log.txt

Running 1 job
{
    "type": "diffusion_trainer",
    "training_folder": "/teamspace/studios/this_studio/ai-toolkit/output",
    "sqlite_db_path": "/teamspace/studios/this_studio/ai-toolkit/aitk_db.db",
    "device": "cuda",
    "trigger_word": "xantaraz1",
    "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": "/teamspace/studios/this_studio/ai-toolkit/datasets/antaramag",
            "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
            ],
            "controls": [],
            "shrink_video_to_frames": true,
            "num_frames": 1,
            "flip_x": false,
            "flip_y": false,
            "num_repeats": 1
        }
    ],
    "train": {
        "batch_size": 1,
        "bypass_guidance_embedding": false,
        "steps": 4000,
        "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"
    },
    "logging": {
        "log_every": 1,
        "use_ui_logger": true
    },
    "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": 250,
        "width": 1024,
        "height": 1024,
        "samples": [
            {
                "prompt": "\"xantaraz1 , \u4e00\u5f35\u771f\u5be6\u96a8\u8208\u7684iPhone\u5feb\u7167\u2014\u2014\u4e00\u5f35\u672a\u7d93\u4efb\u4f55\u5c08\u696d\u9020\u578b\u6216\u6ffe\u93e1\u8655\u7406\u7684\u5168\u8eab\u7167\uff0c\u76f4\u63a5\u5f9e\u76f8\u6a5f\u81a0\u5377\u4e2d\u53d6\u51fa\u3002\u5348\u5f8c\u7684\u967d\u5149\u659c\u5c04\u9032\u6a13\u68af\u9593\u7684\u7a97\u6236\uff0c\u71df\u9020\u51fa\u91d1\u8272\u7684\u6c1b\u570d\u3002\u756b\u9762\u4e2d\u53ea\u6709\u5169\u500b\u4eba\uff1a\u4e00\u500b\u525b\u9ad8\u4e2d\u7562\u696d\u7684\u53ef\u611b18\u6b72\u5370\u5ea6\u5973\u5b69\uff0c\u548c\u4e00\u500b\u5e74\u7d00\u76f8\u4eff\u7684\u5370\u5ea6\u7537\u5b69\u3002\u5973\u5b69\u8dea\u5728\u7a7a\u8569\u8569\u7684\u5b78\u6821\u6a13\u68af\u9593\u5149\u79bf\u79bf\u7684\u6c34\u6ce5\u53f0\u968e\u4e0a\uff0c\u7537\u5b69\u7ad9\u5728\u5979\u53f3\u5074\uff1b\u5979\u7684\u982d\u6b63\u597d\u4f4d\u65bc\u7537\u5b69\u7684\u80ef\u90e8\uff0c\u81c9\u8cbc\u8457\u4ed6\u7684\u9670\u8396\u3002  \u5973\u5b69\uff1a\u4e00\u982d\u9577\u9577\u7684\u6ce2\u6d6a\u6372\u9aee\uff0c\u767d\u7699\u7684\u76ae\u819a\uff0c\u5927\u5927\u7684\u773c\u775b\uff0c\u4ee5\u53ca\u67d4\u5ae9\u5e74\u8f15\u7684\u5bb9\u984f\u3002\u5979\u5b8c\u5168\u7d20\u984f\u2014\u2014\u76ae\u819a\u770b\u8d77\u4f86\u7121\u6bd4\u771f\u5be6\uff0c\u6bdb\u5b54\u7d30\u5c0f\uff0c\u7455\u75b5\u6e05\u6670\u53ef\u898b\u3002\u5979\u7684\u982d\u9aee\u7565\u986f\u51cc\u4e82\uff0c\u5e7e\u7e37\u88ab\u6c57\u6c34\u6d78\u6fd5\u7684\u9aee\u7d72\u8cbc\u5728\u6cdb\u7d05\u7684\u81c9\u4e0a\u3002\u5979\u90a3\u4ef6\u85cf\u85cd\u8272\u62c9\u934a\u5916\u5957\u2014\u2014\u98fe\u6709\u767d\u8272\u62fc\u63a5\u548c\u7d05\u767d\u689d\u7d0b\u2014\u2014\u62c9\u934a\u5b8c\u5168\u655e\u958b\uff0c\u9732\u51fa\u5979\u5c0f\u5de7\u81ea\u7136\u7684A\u7f69\u676f\u80f8\u90e8\u3002\u5979\u90a3\u689d\u914d\u5957\u7684\u85cf\u85cd\u8272\u904b\u52d5\u6821\u8932\u88ab\u96a8\u610f\u5730\u4e1f\u5728\u4e00\u65c1\u3002\u5979\u7684\u4e0b\u534a\u8eab\u8d64\u88f8\uff0c\u9732\u51fa\u9670\u90e8\uff1b\u5979\u9670\u5507\u4e0a\u65b9\u8986\u84cb\u8457\u4e00\u7247\u6fc3\u5bc6\u7684\u3001\u672a\u7d93\u4fee\u526a\u7684\u9577\u9670\u6bdb\u3002\u5979\u7684\u9670\u5507\u5448\u73fe\u67d4\u548c\u7684\u7c89\u8910\u8272\uff0c\u5927\u5c0f\u548c\u5f62\u72c0\u90fd\u5f88\u6b63\u5e38\uff1b\u5979\u751f\u6b96\u5668\u7684\u89e3\u5256\u7d30\u7bc0\u975e\u5e38\u903c\u771f\u3002\u5979\u8173\u4e0a\u7a7f\u8457\u767d\u8272\u904b\u52d5\u978b\u548c\u767d\u8272\u68c9\u896a\u3002\u5979\u4f4e\u8457\u982d\uff0c\u5634\u88e1\u542b\u8457\u7537\u5b69\u52c3\u8d77\u7684\u9670\u8396\uff0c\u6b63\u5728\u9032\u884c\u6fd5\u6f64\u903c\u771f\u7684\u53e3\u4ea4\uff1b\u5979\u7684\u5634\u5507\u5b8c\u5168\u5305\u88f9\u4f4f\u9670\u8396\u7684\u4e2d\u6bb5\uff0c\u820c\u982d\u7684\u52d5\u4f5c\u6e05\u6670\u53ef\u898b\uff0c\u553e\u6db2\u9806\u8457\u9670\u8396\u6ef4\u843d\u3002\u540c\u6642\uff0c\u5979\u5c07\u4e00\u96bb\u624b\u4f38\u5230\u5169\u817f\u4e4b\u9593\uff0c\u8f15\u8f15\u64ab\u6478\u81ea\u5df1\u6fc3\u5bc6\u7684\u9670\u6bdb\u3002  \u7537\u5b69\uff1a\u4ed6\u7a7f\u8457\u4e00\u4ef6\u8207\u5973\u5b69\u76f8\u914d\u7684\u85cf\u85cd\u8272\u62c9\u934a\u5916\u5957\u2014\u2014\u5916\u5957\u4e0a\u4e5f\u98fe\u6709\u767d\u8272\u62fc\u63a5\u548c\u7d05\u767d\u689d\u7d0b\u2014\u2014\u62c9\u934a\u5b8c\u5168\u655e\u958b\uff0c\u9732\u51fa\u4e0a\u534a\u8eab\u3002\u4ed6\u90a3\u689d\u85cf\u85cd\u8272\u7684\u904b\u52d5\u6821\u8932\u88ab\u62c9\u5230\u5927\u817f\u4e2d\u90e8\uff0c\u9732\u51fa\u52c3\u8d77\u7684\u9670\u8396\u3002\u4ed6\u7528\u96d9\u624b\u8f15\u8f15\u6258\u4f4f\u5973\u5b69\u7684\u982d\u2014\u2014\u6bcf\u96bb\u624b\u7684\u4e94\u6839\u624b\u6307\u90fd\u5b8c\u597d\u7121\u640d\u2014\u2014\u4ed6\u7684\u624b\u81c2\u548c\u817f\u90e8\u770b\u8d77\u4f86\u4e5f\u5f88\u6b63\u5e38\u3002\u5973\u5b69\u7f9e\u6f80\u5730\u62ac\u982d\u76f4\u8996\u8457\u7537\u5b69\uff1b\u5979\u7684\u8868\u60c5\u65e2\u7f9e\u6f80\u53c8\u5145\u6eff\u6e34\u671b\uff0c\u8207\u5979\u5929\u771f\u7121\u90aa\u7684\u5b78\u751f\u9762\u5b54\u548c\u5927\u81bd\u7684\u6027\u884c\u70ba\u5f62\u6210\u4e86\u9bae\u660e\u7684\u5c0d\u6bd4\u3002  \u80cc\u666f\uff1a\u7a7a\u8569\u8569\u7684\u5b78\u6821\u6c34\u6ce5\u6a13\u68af\u9593\u7684\u4e00\u89d2\uff0c\u91d1\u5c6c\u6276\u624b\uff0c\u5e7e\u7e37\u967d\u5149\u900f\u904e\u7e2b\u9699\u7051\u4e0b\uff0c\u7a7a\u6c23\u4e2d\u7030\u6f2b\u8457\u7d30\u5c0f\u7684\u7070\u5875\u2014\u2014\u71df\u9020\u51fa\u4e00\u7a2e\u5b89\u975c\u3001\u79c1\u5bc6\u800c\u53c8\u96b1\u853d\u7684\u6c1b\u570d\u3002\u7d30\u7dfb\u7684\u76ae\u819a\u7d0b\u7406\uff0c\u5c0f\u5de7\u800c\u81ea\u7136\u7684\u4e73\u623f\uff1b\u5177\u6709\u672a\u7d93\u7de8\u8f2f\u7684 iPhone \u7167\u7247\u7684\u771f\u5be6\u8cea\u611f\u548c\u81ea\u7136\u8272\u5f69\u3002\""
