76%|#######5  | 2278/3000 [53:10<16:15,  1.35s/it, lr: 1.0e-04 loss: 5.279e-01]
latex_v1:  76%|#######5  | 2278/3000 [53:10<16:15,  1.35s/it, lr: 1.0e-04 loss: 5.279e-01]
latex_v1:  76%|#######5  | 2278/3000 [53:12<16:15,  1.35s/it, lr: 1.0e-04 loss: 1.059e-01]
latex_v1:  76%|#######5  | 2278/3000 [53:12<16:15,  1.35s/it, lr: 1.0e-04 loss: 1.059e-01]
latex_v1:  76%|#######5  | 2279/3000 [53:12<16:48,  1.40s/it, lr: 1.0e-04 loss: 1.059e-01]
latex_v1:  76%|#######5  | 2279/3000 [53:12<16:48,  1.40s/it, lr: 1.0e-04 loss: 1.059e-01]
latex_v1:  76%|#######5  | 2279/3000 [53:14<16:48,  1.40s/it, lr: 1.0e-04 loss: 4.583e-01]
latex_v1:  76%|#######5  | 2279/3000 [53:14<16:48,  1.40s/it, lr: 1.0e-04 loss: 4.583e-01]
latex_v1:  76%|#######6  | 2280/3000 [53:15<16:47,  1.40s/it, lr: 1.0e-04 loss: 5.871e-02]
latex_v1:  76%|#######6  | 2280/3000 [53:15<16:47,  1.40s/it, lr: 1.0e-04 loss: 5.871e-02]
latex_v1:  76%|#######6  | 2281/3000 [53:15<11:07,  1.08it/s, lr: 1.0e-04 loss: 5.871e-02]
latex_v1:  76%|#######6  | 2281/3000 [53:15<11:07,  1.08it/s, lr: 1.0e-04 loss: 5.871e-02]
latex_v1:  76%|#######6  | 2281/3000 [53:16<11:07,  1.08it/s, lr: 1.0e-04 loss: 8.386e-01]
latex_v1:  76%|#######6  | 2281/3000 [53:16<11:07,  1.08it/s, lr: 1.0e-04 loss: 8.386e-01]
latex_v1:  76%|#######6  | 2282/3000 [53:16<10:32,  1.14it/s, lr: 1.0e-04 loss: 8.386e-01]
latex_v1:  76%|#######6  | 2282/3000 [53:16<10:32,  1.14it/s, lr: 1.0e-04 loss: 8.386e-01]
latex_v1:  76%|#######6  | 2282/3000 [53:17<10:32,  1.14it/s, lr: 1.0e-04 loss: 3.903e-01]
latex_v1:  76%|#######6  | 2282/3000 [53:17<10:32,  1.14it/s, lr: 1.0e-04 loss: 3.903e-01]
latex_v1:  76%|#######6  | 2283/3000 [53:17<11:53,  1.01it/s, lr: 1.0e-04 loss: 3.903e-01]
latex_v1:  76%|#######6  | 2283/3000 [53:17<11:53,  1.01it/s, lr: 1.0e-04 loss: 3.903e-01]
latex_v1:  76%|#######6  | 2283/3000 [53:18<11:53,  1.01it/s, lr: 1.0e-04 loss: 6.322e-02]
latex_v1:  76%|#######6  | 2283/3000 [53:18<11:53,  1.01it/s, lr: 1.0e-04 loss: 6.322e-02]
latex_v1:  76%|#######6  | 2284/3000 [53:18<11:03,  1.08it/s, lr: 1.0e-04 loss: 6.322e-02]
latex_v1:  76%|#######6  | 2284/3000 [53:18<11:03,  1.08it/s, lr: 1.0e-04 loss: 6.322e-02]
latex_v1:  76%|#######6  | 2284/3000 [53:20<11:03,  1.08it/s, lr: 1.0e-04 loss: 5.521e-01]
latex_v1:  76%|#######6  | 2284/3000 [53:20<11:03,  1.08it/s, lr: 1.0e-04 loss: 5.521e-01]
latex_v1:  76%|#######6  | 2285/3000 [53:20<14:08,  1.19s/it, lr: 1.0e-04 loss: 5.521e-01]
latex_v1:  76%|#######6  | 2285/3000 [53:20<14:08,  1.19s/it, lr: 1.0e-04 loss: 5.521e-01]
latex_v1:  76%|#######6  | 2285/3000 [53:23<14:08,  1.19s/it, lr: 1.0e-04 loss: 7.631e-01]
latex_v1:  76%|#######6  | 2285/3000 [53:23<14:08,  1.19s/it, lr: 1.0e-04 loss: 7.631e-01]
latex_v1:  76%|#######6  | 2286/3000 [53:23<19:41,  1.66s/it, lr: 1.0e-04 loss: 7.631e-01]
latex_v1:  76%|#######6  | 2286/3000 [53:23<19:41,  1.66s/it, lr: 1.0e-04 loss: 7.631e-01]
latex_v1:  76%|#######6  | 2286/3000 [53:24<19:41,  1.66s/it, lr: 1.0e-04 loss: 3.681e-01]
latex_v1:  76%|#######6  | 2286/3000 [53:24<19:41,  1.66s/it, lr: 1.0e-04 loss: 3.681e-01]
latex_v1:  76%|#######6  | 2287/3000 [53:24<18:49,  1.58s/it, lr: 1.0e-04 loss: 3.681e-01]
latex_v1:  76%|#######6  | 2287/3000 [53:24<18:49,  1.58s/it, lr: 1.0e-04 loss: 3.681e-01]
latex_v1:  76%|#######6  | 2287/3000 [53:26<18:49,  1.58s/it, lr: 1.0e-04 loss: 9.351e-02]
latex_v1:  76%|#######6  | 2287/3000 [53:26<18:49,  1.58s/it, lr: 1.0e-04 loss: 9.351e-02]
latex_v1:  76%|#######6  | 2288/3000 [53:26<18:16,  1.54s/it, lr: 1.0e-04 loss: 9.351e-02]
latex_v1:  76%|#######6  | 2288/3000 [53:26<18:16,  1.54s/it, lr: 1.0e-04 loss: 9.351e-02]
latex_v1:  76%|#######6  | 2288/3000 [53:27<18:16,  1.54s/it, lr: 1.0e-04 loss: 5.038e-01]
latex_v1:  76%|#######6  | 2288/3000 [53:27<18:16,  1.54s/it, lr: 1.0e-04 loss: 5.038e-01]
latex_v1:  76%|#######6  | 2289/3000 [53:27<18:18,  1.54s/it, lr: 1.0e-04 loss: 5.038e-01]
latex_v1:  76%|#######6  | 2289/3000 [53:27<18:18,  1.54s/it, lr: 1.0e-04 loss: 5.038e-01]
latex_v1:  76%|#######6  | 2289/3000 [53:28<18:18,  1.54s/it, lr: 1.0e-04 loss: 7.653e-01]
latex_v1:  76%|#######6  | 2289/3000 [53:28<18:18,  1.54s/it, lr: 1.0e-04 loss: 7.653e-01]
latex_v1:  76%|#######6  | 2290/3000 [53:29<18:16,  1.54s/it, lr: 1.0e-04 loss: 2.188e-01]
latex_v1:  76%|#######6  | 2290/3000 [53:29<18:16,  1.54s/it, lr: 1.0e-04 loss: 2.188e-01]
latex_v1:  76%|#######6  | 2291/3000 [53:29<11:54,  1.01s/it, lr: 1.0e-04 loss: 2.188e-01]
latex_v1:  76%|#######6  | 2291/3000 [53:29<11:54,  1.01s/it, lr: 1.0e-04 loss: 2.188e-01]
latex_v1:  76%|#######6  | 2291/3000 [53:31<11:54,  1.01s/it, lr: 1.0e-04 loss: 3.013e-01]
latex_v1:  76%|#######6  | 2291/3000 [53:31<11:54,  1.01s/it, lr: 1.0e-04 loss: 3.013e-01]
latex_v1:  76%|#######6  | 2292/3000 [53:31<13:58,  1.18s/it, lr: 1.0e-04 loss: 3.013e-01]
latex_v1:  76%|#######6  | 2292/3000 [53:31<13:58,  1.18s/it, lr: 1.0e-04 loss: 3.013e-01]
latex_v1:  76%|#######6  | 2292/3000 [53:32<13:58,  1.18s/it, lr: 1.0e-04 loss: 6.113e-01]
latex_v1:  76%|#######6  | 2292/3000 [53:32<13:58,  1.18s/it, lr: 1.0e-04 loss: 6.113e-01]
latex_v1:  76%|#######6  | 2293/3000 [53:32<12:38,  1.07s/it, lr: 1.0e-04 loss: 6.113e-01]
latex_v1:  76%|#######6  | 2293/3000 [53:32<12:38,  1.07s/it, lr: 1.0e-04 loss: 6.113e-01]
latex_v1:  76%|#######6  | 2293/3000 [53:33<12:38,  1.07s/it, lr: 1.0e-04 loss: 5.136e-01]
latex_v1:  76%|#######6  | 2293/3000 [53:33<12:38,  1.07s/it, lr: 1.0e-04 loss: 5.136e-01]
latex_v1:  76%|#######6  | 2294/3000 [53:33<12:33,  1.07s/it, lr: 1.0e-04 loss: 5.136e-01]
latex_v1:  76%|#######6  | 2294/3000 [53:33<12:33,  1.07s/it, lr: 1.0e-04 loss: 5.136e-01]
latex_v1:  76%|#######6  | 2294/3000 [53:33<12:33,  1.07s/it, lr: 1.0e-04 loss: 4.591e-01]
latex_v1:  76%|#######6  | 2294/3000 [53:33<12:33,  1.07s/it, lr: 1.0e-04 loss: 4.591e-01]
latex_v1:  76%|#######6  | 2295/3000 [53:33<11:32,  1.02it/s, lr: 1.0e-04 loss: 4.591e-01]
latex_v1:  76%|#######6  | 2295/3000 [53:33<11:32,  1.02it/s, lr: 1.0e-04 loss: 4.591e-01]
latex_v1:  76%|#######6  | 2295/3000 [53:34<11:32,  1.02it/s, lr: 1.0e-04 loss: 9.284e-02]
latex_v1:  76%|#######6  | 2295/3000 [53:34<11:32,  1.02it/s, lr: 1.0e-04 loss: 9.284e-02]
latex_v1:  77%|#######6  | 2296/3000 [53:34<10:44,  1.09it/s, lr: 1.0e-04 loss: 9.284e-02]
latex_v1:  77%|#######6  | 2296/3000 [53:34<10:44,  1.09it/s, lr: 1.0e-04 loss: 9.284e-02]
latex_v1:  77%|#######6  | 2296/3000 [53:37<10:44,  1.09it/s, lr: 1.0e-04 loss: 1.893e-01]
latex_v1:  77%|#######6  | 2296/3000 [53:37<10:44,  1.09it/s, lr: 1.0e-04 loss: 1.893e-01]
latex_v1:  77%|#######6  | 2297/3000 [53:37<17:14,  1.47s/it, lr: 1.0e-04 loss: 1.893e-01]
latex_v1:  77%|#######6  | 2297/3000 [53:37<17:14,  1.47s/it, lr: 1.0e-04 loss: 1.893e-01]
latex_v1:  77%|#######6  | 2297/3000 [53:39<17:14,  1.47s/it, lr: 1.0e-04 loss: 4.981e-01]
latex_v1:  77%|#######6  | 2297/3000 [53:39<17:14,  1.47s/it, lr: 1.0e-04 loss: 4.981e-01]
latex_v1:  77%|#######6  | 2298/3000 [53:39<17:24,  1.49s/it, lr: 1.0e-04 loss: 4.981e-01]
latex_v1:  77%|#######6  | 2298/3000 [53:39<17:24,  1.49s/it, lr: 1.0e-04 loss: 4.981e-01]
latex_v1:  77%|#######6  | 2298/3000 [53:40<17:24,  1.49s/it, lr: 1.0e-04 loss: 5.733e-01]
latex_v1:  77%|#######6  | 2298/3000 [53:40<17:24,  1.49s/it, lr: 1.0e-04 loss: 5.733e-01]
latex_v1:  77%|#######6  | 2299/3000 [53:40<18:57,  1.62s/it, lr: 1.0e-04 loss: 5.733e-01]
latex_v1:  77%|#######6  | 2299/3000 [53:40<18:57,  1.62s/it, lr: 1.0e-04 loss: 5.733e-01]
latex_v1:  77%|#######6  | 2299/3000 [53:41<18:57,  1.62s/it, lr: 1.0e-04 loss: 3.813e-01]
latex_v1:  77%|#######6  | 2299/3000 [53:41<18:57,  1.62s/it, lr: 1.0e-04 loss: 3.813e-01]
latex_v1:  77%|#######6  | 2300/3000 [53:43<18:55,  1.62s/it, lr: 1.0e-04 loss: 5.104e-01]
latex_v1:  77%|#######6  | 2300/3000 [53:43<18:55,  1.62s/it, lr: 1.0e-04 loss: 5.104e-01]
latex_v1:  77%|#######6  | 2301/3000 [53:43<13:52,  1.19s/it, lr: 1.0e-04 loss: 5.104e-01]
latex_v1:  77%|#######6  | 2301/3000 [53:43<13:52,  1.19s/it, lr: 1.0e-04 loss: 5.104e-01]
latex_v1:  77%|#######6  | 2301/3000 [53:45<13:52,  1.19s/it, lr: 1.0e-04 loss: 6.917e-01]
latex_v1:  77%|#######6  | 2301/3000 [53:45<13:52,  1.19s/it, lr: 1.0e-04 loss: 6.917e-01]
latex_v1:  77%|#######6  | 2302/3000 [53:45<18:24,  1.58s/it, lr: 1.0e-04 loss: 6.917e-01]
latex_v1:  77%|#######6  | 2302/3000 [53:45<18:24,  1.58s/it, lr: 1.0e-04 loss: 6.917e-01]
latex_v1:  77%|#######6  | 2302/3000 [53:46<18:24,  1.58s/it, lr: 1.0e-04 loss: 4.393e-01]
latex_v1:  77%|#######6  | 2302/3000 [53:46<18:24,  1.58s/it, lr: 1.0e-04 loss: 4.393e-01]
latex_v1:  77%|#######6  | 2303/3000 [53:46<15:49,  1.36s/it, lr: 1.0e-04 loss: 4.393e-01]
latex_v1:  77%|#######6  | 2303/3000 [53:46<15:49,  1.36s/it, lr: 1.0e-04 loss: 4.393e-01]
latex_v1:  77%|#######6  | 2303/3000 [53:47<15:49,  1.36s/it, lr: 1.0e-04 loss: 6.024e-01]
latex_v1:  77%|#######6  | 2303/3000 [53:47<15:49,  1.36s/it, lr: 1.0e-04 loss: 6.024e-01]
latex_v1:  77%|#######6  | 2304/3000 [53:47<13:52,  1.20s/it, lr: 1.0e-04 loss: 6.024e-01]
latex_v1:  77%|#######6  | 2304/3000 [53:47<13:52,  1.20s/it, lr: 1.0e-04 loss: 6.024e-01]
latex_v1:  77%|#######6  | 2304/3000 [53:49<13:52,  1.20s/it, lr: 1.0e-04 loss: 1.372e-01]
latex_v1:  77%|#######6  | 2304/3000 [53:49<13:52,  1.20s/it, lr: 1.0e-04 loss: 1.372e-01]
latex_v1:  77%|#######6  | 2305/3000 [53:49<15:24,  1.33s/it, lr: 1.0e-04 loss: 1.372e-01]
latex_v1:  77%|#######6  | 2305/3000 [53:49<15:24,  1.33s/it, lr: 1.0e-04 loss: 1.372e-01]
latex_v1:  77%|#######6  | 2305/3000 [53:50<15:24,  1.33s/it, lr: 1.0e-04 loss: 1.561e-01]
latex_v1:  77%|#######6  | 2305/3000 [53:50<15:24,  1.33s/it, lr: 1.0e-04 loss: 1.561e-01]
latex_v1:  77%|#######6  | 2306/3000 [53:50<16:01,  1.39s/it, lr: 1.0e-04 loss: 1.561e-01]
latex_v1:  77%|#######6  | 2306/3000 [53:50<16:01,  1.39s/it, lr: 1.0e-04 loss: 1.561e-01]
latex_v1:  77%|#######6  | 2306/3000 [53:51<16:01,  1.39s/it, lr: 1.0e-04 loss: 6.000e-01]
latex_v1:  77%|#######6  | 2306/3000 [53:51<16:01,  1.39s/it, lr: 1.0e-04 loss: 6.000e-01]
latex_v1:  77%|#######6  | 2307/3000 [53:51<16:03,  1.39s/it, lr: 1.0e-04 loss: 6.000e-01]
latex_v1:  77%|#######6  | 2307/3000 [53:51<16:03,  1.39s/it, lr: 1.0e-04 loss: 6.000e-01]
latex_v1:  77%|#######6  | 2307/3000 [53:52<16:03,  1.39s/it, lr: 1.0e-04 loss: 8.166e-02]
latex_v1:  77%|#######6  | 2307/3000 [53:52<16:03,  1.39s/it, lr: 1.0e-04 loss: 8.166e-02]
latex_v1:  77%|#######6  | 2308/3000 [53:52<13:51,  1.20s/it, lr: 1.0e-04 loss: 8.166e-02]
latex_v1:  77%|#######6  | 2308/3000 [53:52<13:51,  1.20s/it, lr: 1.0e-04 loss: 8.166e-02]
latex_v1:  77%|#######6  | 2308/3000 [53:54<13:51,  1.20s/it, lr: 1.0e-04 loss: 2.129e-01]
latex_v1:  77%|#######6  | 2308/3000 [53:54<13:51,  1.20s/it, lr: 1.0e-04 loss: 2.129e-01]
latex_v1:  77%|#######6  | 2309/3000 [53:54<14:38,  1.27s/it, lr: 1.0e-04 loss: 2.129e-01]
latex_v1:  77%|#######6  | 2309/3000 [53:54<14:38,  1.27s/it, lr: 1.0e-04 loss: 2.129e-01]
latex_v1:  77%|#######6  | 2309/3000 [53:54<14:38,  1.27s/it, lr: 1.0e-04 loss: 5.055e-01]
latex_v1:  77%|#######6  | 2309/3000 [53:54<14:38,  1.27s/it, lr: 1.0e-04 loss: 5.055e-01]
latex_v1:  77%|#######7  | 2310/3000 [53:55<14:37,  1.27s/it, lr: 1.0e-04 loss: 4.153e-01]
latex_v1:  77%|#######7  | 2310/3000 [53:55<14:37,  1.27s/it, lr: 1.0e-04 loss: 4.153e-01]
latex_v1:  77%|#######7  | 2311/3000 [53:55<09:54,  1.16it/s, lr: 1.0e-04 loss: 4.153e-01]
latex_v1:  77%|#######7  | 2311/3000 [53:55<09:54,  1.16it/s, lr: 1.0e-04 loss: 4.153e-01]
latex_v1:  77%|#######7  | 2311/3000 [53:57<09:54,  1.16it/s, lr: 1.0e-04 loss: 1.445e-01]
latex_v1:  77%|#######7  | 2311/3000 [53:57<09:54,  1.16it/s, lr: 1.0e-04 loss: 1.445e-01]
latex_v1:  77%|#######7  | 2312/3000 [53:57<11:49,  1.03s/it, lr: 1.0e-04 loss: 1.445e-01]
latex_v1:  77%|#######7  | 2312/3000 [53:57<11:49,  1.03s/it, lr: 1.0e-04 loss: 1.445e-01]
latex_v1:  77%|#######7  | 2312/3000 [53:59<11:49,  1.03s/it, lr: 1.0e-04 loss: 2.895e-01]
latex_v1:  77%|#######7  | 2312/3000 [53:59<11:49,  1.03s/it, lr: 1.0e-04 loss: 2.895e-01]
latex_v1:  77%|#######7  | 2313/3000 [53:59<14:15,  1.24s/it, lr: 1.0e-04 loss: 2.895e-01]
latex_v1:  77%|#######7  | 2313/3000 [53:59<14:15,  1.24s/it, lr: 1.0e-04 loss: 2.895e-01]
latex_v1:  77%|#######7  | 2313/3000 [53:59<14:15,  1.24s/it, lr: 1.0e-04 loss: 4.321e-02]
latex_v1:  77%|#######7  | 2313/3000 [53:59<14:15,  1.24s/it, lr: 1.0e-04 loss: 4.321e-02]
latex_v1:  77%|#######7  | 2314/3000 [53:59<12:44,  1.11s/it, lr: 1.0e-04 loss: 4.321e-02]
latex_v1:  77%|#######7  | 2314/3000 [53:59<12:44,  1.11s/it, lr: 1.0e-04 loss: 4.321e-02]
latex_v1:  77%|#######7  | 2314/3000 [54:00<12:44,  1.11s/it, lr: 1.0e-04 loss: 4.694e-01]
latex_v1:  77%|#######7  | 2314/3000 [54:00<12:44,  1.11s/it, lr: 1.0e-04 loss: 4.694e-01]
latex_v1:  77%|#######7  | 2315/3000 [54:00<11:30,  1.01s/it, lr: 1.0e-04 loss: 4.694e-01]
latex_v1:  77%|#######7  | 2315/3000 [54:00<11:30,  1.01s/it, lr: 1.0e-04 loss: 4.694e-01]
latex_v1:  77%|#######7  | 2315/3000 [54:01<11:30,  1.01s/it, lr: 1.0e-04 loss: 5.641e-01]
latex_v1:  77%|#######7  | 2315/3000 [54:01<11:30,  1.01s/it, lr: 1.0e-04 loss: 5.641e-01]
latex_v1:  77%|#######7  | 2316/3000 [54:01<10:38,  1.07it/s, lr: 1.0e-04 loss: 5.641e-01]
latex_v1:  77%|#######7  | 2316/3000 [54:01<10:38,  1.07it/s, lr: 1.0e-04 loss: 5.641e-01]
latex_v1:  77%|#######7  | 2316/3000 [54:02<10:38,  1.07it/s, lr: 1.0e-04 loss: 3.529e-01]
latex_v1:  77%|#######7  | 2316/3000 [54:02<10:38,  1.07it/s, lr: 1.0e-04 loss: 3.529e-01]
latex_v1:  77%|#######7  | 2317/3000 [54:02<12:16,  1.08s/it, lr: 1.0e-04 loss: 3.529e-01]
latex_v1:  77%|#######7  | 2317/3000 [54:02<12:16,  1.08s/it, lr: 1.0e-04 loss: 3.529e-01]
latex_v1:  77%|#######7  | 2317/3000 [54:03<12:16,  1.08s/it, lr: 1.0e-04 loss: 1.559e-01]
latex_v1:  77%|#######7  | 2317/3000 [54:03<12:16,  1.08s/it, lr: 1.0e-04 loss: 1.559e-01]
latex_v1:  77%|#######7  | 2318/3000 [54:03<11:52,  1.04s/it, lr: 1.0e-04 loss: 1.559e-01]
latex_v1:  77%|#######7  | 2318/3000 [54:03<11:52,  1.04s/it, lr: 1.0e-04 loss: 1.559e-01]
latex_v1:  77%|#######7  | 2318/3000 [54:04<11:52,  1.04s/it, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:  77%|#######7  | 2318/3000 [54:04<11:52,  1.04s/it, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:  77%|#######7  | 2319/3000 [54:04<10:49,  1.05it/s, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:  77%|#######7  | 2319/3000 [54:04<10:49,  1.05it/s, lr: 1.0e-04 loss: 2.513e-01]
latex_v1:  77%|#######7  | 2319/3000 [54:05<10:49,  1.05it/s, lr: 1.0e-04 loss: 5.681e-01]
latex_v1:  77%|#######7  | 2319/3000 [54:05<10:49,  1.05it/s, lr: 1.0e-04 loss: 5.681e-01]
latex_v1:  77%|#######7  | 2320/3000 [54:07<10:48,  1.05it/s, lr: 1.0e-04 loss: 4.255e-01]
latex_v1:  77%|#######7  | 2320/3000 [54:07<10:48,  1.05it/s, lr: 1.0e-04 loss: 4.255e-01]
latex_v1:  77%|#######7  | 2321/3000 [54:07<10:40,  1.06it/s, lr: 1.0e-04 loss: 4.255e-01]
latex_v1:  77%|#######7  | 2321/3000 [54:07<10:40,  1.06it/s, lr: 1.0e-04 loss: 4.255e-01]
latex_v1:  77%|#######7  | 2321/3000 [54:08<10:40,  1.06it/s, lr: 1.0e-04 loss: 2.839e-01]
latex_v1:  77%|#######7  | 2321/3000 [54:08<10:40,  1.06it/s, lr: 1.0e-04 loss: 2.839e-01]
latex_v1:  77%|#######7  | 2322/3000 [54:08<11:15,  1.00it/s, lr: 1.0e-04 loss: 2.839e-01]
latex_v1:  77%|#######7  | 2322/3000 [54:08<11:15,  1.00it/s, lr: 1.0e-04 loss: 2.839e-01]
latex_v1:  77%|#######7  | 2322/3000 [54:10<11:15,  1.00it/s, lr: 1.0e-04 loss: 4.203e-02]
latex_v1:  77%|#######7  | 2322/3000 [54:10<11:15,  1.00it/s, lr: 1.0e-04 loss: 4.203e-02]
latex_v1:  77%|#######7  | 2323/3000 [54:10<12:17,  1.09s/it, lr: 1.0e-04 loss: 4.203e-02]
latex_v1:  77%|#######7  | 2323/3000 [54:10<12:17,  1.09s/it, lr: 1.0e-04 loss: 4.203e-02]
latex_v1:  77%|#######7  | 2323/3000 [54:11<12:17,  1.09s/it, lr: 1.0e-04 loss: 7.012e-02]
latex_v1:  77%|#######7  | 2323/3000 [54:11<12:17,  1.09s/it, lr: 1.0e-04 loss: 7.012e-02]
latex_v1:  77%|#######7  | 2324/3000 [54:11<13:02,  1.16s/it, lr: 1.0e-04 loss: 7.012e-02]
latex_v1:  77%|#######7  | 2324/3000 [54:11<13:02,  1.16s/it, lr: 1.0e-04 loss: 7.012e-02]
latex_v1:  77%|#######7  | 2324/3000 [54:14<13:02,  1.16s/it, lr: 1.0e-04 loss: 2.192e-01]
latex_v1:  77%|#######7  | 2324/3000 [54:14<13:02,  1.16s/it, lr: 1.0e-04 loss: 2.192e-01]
latex_v1:  78%|#######7  | 2325/3000 [54:14<18:15,  1.62s/it, lr: 1.0e-04 loss: 2.192e-01]
latex_v1:  78%|#######7  | 2325/3000 [54:14<18:15,  1.62s/it, lr: 1.0e-04 loss: 2.192e-01]
latex_v1:  78%|#######7  | 2325/3000 [54:15<18:15,  1.62s/it, lr: 1.0e-04 loss: 1.565e-01]
latex_v1:  78%|#######7  | 2325/3000 [54:15<18:15,  1.62s/it, lr: 1.0e-04 loss: 1.565e-01]
latex_v1:  78%|#######7  | 2326/3000 [54:15<15:25,  1.37s/it, lr: 1.0e-04 loss: 1.565e-01]
latex_v1:  78%|#######7  | 2326/3000 [54:15<15:25,  1.37s/it, lr: 1.0e-04 loss: 1.565e-01]
latex_v1:  78%|#######7  | 2326/3000 [54:16<15:25,  1.37s/it, lr: 1.0e-04 loss: 5.420e-01]
latex_v1:  78%|#######7  | 2326/3000 [54:16<15:25,  1.37s/it, lr: 1.0e-04 loss: 5.420e-01]
latex_v1:  78%|#######7  | 2327/3000 [54:16<13:26,  1.20s/it, lr: 1.0e-04 loss: 5.420e-01]
latex_v1:  78%|#######7  | 2327/3000 [54:16<13:26,  1.20s/it, lr: 1.0e-04 loss: 5.420e-01]
latex_v1:  78%|#######7  | 2327/3000 [54:17<13:26,  1.20s/it, lr: 1.0e-04 loss: 1.554e-01]
latex_v1:  78%|#######7  | 2327/3000 [54:17<13:26,  1.20s/it, lr: 1.0e-04 loss: 1.554e-01]
latex_v1:  78%|#######7  | 2328/3000 [54:17<13:47,  1.23s/it, lr: 1.0e-04 loss: 1.554e-01]
latex_v1:  78%|#######7  | 2328/3000 [54:17<13:47,  1.23s/it, lr: 1.0e-04 loss: 1.554e-01]
latex_v1:  78%|#######7  | 2328/3000 [54:18<13:47,  1.23s/it, lr: 1.0e-04 loss: 2.961e-01]
latex_v1:  78%|#######7  | 2328/3000 [54:18<13:47,  1.23s/it, lr: 1.0e-04 loss: 2.961e-01]
latex_v1:  78%|#######7  | 2329/3000 [54:18<12:09,  1.09s/it, lr: 1.0e-04 loss: 2.961e-01]
latex_v1:  78%|#######7  | 2329/3000 [54:18<12:09,  1.09s/it, lr: 1.0e-04 loss: 2.961e-01]
latex_v1:  78%|#######7  | 2329/3000 [54:19<12:09,  1.09s/it, lr: 1.0e-04 loss: 2.579e-02]
latex_v1:  78%|#######7  | 2329/3000 [54:19<12:09,  1.09s/it, lr: 1.0e-04 loss: 2.579e-02]
latex_v1:  78%|#######7  | 2330/3000 [54:21<12:08,  1.09s/it, lr: 1.0e-04 loss: 1.753e-01]
latex_v1:  78%|#######7  | 2330/3000 [54:21<12:08,  1.09s/it, lr: 1.0e-04 loss: 1.753e-01]
latex_v1:  78%|#######7  | 2331/3000 [54:21<10:16,  1.09it/s, lr: 1.0e-04 loss: 1.753e-01]
latex_v1:  78%|#######7  | 2331/3000 [54:21<10:16,  1.09it/s, lr: 1.0e-04 loss: 1.753e-01]
latex_v1:  78%|#######7  | 2331/3000 [54:22<10:16,  1.09it/s, lr: 1.0e-04 loss: 4.888e-01]
latex_v1:  78%|#######7  | 2331/3000 [54:22<10:16,  1.09it/s, lr: 1.0e-04 loss: 4.888e-01]
latex_v1:  78%|#######7  | 2332/3000 [54:22<10:33,  1.06it/s, lr: 1.0e-04 loss: 4.888e-01]
latex_v1:  78%|#######7  | 2332/3000 [54:22<10:33,  1.06it/s, lr: 1.0e-04 loss: 4.888e-01]
latex_v1:  78%|#######7  | 2332/3000 [54:24<10:33,  1.06it/s, lr: 1.0e-04 loss: 1.905e-01]
latex_v1:  78%|#######7  | 2332/3000 [54:24<10:33,  1.06it/s, lr: 1.0e-04 loss: 1.905e-01]
latex_v1:  78%|#######7  | 2333/3000 [54:24<13:47,  1.24s/it, lr: 1.0e-04 loss: 1.905e-01]
latex_v1:  78%|#######7  | 2333/3000 [54:24<13:47,  1.24s/it, lr: 1.0e-04 loss: 1.905e-01]
latex_v1:  78%|#######7  | 2333/3000 [54:25<13:47,  1.24s/it, lr: 1.0e-04 loss: 2.411e-01]
latex_v1:  78%|#######7  | 2333/3000 [54:25<13:47,  1.24s/it, lr: 1.0e-04 loss: 2.411e-01]
latex_v1:  78%|#######7  | 2334/3000 [54:25<14:37,  1.32s/it, lr: 1.0e-04 loss: 2.411e-01]
latex_v1:  78%|#######7  | 2334/3000 [54:25<14:37,  1.32s/it, lr: 1.0e-04 loss: 2.411e-01]
latex_v1:  78%|#######7  | 2334/3000 [54:26<14:37,  1.32s/it, lr: 1.0e-04 loss: 3.143e-01]
latex_v1:  78%|#######7  | 2334/3000 [54:26<14:37,  1.32s/it, lr: 1.0e-04 loss: 3.143e-01]
latex_v1:  78%|#######7  | 2335/3000 [54:26<12:52,  1.16s/it, lr: 1.0e-04 loss: 3.143e-01]
latex_v1:  78%|#######7  | 2335/3000 [54:26<12:52,  1.16s/it, lr: 1.0e-04 loss: 3.143e-01]
latex_v1:  78%|#######7  | 2335/3000 [54:28<12:52,  1.16s/it, lr: 1.0e-04 loss: 4.573e-01]
latex_v1:  78%|#######7  | 2335/3000 [54:28<12:52,  1.16s/it, lr: 1.0e-04 loss: 4.573e-01]
latex_v1:  78%|#######7  | 2336/3000 [54:28<16:01,  1.45s/it, lr: 1.0e-04 loss: 4.573e-01]
latex_v1:  78%|#######7  | 2336/3000 [54:28<16:01,  1.45s/it, lr: 1.0e-04 loss: 4.573e-01]
latex_v1:  78%|#######7  | 2336/3000 [54:30<16:01,  1.45s/it, lr: 1.0e-04 loss: 5.655e-01]
latex_v1:  78%|#######7  | 2336/3000 [54:30<16:01,  1.45s/it, lr: 1.0e-04 loss: 5.655e-01]
latex_v1:  78%|#######7  | 2337/3000 [54:30<15:51,  1.44s/it, lr: 1.0e-04 loss: 5.655e-01]
latex_v1:  78%|#######7  | 2337/3000 [54:30<15:51,  1.44s/it, lr: 1.0e-04 loss: 5.655e-01]
latex_v1:  78%|#######7  | 2337/3000 [54:30<15:51,  1.44s/it, lr: 1.0e-04 loss: 5.361e-01]
latex_v1:  78%|#######7  | 2337/3000 [54:30<15:51,  1.44s/it, lr: 1.0e-04 loss: 5.361e-01]
latex_v1:  78%|#######7  | 2338/3000 [54:30<13:31,  1.23s/it, lr: 1.0e-04 loss: 5.361e-01]
latex_v1:  78%|#######7  | 2338/3000 [54:30<13:31,  1.23s/it, lr: 1.0e-04 loss: 5.361e-01]
latex_v1:  78%|#######7  | 2338/3000 [54:32<13:31,  1.23s/it, lr: 1.0e-04 loss: 1.921e-01]
latex_v1:  78%|#######7  | 2338/3000 [54:32<13:31,  1.23s/it, lr: 1.0e-04 loss: 1.921e-01]
latex_v1:  78%|#######7  | 2339/3000 [54:32<14:30,  1.32s/it, lr: 1.0e-04 loss: 1.921e-01]
latex_v1:  78%|#######7  | 2339/3000 [54:32<14:30,  1.32s/it, lr: 1.0e-04 loss: 1.921e-01]
latex_v1:  78%|#######7  | 2339/3000 [54:33<14:30,  1.32s/it, lr: 1.0e-04 loss: 1.524e-02]
latex_v1:  78%|#######7  | 2339/3000 [54:33<14:30,  1.32s/it, lr: 1.0e-04 loss: 1.524e-02]
latex_v1:  78%|#######8  | 2340/3000 [54:34<14:29,  1.32s/it, lr: 1.0e-04 loss: 2.212e-01]
latex_v1:  78%|#######8  | 2340/3000 [54:34<14:29,  1.32s/it, lr: 1.0e-04 loss: 2.212e-01]
latex_v1:  78%|#######8  | 2341/3000 [54:34<09:44,  1.13it/s, lr: 1.0e-04 loss: 2.212e-01]
latex_v1:  78%|#######8  | 2341/3000 [54:34<09:44,  1.13it/s, lr: 1.0e-04 loss: 2.212e-01]
latex_v1:  78%|#######8  | 2341/3000 [54:35<09:44,  1.13it/s, lr: 1.0e-04 loss: 3.932e-01]
latex_v1:  78%|#######8  | 2341/3000 [54:35<09:44,  1.13it/s, lr: 1.0e-04 loss: 3.932e-01]
latex_v1:  78%|#######8  | 2342/3000 [54:35<09:54,  1.11it/s, lr: 1.0e-04 loss: 3.932e-01]
latex_v1:  78%|#######8  | 2342/3000 [54:35<09:54,  1.11it/s, lr: 1.0e-04 loss: 3.932e-01]
latex_v1:  78%|#######8  | 2342/3000 [54:38<09:54,  1.11it/s, lr: 1.0e-04 loss: 7.005e-01]
latex_v1:  78%|#######8  | 2342/3000 [54:38<09:54,  1.11it/s, lr: 1.0e-04 loss: 7.005e-01]
latex_v1:  78%|#######8  | 2343/3000 [54:38<15:23,  1.41s/it, lr: 1.0e-04 loss: 7.005e-01]
latex_v1:  78%|#######8  | 2343/3000 [54:38<15:23,  1.41s/it, lr: 1.0e-04 loss: 7.005e-01]
latex_v1:  78%|#######8  | 2343/3000 [54:39<15:23,  1.41s/it, lr: 1.0e-04 loss: 5.457e-02]
latex_v1:  78%|#######8  | 2343/3000 [54:39<15:23,  1.41s/it, lr: 1.0e-04 loss: 5.457e-02]
latex_v1:  78%|#######8  | 2344/3000 [54:39<15:28,  1.41s/it, lr: 1.0e-04 loss: 5.457e-02]
latex_v1:  78%|#######8  | 2344/3000 [54:39<15:28,  1.41s/it, lr: 1.0e-04 loss: 5.457e-02]
latex_v1:  78%|#######8  | 2344/3000 [54:41<15:28,  1.41s/it, lr: 1.0e-04 loss: 2.279e-01]
latex_v1:  78%|#######8  | 2344/3000 [54:41<15:28,  1.41s/it, lr: 1.0e-04 loss: 2.279e-01]
latex_v1:  78%|#######8  | 2345/3000 [54:41<17:07,  1.57s/it, lr: 1.0e-04 loss: 2.279e-01]
latex_v1:  78%|#######8  | 2345/3000 [54:41<17:07,  1.57s/it, lr: 1.0e-04 loss: 2.279e-01]
latex_v1:  78%|#######8  | 2345/3000 [54:43<17:07,  1.57s/it, lr: 1.0e-04 loss: 6.538e-01]
latex_v1:  78%|#######8  | 2345/3000 [54:43<17:07,  1.57s/it, lr: 1.0e-04 loss: 6.538e-01]
latex_v1:  78%|#######8  | 2346/3000 [54:43<17:05,  1.57s/it, lr: 1.0e-04 loss: 6.538e-01]
latex_v1:  78%|#######8  | 2346/3000 [54:43<17:05,  1.57s/it, lr: 1.0e-04 loss: 6.538e-01]
latex_v1:  78%|#######8  | 2346/3000 [54:45<17:05,  1.57s/it, lr: 1.0e-04 loss: 1.840e-01]
latex_v1:  78%|#######8  | 2346/3000 [54:45<17:05,  1.57s/it, lr: 1.0e-04 loss: 1.840e-01]
latex_v1:  78%|#######8  | 2347/3000 [54:45<17:31,  1.61s/it, lr: 1.0e-04 loss: 1.840e-01]
latex_v1:  78%|#######8  | 2347/3000 [54:45<17:31,  1.61s/it, lr: 1.0e-04 loss: 1.840e-01]
latex_v1:  78%|#######8  | 2347/3000 [54:45<17:31,  1.61s/it, lr: 1.0e-04 loss: 1.202e-02]
latex_v1:  78%|#######8  | 2347/3000 [54:45<17:31,  1.61s/it, lr: 1.0e-04 loss: 1.202e-02]
latex_v1:  78%|#######8  | 2348/3000 [54:45<14:45,  1.36s/it, lr: 1.0e-04 loss: 1.202e-02]
latex_v1:  78%|#######8  | 2348/3000 [54:45<14:45,  1.36s/it, lr: 1.0e-04 loss: 1.202e-02]
latex_v1:  78%|#######8  | 2348/3000 [54:47<14:45,  1.36s/it, lr: 1.0e-04 loss: 3.981e-01]
latex_v1:  78%|#######8  | 2348/3000 [54:47<14:45,  1.36s/it, lr: 1.0e-04 loss: 3.981e-01]
latex_v1:  78%|#######8  | 2349/3000 [54:47<15:18,  1.41s/it, lr: 1.0e-04 loss: 3.981e-01]
latex_v1:  78%|#######8  | 2349/3000 [54:47<15:18,  1.41s/it, lr: 1.0e-04 loss: 3.981e-01]
latex_v1:  78%|#######8  | 2349/3000 [54:48<15:18,  1.41s/it, lr: 1.0e-04 loss: 4.895e-01]
latex_v1:  78%|#######8  | 2349/3000 [54:48<15:18,  1.41s/it, lr: 1.0e-04 loss: 4.895e-01]
latex_v1:  78%|#######8  | 2350/3000 [54:50<15:17,  1.41s/it, lr: 1.0e-04 loss: 3.339e-01]
latex_v1:  78%|#######8  | 2350/3000 [54:50<15:17,  1.41s/it, lr: 1.0e-04 loss: 3.339e-01]
latex_v1:  78%|#######8  | 2351/3000 [54:50<12:04,  1.12s/it, lr: 1.0e-04 loss: 3.339e-01]
latex_v1:  78%|#######8  | 2351/3000 [54:50<12:04,  1.12s/it, lr: 1.0e-04 loss: 3.339e-01]
latex_v1:  78%|#######8  | 2351/3000 [54:51<12:04,  1.12s/it, lr: 1.0e-04 loss: 3.829e-01]
latex_v1:  78%|#######8  | 2351/3000 [54:51<12:04,  1.12s/it, lr: 1.0e-04 loss: 3.829e-01]
latex_v1:  78%|#######8  | 2352/3000 [54:51<12:55,  1.20s/it, lr: 1.0e-04 loss: 3.829e-01]
latex_v1:  78%|#######8  | 2352/3000 [54:51<12:55,  1.20s/it, lr: 1.0e-04 loss: 3.829e-01]
latex_v1:  78%|#######8  | 2352/3000 [54:53<12:55,  1.20s/it, lr: 1.0e-04 loss: 1.597e-01]
latex_v1:  78%|#######8  | 2352/3000 [54:53<12:55,  1.20s/it, lr: 1.0e-04 loss: 1.597e-01]
latex_v1:  78%|#######8  | 2353/3000 [54:53<13:31,  1.25s/it, lr: 1.0e-04 loss: 1.597e-01]
latex_v1:  78%|#######8  | 2353/3000 [54:53<13:31,  1.25s/it, lr: 1.0e-04 loss: 1.597e-01]
latex_v1:  78%|#######8  | 2353/3000 [54:54<13:31,  1.25s/it, lr: 1.0e-04 loss: 1.347e-01]
latex_v1:  78%|#######8  | 2353/3000 [54:54<13:31,  1.25s/it, lr: 1.0e-04 loss: 1.347e-01]
latex_v1:  78%|#######8  | 2354/3000 [54:54<13:42,  1.27s/it, lr: 1.0e-04 loss: 1.347e-01]
latex_v1:  78%|#######8  | 2354/3000 [54:54<13:42,  1.27s/it, lr: 1.0e-04 loss: 1.347e-01]
latex_v1:  78%|#######8  | 2354/3000 [54:55<13:42,  1.27s/it, lr: 1.0e-04 loss: 3.124e-02]
latex_v1:  78%|#######8  | 2354/3000 [54:55<13:42,  1.27s/it, lr: 1.0e-04 loss: 3.124e-02]
latex_v1:  78%|#######8  | 2355/3000 [54:55<12:06,  1.13s/it, lr: 1.0e-04 loss: 3.124e-02]
latex_v1:  78%|#######8  | 2355/3000 [54:55<12:06,  1.13s/it, lr: 1.0e-04 loss: 3.124e-02]
latex_v1:  78%|#######8  | 2355/3000 [54:56<12:06,  1.13s/it, lr: 1.0e-04 loss: 4.182e-02]
latex_v1:  78%|#######8  | 2355/3000 [54:56<12:06,  1.13s/it, lr: 1.0e-04 loss: 4.182e-02]
latex_v1:  79%|#######8  | 2356/3000 [54:56<12:40,  1.18s/it, lr: 1.0e-04 loss: 4.182e-02]
latex_v1:  79%|#######8  | 2356/3000 [54:56<12:40,  1.18s/it, lr: 1.0e-04 loss: 4.182e-02]
latex_v1:  79%|#######8  | 2356/3000 [54:57<12:40,  1.18s/it, lr: 1.0e-04 loss: 6.196e-01]
latex_v1:  79%|#######8  | 2356/3000 [54:57<12:40,  1.18s/it, lr: 1.0e-04 loss: 6.196e-01]
latex_v1:  79%|#######8  | 2357/3000 [54:57<11:17,  1.05s/it, lr: 1.0e-04 loss: 6.196e-01]
latex_v1:  79%|#######8  | 2357/3000 [54:57<11:17,  1.05s/it, lr: 1.0e-04 loss: 6.196e-01]
latex_v1:  79%|#######8  | 2357/3000 [54:58<11:17,  1.05s/it, lr: 1.0e-04 loss: 2.505e-01]
latex_v1:  79%|#######8  | 2357/3000 [54:58<11:17,  1.05s/it, lr: 1.0e-04 loss: 2.505e-01]
latex_v1:  79%|#######8  | 2358/3000 [54:58<10:18,  1.04it/s, lr: 1.0e-04 loss: 2.505e-01]
latex_v1:  79%|#######8  | 2358/3000 [54:58<10:18,  1.04it/s, lr: 1.0e-04 loss: 2.505e-01]
latex_v1:  79%|#######8  | 2358/3000 [54:59<10:18,  1.04it/s, lr: 1.0e-04 loss: 3.848e-01]
latex_v1:  79%|#######8  | 2358/3000 [54:59<10:18,  1.04it/s, lr: 1.0e-04 loss: 3.848e-01]
latex_v1:  79%|#######8  | 2359/3000 [54:59<12:09,  1.14s/it, lr: 1.0e-04 loss: 3.848e-01]
latex_v1:  79%|#######8  | 2359/3000 [54:59<12:09,  1.14s/it, lr: 1.0e-04 loss: 3.848e-01]
latex_v1:  79%|#######8  | 2359/3000 [55:01<12:09,  1.14s/it, lr: 1.0e-04 loss: 7.271e-01]
latex_v1:  79%|#######8  | 2359/3000 [55:01<12:09,  1.14s/it, lr: 1.0e-04 loss: 7.271e-01]
latex_v1:  79%|#######8  | 2360/3000 [55:02<12:07,  1.14s/it, lr: 1.0e-04 loss: 6.216e-01]
latex_v1:  79%|#######8  | 2360/3000 [55:02<12:07,  1.14s/it, lr: 1.0e-04 loss: 6.216e-01]
latex_v1:  79%|#######8  | 2361/3000 [55:02<09:52,  1.08it/s, lr: 1.0e-04 loss: 6.216e-01]
latex_v1:  79%|#######8  | 2361/3000 [55:02<09:52,  1.08it/s, lr: 1.0e-04 loss: 6.216e-01]
latex_v1:  79%|#######8  | 2361/3000 [55:05<09:52,  1.08it/s, lr: 1.0e-04 loss: 3.878e-01]
latex_v1:  79%|#######8  | 2361/3000 [55:05<09:52,  1.08it/s, lr: 1.0e-04 loss: 3.878e-01]
latex_v1:  79%|#######8  | 2362/3000 [55:05<14:49,  1.39s/it, lr: 1.0e-04 loss: 3.878e-01]
latex_v1:  79%|#######8  | 2362/3000 [55:05<14:49,  1.39s/it, lr: 1.0e-04 loss: 3.878e-01]
latex_v1:  79%|#######8  | 2362/3000 [55:06<14:49,  1.39s/it, lr: 1.0e-04 loss: 3.112e-01]
latex_v1:  79%|#######8  | 2362/3000 [55:06<14:49,  1.39s/it, lr: 1.0e-04 loss: 3.112e-01]
latex_v1:  79%|#######8  | 2363/3000 [55:06<13:50,  1.30s/it, lr: 1.0e-04 loss: 3.112e-01]
latex_v1:  79%|#######8  | 2363/3000 [55:06<13:50,  1.30s/it, lr: 1.0e-04 loss: 3.112e-01]
latex_v1:  79%|#######8  | 2363/3000 [55:07<13:50,  1.30s/it, lr: 1.0e-04 loss: 4.046e-01]
latex_v1:  79%|#######8  | 2363/3000 [55:07<13:50,  1.30s/it, lr: 1.0e-04 loss: 4.046e-01]
latex_v1:  79%|#######8  | 2364/3000 [55:07<13:23,  1.26s/it, lr: 1.0e-04 loss: 4.046e-01]
latex_v1:  79%|#######8  | 2364/3000 [55:07<13:23,  1.26s/it, lr: 1.0e-04 loss: 4.046e-01]
latex_v1:  79%|#######8  | 2364/3000 [55:09<13:23,  1.26s/it, lr: 1.0e-04 loss: 4.332e-01]
latex_v1:  79%|#######8  | 2364/3000 [55:09<13:23,  1.26s/it, lr: 1.0e-04 loss: 4.332e-01]
latex_v1:  79%|#######8  | 2365/3000 [55:09<14:08,  1.34s/it, lr: 1.0e-04 loss: 4.332e-01]
latex_v1:  79%|#######8  | 2365/3000 [55:09<14:08,  1.34s/it, lr: 1.0e-04 loss: 4.332e-01]
latex_v1:  79%|#######8  | 2365/3000 [55:10<14:08,  1.34s/it, lr: 1.0e-04 loss: 1.443e-01]
latex_v1:  79%|#######8  | 2365/3000 [55:10<14:08,  1.34s/it, lr: 1.0e-04 loss: 1.443e-01]
latex_v1:  79%|#######8  | 2366/3000 [55:10<12:23,  1.17s/it, lr: 1.0e-04 loss: 1.443e-01]
latex_v1:  79%|#######8  | 2366/3000 [55:10<12:23,  1.17s/it, lr: 1.0e-04 loss: 1.443e-01]
latex_v1:  79%|#######8  | 2366/3000 [55:11<12:23,  1.17s/it, lr: 1.0e-04 loss: 2.661e-01]
latex_v1:  79%|#######8  | 2366/3000 [55:11<12:23,  1.17s/it, lr: 1.0e-04 loss: 2.661e-01]
latex_v1:  79%|#######8  | 2367/3000 [55:11<13:04,  1.24s/it, lr: 1.0e-04 loss: 2.661e-01]
latex_v1:  79%|#######8  | 2367/3000 [55:11<13:04,  1.24s/it, lr: 1.0e-04 loss: 2.661e-01]
latex_v1:  79%|#######8  | 2367/3000 [55:13<13:04,  1.24s/it, lr: 1.0e-04 loss: 2.276e-01]
latex_v1:  79%|#######8  | 2367/3000 [55:13<13:04,  1.24s/it, lr: 1.0e-04 loss: 2.276e-01]
latex_v1:  79%|#######8  | 2368/3000 [55:13<15:05,  1.43s/it, lr: 1.0e-04 loss: 2.276e-01]
latex_v1:  79%|#######8  | 2368/3000 [55:13<15:05,  1.43s/it, lr: 1.0e-04 loss: 2.276e-01]
latex_v1:  79%|#######8  | 2368/3000 [55:14<15:05,  1.43s/it, lr: 1.0e-04 loss: 2.983e-01]
latex_v1:  79%|#######8  | 2368/3000 [55:14<15:05,  1.43s/it, lr: 1.0e-04 loss: 2.983e-01]
latex_v1:  79%|#######8  | 2369/3000 [55:14<14:04,  1.34s/it, lr: 1.0e-04 loss: 2.983e-01]
latex_v1:  79%|#######8  | 2369/3000 [55:14<14:04,  1.34s/it, lr: 1.0e-04 loss: 2.983e-01]
latex_v1:  79%|#######8  | 2369/3000 [55:17<14:04,  1.34s/it, lr: 1.0e-04 loss: 5.316e-01]
latex_v1:  79%|#######8  | 2369/3000 [55:17<14:04,  1.34s/it, lr: 1.0e-04 loss: 5.316e-01]
latex_v1:  79%|#######9  | 2370/3000 [55:18<14:02,  1.34s/it, lr: 1.0e-04 loss: 2.841e-01]
latex_v1:  79%|#######9  | 2370/3000 [55:18<14:02,  1.34s/it, lr: 1.0e-04 loss: 2.841e-01]
latex_v1:  79%|#######9  | 2371/3000 [55:18<11:17,  1.08s/it, lr: 1.0e-04 loss: 2.841e-01]
latex_v1:  79%|#######9  | 2371/3000 [55:18<11:17,  1.08s/it, lr: 1.0e-04 loss: 2.841e-01]
latex_v1:  79%|#######9  | 2371/3000 [55:20<11:17,  1.08s/it, lr: 1.0e-04 loss: 5.330e-01]
latex_v1:  79%|#######9  | 2371/3000 [55:20<11:17,  1.08s/it, lr: 1.0e-04 loss: 5.330e-01]
latex_v1:  79%|#######9  | 2372/3000 [55:20<12:54,  1.23s/it, lr: 1.0e-04 loss: 5.330e-01]
latex_v1:  79%|#######9  | 2372/3000 [55:20<12:54,  1.23s/it, lr: 1.0e-04 loss: 5.330e-01]
latex_v1:  79%|#######9  | 2372/3000 [55:22<12:54,  1.23s/it, lr: 1.0e-04 loss: 2.753e-01]
latex_v1:  79%|#######9  | 2372/3000 [55:22<12:54,  1.23s/it, lr: 1.0e-04 loss: 2.753e-01]
latex_v1:  79%|#######9  | 2373/3000 [55:22<14:06,  1.35s/it, lr: 1.0e-04 loss: 2.753e-01]
latex_v1:  79%|#######9  | 2373/3000 [55:22<14:06,  1.35s/it, lr: 1.0e-04 loss: 2.753e-01]
latex_v1:  79%|#######9  | 2373/3000 [55:22<14:06,  1.35s/it, lr: 1.0e-04 loss: 7.586e-02]
latex_v1:  79%|#######9  | 2373/3000 [55:22<14:06,  1.35s/it, lr: 1.0e-04 loss: 7.586e-02]
latex_v1:  79%|#######9  | 2374/3000 [55:22<12:25,  1.19s/it, lr: 1.0e-04 loss: 7.586e-02]
latex_v1:  79%|#######9  | 2374/3000 [55:22<12:25,  1.19s/it, lr: 1.0e-04 loss: 7.586e-02]
latex_v1:  79%|#######9  | 2374/3000 [55:23<12:25,  1.19s/it, lr: 1.0e-04 loss: 5.625e-01]
latex_v1:  79%|#######9  | 2374/3000 [55:23<12:25,  1.19s/it, lr: 1.0e-04 loss: 5.625e-01]
latex_v1:  79%|#######9  | 2375/3000 [55:23<11:05,  1.06s/it, lr: 1.0e-04 loss: 5.625e-01]
latex_v1:  79%|#######9  | 2375/3000 [55:23<11:05,  1.06s/it, lr: 1.0e-04 loss: 5.625e-01]
latex_v1:  79%|#######9  | 2375/3000 [55:25<11:05,  1.06s/it, lr: 1.0e-04 loss: 5.844e-02]
latex_v1:  79%|#######9  | 2375/3000 [55:25<11:05,  1.06s/it, lr: 1.0e-04 loss: 5.844e-02]
latex_v1:  79%|#######9  | 2376/3000 [55:25<12:24,  1.19s/it, lr: 1.0e-04 loss: 5.844e-02]
latex_v1:  79%|#######9  | 2376/3000 [55:25<12:24,  1.19s/it, lr: 1.0e-04 loss: 5.844e-02]
latex_v1:  79%|#######9  | 2376/3000 [55:26<12:24,  1.19s/it, lr: 1.0e-04 loss: 2.663e-01]
latex_v1:  79%|#######9  | 2376/3000 [55:26<12:24,  1.19s/it, lr: 1.0e-04 loss: 2.663e-01]
latex_v1:  79%|#######9  | 2377/3000 [55:26<12:39,  1.22s/it, lr: 1.0e-04 loss: 2.663e-01]
latex_v1:  79%|#######9  | 2377/3000 [55:26<12:39,  1.22s/it, lr: 1.0e-04 loss: 2.663e-01]
latex_v1:  79%|#######9  | 2377/3000 [55:27<12:39,  1.22s/it, lr: 1.0e-04 loss: 4.205e-01]
latex_v1:  79%|#######9  | 2377/3000 [55:27<12:39,  1.22s/it, lr: 1.0e-04 loss: 4.205e-01]
latex_v1:  79%|#######9  | 2378/3000 [55:27<11:08,  1.07s/it, lr: 1.0e-04 loss: 4.205e-01]
latex_v1:  79%|#######9  | 2378/3000 [55:27<11:08,  1.07s/it, lr: 1.0e-04 loss: 4.205e-01]
latex_v1:  79%|#######9  | 2378/3000 [55:27<11:08,  1.07s/it, lr: 1.0e-04 loss: 7.339e-01]
latex_v1:  79%|#######9  | 2378/3000 [55:27<11:08,  1.07s/it, lr: 1.0e-04 loss: 7.339e-01]
latex_v1:  79%|#######9  | 2379/3000 [55:27<10:07,  1.02it/s, lr: 1.0e-04 loss: 7.339e-01]
latex_v1:  79%|#######9  | 2379/3000 [55:27<10:07,  1.02it/s, lr: 1.0e-04 loss: 7.339e-01]
latex_v1:  79%|#######9  | 2379/3000 [55:28<10:07,  1.02it/s, lr: 1.0e-04 loss: 6.473e-01]
latex_v1:  79%|#######9  | 2379/3000 [55:28<10:07,  1.02it/s, lr: 1.0e-04 loss: 6.473e-01]
latex_v1:  79%|#######9  | 2380/3000 [55:30<10:06,  1.02it/s, lr: 1.0e-04 loss: 1.931e-01]
latex_v1:  79%|#######9  | 2380/3000 [55:30<10:06,  1.02it/s, lr: 1.0e-04 loss: 1.931e-01]
latex_v1:  79%|#######9  | 2381/3000 [55:30<08:38,  1.19it/s, lr: 1.0e-04 loss: 1.931e-01]
latex_v1:  79%|#######9  | 2381/3000 [55:30<08:38,  1.19it/s, lr: 1.0e-04 loss: 1.931e-01]
latex_v1:  79%|#######9  | 2381/3000 [55:32<08:38,  1.19it/s, lr: 1.0e-04 loss: 6.484e-02]
latex_v1:  79%|#######9  | 2381/3000 [55:32<08:38,  1.19it/s, lr: 1.0e-04 loss: 6.484e-02]
latex_v1:  79%|#######9  | 2382/3000 [55:32<13:17,  1.29s/it, lr: 1.0e-04 loss: 6.484e-02]
latex_v1:  79%|#######9  | 2382/3000 [55:32<13:17,  1.29s/it, lr: 1.0e-04 loss: 6.484e-02]
latex_v1:  79%|#######9  | 2382/3000 [55:33<13:17,  1.29s/it, lr: 1.0e-04 loss: 2.465e-01]
latex_v1:  79%|#######9  | 2382/3000 [55:33<13:17,  1.29s/it, lr: 1.0e-04 loss: 2.465e-01]
latex_v1:  79%|#######9  | 2383/3000 [55:33<11:46,  1.14s/it, lr: 1.0e-04 loss: 2.465e-01]
latex_v1:  79%|#######9  | 2383/3000 [55:33<11:46,  1.14s/it, lr: 1.0e-04 loss: 2.465e-01]
latex_v1:  79%|#######9  | 2383/3000 [55:36<11:46,  1.14s/it, lr: 1.0e-04 loss: 3.080e-01]
latex_v1:  79%|#######9  | 2383/3000 [55:36<11:46,  1.14s/it, lr: 1.0e-04 loss: 3.080e-01]
latex_v1:  79%|#######9  | 2384/3000 [55:36<15:49,  1.54s/it, lr: 1.0e-04 loss: 3.080e-01]
latex_v1:  79%|#######9  | 2384/3000 [55:36<15:49,  1.54s/it, lr: 1.0e-04 loss: 3.080e-01]
latex_v1:  79%|#######9  | 2384/3000 [55:37<15:49,  1.54s/it, lr: 1.0e-04 loss: 1.207e-01]
latex_v1:  79%|#######9  | 2384/3000 [55:37<15:49,  1.54s/it, lr: 1.0e-04 loss: 1.207e-01]
latex_v1:  80%|#######9  | 2385/3000 [55:37<15:30,  1.51s/it, lr: 1.0e-04 loss: 1.207e-01]
latex_v1:  80%|#######9  | 2385/3000 [55:37<15:30,  1.51s/it, lr: 1.0e-04 loss: 1.207e-01]
latex_v1:  80%|#######9  | 2385/3000 [55:39<15:30,  1.51s/it, lr: 1.0e-04 loss: 3.661e-01]
latex_v1:  80%|#######9  | 2385/3000 [55:39<15:30,  1.51s/it, lr: 1.0e-04 loss: 3.661e-01]
latex_v1:  80%|#######9  | 2386/3000 [55:39<16:29,  1.61s/it, lr: 1.0e-04 loss: 3.661e-01]
latex_v1:  80%|#######9  | 2386/3000 [55:39<16:29,  1.61s/it, lr: 1.0e-04 loss: 3.661e-01]
latex_v1:  80%|#######9  | 2386/3000 [55:40<16:29,  1.61s/it, lr: 1.0e-04 loss: 5.645e-01]
latex_v1:  80%|#######9  | 2386/3000 [55:40<16:29,  1.61s/it, lr: 1.0e-04 loss: 5.645e-01]
latex_v1:  80%|#######9  | 2387/3000 [55:40<15:35,  1.53s/it, lr: 1.0e-04 loss: 5.645e-01]
latex_v1:  80%|#######9  | 2387/3000 [55:40<15:35,  1.53s/it, lr: 1.0e-04 loss: 5.645e-01]
latex_v1:  80%|#######9  | 2387/3000 [55:41<15:35,  1.53s/it, lr: 1.0e-04 loss: 4.198e-01]
latex_v1:  80%|#######9  | 2387/3000 [55:41<15:35,  1.53s/it, lr: 1.0e-04 loss: 4.198e-01]
latex_v1:  80%|#######9  | 2388/3000 [55:41<14:00,  1.37s/it, lr: 1.0e-04 loss: 4.198e-01]
latex_v1:  80%|#######9  | 2388/3000 [55:41<14:00,  1.37s/it, lr: 1.0e-04 loss: 4.198e-01]
latex_v1:  80%|#######9  | 2388/3000 [55:42<14:00,  1.37s/it, lr: 1.0e-04 loss: 2.975e-01]
latex_v1:  80%|#######9  | 2388/3000 [55:42<14:00,  1.37s/it, lr: 1.0e-04 loss: 2.975e-01]
latex_v1:  80%|#######9  | 2389/3000 [55:42<12:44,  1.25s/it, lr: 1.0e-04 loss: 2.975e-01]
latex_v1:  80%|#######9  | 2389/3000 [55:42<12:44,  1.25s/it, lr: 1.0e-04 loss: 2.975e-01]
latex_v1:  80%|#######9  | 2389/3000 [55:43<12:44,  1.25s/it, lr: 1.0e-04 loss: 5.147e-01]
latex_v1:  80%|#######9  | 2389/3000 [55:43<12:44,  1.25s/it, lr: 1.0e-04 loss: 5.147e-01]
latex_v1:  80%|#######9  | 2390/3000 [55:45<12:43,  1.25s/it, lr: 1.0e-04 loss: 2.836e-01]
latex_v1:  80%|#######9  | 2390/3000 [55:45<12:43,  1.25s/it, lr: 1.0e-04 loss: 2.836e-01]
latex_v1:  80%|#######9  | 2391/3000 [55:45<11:12,  1.10s/it, lr: 1.0e-04 loss: 2.836e-01]
latex_v1:  80%|#######9  | 2391/3000 [55:45<11:12,  1.10s/it, lr: 1.0e-04 loss: 2.836e-01]
latex_v1:  80%|#######9  | 2391/3000 [55:46<11:12,  1.10s/it, lr: 1.0e-04 loss: 6.155e-01]
latex_v1:  80%|#######9  | 2391/3000 [55:46<11:12,  1.10s/it, lr: 1.0e-04 loss: 6.155e-01]
latex_v1:  80%|#######9  | 2392/3000 [55:46<11:20,  1.12s/it, lr: 1.0e-04 loss: 6.155e-01]
latex_v1:  80%|#######9  | 2392/3000 [55:46<11:20,  1.12s/it, lr: 1.0e-04 loss: 6.155e-01]
latex_v1:  80%|#######9  | 2392/3000 [55:47<11:20,  1.12s/it, lr: 1.0e-04 loss: 3.942e-01]
latex_v1:  80%|#######9  | 2392/3000 [55:47<11:20,  1.12s/it, lr: 1.0e-04 loss: 3.942e-01]
latex_v1:  80%|#######9  | 2393/3000 [55:47<10:21,  1.02s/it, lr: 1.0e-04 loss: 3.942e-01]
latex_v1:  80%|#######9  | 2393/3000 [55:47<10:21,  1.02s/it, lr: 1.0e-04 loss: 3.942e-01]
latex_v1:  80%|#######9  | 2393/3000 [55:48<10:21,  1.02s/it, lr: 1.0e-04 loss: 4.129e-02]
latex_v1:  80%|#######9  | 2393/3000 [55:48<10:21,  1.02s/it, lr: 1.0e-04 loss: 4.129e-02]
latex_v1:  80%|#######9  | 2394/3000 [55:48<09:35,  1.05it/s, lr: 1.0e-04 loss: 4.129e-02]
latex_v1:  80%|#######9  | 2394/3000 [55:48<09:35,  1.05it/s, lr: 1.0e-04 loss: 4.129e-02]
latex_v1:  80%|#######9  | 2394/3000 [55:49<09:35,  1.05it/s, lr: 1.0e-04 loss: 1.877e-01]
latex_v1:  80%|#######9  | 2394/3000 [55:49<09:35,  1.05it/s, lr: 1.0e-04 loss: 1.877e-01]
latex_v1:  80%|#######9  | 2395/3000 [55:49<10:58,  1.09s/it, lr: 1.0e-04 loss: 1.877e-01]
latex_v1:  80%|#######9  | 2395/3000 [55:49<10:58,  1.09s/it, lr: 1.0e-04 loss: 1.877e-01]
latex_v1:  80%|#######9  | 2395/3000 [55:50<10:58,  1.09s/it, lr: 1.0e-04 loss: 1.511e-01]
latex_v1:  80%|#######9  | 2395/3000 [55:50<10:58,  1.09s/it, lr: 1.0e-04 loss: 1.511e-01]
latex_v1:  80%|#######9  | 2396/3000 [55:50<09:55,  1.01it/s, lr: 1.0e-04 loss: 1.511e-01]
latex_v1:  80%|#######9  | 2396/3000 [55:50<09:55,  1.01it/s, lr: 1.0e-04 loss: 1.511e-01]
latex_v1:  80%|#######9  | 2396/3000 [55:52<09:55,  1.01it/s, lr: 1.0e-04 loss: 5.484e-01]
latex_v1:  80%|#######9  | 2396/3000 [55:52<09:55,  1.01it/s, lr: 1.0e-04 loss: 5.484e-01]
latex_v1:  80%|#######9  | 2397/3000 [55:52<11:31,  1.15s/it, lr: 1.0e-04 loss: 5.484e-01]
latex_v1:  80%|#######9  | 2397/3000 [55:52<11:31,  1.15s/it, lr: 1.0e-04 loss: 5.484e-01]
latex_v1:  80%|#######9  | 2397/3000 [55:52<11:31,  1.15s/it, lr: 1.0e-04 loss: 5.346e-01]
latex_v1:  80%|#######9  | 2397/3000 [55:52<11:31,  1.15s/it, lr: 1.0e-04 loss: 5.346e-01]
latex_v1:  80%|#######9  | 2398/3000 [55:52<10:19,  1.03s/it, lr: 1.0e-04 loss: 5.346e-01]
latex_v1:  80%|#######9  | 2398/3000 [55:52<10:19,  1.03s/it, lr: 1.0e-04 loss: 5.346e-01]
latex_v1:  80%|#######9  | 2398/3000 [55:54<10:19,  1.03s/it, lr: 1.0e-04 loss: 3.867e-02]
latex_v1:  80%|#######9  | 2398/3000 [55:54<10:19,  1.03s/it, lr: 1.0e-04 loss: 3.867e-02]
latex_v1:  80%|#######9  | 2399/3000 [55:54<11:47,  1.18s/it, lr: 1.0e-04 loss: 3.867e-02]
latex_v1:  80%|#######9  | 2399/3000 [55:54<11:47,  1.18s/it, lr: 1.0e-04 loss: 3.867e-02]
latex_v1:  80%|#######9  | 2399/3000 [55:55<11:47,  1.18s/it, lr: 1.0e-04 loss: 2.112e-01]
latex_v1:  80%|#######9  | 2399/3000 [55:55<11:47,  1.18s/it, lr: 1.0e-04 loss: 2.112e-01]Unloading assistant lora



Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]


Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.44s/it]
Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.44s/it]


Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.43s/it]
Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.43s/it]


Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.41s/it]
Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.41s/it]


Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.40s/it]
Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.40s/it]


Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.45s/it]
Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.45s/it]


Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.46s/it]
Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.46s/it]


Generating Images: 100%|##########| 7/7 [00:17<00:00,  2.47s/it]
Generating Images: 100%|##########| 7/7 [00:17<00:00,  2.47s/it]


                                                                
                                                                Loading assistant lora

latex_v1:  80%|########  | 2400/3000 [55:56<11:46,  1.18s/it, lr: 1.0e-04 loss: 2.274e-01]
latex_v1:  80%|########  | 2400/3000 [55:56<11:46,  1.18s/it, lr: 1.0e-04 loss: 2.274e-01]
latex_v1:  80%|########  | 2401/3000 [55:56<08:06,  1.23it/s, lr: 1.0e-04 loss: 2.274e-01]
latex_v1:  80%|########  | 2401/3000 [55:56<08:06,  1.23it/s, lr: 1.0e-04 loss: 2.274e-01]
latex_v1:  80%|########  | 2401/3000 [55:58<08:06,  1.23it/s, lr: 1.0e-04 loss: 2.721e-01]
latex_v1:  80%|########  | 2401/3000 [55:58<08:06,  1.23it/s, lr: 1.0e-04 loss: 2.721e-01]
latex_v1:  80%|########  | 2402/3000 [55:58<10:41,  1.07s/it, lr: 1.0e-04 loss: 2.721e-01]
latex_v1:  80%|########  | 2402/3000 [55:58<10:41,  1.07s/it, lr: 1.0e-04 loss: 2.721e-01]
latex_v1:  80%|########  | 2402/3000 [56:01<10:41,  1.07s/it, lr: 1.0e-04 loss: 1.721e-01]
latex_v1:  80%|########  | 2402/3000 [56:01<10:41,  1.07s/it, lr: 1.0e-04 loss: 1.721e-01]
latex_v1:  80%|########  | 2403/3000 [56:01<15:17,  1.54s/it, lr: 1.0e-04 loss: 1.721e-01]
latex_v1:  80%|########  | 2403/3000 [56:01<15:17,  1.54s/it, lr: 1.0e-04 loss: 1.721e-01]
latex_v1:  80%|########  | 2403/3000 [56:02<15:17,  1.54s/it, lr: 1.0e-04 loss: 2.879e-02]
latex_v1:  80%|########  | 2403/3000 [56:02<15:17,  1.54s/it, lr: 1.0e-04 loss: 2.879e-02]
latex_v1:  80%|########  | 2404/3000 [56:02<14:19,  1.44s/it, lr: 1.0e-04 loss: 2.879e-02]
latex_v1:  80%|########  | 2404/3000 [56:02<14:19,  1.44s/it, lr: 1.0e-04 loss: 2.879e-02]
latex_v1:  80%|########  | 2404/3000 [56:04<14:19,  1.44s/it, lr: 1.0e-04 loss: 5.597e-01]
latex_v1:  80%|########  | 2404/3000 [56:04<14:19,  1.44s/it, lr: 1.0e-04 loss: 5.597e-01]
latex_v1:  80%|########  | 2405/3000 [56:04<14:51,  1.50s/it, lr: 1.0e-04 loss: 5.597e-01]
latex_v1:  80%|########  | 2405/3000 [56:04<14:51,  1.50s/it, lr: 1.0e-04 loss: 5.597e-01]
latex_v1:  80%|########  | 2405/3000 [56:04<14:51,  1.50s/it, lr: 1.0e-04 loss: 1.119e-01]
latex_v1:  80%|########  | 2405/3000 [56:04<14:51,  1.50s/it, lr: 1.0e-04 loss: 1.119e-01]
latex_v1:  80%|########  | 2406/3000 [56:04<12:44,  1.29s/it, lr: 1.0e-04 loss: 1.119e-01]
latex_v1:  80%|########  | 2406/3000 [56:04<12:44,  1.29s/it, lr: 1.0e-04 loss: 1.119e-01]
latex_v1:  80%|########  | 2406/3000 [56:05<12:44,  1.29s/it, lr: 1.0e-04 loss: 5.254e-01]
latex_v1:  80%|########  | 2406/3000 [56:05<12:44,  1.29s/it, lr: 1.0e-04 loss: 5.254e-01]
latex_v1:  80%|########  | 2407/3000 [56:05<11:11,  1.13s/it, lr: 1.0e-04 loss: 5.254e-01]
latex_v1:  80%|########  | 2407/3000 [56:05<11:11,  1.13s/it, lr: 1.0e-04 loss: 5.254e-01]
latex_v1:  80%|########  | 2407/3000 [56:07<11:11,  1.13s/it, lr: 1.0e-04 loss: 3.764e-01]
latex_v1:  80%|########  | 2407/3000 [56:07<11:11,  1.13s/it, lr: 1.0e-04 loss: 3.764e-01]
latex_v1:  80%|########  | 2408/3000 [56:07<13:18,  1.35s/it, lr: 1.0e-04 loss: 3.764e-01]
latex_v1:  80%|########  | 2408/3000 [56:07<13:18,  1.35s/it, lr: 1.0e-04 loss: 3.764e-01]
latex_v1:  80%|########  | 2408/3000 [56:08<13:18,  1.35s/it, lr: 1.0e-04 loss: 7.569e-01]
latex_v1:  80%|########  | 2408/3000 [56:08<13:18,  1.35s/it, lr: 1.0e-04 loss: 7.569e-01]
latex_v1:  80%|########  | 2409/3000 [56:08<11:37,  1.18s/it, lr: 1.0e-04 loss: 7.569e-01]
latex_v1:  80%|########  | 2409/3000 [56:08<11:37,  1.18s/it, lr: 1.0e-04 loss: 7.569e-01]
latex_v1:  80%|########  | 2409/3000 [56:08<11:37,  1.18s/it, lr: 1.0e-04 loss: 2.129e-01]
latex_v1:  80%|########  | 2409/3000 [56:08<11:37,  1.18s/it, lr: 1.0e-04 loss: 2.129e-01]
latex_v1:  80%|########  | 2410/3000 [56:11<11:35,  1.18s/it, lr: 1.0e-04 loss: 1.500e-01]
latex_v1:  80%|########  | 2410/3000 [56:11<11:35,  1.18s/it, lr: 1.0e-04 loss: 1.500e-01]
latex_v1:  80%|########  | 2411/3000 [56:11<12:45,  1.30s/it, lr: 1.0e-04 loss: 1.500e-01]
latex_v1:  80%|########  | 2411/3000 [56:11<12:45,  1.30s/it, lr: 1.0e-04 loss: 1.500e-01]
latex_v1:  80%|########  | 2411/3000 [56:14<12:45,  1.30s/it, lr: 1.0e-04 loss: 2.995e-01]
latex_v1:  80%|########  | 2411/3000 [56:14<12:45,  1.30s/it, lr: 1.0e-04 loss: 2.995e-01]
latex_v1:  80%|########  | 2412/3000 [56:14<16:24,  1.67s/it, lr: 1.0e-04 loss: 2.995e-01]
latex_v1:  80%|########  | 2412/3000 [56:14<16:24,  1.67s/it, lr: 1.0e-04 loss: 2.995e-01]
latex_v1:  80%|########  | 2412/3000 [56:15<16:24,  1.67s/it, lr: 1.0e-04 loss: 4.315e-01]
latex_v1:  80%|########  | 2412/3000 [56:15<16:24,  1.67s/it, lr: 1.0e-04 loss: 4.315e-01]
latex_v1:  80%|########  | 2413/3000 [56:15<14:36,  1.49s/it, lr: 1.0e-04 loss: 4.315e-01]
latex_v1:  80%|########  | 2413/3000 [56:15<14:36,  1.49s/it, lr: 1.0e-04 loss: 4.315e-01]
latex_v1:  80%|########  | 2413/3000 [56:18<14:36,  1.49s/it, lr: 1.0e-04 loss: 3.127e-02]
latex_v1:  80%|########  | 2413/3000 [56:18<14:36,  1.49s/it, lr: 1.0e-04 loss: 3.127e-02]
latex_v1:  80%|########  | 2414/3000 [56:18<18:12,  1.86s/it, lr: 1.0e-04 loss: 3.127e-02]
latex_v1:  80%|########  | 2414/3000 [56:18<18:12,  1.86s/it, lr: 1.0e-04 loss: 3.127e-02]
latex_v1:  80%|########  | 2414/3000 [56:19<18:12,  1.86s/it, lr: 1.0e-04 loss: 5.537e-01]
latex_v1:  80%|########  | 2414/3000 [56:19<18:12,  1.86s/it, lr: 1.0e-04 loss: 5.537e-01]
latex_v1:  80%|########  | 2415/3000 [56:19<15:09,  1.55s/it, lr: 1.0e-04 loss: 5.537e-01]
latex_v1:  80%|########  | 2415/3000 [56:19<15:09,  1.55s/it, lr: 1.0e-04 loss: 5.537e-01]
latex_v1:  80%|########  | 2415/3000 [56:20<15:09,  1.55s/it, lr: 1.0e-04 loss: 5.396e-01]
latex_v1:  80%|########  | 2415/3000 [56:20<15:09,  1.55s/it, lr: 1.0e-04 loss: 5.396e-01]
latex_v1:  81%|########  | 2416/3000 [56:20<12:55,  1.33s/it, lr: 1.0e-04 loss: 5.396e-01]
latex_v1:  81%|########  | 2416/3000 [56:20<12:55,  1.33s/it, lr: 1.0e-04 loss: 5.396e-01]
latex_v1:  81%|########  | 2416/3000 [56:20<12:55,  1.33s/it, lr: 1.0e-04 loss: 9.119e-02]
latex_v1:  81%|########  | 2416/3000 [56:20<12:55,  1.33s/it, lr: 1.0e-04 loss: 9.119e-02]
latex_v1:  81%|########  | 2417/3000 [56:20<11:14,  1.16s/it, lr: 1.0e-04 loss: 9.119e-02]
latex_v1:  81%|########  | 2417/3000 [56:20<11:14,  1.16s/it, lr: 1.0e-04 loss: 9.119e-02]
latex_v1:  81%|########  | 2417/3000 [56:22<11:14,  1.16s/it, lr: 1.0e-04 loss: 6.429e-01]
latex_v1:  81%|########  | 2417/3000 [56:22<11:14,  1.16s/it, lr: 1.0e-04 loss: 6.429e-01]
latex_v1:  81%|########  | 2418/3000 [56:22<10:18,  1.06s/it, lr: 1.0e-04 loss: 6.429e-01]
latex_v1:  81%|########  | 2418/3000 [56:22<10:18,  1.06s/it, lr: 1.0e-04 loss: 6.429e-01]
latex_v1:  81%|########  | 2418/3000 [56:23<10:18,  1.06s/it, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  81%|########  | 2418/3000 [56:23<10:18,  1.06s/it, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  81%|########  | 2419/3000 [56:23<10:37,  1.10s/it, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  81%|########  | 2419/3000 [56:23<10:37,  1.10s/it, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  81%|########  | 2419/3000 [56:23<10:37,  1.10s/it, lr: 1.0e-04 loss: 3.928e-02]
latex_v1:  81%|########  | 2419/3000 [56:23<10:37,  1.10s/it, lr: 1.0e-04 loss: 3.928e-02]
latex_v1:  81%|########  | 2420/3000 [56:25<10:36,  1.10s/it, lr: 1.0e-04 loss: 3.140e-01]
latex_v1:  81%|########  | 2420/3000 [56:25<10:36,  1.10s/it, lr: 1.0e-04 loss: 3.140e-01]
latex_v1:  81%|########  | 2421/3000 [56:25<08:39,  1.12it/s, lr: 1.0e-04 loss: 3.140e-01]
latex_v1:  81%|########  | 2421/3000 [56:25<08:39,  1.12it/s, lr: 1.0e-04 loss: 3.140e-01]
latex_v1:  81%|########  | 2421/3000 [56:26<08:39,  1.12it/s, lr: 1.0e-04 loss: 2.027e-01]
latex_v1:  81%|########  | 2421/3000 [56:26<08:39,  1.12it/s, lr: 1.0e-04 loss: 2.027e-01]
latex_v1:  81%|########  | 2422/3000 [56:26<10:07,  1.05s/it, lr: 1.0e-04 loss: 2.027e-01]
latex_v1:  81%|########  | 2422/3000 [56:26<10:07,  1.05s/it, lr: 1.0e-04 loss: 2.027e-01]
latex_v1:  81%|########  | 2422/3000 [56:28<10:07,  1.05s/it, lr: 1.0e-04 loss: 8.279e-02]
latex_v1:  81%|########  | 2422/3000 [56:28<10:07,  1.05s/it, lr: 1.0e-04 loss: 8.279e-02]
latex_v1:  81%|########  | 2423/3000 [56:28<11:18,  1.18s/it, lr: 1.0e-04 loss: 8.279e-02]
latex_v1:  81%|########  | 2423/3000 [56:28<11:18,  1.18s/it, lr: 1.0e-04 loss: 8.279e-02]
latex_v1:  81%|########  | 2423/3000 [56:29<11:18,  1.18s/it, lr: 1.0e-04 loss: 5.206e-01]
latex_v1:  81%|########  | 2423/3000 [56:29<11:18,  1.18s/it, lr: 1.0e-04 loss: 5.206e-01]
latex_v1:  81%|########  | 2424/3000 [56:29<11:47,  1.23s/it, lr: 1.0e-04 loss: 5.206e-01]
latex_v1:  81%|########  | 2424/3000 [56:29<11:47,  1.23s/it, lr: 1.0e-04 loss: 5.206e-01]
latex_v1:  81%|########  | 2424/3000 [56:31<11:47,  1.23s/it, lr: 1.0e-04 loss: 1.986e-01]
latex_v1:  81%|########  | 2424/3000 [56:31<11:47,  1.23s/it, lr: 1.0e-04 loss: 1.986e-01]
latex_v1:  81%|########  | 2425/3000 [56:31<12:35,  1.31s/it, lr: 1.0e-04 loss: 1.986e-01]
latex_v1:  81%|########  | 2425/3000 [56:31<12:35,  1.31s/it, lr: 1.0e-04 loss: 1.986e-01]
latex_v1:  81%|########  | 2425/3000 [56:32<12:35,  1.31s/it, lr: 1.0e-04 loss: 3.266e-01]
latex_v1:  81%|########  | 2425/3000 [56:32<12:35,  1.31s/it, lr: 1.0e-04 loss: 3.266e-01]
latex_v1:  81%|########  | 2426/3000 [56:32<12:55,  1.35s/it, lr: 1.0e-04 loss: 3.266e-01]
latex_v1:  81%|########  | 2426/3000 [56:32<12:55,  1.35s/it, lr: 1.0e-04 loss: 3.266e-01]
latex_v1:  81%|########  | 2426/3000 [56:34<12:55,  1.35s/it, lr: 1.0e-04 loss: 5.427e-01]
latex_v1:  81%|########  | 2426/3000 [56:34<12:55,  1.35s/it, lr: 1.0e-04 loss: 5.427e-01]
latex_v1:  81%|########  | 2427/3000 [56:34<13:25,  1.41s/it, lr: 1.0e-04 loss: 5.427e-01]
latex_v1:  81%|########  | 2427/3000 [56:34<13:25,  1.41s/it, lr: 1.0e-04 loss: 5.427e-01]
latex_v1:  81%|########  | 2427/3000 [56:37<13:25,  1.41s/it, lr: 1.0e-04 loss: 2.144e-01]
latex_v1:  81%|########  | 2427/3000 [56:37<13:25,  1.41s/it, lr: 1.0e-04 loss: 2.144e-01]
latex_v1:  81%|########  | 2428/3000 [56:37<17:58,  1.89s/it, lr: 1.0e-04 loss: 2.144e-01]
latex_v1:  81%|########  | 2428/3000 [56:37<17:58,  1.89s/it, lr: 1.0e-04 loss: 2.144e-01]
latex_v1:  81%|########  | 2428/3000 [56:38<17:58,  1.89s/it, lr: 1.0e-04 loss: 3.684e-01]
latex_v1:  81%|########  | 2428/3000 [56:38<17:58,  1.89s/it, lr: 1.0e-04 loss: 3.684e-01]
latex_v1:  81%|########  | 2429/3000 [56:38<16:43,  1.76s/it, lr: 1.0e-04 loss: 3.684e-01]
latex_v1:  81%|########  | 2429/3000 [56:38<16:43,  1.76s/it, lr: 1.0e-04 loss: 3.684e-01]
latex_v1:  81%|########  | 2429/3000 [56:39<16:43,  1.76s/it, lr: 1.0e-04 loss: 4.030e-01]
latex_v1:  81%|########  | 2429/3000 [56:39<16:43,  1.76s/it, lr: 1.0e-04 loss: 4.030e-01]
latex_v1:  81%|########1 | 2430/3000 [56:40<16:41,  1.76s/it, lr: 1.0e-04 loss: 7.317e-01]
latex_v1:  81%|########1 | 2430/3000 [56:40<16:41,  1.76s/it, lr: 1.0e-04 loss: 7.317e-01]
latex_v1:  81%|########1 | 2431/3000 [56:40<10:40,  1.12s/it, lr: 1.0e-04 loss: 7.317e-01]
latex_v1:  81%|########1 | 2431/3000 [56:40<10:40,  1.12s/it, lr: 1.0e-04 loss: 7.317e-01]
latex_v1:  81%|########1 | 2431/3000 [56:42<10:40,  1.12s/it, lr: 1.0e-04 loss: 4.703e-01]
latex_v1:  81%|########1 | 2431/3000 [56:42<10:40,  1.12s/it, lr: 1.0e-04 loss: 4.703e-01]
latex_v1:  81%|########1 | 2432/3000 [56:42<12:26,  1.31s/it, lr: 1.0e-04 loss: 4.703e-01]
latex_v1:  81%|########1 | 2432/3000 [56:42<12:26,  1.31s/it, lr: 1.0e-04 loss: 4.703e-01]
latex_v1:  81%|########1 | 2432/3000 [56:43<12:26,  1.31s/it, lr: 1.0e-04 loss: 5.169e-01]
latex_v1:  81%|########1 | 2432/3000 [56:43<12:26,  1.31s/it, lr: 1.0e-04 loss: 5.169e-01]
latex_v1:  81%|########1 | 2433/3000 [56:43<11:00,  1.16s/it, lr: 1.0e-04 loss: 5.169e-01]
latex_v1:  81%|########1 | 2433/3000 [56:43<11:00,  1.16s/it, lr: 1.0e-04 loss: 5.169e-01]
latex_v1:  81%|########1 | 2433/3000 [56:43<11:00,  1.16s/it, lr: 1.0e-04 loss: 1.900e-01]
latex_v1:  81%|########1 | 2433/3000 [56:43<11:00,  1.16s/it, lr: 1.0e-04 loss: 1.900e-01]
latex_v1:  81%|########1 | 2434/3000 [56:43<09:58,  1.06s/it, lr: 1.0e-04 loss: 1.900e-01]
latex_v1:  81%|########1 | 2434/3000 [56:43<09:58,  1.06s/it, lr: 1.0e-04 loss: 1.900e-01]
latex_v1:  81%|########1 | 2434/3000 [56:45<09:58,  1.06s/it, lr: 1.0e-04 loss: 8.621e-01]
latex_v1:  81%|########1 | 2434/3000 [56:45<09:58,  1.06s/it, lr: 1.0e-04 loss: 8.621e-01]
latex_v1:  81%|########1 | 2435/3000 [56:45<10:17,  1.09s/it, lr: 1.0e-04 loss: 8.621e-01]
latex_v1:  81%|########1 | 2435/3000 [56:45<10:17,  1.09s/it, lr: 1.0e-04 loss: 8.621e-01]
latex_v1:  81%|########1 | 2435/3000 [56:46<10:17,  1.09s/it, lr: 1.0e-04 loss: 6.676e-01]
latex_v1:  81%|########1 | 2435/3000 [56:46<10:17,  1.09s/it, lr: 1.0e-04 loss: 6.676e-01]
latex_v1:  81%|########1 | 2436/3000 [56:46<09:53,  1.05s/it, lr: 1.0e-04 loss: 6.676e-01]
latex_v1:  81%|########1 | 2436/3000 [56:46<09:53,  1.05s/it, lr: 1.0e-04 loss: 6.676e-01]
latex_v1:  81%|########1 | 2436/3000 [56:47<09:53,  1.05s/it, lr: 1.0e-04 loss: 3.126e-01]
latex_v1:  81%|########1 | 2436/3000 [56:47<09:53,  1.05s/it, lr: 1.0e-04 loss: 3.126e-01]
latex_v1:  81%|########1 | 2437/3000 [56:47<10:49,  1.15s/it, lr: 1.0e-04 loss: 3.126e-01]
latex_v1:  81%|########1 | 2437/3000 [56:47<10:49,  1.15s/it, lr: 1.0e-04 loss: 3.126e-01]
latex_v1:  81%|########1 | 2437/3000 [56:48<10:49,  1.15s/it, lr: 1.0e-04 loss: 2.657e-01]
latex_v1:  81%|########1 | 2437/3000 [56:48<10:49,  1.15s/it, lr: 1.0e-04 loss: 2.657e-01]
latex_v1:  81%|########1 | 2438/3000 [56:48<10:53,  1.16s/it, lr: 1.0e-04 loss: 2.657e-01]
latex_v1:  81%|########1 | 2438/3000 [56:48<10:53,  1.16s/it, lr: 1.0e-04 loss: 2.657e-01]
latex_v1:  81%|########1 | 2438/3000 [56:49<10:53,  1.16s/it, lr: 1.0e-04 loss: 5.516e-01]
latex_v1:  81%|########1 | 2438/3000 [56:49<10:53,  1.16s/it, lr: 1.0e-04 loss: 5.516e-01]
latex_v1:  81%|########1 | 2439/3000 [56:49<10:37,  1.14s/it, lr: 1.0e-04 loss: 5.516e-01]
latex_v1:  81%|########1 | 2439/3000 [56:49<10:37,  1.14s/it, lr: 1.0e-04 loss: 5.516e-01]
latex_v1:  81%|########1 | 2439/3000 [56:50<10:37,  1.14s/it, lr: 1.0e-04 loss: 6.314e-01]
latex_v1:  81%|########1 | 2439/3000 [56:50<10:37,  1.14s/it, lr: 1.0e-04 loss: 6.314e-01]
latex_v1:  81%|########1 | 2440/3000 [56:51<10:36,  1.14s/it, lr: 1.0e-04 loss: 5.825e-01]
latex_v1:  81%|########1 | 2440/3000 [56:51<10:36,  1.14s/it, lr: 1.0e-04 loss: 5.825e-01]
latex_v1:  81%|########1 | 2441/3000 [56:51<08:52,  1.05it/s, lr: 1.0e-04 loss: 5.825e-01]
latex_v1:  81%|########1 | 2441/3000 [56:51<08:52,  1.05it/s, lr: 1.0e-04 loss: 5.825e-01]
latex_v1:  81%|########1 | 2441/3000 [56:52<08:52,  1.05it/s, lr: 1.0e-04 loss: 1.226e-01]
latex_v1:  81%|########1 | 2441/3000 [56:52<08:52,  1.05it/s, lr: 1.0e-04 loss: 1.226e-01]
latex_v1:  81%|########1 | 2442/3000 [56:52<08:54,  1.04it/s, lr: 1.0e-04 loss: 1.226e-01]
latex_v1:  81%|########1 | 2442/3000 [56:52<08:54,  1.04it/s, lr: 1.0e-04 loss: 1.226e-01]
latex_v1:  81%|########1 | 2442/3000 [56:55<08:54,  1.04it/s, lr: 1.0e-04 loss: 1.801e-01]
latex_v1:  81%|########1 | 2442/3000 [56:55<08:54,  1.04it/s, lr: 1.0e-04 loss: 1.801e-01]
latex_v1:  81%|########1 | 2443/3000 [56:55<13:36,  1.47s/it, lr: 1.0e-04 loss: 1.801e-01]
latex_v1:  81%|########1 | 2443/3000 [56:55<13:36,  1.47s/it, lr: 1.0e-04 loss: 1.801e-01]
latex_v1:  81%|########1 | 2443/3000 [56:57<13:36,  1.47s/it, lr: 1.0e-04 loss: 2.756e-01]
latex_v1:  81%|########1 | 2443/3000 [56:57<13:36,  1.47s/it, lr: 1.0e-04 loss: 2.756e-01]
latex_v1:  81%|########1 | 2444/3000 [56:57<13:20,  1.44s/it, lr: 1.0e-04 loss: 2.756e-01]
latex_v1:  81%|########1 | 2444/3000 [56:57<13:20,  1.44s/it, lr: 1.0e-04 loss: 2.756e-01]
latex_v1:  81%|########1 | 2444/3000 [56:58<13:20,  1.44s/it, lr: 1.0e-04 loss: 1.268e-01]
latex_v1:  81%|########1 | 2444/3000 [56:58<13:20,  1.44s/it, lr: 1.0e-04 loss: 1.268e-01]
latex_v1:  82%|########1 | 2445/3000 [56:58<13:35,  1.47s/it, lr: 1.0e-04 loss: 1.268e-01]
latex_v1:  82%|########1 | 2445/3000 [56:58<13:35,  1.47s/it, lr: 1.0e-04 loss: 1.268e-01]
latex_v1:  82%|########1 | 2445/3000 [56:59<13:35,  1.47s/it, lr: 1.0e-04 loss: 9.845e-02]
latex_v1:  82%|########1 | 2445/3000 [56:59<13:35,  1.47s/it, lr: 1.0e-04 loss: 9.845e-02]
latex_v1:  82%|########1 | 2446/3000 [56:59<11:41,  1.27s/it, lr: 1.0e-04 loss: 9.845e-02]
latex_v1:  82%|########1 | 2446/3000 [56:59<11:41,  1.27s/it, lr: 1.0e-04 loss: 9.845e-02]
latex_v1:  82%|########1 | 2446/3000 [57:02<11:41,  1.27s/it, lr: 1.0e-04 loss: 6.879e-01]
latex_v1:  82%|########1 | 2446/3000 [57:02<11:41,  1.27s/it, lr: 1.0e-04 loss: 6.879e-01]
latex_v1:  82%|########1 | 2447/3000 [57:02<15:33,  1.69s/it, lr: 1.0e-04 loss: 6.879e-01]
latex_v1:  82%|########1 | 2447/3000 [57:02<15:33,  1.69s/it, lr: 1.0e-04 loss: 6.879e-01]
latex_v1:  82%|########1 | 2447/3000 [57:04<15:33,  1.69s/it, lr: 1.0e-04 loss: 1.319e-01]
latex_v1:  82%|########1 | 2447/3000 [57:04<15:33,  1.69s/it, lr: 1.0e-04 loss: 1.319e-01]
latex_v1:  82%|########1 | 2448/3000 [57:04<16:21,  1.78s/it, lr: 1.0e-04 loss: 1.319e-01]
latex_v1:  82%|########1 | 2448/3000 [57:04<16:21,  1.78s/it, lr: 1.0e-04 loss: 1.319e-01]
latex_v1:  82%|########1 | 2448/3000 [57:06<16:21,  1.78s/it, lr: 1.0e-04 loss: 4.418e-01]
latex_v1:  82%|########1 | 2448/3000 [57:06<16:21,  1.78s/it, lr: 1.0e-04 loss: 4.418e-01]
latex_v1:  82%|########1 | 2449/3000 [57:06<16:36,  1.81s/it, lr: 1.0e-04 loss: 4.418e-01]
latex_v1:  82%|########1 | 2449/3000 [57:06<16:36,  1.81s/it, lr: 1.0e-04 loss: 4.418e-01]
latex_v1:  82%|########1 | 2449/3000 [57:06<16:36,  1.81s/it, lr: 1.0e-04 loss: 8.812e-02]
latex_v1:  82%|########1 | 2449/3000 [57:06<16:36,  1.81s/it, lr: 1.0e-04 loss: 8.812e-02]
latex_v1:  82%|########1 | 2450/3000 [57:07<16:35,  1.81s/it, lr: 1.0e-04 loss: 5.743e-01]
latex_v1:  82%|########1 | 2450/3000 [57:07<16:35,  1.81s/it, lr: 1.0e-04 loss: 5.743e-01]
latex_v1:  82%|########1 | 2451/3000 [57:07<10:35,  1.16s/it, lr: 1.0e-04 loss: 5.743e-01]
latex_v1:  82%|########1 | 2451/3000 [57:07<10:35,  1.16s/it, lr: 1.0e-04 loss: 5.743e-01]
latex_v1:  82%|########1 | 2451/3000 [57:09<10:35,  1.16s/it, lr: 1.0e-04 loss: 1.081e-01]
latex_v1:  82%|########1 | 2451/3000 [57:09<10:35,  1.16s/it, lr: 1.0e-04 loss: 1.081e-01]
latex_v1:  82%|########1 | 2452/3000 [57:09<11:30,  1.26s/it, lr: 1.0e-04 loss: 1.081e-01]
latex_v1:  82%|########1 | 2452/3000 [57:09<11:30,  1.26s/it, lr: 1.0e-04 loss: 1.081e-01]
latex_v1:  82%|########1 | 2452/3000 [57:10<11:30,  1.26s/it, lr: 1.0e-04 loss: 4.952e-01]
latex_v1:  82%|########1 | 2452/3000 [57:10<11:30,  1.26s/it, lr: 1.0e-04 loss: 4.952e-01]
latex_v1:  82%|########1 | 2453/3000 [57:10<11:18,  1.24s/it, lr: 1.0e-04 loss: 4.952e-01]
latex_v1:  82%|########1 | 2453/3000 [57:10<11:18,  1.24s/it, lr: 1.0e-04 loss: 4.952e-01]
latex_v1:  82%|########1 | 2453/3000 [57:11<11:18,  1.24s/it, lr: 1.0e-04 loss: 6.903e-01]
latex_v1:  82%|########1 | 2453/3000 [57:11<11:18,  1.24s/it, lr: 1.0e-04 loss: 6.903e-01]
latex_v1:  82%|########1 | 2454/3000 [57:11<10:07,  1.11s/it, lr: 1.0e-04 loss: 6.903e-01]
latex_v1:  82%|########1 | 2454/3000 [57:11<10:07,  1.11s/it, lr: 1.0e-04 loss: 6.903e-01]
latex_v1:  82%|########1 | 2454/3000 [57:14<10:07,  1.11s/it, lr: 1.0e-04 loss: 4.938e-01]
latex_v1:  82%|########1 | 2454/3000 [57:14<10:07,  1.11s/it, lr: 1.0e-04 loss: 4.938e-01]
latex_v1:  82%|########1 | 2455/3000 [57:14<14:34,  1.60s/it, lr: 1.0e-04 loss: 4.938e-01]
latex_v1:  82%|########1 | 2455/3000 [57:14<14:34,  1.60s/it, lr: 1.0e-04 loss: 4.938e-01]
latex_v1:  82%|########1 | 2455/3000 [57:14<14:34,  1.60s/it, lr: 1.0e-04 loss: 5.976e-01]
latex_v1:  82%|########1 | 2455/3000 [57:14<14:34,  1.60s/it, lr: 1.0e-04 loss: 5.976e-01]
latex_v1:  82%|########1 | 2456/3000 [57:14<12:25,  1.37s/it, lr: 1.0e-04 loss: 5.976e-01]
latex_v1:  82%|########1 | 2456/3000 [57:14<12:25,  1.37s/it, lr: 1.0e-04 loss: 5.976e-01]
latex_v1:  82%|########1 | 2456/3000 [57:15<12:25,  1.37s/it, lr: 1.0e-04 loss: 5.884e-01]
latex_v1:  82%|########1 | 2456/3000 [57:15<12:25,  1.37s/it, lr: 1.0e-04 loss: 5.884e-01]
latex_v1:  82%|########1 | 2457/3000 [57:15<10:47,  1.19s/it, lr: 1.0e-04 loss: 5.884e-01]
latex_v1:  82%|########1 | 2457/3000 [57:15<10:47,  1.19s/it, lr: 1.0e-04 loss: 5.884e-01]
latex_v1:  82%|########1 | 2457/3000 [57:16<10:47,  1.19s/it, lr: 1.0e-04 loss: 3.125e-01]
latex_v1:  82%|########1 | 2457/3000 [57:16<10:47,  1.19s/it, lr: 1.0e-04 loss: 3.125e-01]
latex_v1:  82%|########1 | 2458/3000 [57:16<09:40,  1.07s/it, lr: 1.0e-04 loss: 3.125e-01]
latex_v1:  82%|########1 | 2458/3000 [57:16<09:40,  1.07s/it, lr: 1.0e-04 loss: 3.125e-01]
latex_v1:  82%|########1 | 2458/3000 [57:17<09:40,  1.07s/it, lr: 1.0e-04 loss: 1.044e-01]
latex_v1:  82%|########1 | 2458/3000 [57:17<09:40,  1.07s/it, lr: 1.0e-04 loss: 1.044e-01]
latex_v1:  82%|########1 | 2459/3000 [57:17<08:50,  1.02it/s, lr: 1.0e-04 loss: 1.044e-01]
latex_v1:  82%|########1 | 2459/3000 [57:17<08:50,  1.02it/s, lr: 1.0e-04 loss: 1.044e-01]
latex_v1:  82%|########1 | 2459/3000 [57:18<08:50,  1.02it/s, lr: 1.0e-04 loss: 5.963e-01]
latex_v1:  82%|########1 | 2459/3000 [57:18<08:50,  1.02it/s, lr: 1.0e-04 loss: 5.963e-01]
latex_v1:  82%|########2 | 2460/3000 [57:20<08:49,  1.02it/s, lr: 1.0e-04 loss: 5.607e-01]
latex_v1:  82%|########2 | 2460/3000 [57:20<08:49,  1.02it/s, lr: 1.0e-04 loss: 5.607e-01]
latex_v1:  82%|########2 | 2461/3000 [57:20<08:12,  1.09it/s, lr: 1.0e-04 loss: 5.607e-01]
latex_v1:  82%|########2 | 2461/3000 [57:20<08:12,  1.09it/s, lr: 1.0e-04 loss: 5.607e-01]
latex_v1:  82%|########2 | 2461/3000 [57:20<08:12,  1.09it/s, lr: 1.0e-04 loss: 2.675e-01]
latex_v1:  82%|########2 | 2461/3000 [57:20<08:12,  1.09it/s, lr: 1.0e-04 loss: 2.675e-01]
latex_v1:  82%|########2 | 2462/3000 [57:20<07:52,  1.14it/s, lr: 1.0e-04 loss: 2.675e-01]
latex_v1:  82%|########2 | 2462/3000 [57:20<07:52,  1.14it/s, lr: 1.0e-04 loss: 2.675e-01]
latex_v1:  82%|########2 | 2462/3000 [57:21<07:52,  1.14it/s, lr: 1.0e-04 loss: 5.881e-01]
latex_v1:  82%|########2 | 2462/3000 [57:21<07:52,  1.14it/s, lr: 1.0e-04 loss: 5.881e-01]
latex_v1:  82%|########2 | 2463/3000 [57:21<07:34,  1.18it/s, lr: 1.0e-04 loss: 5.881e-01]
latex_v1:  82%|########2 | 2463/3000 [57:21<07:34,  1.18it/s, lr: 1.0e-04 loss: 5.881e-01]
latex_v1:  82%|########2 | 2463/3000 [57:23<07:34,  1.18it/s, lr: 1.0e-04 loss: 5.973e-01]
latex_v1:  82%|########2 | 2463/3000 [57:23<07:34,  1.18it/s, lr: 1.0e-04 loss: 5.973e-01]
latex_v1:  82%|########2 | 2464/3000 [57:23<09:56,  1.11s/it, lr: 1.0e-04 loss: 5.973e-01]
latex_v1:  82%|########2 | 2464/3000 [57:23<09:56,  1.11s/it, lr: 1.0e-04 loss: 5.973e-01]
latex_v1:  82%|########2 | 2464/3000 [57:24<09:56,  1.11s/it, lr: 1.0e-04 loss: 1.207e-01]
latex_v1:  82%|########2 | 2464/3000 [57:24<09:56,  1.11s/it, lr: 1.0e-04 loss: 1.207e-01]
latex_v1:  82%|########2 | 2465/3000 [57:24<10:38,  1.19s/it, lr: 1.0e-04 loss: 1.207e-01]
latex_v1:  82%|########2 | 2465/3000 [57:24<10:38,  1.19s/it, lr: 1.0e-04 loss: 1.207e-01]
latex_v1:  82%|########2 | 2465/3000 [57:25<10:38,  1.19s/it, lr: 1.0e-04 loss: 1.678e-01]
latex_v1:  82%|########2 | 2465/3000 [57:25<10:38,  1.19s/it, lr: 1.0e-04 loss: 1.678e-01]
latex_v1:  82%|########2 | 2466/3000 [57:25<09:28,  1.06s/it, lr: 1.0e-04 loss: 1.678e-01]
latex_v1:  82%|########2 | 2466/3000 [57:25<09:28,  1.06s/it, lr: 1.0e-04 loss: 1.678e-01]
latex_v1:  82%|########2 | 2466/3000 [57:26<09:28,  1.06s/it, lr: 1.0e-04 loss: 5.849e-01]
latex_v1:  82%|########2 | 2466/3000 [57:26<09:28,  1.06s/it, lr: 1.0e-04 loss: 5.849e-01]
latex_v1:  82%|########2 | 2467/3000 [57:26<08:39,  1.03it/s, lr: 1.0e-04 loss: 5.849e-01]
latex_v1:  82%|########2 | 2467/3000 [57:26<08:39,  1.03it/s, lr: 1.0e-04 loss: 5.849e-01]
latex_v1:  82%|########2 | 2467/3000 [57:27<08:39,  1.03it/s, lr: 1.0e-04 loss: 2.826e-01]
latex_v1:  82%|########2 | 2467/3000 [57:27<08:39,  1.03it/s, lr: 1.0e-04 loss: 2.826e-01]
latex_v1:  82%|########2 | 2468/3000 [57:27<09:56,  1.12s/it, lr: 1.0e-04 loss: 2.826e-01]
latex_v1:  82%|########2 | 2468/3000 [57:27<09:56,  1.12s/it, lr: 1.0e-04 loss: 2.826e-01]
latex_v1:  82%|########2 | 2468/3000 [57:28<09:56,  1.12s/it, lr: 1.0e-04 loss: 4.337e-01]
latex_v1:  82%|########2 | 2468/3000 [57:28<09:56,  1.12s/it, lr: 1.0e-04 loss: 4.337e-01]
latex_v1:  82%|########2 | 2469/3000 [57:28<08:57,  1.01s/it, lr: 1.0e-04 loss: 4.337e-01]
latex_v1:  82%|########2 | 2469/3000 [57:28<08:57,  1.01s/it, lr: 1.0e-04 loss: 4.337e-01]
latex_v1:  82%|########2 | 2469/3000 [57:30<08:57,  1.01s/it, lr: 1.0e-04 loss: 7.685e-01]
latex_v1:  82%|########2 | 2469/3000 [57:30<08:57,  1.01s/it, lr: 1.0e-04 loss: 7.685e-01]
latex_v1:  82%|########2 | 2470/3000 [57:31<08:56,  1.01s/it, lr: 1.0e-04 loss: 7.293e-01]
latex_v1:  82%|########2 | 2470/3000 [57:31<08:56,  1.01s/it, lr: 1.0e-04 loss: 7.293e-01]
latex_v1:  82%|########2 | 2471/3000 [57:31<07:42,  1.14it/s, lr: 1.0e-04 loss: 7.293e-01]
latex_v1:  82%|########2 | 2471/3000 [57:31<07:42,  1.14it/s, lr: 1.0e-04 loss: 7.293e-01]
latex_v1:  82%|########2 | 2471/3000 [57:32<07:42,  1.14it/s, lr: 1.0e-04 loss: 6.946e-01]
latex_v1:  82%|########2 | 2471/3000 [57:32<07:42,  1.14it/s, lr: 1.0e-04 loss: 6.946e-01]
latex_v1:  82%|########2 | 2472/3000 [57:32<07:26,  1.18it/s, lr: 1.0e-04 loss: 6.946e-01]
latex_v1:  82%|########2 | 2472/3000 [57:32<07:26,  1.18it/s, lr: 1.0e-04 loss: 6.946e-01]
latex_v1:  82%|########2 | 2472/3000 [57:35<07:26,  1.18it/s, lr: 1.0e-04 loss: 3.492e-02]
latex_v1:  82%|########2 | 2472/3000 [57:35<07:26,  1.18it/s, lr: 1.0e-04 loss: 3.492e-02]
latex_v1:  82%|########2 | 2473/3000 [57:35<12:06,  1.38s/it, lr: 1.0e-04 loss: 3.492e-02]
latex_v1:  82%|########2 | 2473/3000 [57:35<12:06,  1.38s/it, lr: 1.0e-04 loss: 3.492e-02]
latex_v1:  82%|########2 | 2473/3000 [57:36<12:06,  1.38s/it, lr: 1.0e-04 loss: 5.518e-01]
latex_v1:  82%|########2 | 2473/3000 [57:36<12:06,  1.38s/it, lr: 1.0e-04 loss: 5.518e-01]
latex_v1:  82%|########2 | 2474/3000 [57:36<12:29,  1.42s/it, lr: 1.0e-04 loss: 5.518e-01]
latex_v1:  82%|########2 | 2474/3000 [57:36<12:29,  1.42s/it, lr: 1.0e-04 loss: 5.518e-01]
latex_v1:  82%|########2 | 2474/3000 [57:38<12:29,  1.42s/it, lr: 1.0e-04 loss: 1.394e-01]
latex_v1:  82%|########2 | 2474/3000 [57:38<12:29,  1.42s/it, lr: 1.0e-04 loss: 1.394e-01]
latex_v1:  82%|########2 | 2475/3000 [57:38<12:47,  1.46s/it, lr: 1.0e-04 loss: 1.394e-01]
latex_v1:  82%|########2 | 2475/3000 [57:38<12:47,  1.46s/it, lr: 1.0e-04 loss: 1.394e-01]
latex_v1:  82%|########2 | 2475/3000 [57:39<12:47,  1.46s/it, lr: 1.0e-04 loss: 2.651e-01]
latex_v1:  82%|########2 | 2475/3000 [57:39<12:47,  1.46s/it, lr: 1.0e-04 loss: 2.651e-01]
latex_v1:  83%|########2 | 2476/3000 [57:39<10:59,  1.26s/it, lr: 1.0e-04 loss: 2.651e-01]
latex_v1:  83%|########2 | 2476/3000 [57:39<10:59,  1.26s/it, lr: 1.0e-04 loss: 2.651e-01]
latex_v1:  83%|########2 | 2476/3000 [57:39<10:59,  1.26s/it, lr: 1.0e-04 loss: 5.902e-01]
latex_v1:  83%|########2 | 2476/3000 [57:39<10:59,  1.26s/it, lr: 1.0e-04 loss: 5.902e-01]
latex_v1:  83%|########2 | 2477/3000 [57:39<09:41,  1.11s/it, lr: 1.0e-04 loss: 5.902e-01]
latex_v1:  83%|########2 | 2477/3000 [57:39<09:41,  1.11s/it, lr: 1.0e-04 loss: 5.902e-01]
latex_v1:  83%|########2 | 2477/3000 [57:40<09:41,  1.11s/it, lr: 1.0e-04 loss: 4.498e-01]
latex_v1:  83%|########2 | 2477/3000 [57:40<09:41,  1.11s/it, lr: 1.0e-04 loss: 4.498e-01]
latex_v1:  83%|########2 | 2478/3000 [57:40<08:45,  1.01s/it, lr: 1.0e-04 loss: 4.498e-01]
latex_v1:  83%|########2 | 2478/3000 [57:40<08:45,  1.01s/it, lr: 1.0e-04 loss: 4.498e-01]
latex_v1:  83%|########2 | 2478/3000 [57:43<08:45,  1.01s/it, lr: 1.0e-04 loss: 7.786e-02]
latex_v1:  83%|########2 | 2478/3000 [57:43<08:45,  1.01s/it, lr: 1.0e-04 loss: 7.786e-02]
latex_v1:  83%|########2 | 2479/3000 [57:43<13:33,  1.56s/it, lr: 1.0e-04 loss: 7.786e-02]
latex_v1:  83%|########2 | 2479/3000 [57:43<13:33,  1.56s/it, lr: 1.0e-04 loss: 7.786e-02]
latex_v1:  83%|########2 | 2479/3000 [57:44<13:33,  1.56s/it, lr: 1.0e-04 loss: 2.968e-01]
latex_v1:  83%|########2 | 2479/3000 [57:44<13:33,  1.56s/it, lr: 1.0e-04 loss: 2.968e-01]
latex_v1:  83%|########2 | 2480/3000 [57:46<13:31,  1.56s/it, lr: 1.0e-04 loss: 1.053e-01]
latex_v1:  83%|########2 | 2480/3000 [57:46<13:31,  1.56s/it, lr: 1.0e-04 loss: 1.053e-01]
latex_v1:  83%|########2 | 2481/3000 [57:46<10:23,  1.20s/it, lr: 1.0e-04 loss: 1.053e-01]
latex_v1:  83%|########2 | 2481/3000 [57:46<10:23,  1.20s/it, lr: 1.0e-04 loss: 1.053e-01]
latex_v1:  83%|########2 | 2481/3000 [57:48<10:23,  1.20s/it, lr: 1.0e-04 loss: 1.118e-01]
latex_v1:  83%|########2 | 2481/3000 [57:48<10:23,  1.20s/it, lr: 1.0e-04 loss: 1.118e-01]
latex_v1:  83%|########2 | 2482/3000 [57:48<11:50,  1.37s/it, lr: 1.0e-04 loss: 1.118e-01]
latex_v1:  83%|########2 | 2482/3000 [57:48<11:50,  1.37s/it, lr: 1.0e-04 loss: 1.118e-01]
latex_v1:  83%|########2 | 2482/3000 [57:50<11:50,  1.37s/it, lr: 1.0e-04 loss: 7.142e-02]
latex_v1:  83%|########2 | 2482/3000 [57:50<11:50,  1.37s/it, lr: 1.0e-04 loss: 7.142e-02]
latex_v1:  83%|########2 | 2483/3000 [57:50<12:38,  1.47s/it, lr: 1.0e-04 loss: 7.142e-02]
latex_v1:  83%|########2 | 2483/3000 [57:50<12:38,  1.47s/it, lr: 1.0e-04 loss: 7.142e-02]
latex_v1:  83%|########2 | 2483/3000 [57:51<12:38,  1.47s/it, lr: 1.0e-04 loss: 3.661e-01]
latex_v1:  83%|########2 | 2483/3000 [57:51<12:38,  1.47s/it, lr: 1.0e-04 loss: 3.661e-01]
latex_v1:  83%|########2 | 2484/3000 [57:51<12:13,  1.42s/it, lr: 1.0e-04 loss: 3.661e-01]
latex_v1:  83%|########2 | 2484/3000 [57:51<12:13,  1.42s/it, lr: 1.0e-04 loss: 3.661e-01]
latex_v1:  83%|########2 | 2484/3000 [57:54<12:13,  1.42s/it, lr: 1.0e-04 loss: 2.867e-01]
latex_v1:  83%|########2 | 2484/3000 [57:54<12:13,  1.42s/it, lr: 1.0e-04 loss: 2.867e-01]
latex_v1:  83%|########2 | 2485/3000 [57:54<15:39,  1.82s/it, lr: 1.0e-04 loss: 2.867e-01]
latex_v1:  83%|########2 | 2485/3000 [57:54<15:39,  1.82s/it, lr: 1.0e-04 loss: 2.867e-01]
latex_v1:  83%|########2 | 2485/3000 [57:55<15:39,  1.82s/it, lr: 1.0e-04 loss: 2.810e-01]
latex_v1:  83%|########2 | 2485/3000 [57:55<15:39,  1.82s/it, lr: 1.0e-04 loss: 2.810e-01]
latex_v1:  83%|########2 | 2486/3000 [57:55<14:58,  1.75s/it, lr: 1.0e-04 loss: 2.810e-01]
latex_v1:  83%|########2 | 2486/3000 [57:55<14:58,  1.75s/it, lr: 1.0e-04 loss: 2.810e-01]
latex_v1:  83%|########2 | 2486/3000 [57:58<14:58,  1.75s/it, lr: 1.0e-04 loss: 1.871e-01]
latex_v1:  83%|########2 | 2486/3000 [57:58<14:58,  1.75s/it, lr: 1.0e-04 loss: 1.871e-01]
latex_v1:  83%|########2 | 2487/3000 [57:58<17:42,  2.07s/it, lr: 1.0e-04 loss: 1.871e-01]
latex_v1:  83%|########2 | 2487/3000 [57:58<17:42,  2.07s/it, lr: 1.0e-04 loss: 1.871e-01]
latex_v1:  83%|########2 | 2487/3000 [58:00<17:42,  2.07s/it, lr: 1.0e-04 loss: 3.748e-02]
latex_v1:  83%|########2 | 2487/3000 [58:00<17:42,  2.07s/it, lr: 1.0e-04 loss: 3.748e-02]
latex_v1:  83%|########2 | 2488/3000 [58:00<16:49,  1.97s/it, lr: 1.0e-04 loss: 3.748e-02]
latex_v1:  83%|########2 | 2488/3000 [58:00<16:49,  1.97s/it, lr: 1.0e-04 loss: 3.748e-02]
latex_v1:  83%|########2 | 2488/3000 [58:01<16:49,  1.97s/it, lr: 1.0e-04 loss: 4.758e-01]
latex_v1:  83%|########2 | 2488/3000 [58:01<16:49,  1.97s/it, lr: 1.0e-04 loss: 4.758e-01]
latex_v1:  83%|########2 | 2489/3000 [58:01<13:41,  1.61s/it, lr: 1.0e-04 loss: 4.758e-01]
latex_v1:  83%|########2 | 2489/3000 [58:01<13:41,  1.61s/it, lr: 1.0e-04 loss: 4.758e-01]
latex_v1:  83%|########2 | 2489/3000 [58:02<13:41,  1.61s/it, lr: 1.0e-04 loss: 2.398e-01]
latex_v1:  83%|########2 | 2489/3000 [58:02<13:41,  1.61s/it, lr: 1.0e-04 loss: 2.398e-01]
latex_v1:  83%|########2 | 2490/3000 [58:03<13:39,  1.61s/it, lr: 1.0e-04 loss: 6.992e-02]
latex_v1:  83%|########2 | 2490/3000 [58:03<13:39,  1.61s/it, lr: 1.0e-04 loss: 6.992e-02]
latex_v1:  83%|########3 | 2491/3000 [58:03<09:58,  1.18s/it, lr: 1.0e-04 loss: 6.992e-02]
latex_v1:  83%|########3 | 2491/3000 [58:03<09:58,  1.18s/it, lr: 1.0e-04 loss: 6.992e-02]
latex_v1:  83%|########3 | 2491/3000 [58:05<09:58,  1.18s/it, lr: 1.0e-04 loss: 3.330e-01]
latex_v1:  83%|########3 | 2491/3000 [58:05<09:58,  1.18s/it, lr: 1.0e-04 loss: 3.330e-01]
latex_v1:  83%|########3 | 2492/3000 [58:05<10:28,  1.24s/it, lr: 1.0e-04 loss: 3.330e-01]
latex_v1:  83%|########3 | 2492/3000 [58:05<10:28,  1.24s/it, lr: 1.0e-04 loss: 3.330e-01]
latex_v1:  83%|########3 | 2492/3000 [58:06<10:28,  1.24s/it, lr: 1.0e-04 loss: 2.432e-01]
latex_v1:  83%|########3 | 2492/3000 [58:06<10:28,  1.24s/it, lr: 1.0e-04 loss: 2.432e-01]
latex_v1:  83%|########3 | 2493/3000 [58:06<09:24,  1.11s/it, lr: 1.0e-04 loss: 2.432e-01]
latex_v1:  83%|########3 | 2493/3000 [58:06<09:24,  1.11s/it, lr: 1.0e-04 loss: 2.432e-01]
latex_v1:  83%|########3 | 2493/3000 [58:07<09:24,  1.11s/it, lr: 1.0e-04 loss: 2.205e-01]
latex_v1:  83%|########3 | 2493/3000 [58:07<09:24,  1.11s/it, lr: 1.0e-04 loss: 2.205e-01]
latex_v1:  83%|########3 | 2494/3000 [58:07<09:00,  1.07s/it, lr: 1.0e-04 loss: 2.205e-01]
latex_v1:  83%|########3 | 2494/3000 [58:07<09:00,  1.07s/it, lr: 1.0e-04 loss: 2.205e-01]
latex_v1:  83%|########3 | 2494/3000 [58:08<09:00,  1.07s/it, lr: 1.0e-04 loss: 2.490e-01]
latex_v1:  83%|########3 | 2494/3000 [58:08<09:00,  1.07s/it, lr: 1.0e-04 loss: 2.490e-01]
latex_v1:  83%|########3 | 2495/3000 [58:08<10:09,  1.21s/it, lr: 1.0e-04 loss: 2.490e-01]
latex_v1:  83%|########3 | 2495/3000 [58:08<10:09,  1.21s/it, lr: 1.0e-04 loss: 2.490e-01]
latex_v1:  83%|########3 | 2495/3000 [58:10<10:09,  1.21s/it, lr: 1.0e-04 loss: 2.838e-01]
latex_v1:  83%|########3 | 2495/3000 [58:10<10:09,  1.21s/it, lr: 1.0e-04 loss: 2.838e-01]
latex_v1:  83%|########3 | 2496/3000 [58:10<11:44,  1.40s/it, lr: 1.0e-04 loss: 2.838e-01]
latex_v1:  83%|########3 | 2496/3000 [58:10<11:44,  1.40s/it, lr: 1.0e-04 loss: 2.838e-01]
latex_v1:  83%|########3 | 2496/3000 [58:11<11:44,  1.40s/it, lr: 1.0e-04 loss: 7.642e-01]
latex_v1:  83%|########3 | 2496/3000 [58:11<11:44,  1.40s/it, lr: 1.0e-04 loss: 7.642e-01]
latex_v1:  83%|########3 | 2497/3000 [58:11<10:45,  1.28s/it, lr: 1.0e-04 loss: 7.642e-01]
latex_v1:  83%|########3 | 2497/3000 [58:11<10:45,  1.28s/it, lr: 1.0e-04 loss: 7.642e-01]
latex_v1:  83%|########3 | 2497/3000 [58:12<10:45,  1.28s/it, lr: 1.0e-04 loss: 3.378e-02]
latex_v1:  83%|########3 | 2497/3000 [58:12<10:45,  1.28s/it, lr: 1.0e-04 loss: 3.378e-02]
latex_v1:  83%|########3 | 2498/3000 [58:12<09:27,  1.13s/it, lr: 1.0e-04 loss: 3.378e-02]
latex_v1:  83%|########3 | 2498/3000 [58:12<09:27,  1.13s/it, lr: 1.0e-04 loss: 3.378e-02]
latex_v1:  83%|########3 | 2498/3000 [58:15<09:27,  1.13s/it, lr: 1.0e-04 loss: 1.263e-01]
latex_v1:  83%|########3 | 2498/3000 [58:15<09:27,  1.13s/it, lr: 1.0e-04 loss: 1.263e-01]
latex_v1:  83%|########3 | 2499/3000 [58:15<13:49,  1.65s/it, lr: 1.0e-04 loss: 1.263e-01]
latex_v1:  83%|########3 | 2499/3000 [58:15<13:49,  1.65s/it, lr: 1.0e-04 loss: 1.263e-01]
latex_v1:  83%|########3 | 2499/3000 [58:17<13:49,  1.65s/it, lr: 1.0e-04 loss: 2.507e-01]
latex_v1:  83%|########3 | 2499/3000 [58:17<13:49,  1.65s/it, lr: 1.0e-04 loss: 2.507e-01]
Saving at step 2500
Saved checkpoint to /data/app/output/latex_v1/latex_v1_000002500.safetensors
Saved optimizer to /data/app/output/latex_v1/optimizer.pt
Removing old save: /data/app/output/latex_v1/latex_v1_000001500.safetensors