            },
            {
                "prompt": "\"xantaraz1 , A sensual, medium-close-up portrait of a stunning, slender young woman posed kneeling on a textured, light-colored bedspread. She is completely nude, with a natural body shape and subtle, natural pubic hair. Her body is arched in a dramatic, expressive posture, with one arm raised behind her head, tossing her voluminous, dark brown hair upward and backward, creating motion blur and dynamic lines. Her eyes are closed or looking down with a captivating, slightly open-mouthed expression conveying deep emotion or ecstasy. The lighting is soft, warm, and golden, suggesting late afternoon sunlight streaming in from the side, creating gentle highlights on her skin and deep shadows that sculpt her figure. The background is softly blurred (shallow depth of field), featuring warm beige and muted brown tones with a subtle geometric, possibly wood-paneled or tiled pattern angled diagonally behind her, adding visual texture. The overall mood is intimate, evocative, and painterly, captured with the aesthetic of fine art photography, high detail, and realistic texture. Cinematic lighting, professional photography, Canon EOS R5., ultra detailed, intricate details, cinematic, photorealistic, masterpiece\""
            },
            {
                "prompt": "\"xantaraz1 , A Sexy 18y Indian woman with perfect body pressed against a rain-streaked window, getting taken from behind, her breasts against the cold glass, She is standing pose and wearing a high knee length black boot, city lights reflecting on her wet skin, intense and cinematic\""
            },
            {
                "prompt": "\"xantaraz1 , anal sex, bridge position, squatting cowgirl position, 1girl, penis, nipples, medium breasts, 1boy, pussy, black thighhighs, black ponytail hair, navel, clothed male nude female, lace-trimmed legwear, closed eyes, spread legs, bottomless, girl on top, male pubic hair, long hair, erection, arm support, lace trim, smile, tattoo on thigh, grin\""
            },
            {
                "prompt": "\"xantaraz1 , A full-body portrait of a stunning Indian woman with long, flowing black hair cascading down her back, standing nude and poised in a serene, softly lit bedroom. Her body is sculpted with perfect, natural curves \u2014 full, round breasts with dark brownish areolas and nipples, a smooth midriff leading to a gently curved waist, and a deeply toned, naturally darkened pubic area that accentuates her feminine form. Her legs are long and slender, ending in a firm, rounded ass that subtly tenses as she stands with her arms relaxed at her sides, fingers slightly curled, exuding quiet confidence and sensual grace. Her gaze is direct and unflinching, meeting the viewer\u2019s eyes with a calm, alluring intensity that draws you in.  The environment is minimalist and intimate, set against a soft, neutral beige background that enhances the natural tones of her skin and hair. Behind her, sheer white curtains filter in diffused daylight, casting gentle shadows across the room, while a simple bed with rumpled white linens and a potted green plant in the corner add subtle domestic warmth without distracting from the central focus. The lighting is soft and even, highlighting the smooth texture of her skin, the subtle contours of her anatomy, and the natural sheen of her hair \u2014 all rendered with photorealistic precision to emphasize her flawless, voluptuous form.  This is a portrait of raw, unfiltered beauty \u2014 a celebration of the female body in its most natural state. Her posture is relaxed yet commanding, her expression serene and self-assured, embodying both innocence and sensuality. The composition is vertically framed, drawing attention to her full, symmetrical silhouette, while the muted, monochromatic backdrop ensures every curve, every detail of her anatomy \u2014 from the delicate arch of her collarbone to the subtle definition of her hips \u2014 is rendered with exquisite clarity. She stands as a living sculpture, a vision of erotic elegance, inviting the viewer to appreciate the harmony of her form and the quiet power of her presence.\""
            }
        ],
        "neg": "",
        "seed": 42,
        "walk_seed": true,
        "guidance_scale": 1,
        "sample_steps": 8,
        "num_frames": 1,
        "fps": 1
    }
}
Using SQLite database at /teamspace/studios/this_studio/ai-toolkit/aitk_db.db
Job ID: "cfb27aa8-eb0e-4d2d-830f-dcad89ded8ab"

#############################################
# Running job: my_first_lora_v8
#############################################


Running  1 process
Loading ZImage model
Loading transformer

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 [00:00<00:01,  1.12it/s]
Loading checkpoint shards:  33%|###3      | 1/3 [00:00<00:01,  1.12it/s]
Loading checkpoint shards:  67%|######6   | 2/3 [00:01<00:00,  1.12it/s]
Loading checkpoint shards:  67%|######6   | 2/3 [00:01<00:00,  1.12it/s]
Loading checkpoint shards: 100%|##########| 3/3 [00:02<00:00,  1.36it/s]
Loading checkpoint shards: 100%|##########| 3/3 [00:02<00:00,  1.36it/s]
Loading checkpoint shards: 100%|##########| 3/3 [00:02<00:00,  1.29it/s]
Loading checkpoint shards: 100%|##########| 3/3 [00:02<00:00,  1.29it/s]

Loading assistant LoRA
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,  6.29it/s]
  3%|3         | 1/30 [00:00<00:04,  6.29it/s]
  7%|6         | 2/30 [00:00<00:03,  7.36it/s]
  7%|6         | 2/30 [00:00<00:03,  7.36it/s]
 10%|#         | 3/30 [00:00<00:03,  7.90it/s]
 10%|#         | 3/30 [00:00<00:03,  7.90it/s]
 13%|#3        | 4/30 [00:00<00:03,  8.31it/s]
 13%|#3        | 4/30 [00:00<00:03,  8.31it/s]
 17%|#6        | 5/30 [00:00<00:02,  8.55it/s]
 17%|#6        | 5/30 [00:00<00:02,  8.55it/s]
 23%|##3       | 7/30 [00:00<00:02,  9.26it/s]
 23%|##3       | 7/30 [00:00<00:02,  9.26it/s]
 27%|##6       | 8/30 [00:00<00:02,  9.07it/s]
 27%|##6       | 8/30 [00:00<00:02,  9.07it/s]
 30%|###       | 9/30 [00:01<00:02,  9.27it/s]
 30%|###       | 9/30 [00:01<00:02,  9.27it/s]
 33%|###3      | 10/30 [00:01<00:02,  9.46it/s]
 33%|###3      | 10/30 [00:01<00:02,  9.46it/s]
 40%|####      | 12/30 [00:01<00:01,  9.42it/s]
 40%|####      | 12/30 [00:01<00:01,  9.42it/s]
 43%|####3     | 13/30 [00:01<00:01,  9.29it/s]
 43%|####3     | 13/30 [00:01<00:01,  9.29it/s]
 47%|####6     | 14/30 [00:01<00:01,  9.12it/s]
 47%|####6     | 14/30 [00:01<00:01,  9.12it/s]
 53%|#####3    | 16/30 [00:01<00:01,  9.53it/s]
 53%|#####3    | 16/30 [00:01<00:01,  9.53it/s]
 60%|######    | 18/30 [00:01<00:01,  9.76it/s]
 60%|######    | 18/30 [00:01<00:01,  9.76it/s]
 67%|######6   | 20/30 [00:02<00:01,  9.79it/s]
 67%|######6   | 20/30 [00:02<00:01,  9.79it/s]
 73%|#######3  | 22/30 [00:02<00:00, 10.22it/s]
 73%|#######3  | 22/30 [00:02<00:00, 10.22it/s]
 80%|########  | 24/30 [00:02<00:00, 10.24it/s]
 80%|########  | 24/30 [00:02<00:00, 10.24it/s]
 87%|########6 | 26/30 [00:02<00:00, 10.00it/s]
 87%|########6 | 26/30 [00:02<00:00, 10.00it/s]
 90%|######### | 27/30 [00:02<00:00,  9.72it/s]
 90%|######### | 27/30 [00:02<00:00,  9.72it/s]
 93%|#########3| 28/30 [00:02<00:00,  9.49it/s]
 93%|#########3| 28/30 [00:02<00:00,  9.49it/s]
100%|##########| 30/30 [00:03<00:00,  9.70it/s]
100%|##########| 30/30 [00:03<00:00,  9.70it/s]
100%|##########| 30/30 [00:03<00:00,  9.42it/s]
100%|##########| 30/30 [00:03<00:00,  9.42it/s]

 - quantizing extras
Text Encoder
`torch_dtype` is deprecated! Use `dtype` instead!
`torch_dtype` is deprecated! Use `dtype` instead!

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, 58.53it/s]
Loading checkpoint shards: 100%|##########| 3/3 [00:00<00:00, 58.53it/s]

Quantizing Text Encoder
Loading VAE
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: /teamspace/studios/this_studio/ai-toolkit/datasets/antaramag
  -  Preprocessing image dimensions

  0%|          | 0/6 [00:00<?, ?it/s]
  0%|          | 0/6 [00:00<?, ?it/s]
100%|##########| 6/6 [00:00<00:00, 151.03it/s]
100%|##########| 6/6 [00:00<00:00, 151.03it/s]

  -  Found 6 images
Bucket sizes for /teamspace/studios/this_studio/ai-toolkit/datasets/antaramag:
384x384: 1 files
384x672: 1 files
672x384: 1 files
480x544: 1 files
416x576: 2 files
5 buckets made
Dataset: /teamspace/studios/this_studio/ai-toolkit/datasets/antaramag
  -  Preprocessing image dimensions

  0%|          | 0/6 [00:00<?, ?it/s]
  0%|          | 0/6 [00:00<?, ?it/s]
100%|##########| 6/6 [00:00<00:00, 24745.16it/s]
100%|##########| 6/6 [00:00<00:00, 24745.16it/s]

  -  Found 6 images
Bucket sizes for /teamspace/studios/this_studio/ai-toolkit/datasets/antaramag:
384x384: 1 files
576x992: 1 files
992x576: 1 files
480x544: 1 files
672x864: 2 files
5 buckets made
Generating baseline samples before training
Unloading assistant lora

Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
Generating Images:  20%|##        | 1/5 [00:08<00:33,  8.38s/it]
Generating Images:  20%|##        | 1/5 [00:08<00:33,  8.38s/it]
Generating Images:  40%|####      | 2/5 [00:16<00:24,  8.03s/it]
Generating Images:  40%|####      | 2/5 [00:16<00:24,  8.03s/it]
Generating Images:  60%|######    | 3/5 [00:23<00:15,  7.80s/it]
Generating Images:  60%|######    | 3/5 [00:23<00:15,  7.80s/it]
Generating Images:  80%|########  | 4/5 [00:31<00:07,  7.72s/it]
Generating Images:  80%|########  | 4/5 [00:31<00:07,  7.72s/it]
Generating Images: 100%|##########| 5/5 [00:39<00:00,  7.90s/it]
Generating Images: 100%|##########| 5/5 [00:39<00:00,  7.90s/it]
                                                                
                                                                