latex_v1:  83%|########3 | 2500/3000 [58:18<13:47,  1.65s/it, lr: 1.0e-04 loss: 8.424e-01]
latex_v1:  83%|########3 | 2500/3000 [58:18<13:47,  1.65s/it, lr: 1.0e-04 loss: 8.424e-01]
latex_v1:  83%|########3 | 2501/3000 [58:18<09:18,  1.12s/it, lr: 1.0e-04 loss: 8.424e-01]
latex_v1:  83%|########3 | 2501/3000 [58:18<09:18,  1.12s/it, lr: 1.0e-04 loss: 8.424e-01]
latex_v1:  83%|########3 | 2501/3000 [58:19<09:18,  1.12s/it, lr: 1.0e-04 loss: 1.843e-01]
latex_v1:  83%|########3 | 2501/3000 [58:19<09:18,  1.12s/it, lr: 1.0e-04 loss: 1.843e-01]
latex_v1:  83%|########3 | 2502/3000 [58:19<10:08,  1.22s/it, lr: 1.0e-04 loss: 1.843e-01]
latex_v1:  83%|########3 | 2502/3000 [58:19<10:08,  1.22s/it, lr: 1.0e-04 loss: 1.843e-01]
latex_v1:  83%|########3 | 2502/3000 [58:22<10:08,  1.22s/it, lr: 1.0e-04 loss: 5.577e-01]
latex_v1:  83%|########3 | 2502/3000 [58:22<10:08,  1.22s/it, lr: 1.0e-04 loss: 5.577e-01]
latex_v1:  83%|########3 | 2503/3000 [58:22<13:33,  1.64s/it, lr: 1.0e-04 loss: 5.577e-01]
latex_v1:  83%|########3 | 2503/3000 [58:22<13:33,  1.64s/it, lr: 1.0e-04 loss: 5.577e-01]
latex_v1:  83%|########3 | 2503/3000 [58:23<13:33,  1.64s/it, lr: 1.0e-04 loss: 6.575e-01]
latex_v1:  83%|########3 | 2503/3000 [58:23<13:33,  1.64s/it, lr: 1.0e-04 loss: 6.575e-01]
latex_v1:  83%|########3 | 2504/3000 [58:23<12:27,  1.51s/it, lr: 1.0e-04 loss: 6.575e-01]
latex_v1:  83%|########3 | 2504/3000 [58:23<12:27,  1.51s/it, lr: 1.0e-04 loss: 6.575e-01]
latex_v1:  83%|########3 | 2504/3000 [58:24<12:27,  1.51s/it, lr: 1.0e-04 loss: 6.026e-01]
latex_v1:  83%|########3 | 2504/3000 [58:24<12:27,  1.51s/it, lr: 1.0e-04 loss: 6.026e-01]
latex_v1:  84%|########3 | 2505/3000 [58:24<10:39,  1.29s/it, lr: 1.0e-04 loss: 6.026e-01]
latex_v1:  84%|########3 | 2505/3000 [58:24<10:39,  1.29s/it, lr: 1.0e-04 loss: 6.026e-01]
latex_v1:  84%|########3 | 2505/3000 [58:26<10:39,  1.29s/it, lr: 1.0e-04 loss: 1.472e-01]
latex_v1:  84%|########3 | 2505/3000 [58:26<10:39,  1.29s/it, lr: 1.0e-04 loss: 1.472e-01]
latex_v1:  84%|########3 | 2506/3000 [58:26<11:12,  1.36s/it, lr: 1.0e-04 loss: 1.472e-01]
latex_v1:  84%|########3 | 2506/3000 [58:26<11:12,  1.36s/it, lr: 1.0e-04 loss: 1.472e-01]
latex_v1:  84%|########3 | 2506/3000 [58:27<11:12,  1.36s/it, lr: 1.0e-04 loss: 2.214e-01]
latex_v1:  84%|########3 | 2506/3000 [58:27<11:12,  1.36s/it, lr: 1.0e-04 loss: 2.214e-01]
latex_v1:  84%|########3 | 2507/3000 [58:27<11:23,  1.39s/it, lr: 1.0e-04 loss: 2.214e-01]
latex_v1:  84%|########3 | 2507/3000 [58:27<11:23,  1.39s/it, lr: 1.0e-04 loss: 2.214e-01]
latex_v1:  84%|########3 | 2507/3000 [58:28<11:23,  1.39s/it, lr: 1.0e-04 loss: 2.919e-01]
latex_v1:  84%|########3 | 2507/3000 [58:28<11:23,  1.39s/it, lr: 1.0e-04 loss: 2.919e-01]
latex_v1:  84%|########3 | 2508/3000 [58:28<10:49,  1.32s/it, lr: 1.0e-04 loss: 2.919e-01]
latex_v1:  84%|########3 | 2508/3000 [58:28<10:49,  1.32s/it, lr: 1.0e-04 loss: 2.919e-01]
latex_v1:  84%|########3 | 2508/3000 [58:30<10:49,  1.32s/it, lr: 1.0e-04 loss: 6.507e-01]
latex_v1:  84%|########3 | 2508/3000 [58:30<10:49,  1.32s/it, lr: 1.0e-04 loss: 6.507e-01]
latex_v1:  84%|########3 | 2509/3000 [58:30<12:09,  1.48s/it, lr: 1.0e-04 loss: 6.507e-01]
latex_v1:  84%|########3 | 2509/3000 [58:30<12:09,  1.48s/it, lr: 1.0e-04 loss: 6.507e-01]
latex_v1:  84%|########3 | 2509/3000 [58:31<12:09,  1.48s/it, lr: 1.0e-04 loss: 6.568e-01]
latex_v1:  84%|########3 | 2509/3000 [58:31<12:09,  1.48s/it, lr: 1.0e-04 loss: 6.568e-01]
latex_v1:  84%|########3 | 2510/3000 [58:33<12:07,  1.48s/it, lr: 1.0e-04 loss: 3.956e-01]
latex_v1:  84%|########3 | 2510/3000 [58:33<12:07,  1.48s/it, lr: 1.0e-04 loss: 3.956e-01]
latex_v1:  84%|########3 | 2511/3000 [58:33<09:08,  1.12s/it, lr: 1.0e-04 loss: 3.956e-01]
latex_v1:  84%|########3 | 2511/3000 [58:33<09:08,  1.12s/it, lr: 1.0e-04 loss: 3.956e-01]
latex_v1:  84%|########3 | 2511/3000 [58:34<09:08,  1.12s/it, lr: 1.0e-04 loss: 6.687e-01]
latex_v1:  84%|########3 | 2511/3000 [58:34<09:08,  1.12s/it, lr: 1.0e-04 loss: 6.687e-01]
latex_v1:  84%|########3 | 2512/3000 [58:34<09:59,  1.23s/it, lr: 1.0e-04 loss: 6.687e-01]
latex_v1:  84%|########3 | 2512/3000 [58:34<09:59,  1.23s/it, lr: 1.0e-04 loss: 6.687e-01]
latex_v1:  84%|########3 | 2512/3000 [58:36<09:59,  1.23s/it, lr: 1.0e-04 loss: 5.403e-01]
latex_v1:  84%|########3 | 2512/3000 [58:36<09:59,  1.23s/it, lr: 1.0e-04 loss: 5.403e-01]
latex_v1:  84%|########3 | 2513/3000 [58:36<11:08,  1.37s/it, lr: 1.0e-04 loss: 5.403e-01]
latex_v1:  84%|########3 | 2513/3000 [58:36<11:08,  1.37s/it, lr: 1.0e-04 loss: 5.403e-01]
latex_v1:  84%|########3 | 2513/3000 [58:37<11:08,  1.37s/it, lr: 1.0e-04 loss: 6.846e-01]
latex_v1:  84%|########3 | 2513/3000 [58:37<11:08,  1.37s/it, lr: 1.0e-04 loss: 6.846e-01]
latex_v1:  84%|########3 | 2514/3000 [58:37<09:48,  1.21s/it, lr: 1.0e-04 loss: 6.846e-01]
latex_v1:  84%|########3 | 2514/3000 [58:37<09:48,  1.21s/it, lr: 1.0e-04 loss: 6.846e-01]
latex_v1:  84%|########3 | 2514/3000 [58:38<09:48,  1.21s/it, lr: 1.0e-04 loss: 3.579e-01]
latex_v1:  84%|########3 | 2514/3000 [58:38<09:48,  1.21s/it, lr: 1.0e-04 loss: 3.579e-01]
latex_v1:  84%|########3 | 2515/3000 [58:38<08:45,  1.08s/it, lr: 1.0e-04 loss: 3.579e-01]
latex_v1:  84%|########3 | 2515/3000 [58:38<08:45,  1.08s/it, lr: 1.0e-04 loss: 3.579e-01]
latex_v1:  84%|########3 | 2515/3000 [58:40<08:45,  1.08s/it, lr: 1.0e-04 loss: 1.596e-01]
latex_v1:  84%|########3 | 2515/3000 [58:40<08:45,  1.08s/it, lr: 1.0e-04 loss: 1.596e-01]
latex_v1:  84%|########3 | 2516/3000 [58:40<12:28,  1.55s/it, lr: 1.0e-04 loss: 1.596e-01]
latex_v1:  84%|########3 | 2516/3000 [58:40<12:28,  1.55s/it, lr: 1.0e-04 loss: 1.596e-01]
latex_v1:  84%|########3 | 2516/3000 [58:41<12:28,  1.55s/it, lr: 1.0e-04 loss: 1.007e-01]
latex_v1:  84%|########3 | 2516/3000 [58:41<12:28,  1.55s/it, lr: 1.0e-04 loss: 1.007e-01]
latex_v1:  84%|########3 | 2517/3000 [58:41<10:38,  1.32s/it, lr: 1.0e-04 loss: 1.007e-01]
latex_v1:  84%|########3 | 2517/3000 [58:41<10:38,  1.32s/it, lr: 1.0e-04 loss: 1.007e-01]
latex_v1:  84%|########3 | 2517/3000 [58:43<10:38,  1.32s/it, lr: 1.0e-04 loss: 2.035e-01]
latex_v1:  84%|########3 | 2517/3000 [58:43<10:38,  1.32s/it, lr: 1.0e-04 loss: 2.035e-01]
latex_v1:  84%|########3 | 2518/3000 [58:43<11:58,  1.49s/it, lr: 1.0e-04 loss: 2.035e-01]
latex_v1:  84%|########3 | 2518/3000 [58:43<11:58,  1.49s/it, lr: 1.0e-04 loss: 2.035e-01]
latex_v1:  84%|########3 | 2518/3000 [58:46<11:58,  1.49s/it, lr: 1.0e-04 loss: 3.044e-01]
latex_v1:  84%|########3 | 2518/3000 [58:46<11:58,  1.49s/it, lr: 1.0e-04 loss: 3.044e-01]
latex_v1:  84%|########3 | 2519/3000 [58:46<15:16,  1.91s/it, lr: 1.0e-04 loss: 3.044e-01]
latex_v1:  84%|########3 | 2519/3000 [58:46<15:16,  1.91s/it, lr: 1.0e-04 loss: 3.044e-01]
latex_v1:  84%|########3 | 2519/3000 [58:47<15:16,  1.91s/it, lr: 1.0e-04 loss: 6.902e-01]
latex_v1:  84%|########3 | 2519/3000 [58:47<15:16,  1.91s/it, lr: 1.0e-04 loss: 6.902e-01]
latex_v1:  84%|########4 | 2520/3000 [58:49<15:14,  1.91s/it, lr: 1.0e-04 loss: 1.605e-01]
latex_v1:  84%|########4 | 2520/3000 [58:49<15:14,  1.91s/it, lr: 1.0e-04 loss: 1.605e-01]
latex_v1:  84%|########4 | 2521/3000 [58:49<11:03,  1.39s/it, lr: 1.0e-04 loss: 1.605e-01]
latex_v1:  84%|########4 | 2521/3000 [58:49<11:03,  1.39s/it, lr: 1.0e-04 loss: 1.605e-01]
latex_v1:  84%|########4 | 2521/3000 [58:51<11:03,  1.39s/it, lr: 1.0e-04 loss: 5.858e-01]
latex_v1:  84%|########4 | 2521/3000 [58:51<11:03,  1.39s/it, lr: 1.0e-04 loss: 5.858e-01]
latex_v1:  84%|########4 | 2522/3000 [58:51<12:11,  1.53s/it, lr: 1.0e-04 loss: 5.858e-01]
latex_v1:  84%|########4 | 2522/3000 [58:51<12:11,  1.53s/it, lr: 1.0e-04 loss: 5.858e-01]
latex_v1:  84%|########4 | 2522/3000 [58:51<12:11,  1.53s/it, lr: 1.0e-04 loss: 3.963e-01]
latex_v1:  84%|########4 | 2522/3000 [58:51<12:11,  1.53s/it, lr: 1.0e-04 loss: 3.963e-01]
latex_v1:  84%|########4 | 2523/3000 [58:51<10:33,  1.33s/it, lr: 1.0e-04 loss: 3.963e-01]
latex_v1:  84%|########4 | 2523/3000 [58:51<10:33,  1.33s/it, lr: 1.0e-04 loss: 3.963e-01]
latex_v1:  84%|########4 | 2523/3000 [58:53<10:33,  1.33s/it, lr: 1.0e-04 loss: 3.500e-01]
latex_v1:  84%|########4 | 2523/3000 [58:53<10:33,  1.33s/it, lr: 1.0e-04 loss: 3.500e-01]
latex_v1:  84%|########4 | 2524/3000 [58:53<10:13,  1.29s/it, lr: 1.0e-04 loss: 3.500e-01]
latex_v1:  84%|########4 | 2524/3000 [58:53<10:13,  1.29s/it, lr: 1.0e-04 loss: 3.500e-01]
latex_v1:  84%|########4 | 2524/3000 [58:53<10:13,  1.29s/it, lr: 1.0e-04 loss: 1.065e-01]
latex_v1:  84%|########4 | 2524/3000 [58:53<10:13,  1.29s/it, lr: 1.0e-04 loss: 1.065e-01]
latex_v1:  84%|########4 | 2525/3000 [58:53<09:00,  1.14s/it, lr: 1.0e-04 loss: 1.065e-01]
latex_v1:  84%|########4 | 2525/3000 [58:53<09:00,  1.14s/it, lr: 1.0e-04 loss: 1.065e-01]
latex_v1:  84%|########4 | 2525/3000 [58:55<09:00,  1.14s/it, lr: 1.0e-04 loss: 5.425e-01]
latex_v1:  84%|########4 | 2525/3000 [58:55<09:00,  1.14s/it, lr: 1.0e-04 loss: 5.425e-01]
latex_v1:  84%|########4 | 2526/3000 [58:55<09:27,  1.20s/it, lr: 1.0e-04 loss: 5.425e-01]
latex_v1:  84%|########4 | 2526/3000 [58:55<09:27,  1.20s/it, lr: 1.0e-04 loss: 5.425e-01]
latex_v1:  84%|########4 | 2526/3000 [58:56<09:27,  1.20s/it, lr: 1.0e-04 loss: 8.779e-02]
latex_v1:  84%|########4 | 2526/3000 [58:56<09:27,  1.20s/it, lr: 1.0e-04 loss: 8.779e-02]
latex_v1:  84%|########4 | 2527/3000 [58:56<09:53,  1.26s/it, lr: 1.0e-04 loss: 8.779e-02]
latex_v1:  84%|########4 | 2527/3000 [58:56<09:53,  1.26s/it, lr: 1.0e-04 loss: 8.779e-02]
latex_v1:  84%|########4 | 2527/3000 [58:57<09:53,  1.26s/it, lr: 1.0e-04 loss: 2.344e-01]
latex_v1:  84%|########4 | 2527/3000 [58:57<09:53,  1.26s/it, lr: 1.0e-04 loss: 2.344e-01]
latex_v1:  84%|########4 | 2528/3000 [58:57<09:13,  1.17s/it, lr: 1.0e-04 loss: 2.344e-01]
latex_v1:  84%|########4 | 2528/3000 [58:57<09:13,  1.17s/it, lr: 1.0e-04 loss: 2.344e-01]
latex_v1:  84%|########4 | 2528/3000 [58:59<09:13,  1.17s/it, lr: 1.0e-04 loss: 4.667e-01]
latex_v1:  84%|########4 | 2528/3000 [58:59<09:13,  1.17s/it, lr: 1.0e-04 loss: 4.667e-01]
latex_v1:  84%|########4 | 2529/3000 [58:59<10:04,  1.28s/it, lr: 1.0e-04 loss: 4.667e-01]
latex_v1:  84%|########4 | 2529/3000 [58:59<10:04,  1.28s/it, lr: 1.0e-04 loss: 4.667e-01]
latex_v1:  84%|########4 | 2529/3000 [58:59<10:04,  1.28s/it, lr: 1.0e-04 loss: 5.410e-01]
latex_v1:  84%|########4 | 2529/3000 [58:59<10:04,  1.28s/it, lr: 1.0e-04 loss: 5.410e-01]
latex_v1:  84%|########4 | 2530/3000 [59:01<10:03,  1.28s/it, lr: 1.0e-04 loss: 1.479e-01]
latex_v1:  84%|########4 | 2530/3000 [59:01<10:03,  1.28s/it, lr: 1.0e-04 loss: 1.479e-01]
latex_v1:  84%|########4 | 2531/3000 [59:01<07:31,  1.04it/s, lr: 1.0e-04 loss: 1.479e-01]
latex_v1:  84%|########4 | 2531/3000 [59:01<07:31,  1.04it/s, lr: 1.0e-04 loss: 1.479e-01]
latex_v1:  84%|########4 | 2531/3000 [59:01<07:31,  1.04it/s, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  84%|########4 | 2531/3000 [59:01<07:31,  1.04it/s, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  84%|########4 | 2532/3000 [59:01<07:05,  1.10it/s, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  84%|########4 | 2532/3000 [59:01<07:05,  1.10it/s, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  84%|########4 | 2532/3000 [59:03<07:05,  1.10it/s, lr: 1.0e-04 loss: 5.728e-01]
latex_v1:  84%|########4 | 2532/3000 [59:03<07:05,  1.10it/s, lr: 1.0e-04 loss: 5.728e-01]
latex_v1:  84%|########4 | 2533/3000 [59:03<08:21,  1.07s/it, lr: 1.0e-04 loss: 5.728e-01]
latex_v1:  84%|########4 | 2533/3000 [59:03<08:21,  1.07s/it, lr: 1.0e-04 loss: 5.728e-01]
latex_v1:  84%|########4 | 2533/3000 [59:04<08:21,  1.07s/it, lr: 1.0e-04 loss: 2.578e-01]
latex_v1:  84%|########4 | 2533/3000 [59:04<08:21,  1.07s/it, lr: 1.0e-04 loss: 2.578e-01]
latex_v1:  84%|########4 | 2534/3000 [59:04<08:18,  1.07s/it, lr: 1.0e-04 loss: 2.578e-01]
latex_v1:  84%|########4 | 2534/3000 [59:04<08:18,  1.07s/it, lr: 1.0e-04 loss: 2.578e-01]
latex_v1:  84%|########4 | 2534/3000 [59:07<08:18,  1.07s/it, lr: 1.0e-04 loss: 2.509e-01]
latex_v1:  84%|########4 | 2534/3000 [59:07<08:18,  1.07s/it, lr: 1.0e-04 loss: 2.509e-01]
latex_v1:  84%|########4 | 2535/3000 [59:07<12:08,  1.57s/it, lr: 1.0e-04 loss: 2.509e-01]
latex_v1:  84%|########4 | 2535/3000 [59:07<12:08,  1.57s/it, lr: 1.0e-04 loss: 2.509e-01]
latex_v1:  84%|########4 | 2535/3000 [59:08<12:08,  1.57s/it, lr: 1.0e-04 loss: 6.095e-01]
latex_v1:  84%|########4 | 2535/3000 [59:08<12:08,  1.57s/it, lr: 1.0e-04 loss: 6.095e-01]
latex_v1:  85%|########4 | 2536/3000 [59:08<10:17,  1.33s/it, lr: 1.0e-04 loss: 6.095e-01]
latex_v1:  85%|########4 | 2536/3000 [59:08<10:17,  1.33s/it, lr: 1.0e-04 loss: 6.095e-01]
latex_v1:  85%|########4 | 2536/3000 [59:08<10:17,  1.33s/it, lr: 1.0e-04 loss: 1.700e-01]
latex_v1:  85%|########4 | 2536/3000 [59:08<10:17,  1.33s/it, lr: 1.0e-04 loss: 1.700e-01]
latex_v1:  85%|########4 | 2537/3000 [59:08<08:57,  1.16s/it, lr: 1.0e-04 loss: 1.700e-01]
latex_v1:  85%|########4 | 2537/3000 [59:08<08:57,  1.16s/it, lr: 1.0e-04 loss: 1.700e-01]
latex_v1:  85%|########4 | 2537/3000 [59:10<08:57,  1.16s/it, lr: 1.0e-04 loss: 1.580e-01]
latex_v1:  85%|########4 | 2537/3000 [59:10<08:57,  1.16s/it, lr: 1.0e-04 loss: 1.580e-01]
latex_v1:  85%|########4 | 2538/3000 [59:10<10:33,  1.37s/it, lr: 1.0e-04 loss: 1.580e-01]
latex_v1:  85%|########4 | 2538/3000 [59:10<10:33,  1.37s/it, lr: 1.0e-04 loss: 1.580e-01]
latex_v1:  85%|########4 | 2538/3000 [59:12<10:33,  1.37s/it, lr: 1.0e-04 loss: 1.753e-01]
latex_v1:  85%|########4 | 2538/3000 [59:12<10:33,  1.37s/it, lr: 1.0e-04 loss: 1.753e-01]
latex_v1:  85%|########4 | 2539/3000 [59:12<10:54,  1.42s/it, lr: 1.0e-04 loss: 1.753e-01]
latex_v1:  85%|########4 | 2539/3000 [59:12<10:54,  1.42s/it, lr: 1.0e-04 loss: 1.753e-01]
latex_v1:  85%|########4 | 2539/3000 [59:13<10:54,  1.42s/it, lr: 1.0e-04 loss: 2.910e-01]
latex_v1:  85%|########4 | 2539/3000 [59:13<10:54,  1.42s/it, lr: 1.0e-04 loss: 2.910e-01]
latex_v1:  85%|########4 | 2540/3000 [59:14<10:53,  1.42s/it, lr: 1.0e-04 loss: 1.234e-01]
latex_v1:  85%|########4 | 2540/3000 [59:14<10:53,  1.42s/it, lr: 1.0e-04 loss: 1.234e-01]
latex_v1:  85%|########4 | 2541/3000 [59:14<07:12,  1.06it/s, lr: 1.0e-04 loss: 1.234e-01]
latex_v1:  85%|########4 | 2541/3000 [59:14<07:12,  1.06it/s, lr: 1.0e-04 loss: 1.234e-01]
latex_v1:  85%|########4 | 2541/3000 [59:15<07:12,  1.06it/s, lr: 1.0e-04 loss: 2.985e-01]
latex_v1:  85%|########4 | 2541/3000 [59:15<07:12,  1.06it/s, lr: 1.0e-04 loss: 2.985e-01]
latex_v1:  85%|########4 | 2542/3000 [59:15<08:02,  1.05s/it, lr: 1.0e-04 loss: 2.985e-01]
latex_v1:  85%|########4 | 2542/3000 [59:15<08:02,  1.05s/it, lr: 1.0e-04 loss: 2.985e-01]
latex_v1:  85%|########4 | 2542/3000 [59:18<08:02,  1.05s/it, lr: 1.0e-04 loss: 3.181e-02]
latex_v1:  85%|########4 | 2542/3000 [59:18<08:02,  1.05s/it, lr: 1.0e-04 loss: 3.181e-02]
latex_v1:  85%|########4 | 2543/3000 [59:18<11:37,  1.53s/it, lr: 1.0e-04 loss: 3.181e-02]
latex_v1:  85%|########4 | 2543/3000 [59:18<11:37,  1.53s/it, lr: 1.0e-04 loss: 3.181e-02]
latex_v1:  85%|########4 | 2543/3000 [59:19<11:37,  1.53s/it, lr: 1.0e-04 loss: 5.152e-01]
latex_v1:  85%|########4 | 2543/3000 [59:19<11:37,  1.53s/it, lr: 1.0e-04 loss: 5.152e-01]
latex_v1:  85%|########4 | 2544/3000 [59:19<11:27,  1.51s/it, lr: 1.0e-04 loss: 5.152e-01]
latex_v1:  85%|########4 | 2544/3000 [59:19<11:27,  1.51s/it, lr: 1.0e-04 loss: 5.152e-01]
latex_v1:  85%|########4 | 2544/3000 [59:20<11:27,  1.51s/it, lr: 1.0e-04 loss: 3.265e-01]
latex_v1:  85%|########4 | 2544/3000 [59:20<11:27,  1.51s/it, lr: 1.0e-04 loss: 3.265e-01]
latex_v1:  85%|########4 | 2545/3000 [59:20<09:50,  1.30s/it, lr: 1.0e-04 loss: 3.265e-01]
latex_v1:  85%|########4 | 2545/3000 [59:20<09:50,  1.30s/it, lr: 1.0e-04 loss: 3.265e-01]
latex_v1:  85%|########4 | 2545/3000 [59:21<09:50,  1.30s/it, lr: 1.0e-04 loss: 2.181e-01]
latex_v1:  85%|########4 | 2545/3000 [59:21<09:50,  1.30s/it, lr: 1.0e-04 loss: 2.181e-01]
latex_v1:  85%|########4 | 2546/3000 [59:21<08:37,  1.14s/it, lr: 1.0e-04 loss: 2.181e-01]
latex_v1:  85%|########4 | 2546/3000 [59:21<08:37,  1.14s/it, lr: 1.0e-04 loss: 2.181e-01]
latex_v1:  85%|########4 | 2546/3000 [59:22<08:37,  1.14s/it, lr: 1.0e-04 loss: 5.985e-02]
latex_v1:  85%|########4 | 2546/3000 [59:22<08:37,  1.14s/it, lr: 1.0e-04 loss: 5.985e-02]
latex_v1:  85%|########4 | 2547/3000 [59:22<07:44,  1.03s/it, lr: 1.0e-04 loss: 5.985e-02]
latex_v1:  85%|########4 | 2547/3000 [59:22<07:44,  1.03s/it, lr: 1.0e-04 loss: 5.985e-02]
latex_v1:  85%|########4 | 2547/3000 [59:24<07:44,  1.03s/it, lr: 1.0e-04 loss: 1.928e-01]
latex_v1:  85%|########4 | 2547/3000 [59:24<07:44,  1.03s/it, lr: 1.0e-04 loss: 1.928e-01]
latex_v1:  85%|########4 | 2548/3000 [59:24<11:45,  1.56s/it, lr: 1.0e-04 loss: 1.928e-01]
latex_v1:  85%|########4 | 2548/3000 [59:24<11:45,  1.56s/it, lr: 1.0e-04 loss: 1.928e-01]
latex_v1:  85%|########4 | 2548/3000 [59:26<11:45,  1.56s/it, lr: 1.0e-04 loss: 1.751e-02]
latex_v1:  85%|########4 | 2548/3000 [59:26<11:45,  1.56s/it, lr: 1.0e-04 loss: 1.751e-02]
latex_v1:  85%|########4 | 2549/3000 [59:26<11:38,  1.55s/it, lr: 1.0e-04 loss: 1.751e-02]
latex_v1:  85%|########4 | 2549/3000 [59:26<11:38,  1.55s/it, lr: 1.0e-04 loss: 1.751e-02]
latex_v1:  85%|########4 | 2549/3000 [59:27<11:38,  1.55s/it, lr: 1.0e-04 loss: 1.814e-01]
latex_v1:  85%|########4 | 2549/3000 [59:27<11:38,  1.55s/it, lr: 1.0e-04 loss: 1.814e-01]
latex_v1:  85%|########5 | 2550/3000 [59:30<11:36,  1.55s/it, lr: 1.0e-04 loss: 1.978e-01]
latex_v1:  85%|########5 | 2550/3000 [59:30<11:36,  1.55s/it, lr: 1.0e-04 loss: 1.978e-01]
latex_v1:  85%|########5 | 2551/3000 [59:30<11:12,  1.50s/it, lr: 1.0e-04 loss: 1.978e-01]
latex_v1:  85%|########5 | 2551/3000 [59:30<11:12,  1.50s/it, lr: 1.0e-04 loss: 1.978e-01]
latex_v1:  85%|########5 | 2551/3000 [59:31<11:12,  1.50s/it, lr: 1.0e-04 loss: 3.721e-01]
latex_v1:  85%|########5 | 2551/3000 [59:31<11:12,  1.50s/it, lr: 1.0e-04 loss: 3.721e-01]
latex_v1:  85%|########5 | 2552/3000 [59:31<10:52,  1.46s/it, lr: 1.0e-04 loss: 3.721e-01]
latex_v1:  85%|########5 | 2552/3000 [59:31<10:52,  1.46s/it, lr: 1.0e-04 loss: 3.721e-01]
latex_v1:  85%|########5 | 2552/3000 [59:34<10:52,  1.46s/it, lr: 1.0e-04 loss: 5.511e-01]
latex_v1:  85%|########5 | 2552/3000 [59:34<10:52,  1.46s/it, lr: 1.0e-04 loss: 5.511e-01]
latex_v1:  85%|########5 | 2553/3000 [59:34<13:32,  1.82s/it, lr: 1.0e-04 loss: 5.511e-01]
latex_v1:  85%|########5 | 2553/3000 [59:34<13:32,  1.82s/it, lr: 1.0e-04 loss: 5.511e-01]
latex_v1:  85%|########5 | 2553/3000 [59:35<13:32,  1.82s/it, lr: 1.0e-04 loss: 1.691e-01]
latex_v1:  85%|########5 | 2553/3000 [59:35<13:32,  1.82s/it, lr: 1.0e-04 loss: 1.691e-01]
latex_v1:  85%|########5 | 2554/3000 [59:35<12:58,  1.75s/it, lr: 1.0e-04 loss: 1.691e-01]
latex_v1:  85%|########5 | 2554/3000 [59:35<12:58,  1.75s/it, lr: 1.0e-04 loss: 1.691e-01]
latex_v1:  85%|########5 | 2554/3000 [59:37<12:58,  1.75s/it, lr: 1.0e-04 loss: 4.619e-01]
latex_v1:  85%|########5 | 2554/3000 [59:37<12:58,  1.75s/it, lr: 1.0e-04 loss: 4.619e-01]
latex_v1:  85%|########5 | 2555/3000 [59:37<12:40,  1.71s/it, lr: 1.0e-04 loss: 4.619e-01]
latex_v1:  85%|########5 | 2555/3000 [59:37<12:40,  1.71s/it, lr: 1.0e-04 loss: 4.619e-01]
latex_v1:  85%|########5 | 2555/3000 [59:38<12:40,  1.71s/it, lr: 1.0e-04 loss: 6.411e-01]
latex_v1:  85%|########5 | 2555/3000 [59:38<12:40,  1.71s/it, lr: 1.0e-04 loss: 6.411e-01]
latex_v1:  85%|########5 | 2556/3000 [59:38<12:18,  1.66s/it, lr: 1.0e-04 loss: 6.411e-01]
latex_v1:  85%|########5 | 2556/3000 [59:38<12:18,  1.66s/it, lr: 1.0e-04 loss: 6.411e-01]
latex_v1:  85%|########5 | 2556/3000 [59:41<12:18,  1.66s/it, lr: 1.0e-04 loss: 1.011e-01]
latex_v1:  85%|########5 | 2556/3000 [59:41<12:18,  1.66s/it, lr: 1.0e-04 loss: 1.011e-01]
latex_v1:  85%|########5 | 2557/3000 [59:41<14:46,  2.00s/it, lr: 1.0e-04 loss: 1.011e-01]
latex_v1:  85%|########5 | 2557/3000 [59:41<14:46,  2.00s/it, lr: 1.0e-04 loss: 1.011e-01]
latex_v1:  85%|########5 | 2557/3000 [59:42<14:46,  2.00s/it, lr: 1.0e-04 loss: 5.400e-01]
latex_v1:  85%|########5 | 2557/3000 [59:42<14:46,  2.00s/it, lr: 1.0e-04 loss: 5.400e-01]
latex_v1:  85%|########5 | 2558/3000 [59:42<12:03,  1.64s/it, lr: 1.0e-04 loss: 5.400e-01]
latex_v1:  85%|########5 | 2558/3000 [59:42<12:03,  1.64s/it, lr: 1.0e-04 loss: 5.400e-01]
latex_v1:  85%|########5 | 2558/3000 [59:43<12:03,  1.64s/it, lr: 1.0e-04 loss: 1.155e-01]
latex_v1:  85%|########5 | 2558/3000 [59:43<12:03,  1.64s/it, lr: 1.0e-04 loss: 1.155e-01]
latex_v1:  85%|########5 | 2559/3000 [59:44<11:39,  1.59s/it, lr: 1.0e-04 loss: 1.155e-01]
latex_v1:  85%|########5 | 2559/3000 [59:44<11:39,  1.59s/it, lr: 1.0e-04 loss: 1.155e-01]
latex_v1:  85%|########5 | 2559/3000 [59:44<11:39,  1.59s/it, lr: 1.0e-04 loss: 5.669e-01]
latex_v1:  85%|########5 | 2559/3000 [59:44<11:39,  1.59s/it, lr: 1.0e-04 loss: 5.669e-01]
latex_v1:  85%|########5 | 2560/3000 [59:45<11:37,  1.59s/it, lr: 1.0e-04 loss: 2.183e-01]
latex_v1:  85%|########5 | 2560/3000 [59:45<11:37,  1.59s/it, lr: 1.0e-04 loss: 2.183e-01]
latex_v1:  85%|########5 | 2561/3000 [59:45<07:33,  1.03s/it, lr: 1.0e-04 loss: 2.183e-01]
latex_v1:  85%|########5 | 2561/3000 [59:45<07:33,  1.03s/it, lr: 1.0e-04 loss: 2.183e-01]
latex_v1:  85%|########5 | 2561/3000 [59:48<07:33,  1.03s/it, lr: 1.0e-04 loss: 6.549e-02]
latex_v1:  85%|########5 | 2561/3000 [59:48<07:33,  1.03s/it, lr: 1.0e-04 loss: 6.549e-02]
latex_v1:  85%|########5 | 2562/3000 [59:48<10:50,  1.49s/it, lr: 1.0e-04 loss: 6.549e-02]
latex_v1:  85%|########5 | 2562/3000 [59:48<10:50,  1.49s/it, lr: 1.0e-04 loss: 6.549e-02]
latex_v1:  85%|########5 | 2562/3000 [59:49<10:50,  1.49s/it, lr: 1.0e-04 loss: 5.060e-01]
latex_v1:  85%|########5 | 2562/3000 [59:49<10:50,  1.49s/it, lr: 1.0e-04 loss: 5.060e-01]
latex_v1:  85%|########5 | 2563/3000 [59:49<10:59,  1.51s/it, lr: 1.0e-04 loss: 5.060e-01]
latex_v1:  85%|########5 | 2563/3000 [59:49<10:59,  1.51s/it, lr: 1.0e-04 loss: 5.060e-01]
latex_v1:  85%|########5 | 2563/3000 [59:51<10:59,  1.51s/it, lr: 1.0e-04 loss: 8.126e-02]
latex_v1:  85%|########5 | 2563/3000 [59:51<10:59,  1.51s/it, lr: 1.0e-04 loss: 8.126e-02]
latex_v1:  85%|########5 | 2564/3000 [59:51<11:41,  1.61s/it, lr: 1.0e-04 loss: 8.126e-02]
latex_v1:  85%|########5 | 2564/3000 [59:51<11:41,  1.61s/it, lr: 1.0e-04 loss: 8.126e-02]
latex_v1:  85%|########5 | 2564/3000 [59:53<11:41,  1.61s/it, lr: 1.0e-04 loss: 1.408e-01]
latex_v1:  85%|########5 | 2564/3000 [59:53<11:41,  1.61s/it, lr: 1.0e-04 loss: 1.408e-01]
latex_v1:  86%|########5 | 2565/3000 [59:53<11:30,  1.59s/it, lr: 1.0e-04 loss: 1.408e-01]
latex_v1:  86%|########5 | 2565/3000 [59:53<11:30,  1.59s/it, lr: 1.0e-04 loss: 1.408e-01]
latex_v1:  86%|########5 | 2565/3000 [59:54<11:30,  1.59s/it, lr: 1.0e-04 loss: 3.754e-01]
latex_v1:  86%|########5 | 2565/3000 [59:54<11:30,  1.59s/it, lr: 1.0e-04 loss: 3.754e-01]
latex_v1:  86%|########5 | 2566/3000 [59:54<09:44,  1.35s/it, lr: 1.0e-04 loss: 3.754e-01]
latex_v1:  86%|########5 | 2566/3000 [59:54<09:44,  1.35s/it, lr: 1.0e-04 loss: 3.754e-01]
latex_v1:  86%|########5 | 2566/3000 [59:55<09:44,  1.35s/it, lr: 1.0e-04 loss: 5.600e-01]
latex_v1:  86%|########5 | 2566/3000 [59:55<09:44,  1.35s/it, lr: 1.0e-04 loss: 5.600e-01]
latex_v1:  86%|########5 | 2567/3000 [59:55<09:56,  1.38s/it, lr: 1.0e-04 loss: 5.600e-01]
latex_v1:  86%|########5 | 2567/3000 [59:55<09:56,  1.38s/it, lr: 1.0e-04 loss: 5.600e-01]
latex_v1:  86%|########5 | 2567/3000 [59:56<09:56,  1.38s/it, lr: 1.0e-04 loss: 3.654e-01]
latex_v1:  86%|########5 | 2567/3000 [59:56<09:56,  1.38s/it, lr: 1.0e-04 loss: 3.654e-01]
latex_v1:  86%|########5 | 2568/3000 [59:56<09:05,  1.26s/it, lr: 1.0e-04 loss: 3.654e-01]
latex_v1:  86%|########5 | 2568/3000 [59:56<09:05,  1.26s/it, lr: 1.0e-04 loss: 3.654e-01]
latex_v1:  86%|########5 | 2568/3000 [59:58<09:05,  1.26s/it, lr: 1.0e-04 loss: 1.538e-01]
latex_v1:  86%|########5 | 2568/3000 [59:58<09:05,  1.26s/it, lr: 1.0e-04 loss: 1.538e-01]
latex_v1:  86%|########5 | 2569/3000 [59:58<10:04,  1.40s/it, lr: 1.0e-04 loss: 1.538e-01]
latex_v1:  86%|########5 | 2569/3000 [59:58<10:04,  1.40s/it, lr: 1.0e-04 loss: 1.538e-01]
latex_v1:  86%|########5 | 2569/3000 [59:59<10:04,  1.40s/it, lr: 1.0e-04 loss: 7.516e-01]
latex_v1:  86%|########5 | 2569/3000 [59:59<10:04,  1.40s/it, lr: 1.0e-04 loss: 7.516e-01]
latex_v1:  86%|########5 | 2570/3000 [1:00:00<10:03,  1.40s/it, lr: 1.0e-04 loss: 3.879e-01]
latex_v1:  86%|########5 | 2570/3000 [1:00:00<10:03,  1.40s/it, lr: 1.0e-04 loss: 3.879e-01]
latex_v1:  86%|########5 | 2571/3000 [1:00:00<07:47,  1.09s/it, lr: 1.0e-04 loss: 3.879e-01]
latex_v1:  86%|########5 | 2571/3000 [1:00:00<07:47,  1.09s/it, lr: 1.0e-04 loss: 3.879e-01]
latex_v1:  86%|########5 | 2571/3000 [1:00:01<07:47,  1.09s/it, lr: 1.0e-04 loss: 5.282e-01]
latex_v1:  86%|########5 | 2571/3000 [1:00:01<07:47,  1.09s/it, lr: 1.0e-04 loss: 5.282e-01]
latex_v1:  86%|########5 | 2572/3000 [1:00:01<08:23,  1.18s/it, lr: 1.0e-04 loss: 5.282e-01]
latex_v1:  86%|########5 | 2572/3000 [1:00:01<08:23,  1.18s/it, lr: 1.0e-04 loss: 5.282e-01]
latex_v1:  86%|########5 | 2572/3000 [1:00:04<08:23,  1.18s/it, lr: 1.0e-04 loss: 3.880e-01]
latex_v1:  86%|########5 | 2572/3000 [1:00:04<08:23,  1.18s/it, lr: 1.0e-04 loss: 3.880e-01]
latex_v1:  86%|########5 | 2573/3000 [1:00:04<11:05,  1.56s/it, lr: 1.0e-04 loss: 3.880e-01]
latex_v1:  86%|########5 | 2573/3000 [1:00:04<11:05,  1.56s/it, lr: 1.0e-04 loss: 3.880e-01]
latex_v1:  86%|########5 | 2573/3000 [1:00:05<11:05,  1.56s/it, lr: 1.0e-04 loss: 6.804e-01]
latex_v1:  86%|########5 | 2573/3000 [1:00:05<11:05,  1.56s/it, lr: 1.0e-04 loss: 6.804e-01]
latex_v1:  86%|########5 | 2574/3000 [1:00:05<10:47,  1.52s/it, lr: 1.0e-04 loss: 6.804e-01]
latex_v1:  86%|########5 | 2574/3000 [1:00:05<10:47,  1.52s/it, lr: 1.0e-04 loss: 6.804e-01]
latex_v1:  86%|########5 | 2574/3000 [1:00:07<10:47,  1.52s/it, lr: 1.0e-04 loss: 6.754e-01]
latex_v1:  86%|########5 | 2574/3000 [1:00:07<10:47,  1.52s/it, lr: 1.0e-04 loss: 6.754e-01]
latex_v1:  86%|########5 | 2575/3000 [1:00:07<10:06,  1.43s/it, lr: 1.0e-04 loss: 6.754e-01]
latex_v1:  86%|########5 | 2575/3000 [1:00:07<10:06,  1.43s/it, lr: 1.0e-04 loss: 6.754e-01]
latex_v1:  86%|########5 | 2575/3000 [1:00:08<10:06,  1.43s/it, lr: 1.0e-04 loss: 5.930e-01]
latex_v1:  86%|########5 | 2575/3000 [1:00:08<10:06,  1.43s/it, lr: 1.0e-04 loss: 5.930e-01]
latex_v1:  86%|########5 | 2576/3000 [1:00:08<09:19,  1.32s/it, lr: 1.0e-04 loss: 5.930e-01]
latex_v1:  86%|########5 | 2576/3000 [1:00:08<09:19,  1.32s/it, lr: 1.0e-04 loss: 5.930e-01]
latex_v1:  86%|########5 | 2576/3000 [1:00:09<09:19,  1.32s/it, lr: 1.0e-04 loss: 1.156e-01]
latex_v1:  86%|########5 | 2576/3000 [1:00:09<09:19,  1.32s/it, lr: 1.0e-04 loss: 1.156e-01]
latex_v1:  86%|########5 | 2577/3000 [1:00:09<09:44,  1.38s/it, lr: 1.0e-04 loss: 1.156e-01]
latex_v1:  86%|########5 | 2577/3000 [1:00:09<09:44,  1.38s/it, lr: 1.0e-04 loss: 1.156e-01]
latex_v1:  86%|########5 | 2577/3000 [1:00:11<09:44,  1.38s/it, lr: 1.0e-04 loss: 5.640e-01]
latex_v1:  86%|########5 | 2577/3000 [1:00:11<09:44,  1.38s/it, lr: 1.0e-04 loss: 5.640e-01]
latex_v1:  86%|########5 | 2578/3000 [1:00:11<10:43,  1.52s/it, lr: 1.0e-04 loss: 5.640e-01]
latex_v1:  86%|########5 | 2578/3000 [1:00:11<10:43,  1.52s/it, lr: 1.0e-04 loss: 5.640e-01]
latex_v1:  86%|########5 | 2578/3000 [1:00:13<10:43,  1.52s/it, lr: 1.0e-04 loss: 5.648e-01]
latex_v1:  86%|########5 | 2578/3000 [1:00:13<10:43,  1.52s/it, lr: 1.0e-04 loss: 5.648e-01]
latex_v1:  86%|########5 | 2579/3000 [1:00:13<10:28,  1.49s/it, lr: 1.0e-04 loss: 5.648e-01]
latex_v1:  86%|########5 | 2579/3000 [1:00:13<10:28,  1.49s/it, lr: 1.0e-04 loss: 5.648e-01]
latex_v1:  86%|########5 | 2579/3000 [1:00:13<10:28,  1.49s/it, lr: 1.0e-04 loss: 3.054e-01]
latex_v1:  86%|########5 | 2579/3000 [1:00:13<10:28,  1.49s/it, lr: 1.0e-04 loss: 3.054e-01]
latex_v1:  86%|########6 | 2580/3000 [1:00:14<10:26,  1.49s/it, lr: 1.0e-04 loss: 4.084e-01]
latex_v1:  86%|########6 | 2580/3000 [1:00:14<10:26,  1.49s/it, lr: 1.0e-04 loss: 4.084e-01]
latex_v1:  86%|########6 | 2581/3000 [1:00:14<07:11,  1.03s/it, lr: 1.0e-04 loss: 4.084e-01]
latex_v1:  86%|########6 | 2581/3000 [1:00:14<07:11,  1.03s/it, lr: 1.0e-04 loss: 4.084e-01]
latex_v1:  86%|########6 | 2581/3000 [1:00:16<07:11,  1.03s/it, lr: 1.0e-04 loss: 1.430e-01]
latex_v1:  86%|########6 | 2581/3000 [1:00:16<07:11,  1.03s/it, lr: 1.0e-04 loss: 1.430e-01]
latex_v1:  86%|########6 | 2582/3000 [1:00:16<07:37,  1.10s/it, lr: 1.0e-04 loss: 1.430e-01]
latex_v1:  86%|########6 | 2582/3000 [1:00:16<07:37,  1.10s/it, lr: 1.0e-04 loss: 1.430e-01]
latex_v1:  86%|########6 | 2582/3000 [1:00:17<07:37,  1.10s/it, lr: 1.0e-04 loss: 2.957e-01]
latex_v1:  86%|########6 | 2582/3000 [1:00:17<07:37,  1.10s/it, lr: 1.0e-04 loss: 2.957e-01]
latex_v1:  86%|########6 | 2583/3000 [1:00:17<08:20,  1.20s/it, lr: 1.0e-04 loss: 2.957e-01]
latex_v1:  86%|########6 | 2583/3000 [1:00:17<08:20,  1.20s/it, lr: 1.0e-04 loss: 2.957e-01]
latex_v1:  86%|########6 | 2583/3000 [1:00:19<08:20,  1.20s/it, lr: 1.0e-04 loss: 1.164e-01]
latex_v1:  86%|########6 | 2583/3000 [1:00:19<08:20,  1.20s/it, lr: 1.0e-04 loss: 1.164e-01]
latex_v1:  86%|########6 | 2584/3000 [1:00:19<10:10,  1.47s/it, lr: 1.0e-04 loss: 1.164e-01]
latex_v1:  86%|########6 | 2584/3000 [1:00:19<10:10,  1.47s/it, lr: 1.0e-04 loss: 1.164e-01]
latex_v1:  86%|########6 | 2584/3000 [1:00:21<10:10,  1.47s/it, lr: 1.0e-04 loss: 3.217e-01]
latex_v1:  86%|########6 | 2584/3000 [1:00:21<10:10,  1.47s/it, lr: 1.0e-04 loss: 3.217e-01]
latex_v1:  86%|########6 | 2585/3000 [1:00:21<10:55,  1.58s/it, lr: 1.0e-04 loss: 3.217e-01]
latex_v1:  86%|########6 | 2585/3000 [1:00:21<10:55,  1.58s/it, lr: 1.0e-04 loss: 3.217e-01]
latex_v1:  86%|########6 | 2585/3000 [1:00:22<10:55,  1.58s/it, lr: 1.0e-04 loss: 4.859e-01]
latex_v1:  86%|########6 | 2585/3000 [1:00:22<10:55,  1.58s/it, lr: 1.0e-04 loss: 4.859e-01]
latex_v1:  86%|########6 | 2586/3000 [1:00:22<09:40,  1.40s/it, lr: 1.0e-04 loss: 4.859e-01]
latex_v1:  86%|########6 | 2586/3000 [1:00:22<09:40,  1.40s/it, lr: 1.0e-04 loss: 4.859e-01]
latex_v1:  86%|########6 | 2586/3000 [1:00:23<09:40,  1.40s/it, lr: 1.0e-04 loss: 3.698e-01]
latex_v1:  86%|########6 | 2586/3000 [1:00:23<09:40,  1.40s/it, lr: 1.0e-04 loss: 3.698e-01]
latex_v1:  86%|########6 | 2587/3000 [1:00:23<08:22,  1.22s/it, lr: 1.0e-04 loss: 3.698e-01]
latex_v1:  86%|########6 | 2587/3000 [1:00:23<08:22,  1.22s/it, lr: 1.0e-04 loss: 3.698e-01]
latex_v1:  86%|########6 | 2587/3000 [1:00:25<08:22,  1.22s/it, lr: 1.0e-04 loss: 6.580e-02]
latex_v1:  86%|########6 | 2587/3000 [1:00:25<08:22,  1.22s/it, lr: 1.0e-04 loss: 6.580e-02]
latex_v1:  86%|########6 | 2588/3000 [1:00:25<09:39,  1.41s/it, lr: 1.0e-04 loss: 6.580e-02]
latex_v1:  86%|########6 | 2588/3000 [1:00:25<09:39,  1.41s/it, lr: 1.0e-04 loss: 6.580e-02]
latex_v1:  86%|########6 | 2588/3000 [1:00:26<09:39,  1.41s/it, lr: 1.0e-04 loss: 1.392e-01]
latex_v1:  86%|########6 | 2588/3000 [1:00:26<09:39,  1.41s/it, lr: 1.0e-04 loss: 1.392e-01]
latex_v1:  86%|########6 | 2589/3000 [1:00:26<09:39,  1.41s/it, lr: 1.0e-04 loss: 1.392e-01]
latex_v1:  86%|########6 | 2589/3000 [1:00:26<09:39,  1.41s/it, lr: 1.0e-04 loss: 1.392e-01]
latex_v1:  86%|########6 | 2589/3000 [1:00:28<09:39,  1.41s/it, lr: 1.0e-04 loss: 7.562e-02]
latex_v1:  86%|########6 | 2589/3000 [1:00:28<09:39,  1.41s/it, lr: 1.0e-04 loss: 7.562e-02]
latex_v1:  86%|########6 | 2590/3000 [1:00:28<09:38,  1.41s/it, lr: 1.0e-04 loss: 1.725e-01]
latex_v1:  86%|########6 | 2590/3000 [1:00:28<09:38,  1.41s/it, lr: 1.0e-04 loss: 1.725e-01]
latex_v1:  86%|########6 | 2591/3000 [1:00:28<06:22,  1.07it/s, lr: 1.0e-04 loss: 1.725e-01]
latex_v1:  86%|########6 | 2591/3000 [1:00:28<06:22,  1.07it/s, lr: 1.0e-04 loss: 1.725e-01]
latex_v1:  86%|########6 | 2591/3000 [1:00:29<06:22,  1.07it/s, lr: 1.0e-04 loss: 5.968e-01]
latex_v1:  86%|########6 | 2591/3000 [1:00:29<06:22,  1.07it/s, lr: 1.0e-04 loss: 5.968e-01]
latex_v1:  86%|########6 | 2592/3000 [1:00:29<06:03,  1.12it/s, lr: 1.0e-04 loss: 5.968e-01]
latex_v1:  86%|########6 | 2592/3000 [1:00:29<06:03,  1.12it/s, lr: 1.0e-04 loss: 5.968e-01]
latex_v1:  86%|########6 | 2592/3000 [1:00:31<06:03,  1.12it/s, lr: 1.0e-04 loss: 5.608e-01]
latex_v1:  86%|########6 | 2592/3000 [1:00:31<06:03,  1.12it/s, lr: 1.0e-04 loss: 5.608e-01]
latex_v1:  86%|########6 | 2593/3000 [1:00:31<07:11,  1.06s/it, lr: 1.0e-04 loss: 5.608e-01]
latex_v1:  86%|########6 | 2593/3000 [1:00:31<07:11,  1.06s/it, lr: 1.0e-04 loss: 5.608e-01]
latex_v1:  86%|########6 | 2593/3000 [1:00:31<07:11,  1.06s/it, lr: 1.0e-04 loss: 1.497e-01]
latex_v1:  86%|########6 | 2593/3000 [1:00:31<07:11,  1.06s/it, lr: 1.0e-04 loss: 1.497e-01]
latex_v1:  86%|########6 | 2594/3000 [1:00:31<06:35,  1.03it/s, lr: 1.0e-04 loss: 1.497e-01]
latex_v1:  86%|########6 | 2594/3000 [1:00:31<06:35,  1.03it/s, lr: 1.0e-04 loss: 1.497e-01]
latex_v1:  86%|########6 | 2594/3000 [1:00:32<06:35,  1.03it/s, lr: 1.0e-04 loss: 2.162e-01]
latex_v1:  86%|########6 | 2594/3000 [1:00:32<06:35,  1.03it/s, lr: 1.0e-04 loss: 2.162e-01]
latex_v1:  86%|########6 | 2595/3000 [1:00:32<06:06,  1.10it/s, lr: 1.0e-04 loss: 2.162e-01]
latex_v1:  86%|########6 | 2595/3000 [1:00:32<06:06,  1.10it/s, lr: 1.0e-04 loss: 2.162e-01]
latex_v1:  86%|########6 | 2595/3000 [1:00:33<06:06,  1.10it/s, lr: 1.0e-04 loss: 1.969e-01]
latex_v1:  86%|########6 | 2595/3000 [1:00:33<06:06,  1.10it/s, lr: 1.0e-04 loss: 1.969e-01]
latex_v1:  87%|########6 | 2596/3000 [1:00:33<05:45,  1.17it/s, lr: 1.0e-04 loss: 1.969e-01]
latex_v1:  87%|########6 | 2596/3000 [1:00:33<05:45,  1.17it/s, lr: 1.0e-04 loss: 1.969e-01]
latex_v1:  87%|########6 | 2596/3000 [1:00:35<05:45,  1.17it/s, lr: 1.0e-04 loss: 5.486e-01]
latex_v1:  87%|########6 | 2596/3000 [1:00:35<05:45,  1.17it/s, lr: 1.0e-04 loss: 5.486e-01]
latex_v1:  87%|########6 | 2597/3000 [1:00:35<07:37,  1.13s/it, lr: 1.0e-04 loss: 5.486e-01]
latex_v1:  87%|########6 | 2597/3000 [1:00:35<07:37,  1.13s/it, lr: 1.0e-04 loss: 5.486e-01]
latex_v1:  87%|########6 | 2597/3000 [1:00:35<07:37,  1.13s/it, lr: 1.0e-04 loss: 3.443e-01]
latex_v1:  87%|########6 | 2597/3000 [1:00:35<07:37,  1.13s/it, lr: 1.0e-04 loss: 3.443e-01]
latex_v1:  87%|########6 | 2598/3000 [1:00:35<06:50,  1.02s/it, lr: 1.0e-04 loss: 3.443e-01]
latex_v1:  87%|########6 | 2598/3000 [1:00:35<06:50,  1.02s/it, lr: 1.0e-04 loss: 3.443e-01]
latex_v1:  87%|########6 | 2598/3000 [1:00:36<06:50,  1.02s/it, lr: 1.0e-04 loss: 8.397e-02]
latex_v1:  87%|########6 | 2598/3000 [1:00:36<06:50,  1.02s/it, lr: 1.0e-04 loss: 8.397e-02]
latex_v1:  87%|########6 | 2599/3000 [1:00:36<06:20,  1.05it/s, lr: 1.0e-04 loss: 8.397e-02]
latex_v1:  87%|########6 | 2599/3000 [1:00:36<06:20,  1.05it/s, lr: 1.0e-04 loss: 8.397e-02]
latex_v1:  87%|########6 | 2599/3000 [1:00:38<06:20,  1.05it/s, lr: 1.0e-04 loss: 1.792e-01]
latex_v1:  87%|########6 | 2599/3000 [1:00:38<06:20,  1.05it/s, lr: 1.0e-04 loss: 1.792e-01]
latex_v1:  87%|########6 | 2600/3000 [1:00:38<06:19,  1.05it/s, lr: 1.0e-04 loss: 4.015e-01]
latex_v1:  87%|########6 | 2600/3000 [1:00:38<06:19,  1.05it/s, lr: 1.0e-04 loss: 4.015e-01]
latex_v1:  87%|########6 | 2601/3000 [1:00:38<04:36,  1.44it/s, lr: 1.0e-04 loss: 4.015e-01]