Loading assistant lora

my_first_lora_v8:   0%|          | 0/4000 [00:00<?, ?it/s]
my_first_lora_v8:   0%|          | 0/4000 [00:00<?, ?it/s]
my_first_lora_v8:   0%|          | 0/4000 [00:01<?, ?it/s, lr: 1.0e-04 loss: 2.474e-01]
my_first_lora_v8:   0%|          | 0/4000 [00:01<?, ?it/s, lr: 1.0e-04 loss: 2.474e-01]
my_first_lora_v8:   0%|          | 0/4000 [00:01<?, ?it/s, lr: 1.0e-04 loss: 2.474e-01]
my_first_lora_v8:   0%|          | 0/4000 [00:01<?, ?it/s, lr: 1.0e-04 loss: 2.474e-01]
my_first_lora_v8:   0%|          | 0/4000 [00:02<?, ?it/s, lr: 1.0e-04 loss: 6.980e-01]
my_first_lora_v8:   0%|          | 0/4000 [00:02<?, ?it/s, lr: 1.0e-04 loss: 6.980e-01]
my_first_lora_v8:   0%|          | 1/4000 [00:02<3:10:05,  2.85s/it, lr: 1.0e-04 loss: 7.479e-02]
my_first_lora_v8:   0%|          | 1/4000 [00:02<3:10:05,  2.85s/it, lr: 1.0e-04 loss: 7.479e-02]
my_first_lora_v8:   0%|          | 2/4000 [00:04<2:24:56,  2.18s/it, lr: 1.0e-04 loss: 1.952e-01]
my_first_lora_v8:   0%|          | 2/4000 [00:04<2:24:56,  2.18s/it, lr: 1.0e-04 loss: 1.952e-01]
my_first_lora_v8:   0%|          | 3/4000 [00:05<2:09:39,  1.95s/it, lr: 1.0e-04 loss: 8.164e-01]
my_first_lora_v8:   0%|          | 3/4000 [00:05<2:09:39,  1.95s/it, lr: 1.0e-04 loss: 8.164e-01]
my_first_lora_v8:   0%|          | 4/4000 [00:06<1:50:21,  1.66s/it, lr: 1.0e-04 loss: 7.071e-01]
my_first_lora_v8:   0%|          | 4/4000 [00:06<1:50:21,  1.66s/it, lr: 1.0e-04 loss: 7.071e-01]
my_first_lora_v8:   0%|          | 5/4000 [00:08<1:47:47,  1.62s/it, lr: 1.0e-04 loss: 3.621e-01]
my_first_lora_v8:   0%|          | 5/4000 [00:08<1:47:47,  1.62s/it, lr: 1.0e-04 loss: 3.621e-01]
my_first_lora_v8:   0%|          | 6/4000 [00:09<1:45:55,  1.59s/it, lr: 1.0e-04 loss: 6.580e-01]
my_first_lora_v8:   0%|          | 6/4000 [00:09<1:45:55,  1.59s/it, lr: 1.0e-04 loss: 6.580e-01]
my_first_lora_v8:   0%|          | 7/4000 [00:10<1:38:30,  1.48s/it, lr: 1.0e-04 loss: 1.603e-01]
my_first_lora_v8:   0%|          | 7/4000 [00:10<1:38:30,  1.48s/it, lr: 1.0e-04 loss: 1.603e-01]
my_first_lora_v8:   0%|          | 8/4000 [00:11<1:32:59,  1.40s/it, lr: 1.0e-04 loss: 7.644e-01]
my_first_lora_v8:   0%|          | 8/4000 [00:11<1:32:59,  1.40s/it, lr: 1.0e-04 loss: 7.644e-01]
my_first_lora_v8:   0%|          | 9/4000 [00:11<1:28:35,  1.33s/it, lr: 1.0e-04 loss: 6.681e-01]
my_first_lora_v8:   0%|          | 9/4000 [00:11<1:28:35,  1.33s/it, lr: 1.0e-04 loss: 6.681e-01]
my_first_lora_v8:   0%|          | 10/4000 [00:12<1:24:53,  1.28s/it, lr: 1.0e-04 loss: 1.036e-01]
my_first_lora_v8:   0%|          | 10/4000 [00:12<1:24:53,  1.28s/it, lr: 1.0e-04 loss: 1.036e-01]
my_first_lora_v8:   0%|          | 11/4000 [00:14<1:27:07,  1.31s/it, lr: 1.0e-04 loss: 9.076e-02]
my_first_lora_v8:   0%|          | 11/4000 [00:14<1:27:07,  1.31s/it, lr: 1.0e-04 loss: 9.076e-02]
my_first_lora_v8:   0%|          | 12/4000 [00:15<1:26:10,  1.30s/it, lr: 1.0e-04 loss: 2.006e-02]
my_first_lora_v8:   0%|          | 12/4000 [00:15<1:26:10,  1.30s/it, lr: 1.0e-04 loss: 2.006e-02]
my_first_lora_v8:   0%|          | 13/4000 [00:16<1:23:36,  1.26s/it, lr: 1.0e-04 loss: 2.384e-01]
my_first_lora_v8:   0%|          | 13/4000 [00:16<1:23:36,  1.26s/it, lr: 1.0e-04 loss: 2.384e-01]
my_first_lora_v8:   0%|          | 14/4000 [00:17<1:24:36,  1.27s/it, lr: 1.0e-04 loss: 2.811e-01]
my_first_lora_v8:   0%|          | 14/4000 [00:17<1:24:36,  1.27s/it, lr: 1.0e-04 loss: 2.811e-01]
my_first_lora_v8:   0%|          | 15/4000 [00:18<1:22:22,  1.24s/it, lr: 1.0e-04 loss: 2.792e-01]
my_first_lora_v8:   0%|          | 15/4000 [00:18<1:22:22,  1.24s/it, lr: 1.0e-04 loss: 2.792e-01]
my_first_lora_v8:   0%|          | 16/4000 [00:19<1:20:37,  1.21s/it, lr: 1.0e-04 loss: 6.337e-01]
my_first_lora_v8:   0%|          | 16/4000 [00:19<1:20:37,  1.21s/it, lr: 1.0e-04 loss: 6.337e-01]
my_first_lora_v8:   0%|          | 17/4000 [00:20<1:18:56,  1.19s/it, lr: 1.0e-04 loss: 6.168e-01]
my_first_lora_v8:   0%|          | 17/4000 [00:20<1:18:56,  1.19s/it, lr: 1.0e-04 loss: 6.168e-01]
my_first_lora_v8:   0%|          | 18/4000 [00:20<1:17:22,  1.17s/it, lr: 1.0e-04 loss: 5.909e-01]
my_first_lora_v8:   0%|          | 18/4000 [00:20<1:17:22,  1.17s/it, lr: 1.0e-04 loss: 5.909e-01]
my_first_lora_v8:   0%|          | 19/4000 [00:22<1:18:29,  1.18s/it, lr: 1.0e-04 loss: 2.269e-01]
my_first_lora_v8:   0%|          | 19/4000 [00:22<1:18:29,  1.18s/it, lr: 1.0e-04 loss: 2.269e-01]
my_first_lora_v8:   0%|          | 20/4000 [00:23<1:17:12,  1.16s/it, lr: 1.0e-04 loss: 3.162e-01]
my_first_lora_v8:   0%|          | 20/4000 [00:23<1:17:12,  1.16s/it, lr: 1.0e-04 loss: 3.162e-01]
my_first_lora_v8:   1%|          | 21/4000 [00:24<1:15:56,  1.15s/it, lr: 1.0e-04 loss: 2.817e-01]
my_first_lora_v8:   1%|          | 21/4000 [00:24<1:15:56,  1.15s/it, lr: 1.0e-04 loss: 2.817e-01]
my_first_lora_v8:   1%|          | 22/4000 [00:25<1:16:55,  1.16s/it, lr: 1.0e-04 loss: 4.580e-01]
my_first_lora_v8:   1%|          | 22/4000 [00:25<1:16:55,  1.16s/it, lr: 1.0e-04 loss: 4.580e-01]
my_first_lora_v8:   1%|          | 23/4000 [00:26<1:16:18,  1.15s/it, lr: 1.0e-04 loss: 6.318e-01]
my_first_lora_v8:   1%|          | 23/4000 [00:26<1:16:18,  1.15s/it, lr: 1.0e-04 loss: 6.318e-01]
my_first_lora_v8:   1%|          | 24/4000 [00:27<1:15:21,  1.14s/it, lr: 1.0e-04 loss: 4.180e-01]
my_first_lora_v8:   1%|          | 24/4000 [00:27<1:15:21,  1.14s/it, lr: 1.0e-04 loss: 4.180e-01]
my_first_lora_v8:   1%|          | 25/4000 [00:28<1:16:16,  1.15s/it, lr: 1.0e-04 loss: 7.750e-01]
my_first_lora_v8:   1%|          | 25/4000 [00:28<1:16:16,  1.15s/it, lr: 1.0e-04 loss: 7.750e-01]
my_first_lora_v8:   1%|          | 26/4000 [00:29<1:16:14,  1.15s/it, lr: 1.0e-04 loss: 4.897e-01]
my_first_lora_v8:   1%|          | 26/4000 [00:29<1:16:14,  1.15s/it, lr: 1.0e-04 loss: 4.897e-01]
my_first_lora_v8:   1%|          | 27/4000 [00:30<1:15:18,  1.14s/it, lr: 1.0e-04 loss: 3.684e-01]
my_first_lora_v8:   1%|          | 27/4000 [00:30<1:15:18,  1.14s/it, lr: 1.0e-04 loss: 3.684e-01]
my_first_lora_v8:   1%|          | 28/4000 [00:31<1:14:29,  1.13s/it, lr: 1.0e-04 loss: 5.955e-01]
my_first_lora_v8:   1%|          | 28/4000 [00:31<1:14:29,  1.13s/it, lr: 1.0e-04 loss: 5.955e-01]
my_first_lora_v8:   1%|          | 29/4000 [00:32<1:13:43,  1.11s/it, lr: 1.0e-04 loss: 2.243e-01]
my_first_lora_v8:   1%|          | 29/4000 [00:32<1:13:43,  1.11s/it, lr: 1.0e-04 loss: 2.243e-01]
my_first_lora_v8:   1%|          | 30/4000 [00:33<1:12:57,  1.10s/it, lr: 1.0e-04 loss: 3.346e-01]
my_first_lora_v8:   1%|          | 30/4000 [00:33<1:12:57,  1.10s/it, lr: 1.0e-04 loss: 3.346e-01]
my_first_lora_v8:   1%|          | 31/4000 [00:33<1:12:14,  1.09s/it, lr: 1.0e-04 loss: 1.979e-01]
my_first_lora_v8:   1%|          | 31/4000 [00:33<1:12:14,  1.09s/it, lr: 1.0e-04 loss: 1.979e-01]
my_first_lora_v8:   1%|          | 32/4000 [00:35<1:13:01,  1.10s/it, lr: 1.0e-04 loss: 4.776e-01]
my_first_lora_v8:   1%|          | 32/4000 [00:35<1:13:01,  1.10s/it, lr: 1.0e-04 loss: 4.776e-01]
my_first_lora_v8:   1%|          | 33/4000 [00:36<1:13:45,  1.12s/it, lr: 1.0e-04 loss: 3.852e-01]
my_first_lora_v8:   1%|          | 33/4000 [00:36<1:13:45,  1.12s/it, lr: 1.0e-04 loss: 3.852e-01]
my_first_lora_v8:   1%|          | 34/4000 [00:38<1:14:29,  1.13s/it, lr: 1.0e-04 loss: 1.793e-01]
my_first_lora_v8:   1%|          | 34/4000 [00:38<1:14:29,  1.13s/it, lr: 1.0e-04 loss: 1.793e-01]
my_first_lora_v8:   1%|          | 35/4000 [00:39<1:15:24,  1.14s/it, lr: 1.0e-04 loss: 3.841e-01]
my_first_lora_v8:   1%|          | 35/4000 [00:39<1:15:24,  1.14s/it, lr: 1.0e-04 loss: 3.841e-01]
my_first_lora_v8:   1%|          | 36/4000 [00:41<1:15:59,  1.15s/it, lr: 1.0e-04 loss: 4.020e-01]
my_first_lora_v8:   1%|          | 36/4000 [00:41<1:15:59,  1.15s/it, lr: 1.0e-04 loss: 4.020e-01]
my_first_lora_v8:   1%|          | 37/4000 [00:42<1:15:22,  1.14s/it, lr: 1.0e-04 loss: 7.128e-01]
my_first_lora_v8:   1%|          | 37/4000 [00:42<1:15:22,  1.14s/it, lr: 1.0e-04 loss: 7.128e-01]
my_first_lora_v8:   1%|          | 38/4000 [00:43<1:15:56,  1.15s/it, lr: 1.0e-04 loss: 5.841e-01]
my_first_lora_v8:   1%|          | 38/4000 [00:43<1:15:56,  1.15s/it, lr: 1.0e-04 loss: 5.841e-01]
my_first_lora_v8:   1%|          | 39/4000 [00:44<1:15:56,  1.15s/it, lr: 1.0e-04 loss: 1.959e-01]
my_first_lora_v8:   1%|          | 39/4000 [00:44<1:15:56,  1.15s/it, lr: 1.0e-04 loss: 1.959e-01]
my_first_lora_v8:   1%|1         | 40/4000 [00:45<1:15:22,  1.14s/it, lr: 1.0e-04 loss: 3.858e-01]
my_first_lora_v8:   1%|1         | 40/4000 [00:45<1:15:22,  1.14s/it, lr: 1.0e-04 loss: 3.858e-01]
my_first_lora_v8:   1%|1         | 41/4000 [00:46<1:14:45,  1.13s/it, lr: 1.0e-04 loss: 6.643e-01]
my_first_lora_v8:   1%|1         | 41/4000 [00:46<1:14:45,  1.13s/it, lr: 1.0e-04 loss: 6.643e-01]
my_first_lora_v8:   1%|1         | 42/4000 [00:47<1:14:14,  1.13s/it, lr: 1.0e-04 loss: 4.350e-01]
my_first_lora_v8:   1%|1         | 42/4000 [00:47<1:14:14,  1.13s/it, lr: 1.0e-04 loss: 4.350e-01]
my_first_lora_v8:   1%|1         | 43/4000 [00:48<1:13:43,  1.12s/it, lr: 1.0e-04 loss: 2.820e-01]
my_first_lora_v8:   1%|1         | 43/4000 [00:48<1:13:43,  1.12s/it, lr: 1.0e-04 loss: 2.820e-01]
my_first_lora_v8:   1%|1         | 44/4000 [00:48<1:13:12,  1.11s/it, lr: 1.0e-04 loss: 7.087e-01]