latex_v1:  87%|########6 | 2601/3000 [1:00:38<04:36,  1.44it/s, lr: 1.0e-04 loss: 4.015e-01]
latex_v1:  87%|########6 | 2601/3000 [1:00:40<04:36,  1.44it/s, lr: 1.0e-04 loss: 1.093e-01]
latex_v1:  87%|########6 | 2601/3000 [1:00:40<04:36,  1.44it/s, lr: 1.0e-04 loss: 1.093e-01]
latex_v1:  87%|########6 | 2602/3000 [1:00:40<05:45,  1.15it/s, lr: 1.0e-04 loss: 1.093e-01]
latex_v1:  87%|########6 | 2602/3000 [1:00:40<05:45,  1.15it/s, lr: 1.0e-04 loss: 1.093e-01]
latex_v1:  87%|########6 | 2602/3000 [1:00:41<05:45,  1.15it/s, lr: 1.0e-04 loss: 8.754e-01]
latex_v1:  87%|########6 | 2602/3000 [1:00:41<05:45,  1.15it/s, lr: 1.0e-04 loss: 8.754e-01]
latex_v1:  87%|########6 | 2603/3000 [1:00:41<06:14,  1.06it/s, lr: 1.0e-04 loss: 8.754e-01]
latex_v1:  87%|########6 | 2603/3000 [1:00:41<06:14,  1.06it/s, lr: 1.0e-04 loss: 8.754e-01]
latex_v1:  87%|########6 | 2603/3000 [1:00:43<06:14,  1.06it/s, lr: 1.0e-04 loss: 6.443e-01]
latex_v1:  87%|########6 | 2603/3000 [1:00:43<06:14,  1.06it/s, lr: 1.0e-04 loss: 6.443e-01]
latex_v1:  87%|########6 | 2604/3000 [1:00:43<06:42,  1.02s/it, lr: 1.0e-04 loss: 6.443e-01]
latex_v1:  87%|########6 | 2604/3000 [1:00:43<06:42,  1.02s/it, lr: 1.0e-04 loss: 6.443e-01]
latex_v1:  87%|########6 | 2604/3000 [1:00:44<06:42,  1.02s/it, lr: 1.0e-04 loss: 5.703e-02]
latex_v1:  87%|########6 | 2604/3000 [1:00:44<06:42,  1.02s/it, lr: 1.0e-04 loss: 5.703e-02]
latex_v1:  87%|########6 | 2605/3000 [1:00:44<07:28,  1.14s/it, lr: 1.0e-04 loss: 5.703e-02]
latex_v1:  87%|########6 | 2605/3000 [1:00:44<07:28,  1.14s/it, lr: 1.0e-04 loss: 5.703e-02]
latex_v1:  87%|########6 | 2605/3000 [1:00:45<07:28,  1.14s/it, lr: 1.0e-04 loss: 6.100e-01]
latex_v1:  87%|########6 | 2605/3000 [1:00:45<07:28,  1.14s/it, lr: 1.0e-04 loss: 6.100e-01]
latex_v1:  87%|########6 | 2606/3000 [1:00:45<06:43,  1.02s/it, lr: 1.0e-04 loss: 6.100e-01]
latex_v1:  87%|########6 | 2606/3000 [1:00:45<06:43,  1.02s/it, lr: 1.0e-04 loss: 6.100e-01]
latex_v1:  87%|########6 | 2606/3000 [1:00:45<06:43,  1.02s/it, lr: 1.0e-04 loss: 2.803e-01]
latex_v1:  87%|########6 | 2606/3000 [1:00:45<06:43,  1.02s/it, lr: 1.0e-04 loss: 2.803e-01]
latex_v1:  87%|########6 | 2607/3000 [1:00:45<06:09,  1.06it/s, lr: 1.0e-04 loss: 2.803e-01]
latex_v1:  87%|########6 | 2607/3000 [1:00:45<06:09,  1.06it/s, lr: 1.0e-04 loss: 2.803e-01]
latex_v1:  87%|########6 | 2607/3000 [1:00:47<06:09,  1.06it/s, lr: 1.0e-04 loss: 6.656e-01]
latex_v1:  87%|########6 | 2607/3000 [1:00:47<06:09,  1.06it/s, lr: 1.0e-04 loss: 6.656e-01]
latex_v1:  87%|########6 | 2608/3000 [1:00:47<07:55,  1.21s/it, lr: 1.0e-04 loss: 6.656e-01]
latex_v1:  87%|########6 | 2608/3000 [1:00:47<07:55,  1.21s/it, lr: 1.0e-04 loss: 6.656e-01]
latex_v1:  87%|########6 | 2608/3000 [1:00:49<07:55,  1.21s/it, lr: 1.0e-04 loss: 6.677e-01]
latex_v1:  87%|########6 | 2608/3000 [1:00:49<07:55,  1.21s/it, lr: 1.0e-04 loss: 6.677e-01]
latex_v1:  87%|########6 | 2609/3000 [1:00:49<08:30,  1.31s/it, lr: 1.0e-04 loss: 6.677e-01]
latex_v1:  87%|########6 | 2609/3000 [1:00:49<08:30,  1.31s/it, lr: 1.0e-04 loss: 6.677e-01]
latex_v1:  87%|########6 | 2609/3000 [1:00:50<08:30,  1.31s/it, lr: 1.0e-04 loss: 4.461e-02]
latex_v1:  87%|########6 | 2609/3000 [1:00:50<08:30,  1.31s/it, lr: 1.0e-04 loss: 4.461e-02]
latex_v1:  87%|########7 | 2610/3000 [1:00:51<08:29,  1.31s/it, lr: 1.0e-04 loss: 1.437e-01]
latex_v1:  87%|########7 | 2610/3000 [1:00:51<08:29,  1.31s/it, lr: 1.0e-04 loss: 1.437e-01]
latex_v1:  87%|########7 | 2611/3000 [1:00:51<06:43,  1.04s/it, lr: 1.0e-04 loss: 1.437e-01]
latex_v1:  87%|########7 | 2611/3000 [1:00:51<06:43,  1.04s/it, lr: 1.0e-04 loss: 1.437e-01]
latex_v1:  87%|########7 | 2611/3000 [1:00:53<06:43,  1.04s/it, lr: 1.0e-04 loss: 2.435e-01]
latex_v1:  87%|########7 | 2611/3000 [1:00:53<06:43,  1.04s/it, lr: 1.0e-04 loss: 2.435e-01]
latex_v1:  87%|########7 | 2612/3000 [1:00:53<07:19,  1.13s/it, lr: 1.0e-04 loss: 2.435e-01]
latex_v1:  87%|########7 | 2612/3000 [1:00:53<07:19,  1.13s/it, lr: 1.0e-04 loss: 2.435e-01]
latex_v1:  87%|########7 | 2612/3000 [1:00:55<07:19,  1.13s/it, lr: 1.0e-04 loss: 4.599e-01]
latex_v1:  87%|########7 | 2612/3000 [1:00:55<07:19,  1.13s/it, lr: 1.0e-04 loss: 4.599e-01]
latex_v1:  87%|########7 | 2613/3000 [1:00:55<08:28,  1.31s/it, lr: 1.0e-04 loss: 4.599e-01]
latex_v1:  87%|########7 | 2613/3000 [1:00:55<08:28,  1.31s/it, lr: 1.0e-04 loss: 4.599e-01]
latex_v1:  87%|########7 | 2613/3000 [1:00:55<08:28,  1.31s/it, lr: 1.0e-04 loss: 5.408e-01]
latex_v1:  87%|########7 | 2613/3000 [1:00:55<08:28,  1.31s/it, lr: 1.0e-04 loss: 5.408e-01]
latex_v1:  87%|########7 | 2614/3000 [1:00:55<07:27,  1.16s/it, lr: 1.0e-04 loss: 5.408e-01]
latex_v1:  87%|########7 | 2614/3000 [1:00:55<07:27,  1.16s/it, lr: 1.0e-04 loss: 5.408e-01]
latex_v1:  87%|########7 | 2614/3000 [1:00:56<07:27,  1.16s/it, lr: 1.0e-04 loss: 2.408e-01]
latex_v1:  87%|########7 | 2614/3000 [1:00:56<07:27,  1.16s/it, lr: 1.0e-04 loss: 2.408e-01]
latex_v1:  87%|########7 | 2615/3000 [1:00:56<06:39,  1.04s/it, lr: 1.0e-04 loss: 2.408e-01]
latex_v1:  87%|########7 | 2615/3000 [1:00:56<06:39,  1.04s/it, lr: 1.0e-04 loss: 2.408e-01]
latex_v1:  87%|########7 | 2615/3000 [1:00:57<06:39,  1.04s/it, lr: 1.0e-04 loss: 8.223e-02]
latex_v1:  87%|########7 | 2615/3000 [1:00:57<06:39,  1.04s/it, lr: 1.0e-04 loss: 8.223e-02]
latex_v1:  87%|########7 | 2616/3000 [1:00:57<06:06,  1.05it/s, lr: 1.0e-04 loss: 8.223e-02]
latex_v1:  87%|########7 | 2616/3000 [1:00:57<06:06,  1.05it/s, lr: 1.0e-04 loss: 8.223e-02]
latex_v1:  87%|########7 | 2616/3000 [1:00:58<06:06,  1.05it/s, lr: 1.0e-04 loss: 3.451e-01]
latex_v1:  87%|########7 | 2616/3000 [1:00:58<06:06,  1.05it/s, lr: 1.0e-04 loss: 3.451e-01]
latex_v1:  87%|########7 | 2617/3000 [1:00:58<06:50,  1.07s/it, lr: 1.0e-04 loss: 3.451e-01]
latex_v1:  87%|########7 | 2617/3000 [1:00:58<06:50,  1.07s/it, lr: 1.0e-04 loss: 3.451e-01]
latex_v1:  87%|########7 | 2617/3000 [1:01:00<06:50,  1.07s/it, lr: 1.0e-04 loss: 3.896e-01]
latex_v1:  87%|########7 | 2617/3000 [1:01:00<06:50,  1.07s/it, lr: 1.0e-04 loss: 3.896e-01]
latex_v1:  87%|########7 | 2618/3000 [1:01:00<07:16,  1.14s/it, lr: 1.0e-04 loss: 3.896e-01]
latex_v1:  87%|########7 | 2618/3000 [1:01:00<07:16,  1.14s/it, lr: 1.0e-04 loss: 3.896e-01]
latex_v1:  87%|########7 | 2618/3000 [1:01:01<07:16,  1.14s/it, lr: 1.0e-04 loss: 5.084e-01]
latex_v1:  87%|########7 | 2618/3000 [1:01:01<07:16,  1.14s/it, lr: 1.0e-04 loss: 5.084e-01]
latex_v1:  87%|########7 | 2619/3000 [1:01:01<07:58,  1.26s/it, lr: 1.0e-04 loss: 5.084e-01]
latex_v1:  87%|########7 | 2619/3000 [1:01:01<07:58,  1.26s/it, lr: 1.0e-04 loss: 5.084e-01]
latex_v1:  87%|########7 | 2619/3000 [1:01:02<07:58,  1.26s/it, lr: 1.0e-04 loss: 3.786e-02]
latex_v1:  87%|########7 | 2619/3000 [1:01:02<07:58,  1.26s/it, lr: 1.0e-04 loss: 3.786e-02]
latex_v1:  87%|########7 | 2620/3000 [1:01:03<07:57,  1.26s/it, lr: 1.0e-04 loss: 1.509e-01]
latex_v1:  87%|########7 | 2620/3000 [1:01:03<07:57,  1.26s/it, lr: 1.0e-04 loss: 1.509e-01]
latex_v1:  87%|########7 | 2621/3000 [1:01:03<05:23,  1.17it/s, lr: 1.0e-04 loss: 1.509e-01]
latex_v1:  87%|########7 | 2621/3000 [1:01:03<05:23,  1.17it/s, lr: 1.0e-04 loss: 1.509e-01]
latex_v1:  87%|########7 | 2621/3000 [1:01:03<05:23,  1.17it/s, lr: 1.0e-04 loss: 2.956e-01]
latex_v1:  87%|########7 | 2621/3000 [1:01:03<05:23,  1.17it/s, lr: 1.0e-04 loss: 2.956e-01]
latex_v1:  87%|########7 | 2622/3000 [1:01:03<05:12,  1.21it/s, lr: 1.0e-04 loss: 2.956e-01]
latex_v1:  87%|########7 | 2622/3000 [1:01:03<05:12,  1.21it/s, lr: 1.0e-04 loss: 2.956e-01]
latex_v1:  87%|########7 | 2622/3000 [1:01:06<05:12,  1.21it/s, lr: 1.0e-04 loss: 5.948e-01]
latex_v1:  87%|########7 | 2622/3000 [1:01:06<05:12,  1.21it/s, lr: 1.0e-04 loss: 5.948e-01]
latex_v1:  87%|########7 | 2623/3000 [1:01:06<08:23,  1.34s/it, lr: 1.0e-04 loss: 5.948e-01]
latex_v1:  87%|########7 | 2623/3000 [1:01:06<08:23,  1.34s/it, lr: 1.0e-04 loss: 5.948e-01]
latex_v1:  87%|########7 | 2623/3000 [1:01:08<08:23,  1.34s/it, lr: 1.0e-04 loss: 2.977e-01]
latex_v1:  87%|########7 | 2623/3000 [1:01:08<08:23,  1.34s/it, lr: 1.0e-04 loss: 2.977e-01]
latex_v1:  87%|########7 | 2624/3000 [1:01:08<08:41,  1.39s/it, lr: 1.0e-04 loss: 2.977e-01]
latex_v1:  87%|########7 | 2624/3000 [1:01:08<08:41,  1.39s/it, lr: 1.0e-04 loss: 2.977e-01]
latex_v1:  87%|########7 | 2624/3000 [1:01:08<08:41,  1.39s/it, lr: 1.0e-04 loss: 3.446e-01]
latex_v1:  87%|########7 | 2624/3000 [1:01:08<08:41,  1.39s/it, lr: 1.0e-04 loss: 3.446e-01]
latex_v1:  88%|########7 | 2625/3000 [1:01:08<07:34,  1.21s/it, lr: 1.0e-04 loss: 3.446e-01]
latex_v1:  88%|########7 | 2625/3000 [1:01:08<07:34,  1.21s/it, lr: 1.0e-04 loss: 3.446e-01]
latex_v1:  88%|########7 | 2625/3000 [1:01:09<07:34,  1.21s/it, lr: 1.0e-04 loss: 4.392e-01]
latex_v1:  88%|########7 | 2625/3000 [1:01:09<07:34,  1.21s/it, lr: 1.0e-04 loss: 4.392e-01]
latex_v1:  88%|########7 | 2626/3000 [1:01:09<06:45,  1.09s/it, lr: 1.0e-04 loss: 4.392e-01]
latex_v1:  88%|########7 | 2626/3000 [1:01:09<06:45,  1.09s/it, lr: 1.0e-04 loss: 4.392e-01]
latex_v1:  88%|########7 | 2626/3000 [1:01:12<06:45,  1.09s/it, lr: 1.0e-04 loss: 3.756e-02]
latex_v1:  88%|########7 | 2626/3000 [1:01:12<06:45,  1.09s/it, lr: 1.0e-04 loss: 3.756e-02]
latex_v1:  88%|########7 | 2627/3000 [1:01:12<09:31,  1.53s/it, lr: 1.0e-04 loss: 3.756e-02]
latex_v1:  88%|########7 | 2627/3000 [1:01:12<09:31,  1.53s/it, lr: 1.0e-04 loss: 3.756e-02]
latex_v1:  88%|########7 | 2627/3000 [1:01:15<09:31,  1.53s/it, lr: 1.0e-04 loss: 6.792e-01]
latex_v1:  88%|########7 | 2627/3000 [1:01:15<09:31,  1.53s/it, lr: 1.0e-04 loss: 6.792e-01]
latex_v1:  88%|########7 | 2628/3000 [1:01:15<11:53,  1.92s/it, lr: 1.0e-04 loss: 6.792e-01]
latex_v1:  88%|########7 | 2628/3000 [1:01:15<11:53,  1.92s/it, lr: 1.0e-04 loss: 6.792e-01]
latex_v1:  88%|########7 | 2628/3000 [1:01:15<11:53,  1.92s/it, lr: 1.0e-04 loss: 6.653e-01]
latex_v1:  88%|########7 | 2628/3000 [1:01:15<11:53,  1.92s/it, lr: 1.0e-04 loss: 6.653e-01]
latex_v1:  88%|########7 | 2629/3000 [1:01:15<09:43,  1.57s/it, lr: 1.0e-04 loss: 6.653e-01]
latex_v1:  88%|########7 | 2629/3000 [1:01:15<09:43,  1.57s/it, lr: 1.0e-04 loss: 6.653e-01]
latex_v1:  88%|########7 | 2629/3000 [1:01:17<09:43,  1.57s/it, lr: 1.0e-04 loss: 3.216e-01]
latex_v1:  88%|########7 | 2629/3000 [1:01:17<09:43,  1.57s/it, lr: 1.0e-04 loss: 3.216e-01]
latex_v1:  88%|########7 | 2630/3000 [1:01:18<09:41,  1.57s/it, lr: 1.0e-04 loss: 4.562e-01]
latex_v1:  88%|########7 | 2630/3000 [1:01:18<09:41,  1.57s/it, lr: 1.0e-04 loss: 4.562e-01]
latex_v1:  88%|########7 | 2631/3000 [1:01:18<06:44,  1.10s/it, lr: 1.0e-04 loss: 4.562e-01]
latex_v1:  88%|########7 | 2631/3000 [1:01:18<06:44,  1.10s/it, lr: 1.0e-04 loss: 4.562e-01]
latex_v1:  88%|########7 | 2631/3000 [1:01:19<06:44,  1.10s/it, lr: 1.0e-04 loss: 1.826e-01]
latex_v1:  88%|########7 | 2631/3000 [1:01:19<06:44,  1.10s/it, lr: 1.0e-04 loss: 1.826e-01]
latex_v1:  88%|########7 | 2632/3000 [1:01:19<07:21,  1.20s/it, lr: 1.0e-04 loss: 1.826e-01]
latex_v1:  88%|########7 | 2632/3000 [1:01:19<07:21,  1.20s/it, lr: 1.0e-04 loss: 1.826e-01]
latex_v1:  88%|########7 | 2632/3000 [1:01:20<07:21,  1.20s/it, lr: 1.0e-04 loss: 1.732e-01]
latex_v1:  88%|########7 | 2632/3000 [1:01:20<07:21,  1.20s/it, lr: 1.0e-04 loss: 1.732e-01]
latex_v1:  88%|########7 | 2633/3000 [1:01:20<07:35,  1.24s/it, lr: 1.0e-04 loss: 1.732e-01]
latex_v1:  88%|########7 | 2633/3000 [1:01:20<07:35,  1.24s/it, lr: 1.0e-04 loss: 1.732e-01]
latex_v1:  88%|########7 | 2633/3000 [1:01:23<07:35,  1.24s/it, lr: 1.0e-04 loss: 4.576e-01]
latex_v1:  88%|########7 | 2633/3000 [1:01:23<07:35,  1.24s/it, lr: 1.0e-04 loss: 4.576e-01]
latex_v1:  88%|########7 | 2634/3000 [1:01:23<10:13,  1.68s/it, lr: 1.0e-04 loss: 4.576e-01]
latex_v1:  88%|########7 | 2634/3000 [1:01:23<10:13,  1.68s/it, lr: 1.0e-04 loss: 4.576e-01]
latex_v1:  88%|########7 | 2634/3000 [1:01:26<10:13,  1.68s/it, lr: 1.0e-04 loss: 5.728e-01]
latex_v1:  88%|########7 | 2634/3000 [1:01:26<10:13,  1.68s/it, lr: 1.0e-04 loss: 5.728e-01]
latex_v1:  88%|########7 | 2635/3000 [1:01:26<12:10,  2.00s/it, lr: 1.0e-04 loss: 5.728e-01]
latex_v1:  88%|########7 | 2635/3000 [1:01:26<12:10,  2.00s/it, lr: 1.0e-04 loss: 5.728e-01]
latex_v1:  88%|########7 | 2635/3000 [1:01:28<12:10,  2.00s/it, lr: 1.0e-04 loss: 5.256e-02]
latex_v1:  88%|########7 | 2635/3000 [1:01:28<12:10,  2.00s/it, lr: 1.0e-04 loss: 5.256e-02]
latex_v1:  88%|########7 | 2636/3000 [1:01:28<11:53,  1.96s/it, lr: 1.0e-04 loss: 5.256e-02]
latex_v1:  88%|########7 | 2636/3000 [1:01:28<11:53,  1.96s/it, lr: 1.0e-04 loss: 5.256e-02]
latex_v1:  88%|########7 | 2636/3000 [1:01:29<11:53,  1.96s/it, lr: 1.0e-04 loss: 6.906e-02]
latex_v1:  88%|########7 | 2636/3000 [1:01:29<11:53,  1.96s/it, lr: 1.0e-04 loss: 6.906e-02]
latex_v1:  88%|########7 | 2637/3000 [1:01:29<09:45,  1.61s/it, lr: 1.0e-04 loss: 6.906e-02]
latex_v1:  88%|########7 | 2637/3000 [1:01:29<09:45,  1.61s/it, lr: 1.0e-04 loss: 6.906e-02]
latex_v1:  88%|########7 | 2637/3000 [1:01:30<09:45,  1.61s/it, lr: 1.0e-04 loss: 1.251e-01]
latex_v1:  88%|########7 | 2637/3000 [1:01:30<09:45,  1.61s/it, lr: 1.0e-04 loss: 1.251e-01]
latex_v1:  88%|########7 | 2638/3000 [1:01:30<08:36,  1.43s/it, lr: 1.0e-04 loss: 1.251e-01]
latex_v1:  88%|########7 | 2638/3000 [1:01:30<08:36,  1.43s/it, lr: 1.0e-04 loss: 1.251e-01]
latex_v1:  88%|########7 | 2638/3000 [1:01:32<08:36,  1.43s/it, lr: 1.0e-04 loss: 5.328e-02]
latex_v1:  88%|########7 | 2638/3000 [1:01:32<08:36,  1.43s/it, lr: 1.0e-04 loss: 5.328e-02]
latex_v1:  88%|########7 | 2639/3000 [1:01:32<09:32,  1.58s/it, lr: 1.0e-04 loss: 5.328e-02]
latex_v1:  88%|########7 | 2639/3000 [1:01:32<09:32,  1.58s/it, lr: 1.0e-04 loss: 5.328e-02]
latex_v1:  88%|########7 | 2639/3000 [1:01:33<09:32,  1.58s/it, lr: 1.0e-04 loss: 2.530e-01]
latex_v1:  88%|########7 | 2639/3000 [1:01:33<09:32,  1.58s/it, lr: 1.0e-04 loss: 2.530e-01]
latex_v1:  88%|########8 | 2640/3000 [1:01:34<09:30,  1.58s/it, lr: 1.0e-04 loss: 3.862e-01]
latex_v1:  88%|########8 | 2640/3000 [1:01:34<09:30,  1.58s/it, lr: 1.0e-04 loss: 3.862e-01]
latex_v1:  88%|########8 | 2641/3000 [1:01:34<06:55,  1.16s/it, lr: 1.0e-04 loss: 3.862e-01]
latex_v1:  88%|########8 | 2641/3000 [1:01:34<06:55,  1.16s/it, lr: 1.0e-04 loss: 3.862e-01]
latex_v1:  88%|########8 | 2641/3000 [1:01:36<06:55,  1.16s/it, lr: 1.0e-04 loss: 7.445e-01]
latex_v1:  88%|########8 | 2641/3000 [1:01:36<06:55,  1.16s/it, lr: 1.0e-04 loss: 7.445e-01]
latex_v1:  88%|########8 | 2642/3000 [1:01:36<06:54,  1.16s/it, lr: 1.0e-04 loss: 7.445e-01]
latex_v1:  88%|########8 | 2642/3000 [1:01:36<06:54,  1.16s/it, lr: 1.0e-04 loss: 7.445e-01]
latex_v1:  88%|########8 | 2642/3000 [1:01:37<06:54,  1.16s/it, lr: 1.0e-04 loss: 1.956e-01]
latex_v1:  88%|########8 | 2642/3000 [1:01:37<06:54,  1.16s/it, lr: 1.0e-04 loss: 1.956e-01]
latex_v1:  88%|########8 | 2643/3000 [1:01:37<07:16,  1.22s/it, lr: 1.0e-04 loss: 1.956e-01]
latex_v1:  88%|########8 | 2643/3000 [1:01:37<07:16,  1.22s/it, lr: 1.0e-04 loss: 1.956e-01]
latex_v1:  88%|########8 | 2643/3000 [1:01:38<07:16,  1.22s/it, lr: 1.0e-04 loss: 3.657e-01]
latex_v1:  88%|########8 | 2643/3000 [1:01:38<07:16,  1.22s/it, lr: 1.0e-04 loss: 3.657e-01]
latex_v1:  88%|########8 | 2644/3000 [1:01:38<07:34,  1.28s/it, lr: 1.0e-04 loss: 3.657e-01]
latex_v1:  88%|########8 | 2644/3000 [1:01:38<07:34,  1.28s/it, lr: 1.0e-04 loss: 3.657e-01]
latex_v1:  88%|########8 | 2644/3000 [1:01:40<07:34,  1.28s/it, lr: 1.0e-04 loss: 1.664e-01]
latex_v1:  88%|########8 | 2644/3000 [1:01:40<07:34,  1.28s/it, lr: 1.0e-04 loss: 1.664e-01]
latex_v1:  88%|########8 | 2645/3000 [1:01:40<07:50,  1.32s/it, lr: 1.0e-04 loss: 1.664e-01]
latex_v1:  88%|########8 | 2645/3000 [1:01:40<07:50,  1.32s/it, lr: 1.0e-04 loss: 1.664e-01]
latex_v1:  88%|########8 | 2645/3000 [1:01:41<07:50,  1.32s/it, lr: 1.0e-04 loss: 8.135e-01]
latex_v1:  88%|########8 | 2645/3000 [1:01:41<07:50,  1.32s/it, lr: 1.0e-04 loss: 8.135e-01]
latex_v1:  88%|########8 | 2646/3000 [1:01:41<07:11,  1.22s/it, lr: 1.0e-04 loss: 8.135e-01]
latex_v1:  88%|########8 | 2646/3000 [1:01:41<07:11,  1.22s/it, lr: 1.0e-04 loss: 8.135e-01]
latex_v1:  88%|########8 | 2646/3000 [1:01:43<07:11,  1.22s/it, lr: 1.0e-04 loss: 5.130e-01]
latex_v1:  88%|########8 | 2646/3000 [1:01:43<07:11,  1.22s/it, lr: 1.0e-04 loss: 5.130e-01]
latex_v1:  88%|########8 | 2647/3000 [1:01:43<08:20,  1.42s/it, lr: 1.0e-04 loss: 5.130e-01]
latex_v1:  88%|########8 | 2647/3000 [1:01:43<08:20,  1.42s/it, lr: 1.0e-04 loss: 5.130e-01]
latex_v1:  88%|########8 | 2647/3000 [1:01:44<08:20,  1.42s/it, lr: 1.0e-04 loss: 2.476e-01]
latex_v1:  88%|########8 | 2647/3000 [1:01:44<08:20,  1.42s/it, lr: 1.0e-04 loss: 2.476e-01]
latex_v1:  88%|########8 | 2648/3000 [1:01:44<08:32,  1.46s/it, lr: 1.0e-04 loss: 2.476e-01]
latex_v1:  88%|########8 | 2648/3000 [1:01:44<08:32,  1.46s/it, lr: 1.0e-04 loss: 2.476e-01]
latex_v1:  88%|########8 | 2648/3000 [1:01:45<08:32,  1.46s/it, lr: 1.0e-04 loss: 4.852e-01]
latex_v1:  88%|########8 | 2648/3000 [1:01:45<08:32,  1.46s/it, lr: 1.0e-04 loss: 4.852e-01]
latex_v1:  88%|########8 | 2649/3000 [1:01:45<07:17,  1.25s/it, lr: 1.0e-04 loss: 4.852e-01]
latex_v1:  88%|########8 | 2649/3000 [1:01:45<07:17,  1.25s/it, lr: 1.0e-04 loss: 4.852e-01]
latex_v1:  88%|########8 | 2649/3000 [1:01:47<07:17,  1.25s/it, lr: 1.0e-04 loss: 3.608e-01]
latex_v1:  88%|########8 | 2649/3000 [1:01:47<07:17,  1.25s/it, lr: 1.0e-04 loss: 3.608e-01]
latex_v1:  88%|########8 | 2650/3000 [1:01:48<07:15,  1.25s/it, lr: 1.0e-04 loss: 2.587e-01]
latex_v1:  88%|########8 | 2650/3000 [1:01:48<07:15,  1.25s/it, lr: 1.0e-04 loss: 2.587e-01]
latex_v1:  88%|########8 | 2651/3000 [1:01:48<05:58,  1.03s/it, lr: 1.0e-04 loss: 2.587e-01]
latex_v1:  88%|########8 | 2651/3000 [1:01:48<05:58,  1.03s/it, lr: 1.0e-04 loss: 2.587e-01]
latex_v1:  88%|########8 | 2651/3000 [1:01:49<05:58,  1.03s/it, lr: 1.0e-04 loss: 1.078e-01]
latex_v1:  88%|########8 | 2651/3000 [1:01:49<05:58,  1.03s/it, lr: 1.0e-04 loss: 1.078e-01]
latex_v1:  88%|########8 | 2652/3000 [1:01:49<05:53,  1.02s/it, lr: 1.0e-04 loss: 1.078e-01]
latex_v1:  88%|########8 | 2652/3000 [1:01:49<05:53,  1.02s/it, lr: 1.0e-04 loss: 1.078e-01]
latex_v1:  88%|########8 | 2652/3000 [1:01:51<05:53,  1.02s/it, lr: 1.0e-04 loss: 1.341e-02]
latex_v1:  88%|########8 | 2652/3000 [1:01:51<05:53,  1.02s/it, lr: 1.0e-04 loss: 1.341e-02]
latex_v1:  88%|########8 | 2653/3000 [1:01:51<06:39,  1.15s/it, lr: 1.0e-04 loss: 1.341e-02]
latex_v1:  88%|########8 | 2653/3000 [1:01:51<06:39,  1.15s/it, lr: 1.0e-04 loss: 1.341e-02]
latex_v1:  88%|########8 | 2653/3000 [1:01:52<06:39,  1.15s/it, lr: 1.0e-04 loss: 2.802e-01]
latex_v1:  88%|########8 | 2653/3000 [1:01:52<06:39,  1.15s/it, lr: 1.0e-04 loss: 2.802e-01]
latex_v1:  88%|########8 | 2654/3000 [1:01:52<06:41,  1.16s/it, lr: 1.0e-04 loss: 2.802e-01]
latex_v1:  88%|########8 | 2654/3000 [1:01:52<06:41,  1.16s/it, lr: 1.0e-04 loss: 2.802e-01]
latex_v1:  88%|########8 | 2654/3000 [1:01:55<06:41,  1.16s/it, lr: 1.0e-04 loss: 5.817e-02]
latex_v1:  88%|########8 | 2654/3000 [1:01:55<06:41,  1.16s/it, lr: 1.0e-04 loss: 5.817e-02]
latex_v1:  88%|########8 | 2655/3000 [1:01:55<09:20,  1.63s/it, lr: 1.0e-04 loss: 5.817e-02]
latex_v1:  88%|########8 | 2655/3000 [1:01:55<09:20,  1.63s/it, lr: 1.0e-04 loss: 5.817e-02]
latex_v1:  88%|########8 | 2655/3000 [1:01:55<09:20,  1.63s/it, lr: 1.0e-04 loss: 7.654e-01]
latex_v1:  88%|########8 | 2655/3000 [1:01:55<09:20,  1.63s/it, lr: 1.0e-04 loss: 7.654e-01]
latex_v1:  89%|########8 | 2656/3000 [1:01:55<07:53,  1.38s/it, lr: 1.0e-04 loss: 7.654e-01]
latex_v1:  89%|########8 | 2656/3000 [1:01:55<07:53,  1.38s/it, lr: 1.0e-04 loss: 7.654e-01]
latex_v1:  89%|########8 | 2656/3000 [1:01:56<07:53,  1.38s/it, lr: 1.0e-04 loss: 8.746e-02]
latex_v1:  89%|########8 | 2656/3000 [1:01:56<07:53,  1.38s/it, lr: 1.0e-04 loss: 8.746e-02]
latex_v1:  89%|########8 | 2657/3000 [1:01:56<06:52,  1.20s/it, lr: 1.0e-04 loss: 8.746e-02]
latex_v1:  89%|########8 | 2657/3000 [1:01:56<06:52,  1.20s/it, lr: 1.0e-04 loss: 8.746e-02]
latex_v1:  89%|########8 | 2657/3000 [1:01:58<06:52,  1.20s/it, lr: 1.0e-04 loss: 2.283e-01]
latex_v1:  89%|########8 | 2657/3000 [1:01:58<06:52,  1.20s/it, lr: 1.0e-04 loss: 2.283e-01]
latex_v1:  89%|########8 | 2658/3000 [1:01:58<07:15,  1.27s/it, lr: 1.0e-04 loss: 2.283e-01]
latex_v1:  89%|########8 | 2658/3000 [1:01:58<07:15,  1.27s/it, lr: 1.0e-04 loss: 2.283e-01]
latex_v1:  89%|########8 | 2658/3000 [1:01:59<07:15,  1.27s/it, lr: 1.0e-04 loss: 2.578e-01]
latex_v1:  89%|########8 | 2658/3000 [1:01:59<07:15,  1.27s/it, lr: 1.0e-04 loss: 2.578e-01]
latex_v1:  89%|########8 | 2659/3000 [1:01:59<07:28,  1.31s/it, lr: 1.0e-04 loss: 2.578e-01]
latex_v1:  89%|########8 | 2659/3000 [1:01:59<07:28,  1.31s/it, lr: 1.0e-04 loss: 2.578e-01]
latex_v1:  89%|########8 | 2659/3000 [1:02:00<07:28,  1.31s/it, lr: 1.0e-04 loss: 6.092e-01]
latex_v1:  89%|########8 | 2659/3000 [1:02:00<07:28,  1.31s/it, lr: 1.0e-04 loss: 6.092e-01]
latex_v1:  89%|########8 | 2660/3000 [1:02:03<07:27,  1.31s/it, lr: 1.0e-04 loss: 1.371e-01]
latex_v1:  89%|########8 | 2660/3000 [1:02:03<07:27,  1.31s/it, lr: 1.0e-04 loss: 1.371e-01]
latex_v1:  89%|########8 | 2661/3000 [1:02:03<07:44,  1.37s/it, lr: 1.0e-04 loss: 1.371e-01]
latex_v1:  89%|########8 | 2661/3000 [1:02:03<07:44,  1.37s/it, lr: 1.0e-04 loss: 1.371e-01]
latex_v1:  89%|########8 | 2661/3000 [1:02:05<07:44,  1.37s/it, lr: 1.0e-04 loss: 1.874e-01]
latex_v1:  89%|########8 | 2661/3000 [1:02:05<07:44,  1.37s/it, lr: 1.0e-04 loss: 1.874e-01]
latex_v1:  89%|########8 | 2662/3000 [1:02:05<08:26,  1.50s/it, lr: 1.0e-04 loss: 1.874e-01]
latex_v1:  89%|########8 | 2662/3000 [1:02:05<08:26,  1.50s/it, lr: 1.0e-04 loss: 1.874e-01]
latex_v1:  89%|########8 | 2662/3000 [1:02:06<08:26,  1.50s/it, lr: 1.0e-04 loss: 3.282e-01]
latex_v1:  89%|########8 | 2662/3000 [1:02:06<08:26,  1.50s/it, lr: 1.0e-04 loss: 3.282e-01]
latex_v1:  89%|########8 | 2663/3000 [1:02:06<07:19,  1.30s/it, lr: 1.0e-04 loss: 3.282e-01]
latex_v1:  89%|########8 | 2663/3000 [1:02:06<07:19,  1.30s/it, lr: 1.0e-04 loss: 3.282e-01]
latex_v1:  89%|########8 | 2663/3000 [1:02:07<07:19,  1.30s/it, lr: 1.0e-04 loss: 5.684e-01]
latex_v1:  89%|########8 | 2663/3000 [1:02:07<07:19,  1.30s/it, lr: 1.0e-04 loss: 5.684e-01]
latex_v1:  89%|########8 | 2664/3000 [1:02:07<07:40,  1.37s/it, lr: 1.0e-04 loss: 5.684e-01]
latex_v1:  89%|########8 | 2664/3000 [1:02:07<07:40,  1.37s/it, lr: 1.0e-04 loss: 5.684e-01]
latex_v1:  89%|########8 | 2664/3000 [1:02:08<07:40,  1.37s/it, lr: 1.0e-04 loss: 2.634e-01]
latex_v1:  89%|########8 | 2664/3000 [1:02:08<07:40,  1.37s/it, lr: 1.0e-04 loss: 2.634e-01]
latex_v1:  89%|########8 | 2665/3000 [1:02:08<07:03,  1.26s/it, lr: 1.0e-04 loss: 2.634e-01]
latex_v1:  89%|########8 | 2665/3000 [1:02:08<07:03,  1.26s/it, lr: 1.0e-04 loss: 2.634e-01]
latex_v1:  89%|########8 | 2665/3000 [1:02:09<07:03,  1.26s/it, lr: 1.0e-04 loss: 4.962e-01]
latex_v1:  89%|########8 | 2665/3000 [1:02:09<07:03,  1.26s/it, lr: 1.0e-04 loss: 4.962e-01]
latex_v1:  89%|########8 | 2666/3000 [1:02:09<06:16,  1.13s/it, lr: 1.0e-04 loss: 4.962e-01]
latex_v1:  89%|########8 | 2666/3000 [1:02:09<06:16,  1.13s/it, lr: 1.0e-04 loss: 4.962e-01]
latex_v1:  89%|########8 | 2666/3000 [1:02:11<06:16,  1.13s/it, lr: 1.0e-04 loss: 1.523e-01]
latex_v1:  89%|########8 | 2666/3000 [1:02:11<06:16,  1.13s/it, lr: 1.0e-04 loss: 1.523e-01]
latex_v1:  89%|########8 | 2667/3000 [1:02:11<06:53,  1.24s/it, lr: 1.0e-04 loss: 1.523e-01]
latex_v1:  89%|########8 | 2667/3000 [1:02:11<06:53,  1.24s/it, lr: 1.0e-04 loss: 1.523e-01]
latex_v1:  89%|########8 | 2667/3000 [1:02:11<06:53,  1.24s/it, lr: 1.0e-04 loss: 5.773e-01]
latex_v1:  89%|########8 | 2667/3000 [1:02:11<06:53,  1.24s/it, lr: 1.0e-04 loss: 5.773e-01]
latex_v1:  89%|########8 | 2668/3000 [1:02:11<06:04,  1.10s/it, lr: 1.0e-04 loss: 5.773e-01]
latex_v1:  89%|########8 | 2668/3000 [1:02:11<06:04,  1.10s/it, lr: 1.0e-04 loss: 5.773e-01]
latex_v1:  89%|########8 | 2668/3000 [1:02:13<06:04,  1.10s/it, lr: 1.0e-04 loss: 3.979e-01]
latex_v1:  89%|########8 | 2668/3000 [1:02:13<06:04,  1.10s/it, lr: 1.0e-04 loss: 3.979e-01]
latex_v1:  89%|########8 | 2669/3000 [1:02:13<06:26,  1.17s/it, lr: 1.0e-04 loss: 3.979e-01]
latex_v1:  89%|########8 | 2669/3000 [1:02:13<06:26,  1.17s/it, lr: 1.0e-04 loss: 3.979e-01]
latex_v1:  89%|########8 | 2669/3000 [1:02:15<06:26,  1.17s/it, lr: 1.0e-04 loss: 1.707e-01]
latex_v1:  89%|########8 | 2669/3000 [1:02:15<06:26,  1.17s/it, lr: 1.0e-04 loss: 1.707e-01]
latex_v1:  89%|########9 | 2670/3000 [1:02:16<06:25,  1.17s/it, lr: 1.0e-04 loss: 4.277e-01]
latex_v1:  89%|########9 | 2670/3000 [1:02:16<06:25,  1.17s/it, lr: 1.0e-04 loss: 4.277e-01]
latex_v1:  89%|########9 | 2671/3000 [1:02:16<04:23,  1.25it/s, lr: 1.0e-04 loss: 4.277e-01]
latex_v1:  89%|########9 | 2671/3000 [1:02:16<04:23,  1.25it/s, lr: 1.0e-04 loss: 4.277e-01]
latex_v1:  89%|########9 | 2671/3000 [1:02:17<04:23,  1.25it/s, lr: 1.0e-04 loss: 4.830e-01]
latex_v1:  89%|########9 | 2671/3000 [1:02:17<04:23,  1.25it/s, lr: 1.0e-04 loss: 4.830e-01]
latex_v1:  89%|########9 | 2672/3000 [1:02:17<04:19,  1.26it/s, lr: 1.0e-04 loss: 4.830e-01]
latex_v1:  89%|########9 | 2672/3000 [1:02:17<04:19,  1.26it/s, lr: 1.0e-04 loss: 4.830e-01]
latex_v1:  89%|########9 | 2672/3000 [1:02:19<04:19,  1.26it/s, lr: 1.0e-04 loss: 5.390e-01]
latex_v1:  89%|########9 | 2672/3000 [1:02:19<04:19,  1.26it/s, lr: 1.0e-04 loss: 5.390e-01]
latex_v1:  89%|########9 | 2673/3000 [1:02:19<05:51,  1.08s/it, lr: 1.0e-04 loss: 5.390e-01]
latex_v1:  89%|########9 | 2673/3000 [1:02:19<05:51,  1.08s/it, lr: 1.0e-04 loss: 5.390e-01]
latex_v1:  89%|########9 | 2673/3000 [1:02:22<05:51,  1.08s/it, lr: 1.0e-04 loss: 4.408e-01]
latex_v1:  89%|########9 | 2673/3000 [1:02:22<05:51,  1.08s/it, lr: 1.0e-04 loss: 4.408e-01]
latex_v1:  89%|########9 | 2674/3000 [1:02:22<08:33,  1.58s/it, lr: 1.0e-04 loss: 4.408e-01]
latex_v1:  89%|########9 | 2674/3000 [1:02:22<08:33,  1.58s/it, lr: 1.0e-04 loss: 4.408e-01]
latex_v1:  89%|########9 | 2674/3000 [1:02:23<08:33,  1.58s/it, lr: 1.0e-04 loss: 5.604e-01]
latex_v1:  89%|########9 | 2674/3000 [1:02:23<08:33,  1.58s/it, lr: 1.0e-04 loss: 5.604e-01]
latex_v1:  89%|########9 | 2675/3000 [1:02:23<08:38,  1.60s/it, lr: 1.0e-04 loss: 5.604e-01]
latex_v1:  89%|########9 | 2675/3000 [1:02:23<08:38,  1.60s/it, lr: 1.0e-04 loss: 5.604e-01]
latex_v1:  89%|########9 | 2675/3000 [1:02:25<08:38,  1.60s/it, lr: 1.0e-04 loss: 7.828e-02]
latex_v1:  89%|########9 | 2675/3000 [1:02:25<08:38,  1.60s/it, lr: 1.0e-04 loss: 7.828e-02]
latex_v1:  89%|########9 | 2676/3000 [1:02:25<08:21,  1.55s/it, lr: 1.0e-04 loss: 7.828e-02]
latex_v1:  89%|########9 | 2676/3000 [1:02:25<08:21,  1.55s/it, lr: 1.0e-04 loss: 7.828e-02]
latex_v1:  89%|########9 | 2676/3000 [1:02:28<08:21,  1.55s/it, lr: 1.0e-04 loss: 3.207e-01]
latex_v1:  89%|########9 | 2676/3000 [1:02:28<08:21,  1.55s/it, lr: 1.0e-04 loss: 3.207e-01]
latex_v1:  89%|########9 | 2677/3000 [1:02:28<10:20,  1.92s/it, lr: 1.0e-04 loss: 3.207e-01]
latex_v1:  89%|########9 | 2677/3000 [1:02:28<10:20,  1.92s/it, lr: 1.0e-04 loss: 3.207e-01]
latex_v1:  89%|########9 | 2677/3000 [1:02:30<10:20,  1.92s/it, lr: 1.0e-04 loss: 1.020e-01]
latex_v1:  89%|########9 | 2677/3000 [1:02:30<10:20,  1.92s/it, lr: 1.0e-04 loss: 1.020e-01]
latex_v1:  89%|########9 | 2678/3000 [1:02:30<10:55,  2.03s/it, lr: 1.0e-04 loss: 1.020e-01]
latex_v1:  89%|########9 | 2678/3000 [1:02:30<10:55,  2.03s/it, lr: 1.0e-04 loss: 1.020e-01]
latex_v1:  89%|########9 | 2678/3000 [1:02:31<10:55,  2.03s/it, lr: 1.0e-04 loss: 3.825e-01]
latex_v1:  89%|########9 | 2678/3000 [1:02:31<10:55,  2.03s/it, lr: 1.0e-04 loss: 3.825e-01]
latex_v1:  89%|########9 | 2679/3000 [1:02:31<09:31,  1.78s/it, lr: 1.0e-04 loss: 3.825e-01]
latex_v1:  89%|########9 | 2679/3000 [1:02:31<09:31,  1.78s/it, lr: 1.0e-04 loss: 3.825e-01]
latex_v1:  89%|########9 | 2679/3000 [1:02:33<09:31,  1.78s/it, lr: 1.0e-04 loss: 5.168e-01]
latex_v1:  89%|########9 | 2679/3000 [1:02:33<09:31,  1.78s/it, lr: 1.0e-04 loss: 5.168e-01]
latex_v1:  89%|########9 | 2680/3000 [1:02:34<09:29,  1.78s/it, lr: 1.0e-04 loss: 4.646e-01]
latex_v1:  89%|########9 | 2680/3000 [1:02:34<09:29,  1.78s/it, lr: 1.0e-04 loss: 4.646e-01]
latex_v1:  89%|########9 | 2681/3000 [1:02:34<06:55,  1.30s/it, lr: 1.0e-04 loss: 4.646e-01]
latex_v1:  89%|########9 | 2681/3000 [1:02:34<06:55,  1.30s/it, lr: 1.0e-04 loss: 4.646e-01]
latex_v1:  89%|########9 | 2681/3000 [1:02:35<06:55,  1.30s/it, lr: 1.0e-04 loss: 7.558e-01]
latex_v1:  89%|########9 | 2681/3000 [1:02:35<06:55,  1.30s/it, lr: 1.0e-04 loss: 7.558e-01]
latex_v1:  89%|########9 | 2682/3000 [1:02:35<06:11,  1.17s/it, lr: 1.0e-04 loss: 7.558e-01]
latex_v1:  89%|########9 | 2682/3000 [1:02:35<06:11,  1.17s/it, lr: 1.0e-04 loss: 7.558e-01]
latex_v1:  89%|########9 | 2682/3000 [1:02:36<06:11,  1.17s/it, lr: 1.0e-04 loss: 6.676e-01]
latex_v1:  89%|########9 | 2682/3000 [1:02:36<06:11,  1.17s/it, lr: 1.0e-04 loss: 6.676e-01]
latex_v1:  89%|########9 | 2683/3000 [1:02:36<05:37,  1.07s/it, lr: 1.0e-04 loss: 6.676e-01]
latex_v1:  89%|########9 | 2683/3000 [1:02:36<05:37,  1.07s/it, lr: 1.0e-04 loss: 6.676e-01]
latex_v1:  89%|########9 | 2683/3000 [1:02:37<05:37,  1.07s/it, lr: 1.0e-04 loss: 3.814e-01]
latex_v1:  89%|########9 | 2683/3000 [1:02:37<05:37,  1.07s/it, lr: 1.0e-04 loss: 3.814e-01]
latex_v1:  89%|########9 | 2684/3000 [1:02:37<05:59,  1.14s/it, lr: 1.0e-04 loss: 3.814e-01]
latex_v1:  89%|########9 | 2684/3000 [1:02:37<05:59,  1.14s/it, lr: 1.0e-04 loss: 3.814e-01]
latex_v1:  89%|########9 | 2684/3000 [1:02:38<05:59,  1.14s/it, lr: 1.0e-04 loss: 3.847e-01]
latex_v1:  89%|########9 | 2684/3000 [1:02:38<05:59,  1.14s/it, lr: 1.0e-04 loss: 3.847e-01]
latex_v1:  90%|########9 | 2685/3000 [1:02:38<06:26,  1.23s/it, lr: 1.0e-04 loss: 3.847e-01]
latex_v1:  90%|########9 | 2685/3000 [1:02:38<06:26,  1.23s/it, lr: 1.0e-04 loss: 3.847e-01]
latex_v1:  90%|########9 | 2685/3000 [1:02:39<06:26,  1.23s/it, lr: 1.0e-04 loss: 4.036e-01]
latex_v1:  90%|########9 | 2685/3000 [1:02:39<06:26,  1.23s/it, lr: 1.0e-04 loss: 4.036e-01]
latex_v1:  90%|########9 | 2686/3000 [1:02:39<06:10,  1.18s/it, lr: 1.0e-04 loss: 4.036e-01]
latex_v1:  90%|########9 | 2686/3000 [1:02:39<06:10,  1.18s/it, lr: 1.0e-04 loss: 4.036e-01]
latex_v1:  90%|########9 | 2686/3000 [1:02:40<06:10,  1.18s/it, lr: 1.0e-04 loss: 2.923e-01]
latex_v1:  90%|########9 | 2686/3000 [1:02:40<06:10,  1.18s/it, lr: 1.0e-04 loss: 2.923e-01]
latex_v1:  90%|########9 | 2687/3000 [1:02:40<05:30,  1.06s/it, lr: 1.0e-04 loss: 2.923e-01]
latex_v1:  90%|########9 | 2687/3000 [1:02:40<05:30,  1.06s/it, lr: 1.0e-04 loss: 2.923e-01]
latex_v1:  90%|########9 | 2687/3000 [1:02:42<05:30,  1.06s/it, lr: 1.0e-04 loss: 1.362e-01]
latex_v1:  90%|########9 | 2687/3000 [1:02:42<05:30,  1.06s/it, lr: 1.0e-04 loss: 1.362e-01]
latex_v1:  90%|########9 | 2688/3000 [1:02:42<06:31,  1.25s/it, lr: 1.0e-04 loss: 1.362e-01]
latex_v1:  90%|########9 | 2688/3000 [1:02:42<06:31,  1.25s/it, lr: 1.0e-04 loss: 1.362e-01]
latex_v1:  90%|########9 | 2688/3000 [1:02:43<06:31,  1.25s/it, lr: 1.0e-04 loss: 1.918e-01]
latex_v1:  90%|########9 | 2688/3000 [1:02:43<06:31,  1.25s/it, lr: 1.0e-04 loss: 1.918e-01]
latex_v1:  90%|########9 | 2689/3000 [1:02:43<06:04,  1.17s/it, lr: 1.0e-04 loss: 1.918e-01]
latex_v1:  90%|########9 | 2689/3000 [1:02:43<06:04,  1.17s/it, lr: 1.0e-04 loss: 1.918e-01]
latex_v1:  90%|########9 | 2689/3000 [1:02:44<06:04,  1.17s/it, lr: 1.0e-04 loss: 4.704e-01]
latex_v1:  90%|########9 | 2689/3000 [1:02:44<06:04,  1.17s/it, lr: 1.0e-04 loss: 4.704e-01]
latex_v1:  90%|########9 | 2690/3000 [1:02:45<06:03,  1.17s/it, lr: 1.0e-04 loss: 6.254e-02]
latex_v1:  90%|########9 | 2690/3000 [1:02:45<06:03,  1.17s/it, lr: 1.0e-04 loss: 6.254e-02]
latex_v1:  90%|########9 | 2691/3000 [1:02:45<05:07,  1.00it/s, lr: 1.0e-04 loss: 6.254e-02]
latex_v1:  90%|########9 | 2691/3000 [1:02:45<05:07,  1.00it/s, lr: 1.0e-04 loss: 6.254e-02]
latex_v1:  90%|########9 | 2691/3000 [1:02:47<05:07,  1.00it/s, lr: 1.0e-04 loss: 3.648e-01]
latex_v1:  90%|########9 | 2691/3000 [1:02:47<05:07,  1.00it/s, lr: 1.0e-04 loss: 3.648e-01]
latex_v1:  90%|########9 | 2692/3000 [1:02:47<05:47,  1.13s/it, lr: 1.0e-04 loss: 3.648e-01]
latex_v1:  90%|########9 | 2692/3000 [1:02:47<05:47,  1.13s/it, lr: 1.0e-04 loss: 3.648e-01]
latex_v1:  90%|########9 | 2692/3000 [1:02:48<05:47,  1.13s/it, lr: 1.0e-04 loss: 2.390e-01]
latex_v1:  90%|########9 | 2692/3000 [1:02:48<05:47,  1.13s/it, lr: 1.0e-04 loss: 2.390e-01]
latex_v1:  90%|########9 | 2693/3000 [1:02:48<05:34,  1.09s/it, lr: 1.0e-04 loss: 2.390e-01]
latex_v1:  90%|########9 | 2693/3000 [1:02:48<05:34,  1.09s/it, lr: 1.0e-04 loss: 2.390e-01]
latex_v1:  90%|########9 | 2693/3000 [1:02:49<05:34,  1.09s/it, lr: 1.0e-04 loss: 5.620e-01]
latex_v1:  90%|########9 | 2693/3000 [1:02:49<05:34,  1.09s/it, lr: 1.0e-04 loss: 5.620e-01]
latex_v1:  90%|########9 | 2694/3000 [1:02:49<05:03,  1.01it/s, lr: 1.0e-04 loss: 5.620e-01]
latex_v1:  90%|########9 | 2694/3000 [1:02:49<05:03,  1.01it/s, lr: 1.0e-04 loss: 5.620e-01]
latex_v1:  90%|########9 | 2694/3000 [1:02:50<05:03,  1.01it/s, lr: 1.0e-04 loss: 1.362e-01]
latex_v1:  90%|########9 | 2694/3000 [1:02:50<05:03,  1.01it/s, lr: 1.0e-04 loss: 1.362e-01]
latex_v1:  90%|########9 | 2695/3000 [1:02:50<05:41,  1.12s/it, lr: 1.0e-04 loss: 1.362e-01]
latex_v1:  90%|########9 | 2695/3000 [1:02:50<05:41,  1.12s/it, lr: 1.0e-04 loss: 1.362e-01]
latex_v1:  90%|########9 | 2695/3000 [1:02:51<05:41,  1.12s/it, lr: 1.0e-04 loss: 1.675e-01]
latex_v1:  90%|########9 | 2695/3000 [1:02:51<05:41,  1.12s/it, lr: 1.0e-04 loss: 1.675e-01]
latex_v1:  90%|########9 | 2696/3000 [1:02:51<05:07,  1.01s/it, lr: 1.0e-04 loss: 1.675e-01]
latex_v1:  90%|########9 | 2696/3000 [1:02:51<05:07,  1.01s/it, lr: 1.0e-04 loss: 1.675e-01]
latex_v1:  90%|########9 | 2696/3000 [1:02:53<05:07,  1.01s/it, lr: 1.0e-04 loss: 5.243e-02]
latex_v1:  90%|########9 | 2696/3000 [1:02:53<05:07,  1.01s/it, lr: 1.0e-04 loss: 5.243e-02]
latex_v1:  90%|########9 | 2697/3000 [1:02:53<05:55,  1.17s/it, lr: 1.0e-04 loss: 5.243e-02]
latex_v1:  90%|########9 | 2697/3000 [1:02:53<05:55,  1.17s/it, lr: 1.0e-04 loss: 5.243e-02]
latex_v1:  90%|########9 | 2697/3000 [1:02:54<05:55,  1.17s/it, lr: 1.0e-04 loss: 2.512e-02]
latex_v1:  90%|########9 | 2697/3000 [1:02:54<05:55,  1.17s/it, lr: 1.0e-04 loss: 2.512e-02]
latex_v1:  90%|########9 | 2698/3000 [1:02:54<05:34,  1.11s/it, lr: 1.0e-04 loss: 2.512e-02]
latex_v1:  90%|########9 | 2698/3000 [1:02:54<05:34,  1.11s/it, lr: 1.0e-04 loss: 2.512e-02]
latex_v1:  90%|########9 | 2698/3000 [1:02:54<05:34,  1.11s/it, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  90%|########9 | 2698/3000 [1:02:54<05:34,  1.11s/it, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  90%|########9 | 2699/3000 [1:02:54<05:02,  1.01s/it, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  90%|########9 | 2699/3000 [1:02:54<05:02,  1.01s/it, lr: 1.0e-04 loss: 2.425e-01]
latex_v1:  90%|########9 | 2699/3000 [1:02:55<05:02,  1.01s/it, lr: 1.0e-04 loss: 1.937e-01]
latex_v1:  90%|########9 | 2699/3000 [1:02:55<05:02,  1.01s/it, lr: 1.0e-04 loss: 1.937e-01]Unloading assistant lora



Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]


Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.42s/it]
Generating Images:  14%|#4        | 1/7 [00:02<00:14,  2.42s/it]


Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.41s/it]
Generating Images:  29%|##8       | 2/7 [00:04<00:12,  2.41s/it]


Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.40s/it]
Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.40s/it]


Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.43s/it]
Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.43s/it]


Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.42s/it]
Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.42s/it]


Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.41s/it]
Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.41s/it]


Generating Images: 100%|##########| 7/7 [00:16<00:00,  2.42s/it]
Generating Images: 100%|##########| 7/7 [00:16<00:00,  2.42s/it]


                                                                
                                                                Loading assistant lora

latex_v1:  90%|######### | 2700/3000 [1:02:56<05:01,  1.01s/it, lr: 1.0e-04 loss: 2.088e-01]
latex_v1:  90%|######### | 2700/3000 [1:02:56<05:01,  1.01s/it, lr: 1.0e-04 loss: 2.088e-01]
latex_v1:  90%|######### | 2701/3000 [1:02:56<03:35,  1.39it/s, lr: 1.0e-04 loss: 2.088e-01]
latex_v1:  90%|######### | 2701/3000 [1:02:56<03:35,  1.39it/s, lr: 1.0e-04 loss: 2.088e-01]
latex_v1:  90%|######### | 2701/3000 [1:02:59<03:35,  1.39it/s, lr: 1.0e-04 loss: 5.638e-01]
latex_v1:  90%|######### | 2701/3000 [1:02:59<03:35,  1.39it/s, lr: 1.0e-04 loss: 5.638e-01]
latex_v1:  90%|######### | 2702/3000 [1:02:59<05:53,  1.19s/it, lr: 1.0e-04 loss: 5.638e-01]
latex_v1:  90%|######### | 2702/3000 [1:02:59<05:53,  1.19s/it, lr: 1.0e-04 loss: 5.638e-01]
latex_v1:  90%|######### | 2702/3000 [1:03:01<05:53,  1.19s/it, lr: 1.0e-04 loss: 1.002e-01]
latex_v1:  90%|######### | 2702/3000 [1:03:01<05:53,  1.19s/it, lr: 1.0e-04 loss: 1.002e-01]
latex_v1:  90%|######### | 2703/3000 [1:03:01<08:00,  1.62s/it, lr: 1.0e-04 loss: 1.002e-01]
latex_v1:  90%|######### | 2703/3000 [1:03:01<08:00,  1.62s/it, lr: 1.0e-04 loss: 1.002e-01]
latex_v1:  90%|######### | 2703/3000 [1:03:02<08:00,  1.62s/it, lr: 1.0e-04 loss: 4.243e-01]
latex_v1:  90%|######### | 2703/3000 [1:03:02<08:00,  1.62s/it, lr: 1.0e-04 loss: 4.243e-01]
latex_v1:  90%|######### | 2704/3000 [1:03:02<06:49,  1.38s/it, lr: 1.0e-04 loss: 4.243e-01]
latex_v1:  90%|######### | 2704/3000 [1:03:02<06:49,  1.38s/it, lr: 1.0e-04 loss: 4.243e-01]
latex_v1:  90%|######### | 2704/3000 [1:03:04<06:49,  1.38s/it, lr: 1.0e-04 loss: 3.069e-01]
latex_v1:  90%|######### | 2704/3000 [1:03:04<06:49,  1.38s/it, lr: 1.0e-04 loss: 3.069e-01]
latex_v1:  90%|######### | 2705/3000 [1:03:04<07:09,  1.46s/it, lr: 1.0e-04 loss: 3.069e-01]
latex_v1:  90%|######### | 2705/3000 [1:03:04<07:09,  1.46s/it, lr: 1.0e-04 loss: 3.069e-01]
latex_v1:  90%|######### | 2705/3000 [1:03:05<07:09,  1.46s/it, lr: 1.0e-04 loss: 9.022e-02]
latex_v1:  90%|######### | 2705/3000 [1:03:05<07:09,  1.46s/it, lr: 1.0e-04 loss: 9.022e-02]
latex_v1:  90%|######### | 2706/3000 [1:03:05<06:44,  1.38s/it, lr: 1.0e-04 loss: 9.022e-02]
latex_v1:  90%|######### | 2706/3000 [1:03:05<06:44,  1.38s/it, lr: 1.0e-04 loss: 9.022e-02]
latex_v1:  90%|######### | 2706/3000 [1:03:06<06:44,  1.38s/it, lr: 1.0e-04 loss: 5.253e-01]
latex_v1:  90%|######### | 2706/3000 [1:03:06<06:44,  1.38s/it, lr: 1.0e-04 loss: 5.253e-01]
latex_v1:  90%|######### | 2707/3000 [1:03:06<06:45,  1.38s/it, lr: 1.0e-04 loss: 5.253e-01]
latex_v1:  90%|######### | 2707/3000 [1:03:06<06:45,  1.38s/it, lr: 1.0e-04 loss: 5.253e-01]
latex_v1:  90%|######### | 2707/3000 [1:03:08<06:45,  1.38s/it, lr: 1.0e-04 loss: 5.237e-01]
latex_v1:  90%|######### | 2707/3000 [1:03:08<06:45,  1.38s/it, lr: 1.0e-04 loss: 5.237e-01]
latex_v1:  90%|######### | 2708/3000 [1:03:08<06:38,  1.36s/it, lr: 1.0e-04 loss: 5.237e-01]
latex_v1:  90%|######### | 2708/3000 [1:03:08<06:38,  1.36s/it, lr: 1.0e-04 loss: 5.237e-01]
latex_v1:  90%|######### | 2708/3000 [1:03:11<06:38,  1.36s/it, lr: 1.0e-04 loss: 1.768e-01]
latex_v1:  90%|######### | 2708/3000 [1:03:11<06:38,  1.36s/it, lr: 1.0e-04 loss: 1.768e-01]
latex_v1:  90%|######### | 2709/3000 [1:03:11<08:43,  1.80s/it, lr: 1.0e-04 loss: 1.768e-01]
latex_v1:  90%|######### | 2709/3000 [1:03:11<08:43,  1.80s/it, lr: 1.0e-04 loss: 1.768e-01]
latex_v1:  90%|######### | 2709/3000 [1:03:11<08:43,  1.80s/it, lr: 1.0e-04 loss: 4.728e-01]
latex_v1:  90%|######### | 2709/3000 [1:03:11<08:43,  1.80s/it, lr: 1.0e-04 loss: 4.728e-01]
latex_v1:  90%|######### | 2710/3000 [1:03:12<08:41,  1.80s/it, lr: 1.0e-04 loss: 1.952e-01]
latex_v1:  90%|######### | 2710/3000 [1:03:12<08:41,  1.80s/it, lr: 1.0e-04 loss: 1.952e-01]
latex_v1:  90%|######### | 2711/3000 [1:03:12<05:59,  1.24s/it, lr: 1.0e-04 loss: 1.952e-01]
latex_v1:  90%|######### | 2711/3000 [1:03:12<05:59,  1.24s/it, lr: 1.0e-04 loss: 1.952e-01]
latex_v1:  90%|######### | 2711/3000 [1:03:14<05:59,  1.24s/it, lr: 1.0e-04 loss: 2.368e-01]
latex_v1:  90%|######### | 2711/3000 [1:03:14<05:59,  1.24s/it, lr: 1.0e-04 loss: 2.368e-01]
latex_v1:  90%|######### | 2712/3000 [1:03:14<06:16,  1.31s/it, lr: 1.0e-04 loss: 2.368e-01]
latex_v1:  90%|######### | 2712/3000 [1:03:14<06:16,  1.31s/it, lr: 1.0e-04 loss: 2.368e-01]
latex_v1:  90%|######### | 2712/3000 [1:03:15<06:16,  1.31s/it, lr: 1.0e-04 loss: 1.070e-01]
latex_v1:  90%|######### | 2712/3000 [1:03:15<06:16,  1.31s/it, lr: 1.0e-04 loss: 1.070e-01]
latex_v1:  90%|######### | 2713/3000 [1:03:15<05:51,  1.22s/it, lr: 1.0e-04 loss: 1.070e-01]
latex_v1:  90%|######### | 2713/3000 [1:03:15<05:51,  1.22s/it, lr: 1.0e-04 loss: 1.070e-01]
latex_v1:  90%|######### | 2713/3000 [1:03:17<05:51,  1.22s/it, lr: 1.0e-04 loss: 3.094e-01]
latex_v1:  90%|######### | 2713/3000 [1:03:17<05:51,  1.22s/it, lr: 1.0e-04 loss: 3.094e-01]
latex_v1:  90%|######### | 2714/3000 [1:03:17<06:41,  1.41s/it, lr: 1.0e-04 loss: 3.094e-01]
latex_v1:  90%|######### | 2714/3000 [1:03:17<06:41,  1.41s/it, lr: 1.0e-04 loss: 3.094e-01]
latex_v1:  90%|######### | 2714/3000 [1:03:19<06:41,  1.41s/it, lr: 1.0e-04 loss: 5.223e-01]
latex_v1:  90%|######### | 2714/3000 [1:03:19<06:41,  1.41s/it, lr: 1.0e-04 loss: 5.223e-01]
latex_v1:  90%|######### | 2715/3000 [1:03:19<07:24,  1.56s/it, lr: 1.0e-04 loss: 5.223e-01]
latex_v1:  90%|######### | 2715/3000 [1:03:19<07:24,  1.56s/it, lr: 1.0e-04 loss: 5.223e-01]
latex_v1:  90%|######### | 2715/3000 [1:03:20<07:24,  1.56s/it, lr: 1.0e-04 loss: 1.448e-01]
latex_v1:  90%|######### | 2715/3000 [1:03:20<07:24,  1.56s/it, lr: 1.0e-04 loss: 1.448e-01]
latex_v1:  91%|######### | 2716/3000 [1:03:20<07:13,  1.53s/it, lr: 1.0e-04 loss: 1.448e-01]
latex_v1:  91%|######### | 2716/3000 [1:03:20<07:13,  1.53s/it, lr: 1.0e-04 loss: 1.448e-01]
latex_v1:  91%|######### | 2716/3000 [1:03:22<07:13,  1.53s/it, lr: 1.0e-04 loss: 6.773e-01]
latex_v1:  91%|######### | 2716/3000 [1:03:22<07:13,  1.53s/it, lr: 1.0e-04 loss: 6.773e-01]
latex_v1:  91%|######### | 2717/3000 [1:03:22<06:57,  1.48s/it, lr: 1.0e-04 loss: 6.773e-01]
latex_v1:  91%|######### | 2717/3000 [1:03:22<06:57,  1.48s/it, lr: 1.0e-04 loss: 6.773e-01]
latex_v1:  91%|######### | 2717/3000 [1:03:23<06:57,  1.48s/it, lr: 1.0e-04 loss: 2.539e-01]
latex_v1:  91%|######### | 2717/3000 [1:03:23<06:57,  1.48s/it, lr: 1.0e-04 loss: 2.539e-01]
latex_v1:  91%|######### | 2718/3000 [1:03:23<06:50,  1.45s/it, lr: 1.0e-04 loss: 2.539e-01]
latex_v1:  91%|######### | 2718/3000 [1:03:23<06:50,  1.45s/it, lr: 1.0e-04 loss: 2.539e-01]
latex_v1:  91%|######### | 2718/3000 [1:03:24<06:50,  1.45s/it, lr: 1.0e-04 loss: 1.643e-01]
latex_v1:  91%|######### | 2718/3000 [1:03:24<06:50,  1.45s/it, lr: 1.0e-04 loss: 1.643e-01]
latex_v1:  91%|######### | 2719/3000 [1:03:24<05:48,  1.24s/it, lr: 1.0e-04 loss: 1.643e-01]
latex_v1:  91%|######### | 2719/3000 [1:03:24<05:48,  1.24s/it, lr: 1.0e-04 loss: 1.643e-01]
latex_v1:  91%|######### | 2719/3000 [1:03:24<05:48,  1.24s/it, lr: 1.0e-04 loss: 3.253e-01]
latex_v1:  91%|######### | 2719/3000 [1:03:24<05:48,  1.24s/it, lr: 1.0e-04 loss: 3.253e-01]
latex_v1:  91%|######### | 2720/3000 [1:03:25<05:47,  1.24s/it, lr: 1.0e-04 loss: 1.677e-01]
latex_v1:  91%|######### | 2720/3000 [1:03:25<05:47,  1.24s/it, lr: 1.0e-04 loss: 1.677e-01]
latex_v1:  91%|######### | 2721/3000 [1:03:25<03:55,  1.19it/s, lr: 1.0e-04 loss: 1.677e-01]
latex_v1:  91%|######### | 2721/3000 [1:03:25<03:55,  1.19it/s, lr: 1.0e-04 loss: 1.677e-01]
latex_v1:  91%|######### | 2721/3000 [1:03:27<03:55,  1.19it/s, lr: 1.0e-04 loss: 5.813e-01]
latex_v1:  91%|######### | 2721/3000 [1:03:27<03:55,  1.19it/s, lr: 1.0e-04 loss: 5.813e-01]
latex_v1:  91%|######### | 2722/3000 [1:03:27<04:35,  1.01it/s, lr: 1.0e-04 loss: 5.813e-01]
latex_v1:  91%|######### | 2722/3000 [1:03:27<04:35,  1.01it/s, lr: 1.0e-04 loss: 5.813e-01]
latex_v1:  91%|######### | 2722/3000 [1:03:28<04:35,  1.01it/s, lr: 1.0e-04 loss: 4.238e-02]
latex_v1:  91%|######### | 2722/3000 [1:03:28<04:35,  1.01it/s, lr: 1.0e-04 loss: 4.238e-02]
latex_v1:  91%|######### | 2723/3000 [1:03:28<05:08,  1.11s/it, lr: 1.0e-04 loss: 4.238e-02]
latex_v1:  91%|######### | 2723/3000 [1:03:28<05:08,  1.11s/it, lr: 1.0e-04 loss: 4.238e-02]
latex_v1:  91%|######### | 2723/3000 [1:03:30<05:08,  1.11s/it, lr: 1.0e-04 loss: 3.919e-02]
latex_v1:  91%|######### | 2723/3000 [1:03:30<05:08,  1.11s/it, lr: 1.0e-04 loss: 3.919e-02]
latex_v1:  91%|######### | 2724/3000 [1:03:30<06:02,  1.31s/it, lr: 1.0e-04 loss: 3.919e-02]
latex_v1:  91%|######### | 2724/3000 [1:03:30<06:02,  1.31s/it, lr: 1.0e-04 loss: 3.919e-02]
latex_v1:  91%|######### | 2724/3000 [1:03:31<06:02,  1.31s/it, lr: 1.0e-04 loss: 5.819e-01]
latex_v1:  91%|######### | 2724/3000 [1:03:31<06:02,  1.31s/it, lr: 1.0e-04 loss: 5.819e-01]
latex_v1:  91%|######### | 2725/3000 [1:03:31<05:17,  1.15s/it, lr: 1.0e-04 loss: 5.819e-01]
latex_v1:  91%|######### | 2725/3000 [1:03:31<05:17,  1.15s/it, lr: 1.0e-04 loss: 5.819e-01]
latex_v1:  91%|######### | 2725/3000 [1:03:32<05:17,  1.15s/it, lr: 1.0e-04 loss: 1.392e-01]
latex_v1:  91%|######### | 2725/3000 [1:03:32<05:17,  1.15s/it, lr: 1.0e-04 loss: 1.392e-01]
latex_v1:  91%|######### | 2726/3000 [1:03:32<05:29,  1.20s/it, lr: 1.0e-04 loss: 1.392e-01]
latex_v1:  91%|######### | 2726/3000 [1:03:32<05:29,  1.20s/it, lr: 1.0e-04 loss: 1.392e-01]
latex_v1:  91%|######### | 2726/3000 [1:03:34<05:29,  1.20s/it, lr: 1.0e-04 loss: 2.623e-01]
latex_v1:  91%|######### | 2726/3000 [1:03:34<05:29,  1.20s/it, lr: 1.0e-04 loss: 2.623e-01]
latex_v1:  91%|######### | 2727/3000 [1:03:34<05:54,  1.30s/it, lr: 1.0e-04 loss: 2.623e-01]
latex_v1:  91%|######### | 2727/3000 [1:03:34<05:54,  1.30s/it, lr: 1.0e-04 loss: 2.623e-01]
latex_v1:  91%|######### | 2727/3000 [1:03:35<05:54,  1.30s/it, lr: 1.0e-04 loss: 1.622e-01]
latex_v1:  91%|######### | 2727/3000 [1:03:35<05:54,  1.30s/it, lr: 1.0e-04 loss: 1.622e-01]
latex_v1:  91%|######### | 2728/3000 [1:03:35<06:11,  1.37s/it, lr: 1.0e-04 loss: 1.622e-01]
latex_v1:  91%|######### | 2728/3000 [1:03:35<06:11,  1.37s/it, lr: 1.0e-04 loss: 1.622e-01]
latex_v1:  91%|######### | 2728/3000 [1:03:36<06:11,  1.37s/it, lr: 1.0e-04 loss: 1.277e-01]
latex_v1:  91%|######### | 2728/3000 [1:03:36<06:11,  1.37s/it, lr: 1.0e-04 loss: 1.277e-01]
latex_v1:  91%|######### | 2729/3000 [1:03:36<05:21,  1.18s/it, lr: 1.0e-04 loss: 1.277e-01]
latex_v1:  91%|######### | 2729/3000 [1:03:36<05:21,  1.18s/it, lr: 1.0e-04 loss: 1.277e-01]
latex_v1:  91%|######### | 2729/3000 [1:03:37<05:21,  1.18s/it, lr: 1.0e-04 loss: 2.741e-01]
latex_v1:  91%|######### | 2729/3000 [1:03:37<05:21,  1.18s/it, lr: 1.0e-04 loss: 2.741e-01]
latex_v1:  91%|#########1| 2730/3000 [1:03:37<05:19,  1.18s/it, lr: 1.0e-04 loss: 8.108e-01]
latex_v1:  91%|#########1| 2730/3000 [1:03:37<05:19,  1.18s/it, lr: 1.0e-04 loss: 8.108e-01]
latex_v1:  91%|#########1| 2731/3000 [1:03:37<03:38,  1.23it/s, lr: 1.0e-04 loss: 8.108e-01]
latex_v1:  91%|#########1| 2731/3000 [1:03:37<03:38,  1.23it/s, lr: 1.0e-04 loss: 8.108e-01]
latex_v1:  91%|#########1| 2731/3000 [1:03:38<03:38,  1.23it/s, lr: 1.0e-04 loss: 5.535e-01]
latex_v1:  91%|#########1| 2731/3000 [1:03:38<03:38,  1.23it/s, lr: 1.0e-04 loss: 5.535e-01]
latex_v1:  91%|#########1| 2732/3000 [1:03:38<03:32,  1.26it/s, lr: 1.0e-04 loss: 5.535e-01]
latex_v1:  91%|#########1| 2732/3000 [1:03:38<03:32,  1.26it/s, lr: 1.0e-04 loss: 5.535e-01]
latex_v1:  91%|#########1| 2732/3000 [1:03:41<03:32,  1.26it/s, lr: 1.0e-04 loss: 6.173e-01]
latex_v1:  91%|#########1| 2732/3000 [1:03:41<03:32,  1.26it/s, lr: 1.0e-04 loss: 6.173e-01]
latex_v1:  91%|#########1| 2733/3000 [1:03:41<05:38,  1.27s/it, lr: 1.0e-04 loss: 6.173e-01]
latex_v1:  91%|#########1| 2733/3000 [1:03:41<05:38,  1.27s/it, lr: 1.0e-04 loss: 6.173e-01]
latex_v1:  91%|#########1| 2733/3000 [1:03:41<05:38,  1.27s/it, lr: 1.0e-04 loss: 7.007e-01]
latex_v1:  91%|#########1| 2733/3000 [1:03:41<05:38,  1.27s/it, lr: 1.0e-04 loss: 7.007e-01]
latex_v1:  91%|#########1| 2734/3000 [1:03:41<04:59,  1.13s/it, lr: 1.0e-04 loss: 7.007e-01]
latex_v1:  91%|#########1| 2734/3000 [1:03:41<04:59,  1.13s/it, lr: 1.0e-04 loss: 7.007e-01]
latex_v1:  91%|#########1| 2734/3000 [1:03:43<04:59,  1.13s/it, lr: 1.0e-04 loss: 1.841e-01]
latex_v1:  91%|#########1| 2734/3000 [1:03:43<04:59,  1.13s/it, lr: 1.0e-04 loss: 1.841e-01]
latex_v1:  91%|#########1| 2735/3000 [1:03:43<05:20,  1.21s/it, lr: 1.0e-04 loss: 1.841e-01]
latex_v1:  91%|#########1| 2735/3000 [1:03:43<05:20,  1.21s/it, lr: 1.0e-04 loss: 1.841e-01]
latex_v1:  91%|#########1| 2735/3000 [1:03:44<05:20,  1.21s/it, lr: 1.0e-04 loss: 3.280e-01]
latex_v1:  91%|#########1| 2735/3000 [1:03:44<05:20,  1.21s/it, lr: 1.0e-04 loss: 3.280e-01]
latex_v1:  91%|#########1| 2736/3000 [1:03:44<04:43,  1.08s/it, lr: 1.0e-04 loss: 3.280e-01]
latex_v1:  91%|#########1| 2736/3000 [1:03:44<04:43,  1.08s/it, lr: 1.0e-04 loss: 3.280e-01]
latex_v1:  91%|#########1| 2736/3000 [1:03:46<04:43,  1.08s/it, lr: 1.0e-04 loss: 5.879e-01]
latex_v1:  91%|#########1| 2736/3000 [1:03:46<04:43,  1.08s/it, lr: 1.0e-04 loss: 5.879e-01]
latex_v1:  91%|#########1| 2737/3000 [1:03:46<06:56,  1.58s/it, lr: 1.0e-04 loss: 5.879e-01]
latex_v1:  91%|#########1| 2737/3000 [1:03:46<06:56,  1.58s/it, lr: 1.0e-04 loss: 5.879e-01]
latex_v1:  91%|#########1| 2737/3000 [1:03:47<06:56,  1.58s/it, lr: 1.0e-04 loss: 1.140e-01]
latex_v1:  91%|#########1| 2737/3000 [1:03:47<06:56,  1.58s/it, lr: 1.0e-04 loss: 1.140e-01]
latex_v1:  91%|#########1| 2738/3000 [1:03:47<05:49,  1.34s/it, lr: 1.0e-04 loss: 1.140e-01]
latex_v1:  91%|#########1| 2738/3000 [1:03:47<05:49,  1.34s/it, lr: 1.0e-04 loss: 1.140e-01]
latex_v1:  91%|#########1| 2738/3000 [1:03:49<05:49,  1.34s/it, lr: 1.0e-04 loss: 6.405e-02]
latex_v1:  91%|#########1| 2738/3000 [1:03:49<05:49,  1.34s/it, lr: 1.0e-04 loss: 6.405e-02]
latex_v1:  91%|#########1| 2739/3000 [1:03:49<06:04,  1.40s/it, lr: 1.0e-04 loss: 6.405e-02]
latex_v1:  91%|#########1| 2739/3000 [1:03:49<06:04,  1.40s/it, lr: 1.0e-04 loss: 6.405e-02]
latex_v1:  91%|#########1| 2739/3000 [1:03:50<06:04,  1.40s/it, lr: 1.0e-04 loss: 1.908e-01]
latex_v1:  91%|#########1| 2739/3000 [1:03:50<06:04,  1.40s/it, lr: 1.0e-04 loss: 1.908e-01]
latex_v1:  91%|#########1| 2740/3000 [1:03:52<06:02,  1.40s/it, lr: 1.0e-04 loss: 2.205e-01]
latex_v1:  91%|#########1| 2740/3000 [1:03:52<06:02,  1.40s/it, lr: 1.0e-04 loss: 2.205e-01]
latex_v1:  91%|#########1| 2741/3000 [1:03:52<05:06,  1.18s/it, lr: 1.0e-04 loss: 2.205e-01]
latex_v1:  91%|#########1| 2741/3000 [1:03:52<05:06,  1.18s/it, lr: 1.0e-04 loss: 2.205e-01]
latex_v1:  91%|#########1| 2741/3000 [1:03:53<05:06,  1.18s/it, lr: 1.0e-04 loss: 2.401e-01]
latex_v1:  91%|#########1| 2741/3000 [1:03:53<05:06,  1.18s/it, lr: 1.0e-04 loss: 2.401e-01]
latex_v1:  91%|#########1| 2742/3000 [1:03:53<04:53,  1.14s/it, lr: 1.0e-04 loss: 2.401e-01]
latex_v1:  91%|#########1| 2742/3000 [1:03:53<04:53,  1.14s/it, lr: 1.0e-04 loss: 2.401e-01]
latex_v1:  91%|#########1| 2742/3000 [1:03:54<04:53,  1.14s/it, lr: 1.0e-04 loss: 2.691e-01]
latex_v1:  91%|#########1| 2742/3000 [1:03:54<04:53,  1.14s/it, lr: 1.0e-04 loss: 2.691e-01]
latex_v1:  91%|#########1| 2743/3000 [1:03:54<04:27,  1.04s/it, lr: 1.0e-04 loss: 2.691e-01]
latex_v1:  91%|#########1| 2743/3000 [1:03:54<04:27,  1.04s/it, lr: 1.0e-04 loss: 2.691e-01]
latex_v1:  91%|#########1| 2743/3000 [1:03:55<04:27,  1.04s/it, lr: 1.0e-04 loss: 8.661e-02]
latex_v1:  91%|#########1| 2743/3000 [1:03:55<04:27,  1.04s/it, lr: 1.0e-04 loss: 8.661e-02]
latex_v1:  91%|#########1| 2744/3000 [1:03:55<05:00,  1.17s/it, lr: 1.0e-04 loss: 8.661e-02]
latex_v1:  91%|#########1| 2744/3000 [1:03:55<05:00,  1.17s/it, lr: 1.0e-04 loss: 8.661e-02]
latex_v1:  91%|#########1| 2744/3000 [1:03:57<05:00,  1.17s/it, lr: 1.0e-04 loss: 3.066e-01]
latex_v1:  91%|#########1| 2744/3000 [1:03:57<05:00,  1.17s/it, lr: 1.0e-04 loss: 3.066e-01]
latex_v1:  92%|#########1| 2745/3000 [1:03:57<05:26,  1.28s/it, lr: 1.0e-04 loss: 3.066e-01]
latex_v1:  92%|#########1| 2745/3000 [1:03:57<05:26,  1.28s/it, lr: 1.0e-04 loss: 3.066e-01]
latex_v1:  92%|#########1| 2745/3000 [1:03:58<05:26,  1.28s/it, lr: 1.0e-04 loss: 7.960e-02]
latex_v1:  92%|#########1| 2745/3000 [1:03:58<05:26,  1.28s/it, lr: 1.0e-04 loss: 7.960e-02]
latex_v1:  92%|#########1| 2746/3000 [1:03:58<05:37,  1.33s/it, lr: 1.0e-04 loss: 7.960e-02]
latex_v1:  92%|#########1| 2746/3000 [1:03:58<05:37,  1.33s/it, lr: 1.0e-04 loss: 7.960e-02]
latex_v1:  92%|#########1| 2746/3000 [1:03:59<05:37,  1.33s/it, lr: 1.0e-04 loss: 6.573e-01]
latex_v1:  92%|#########1| 2746/3000 [1:03:59<05:37,  1.33s/it, lr: 1.0e-04 loss: 6.573e-01]
latex_v1:  92%|#########1| 2747/3000 [1:03:59<04:54,  1.16s/it, lr: 1.0e-04 loss: 6.573e-01]
latex_v1:  92%|#########1| 2747/3000 [1:03:59<04:54,  1.16s/it, lr: 1.0e-04 loss: 6.573e-01]
latex_v1:  92%|#########1| 2747/3000 [1:04:01<04:54,  1.16s/it, lr: 1.0e-04 loss: 3.476e-01]
latex_v1:  92%|#########1| 2747/3000 [1:04:01<04:54,  1.16s/it, lr: 1.0e-04 loss: 3.476e-01]
latex_v1:  92%|#########1| 2748/3000 [1:04:01<05:45,  1.37s/it, lr: 1.0e-04 loss: 3.476e-01]
latex_v1:  92%|#########1| 2748/3000 [1:04:01<05:45,  1.37s/it, lr: 1.0e-04 loss: 3.476e-01]
latex_v1:  92%|#########1| 2748/3000 [1:04:02<05:45,  1.37s/it, lr: 1.0e-04 loss: 2.621e-01]
latex_v1:  92%|#########1| 2748/3000 [1:04:02<05:45,  1.37s/it, lr: 1.0e-04 loss: 2.621e-01]
latex_v1:  92%|#########1| 2749/3000 [1:04:02<05:40,  1.36s/it, lr: 1.0e-04 loss: 2.621e-01]
latex_v1:  92%|#########1| 2749/3000 [1:04:02<05:40,  1.36s/it, lr: 1.0e-04 loss: 2.621e-01]
latex_v1:  92%|#########1| 2749/3000 [1:04:03<05:40,  1.36s/it, lr: 1.0e-04 loss: 5.944e-01]
latex_v1:  92%|#########1| 2749/3000 [1:04:03<05:40,  1.36s/it, lr: 1.0e-04 loss: 5.944e-01]
Saving at step 2750
Saved checkpoint to /data/app/output/latex_v1/latex_v1_000002750.safetensors
Saved optimizer to /data/app/output/latex_v1/optimizer.pt
Removing old save: /data/app/output/latex_v1/latex_v1_000001750.safetensors