my_first_lora_v8:   1%|1         | 44/4000 [00:48<1:13:12,  1.11s/it, lr: 1.0e-04 loss: 7.087e-01]
my_first_lora_v8:   1%|1         | 45/4000 [00:49<1:12:40,  1.10s/it, lr: 1.0e-04 loss: 7.949e-02]
my_first_lora_v8:   1%|1         | 45/4000 [00:49<1:12:40,  1.10s/it, lr: 1.0e-04 loss: 7.949e-02]
my_first_lora_v8:   1%|1         | 46/4000 [00:51<1:13:12,  1.11s/it, lr: 1.0e-04 loss: 3.489e-01]
my_first_lora_v8:   1%|1         | 46/4000 [00:51<1:13:12,  1.11s/it, lr: 1.0e-04 loss: 3.489e-01]
my_first_lora_v8:   1%|1         | 47/4000 [00:52<1:13:02,  1.11s/it, lr: 1.0e-04 loss: 5.593e-01]
my_first_lora_v8:   1%|1         | 47/4000 [00:52<1:13:02,  1.11s/it, lr: 1.0e-04 loss: 5.593e-01]
my_first_lora_v8:   1%|1         | 48/4000 [00:52<1:12:36,  1.10s/it, lr: 1.0e-04 loss: 4.396e-01]
my_first_lora_v8:   1%|1         | 48/4000 [00:52<1:12:36,  1.10s/it, lr: 1.0e-04 loss: 4.396e-01]
my_first_lora_v8:   1%|1         | 49/4000 [00:53<1:12:09,  1.10s/it, lr: 1.0e-04 loss: 1.827e-01]
my_first_lora_v8:   1%|1         | 49/4000 [00:53<1:12:09,  1.10s/it, lr: 1.0e-04 loss: 1.827e-01]
my_first_lora_v8:   1%|1         | 50/4000 [00:54<1:11:45,  1.09s/it, lr: 1.0e-04 loss: 1.524e-02]
my_first_lora_v8:   1%|1         | 50/4000 [00:54<1:11:45,  1.09s/it, lr: 1.0e-04 loss: 1.524e-02]
my_first_lora_v8:   1%|1         | 51/4000 [00:55<1:11:20,  1.08s/it, lr: 1.0e-04 loss: 2.148e-01]
my_first_lora_v8:   1%|1         | 51/4000 [00:55<1:11:20,  1.08s/it, lr: 1.0e-04 loss: 2.148e-01]
my_first_lora_v8:   1%|1         | 52/4000 [00:56<1:11:49,  1.09s/it, lr: 1.0e-04 loss: 6.338e-01]
my_first_lora_v8:   1%|1         | 52/4000 [00:56<1:11:49,  1.09s/it, lr: 1.0e-04 loss: 6.338e-01]
my_first_lora_v8:   1%|1         | 53/4000 [00:57<1:11:52,  1.09s/it, lr: 1.0e-04 loss: 5.627e-01]
my_first_lora_v8:   1%|1         | 53/4000 [00:57<1:11:52,  1.09s/it, lr: 1.0e-04 loss: 5.627e-01]
my_first_lora_v8:   1%|1         | 54/4000 [00:59<1:12:20,  1.10s/it, lr: 1.0e-04 loss: 1.034e-01]
my_first_lora_v8:   1%|1         | 54/4000 [00:59<1:12:20,  1.10s/it, lr: 1.0e-04 loss: 1.034e-01]
my_first_lora_v8:   1%|1         | 55/4000 [01:00<1:12:48,  1.11s/it, lr: 1.0e-04 loss: 4.395e-02]
my_first_lora_v8:   1%|1         | 55/4000 [01:00<1:12:48,  1.11s/it, lr: 1.0e-04 loss: 4.395e-02]
my_first_lora_v8:   1%|1         | 56/4000 [01:01<1:12:24,  1.10s/it, lr: 1.0e-04 loss: 2.649e-01]
my_first_lora_v8:   1%|1         | 56/4000 [01:01<1:12:24,  1.10s/it, lr: 1.0e-04 loss: 2.649e-01]
my_first_lora_v8:   1%|1         | 57/4000 [01:03<1:12:51,  1.11s/it, lr: 1.0e-04 loss: 5.220e-01]
my_first_lora_v8:   1%|1         | 57/4000 [01:03<1:12:51,  1.11s/it, lr: 1.0e-04 loss: 5.220e-01]
my_first_lora_v8:   1%|1         | 58/4000 [01:04<1:12:30,  1.10s/it, lr: 1.0e-04 loss: 6.000e-01]
my_first_lora_v8:   1%|1         | 58/4000 [01:04<1:12:30,  1.10s/it, lr: 1.0e-04 loss: 6.000e-01]
my_first_lora_v8:   1%|1         | 59/4000 [01:04<1:12:20,  1.10s/it, lr: 1.0e-04 loss: 8.002e-01]
my_first_lora_v8:   1%|1         | 59/4000 [01:04<1:12:20,  1.10s/it, lr: 1.0e-04 loss: 8.002e-01]
my_first_lora_v8:   2%|1         | 60/4000 [01:05<1:12:00,  1.10s/it, lr: 1.0e-04 loss: 4.433e-01]
my_first_lora_v8:   2%|1         | 60/4000 [01:05<1:12:00,  1.10s/it, lr: 1.0e-04 loss: 4.433e-01]
my_first_lora_v8:   2%|1         | 61/4000 [01:06<1:11:39,  1.09s/it, lr: 1.0e-04 loss: 5.988e-01]
my_first_lora_v8:   2%|1         | 61/4000 [01:06<1:11:39,  1.09s/it, lr: 1.0e-04 loss: 5.988e-01]
my_first_lora_v8:   2%|1         | 62/4000 [01:08<1:12:04,  1.10s/it, lr: 1.0e-04 loss: 9.040e-02]
my_first_lora_v8:   2%|1         | 62/4000 [01:08<1:12:04,  1.10s/it, lr: 1.0e-04 loss: 9.040e-02]
my_first_lora_v8:   2%|1         | 63/4000 [01:08<1:11:43,  1.09s/it, lr: 1.0e-04 loss: 2.478e-01]
my_first_lora_v8:   2%|1         | 63/4000 [01:08<1:11:43,  1.09s/it, lr: 1.0e-04 loss: 2.478e-01]
my_first_lora_v8:   2%|1         | 64/4000 [01:09<1:11:22,  1.09s/it, lr: 1.0e-04 loss: 2.979e-01]
my_first_lora_v8:   2%|1         | 64/4000 [01:09<1:11:22,  1.09s/it, lr: 1.0e-04 loss: 2.979e-01]
my_first_lora_v8:   2%|1         | 65/4000 [01:10<1:11:25,  1.09s/it, lr: 1.0e-04 loss: 5.542e-01]
my_first_lora_v8:   2%|1         | 65/4000 [01:10<1:11:25,  1.09s/it, lr: 1.0e-04 loss: 5.542e-01]
my_first_lora_v8:   2%|1         | 66/4000 [01:11<1:11:08,  1.09s/it, lr: 1.0e-04 loss: 2.887e-01]
my_first_lora_v8:   2%|1         | 66/4000 [01:11<1:11:08,  1.09s/it, lr: 1.0e-04 loss: 2.887e-01]
my_first_lora_v8:   2%|1         | 67/4000 [01:12<1:10:53,  1.08s/it, lr: 1.0e-04 loss: 6.990e-01]
my_first_lora_v8:   2%|1         | 67/4000 [01:12<1:10:53,  1.08s/it, lr: 1.0e-04 loss: 6.990e-01]