latex_v1:  92%|#########1| 2750/3000 [1:04:04<05:39,  1.36s/it, lr: 1.0e-04 loss: 4.832e-01]
latex_v1:  92%|#########1| 2750/3000 [1:04:04<05:39,  1.36s/it, lr: 1.0e-04 loss: 4.832e-01]
latex_v1:  92%|#########1| 2751/3000 [1:04:04<04:00,  1.04it/s, lr: 1.0e-04 loss: 4.832e-01]
latex_v1:  92%|#########1| 2751/3000 [1:04:04<04:00,  1.04it/s, lr: 1.0e-04 loss: 4.832e-01]
latex_v1:  92%|#########1| 2751/3000 [1:04:07<04:00,  1.04it/s, lr: 1.0e-04 loss: 3.205e-01]
latex_v1:  92%|#########1| 2751/3000 [1:04:07<04:00,  1.04it/s, lr: 1.0e-04 loss: 3.205e-01]
latex_v1:  92%|#########1| 2752/3000 [1:04:07<05:12,  1.26s/it, lr: 1.0e-04 loss: 3.205e-01]
latex_v1:  92%|#########1| 2752/3000 [1:04:07<05:12,  1.26s/it, lr: 1.0e-04 loss: 3.205e-01]
latex_v1:  92%|#########1| 2752/3000 [1:04:08<05:12,  1.26s/it, lr: 1.0e-04 loss: 2.336e-01]
latex_v1:  92%|#########1| 2752/3000 [1:04:08<05:12,  1.26s/it, lr: 1.0e-04 loss: 2.336e-01]
latex_v1:  92%|#########1| 2753/3000 [1:04:08<05:16,  1.28s/it, lr: 1.0e-04 loss: 2.336e-01]
latex_v1:  92%|#########1| 2753/3000 [1:04:08<05:16,  1.28s/it, lr: 1.0e-04 loss: 2.336e-01]
latex_v1:  92%|#########1| 2753/3000 [1:04:09<05:16,  1.28s/it, lr: 1.0e-04 loss: 4.950e-01]
latex_v1:  92%|#########1| 2753/3000 [1:04:09<05:16,  1.28s/it, lr: 1.0e-04 loss: 4.950e-01]
latex_v1:  92%|#########1| 2754/3000 [1:04:09<05:16,  1.29s/it, lr: 1.0e-04 loss: 4.950e-01]
latex_v1:  92%|#########1| 2754/3000 [1:04:09<05:16,  1.29s/it, lr: 1.0e-04 loss: 4.950e-01]
latex_v1:  92%|#########1| 2754/3000 [1:04:12<05:16,  1.29s/it, lr: 1.0e-04 loss: 1.579e-01]
latex_v1:  92%|#########1| 2754/3000 [1:04:12<05:16,  1.29s/it, lr: 1.0e-04 loss: 1.579e-01]
latex_v1:  92%|#########1| 2755/3000 [1:04:12<07:00,  1.72s/it, lr: 1.0e-04 loss: 1.579e-01]
latex_v1:  92%|#########1| 2755/3000 [1:04:12<07:00,  1.72s/it, lr: 1.0e-04 loss: 1.579e-01]
latex_v1:  92%|#########1| 2755/3000 [1:04:14<07:00,  1.72s/it, lr: 1.0e-04 loss: 2.072e-01]
latex_v1:  92%|#########1| 2755/3000 [1:04:14<07:00,  1.72s/it, lr: 1.0e-04 loss: 2.072e-01]
latex_v1:  92%|#########1| 2756/3000 [1:04:14<06:59,  1.72s/it, lr: 1.0e-04 loss: 2.072e-01]
latex_v1:  92%|#########1| 2756/3000 [1:04:14<06:59,  1.72s/it, lr: 1.0e-04 loss: 2.072e-01]
latex_v1:  92%|#########1| 2756/3000 [1:04:15<06:59,  1.72s/it, lr: 1.0e-04 loss: 4.321e-01]
latex_v1:  92%|#########1| 2756/3000 [1:04:15<06:59,  1.72s/it, lr: 1.0e-04 loss: 4.321e-01]
latex_v1:  92%|#########1| 2757/3000 [1:04:15<06:38,  1.64s/it, lr: 1.0e-04 loss: 4.321e-01]
latex_v1:  92%|#########1| 2757/3000 [1:04:15<06:38,  1.64s/it, lr: 1.0e-04 loss: 4.321e-01]
latex_v1:  92%|#########1| 2757/3000 [1:04:17<06:38,  1.64s/it, lr: 1.0e-04 loss: 2.231e-01]
latex_v1:  92%|#########1| 2757/3000 [1:04:17<06:38,  1.64s/it, lr: 1.0e-04 loss: 2.231e-01]
latex_v1:  92%|#########1| 2758/3000 [1:04:17<06:28,  1.61s/it, lr: 1.0e-04 loss: 2.231e-01]
latex_v1:  92%|#########1| 2758/3000 [1:04:17<06:28,  1.61s/it, lr: 1.0e-04 loss: 2.231e-01]
latex_v1:  92%|#########1| 2758/3000 [1:04:17<06:28,  1.61s/it, lr: 1.0e-04 loss: 1.078e-01]
latex_v1:  92%|#########1| 2758/3000 [1:04:17<06:28,  1.61s/it, lr: 1.0e-04 loss: 1.078e-01]
latex_v1:  92%|#########1| 2759/3000 [1:04:17<05:26,  1.35s/it, lr: 1.0e-04 loss: 1.078e-01]
latex_v1:  92%|#########1| 2759/3000 [1:04:17<05:26,  1.35s/it, lr: 1.0e-04 loss: 1.078e-01]
latex_v1:  92%|#########1| 2759/3000 [1:04:19<05:26,  1.35s/it, lr: 1.0e-04 loss: 3.104e-01]
latex_v1:  92%|#########1| 2759/3000 [1:04:19<05:26,  1.35s/it, lr: 1.0e-04 loss: 3.104e-01]
latex_v1:  92%|#########2| 2760/3000 [1:04:20<05:25,  1.35s/it, lr: 1.0e-04 loss: 7.362e-01]
latex_v1:  92%|#########2| 2760/3000 [1:04:20<05:25,  1.35s/it, lr: 1.0e-04 loss: 7.362e-01]
latex_v1:  92%|#########2| 2761/3000 [1:04:20<03:59,  1.00s/it, lr: 1.0e-04 loss: 7.362e-01]
latex_v1:  92%|#########2| 2761/3000 [1:04:20<03:59,  1.00s/it, lr: 1.0e-04 loss: 7.362e-01]
latex_v1:  92%|#########2| 2761/3000 [1:04:22<03:59,  1.00s/it, lr: 1.0e-04 loss: 1.237e-01]
latex_v1:  92%|#########2| 2761/3000 [1:04:22<03:59,  1.00s/it, lr: 1.0e-04 loss: 1.237e-01]
latex_v1:  92%|#########2| 2762/3000 [1:04:22<04:30,  1.13s/it, lr: 1.0e-04 loss: 1.237e-01]
latex_v1:  92%|#########2| 2762/3000 [1:04:22<04:30,  1.13s/it, lr: 1.0e-04 loss: 1.237e-01]
latex_v1:  92%|#########2| 2762/3000 [1:04:24<04:30,  1.13s/it, lr: 1.0e-04 loss: 4.238e-01]
latex_v1:  92%|#########2| 2762/3000 [1:04:24<04:30,  1.13s/it, lr: 1.0e-04 loss: 4.238e-01]
latex_v1:  92%|#########2| 2763/3000 [1:04:24<05:23,  1.36s/it, lr: 1.0e-04 loss: 4.238e-01]
latex_v1:  92%|#########2| 2763/3000 [1:04:24<05:23,  1.36s/it, lr: 1.0e-04 loss: 4.238e-01]
latex_v1:  92%|#########2| 2763/3000 [1:04:27<05:23,  1.36s/it, lr: 1.0e-04 loss: 1.227e-01]
latex_v1:  92%|#########2| 2763/3000 [1:04:27<05:23,  1.36s/it, lr: 1.0e-04 loss: 1.227e-01]
latex_v1:  92%|#########2| 2764/3000 [1:04:27<06:57,  1.77s/it, lr: 1.0e-04 loss: 1.227e-01]
latex_v1:  92%|#########2| 2764/3000 [1:04:27<06:57,  1.77s/it, lr: 1.0e-04 loss: 1.227e-01]
latex_v1:  92%|#########2| 2764/3000 [1:04:27<06:57,  1.77s/it, lr: 1.0e-04 loss: 2.549e-01]
latex_v1:  92%|#########2| 2764/3000 [1:04:27<06:57,  1.77s/it, lr: 1.0e-04 loss: 2.549e-01]
latex_v1:  92%|#########2| 2765/3000 [1:04:27<05:48,  1.48s/it, lr: 1.0e-04 loss: 2.549e-01]
latex_v1:  92%|#########2| 2765/3000 [1:04:27<05:48,  1.48s/it, lr: 1.0e-04 loss: 2.549e-01]
latex_v1:  92%|#########2| 2765/3000 [1:04:28<05:48,  1.48s/it, lr: 1.0e-04 loss: 5.568e-01]
latex_v1:  92%|#########2| 2765/3000 [1:04:28<05:48,  1.48s/it, lr: 1.0e-04 loss: 5.568e-01]
latex_v1:  92%|#########2| 2766/3000 [1:04:28<05:00,  1.28s/it, lr: 1.0e-04 loss: 5.568e-01]
latex_v1:  92%|#########2| 2766/3000 [1:04:28<05:00,  1.28s/it, lr: 1.0e-04 loss: 5.568e-01]
latex_v1:  92%|#########2| 2766/3000 [1:04:29<05:00,  1.28s/it, lr: 1.0e-04 loss: 8.642e-02]
latex_v1:  92%|#########2| 2766/3000 [1:04:29<05:00,  1.28s/it, lr: 1.0e-04 loss: 8.642e-02]
latex_v1:  92%|#########2| 2767/3000 [1:04:29<04:22,  1.12s/it, lr: 1.0e-04 loss: 8.642e-02]
latex_v1:  92%|#########2| 2767/3000 [1:04:29<04:22,  1.12s/it, lr: 1.0e-04 loss: 8.642e-02]
latex_v1:  92%|#########2| 2767/3000 [1:04:30<04:22,  1.12s/it, lr: 1.0e-04 loss: 6.398e-01]
latex_v1:  92%|#########2| 2767/3000 [1:04:30<04:22,  1.12s/it, lr: 1.0e-04 loss: 6.398e-01]
latex_v1:  92%|#########2| 2768/3000 [1:04:30<04:24,  1.14s/it, lr: 1.0e-04 loss: 6.398e-01]
latex_v1:  92%|#########2| 2768/3000 [1:04:30<04:24,  1.14s/it, lr: 1.0e-04 loss: 6.398e-01]
latex_v1:  92%|#########2| 2768/3000 [1:04:31<04:24,  1.14s/it, lr: 1.0e-04 loss: 8.470e-01]
latex_v1:  92%|#########2| 2768/3000 [1:04:31<04:24,  1.14s/it, lr: 1.0e-04 loss: 8.470e-01]
latex_v1:  92%|#########2| 2769/3000 [1:04:31<04:10,  1.09s/it, lr: 1.0e-04 loss: 8.470e-01]
latex_v1:  92%|#########2| 2769/3000 [1:04:31<04:10,  1.09s/it, lr: 1.0e-04 loss: 8.470e-01]
latex_v1:  92%|#########2| 2769/3000 [1:04:32<04:10,  1.09s/it, lr: 1.0e-04 loss: 6.489e-01]
latex_v1:  92%|#########2| 2769/3000 [1:04:32<04:10,  1.09s/it, lr: 1.0e-04 loss: 6.489e-01]
latex_v1:  92%|#########2| 2770/3000 [1:04:34<04:09,  1.09s/it, lr: 1.0e-04 loss: 1.009e-01]
latex_v1:  92%|#########2| 2770/3000 [1:04:34<04:09,  1.09s/it, lr: 1.0e-04 loss: 1.009e-01]
latex_v1:  92%|#########2| 2771/3000 [1:04:34<03:29,  1.09it/s, lr: 1.0e-04 loss: 1.009e-01]
latex_v1:  92%|#########2| 2771/3000 [1:04:34<03:29,  1.09it/s, lr: 1.0e-04 loss: 1.009e-01]
latex_v1:  92%|#########2| 2771/3000 [1:04:35<03:29,  1.09it/s, lr: 1.0e-04 loss: 7.900e-01]
latex_v1:  92%|#########2| 2771/3000 [1:04:35<03:29,  1.09it/s, lr: 1.0e-04 loss: 7.900e-01]
latex_v1:  92%|#########2| 2772/3000 [1:04:35<03:43,  1.02it/s, lr: 1.0e-04 loss: 7.900e-01]
latex_v1:  92%|#########2| 2772/3000 [1:04:35<03:43,  1.02it/s, lr: 1.0e-04 loss: 7.900e-01]
latex_v1:  92%|#########2| 2772/3000 [1:04:36<03:43,  1.02it/s, lr: 1.0e-04 loss: 3.842e-01]
latex_v1:  92%|#########2| 2772/3000 [1:04:36<03:43,  1.02it/s, lr: 1.0e-04 loss: 3.842e-01]
latex_v1:  92%|#########2| 2773/3000 [1:04:36<03:29,  1.09it/s, lr: 1.0e-04 loss: 3.842e-01]
latex_v1:  92%|#########2| 2773/3000 [1:04:36<03:29,  1.09it/s, lr: 1.0e-04 loss: 3.842e-01]
latex_v1:  92%|#########2| 2773/3000 [1:04:37<03:29,  1.09it/s, lr: 1.0e-04 loss: 4.021e-01]
latex_v1:  92%|#########2| 2773/3000 [1:04:37<03:29,  1.09it/s, lr: 1.0e-04 loss: 4.021e-01]
latex_v1:  92%|#########2| 2774/3000 [1:04:37<04:05,  1.09s/it, lr: 1.0e-04 loss: 4.021e-01]
latex_v1:  92%|#########2| 2774/3000 [1:04:37<04:05,  1.09s/it, lr: 1.0e-04 loss: 4.021e-01]
latex_v1:  92%|#########2| 2774/3000 [1:04:38<04:05,  1.09s/it, lr: 1.0e-04 loss: 5.473e-01]
latex_v1:  92%|#########2| 2774/3000 [1:04:38<04:05,  1.09s/it, lr: 1.0e-04 loss: 5.473e-01]
latex_v1:  92%|#########2| 2775/3000 [1:04:38<03:45,  1.00s/it, lr: 1.0e-04 loss: 5.473e-01]
latex_v1:  92%|#########2| 2775/3000 [1:04:38<03:45,  1.00s/it, lr: 1.0e-04 loss: 5.473e-01]
latex_v1:  92%|#########2| 2775/3000 [1:04:40<03:45,  1.00s/it, lr: 1.0e-04 loss: 5.285e-01]
latex_v1:  92%|#########2| 2775/3000 [1:04:40<03:45,  1.00s/it, lr: 1.0e-04 loss: 5.285e-01]
latex_v1:  93%|#########2| 2776/3000 [1:04:40<04:40,  1.25s/it, lr: 1.0e-04 loss: 5.285e-01]
latex_v1:  93%|#########2| 2776/3000 [1:04:40<04:40,  1.25s/it, lr: 1.0e-04 loss: 5.285e-01]
latex_v1:  93%|#########2| 2776/3000 [1:04:42<04:40,  1.25s/it, lr: 1.0e-04 loss: 4.222e-01]
latex_v1:  93%|#########2| 2776/3000 [1:04:42<04:40,  1.25s/it, lr: 1.0e-04 loss: 4.222e-01]
latex_v1:  93%|#########2| 2777/3000 [1:04:42<04:58,  1.34s/it, lr: 1.0e-04 loss: 4.222e-01]
latex_v1:  93%|#########2| 2777/3000 [1:04:42<04:58,  1.34s/it, lr: 1.0e-04 loss: 4.222e-01]
latex_v1:  93%|#########2| 2777/3000 [1:04:43<04:58,  1.34s/it, lr: 1.0e-04 loss: 2.818e-01]
latex_v1:  93%|#########2| 2777/3000 [1:04:43<04:58,  1.34s/it, lr: 1.0e-04 loss: 2.818e-01]
latex_v1:  93%|#########2| 2778/3000 [1:04:43<05:12,  1.41s/it, lr: 1.0e-04 loss: 2.818e-01]
latex_v1:  93%|#########2| 2778/3000 [1:04:43<05:12,  1.41s/it, lr: 1.0e-04 loss: 2.818e-01]
latex_v1:  93%|#########2| 2778/3000 [1:04:46<05:12,  1.41s/it, lr: 1.0e-04 loss: 1.783e-01]
latex_v1:  93%|#########2| 2778/3000 [1:04:46<05:12,  1.41s/it, lr: 1.0e-04 loss: 1.783e-01]
latex_v1:  93%|#########2| 2779/3000 [1:04:46<06:48,  1.85s/it, lr: 1.0e-04 loss: 1.783e-01]
latex_v1:  93%|#########2| 2779/3000 [1:04:46<06:48,  1.85s/it, lr: 1.0e-04 loss: 1.783e-01]
latex_v1:  93%|#########2| 2779/3000 [1:04:49<06:48,  1.85s/it, lr: 1.0e-04 loss: 2.243e-01]
latex_v1:  93%|#########2| 2779/3000 [1:04:49<06:48,  1.85s/it, lr: 1.0e-04 loss: 2.243e-01]
latex_v1:  93%|#########2| 2780/3000 [1:04:52<06:46,  1.85s/it, lr: 1.0e-04 loss: 3.883e-01]
latex_v1:  93%|#########2| 2780/3000 [1:04:52<06:46,  1.85s/it, lr: 1.0e-04 loss: 3.883e-01]
latex_v1:  93%|#########2| 2781/3000 [1:04:52<06:00,  1.65s/it, lr: 1.0e-04 loss: 3.883e-01]
latex_v1:  93%|#########2| 2781/3000 [1:04:52<06:00,  1.65s/it, lr: 1.0e-04 loss: 3.883e-01]
latex_v1:  93%|#########2| 2781/3000 [1:04:52<06:00,  1.65s/it, lr: 1.0e-04 loss: 7.292e-01]
latex_v1:  93%|#########2| 2781/3000 [1:04:52<06:00,  1.65s/it, lr: 1.0e-04 loss: 7.292e-01]
latex_v1:  93%|#########2| 2782/3000 [1:04:52<05:11,  1.43s/it, lr: 1.0e-04 loss: 7.292e-01]
latex_v1:  93%|#########2| 2782/3000 [1:04:52<05:11,  1.43s/it, lr: 1.0e-04 loss: 7.292e-01]
latex_v1:  93%|#########2| 2782/3000 [1:04:53<05:11,  1.43s/it, lr: 1.0e-04 loss: 6.814e-01]
latex_v1:  93%|#########2| 2782/3000 [1:04:53<05:11,  1.43s/it, lr: 1.0e-04 loss: 6.814e-01]
latex_v1:  93%|#########2| 2783/3000 [1:04:53<04:31,  1.25s/it, lr: 1.0e-04 loss: 6.814e-01]
latex_v1:  93%|#########2| 2783/3000 [1:04:53<04:31,  1.25s/it, lr: 1.0e-04 loss: 6.814e-01]
latex_v1:  93%|#########2| 2783/3000 [1:04:54<04:31,  1.25s/it, lr: 1.0e-04 loss: 1.469e-01]
latex_v1:  93%|#########2| 2783/3000 [1:04:54<04:31,  1.25s/it, lr: 1.0e-04 loss: 1.469e-01]
latex_v1:  93%|#########2| 2784/3000 [1:04:54<04:18,  1.20s/it, lr: 1.0e-04 loss: 1.469e-01]
latex_v1:  93%|#########2| 2784/3000 [1:04:54<04:18,  1.20s/it, lr: 1.0e-04 loss: 1.469e-01]
latex_v1:  93%|#########2| 2784/3000 [1:04:55<04:18,  1.20s/it, lr: 1.0e-04 loss: 1.687e-01]
latex_v1:  93%|#########2| 2784/3000 [1:04:55<04:18,  1.20s/it, lr: 1.0e-04 loss: 1.687e-01]
latex_v1:  93%|#########2| 2785/3000 [1:04:55<03:50,  1.07s/it, lr: 1.0e-04 loss: 1.687e-01]
latex_v1:  93%|#########2| 2785/3000 [1:04:55<03:50,  1.07s/it, lr: 1.0e-04 loss: 1.687e-01]
latex_v1:  93%|#########2| 2785/3000 [1:04:56<03:50,  1.07s/it, lr: 1.0e-04 loss: 9.120e-02]
latex_v1:  93%|#########2| 2785/3000 [1:04:56<03:50,  1.07s/it, lr: 1.0e-04 loss: 9.120e-02]
latex_v1:  93%|#########2| 2786/3000 [1:04:56<03:29,  1.02it/s, lr: 1.0e-04 loss: 9.120e-02]
latex_v1:  93%|#########2| 2786/3000 [1:04:56<03:29,  1.02it/s, lr: 1.0e-04 loss: 9.120e-02]
latex_v1:  93%|#########2| 2786/3000 [1:04:57<03:29,  1.02it/s, lr: 1.0e-04 loss: 3.553e-01]
latex_v1:  93%|#########2| 2786/3000 [1:04:57<03:29,  1.02it/s, lr: 1.0e-04 loss: 3.553e-01]
latex_v1:  93%|#########2| 2787/3000 [1:04:57<04:05,  1.15s/it, lr: 1.0e-04 loss: 3.553e-01]
latex_v1:  93%|#########2| 2787/3000 [1:04:57<04:05,  1.15s/it, lr: 1.0e-04 loss: 3.553e-01]
latex_v1:  93%|#########2| 2787/3000 [1:04:58<04:05,  1.15s/it, lr: 1.0e-04 loss: 2.636e-01]
latex_v1:  93%|#########2| 2787/3000 [1:04:58<04:05,  1.15s/it, lr: 1.0e-04 loss: 2.636e-01]
latex_v1:  93%|#########2| 2788/3000 [1:04:58<04:05,  1.16s/it, lr: 1.0e-04 loss: 2.636e-01]
latex_v1:  93%|#########2| 2788/3000 [1:04:58<04:05,  1.16s/it, lr: 1.0e-04 loss: 2.636e-01]
latex_v1:  93%|#########2| 2788/3000 [1:05:00<04:05,  1.16s/it, lr: 1.0e-04 loss: 4.993e-01]
latex_v1:  93%|#########2| 2788/3000 [1:05:00<04:05,  1.16s/it, lr: 1.0e-04 loss: 4.993e-01]
latex_v1:  93%|#########2| 2789/3000 [1:05:00<04:30,  1.28s/it, lr: 1.0e-04 loss: 4.993e-01]
latex_v1:  93%|#########2| 2789/3000 [1:05:00<04:30,  1.28s/it, lr: 1.0e-04 loss: 4.993e-01]
latex_v1:  93%|#########2| 2789/3000 [1:05:01<04:30,  1.28s/it, lr: 1.0e-04 loss: 2.942e-01]
latex_v1:  93%|#########2| 2789/3000 [1:05:01<04:30,  1.28s/it, lr: 1.0e-04 loss: 2.942e-01]
latex_v1:  93%|#########3| 2790/3000 [1:05:02<04:28,  1.28s/it, lr: 1.0e-04 loss: 4.132e-01]
latex_v1:  93%|#########3| 2790/3000 [1:05:02<04:28,  1.28s/it, lr: 1.0e-04 loss: 4.132e-01]
latex_v1:  93%|#########3| 2791/3000 [1:05:02<03:02,  1.15it/s, lr: 1.0e-04 loss: 4.132e-01]
latex_v1:  93%|#########3| 2791/3000 [1:05:02<03:02,  1.15it/s, lr: 1.0e-04 loss: 4.132e-01]
latex_v1:  93%|#########3| 2791/3000 [1:05:04<03:02,  1.15it/s, lr: 1.0e-04 loss: 5.256e-01]
latex_v1:  93%|#########3| 2791/3000 [1:05:04<03:02,  1.15it/s, lr: 1.0e-04 loss: 5.256e-01]
latex_v1:  93%|#########3| 2792/3000 [1:05:04<04:06,  1.19s/it, lr: 1.0e-04 loss: 5.256e-01]
latex_v1:  93%|#########3| 2792/3000 [1:05:04<04:06,  1.19s/it, lr: 1.0e-04 loss: 5.256e-01]
latex_v1:  93%|#########3| 2792/3000 [1:05:07<04:06,  1.19s/it, lr: 1.0e-04 loss: 2.427e-02]
latex_v1:  93%|#########3| 2792/3000 [1:05:07<04:06,  1.19s/it, lr: 1.0e-04 loss: 2.427e-02]
latex_v1:  93%|#########3| 2793/3000 [1:05:07<05:37,  1.63s/it, lr: 1.0e-04 loss: 2.427e-02]
latex_v1:  93%|#########3| 2793/3000 [1:05:07<05:37,  1.63s/it, lr: 1.0e-04 loss: 2.427e-02]
latex_v1:  93%|#########3| 2793/3000 [1:05:09<05:37,  1.63s/it, lr: 1.0e-04 loss: 1.079e-01]
latex_v1:  93%|#########3| 2793/3000 [1:05:09<05:37,  1.63s/it, lr: 1.0e-04 loss: 1.079e-01]
latex_v1:  93%|#########3| 2794/3000 [1:05:09<05:36,  1.64s/it, lr: 1.0e-04 loss: 1.079e-01]
latex_v1:  93%|#########3| 2794/3000 [1:05:09<05:36,  1.64s/it, lr: 1.0e-04 loss: 1.079e-01]
latex_v1:  93%|#########3| 2794/3000 [1:05:10<05:36,  1.64s/it, lr: 1.0e-04 loss: 1.969e-01]
latex_v1:  93%|#########3| 2794/3000 [1:05:10<05:36,  1.64s/it, lr: 1.0e-04 loss: 1.969e-01]
latex_v1:  93%|#########3| 2795/3000 [1:05:10<04:45,  1.39s/it, lr: 1.0e-04 loss: 1.969e-01]
latex_v1:  93%|#########3| 2795/3000 [1:05:10<04:45,  1.39s/it, lr: 1.0e-04 loss: 1.969e-01]
latex_v1:  93%|#########3| 2795/3000 [1:05:11<04:45,  1.39s/it, lr: 1.0e-04 loss: 2.854e-01]
latex_v1:  93%|#########3| 2795/3000 [1:05:11<04:45,  1.39s/it, lr: 1.0e-04 loss: 2.854e-01]
latex_v1:  93%|#########3| 2796/3000 [1:05:11<04:47,  1.41s/it, lr: 1.0e-04 loss: 2.854e-01]
latex_v1:  93%|#########3| 2796/3000 [1:05:11<04:47,  1.41s/it, lr: 1.0e-04 loss: 2.854e-01]
latex_v1:  93%|#########3| 2796/3000 [1:05:13<04:47,  1.41s/it, lr: 1.0e-04 loss: 3.666e-01]
latex_v1:  93%|#########3| 2796/3000 [1:05:13<04:47,  1.41s/it, lr: 1.0e-04 loss: 3.666e-01]
latex_v1:  93%|#########3| 2797/3000 [1:05:13<05:14,  1.55s/it, lr: 1.0e-04 loss: 3.666e-01]
latex_v1:  93%|#########3| 2797/3000 [1:05:13<05:14,  1.55s/it, lr: 1.0e-04 loss: 3.666e-01]
latex_v1:  93%|#########3| 2797/3000 [1:05:14<05:14,  1.55s/it, lr: 1.0e-04 loss: 7.163e-01]
latex_v1:  93%|#########3| 2797/3000 [1:05:14<05:14,  1.55s/it, lr: 1.0e-04 loss: 7.163e-01]
latex_v1:  93%|#########3| 2798/3000 [1:05:14<04:51,  1.44s/it, lr: 1.0e-04 loss: 7.163e-01]
latex_v1:  93%|#########3| 2798/3000 [1:05:14<04:51,  1.44s/it, lr: 1.0e-04 loss: 7.163e-01]
latex_v1:  93%|#########3| 2798/3000 [1:05:16<04:51,  1.44s/it, lr: 1.0e-04 loss: 1.206e-01]
latex_v1:  93%|#########3| 2798/3000 [1:05:16<04:51,  1.44s/it, lr: 1.0e-04 loss: 1.206e-01]
latex_v1:  93%|#########3| 2799/3000 [1:05:16<04:48,  1.43s/it, lr: 1.0e-04 loss: 1.206e-01]
latex_v1:  93%|#########3| 2799/3000 [1:05:16<04:48,  1.43s/it, lr: 1.0e-04 loss: 1.206e-01]
latex_v1:  93%|#########3| 2799/3000 [1:05:17<04:48,  1.43s/it, lr: 1.0e-04 loss: 9.551e-02]
latex_v1:  93%|#########3| 2799/3000 [1:05:17<04:48,  1.43s/it, lr: 1.0e-04 loss: 9.551e-02]
latex_v1:  93%|#########3| 2800/3000 [1:05:18<04:46,  1.43s/it, lr: 1.0e-04 loss: 1.819e-01]
latex_v1:  93%|#########3| 2800/3000 [1:05:18<04:46,  1.43s/it, lr: 1.0e-04 loss: 1.819e-01]
latex_v1:  93%|#########3| 2801/3000 [1:05:18<03:09,  1.05it/s, lr: 1.0e-04 loss: 1.819e-01]
latex_v1:  93%|#########3| 2801/3000 [1:05:18<03:09,  1.05it/s, lr: 1.0e-04 loss: 1.819e-01]
latex_v1:  93%|#########3| 2801/3000 [1:05:19<03:09,  1.05it/s, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  93%|#########3| 2801/3000 [1:05:19<03:09,  1.05it/s, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  93%|#########3| 2802/3000 [1:05:19<03:33,  1.08s/it, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  93%|#########3| 2802/3000 [1:05:19<03:33,  1.08s/it, lr: 1.0e-04 loss: 4.547e-01]
latex_v1:  93%|#########3| 2802/3000 [1:05:21<03:33,  1.08s/it, lr: 1.0e-04 loss: 2.511e-01]
latex_v1:  93%|#########3| 2802/3000 [1:05:21<03:33,  1.08s/it, lr: 1.0e-04 loss: 2.511e-01]
latex_v1:  93%|#########3| 2803/3000 [1:05:21<03:37,  1.10s/it, lr: 1.0e-04 loss: 2.511e-01]
latex_v1:  93%|#########3| 2803/3000 [1:05:21<03:37,  1.10s/it, lr: 1.0e-04 loss: 2.511e-01]
latex_v1:  93%|#########3| 2803/3000 [1:05:22<03:37,  1.10s/it, lr: 1.0e-04 loss: 3.459e-01]
latex_v1:  93%|#########3| 2803/3000 [1:05:22<03:37,  1.10s/it, lr: 1.0e-04 loss: 3.459e-01]
latex_v1:  93%|#########3| 2804/3000 [1:05:22<03:55,  1.20s/it, lr: 1.0e-04 loss: 3.459e-01]
latex_v1:  93%|#########3| 2804/3000 [1:05:22<03:55,  1.20s/it, lr: 1.0e-04 loss: 3.459e-01]
latex_v1:  93%|#########3| 2804/3000 [1:05:24<03:55,  1.20s/it, lr: 1.0e-04 loss: 2.190e-01]
latex_v1:  93%|#########3| 2804/3000 [1:05:24<03:55,  1.20s/it, lr: 1.0e-04 loss: 2.190e-01]
latex_v1:  94%|#########3| 2805/3000 [1:05:24<04:44,  1.46s/it, lr: 1.0e-04 loss: 2.190e-01]
latex_v1:  94%|#########3| 2805/3000 [1:05:24<04:44,  1.46s/it, lr: 1.0e-04 loss: 2.190e-01]
latex_v1:  94%|#########3| 2805/3000 [1:05:26<04:44,  1.46s/it, lr: 1.0e-04 loss: 6.277e-01]
latex_v1:  94%|#########3| 2805/3000 [1:05:26<04:44,  1.46s/it, lr: 1.0e-04 loss: 6.277e-01]
latex_v1:  94%|#########3| 2806/3000 [1:05:26<04:38,  1.43s/it, lr: 1.0e-04 loss: 6.277e-01]
latex_v1:  94%|#########3| 2806/3000 [1:05:26<04:38,  1.43s/it, lr: 1.0e-04 loss: 6.277e-01]
latex_v1:  94%|#########3| 2806/3000 [1:05:26<04:38,  1.43s/it, lr: 1.0e-04 loss: 1.416e-01]
latex_v1:  94%|#########3| 2806/3000 [1:05:26<04:38,  1.43s/it, lr: 1.0e-04 loss: 1.416e-01]
latex_v1:  94%|#########3| 2807/3000 [1:05:26<03:59,  1.24s/it, lr: 1.0e-04 loss: 1.416e-01]
latex_v1:  94%|#########3| 2807/3000 [1:05:26<03:59,  1.24s/it, lr: 1.0e-04 loss: 1.416e-01]
latex_v1:  94%|#########3| 2807/3000 [1:05:27<03:59,  1.24s/it, lr: 1.0e-04 loss: 2.459e-02]
latex_v1:  94%|#########3| 2807/3000 [1:05:27<03:59,  1.24s/it, lr: 1.0e-04 loss: 2.459e-02]
latex_v1:  94%|#########3| 2808/3000 [1:05:27<03:31,  1.10s/it, lr: 1.0e-04 loss: 2.459e-02]
latex_v1:  94%|#########3| 2808/3000 [1:05:27<03:31,  1.10s/it, lr: 1.0e-04 loss: 2.459e-02]
latex_v1:  94%|#########3| 2808/3000 [1:05:28<03:31,  1.10s/it, lr: 1.0e-04 loss: 3.031e-01]
latex_v1:  94%|#########3| 2808/3000 [1:05:28<03:31,  1.10s/it, lr: 1.0e-04 loss: 3.031e-01]
latex_v1:  94%|#########3| 2809/3000 [1:05:28<03:34,  1.12s/it, lr: 1.0e-04 loss: 3.031e-01]
latex_v1:  94%|#########3| 2809/3000 [1:05:28<03:34,  1.12s/it, lr: 1.0e-04 loss: 3.031e-01]
latex_v1:  94%|#########3| 2809/3000 [1:05:29<03:34,  1.12s/it, lr: 1.0e-04 loss: 5.382e-01]
latex_v1:  94%|#########3| 2809/3000 [1:05:29<03:34,  1.12s/it, lr: 1.0e-04 loss: 5.382e-01]
latex_v1:  94%|#########3| 2810/3000 [1:05:32<03:33,  1.12s/it, lr: 1.0e-04 loss: 1.141e-01]
latex_v1:  94%|#########3| 2810/3000 [1:05:32<03:33,  1.12s/it, lr: 1.0e-04 loss: 1.141e-01]
latex_v1:  94%|#########3| 2811/3000 [1:05:32<03:59,  1.27s/it, lr: 1.0e-04 loss: 1.141e-01]
latex_v1:  94%|#########3| 2811/3000 [1:05:32<03:59,  1.27s/it, lr: 1.0e-04 loss: 1.141e-01]
latex_v1:  94%|#########3| 2811/3000 [1:05:33<03:59,  1.27s/it, lr: 1.0e-04 loss: 6.090e-01]
latex_v1:  94%|#########3| 2811/3000 [1:05:33<03:59,  1.27s/it, lr: 1.0e-04 loss: 6.090e-01]
latex_v1:  94%|#########3| 2812/3000 [1:05:33<03:34,  1.14s/it, lr: 1.0e-04 loss: 6.090e-01]
latex_v1:  94%|#########3| 2812/3000 [1:05:33<03:34,  1.14s/it, lr: 1.0e-04 loss: 6.090e-01]
latex_v1:  94%|#########3| 2812/3000 [1:05:33<03:34,  1.14s/it, lr: 1.0e-04 loss: 2.026e-01]
latex_v1:  94%|#########3| 2812/3000 [1:05:33<03:34,  1.14s/it, lr: 1.0e-04 loss: 2.026e-01]
latex_v1:  94%|#########3| 2813/3000 [1:05:33<03:13,  1.04s/it, lr: 1.0e-04 loss: 2.026e-01]
latex_v1:  94%|#########3| 2813/3000 [1:05:33<03:13,  1.04s/it, lr: 1.0e-04 loss: 2.026e-01]
latex_v1:  94%|#########3| 2813/3000 [1:05:34<03:13,  1.04s/it, lr: 1.0e-04 loss: 4.583e-01]
latex_v1:  94%|#########3| 2813/3000 [1:05:34<03:13,  1.04s/it, lr: 1.0e-04 loss: 4.583e-01]
latex_v1:  94%|#########3| 2814/3000 [1:05:34<03:13,  1.04s/it, lr: 1.0e-04 loss: 4.583e-01]
latex_v1:  94%|#########3| 2814/3000 [1:05:34<03:13,  1.04s/it, lr: 1.0e-04 loss: 4.583e-01]
latex_v1:  94%|#########3| 2814/3000 [1:05:36<03:13,  1.04s/it, lr: 1.0e-04 loss: 5.849e-01]
latex_v1:  94%|#########3| 2814/3000 [1:05:36<03:13,  1.04s/it, lr: 1.0e-04 loss: 5.849e-01]
latex_v1:  94%|#########3| 2815/3000 [1:05:36<03:37,  1.18s/it, lr: 1.0e-04 loss: 5.849e-01]
latex_v1:  94%|#########3| 2815/3000 [1:05:36<03:37,  1.18s/it, lr: 1.0e-04 loss: 5.849e-01]
latex_v1:  94%|#########3| 2815/3000 [1:05:38<03:37,  1.18s/it, lr: 1.0e-04 loss: 2.890e-01]
latex_v1:  94%|#########3| 2815/3000 [1:05:38<03:37,  1.18s/it, lr: 1.0e-04 loss: 2.890e-01]
latex_v1:  94%|#########3| 2816/3000 [1:05:38<03:56,  1.29s/it, lr: 1.0e-04 loss: 2.890e-01]
latex_v1:  94%|#########3| 2816/3000 [1:05:38<03:56,  1.29s/it, lr: 1.0e-04 loss: 2.890e-01]
latex_v1:  94%|#########3| 2816/3000 [1:05:39<03:56,  1.29s/it, lr: 1.0e-04 loss: 2.203e-01]
latex_v1:  94%|#########3| 2816/3000 [1:05:39<03:56,  1.29s/it, lr: 1.0e-04 loss: 2.203e-01]
latex_v1:  94%|#########3| 2817/3000 [1:05:39<04:09,  1.37s/it, lr: 1.0e-04 loss: 2.203e-01]
latex_v1:  94%|#########3| 2817/3000 [1:05:39<04:09,  1.37s/it, lr: 1.0e-04 loss: 2.203e-01]
latex_v1:  94%|#########3| 2817/3000 [1:05:40<04:09,  1.37s/it, lr: 1.0e-04 loss: 4.431e-01]
latex_v1:  94%|#########3| 2817/3000 [1:05:40<04:09,  1.37s/it, lr: 1.0e-04 loss: 4.431e-01]
latex_v1:  94%|#########3| 2818/3000 [1:05:40<03:47,  1.25s/it, lr: 1.0e-04 loss: 4.431e-01]
latex_v1:  94%|#########3| 2818/3000 [1:05:40<03:47,  1.25s/it, lr: 1.0e-04 loss: 4.431e-01]
latex_v1:  94%|#########3| 2818/3000 [1:05:41<03:47,  1.25s/it, lr: 1.0e-04 loss: 4.485e-01]
latex_v1:  94%|#########3| 2818/3000 [1:05:41<03:47,  1.25s/it, lr: 1.0e-04 loss: 4.485e-01]
latex_v1:  94%|#########3| 2819/3000 [1:05:41<03:19,  1.10s/it, lr: 1.0e-04 loss: 4.485e-01]
latex_v1:  94%|#########3| 2819/3000 [1:05:41<03:19,  1.10s/it, lr: 1.0e-04 loss: 4.485e-01]
latex_v1:  94%|#########3| 2819/3000 [1:05:42<03:19,  1.10s/it, lr: 1.0e-04 loss: 6.024e-01]
latex_v1:  94%|#########3| 2819/3000 [1:05:42<03:19,  1.10s/it, lr: 1.0e-04 loss: 6.024e-01]
latex_v1:  94%|#########3| 2820/3000 [1:05:43<03:18,  1.10s/it, lr: 1.0e-04 loss: 1.560e-01]
latex_v1:  94%|#########3| 2820/3000 [1:05:43<03:18,  1.10s/it, lr: 1.0e-04 loss: 1.560e-01]
latex_v1:  94%|#########4| 2821/3000 [1:05:43<02:17,  1.30it/s, lr: 1.0e-04 loss: 1.560e-01]
latex_v1:  94%|#########4| 2821/3000 [1:05:43<02:17,  1.30it/s, lr: 1.0e-04 loss: 1.560e-01]
latex_v1:  94%|#########4| 2821/3000 [1:05:45<02:17,  1.30it/s, lr: 1.0e-04 loss: 2.664e-01]
latex_v1:  94%|#########4| 2821/3000 [1:05:45<02:17,  1.30it/s, lr: 1.0e-04 loss: 2.664e-01]
latex_v1:  94%|#########4| 2822/3000 [1:05:45<03:06,  1.05s/it, lr: 1.0e-04 loss: 2.664e-01]
latex_v1:  94%|#########4| 2822/3000 [1:05:45<03:06,  1.05s/it, lr: 1.0e-04 loss: 2.664e-01]
latex_v1:  94%|#########4| 2822/3000 [1:05:46<03:06,  1.05s/it, lr: 1.0e-04 loss: 1.898e-01]
latex_v1:  94%|#########4| 2822/3000 [1:05:46<03:06,  1.05s/it, lr: 1.0e-04 loss: 1.898e-01]
latex_v1:  94%|#########4| 2823/3000 [1:05:46<03:22,  1.15s/it, lr: 1.0e-04 loss: 1.898e-01]
latex_v1:  94%|#########4| 2823/3000 [1:05:46<03:22,  1.15s/it, lr: 1.0e-04 loss: 1.898e-01]
latex_v1:  94%|#########4| 2823/3000 [1:05:48<03:22,  1.15s/it, lr: 1.0e-04 loss: 4.118e-01]
latex_v1:  94%|#########4| 2823/3000 [1:05:48<03:22,  1.15s/it, lr: 1.0e-04 loss: 4.118e-01]
latex_v1:  94%|#########4| 2824/3000 [1:05:48<03:39,  1.25s/it, lr: 1.0e-04 loss: 4.118e-01]
latex_v1:  94%|#########4| 2824/3000 [1:05:48<03:39,  1.25s/it, lr: 1.0e-04 loss: 4.118e-01]
latex_v1:  94%|#########4| 2824/3000 [1:05:49<03:39,  1.25s/it, lr: 1.0e-04 loss: 3.063e-01]
latex_v1:  94%|#########4| 2824/3000 [1:05:49<03:39,  1.25s/it, lr: 1.0e-04 loss: 3.063e-01]
latex_v1:  94%|#########4| 2825/3000 [1:05:49<03:44,  1.28s/it, lr: 1.0e-04 loss: 3.063e-01]
latex_v1:  94%|#########4| 2825/3000 [1:05:49<03:44,  1.28s/it, lr: 1.0e-04 loss: 3.063e-01]
latex_v1:  94%|#########4| 2825/3000 [1:05:52<03:44,  1.28s/it, lr: 1.0e-04 loss: 4.335e-01]
latex_v1:  94%|#########4| 2825/3000 [1:05:52<03:44,  1.28s/it, lr: 1.0e-04 loss: 4.335e-01]
latex_v1:  94%|#########4| 2826/3000 [1:05:52<05:03,  1.74s/it, lr: 1.0e-04 loss: 4.335e-01]
latex_v1:  94%|#########4| 2826/3000 [1:05:52<05:03,  1.74s/it, lr: 1.0e-04 loss: 4.335e-01]
latex_v1:  94%|#########4| 2826/3000 [1:05:55<05:03,  1.74s/it, lr: 1.0e-04 loss: 6.139e-01]
latex_v1:  94%|#########4| 2826/3000 [1:05:55<05:03,  1.74s/it, lr: 1.0e-04 loss: 6.139e-01]
latex_v1:  94%|#########4| 2827/3000 [1:05:55<05:49,  2.02s/it, lr: 1.0e-04 loss: 6.139e-01]
latex_v1:  94%|#########4| 2827/3000 [1:05:55<05:49,  2.02s/it, lr: 1.0e-04 loss: 6.139e-01]
latex_v1:  94%|#########4| 2827/3000 [1:05:57<05:49,  2.02s/it, lr: 1.0e-04 loss: 4.256e-01]
latex_v1:  94%|#########4| 2827/3000 [1:05:57<05:49,  2.02s/it, lr: 1.0e-04 loss: 4.256e-01]
latex_v1:  94%|#########4| 2828/3000 [1:05:57<05:43,  2.00s/it, lr: 1.0e-04 loss: 4.256e-01]
latex_v1:  94%|#########4| 2828/3000 [1:05:57<05:43,  2.00s/it, lr: 1.0e-04 loss: 4.256e-01]
latex_v1:  94%|#########4| 2828/3000 [1:05:58<05:43,  2.00s/it, lr: 1.0e-04 loss: 1.305e-01]
latex_v1:  94%|#########4| 2828/3000 [1:05:58<05:43,  2.00s/it, lr: 1.0e-04 loss: 1.305e-01]
latex_v1:  94%|#########4| 2829/3000 [1:05:58<04:38,  1.63s/it, lr: 1.0e-04 loss: 1.305e-01]
latex_v1:  94%|#########4| 2829/3000 [1:05:58<04:38,  1.63s/it, lr: 1.0e-04 loss: 1.305e-01]
latex_v1:  94%|#########4| 2829/3000 [1:05:59<04:38,  1.63s/it, lr: 1.0e-04 loss: 3.273e-01]
latex_v1:  94%|#########4| 2829/3000 [1:05:59<04:38,  1.63s/it, lr: 1.0e-04 loss: 3.273e-01]
latex_v1:  94%|#########4| 2830/3000 [1:06:00<04:36,  1.63s/it, lr: 1.0e-04 loss: 8.444e-01]
latex_v1:  94%|#########4| 2830/3000 [1:06:00<04:36,  1.63s/it, lr: 1.0e-04 loss: 8.444e-01]
latex_v1:  94%|#########4| 2831/3000 [1:06:00<03:06,  1.11s/it, lr: 1.0e-04 loss: 8.444e-01]
latex_v1:  94%|#########4| 2831/3000 [1:06:00<03:06,  1.11s/it, lr: 1.0e-04 loss: 8.444e-01]
latex_v1:  94%|#########4| 2831/3000 [1:06:01<03:06,  1.11s/it, lr: 1.0e-04 loss: 6.073e-01]
latex_v1:  94%|#########4| 2831/3000 [1:06:01<03:06,  1.11s/it, lr: 1.0e-04 loss: 6.073e-01]
latex_v1:  94%|#########4| 2832/3000 [1:06:02<03:24,  1.21s/it, lr: 1.0e-04 loss: 6.073e-01]
latex_v1:  94%|#########4| 2832/3000 [1:06:02<03:24,  1.21s/it, lr: 1.0e-04 loss: 6.073e-01]
latex_v1:  94%|#########4| 2832/3000 [1:06:03<03:24,  1.21s/it, lr: 1.0e-04 loss: 1.760e-01]
latex_v1:  94%|#########4| 2832/3000 [1:06:03<03:24,  1.21s/it, lr: 1.0e-04 loss: 1.760e-01]
latex_v1:  94%|#########4| 2833/3000 [1:06:03<03:34,  1.29s/it, lr: 1.0e-04 loss: 1.760e-01]
latex_v1:  94%|#########4| 2833/3000 [1:06:03<03:34,  1.29s/it, lr: 1.0e-04 loss: 1.760e-01]
latex_v1:  94%|#########4| 2833/3000 [1:06:04<03:34,  1.29s/it, lr: 1.0e-04 loss: 7.410e-01]
latex_v1:  94%|#########4| 2833/3000 [1:06:04<03:34,  1.29s/it, lr: 1.0e-04 loss: 7.410e-01]
latex_v1:  94%|#########4| 2834/3000 [1:06:04<03:09,  1.14s/it, lr: 1.0e-04 loss: 7.410e-01]
latex_v1:  94%|#########4| 2834/3000 [1:06:04<03:09,  1.14s/it, lr: 1.0e-04 loss: 7.410e-01]
latex_v1:  94%|#########4| 2834/3000 [1:06:05<03:09,  1.14s/it, lr: 1.0e-04 loss: 4.616e-01]
latex_v1:  94%|#########4| 2834/3000 [1:06:05<03:09,  1.14s/it, lr: 1.0e-04 loss: 4.616e-01]
latex_v1:  94%|#########4| 2835/3000 [1:06:05<03:26,  1.25s/it, lr: 1.0e-04 loss: 4.616e-01]
latex_v1:  94%|#########4| 2835/3000 [1:06:05<03:26,  1.25s/it, lr: 1.0e-04 loss: 4.616e-01]
latex_v1:  94%|#########4| 2835/3000 [1:06:07<03:26,  1.25s/it, lr: 1.0e-04 loss: 5.839e-01]
latex_v1:  94%|#########4| 2835/3000 [1:06:07<03:26,  1.25s/it, lr: 1.0e-04 loss: 5.839e-01]
latex_v1:  95%|#########4| 2836/3000 [1:06:07<03:39,  1.34s/it, lr: 1.0e-04 loss: 5.839e-01]
latex_v1:  95%|#########4| 2836/3000 [1:06:07<03:39,  1.34s/it, lr: 1.0e-04 loss: 5.839e-01]
latex_v1:  95%|#########4| 2836/3000 [1:06:08<03:39,  1.34s/it, lr: 1.0e-04 loss: 5.481e-01]
latex_v1:  95%|#########4| 2836/3000 [1:06:08<03:39,  1.34s/it, lr: 1.0e-04 loss: 5.481e-01]
latex_v1:  95%|#########4| 2837/3000 [1:06:08<03:10,  1.17s/it, lr: 1.0e-04 loss: 5.481e-01]
latex_v1:  95%|#########4| 2837/3000 [1:06:08<03:10,  1.17s/it, lr: 1.0e-04 loss: 5.481e-01]
latex_v1:  95%|#########4| 2837/3000 [1:06:08<03:10,  1.17s/it, lr: 1.0e-04 loss: 6.493e-01]
latex_v1:  95%|#########4| 2837/3000 [1:06:08<03:10,  1.17s/it, lr: 1.0e-04 loss: 6.493e-01]
latex_v1:  95%|#########4| 2838/3000 [1:06:08<02:50,  1.05s/it, lr: 1.0e-04 loss: 6.493e-01]
latex_v1:  95%|#########4| 2838/3000 [1:06:08<02:50,  1.05s/it, lr: 1.0e-04 loss: 6.493e-01]
latex_v1:  95%|#########4| 2838/3000 [1:06:09<02:50,  1.05s/it, lr: 1.0e-04 loss: 4.518e-01]
latex_v1:  95%|#########4| 2838/3000 [1:06:09<02:50,  1.05s/it, lr: 1.0e-04 loss: 4.518e-01]
latex_v1:  95%|#########4| 2839/3000 [1:06:09<02:35,  1.04it/s, lr: 1.0e-04 loss: 4.518e-01]
latex_v1:  95%|#########4| 2839/3000 [1:06:09<02:35,  1.04it/s, lr: 1.0e-04 loss: 4.518e-01]
latex_v1:  95%|#########4| 2839/3000 [1:06:10<02:35,  1.04it/s, lr: 1.0e-04 loss: 2.899e-01]
latex_v1:  95%|#########4| 2839/3000 [1:06:10<02:35,  1.04it/s, lr: 1.0e-04 loss: 2.899e-01]
latex_v1:  95%|#########4| 2840/3000 [1:06:11<02:34,  1.04it/s, lr: 1.0e-04 loss: 3.042e-01]
latex_v1:  95%|#########4| 2840/3000 [1:06:11<02:34,  1.04it/s, lr: 1.0e-04 loss: 3.042e-01]
latex_v1:  95%|#########4| 2841/3000 [1:06:11<01:50,  1.44it/s, lr: 1.0e-04 loss: 3.042e-01]
latex_v1:  95%|#########4| 2841/3000 [1:06:11<01:50,  1.44it/s, lr: 1.0e-04 loss: 3.042e-01]
latex_v1:  95%|#########4| 2841/3000 [1:06:11<01:50,  1.44it/s, lr: 1.0e-04 loss: 7.059e-01]
latex_v1:  95%|#########4| 2841/3000 [1:06:11<01:50,  1.44it/s, lr: 1.0e-04 loss: 7.059e-01]
latex_v1:  95%|#########4| 2842/3000 [1:06:11<01:51,  1.42it/s, lr: 1.0e-04 loss: 7.059e-01]
latex_v1:  95%|#########4| 2842/3000 [1:06:11<01:51,  1.42it/s, lr: 1.0e-04 loss: 7.059e-01]
latex_v1:  95%|#########4| 2842/3000 [1:06:13<01:51,  1.42it/s, lr: 1.0e-04 loss: 4.425e-01]
latex_v1:  95%|#########4| 2842/3000 [1:06:13<01:51,  1.42it/s, lr: 1.0e-04 loss: 4.425e-01]
latex_v1:  95%|#########4| 2843/3000 [1:06:13<02:21,  1.11it/s, lr: 1.0e-04 loss: 4.425e-01]
latex_v1:  95%|#########4| 2843/3000 [1:06:13<02:21,  1.11it/s, lr: 1.0e-04 loss: 4.425e-01]
latex_v1:  95%|#########4| 2843/3000 [1:06:14<02:21,  1.11it/s, lr: 1.0e-04 loss: 6.687e-01]
latex_v1:  95%|#########4| 2843/3000 [1:06:14<02:21,  1.11it/s, lr: 1.0e-04 loss: 6.687e-01]
latex_v1:  95%|#########4| 2844/3000 [1:06:14<02:47,  1.07s/it, lr: 1.0e-04 loss: 6.687e-01]
latex_v1:  95%|#########4| 2844/3000 [1:06:14<02:47,  1.07s/it, lr: 1.0e-04 loss: 6.687e-01]
latex_v1:  95%|#########4| 2844/3000 [1:06:17<02:47,  1.07s/it, lr: 1.0e-04 loss: 1.339e-01]
latex_v1:  95%|#########4| 2844/3000 [1:06:17<02:47,  1.07s/it, lr: 1.0e-04 loss: 1.339e-01]
latex_v1:  95%|#########4| 2845/3000 [1:06:17<04:02,  1.57s/it, lr: 1.0e-04 loss: 1.339e-01]
latex_v1:  95%|#########4| 2845/3000 [1:06:17<04:02,  1.57s/it, lr: 1.0e-04 loss: 1.339e-01]
latex_v1:  95%|#########4| 2845/3000 [1:06:19<04:02,  1.57s/it, lr: 1.0e-04 loss: 3.302e-02]
latex_v1:  95%|#########4| 2845/3000 [1:06:19<04:02,  1.57s/it, lr: 1.0e-04 loss: 3.302e-02]
latex_v1:  95%|#########4| 2846/3000 [1:06:19<04:28,  1.74s/it, lr: 1.0e-04 loss: 3.302e-02]
latex_v1:  95%|#########4| 2846/3000 [1:06:19<04:28,  1.74s/it, lr: 1.0e-04 loss: 3.302e-02]
latex_v1:  95%|#########4| 2846/3000 [1:06:21<04:28,  1.74s/it, lr: 1.0e-04 loss: 7.851e-02]
latex_v1:  95%|#########4| 2846/3000 [1:06:21<04:28,  1.74s/it, lr: 1.0e-04 loss: 7.851e-02]
latex_v1:  95%|#########4| 2847/3000 [1:06:21<04:40,  1.83s/it, lr: 1.0e-04 loss: 7.851e-02]
latex_v1:  95%|#########4| 2847/3000 [1:06:21<04:40,  1.83s/it, lr: 1.0e-04 loss: 7.851e-02]
latex_v1:  95%|#########4| 2847/3000 [1:06:23<04:40,  1.83s/it, lr: 1.0e-04 loss: 1.843e-01]
latex_v1:  95%|#########4| 2847/3000 [1:06:23<04:40,  1.83s/it, lr: 1.0e-04 loss: 1.843e-01]
latex_v1:  95%|#########4| 2848/3000 [1:06:23<04:24,  1.74s/it, lr: 1.0e-04 loss: 1.843e-01]
latex_v1:  95%|#########4| 2848/3000 [1:06:23<04:24,  1.74s/it, lr: 1.0e-04 loss: 1.843e-01]
latex_v1:  95%|#########4| 2848/3000 [1:06:24<04:24,  1.74s/it, lr: 1.0e-04 loss: 4.441e-01]
latex_v1:  95%|#########4| 2848/3000 [1:06:24<04:24,  1.74s/it, lr: 1.0e-04 loss: 4.441e-01]
latex_v1:  95%|#########4| 2849/3000 [1:06:25<04:14,  1.68s/it, lr: 1.0e-04 loss: 4.441e-01]
latex_v1:  95%|#########4| 2849/3000 [1:06:25<04:14,  1.68s/it, lr: 1.0e-04 loss: 4.441e-01]
latex_v1:  95%|#########4| 2849/3000 [1:06:26<04:14,  1.68s/it, lr: 1.0e-04 loss: 2.468e-01]
latex_v1:  95%|#########4| 2849/3000 [1:06:26<04:14,  1.68s/it, lr: 1.0e-04 loss: 2.468e-01]
latex_v1:  95%|#########5| 2850/3000 [1:06:29<04:12,  1.68s/it, lr: 1.0e-04 loss: 1.328e-01]
latex_v1:  95%|#########5| 2850/3000 [1:06:29<04:12,  1.68s/it, lr: 1.0e-04 loss: 1.328e-01]
latex_v1:  95%|#########5| 2851/3000 [1:06:29<03:53,  1.57s/it, lr: 1.0e-04 loss: 1.328e-01]
latex_v1:  95%|#########5| 2851/3000 [1:06:29<03:53,  1.57s/it, lr: 1.0e-04 loss: 1.328e-01]
latex_v1:  95%|#########5| 2851/3000 [1:06:32<03:53,  1.57s/it, lr: 1.0e-04 loss: 4.205e-01]
latex_v1:  95%|#########5| 2851/3000 [1:06:32<03:53,  1.57s/it, lr: 1.0e-04 loss: 4.205e-01]
latex_v1:  95%|#########5| 2852/3000 [1:06:32<04:31,  1.83s/it, lr: 1.0e-04 loss: 4.205e-01]
latex_v1:  95%|#########5| 2852/3000 [1:06:32<04:31,  1.83s/it, lr: 1.0e-04 loss: 4.205e-01]
latex_v1:  95%|#########5| 2852/3000 [1:06:33<04:31,  1.83s/it, lr: 1.0e-04 loss: 1.550e-01]
latex_v1:  95%|#########5| 2852/3000 [1:06:33<04:31,  1.83s/it, lr: 1.0e-04 loss: 1.550e-01]
latex_v1:  95%|#########5| 2853/3000 [1:06:33<04:10,  1.70s/it, lr: 1.0e-04 loss: 1.550e-01]
latex_v1:  95%|#########5| 2853/3000 [1:06:33<04:10,  1.70s/it, lr: 1.0e-04 loss: 1.550e-01]
latex_v1:  95%|#########5| 2853/3000 [1:06:34<04:10,  1.70s/it, lr: 1.0e-04 loss: 5.283e-01]
latex_v1:  95%|#########5| 2853/3000 [1:06:34<04:10,  1.70s/it, lr: 1.0e-04 loss: 5.283e-01]
latex_v1:  95%|#########5| 2854/3000 [1:06:34<03:30,  1.44s/it, lr: 1.0e-04 loss: 5.283e-01]
latex_v1:  95%|#########5| 2854/3000 [1:06:34<03:30,  1.44s/it, lr: 1.0e-04 loss: 5.283e-01]
latex_v1:  95%|#########5| 2854/3000 [1:06:34<03:30,  1.44s/it, lr: 1.0e-04 loss: 4.172e-01]
latex_v1:  95%|#########5| 2854/3000 [1:06:34<03:30,  1.44s/it, lr: 1.0e-04 loss: 4.172e-01]
latex_v1:  95%|#########5| 2855/3000 [1:06:34<03:01,  1.25s/it, lr: 1.0e-04 loss: 4.172e-01]
latex_v1:  95%|#########5| 2855/3000 [1:06:34<03:01,  1.25s/it, lr: 1.0e-04 loss: 4.172e-01]
latex_v1:  95%|#########5| 2855/3000 [1:06:36<03:01,  1.25s/it, lr: 1.0e-04 loss: 4.331e-01]
latex_v1:  95%|#########5| 2855/3000 [1:06:36<03:01,  1.25s/it, lr: 1.0e-04 loss: 4.331e-01]
latex_v1:  95%|#########5| 2856/3000 [1:06:36<03:07,  1.30s/it, lr: 1.0e-04 loss: 4.331e-01]
latex_v1:  95%|#########5| 2856/3000 [1:06:36<03:07,  1.30s/it, lr: 1.0e-04 loss: 4.331e-01]
latex_v1:  95%|#########5| 2856/3000 [1:06:38<03:07,  1.30s/it, lr: 1.0e-04 loss: 4.107e-01]
latex_v1:  95%|#########5| 2856/3000 [1:06:38<03:07,  1.30s/it, lr: 1.0e-04 loss: 4.107e-01]
latex_v1:  95%|#########5| 2857/3000 [1:06:38<03:30,  1.47s/it, lr: 1.0e-04 loss: 4.107e-01]
latex_v1:  95%|#########5| 2857/3000 [1:06:38<03:30,  1.47s/it, lr: 1.0e-04 loss: 4.107e-01]
latex_v1:  95%|#########5| 2857/3000 [1:06:39<03:30,  1.47s/it, lr: 1.0e-04 loss: 5.776e-01]
latex_v1:  95%|#########5| 2857/3000 [1:06:39<03:30,  1.47s/it, lr: 1.0e-04 loss: 5.776e-01]
latex_v1:  95%|#########5| 2858/3000 [1:06:39<03:32,  1.49s/it, lr: 1.0e-04 loss: 5.776e-01]
latex_v1:  95%|#########5| 2858/3000 [1:06:39<03:32,  1.49s/it, lr: 1.0e-04 loss: 5.776e-01]
latex_v1:  95%|#########5| 2858/3000 [1:06:42<03:32,  1.49s/it, lr: 1.0e-04 loss: 5.571e-01]
latex_v1:  95%|#########5| 2858/3000 [1:06:42<03:32,  1.49s/it, lr: 1.0e-04 loss: 5.571e-01]
latex_v1:  95%|#########5| 2859/3000 [1:06:42<04:28,  1.91s/it, lr: 1.0e-04 loss: 5.571e-01]
latex_v1:  95%|#########5| 2859/3000 [1:06:42<04:28,  1.91s/it, lr: 1.0e-04 loss: 5.571e-01]
latex_v1:  95%|#########5| 2859/3000 [1:06:44<04:28,  1.91s/it, lr: 1.0e-04 loss: 4.320e-01]
latex_v1:  95%|#########5| 2859/3000 [1:06:44<04:28,  1.91s/it, lr: 1.0e-04 loss: 4.320e-01]
latex_v1:  95%|#########5| 2860/3000 [1:06:44<04:26,  1.91s/it, lr: 1.0e-04 loss: 4.166e-01]
latex_v1:  95%|#########5| 2860/3000 [1:06:44<04:26,  1.91s/it, lr: 1.0e-04 loss: 4.166e-01]
latex_v1:  95%|#########5| 2861/3000 [1:06:44<02:47,  1.21s/it, lr: 1.0e-04 loss: 4.166e-01]
latex_v1:  95%|#########5| 2861/3000 [1:06:44<02:47,  1.21s/it, lr: 1.0e-04 loss: 4.166e-01]
latex_v1:  95%|#########5| 2861/3000 [1:06:46<02:47,  1.21s/it, lr: 1.0e-04 loss: 9.224e-02]
latex_v1:  95%|#########5| 2861/3000 [1:06:46<02:47,  1.21s/it, lr: 1.0e-04 loss: 9.224e-02]
latex_v1:  95%|#########5| 2862/3000 [1:06:46<02:57,  1.29s/it, lr: 1.0e-04 loss: 9.224e-02]
latex_v1:  95%|#########5| 2862/3000 [1:06:46<02:57,  1.29s/it, lr: 1.0e-04 loss: 9.224e-02]
latex_v1:  95%|#########5| 2862/3000 [1:06:47<02:57,  1.29s/it, lr: 1.0e-04 loss: 5.689e-01]
latex_v1:  95%|#########5| 2862/3000 [1:06:47<02:57,  1.29s/it, lr: 1.0e-04 loss: 5.689e-01]
latex_v1:  95%|#########5| 2863/3000 [1:06:47<02:37,  1.15s/it, lr: 1.0e-04 loss: 5.689e-01]
latex_v1:  95%|#########5| 2863/3000 [1:06:47<02:37,  1.15s/it, lr: 1.0e-04 loss: 5.689e-01]
latex_v1:  95%|#########5| 2863/3000 [1:06:48<02:37,  1.15s/it, lr: 1.0e-04 loss: 5.720e-02]
latex_v1:  95%|#########5| 2863/3000 [1:06:48<02:37,  1.15s/it, lr: 1.0e-04 loss: 5.720e-02]
latex_v1:  95%|#########5| 2864/3000 [1:06:48<02:47,  1.23s/it, lr: 1.0e-04 loss: 5.720e-02]
latex_v1:  95%|#########5| 2864/3000 [1:06:48<02:47,  1.23s/it, lr: 1.0e-04 loss: 5.720e-02]
latex_v1:  95%|#########5| 2864/3000 [1:06:49<02:47,  1.23s/it, lr: 1.0e-04 loss: 4.555e-02]
latex_v1:  95%|#########5| 2864/3000 [1:06:49<02:47,  1.23s/it, lr: 1.0e-04 loss: 4.555e-02]
latex_v1:  96%|#########5| 2865/3000 [1:06:49<02:28,  1.10s/it, lr: 1.0e-04 loss: 4.555e-02]
latex_v1:  96%|#########5| 2865/3000 [1:06:49<02:28,  1.10s/it, lr: 1.0e-04 loss: 4.555e-02]
latex_v1:  96%|#########5| 2865/3000 [1:06:50<02:28,  1.10s/it, lr: 1.0e-04 loss: 5.652e-01]
latex_v1:  96%|#########5| 2865/3000 [1:06:50<02:28,  1.10s/it, lr: 1.0e-04 loss: 5.652e-01]
latex_v1:  96%|#########5| 2866/3000 [1:06:50<02:41,  1.21s/it, lr: 1.0e-04 loss: 5.652e-01]
latex_v1:  96%|#########5| 2866/3000 [1:06:50<02:41,  1.21s/it, lr: 1.0e-04 loss: 5.652e-01]
latex_v1:  96%|#########5| 2866/3000 [1:06:51<02:41,  1.21s/it, lr: 1.0e-04 loss: 5.144e-01]
latex_v1:  96%|#########5| 2866/3000 [1:06:51<02:41,  1.21s/it, lr: 1.0e-04 loss: 5.144e-01]
latex_v1:  96%|#########5| 2867/3000 [1:06:51<02:23,  1.08s/it, lr: 1.0e-04 loss: 5.144e-01]
latex_v1:  96%|#########5| 2867/3000 [1:06:51<02:23,  1.08s/it, lr: 1.0e-04 loss: 5.144e-01]
latex_v1:  96%|#########5| 2867/3000 [1:06:52<02:23,  1.08s/it, lr: 1.0e-04 loss: 9.557e-02]
latex_v1:  96%|#########5| 2867/3000 [1:06:52<02:23,  1.08s/it, lr: 1.0e-04 loss: 9.557e-02]
latex_v1:  96%|#########5| 2868/3000 [1:06:52<02:09,  1.02it/s, lr: 1.0e-04 loss: 9.557e-02]
latex_v1:  96%|#########5| 2868/3000 [1:06:52<02:09,  1.02it/s, lr: 1.0e-04 loss: 9.557e-02]
latex_v1:  96%|#########5| 2868/3000 [1:06:53<02:09,  1.02it/s, lr: 1.0e-04 loss: 8.679e-01]
latex_v1:  96%|#########5| 2868/3000 [1:06:53<02:09,  1.02it/s, lr: 1.0e-04 loss: 8.679e-01]
latex_v1:  96%|#########5| 2869/3000 [1:06:53<02:16,  1.04s/it, lr: 1.0e-04 loss: 8.679e-01]
latex_v1:  96%|#########5| 2869/3000 [1:06:53<02:16,  1.04s/it, lr: 1.0e-04 loss: 8.679e-01]
latex_v1:  96%|#########5| 2869/3000 [1:06:54<02:16,  1.04s/it, lr: 1.0e-04 loss: 7.135e-01]
latex_v1:  96%|#########5| 2869/3000 [1:06:54<02:16,  1.04s/it, lr: 1.0e-04 loss: 7.135e-01]
latex_v1:  96%|#########5| 2870/3000 [1:06:55<02:15,  1.04s/it, lr: 1.0e-04 loss: 1.215e-01]
latex_v1:  96%|#########5| 2870/3000 [1:06:55<02:15,  1.04s/it, lr: 1.0e-04 loss: 1.215e-01]
latex_v1:  96%|#########5| 2871/3000 [1:06:55<01:35,  1.34it/s, lr: 1.0e-04 loss: 1.215e-01]
latex_v1:  96%|#########5| 2871/3000 [1:06:55<01:35,  1.34it/s, lr: 1.0e-04 loss: 1.215e-01]
latex_v1:  96%|#########5| 2871/3000 [1:06:56<01:35,  1.34it/s, lr: 1.0e-04 loss: 5.802e-01]
latex_v1:  96%|#########5| 2871/3000 [1:06:56<01:35,  1.34it/s, lr: 1.0e-04 loss: 5.802e-01]
latex_v1:  96%|#########5| 2872/3000 [1:06:56<01:35,  1.33it/s, lr: 1.0e-04 loss: 5.802e-01]
latex_v1:  96%|#########5| 2872/3000 [1:06:56<01:35,  1.33it/s, lr: 1.0e-04 loss: 5.802e-01]
latex_v1:  96%|#########5| 2872/3000 [1:06:57<01:35,  1.33it/s, lr: 1.0e-04 loss: 4.205e-01]
latex_v1:  96%|#########5| 2872/3000 [1:06:57<01:35,  1.33it/s, lr: 1.0e-04 loss: 4.205e-01]
latex_v1:  96%|#########5| 2873/3000 [1:06:57<01:44,  1.22it/s, lr: 1.0e-04 loss: 4.205e-01]
latex_v1:  96%|#########5| 2873/3000 [1:06:57<01:44,  1.22it/s, lr: 1.0e-04 loss: 4.205e-01]
latex_v1:  96%|#########5| 2873/3000 [1:06:58<01:44,  1.22it/s, lr: 1.0e-04 loss: 4.062e-01]
latex_v1:  96%|#########5| 2873/3000 [1:06:58<01:44,  1.22it/s, lr: 1.0e-04 loss: 4.062e-01]
latex_v1:  96%|#########5| 2874/3000 [1:06:58<01:51,  1.13it/s, lr: 1.0e-04 loss: 4.062e-01]
latex_v1:  96%|#########5| 2874/3000 [1:06:58<01:51,  1.13it/s, lr: 1.0e-04 loss: 4.062e-01]
latex_v1:  96%|#########5| 2874/3000 [1:07:01<01:51,  1.13it/s, lr: 1.0e-04 loss: 1.440e-01]
latex_v1:  96%|#########5| 2874/3000 [1:07:01<01:51,  1.13it/s, lr: 1.0e-04 loss: 1.440e-01]
latex_v1:  96%|#########5| 2875/3000 [1:07:01<02:59,  1.44s/it, lr: 1.0e-04 loss: 1.440e-01]
latex_v1:  96%|#########5| 2875/3000 [1:07:01<02:59,  1.44s/it, lr: 1.0e-04 loss: 1.440e-01]
latex_v1:  96%|#########5| 2875/3000 [1:07:02<02:59,  1.44s/it, lr: 1.0e-04 loss: 2.295e-01]
latex_v1:  96%|#########5| 2875/3000 [1:07:02<02:59,  1.44s/it, lr: 1.0e-04 loss: 2.295e-01]
latex_v1:  96%|#########5| 2876/3000 [1:07:02<02:55,  1.42s/it, lr: 1.0e-04 loss: 2.295e-01]
latex_v1:  96%|#########5| 2876/3000 [1:07:02<02:55,  1.42s/it, lr: 1.0e-04 loss: 2.295e-01]
latex_v1:  96%|#########5| 2876/3000 [1:07:04<02:55,  1.42s/it, lr: 1.0e-04 loss: 1.548e-01]
latex_v1:  96%|#########5| 2876/3000 [1:07:04<02:55,  1.42s/it, lr: 1.0e-04 loss: 1.548e-01]
latex_v1:  96%|#########5| 2877/3000 [1:07:04<02:51,  1.39s/it, lr: 1.0e-04 loss: 1.548e-01]
latex_v1:  96%|#########5| 2877/3000 [1:07:04<02:51,  1.39s/it, lr: 1.0e-04 loss: 1.548e-01]
latex_v1:  96%|#########5| 2877/3000 [1:07:05<02:51,  1.39s/it, lr: 1.0e-04 loss: 3.156e-02]
latex_v1:  96%|#########5| 2877/3000 [1:07:05<02:51,  1.39s/it, lr: 1.0e-04 loss: 3.156e-02]
latex_v1:  96%|#########5| 2878/3000 [1:07:05<02:42,  1.33s/it, lr: 1.0e-04 loss: 3.156e-02]
latex_v1:  96%|#########5| 2878/3000 [1:07:05<02:42,  1.33s/it, lr: 1.0e-04 loss: 3.156e-02]
latex_v1:  96%|#########5| 2878/3000 [1:07:05<02:42,  1.33s/it, lr: 1.0e-04 loss: 6.921e-01]
latex_v1:  96%|#########5| 2878/3000 [1:07:05<02:42,  1.33s/it, lr: 1.0e-04 loss: 6.921e-01]
latex_v1:  96%|#########5| 2879/3000 [1:07:05<02:20,  1.16s/it, lr: 1.0e-04 loss: 6.921e-01]
latex_v1:  96%|#########5| 2879/3000 [1:07:05<02:20,  1.16s/it, lr: 1.0e-04 loss: 6.921e-01]
latex_v1:  96%|#########5| 2879/3000 [1:07:08<02:20,  1.16s/it, lr: 1.0e-04 loss: 7.278e-01]
latex_v1:  96%|#########5| 2879/3000 [1:07:08<02:20,  1.16s/it, lr: 1.0e-04 loss: 7.278e-01]
latex_v1:  96%|#########6| 2880/3000 [1:07:10<02:19,  1.16s/it, lr: 1.0e-04 loss: 7.692e-02]
latex_v1:  96%|#########6| 2880/3000 [1:07:10<02:19,  1.16s/it, lr: 1.0e-04 loss: 7.692e-02]
latex_v1:  96%|#########6| 2881/3000 [1:07:10<02:02,  1.03s/it, lr: 1.0e-04 loss: 7.692e-02]
latex_v1:  96%|#########6| 2881/3000 [1:07:10<02:02,  1.03s/it, lr: 1.0e-04 loss: 7.692e-02]
latex_v1:  96%|#########6| 2881/3000 [1:07:11<02:02,  1.03s/it, lr: 1.0e-04 loss: 5.756e-01]
latex_v1:  96%|#########6| 2881/3000 [1:07:11<02:02,  1.03s/it, lr: 1.0e-04 loss: 5.756e-01]
latex_v1:  96%|#########6| 2882/3000 [1:07:11<01:52,  1.05it/s, lr: 1.0e-04 loss: 5.756e-01]
latex_v1:  96%|#########6| 2882/3000 [1:07:11<01:52,  1.05it/s, lr: 1.0e-04 loss: 5.756e-01]
latex_v1:  96%|#########6| 2882/3000 [1:07:12<01:52,  1.05it/s, lr: 1.0e-04 loss: 2.254e-01]
latex_v1:  96%|#########6| 2882/3000 [1:07:12<01:52,  1.05it/s, lr: 1.0e-04 loss: 2.254e-01]
latex_v1:  96%|#########6| 2883/3000 [1:07:12<01:47,  1.09it/s, lr: 1.0e-04 loss: 2.254e-01]
latex_v1:  96%|#########6| 2883/3000 [1:07:12<01:47,  1.09it/s, lr: 1.0e-04 loss: 2.254e-01]
latex_v1:  96%|#########6| 2883/3000 [1:07:13<01:47,  1.09it/s, lr: 1.0e-04 loss: 8.828e-02]
latex_v1:  96%|#########6| 2883/3000 [1:07:13<01:47,  1.09it/s, lr: 1.0e-04 loss: 8.828e-02]
latex_v1:  96%|#########6| 2884/3000 [1:07:13<02:03,  1.07s/it, lr: 1.0e-04 loss: 8.828e-02]
latex_v1:  96%|#########6| 2884/3000 [1:07:13<02:03,  1.07s/it, lr: 1.0e-04 loss: 8.828e-02]
latex_v1:  96%|#########6| 2884/3000 [1:07:16<02:03,  1.07s/it, lr: 1.0e-04 loss: 1.398e-01]
latex_v1:  96%|#########6| 2884/3000 [1:07:16<02:03,  1.07s/it, lr: 1.0e-04 loss: 1.398e-01]
latex_v1:  96%|#########6| 2885/3000 [1:07:16<02:58,  1.56s/it, lr: 1.0e-04 loss: 1.398e-01]
latex_v1:  96%|#########6| 2885/3000 [1:07:16<02:58,  1.56s/it, lr: 1.0e-04 loss: 1.398e-01]
latex_v1:  96%|#########6| 2885/3000 [1:07:18<02:58,  1.56s/it, lr: 1.0e-04 loss: 5.544e-01]
latex_v1:  96%|#########6| 2885/3000 [1:07:18<02:58,  1.56s/it, lr: 1.0e-04 loss: 5.544e-01]
latex_v1:  96%|#########6| 2886/3000 [1:07:18<03:00,  1.58s/it, lr: 1.0e-04 loss: 5.544e-01]
latex_v1:  96%|#########6| 2886/3000 [1:07:18<03:00,  1.58s/it, lr: 1.0e-04 loss: 5.544e-01]
latex_v1:  96%|#########6| 2886/3000 [1:07:21<03:00,  1.58s/it, lr: 1.0e-04 loss: 1.535e-01]
latex_v1:  96%|#########6| 2886/3000 [1:07:21<03:00,  1.58s/it, lr: 1.0e-04 loss: 1.535e-01]
latex_v1:  96%|#########6| 2887/3000 [1:07:21<03:40,  1.95s/it, lr: 1.0e-04 loss: 1.535e-01]
latex_v1:  96%|#########6| 2887/3000 [1:07:21<03:40,  1.95s/it, lr: 1.0e-04 loss: 1.535e-01]
latex_v1:  96%|#########6| 2887/3000 [1:07:22<03:40,  1.95s/it, lr: 1.0e-04 loss: 4.742e-01]
latex_v1:  96%|#########6| 2887/3000 [1:07:22<03:40,  1.95s/it, lr: 1.0e-04 loss: 4.742e-01]
latex_v1:  96%|#########6| 2888/3000 [1:07:22<03:28,  1.86s/it, lr: 1.0e-04 loss: 4.742e-01]
latex_v1:  96%|#########6| 2888/3000 [1:07:22<03:28,  1.86s/it, lr: 1.0e-04 loss: 4.742e-01]
latex_v1:  96%|#########6| 2888/3000 [1:07:24<03:28,  1.86s/it, lr: 1.0e-04 loss: 3.584e-01]
latex_v1:  96%|#########6| 2888/3000 [1:07:24<03:28,  1.86s/it, lr: 1.0e-04 loss: 3.584e-01]
latex_v1:  96%|#########6| 2889/3000 [1:07:24<03:12,  1.73s/it, lr: 1.0e-04 loss: 3.584e-01]
latex_v1:  96%|#########6| 2889/3000 [1:07:24<03:12,  1.73s/it, lr: 1.0e-04 loss: 3.584e-01]
latex_v1:  96%|#########6| 2889/3000 [1:07:25<03:12,  1.73s/it, lr: 1.0e-04 loss: 2.896e-01]
latex_v1:  96%|#########6| 2889/3000 [1:07:25<03:12,  1.73s/it, lr: 1.0e-04 loss: 2.896e-01]
latex_v1:  96%|#########6| 2890/3000 [1:07:26<03:10,  1.73s/it, lr: 1.0e-04 loss: 8.106e-01]
latex_v1:  96%|#########6| 2890/3000 [1:07:26<03:10,  1.73s/it, lr: 1.0e-04 loss: 8.106e-01]
latex_v1:  96%|#########6| 2891/3000 [1:07:26<02:06,  1.16s/it, lr: 1.0e-04 loss: 8.106e-01]
latex_v1:  96%|#########6| 2891/3000 [1:07:26<02:06,  1.16s/it, lr: 1.0e-04 loss: 8.106e-01]
latex_v1:  96%|#########6| 2891/3000 [1:07:27<02:06,  1.16s/it, lr: 1.0e-04 loss: 6.549e-01]
latex_v1:  96%|#########6| 2891/3000 [1:07:27<02:06,  1.16s/it, lr: 1.0e-04 loss: 6.549e-01]
latex_v1:  96%|#########6| 2892/3000 [1:07:27<02:25,  1.34s/it, lr: 1.0e-04 loss: 6.549e-01]
latex_v1:  96%|#########6| 2892/3000 [1:07:27<02:25,  1.34s/it, lr: 1.0e-04 loss: 6.549e-01]
latex_v1:  96%|#########6| 2892/3000 [1:07:30<02:25,  1.34s/it, lr: 1.0e-04 loss: 5.078e-01]
latex_v1:  96%|#########6| 2892/3000 [1:07:30<02:25,  1.34s/it, lr: 1.0e-04 loss: 5.078e-01]
latex_v1:  96%|#########6| 2893/3000 [1:07:30<02:59,  1.68s/it, lr: 1.0e-04 loss: 5.078e-01]
latex_v1:  96%|#########6| 2893/3000 [1:07:30<02:59,  1.68s/it, lr: 1.0e-04 loss: 5.078e-01]
latex_v1:  96%|#########6| 2893/3000 [1:07:31<02:59,  1.68s/it, lr: 1.0e-04 loss: 6.397e-01]
latex_v1:  96%|#########6| 2893/3000 [1:07:31<02:59,  1.68s/it, lr: 1.0e-04 loss: 6.397e-01]
latex_v1:  96%|#########6| 2894/3000 [1:07:31<02:43,  1.54s/it, lr: 1.0e-04 loss: 6.397e-01]
latex_v1:  96%|#########6| 2894/3000 [1:07:31<02:43,  1.54s/it, lr: 1.0e-04 loss: 6.397e-01]
latex_v1:  96%|#########6| 2894/3000 [1:07:33<02:43,  1.54s/it, lr: 1.0e-04 loss: 1.563e-01]
latex_v1:  96%|#########6| 2894/3000 [1:07:33<02:43,  1.54s/it, lr: 1.0e-04 loss: 1.563e-01]
latex_v1:  96%|#########6| 2895/3000 [1:07:33<02:41,  1.53s/it, lr: 1.0e-04 loss: 1.563e-01]
latex_v1:  96%|#########6| 2895/3000 [1:07:33<02:41,  1.53s/it, lr: 1.0e-04 loss: 1.563e-01]
latex_v1:  96%|#########6| 2895/3000 [1:07:34<02:41,  1.53s/it, lr: 1.0e-04 loss: 6.066e-01]
latex_v1:  96%|#########6| 2895/3000 [1:07:34<02:41,  1.53s/it, lr: 1.0e-04 loss: 6.066e-01]
latex_v1:  97%|#########6| 2896/3000 [1:07:34<02:16,  1.31s/it, lr: 1.0e-04 loss: 6.066e-01]
latex_v1:  97%|#########6| 2896/3000 [1:07:34<02:16,  1.31s/it, lr: 1.0e-04 loss: 6.066e-01]
latex_v1:  97%|#########6| 2896/3000 [1:07:36<02:16,  1.31s/it, lr: 1.0e-04 loss: 3.757e-01]
latex_v1:  97%|#########6| 2896/3000 [1:07:36<02:16,  1.31s/it, lr: 1.0e-04 loss: 3.757e-01]
latex_v1:  97%|#########6| 2897/3000 [1:07:36<02:40,  1.56s/it, lr: 1.0e-04 loss: 3.757e-01]
latex_v1:  97%|#########6| 2897/3000 [1:07:36<02:40,  1.56s/it, lr: 1.0e-04 loss: 3.757e-01]
latex_v1:  97%|#########6| 2897/3000 [1:07:36<02:40,  1.56s/it, lr: 1.0e-04 loss: 7.226e-01]
latex_v1:  97%|#########6| 2897/3000 [1:07:36<02:40,  1.56s/it, lr: 1.0e-04 loss: 7.226e-01]
latex_v1:  97%|#########6| 2898/3000 [1:07:36<02:14,  1.32s/it, lr: 1.0e-04 loss: 7.226e-01]
latex_v1:  97%|#########6| 2898/3000 [1:07:36<02:14,  1.32s/it, lr: 1.0e-04 loss: 7.226e-01]
latex_v1:  97%|#########6| 2898/3000 [1:07:38<02:14,  1.32s/it, lr: 1.0e-04 loss: 5.852e-01]
latex_v1:  97%|#########6| 2898/3000 [1:07:38<02:14,  1.32s/it, lr: 1.0e-04 loss: 5.852e-01]
latex_v1:  97%|#########6| 2899/3000 [1:07:38<02:20,  1.39s/it, lr: 1.0e-04 loss: 5.852e-01]
latex_v1:  97%|#########6| 2899/3000 [1:07:38<02:20,  1.39s/it, lr: 1.0e-04 loss: 5.852e-01]
latex_v1:  97%|#########6| 2899/3000 [1:07:40<02:20,  1.39s/it, lr: 1.0e-04 loss: 1.252e-01]
latex_v1:  97%|#########6| 2899/3000 [1:07:40<02:20,  1.39s/it, lr: 1.0e-04 loss: 1.252e-01]
latex_v1:  97%|#########6| 2900/3000 [1:07:42<02:19,  1.39s/it, lr: 1.0e-04 loss: 1.542e-01]
latex_v1:  97%|#########6| 2900/3000 [1:07:42<02:19,  1.39s/it, lr: 1.0e-04 loss: 1.542e-01]
latex_v1:  97%|#########6| 2901/3000 [1:07:42<01:50,  1.11s/it, lr: 1.0e-04 loss: 1.542e-01]
latex_v1:  97%|#########6| 2901/3000 [1:07:42<01:50,  1.11s/it, lr: 1.0e-04 loss: 1.542e-01]
latex_v1:  97%|#########6| 2901/3000 [1:07:43<01:50,  1.11s/it, lr: 1.0e-04 loss: 1.555e-01]
latex_v1:  97%|#########6| 2901/3000 [1:07:43<01:50,  1.11s/it, lr: 1.0e-04 loss: 1.555e-01]
latex_v1:  97%|#########6| 2902/3000 [1:07:43<02:03,  1.26s/it, lr: 1.0e-04 loss: 1.555e-01]
latex_v1:  97%|#########6| 2902/3000 [1:07:43<02:03,  1.26s/it, lr: 1.0e-04 loss: 1.555e-01]
latex_v1:  97%|#########6| 2902/3000 [1:07:45<02:03,  1.26s/it, lr: 1.0e-04 loss: 1.373e-01]
latex_v1:  97%|#########6| 2902/3000 [1:07:45<02:03,  1.26s/it, lr: 1.0e-04 loss: 1.373e-01]
latex_v1:  97%|#########6| 2903/3000 [1:07:45<02:03,  1.28s/it, lr: 1.0e-04 loss: 1.373e-01]
latex_v1:  97%|#########6| 2903/3000 [1:07:45<02:03,  1.28s/it, lr: 1.0e-04 loss: 1.373e-01]
latex_v1:  97%|#########6| 2903/3000 [1:07:47<02:03,  1.28s/it, lr: 1.0e-04 loss: 6.779e-01]
latex_v1:  97%|#########6| 2903/3000 [1:07:47<02:03,  1.28s/it, lr: 1.0e-04 loss: 6.779e-01]
latex_v1:  97%|#########6| 2904/3000 [1:07:47<02:39,  1.66s/it, lr: 1.0e-04 loss: 6.779e-01]
latex_v1:  97%|#########6| 2904/3000 [1:07:47<02:39,  1.66s/it, lr: 1.0e-04 loss: 6.779e-01]
latex_v1:  97%|#########6| 2904/3000 [1:07:50<02:39,  1.66s/it, lr: 1.0e-04 loss: 1.217e-01]
latex_v1:  97%|#########6| 2904/3000 [1:07:50<02:39,  1.66s/it, lr: 1.0e-04 loss: 1.217e-01]
latex_v1:  97%|#########6| 2905/3000 [1:07:50<03:10,  2.00s/it, lr: 1.0e-04 loss: 1.217e-01]
latex_v1:  97%|#########6| 2905/3000 [1:07:50<03:10,  2.00s/it, lr: 1.0e-04 loss: 1.217e-01]
latex_v1:  97%|#########6| 2905/3000 [1:07:52<03:10,  2.00s/it, lr: 1.0e-04 loss: 1.736e-01]
latex_v1:  97%|#########6| 2905/3000 [1:07:52<03:10,  2.00s/it, lr: 1.0e-04 loss: 1.736e-01]
latex_v1:  97%|#########6| 2906/3000 [1:07:52<02:55,  1.86s/it, lr: 1.0e-04 loss: 1.736e-01]
latex_v1:  97%|#########6| 2906/3000 [1:07:52<02:55,  1.86s/it, lr: 1.0e-04 loss: 1.736e-01]
latex_v1:  97%|#########6| 2906/3000 [1:07:52<02:55,  1.86s/it, lr: 1.0e-04 loss: 6.365e-01]
latex_v1:  97%|#########6| 2906/3000 [1:07:52<02:55,  1.86s/it, lr: 1.0e-04 loss: 6.365e-01]
latex_v1:  97%|#########6| 2907/3000 [1:07:52<02:23,  1.54s/it, lr: 1.0e-04 loss: 6.365e-01]
latex_v1:  97%|#########6| 2907/3000 [1:07:52<02:23,  1.54s/it, lr: 1.0e-04 loss: 6.365e-01]
latex_v1:  97%|#########6| 2907/3000 [1:07:54<02:23,  1.54s/it, lr: 1.0e-04 loss: 2.833e-02]
latex_v1:  97%|#########6| 2907/3000 [1:07:54<02:23,  1.54s/it, lr: 1.0e-04 loss: 2.833e-02]
latex_v1:  97%|#########6| 2908/3000 [1:07:54<02:21,  1.54s/it, lr: 1.0e-04 loss: 2.833e-02]
latex_v1:  97%|#########6| 2908/3000 [1:07:54<02:21,  1.54s/it, lr: 1.0e-04 loss: 2.833e-02]
latex_v1:  97%|#########6| 2908/3000 [1:07:55<02:21,  1.54s/it, lr: 1.0e-04 loss: 2.681e-01]
latex_v1:  97%|#########6| 2908/3000 [1:07:55<02:21,  1.54s/it, lr: 1.0e-04 loss: 2.681e-01]
latex_v1:  97%|#########6| 2909/3000 [1:07:55<01:59,  1.31s/it, lr: 1.0e-04 loss: 2.681e-01]
latex_v1:  97%|#########6| 2909/3000 [1:07:55<01:59,  1.31s/it, lr: 1.0e-04 loss: 2.681e-01]
latex_v1:  97%|#########6| 2909/3000 [1:07:56<01:59,  1.31s/it, lr: 1.0e-04 loss: 5.968e-01]
latex_v1:  97%|#########6| 2909/3000 [1:07:56<01:59,  1.31s/it, lr: 1.0e-04 loss: 5.968e-01]
latex_v1:  97%|#########7| 2910/3000 [1:07:58<01:58,  1.31s/it, lr: 1.0e-04 loss: 4.346e-02]
latex_v1:  97%|#########7| 2910/3000 [1:07:58<01:58,  1.31s/it, lr: 1.0e-04 loss: 4.346e-02]
latex_v1:  97%|#########7| 2911/3000 [1:07:58<01:34,  1.06s/it, lr: 1.0e-04 loss: 4.346e-02]
latex_v1:  97%|#########7| 2911/3000 [1:07:58<01:34,  1.06s/it, lr: 1.0e-04 loss: 4.346e-02]
latex_v1:  97%|#########7| 2911/3000 [1:07:59<01:34,  1.06s/it, lr: 1.0e-04 loss: 6.879e-01]
latex_v1:  97%|#########7| 2911/3000 [1:07:59<01:34,  1.06s/it, lr: 1.0e-04 loss: 6.879e-01]
latex_v1:  97%|#########7| 2912/3000 [1:07:59<01:39,  1.13s/it, lr: 1.0e-04 loss: 6.879e-01]
latex_v1:  97%|#########7| 2912/3000 [1:07:59<01:39,  1.13s/it, lr: 1.0e-04 loss: 6.879e-01]
latex_v1:  97%|#########7| 2912/3000 [1:08:02<01:39,  1.13s/it, lr: 1.0e-04 loss: 2.802e-01]
latex_v1:  97%|#########7| 2912/3000 [1:08:02<01:39,  1.13s/it, lr: 1.0e-04 loss: 2.802e-01]
latex_v1:  97%|#########7| 2913/3000 [1:08:02<02:16,  1.57s/it, lr: 1.0e-04 loss: 2.802e-01]
latex_v1:  97%|#########7| 2913/3000 [1:08:02<02:16,  1.57s/it, lr: 1.0e-04 loss: 2.802e-01]
latex_v1:  97%|#########7| 2913/3000 [1:08:03<02:16,  1.57s/it, lr: 1.0e-04 loss: 3.255e-01]
latex_v1:  97%|#########7| 2913/3000 [1:08:03<02:16,  1.57s/it, lr: 1.0e-04 loss: 3.255e-01]
latex_v1:  97%|#########7| 2914/3000 [1:08:03<02:05,  1.46s/it, lr: 1.0e-04 loss: 3.255e-01]
latex_v1:  97%|#########7| 2914/3000 [1:08:03<02:05,  1.46s/it, lr: 1.0e-04 loss: 3.255e-01]
latex_v1:  97%|#########7| 2914/3000 [1:08:04<02:05,  1.46s/it, lr: 1.0e-04 loss: 3.629e-01]
latex_v1:  97%|#########7| 2914/3000 [1:08:04<02:05,  1.46s/it, lr: 1.0e-04 loss: 3.629e-01]
latex_v1:  97%|#########7| 2915/3000 [1:08:04<01:52,  1.33s/it, lr: 1.0e-04 loss: 3.629e-01]
latex_v1:  97%|#########7| 2915/3000 [1:08:04<01:52,  1.33s/it, lr: 1.0e-04 loss: 3.629e-01]
latex_v1:  97%|#########7| 2915/3000 [1:08:05<01:52,  1.33s/it, lr: 1.0e-04 loss: 6.250e-01]
latex_v1:  97%|#########7| 2915/3000 [1:08:05<01:52,  1.33s/it, lr: 1.0e-04 loss: 6.250e-01]
latex_v1:  97%|#########7| 2916/3000 [1:08:05<01:47,  1.28s/it, lr: 1.0e-04 loss: 6.250e-01]
latex_v1:  97%|#########7| 2916/3000 [1:08:05<01:47,  1.28s/it, lr: 1.0e-04 loss: 6.250e-01]
latex_v1:  97%|#########7| 2916/3000 [1:08:07<01:47,  1.28s/it, lr: 1.0e-04 loss: 5.130e-01]
latex_v1:  97%|#########7| 2916/3000 [1:08:07<01:47,  1.28s/it, lr: 1.0e-04 loss: 5.130e-01]
latex_v1:  97%|#########7| 2917/3000 [1:08:07<01:52,  1.35s/it, lr: 1.0e-04 loss: 5.130e-01]
latex_v1:  97%|#########7| 2917/3000 [1:08:07<01:52,  1.35s/it, lr: 1.0e-04 loss: 5.130e-01]
latex_v1:  97%|#########7| 2917/3000 [1:08:08<01:52,  1.35s/it, lr: 1.0e-04 loss: 3.883e-01]
latex_v1:  97%|#########7| 2917/3000 [1:08:08<01:52,  1.35s/it, lr: 1.0e-04 loss: 3.883e-01]
latex_v1:  97%|#########7| 2918/3000 [1:08:08<01:36,  1.17s/it, lr: 1.0e-04 loss: 3.883e-01]
latex_v1:  97%|#########7| 2918/3000 [1:08:08<01:36,  1.17s/it, lr: 1.0e-04 loss: 3.883e-01]
latex_v1:  97%|#########7| 2918/3000 [1:08:08<01:36,  1.17s/it, lr: 1.0e-04 loss: 5.550e-01]
latex_v1:  97%|#########7| 2918/3000 [1:08:08<01:36,  1.17s/it, lr: 1.0e-04 loss: 5.550e-01]