my_first_lora_v8:   2%|1         | 68/4000 [01:13<1:11:16,  1.09s/it, lr: 1.0e-04 loss: 6.108e-01]
my_first_lora_v8:   2%|1         | 68/4000 [01:13<1:11:16,  1.09s/it, lr: 1.0e-04 loss: 6.108e-01]
my_first_lora_v8:   2%|1         | 69/4000 [01:15<1:11:40,  1.09s/it, lr: 1.0e-04 loss: 5.730e-01]
my_first_lora_v8:   2%|1         | 69/4000 [01:15<1:11:40,  1.09s/it, lr: 1.0e-04 loss: 5.730e-01]
my_first_lora_v8:   2%|1         | 70/4000 [01:16<1:12:02,  1.10s/it, lr: 1.0e-04 loss: 5.789e-01]
my_first_lora_v8:   2%|1         | 70/4000 [01:16<1:12:02,  1.10s/it, lr: 1.0e-04 loss: 5.789e-01]
my_first_lora_v8:   2%|1         | 71/4000 [01:18<1:12:31,  1.11s/it, lr: 1.0e-04 loss: 7.402e-01]
my_first_lora_v8:   2%|1         | 71/4000 [01:18<1:12:31,  1.11s/it, lr: 1.0e-04 loss: 7.402e-01]
my_first_lora_v8:   2%|1         | 72/4000 [01:19<1:12:12,  1.10s/it, lr: 1.0e-04 loss: 4.072e-01]
my_first_lora_v8:   2%|1         | 72/4000 [01:19<1:12:12,  1.10s/it, lr: 1.0e-04 loss: 4.072e-01]
my_first_lora_v8:   2%|1         | 73/4000 [01:20<1:11:53,  1.10s/it, lr: 1.0e-04 loss: 7.888e-01]
my_first_lora_v8:   2%|1         | 73/4000 [01:20<1:11:53,  1.10s/it, lr: 1.0e-04 loss: 7.888e-01]
my_first_lora_v8:   2%|1         | 74/4000 [01:20<1:11:36,  1.09s/it, lr: 1.0e-04 loss: 5.446e-01]
my_first_lora_v8:   2%|1         | 74/4000 [01:20<1:11:36,  1.09s/it, lr: 1.0e-04 loss: 5.446e-01]
my_first_lora_v8:   2%|1         | 75/4000 [01:22<1:11:57,  1.10s/it, lr: 1.0e-04 loss: 7.385e-01]
my_first_lora_v8:   2%|1         | 75/4000 [01:22<1:11:57,  1.10s/it, lr: 1.0e-04 loss: 7.385e-01]
my_first_lora_v8:   2%|1         | 76/4000 [01:24<1:12:18,  1.11s/it, lr: 1.0e-04 loss: 2.023e-01]
my_first_lora_v8:   2%|1         | 76/4000 [01:24<1:12:18,  1.11s/it, lr: 1.0e-04 loss: 2.023e-01]
my_first_lora_v8:   2%|1         | 77/4000 [01:24<1:11:59,  1.10s/it, lr: 1.0e-04 loss: 1.639e-01]
my_first_lora_v8:   2%|1         | 77/4000 [01:24<1:11:59,  1.10s/it, lr: 1.0e-04 loss: 1.639e-01]
my_first_lora_v8:   2%|1         | 78/4000 [01:25<1:11:43,  1.10s/it, lr: 1.0e-04 loss: 2.089e-01]
my_first_lora_v8:   2%|1         | 78/4000 [01:25<1:11:43,  1.10s/it, lr: 1.0e-04 loss: 2.089e-01]
my_first_lora_v8:   2%|1         | 79/4000 [01:26<1:11:46,  1.10s/it, lr: 1.0e-04 loss: 6.431e-01]
my_first_lora_v8:   2%|1         | 79/4000 [01:26<1:11:46,  1.10s/it, lr: 1.0e-04 loss: 6.431e-01]
my_first_lora_v8:   2%|2         | 80/4000 [01:28<1:12:04,  1.10s/it, lr: 1.0e-04 loss: 6.541e-01]
my_first_lora_v8:   2%|2         | 80/4000 [01:28<1:12:04,  1.10s/it, lr: 1.0e-04 loss: 6.541e-01]
my_first_lora_v8:   2%|2         | 81/4000 [01:29<1:11:47,  1.10s/it, lr: 1.0e-04 loss: 3.323e-01]
my_first_lora_v8:   2%|2         | 81/4000 [01:29<1:11:47,  1.10s/it, lr: 1.0e-04 loss: 3.323e-01]
my_first_lora_v8:   2%|2         | 82/4000 [01:29<1:11:31,  1.10s/it, lr: 1.0e-04 loss: 4.725e-01]
my_first_lora_v8:   2%|2         | 82/4000 [01:29<1:11:31,  1.10s/it, lr: 1.0e-04 loss: 4.725e-01]
my_first_lora_v8:   2%|2         | 83/4000 [01:30<1:11:26,  1.09s/it, lr: 1.0e-04 loss: 7.769e-01]
my_first_lora_v8:   2%|2         | 83/4000 [01:30<1:11:26,  1.09s/it, lr: 1.0e-04 loss: 7.769e-01]
my_first_lora_v8:   2%|2         | 84/4000 [01:32<1:11:43,  1.10s/it, lr: 1.0e-04 loss: 7.287e-01]
my_first_lora_v8:   2%|2         | 84/4000 [01:32<1:11:43,  1.10s/it, lr: 1.0e-04 loss: 7.287e-01]
my_first_lora_v8:   2%|2         | 85/4000 [01:33<1:11:30,  1.10s/it, lr: 1.0e-04 loss: 1.573e-01]
my_first_lora_v8:   2%|2         | 85/4000 [01:33<1:11:30,  1.10s/it, lr: 1.0e-04 loss: 1.573e-01]
my_first_lora_v8:   2%|2         | 86/4000 [01:34<1:11:47,  1.10s/it, lr: 1.0e-04 loss: 6.427e-02]
my_first_lora_v8:   2%|2         | 86/4000 [01:34<1:11:47,  1.10s/it, lr: 1.0e-04 loss: 6.427e-02]
my_first_lora_v8:   2%|2         | 87/4000 [01:35<1:11:32,  1.10s/it, lr: 1.0e-04 loss: 1.600e-01]
my_first_lora_v8:   2%|2         | 87/4000 [01:35<1:11:32,  1.10s/it, lr: 1.0e-04 loss: 1.600e-01]
my_first_lora_v8:   2%|2         | 88/4000 [01:36<1:11:19,  1.09s/it, lr: 1.0e-04 loss: 7.330e-01]
my_first_lora_v8:   2%|2         | 88/4000 [01:36<1:11:19,  1.09s/it, lr: 1.0e-04 loss: 7.330e-01]
my_first_lora_v8:   2%|2         | 89/4000 [01:37<1:11:04,  1.09s/it, lr: 1.0e-04 loss: 6.700e-01]
my_first_lora_v8:   2%|2         | 89/4000 [01:37<1:11:04,  1.09s/it, lr: 1.0e-04 loss: 6.700e-01]
my_first_lora_v8:   2%|2         | 90/4000 [01:38<1:11:22,  1.10s/it, lr: 1.0e-04 loss: 6.541e-01]
my_first_lora_v8:   2%|2         | 90/4000 [01:38<1:11:22,  1.10s/it, lr: 1.0e-04 loss: 6.541e-01]
my_first_lora_v8:   2%|2         | 91/4000 [01:40<1:11:39,  1.10s/it, lr: 1.0e-04 loss: 3.567e-01]