latex_v1:  97%|#########7| 2919/3000 [1:08:08<01:24,  1.05s/it, lr: 1.0e-04 loss: 5.550e-01]
latex_v1:  97%|#########7| 2919/3000 [1:08:08<01:24,  1.05s/it, lr: 1.0e-04 loss: 5.550e-01]
latex_v1:  97%|#########7| 2919/3000 [1:08:11<01:24,  1.05s/it, lr: 1.0e-04 loss: 1.195e-01]
latex_v1:  97%|#########7| 2919/3000 [1:08:11<01:24,  1.05s/it, lr: 1.0e-04 loss: 1.195e-01]
latex_v1:  97%|#########7| 2920/3000 [1:08:12<01:23,  1.05s/it, lr: 1.0e-04 loss: 4.975e-01]
latex_v1:  97%|#########7| 2920/3000 [1:08:12<01:23,  1.05s/it, lr: 1.0e-04 loss: 4.975e-01]
latex_v1:  97%|#########7| 2921/3000 [1:08:12<00:58,  1.36it/s, lr: 1.0e-04 loss: 4.975e-01]
latex_v1:  97%|#########7| 2921/3000 [1:08:12<00:58,  1.36it/s, lr: 1.0e-04 loss: 4.975e-01]
latex_v1:  97%|#########7| 2921/3000 [1:08:13<00:58,  1.36it/s, lr: 1.0e-04 loss: 6.611e-01]
latex_v1:  97%|#########7| 2921/3000 [1:08:13<00:58,  1.36it/s, lr: 1.0e-04 loss: 6.611e-01]
latex_v1:  97%|#########7| 2922/3000 [1:08:13<00:58,  1.34it/s, lr: 1.0e-04 loss: 6.611e-01]
latex_v1:  97%|#########7| 2922/3000 [1:08:13<00:58,  1.34it/s, lr: 1.0e-04 loss: 6.611e-01]
latex_v1:  97%|#########7| 2922/3000 [1:08:14<00:58,  1.34it/s, lr: 1.0e-04 loss: 1.239e-01]
latex_v1:  97%|#########7| 2922/3000 [1:08:14<00:58,  1.34it/s, lr: 1.0e-04 loss: 1.239e-01]
latex_v1:  97%|#########7| 2923/3000 [1:08:14<01:19,  1.04s/it, lr: 1.0e-04 loss: 1.239e-01]
latex_v1:  97%|#########7| 2923/3000 [1:08:14<01:19,  1.04s/it, lr: 1.0e-04 loss: 1.239e-01]
latex_v1:  97%|#########7| 2923/3000 [1:08:16<01:19,  1.04s/it, lr: 1.0e-04 loss: 2.093e-01]
latex_v1:  97%|#########7| 2923/3000 [1:08:16<01:19,  1.04s/it, lr: 1.0e-04 loss: 2.093e-01]
latex_v1:  97%|#########7| 2924/3000 [1:08:16<01:24,  1.11s/it, lr: 1.0e-04 loss: 2.093e-01]
latex_v1:  97%|#########7| 2924/3000 [1:08:16<01:24,  1.11s/it, lr: 1.0e-04 loss: 2.093e-01]
latex_v1:  97%|#########7| 2924/3000 [1:08:17<01:24,  1.11s/it, lr: 1.0e-04 loss: 6.463e-01]
latex_v1:  97%|#########7| 2924/3000 [1:08:17<01:24,  1.11s/it, lr: 1.0e-04 loss: 6.463e-01]
latex_v1:  98%|#########7| 2925/3000 [1:08:17<01:15,  1.01s/it, lr: 1.0e-04 loss: 6.463e-01]
latex_v1:  98%|#########7| 2925/3000 [1:08:17<01:15,  1.01s/it, lr: 1.0e-04 loss: 6.463e-01]
latex_v1:  98%|#########7| 2925/3000 [1:08:17<01:15,  1.01s/it, lr: 1.0e-04 loss: 3.255e-01]
latex_v1:  98%|#########7| 2925/3000 [1:08:17<01:15,  1.01s/it, lr: 1.0e-04 loss: 3.255e-01]
latex_v1:  98%|#########7| 2926/3000 [1:08:17<01:09,  1.07it/s, lr: 1.0e-04 loss: 3.255e-01]
latex_v1:  98%|#########7| 2926/3000 [1:08:17<01:09,  1.07it/s, lr: 1.0e-04 loss: 3.255e-01]
latex_v1:  98%|#########7| 2926/3000 [1:08:18<01:09,  1.07it/s, lr: 1.0e-04 loss: 6.451e-02]
latex_v1:  98%|#########7| 2926/3000 [1:08:18<01:09,  1.07it/s, lr: 1.0e-04 loss: 6.451e-02]
latex_v1:  98%|#########7| 2927/3000 [1:08:18<01:04,  1.14it/s, lr: 1.0e-04 loss: 6.451e-02]
latex_v1:  98%|#########7| 2927/3000 [1:08:18<01:04,  1.14it/s, lr: 1.0e-04 loss: 6.451e-02]
latex_v1:  98%|#########7| 2927/3000 [1:08:21<01:04,  1.14it/s, lr: 1.0e-04 loss: 1.137e-01]
latex_v1:  98%|#########7| 2927/3000 [1:08:21<01:04,  1.14it/s, lr: 1.0e-04 loss: 1.137e-01]
latex_v1:  98%|#########7| 2928/3000 [1:08:21<01:46,  1.48s/it, lr: 1.0e-04 loss: 1.137e-01]
latex_v1:  98%|#########7| 2928/3000 [1:08:21<01:46,  1.48s/it, lr: 1.0e-04 loss: 1.137e-01]
latex_v1:  98%|#########7| 2928/3000 [1:08:22<01:46,  1.48s/it, lr: 1.0e-04 loss: 1.767e-01]
latex_v1:  98%|#########7| 2928/3000 [1:08:22<01:46,  1.48s/it, lr: 1.0e-04 loss: 1.767e-01]
latex_v1:  98%|#########7| 2929/3000 [1:08:22<01:32,  1.31s/it, lr: 1.0e-04 loss: 1.767e-01]
latex_v1:  98%|#########7| 2929/3000 [1:08:22<01:32,  1.31s/it, lr: 1.0e-04 loss: 1.767e-01]
latex_v1:  98%|#########7| 2929/3000 [1:08:23<01:32,  1.31s/it, lr: 1.0e-04 loss: 5.747e-01]
latex_v1:  98%|#########7| 2929/3000 [1:08:23<01:32,  1.31s/it, lr: 1.0e-04 loss: 5.747e-01]
latex_v1:  98%|#########7| 2930/3000 [1:08:24<01:31,  1.31s/it, lr: 1.0e-04 loss: 4.050e-01]
latex_v1:  98%|#########7| 2930/3000 [1:08:24<01:31,  1.31s/it, lr: 1.0e-04 loss: 4.050e-01]
latex_v1:  98%|#########7| 2931/3000 [1:08:24<01:00,  1.14it/s, lr: 1.0e-04 loss: 4.050e-01]
latex_v1:  98%|#########7| 2931/3000 [1:08:24<01:00,  1.14it/s, lr: 1.0e-04 loss: 4.050e-01]
latex_v1:  98%|#########7| 2931/3000 [1:08:25<01:00,  1.14it/s, lr: 1.0e-04 loss: 2.546e-01]
latex_v1:  98%|#########7| 2931/3000 [1:08:25<01:00,  1.14it/s, lr: 1.0e-04 loss: 2.546e-01]
latex_v1:  98%|#########7| 2932/3000 [1:08:25<01:08,  1.01s/it, lr: 1.0e-04 loss: 2.546e-01]
latex_v1:  98%|#########7| 2932/3000 [1:08:25<01:08,  1.01s/it, lr: 1.0e-04 loss: 2.546e-01]
latex_v1:  98%|#########7| 2932/3000 [1:08:26<01:08,  1.01s/it, lr: 1.0e-04 loss: 4.467e-01]
latex_v1:  98%|#########7| 2932/3000 [1:08:26<01:08,  1.01s/it, lr: 1.0e-04 loss: 4.467e-01]
latex_v1:  98%|#########7| 2933/3000 [1:08:26<01:03,  1.06it/s, lr: 1.0e-04 loss: 4.467e-01]
latex_v1:  98%|#########7| 2933/3000 [1:08:26<01:03,  1.06it/s, lr: 1.0e-04 loss: 4.467e-01]
latex_v1:  98%|#########7| 2933/3000 [1:08:27<01:03,  1.06it/s, lr: 1.0e-04 loss: 8.354e-01]
latex_v1:  98%|#########7| 2933/3000 [1:08:27<01:03,  1.06it/s, lr: 1.0e-04 loss: 8.354e-01]
latex_v1:  98%|#########7| 2934/3000 [1:08:27<01:06,  1.00s/it, lr: 1.0e-04 loss: 8.354e-01]
latex_v1:  98%|#########7| 2934/3000 [1:08:27<01:06,  1.00s/it, lr: 1.0e-04 loss: 8.354e-01]
latex_v1:  98%|#########7| 2934/3000 [1:08:29<01:06,  1.00s/it, lr: 1.0e-04 loss: 1.230e-01]
latex_v1:  98%|#########7| 2934/3000 [1:08:29<01:06,  1.00s/it, lr: 1.0e-04 loss: 1.230e-01]
latex_v1:  98%|#########7| 2935/3000 [1:08:29<01:14,  1.15s/it, lr: 1.0e-04 loss: 1.230e-01]
latex_v1:  98%|#########7| 2935/3000 [1:08:29<01:14,  1.15s/it, lr: 1.0e-04 loss: 1.230e-01]
latex_v1:  98%|#########7| 2935/3000 [1:08:30<01:14,  1.15s/it, lr: 1.0e-04 loss: 4.550e-01]
latex_v1:  98%|#########7| 2935/3000 [1:08:30<01:14,  1.15s/it, lr: 1.0e-04 loss: 4.550e-01]
latex_v1:  98%|#########7| 2936/3000 [1:08:30<01:06,  1.03s/it, lr: 1.0e-04 loss: 4.550e-01]
latex_v1:  98%|#########7| 2936/3000 [1:08:30<01:06,  1.03s/it, lr: 1.0e-04 loss: 4.550e-01]
latex_v1:  98%|#########7| 2936/3000 [1:08:31<01:06,  1.03s/it, lr: 1.0e-04 loss: 2.448e-01]
latex_v1:  98%|#########7| 2936/3000 [1:08:31<01:06,  1.03s/it, lr: 1.0e-04 loss: 2.448e-01]
latex_v1:  98%|#########7| 2937/3000 [1:08:31<01:11,  1.14s/it, lr: 1.0e-04 loss: 2.448e-01]
latex_v1:  98%|#########7| 2937/3000 [1:08:31<01:11,  1.14s/it, lr: 1.0e-04 loss: 2.448e-01]
latex_v1:  98%|#########7| 2937/3000 [1:08:32<01:11,  1.14s/it, lr: 1.0e-04 loss: 1.316e-02]
latex_v1:  98%|#########7| 2937/3000 [1:08:32<01:11,  1.14s/it, lr: 1.0e-04 loss: 1.316e-02]
latex_v1:  98%|#########7| 2938/3000 [1:08:32<01:03,  1.03s/it, lr: 1.0e-04 loss: 1.316e-02]
latex_v1:  98%|#########7| 2938/3000 [1:08:32<01:03,  1.03s/it, lr: 1.0e-04 loss: 1.316e-02]
latex_v1:  98%|#########7| 2938/3000 [1:08:35<01:03,  1.03s/it, lr: 1.0e-04 loss: 5.023e-02]
latex_v1:  98%|#########7| 2938/3000 [1:08:35<01:03,  1.03s/it, lr: 1.0e-04 loss: 5.023e-02]
latex_v1:  98%|#########7| 2939/3000 [1:08:35<01:35,  1.56s/it, lr: 1.0e-04 loss: 5.023e-02]
latex_v1:  98%|#########7| 2939/3000 [1:08:35<01:35,  1.56s/it, lr: 1.0e-04 loss: 5.023e-02]
latex_v1:  98%|#########7| 2939/3000 [1:08:36<01:35,  1.56s/it, lr: 1.0e-04 loss: 1.596e-01]
latex_v1:  98%|#########7| 2939/3000 [1:08:36<01:35,  1.56s/it, lr: 1.0e-04 loss: 1.596e-01]
latex_v1:  98%|#########8| 2940/3000 [1:08:36<01:33,  1.56s/it, lr: 1.0e-04 loss: 5.558e-01]
latex_v1:  98%|#########8| 2940/3000 [1:08:36<01:33,  1.56s/it, lr: 1.0e-04 loss: 5.558e-01]
latex_v1:  98%|#########8| 2941/3000 [1:08:36<00:59,  1.02s/it, lr: 1.0e-04 loss: 5.558e-01]
latex_v1:  98%|#########8| 2941/3000 [1:08:36<00:59,  1.02s/it, lr: 1.0e-04 loss: 5.558e-01]
latex_v1:  98%|#########8| 2941/3000 [1:08:38<00:59,  1.02s/it, lr: 1.0e-04 loss: 6.109e-01]
latex_v1:  98%|#########8| 2941/3000 [1:08:38<00:59,  1.02s/it, lr: 1.0e-04 loss: 6.109e-01]
latex_v1:  98%|#########8| 2942/3000 [1:08:38<01:06,  1.15s/it, lr: 1.0e-04 loss: 6.109e-01]
latex_v1:  98%|#########8| 2942/3000 [1:08:38<01:06,  1.15s/it, lr: 1.0e-04 loss: 6.109e-01]
latex_v1:  98%|#########8| 2942/3000 [1:08:39<01:06,  1.15s/it, lr: 1.0e-04 loss: 5.924e-01]
latex_v1:  98%|#########8| 2942/3000 [1:08:39<01:06,  1.15s/it, lr: 1.0e-04 loss: 5.924e-01]
latex_v1:  98%|#########8| 2943/3000 [1:08:39<01:11,  1.25s/it, lr: 1.0e-04 loss: 5.924e-01]
latex_v1:  98%|#########8| 2943/3000 [1:08:39<01:11,  1.25s/it, lr: 1.0e-04 loss: 5.924e-01]
latex_v1:  98%|#########8| 2943/3000 [1:08:41<01:11,  1.25s/it, lr: 1.0e-04 loss: 3.583e-01]
latex_v1:  98%|#########8| 2943/3000 [1:08:41<01:11,  1.25s/it, lr: 1.0e-04 loss: 3.583e-01]
latex_v1:  98%|#########8| 2944/3000 [1:08:41<01:08,  1.23s/it, lr: 1.0e-04 loss: 3.583e-01]
latex_v1:  98%|#########8| 2944/3000 [1:08:41<01:08,  1.23s/it, lr: 1.0e-04 loss: 3.583e-01]
latex_v1:  98%|#########8| 2944/3000 [1:08:41<01:08,  1.23s/it, lr: 1.0e-04 loss: 2.606e-01]
latex_v1:  98%|#########8| 2944/3000 [1:08:41<01:08,  1.23s/it, lr: 1.0e-04 loss: 2.606e-01]
latex_v1:  98%|#########8| 2945/3000 [1:08:41<01:00,  1.09s/it, lr: 1.0e-04 loss: 2.606e-01]
latex_v1:  98%|#########8| 2945/3000 [1:08:41<01:00,  1.09s/it, lr: 1.0e-04 loss: 2.606e-01]
latex_v1:  98%|#########8| 2945/3000 [1:08:42<01:00,  1.09s/it, lr: 1.0e-04 loss: 5.715e-01]
latex_v1:  98%|#########8| 2945/3000 [1:08:42<01:00,  1.09s/it, lr: 1.0e-04 loss: 5.715e-01]
latex_v1:  98%|#########8| 2946/3000 [1:08:42<00:53,  1.01it/s, lr: 1.0e-04 loss: 5.715e-01]
latex_v1:  98%|#########8| 2946/3000 [1:08:42<00:53,  1.01it/s, lr: 1.0e-04 loss: 5.715e-01]
latex_v1:  98%|#########8| 2946/3000 [1:08:45<00:53,  1.01it/s, lr: 1.0e-04 loss: 4.393e-01]
latex_v1:  98%|#########8| 2946/3000 [1:08:45<00:53,  1.01it/s, lr: 1.0e-04 loss: 4.393e-01]
latex_v1:  98%|#########8| 2947/3000 [1:08:45<01:20,  1.52s/it, lr: 1.0e-04 loss: 4.393e-01]
latex_v1:  98%|#########8| 2947/3000 [1:08:45<01:20,  1.52s/it, lr: 1.0e-04 loss: 4.393e-01]
latex_v1:  98%|#########8| 2947/3000 [1:08:47<01:20,  1.52s/it, lr: 1.0e-04 loss: 4.697e-01]
latex_v1:  98%|#########8| 2947/3000 [1:08:47<01:20,  1.52s/it, lr: 1.0e-04 loss: 4.697e-01]
latex_v1:  98%|#########8| 2948/3000 [1:08:47<01:24,  1.62s/it, lr: 1.0e-04 loss: 4.697e-01]
latex_v1:  98%|#########8| 2948/3000 [1:08:47<01:24,  1.62s/it, lr: 1.0e-04 loss: 4.697e-01]
latex_v1:  98%|#########8| 2948/3000 [1:08:49<01:24,  1.62s/it, lr: 1.0e-04 loss: 2.043e-01]
latex_v1:  98%|#########8| 2948/3000 [1:08:49<01:24,  1.62s/it, lr: 1.0e-04 loss: 2.043e-01]
latex_v1:  98%|#########8| 2949/3000 [1:08:49<01:26,  1.69s/it, lr: 1.0e-04 loss: 2.043e-01]
latex_v1:  98%|#########8| 2949/3000 [1:08:49<01:26,  1.69s/it, lr: 1.0e-04 loss: 2.043e-01]
latex_v1:  98%|#########8| 2949/3000 [1:08:50<01:26,  1.69s/it, lr: 1.0e-04 loss: 3.147e-01]
latex_v1:  98%|#########8| 2949/3000 [1:08:50<01:26,  1.69s/it, lr: 1.0e-04 loss: 3.147e-01]
latex_v1:  98%|#########8| 2950/3000 [1:08:51<01:24,  1.69s/it, lr: 1.0e-04 loss: 4.368e-01]
latex_v1:  98%|#########8| 2950/3000 [1:08:51<01:24,  1.69s/it, lr: 1.0e-04 loss: 4.368e-01]
latex_v1:  98%|#########8| 2951/3000 [1:08:51<00:53,  1.10s/it, lr: 1.0e-04 loss: 4.368e-01]
latex_v1:  98%|#########8| 2951/3000 [1:08:51<00:53,  1.10s/it, lr: 1.0e-04 loss: 4.368e-01]
latex_v1:  98%|#########8| 2951/3000 [1:08:53<00:53,  1.10s/it, lr: 1.0e-04 loss: 2.497e-01]
latex_v1:  98%|#########8| 2951/3000 [1:08:53<00:53,  1.10s/it, lr: 1.0e-04 loss: 2.497e-01]
latex_v1:  98%|#########8| 2952/3000 [1:08:53<00:55,  1.16s/it, lr: 1.0e-04 loss: 2.497e-01]
latex_v1:  98%|#########8| 2952/3000 [1:08:53<00:55,  1.16s/it, lr: 1.0e-04 loss: 2.497e-01]
latex_v1:  98%|#########8| 2952/3000 [1:08:54<00:55,  1.16s/it, lr: 1.0e-04 loss: 2.017e-01]
latex_v1:  98%|#########8| 2952/3000 [1:08:54<00:55,  1.16s/it, lr: 1.0e-04 loss: 2.017e-01]
latex_v1:  98%|#########8| 2953/3000 [1:08:54<00:59,  1.26s/it, lr: 1.0e-04 loss: 2.017e-01]
latex_v1:  98%|#########8| 2953/3000 [1:08:54<00:59,  1.26s/it, lr: 1.0e-04 loss: 2.017e-01]
latex_v1:  98%|#########8| 2953/3000 [1:08:55<00:59,  1.26s/it, lr: 1.0e-04 loss: 1.513e-02]
latex_v1:  98%|#########8| 2953/3000 [1:08:55<00:59,  1.26s/it, lr: 1.0e-04 loss: 1.513e-02]
latex_v1:  98%|#########8| 2954/3000 [1:08:55<00:51,  1.12s/it, lr: 1.0e-04 loss: 1.513e-02]
latex_v1:  98%|#########8| 2954/3000 [1:08:55<00:51,  1.12s/it, lr: 1.0e-04 loss: 1.513e-02]
latex_v1:  98%|#########8| 2954/3000 [1:08:56<00:51,  1.12s/it, lr: 1.0e-04 loss: 2.945e-01]
latex_v1:  98%|#########8| 2954/3000 [1:08:56<00:51,  1.12s/it, lr: 1.0e-04 loss: 2.945e-01]
latex_v1:  98%|#########8| 2955/3000 [1:08:56<00:53,  1.19s/it, lr: 1.0e-04 loss: 2.945e-01]
latex_v1:  98%|#########8| 2955/3000 [1:08:56<00:53,  1.19s/it, lr: 1.0e-04 loss: 2.945e-01]
latex_v1:  98%|#########8| 2955/3000 [1:08:57<00:53,  1.19s/it, lr: 1.0e-04 loss: 5.734e-01]
latex_v1:  98%|#########8| 2955/3000 [1:08:57<00:53,  1.19s/it, lr: 1.0e-04 loss: 5.734e-01]
latex_v1:  99%|#########8| 2956/3000 [1:08:57<00:50,  1.15s/it, lr: 1.0e-04 loss: 5.734e-01]
latex_v1:  99%|#########8| 2956/3000 [1:08:57<00:50,  1.15s/it, lr: 1.0e-04 loss: 5.734e-01]
latex_v1:  99%|#########8| 2956/3000 [1:08:58<00:50,  1.15s/it, lr: 1.0e-04 loss: 6.792e-01]
latex_v1:  99%|#########8| 2956/3000 [1:08:58<00:50,  1.15s/it, lr: 1.0e-04 loss: 6.792e-01]
latex_v1:  99%|#########8| 2957/3000 [1:08:58<00:47,  1.10s/it, lr: 1.0e-04 loss: 6.792e-01]
latex_v1:  99%|#########8| 2957/3000 [1:08:58<00:47,  1.10s/it, lr: 1.0e-04 loss: 6.792e-01]
latex_v1:  99%|#########8| 2957/3000 [1:09:00<00:47,  1.10s/it, lr: 1.0e-04 loss: 5.329e-02]
latex_v1:  99%|#########8| 2957/3000 [1:09:00<00:47,  1.10s/it, lr: 1.0e-04 loss: 5.329e-02]
latex_v1:  99%|#########8| 2958/3000 [1:09:00<00:50,  1.20s/it, lr: 1.0e-04 loss: 5.329e-02]
latex_v1:  99%|#########8| 2958/3000 [1:09:00<00:50,  1.20s/it, lr: 1.0e-04 loss: 5.329e-02]
latex_v1:  99%|#########8| 2958/3000 [1:09:01<00:50,  1.20s/it, lr: 1.0e-04 loss: 5.440e-01]
latex_v1:  99%|#########8| 2958/3000 [1:09:01<00:50,  1.20s/it, lr: 1.0e-04 loss: 5.440e-01]
latex_v1:  99%|#########8| 2959/3000 [1:09:01<00:53,  1.30s/it, lr: 1.0e-04 loss: 5.440e-01]
latex_v1:  99%|#########8| 2959/3000 [1:09:01<00:53,  1.30s/it, lr: 1.0e-04 loss: 5.440e-01]
latex_v1:  99%|#########8| 2959/3000 [1:09:02<00:53,  1.30s/it, lr: 1.0e-04 loss: 8.687e-01]
latex_v1:  99%|#########8| 2959/3000 [1:09:02<00:53,  1.30s/it, lr: 1.0e-04 loss: 8.687e-01]
latex_v1:  99%|#########8| 2960/3000 [1:09:03<00:51,  1.30s/it, lr: 1.0e-04 loss: 4.829e-01]
latex_v1:  99%|#########8| 2960/3000 [1:09:03<00:51,  1.30s/it, lr: 1.0e-04 loss: 4.829e-01]
latex_v1:  99%|#########8| 2961/3000 [1:09:03<00:37,  1.03it/s, lr: 1.0e-04 loss: 4.829e-01]
latex_v1:  99%|#########8| 2961/3000 [1:09:03<00:37,  1.03it/s, lr: 1.0e-04 loss: 4.829e-01]
latex_v1:  99%|#########8| 2961/3000 [1:09:04<00:37,  1.03it/s, lr: 1.0e-04 loss: 4.949e-01]
latex_v1:  99%|#########8| 2961/3000 [1:09:04<00:37,  1.03it/s, lr: 1.0e-04 loss: 4.949e-01]
latex_v1:  99%|#########8| 2962/3000 [1:09:04<00:34,  1.09it/s, lr: 1.0e-04 loss: 4.949e-01]
latex_v1:  99%|#########8| 2962/3000 [1:09:04<00:34,  1.09it/s, lr: 1.0e-04 loss: 4.949e-01]
latex_v1:  99%|#########8| 2962/3000 [1:09:05<00:34,  1.09it/s, lr: 1.0e-04 loss: 6.849e-01]
latex_v1:  99%|#########8| 2962/3000 [1:09:05<00:34,  1.09it/s, lr: 1.0e-04 loss: 6.849e-01]
latex_v1:  99%|#########8| 2963/3000 [1:09:05<00:38,  1.05s/it, lr: 1.0e-04 loss: 6.849e-01]
latex_v1:  99%|#########8| 2963/3000 [1:09:05<00:38,  1.05s/it, lr: 1.0e-04 loss: 6.849e-01]
latex_v1:  99%|#########8| 2963/3000 [1:09:07<00:38,  1.05s/it, lr: 1.0e-04 loss: 4.484e-01]
latex_v1:  99%|#########8| 2963/3000 [1:09:07<00:38,  1.05s/it, lr: 1.0e-04 loss: 4.484e-01]
latex_v1:  99%|#########8| 2964/3000 [1:09:07<00:41,  1.16s/it, lr: 1.0e-04 loss: 4.484e-01]
latex_v1:  99%|#########8| 2964/3000 [1:09:07<00:41,  1.16s/it, lr: 1.0e-04 loss: 4.484e-01]
latex_v1:  99%|#########8| 2964/3000 [1:09:07<00:41,  1.16s/it, lr: 1.0e-04 loss: 6.030e-01]
latex_v1:  99%|#########8| 2964/3000 [1:09:07<00:41,  1.16s/it, lr: 1.0e-04 loss: 6.030e-01]
latex_v1:  99%|#########8| 2965/3000 [1:09:07<00:36,  1.04s/it, lr: 1.0e-04 loss: 6.030e-01]
latex_v1:  99%|#########8| 2965/3000 [1:09:07<00:36,  1.04s/it, lr: 1.0e-04 loss: 6.030e-01]
latex_v1:  99%|#########8| 2965/3000 [1:09:09<00:36,  1.04s/it, lr: 1.0e-04 loss: 1.028e-01]
latex_v1:  99%|#########8| 2965/3000 [1:09:09<00:36,  1.04s/it, lr: 1.0e-04 loss: 1.028e-01]
latex_v1:  99%|#########8| 2966/3000 [1:09:09<00:38,  1.14s/it, lr: 1.0e-04 loss: 1.028e-01]
latex_v1:  99%|#########8| 2966/3000 [1:09:09<00:38,  1.14s/it, lr: 1.0e-04 loss: 1.028e-01]
latex_v1:  99%|#########8| 2966/3000 [1:09:10<00:38,  1.14s/it, lr: 1.0e-04 loss: 1.034e-01]
latex_v1:  99%|#########8| 2966/3000 [1:09:10<00:38,  1.14s/it, lr: 1.0e-04 loss: 1.034e-01]
latex_v1:  99%|#########8| 2967/3000 [1:09:10<00:33,  1.03s/it, lr: 1.0e-04 loss: 1.034e-01]
latex_v1:  99%|#########8| 2967/3000 [1:09:10<00:33,  1.03s/it, lr: 1.0e-04 loss: 1.034e-01]
latex_v1:  99%|#########8| 2967/3000 [1:09:10<00:33,  1.03s/it, lr: 1.0e-04 loss: 1.868e-01]
latex_v1:  99%|#########8| 2967/3000 [1:09:10<00:33,  1.03s/it, lr: 1.0e-04 loss: 1.868e-01]
latex_v1:  99%|#########8| 2968/3000 [1:09:10<00:30,  1.05it/s, lr: 1.0e-04 loss: 1.868e-01]
latex_v1:  99%|#########8| 2968/3000 [1:09:10<00:30,  1.05it/s, lr: 1.0e-04 loss: 1.868e-01]
latex_v1:  99%|#########8| 2968/3000 [1:09:11<00:30,  1.05it/s, lr: 1.0e-04 loss: 1.621e-01]
latex_v1:  99%|#########8| 2968/3000 [1:09:11<00:30,  1.05it/s, lr: 1.0e-04 loss: 1.621e-01]
latex_v1:  99%|#########8| 2969/3000 [1:09:11<00:27,  1.12it/s, lr: 1.0e-04 loss: 1.621e-01]
latex_v1:  99%|#########8| 2969/3000 [1:09:11<00:27,  1.12it/s, lr: 1.0e-04 loss: 1.621e-01]
latex_v1:  99%|#########8| 2969/3000 [1:09:13<00:27,  1.12it/s, lr: 1.0e-04 loss: 5.583e-01]
latex_v1:  99%|#########8| 2969/3000 [1:09:13<00:27,  1.12it/s, lr: 1.0e-04 loss: 5.583e-01]
latex_v1:  99%|#########9| 2970/3000 [1:09:15<00:26,  1.12it/s, lr: 1.0e-04 loss: 5.630e-01]
latex_v1:  99%|#########9| 2970/3000 [1:09:15<00:26,  1.12it/s, lr: 1.0e-04 loss: 5.630e-01]
latex_v1:  99%|#########9| 2971/3000 [1:09:15<00:26,  1.10it/s, lr: 1.0e-04 loss: 5.630e-01]
latex_v1:  99%|#########9| 2971/3000 [1:09:15<00:26,  1.10it/s, lr: 1.0e-04 loss: 5.630e-01]
latex_v1:  99%|#########9| 2971/3000 [1:09:16<00:26,  1.10it/s, lr: 1.0e-04 loss: 2.177e-01]
latex_v1:  99%|#########9| 2971/3000 [1:09:16<00:26,  1.10it/s, lr: 1.0e-04 loss: 2.177e-01]
latex_v1:  99%|#########9| 2972/3000 [1:09:16<00:28,  1.01s/it, lr: 1.0e-04 loss: 2.177e-01]
latex_v1:  99%|#########9| 2972/3000 [1:09:16<00:28,  1.01s/it, lr: 1.0e-04 loss: 2.177e-01]
latex_v1:  99%|#########9| 2972/3000 [1:09:18<00:28,  1.01s/it, lr: 1.0e-04 loss: 1.173e-01]
latex_v1:  99%|#########9| 2972/3000 [1:09:18<00:28,  1.01s/it, lr: 1.0e-04 loss: 1.173e-01]
latex_v1:  99%|#########9| 2973/3000 [1:09:18<00:33,  1.23s/it, lr: 1.0e-04 loss: 1.173e-01]
latex_v1:  99%|#########9| 2973/3000 [1:09:18<00:33,  1.23s/it, lr: 1.0e-04 loss: 1.173e-01]
latex_v1:  99%|#########9| 2973/3000 [1:09:19<00:33,  1.23s/it, lr: 1.0e-04 loss: 5.703e-01]
latex_v1:  99%|#########9| 2973/3000 [1:09:19<00:33,  1.23s/it, lr: 1.0e-04 loss: 5.703e-01]
latex_v1:  99%|#########9| 2974/3000 [1:09:19<00:28,  1.10s/it, lr: 1.0e-04 loss: 5.703e-01]
latex_v1:  99%|#########9| 2974/3000 [1:09:19<00:28,  1.10s/it, lr: 1.0e-04 loss: 5.703e-01]
latex_v1:  99%|#########9| 2974/3000 [1:09:20<00:28,  1.10s/it, lr: 1.0e-04 loss: 1.014e-01]
latex_v1:  99%|#########9| 2974/3000 [1:09:20<00:28,  1.10s/it, lr: 1.0e-04 loss: 1.014e-01]
latex_v1:  99%|#########9| 2975/3000 [1:09:20<00:30,  1.23s/it, lr: 1.0e-04 loss: 1.014e-01]
latex_v1:  99%|#########9| 2975/3000 [1:09:20<00:30,  1.23s/it, lr: 1.0e-04 loss: 1.014e-01]
latex_v1:  99%|#########9| 2975/3000 [1:09:23<00:30,  1.23s/it, lr: 1.0e-04 loss: 4.456e-01]
latex_v1:  99%|#########9| 2975/3000 [1:09:23<00:30,  1.23s/it, lr: 1.0e-04 loss: 4.456e-01]
latex_v1:  99%|#########9| 2976/3000 [1:09:23<00:41,  1.71s/it, lr: 1.0e-04 loss: 4.456e-01]
latex_v1:  99%|#########9| 2976/3000 [1:09:23<00:41,  1.71s/it, lr: 1.0e-04 loss: 4.456e-01]
latex_v1:  99%|#########9| 2976/3000 [1:09:24<00:41,  1.71s/it, lr: 1.0e-04 loss: 4.743e-02]
latex_v1:  99%|#########9| 2976/3000 [1:09:24<00:41,  1.71s/it, lr: 1.0e-04 loss: 4.743e-02]
latex_v1:  99%|#########9| 2977/3000 [1:09:24<00:33,  1.44s/it, lr: 1.0e-04 loss: 4.743e-02]
latex_v1:  99%|#########9| 2977/3000 [1:09:24<00:33,  1.44s/it, lr: 1.0e-04 loss: 4.743e-02]
latex_v1:  99%|#########9| 2977/3000 [1:09:26<00:33,  1.44s/it, lr: 1.0e-04 loss: 1.656e-01]
latex_v1:  99%|#########9| 2977/3000 [1:09:26<00:33,  1.44s/it, lr: 1.0e-04 loss: 1.656e-01]
latex_v1:  99%|#########9| 2978/3000 [1:09:26<00:32,  1.46s/it, lr: 1.0e-04 loss: 1.656e-01]
latex_v1:  99%|#########9| 2978/3000 [1:09:26<00:32,  1.46s/it, lr: 1.0e-04 loss: 1.656e-01]
latex_v1:  99%|#########9| 2978/3000 [1:09:27<00:32,  1.46s/it, lr: 1.0e-04 loss: 8.142e-01]
latex_v1:  99%|#########9| 2978/3000 [1:09:27<00:32,  1.46s/it, lr: 1.0e-04 loss: 8.142e-01]
latex_v1:  99%|#########9| 2979/3000 [1:09:27<00:28,  1.38s/it, lr: 1.0e-04 loss: 8.142e-01]
latex_v1:  99%|#########9| 2979/3000 [1:09:27<00:28,  1.38s/it, lr: 1.0e-04 loss: 8.142e-01]
latex_v1:  99%|#########9| 2979/3000 [1:09:28<00:28,  1.38s/it, lr: 1.0e-04 loss: 2.182e-01]
latex_v1:  99%|#########9| 2979/3000 [1:09:28<00:28,  1.38s/it, lr: 1.0e-04 loss: 2.182e-01]
latex_v1:  99%|#########9| 2980/3000 [1:09:29<00:27,  1.38s/it, lr: 1.0e-04 loss: 1.220e-01]
latex_v1:  99%|#########9| 2980/3000 [1:09:29<00:27,  1.38s/it, lr: 1.0e-04 loss: 1.220e-01]
latex_v1:  99%|#########9| 2981/3000 [1:09:29<00:21,  1.13s/it, lr: 1.0e-04 loss: 1.220e-01]
latex_v1:  99%|#########9| 2981/3000 [1:09:29<00:21,  1.13s/it, lr: 1.0e-04 loss: 1.220e-01]
latex_v1:  99%|#########9| 2981/3000 [1:09:30<00:21,  1.13s/it, lr: 1.0e-04 loss: 7.124e-02]
latex_v1:  99%|#########9| 2981/3000 [1:09:30<00:21,  1.13s/it, lr: 1.0e-04 loss: 7.124e-02]
latex_v1:  99%|#########9| 2982/3000 [1:09:30<00:19,  1.11s/it, lr: 1.0e-04 loss: 7.124e-02]
latex_v1:  99%|#########9| 2982/3000 [1:09:30<00:19,  1.11s/it, lr: 1.0e-04 loss: 7.124e-02]
latex_v1:  99%|#########9| 2982/3000 [1:09:31<00:19,  1.11s/it, lr: 1.0e-04 loss: 2.616e-01]
latex_v1:  99%|#########9| 2982/3000 [1:09:31<00:19,  1.11s/it, lr: 1.0e-04 loss: 2.616e-01]
latex_v1:  99%|#########9| 2983/3000 [1:09:31<00:18,  1.10s/it, lr: 1.0e-04 loss: 2.616e-01]
latex_v1:  99%|#########9| 2983/3000 [1:09:31<00:18,  1.10s/it, lr: 1.0e-04 loss: 2.616e-01]
latex_v1:  99%|#########9| 2983/3000 [1:09:32<00:18,  1.10s/it, lr: 1.0e-04 loss: 3.713e-02]
latex_v1:  99%|#########9| 2983/3000 [1:09:32<00:18,  1.10s/it, lr: 1.0e-04 loss: 3.713e-02]
latex_v1:  99%|#########9| 2984/3000 [1:09:32<00:15,  1.00it/s, lr: 1.0e-04 loss: 3.713e-02]
latex_v1:  99%|#########9| 2984/3000 [1:09:32<00:15,  1.00it/s, lr: 1.0e-04 loss: 3.713e-02]
latex_v1:  99%|#########9| 2984/3000 [1:09:33<00:15,  1.00it/s, lr: 1.0e-04 loss: 1.225e-01]
latex_v1:  99%|#########9| 2984/3000 [1:09:33<00:15,  1.00it/s, lr: 1.0e-04 loss: 1.225e-01]
latex_v1: 100%|#########9| 2985/3000 [1:09:33<00:14,  1.07it/s, lr: 1.0e-04 loss: 1.225e-01]
latex_v1: 100%|#########9| 2985/3000 [1:09:33<00:14,  1.07it/s, lr: 1.0e-04 loss: 1.225e-01]
latex_v1: 100%|#########9| 2985/3000 [1:09:34<00:14,  1.07it/s, lr: 1.0e-04 loss: 4.194e-01]
latex_v1: 100%|#########9| 2985/3000 [1:09:34<00:14,  1.07it/s, lr: 1.0e-04 loss: 4.194e-01]
latex_v1: 100%|#########9| 2986/3000 [1:09:34<00:14,  1.00s/it, lr: 1.0e-04 loss: 4.194e-01]
latex_v1: 100%|#########9| 2986/3000 [1:09:34<00:14,  1.00s/it, lr: 1.0e-04 loss: 4.194e-01]
latex_v1: 100%|#########9| 2986/3000 [1:09:36<00:14,  1.00s/it, lr: 1.0e-04 loss: 4.349e-01]
latex_v1: 100%|#########9| 2986/3000 [1:09:36<00:14,  1.00s/it, lr: 1.0e-04 loss: 4.349e-01]
latex_v1: 100%|#########9| 2987/3000 [1:09:36<00:14,  1.13s/it, lr: 1.0e-04 loss: 4.349e-01]
latex_v1: 100%|#########9| 2987/3000 [1:09:36<00:14,  1.13s/it, lr: 1.0e-04 loss: 4.349e-01]
latex_v1: 100%|#########9| 2987/3000 [1:09:36<00:14,  1.13s/it, lr: 1.0e-04 loss: 1.838e-01]
latex_v1: 100%|#########9| 2987/3000 [1:09:36<00:14,  1.13s/it, lr: 1.0e-04 loss: 1.838e-01]
latex_v1: 100%|#########9| 2988/3000 [1:09:36<00:12,  1.02s/it, lr: 1.0e-04 loss: 1.838e-01]
latex_v1: 100%|#########9| 2988/3000 [1:09:36<00:12,  1.02s/it, lr: 1.0e-04 loss: 1.838e-01]
latex_v1: 100%|#########9| 2988/3000 [1:09:38<00:12,  1.02s/it, lr: 1.0e-04 loss: 5.586e-01]
latex_v1: 100%|#########9| 2988/3000 [1:09:38<00:12,  1.02s/it, lr: 1.0e-04 loss: 5.586e-01]
latex_v1: 100%|#########9| 2989/3000 [1:09:38<00:12,  1.14s/it, lr: 1.0e-04 loss: 5.586e-01]
latex_v1: 100%|#########9| 2989/3000 [1:09:38<00:12,  1.14s/it, lr: 1.0e-04 loss: 5.586e-01]
latex_v1: 100%|#########9| 2989/3000 [1:09:38<00:12,  1.14s/it, lr: 1.0e-04 loss: 2.133e-01]
latex_v1: 100%|#########9| 2989/3000 [1:09:38<00:12,  1.14s/it, lr: 1.0e-04 loss: 2.133e-01]
latex_v1: 100%|#########9| 2990/3000 [1:09:39<00:11,  1.14s/it, lr: 1.0e-04 loss: 5.493e-01]
latex_v1: 100%|#########9| 2990/3000 [1:09:39<00:11,  1.14s/it, lr: 1.0e-04 loss: 5.493e-01]
latex_v1: 100%|#########9| 2991/3000 [1:09:39<00:07,  1.27it/s, lr: 1.0e-04 loss: 5.493e-01]
latex_v1: 100%|#########9| 2991/3000 [1:09:39<00:07,  1.27it/s, lr: 1.0e-04 loss: 5.493e-01]
latex_v1: 100%|#########9| 2991/3000 [1:09:40<00:07,  1.27it/s, lr: 1.0e-04 loss: 6.611e-01]
latex_v1: 100%|#########9| 2991/3000 [1:09:40<00:07,  1.27it/s, lr: 1.0e-04 loss: 6.611e-01]
latex_v1: 100%|#########9| 2992/3000 [1:09:40<00:07,  1.14it/s, lr: 1.0e-04 loss: 6.611e-01]
latex_v1: 100%|#########9| 2992/3000 [1:09:40<00:07,  1.14it/s, lr: 1.0e-04 loss: 6.611e-01]
latex_v1: 100%|#########9| 2992/3000 [1:09:41<00:07,  1.14it/s, lr: 1.0e-04 loss: 5.174e-01]
latex_v1: 100%|#########9| 2992/3000 [1:09:41<00:07,  1.14it/s, lr: 1.0e-04 loss: 5.174e-01]
latex_v1: 100%|#########9| 2993/3000 [1:09:41<00:05,  1.19it/s, lr: 1.0e-04 loss: 5.174e-01]
latex_v1: 100%|#########9| 2993/3000 [1:09:41<00:05,  1.19it/s, lr: 1.0e-04 loss: 5.174e-01]
latex_v1: 100%|#########9| 2993/3000 [1:09:43<00:05,  1.19it/s, lr: 1.0e-04 loss: 6.205e-01]
latex_v1: 100%|#########9| 2993/3000 [1:09:43<00:05,  1.19it/s, lr: 1.0e-04 loss: 6.205e-01]
latex_v1: 100%|#########9| 2994/3000 [1:09:43<00:06,  1.03s/it, lr: 1.0e-04 loss: 6.205e-01]
latex_v1: 100%|#########9| 2994/3000 [1:09:43<00:06,  1.03s/it, lr: 1.0e-04 loss: 6.205e-01]
latex_v1: 100%|#########9| 2994/3000 [1:09:43<00:06,  1.03s/it, lr: 1.0e-04 loss: 7.933e-02]
latex_v1: 100%|#########9| 2994/3000 [1:09:43<00:06,  1.03s/it, lr: 1.0e-04 loss: 7.933e-02]
latex_v1: 100%|#########9| 2995/3000 [1:09:43<00:04,  1.05it/s, lr: 1.0e-04 loss: 7.933e-02]
latex_v1: 100%|#########9| 2995/3000 [1:09:43<00:04,  1.05it/s, lr: 1.0e-04 loss: 7.933e-02]
latex_v1: 100%|#########9| 2995/3000 [1:09:45<00:04,  1.05it/s, lr: 1.0e-04 loss: 3.373e-01]
latex_v1: 100%|#########9| 2995/3000 [1:09:45<00:04,  1.05it/s, lr: 1.0e-04 loss: 3.373e-01]
latex_v1: 100%|#########9| 2996/3000 [1:09:45<00:04,  1.06s/it, lr: 1.0e-04 loss: 3.373e-01]
latex_v1: 100%|#########9| 2996/3000 [1:09:45<00:04,  1.06s/it, lr: 1.0e-04 loss: 3.373e-01]
latex_v1: 100%|#########9| 2996/3000 [1:09:45<00:04,  1.06s/it, lr: 1.0e-04 loss: 3.054e-01]
latex_v1: 100%|#########9| 2996/3000 [1:09:45<00:04,  1.06s/it, lr: 1.0e-04 loss: 3.054e-01]
latex_v1: 100%|#########9| 2997/3000 [1:09:45<00:02,  1.03it/s, lr: 1.0e-04 loss: 3.054e-01]
latex_v1: 100%|#########9| 2997/3000 [1:09:45<00:02,  1.03it/s, lr: 1.0e-04 loss: 3.054e-01]
latex_v1: 100%|#########9| 2997/3000 [1:09:47<00:02,  1.03it/s, lr: 1.0e-04 loss: 4.990e-01]
latex_v1: 100%|#########9| 2997/3000 [1:09:47<00:02,  1.03it/s, lr: 1.0e-04 loss: 4.990e-01]
latex_v1: 100%|#########9| 2998/3000 [1:09:47<00:02,  1.19s/it, lr: 1.0e-04 loss: 4.990e-01]
latex_v1: 100%|#########9| 2998/3000 [1:09:47<00:02,  1.19s/it, lr: 1.0e-04 loss: 4.990e-01]
latex_v1: 100%|#########9| 2998/3000 [1:09:48<00:02,  1.19s/it, lr: 1.0e-04 loss: 1.075e-01]
latex_v1: 100%|#########9| 2998/3000 [1:09:48<00:02,  1.19s/it, lr: 1.0e-04 loss: 1.075e-01]
latex_v1: 100%|#########9| 2999/3000 [1:09:48<00:01,  1.06s/it, lr: 1.0e-04 loss: 1.075e-01]
latex_v1: 100%|#########9| 2999/3000 [1:09:48<00:01,  1.06s/it, lr: 1.0e-04 loss: 1.075e-01]
latex_v1: 100%|#########9| 2999/3000 [1:09:48<00:01,  1.40s/it, lr: 1.0e-04 loss: 1.075e-01]
latex_v1: 100%|#########9| 2999/3000 [1:09:48<00:01,  1.40s/it, lr: 1.0e-04 loss: 1.075e-01]

Unloading assistant lora

Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/7 [00:00<?, ?it/s]
Generating Images:  14%|#4        | 1/7 [00:02<00:15,  2.66s/it]
Generating Images:  14%|#4        | 1/7 [00:02<00:15,  2.66s/it]
Generating Images:  29%|##8       | 2/7 [00:05<00:12,  2.54s/it]
Generating Images:  29%|##8       | 2/7 [00:05<00:12,  2.54s/it]
Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.49s/it]
Generating Images:  43%|####2     | 3/7 [00:07<00:09,  2.49s/it]
Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.46s/it]
Generating Images:  57%|#####7    | 4/7 [00:09<00:07,  2.46s/it]
Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.49s/it]
Generating Images:  71%|#######1  | 5/7 [00:12<00:04,  2.49s/it]
Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.49s/it]
Generating Images:  86%|########5 | 6/7 [00:14<00:02,  2.49s/it]
Generating Images: 100%|##########| 7/7 [00:17<00:00,  2.46s/it]
Generating Images: 100%|##########| 7/7 [00:17<00:00,  2.46s/it]
                                                                
                                                                

Loading assistant lora

Saved checkpoint to /data/app/output/latex_v1/latex_v1.safetensors
Saved optimizer to /data/app/output/latex_v1/optimizer.pt