my_first_lora_v8:   2%|2         | 91/4000 [01:40<1:11:39,  1.10s/it, lr: 1.0e-04 loss: 3.567e-01]
my_first_lora_v8:   2%|2         | 92/4000 [01:40<1:11:27,  1.10s/it, lr: 1.0e-04 loss: 6.872e-01]
my_first_lora_v8:   2%|2         | 92/4000 [01:40<1:11:27,  1.10s/it, lr: 1.0e-04 loss: 6.872e-01]
my_first_lora_v8:   2%|2         | 93/4000 [01:42<1:11:30,  1.10s/it, lr: 1.0e-04 loss: 4.607e-01]
my_first_lora_v8:   2%|2         | 93/4000 [01:42<1:11:30,  1.10s/it, lr: 1.0e-04 loss: 4.607e-01]
my_first_lora_v8:   2%|2         | 94/4000 [01:42<1:11:16,  1.09s/it, lr: 1.0e-04 loss: 4.286e-01]
my_first_lora_v8:   2%|2         | 94/4000 [01:42<1:11:16,  1.09s/it, lr: 1.0e-04 loss: 4.286e-01]
my_first_lora_v8:   2%|2         | 95/4000 [01:43<1:11:11,  1.09s/it, lr: 1.0e-04 loss: 4.069e-01]
my_first_lora_v8:   2%|2         | 95/4000 [01:43<1:11:11,  1.09s/it, lr: 1.0e-04 loss: 4.069e-01]
my_first_lora_v8:   2%|2         | 96/4000 [01:44<1:10:57,  1.09s/it, lr: 1.0e-04 loss: 2.056e-02]
my_first_lora_v8:   2%|2         | 96/4000 [01:44<1:10:57,  1.09s/it, lr: 1.0e-04 loss: 2.056e-02]
my_first_lora_v8:   2%|2         | 97/4000 [01:45<1:10:44,  1.09s/it, lr: 1.0e-04 loss: 4.892e-01]
my_first_lora_v8:   2%|2         | 97/4000 [01:45<1:10:44,  1.09s/it, lr: 1.0e-04 loss: 4.892e-01]
my_first_lora_v8:   2%|2         | 98/4000 [01:46<1:10:31,  1.08s/it, lr: 1.0e-04 loss: 1.415e-01]
my_first_lora_v8:   2%|2         | 98/4000 [01:46<1:10:31,  1.08s/it, lr: 1.0e-04 loss: 1.415e-01]
my_first_lora_v8:   2%|2         | 99/4000 [01:47<1:10:18,  1.08s/it, lr: 1.0e-04 loss: 7.171e-01]
my_first_lora_v8:   2%|2         | 99/4000 [01:47<1:10:18,  1.08s/it, lr: 1.0e-04 loss: 7.171e-01]
my_first_lora_v8:   2%|2         | 100/4000 [01:47<1:10:06,  1.08s/it, lr: 1.0e-04 loss: 3.720e-01]
my_first_lora_v8:   2%|2         | 100/4000 [01:47<1:10:06,  1.08s/it, lr: 1.0e-04 loss: 3.720e-01]
my_first_lora_v8:   3%|2         | 101/4000 [01:49<1:10:23,  1.08s/it, lr: 1.0e-04 loss: 6.633e-01]
my_first_lora_v8:   3%|2         | 101/4000 [01:49<1:10:23,  1.08s/it, lr: 1.0e-04 loss: 6.633e-01]
my_first_lora_v8:   3%|2         | 102/4000 [01:50<1:10:39,  1.09s/it, lr: 1.0e-04 loss: 8.288e-01]
my_first_lora_v8:   3%|2         | 102/4000 [01:50<1:10:39,  1.09s/it, lr: 1.0e-04 loss: 8.288e-01]
my_first_lora_v8:   3%|2         | 103/4000 [01:52<1:10:53,  1.09s/it, lr: 1.0e-04 loss: 7.203e-01]
my_first_lora_v8:   3%|2         | 103/4000 [01:52<1:10:53,  1.09s/it, lr: 1.0e-04 loss: 7.203e-01]
my_first_lora_v8:   3%|2         | 104/4000 [01:53<1:10:41,  1.09s/it, lr: 1.0e-04 loss: 4.913e-01]
my_first_lora_v8:   3%|2         | 104/4000 [01:53<1:10:41,  1.09s/it, lr: 1.0e-04 loss: 4.913e-01]
my_first_lora_v8:   3%|2         | 105/4000 [01:54<1:10:30,  1.09s/it, lr: 1.0e-04 loss: 1.430e-01]
my_first_lora_v8:   3%|2         | 105/4000 [01:54<1:10:30,  1.09s/it, lr: 1.0e-04 loss: 1.430e-01]
my_first_lora_v8:   3%|2         | 106/4000 [01:55<1:10:58,  1.09s/it, lr: 1.0e-04 loss: 6.835e-01]
my_first_lora_v8:   3%|2         | 106/4000 [01:55<1:10:58,  1.09s/it, lr: 1.0e-04 loss: 6.835e-01]
my_first_lora_v8:   3%|2         | 107/4000 [01:57<1:11:18,  1.10s/it, lr: 1.0e-04 loss: 2.272e-01]
my_first_lora_v8:   3%|2         | 107/4000 [01:57<1:11:18,  1.10s/it, lr: 1.0e-04 loss: 2.272e-01]
my_first_lora_v8:   3%|2         | 108/4000 [01:58<1:11:08,  1.10s/it, lr: 1.0e-04 loss: 6.324e-01]
my_first_lora_v8:   3%|2         | 108/4000 [01:58<1:11:08,  1.10s/it, lr: 1.0e-04 loss: 6.324e-01]
my_first_lora_v8:   3%|2         | 109/4000 [01:59<1:10:55,  1.09s/it, lr: 1.0e-04 loss: 1.706e-01]
my_first_lora_v8:   3%|2         | 109/4000 [01:59<1:10:55,  1.09s/it, lr: 1.0e-04 loss: 1.706e-01]
my_first_lora_v8:   3%|2         | 110/4000 [02:00<1:10:44,  1.09s/it, lr: 1.0e-04 loss: 2.232e-01]
my_first_lora_v8:   3%|2         | 110/4000 [02:00<1:10:44,  1.09s/it, lr: 1.0e-04 loss: 2.232e-01]
my_first_lora_v8:   3%|2         | 111/4000 [02:00<1:10:32,  1.09s/it, lr: 1.0e-04 loss: 3.191e-01]
my_first_lora_v8:   3%|2         | 111/4000 [02:00<1:10:32,  1.09s/it, lr: 1.0e-04 loss: 3.191e-01]
my_first_lora_v8:   3%|2         | 112/4000 [02:02<1:10:46,  1.09s/it, lr: 1.0e-04 loss: 4.004e-01]
my_first_lora_v8:   3%|2         | 112/4000 [02:02<1:10:46,  1.09s/it, lr: 1.0e-04 loss: 4.004e-01]
my_first_lora_v8:   3%|2         | 113/4000 [02:03<1:10:33,  1.09s/it, lr: 1.0e-04 loss: 6.469e-01]
my_first_lora_v8:   3%|2         | 113/4000 [02:03<1:10:33,  1.09s/it, lr: 1.0e-04 loss: 6.469e-01]
my_first_lora_v8:   3%|2         | 114/4000 [02:03<1:10:21,  1.09s/it, lr: 1.0e-04 loss: 6.814e-01]
my_first_lora_v8:   3%|2         | 114/4000 [02:03<1:10:21,  1.09s/it, lr: 1.0e-04 loss: 6.814e-01]
my_first_lora_v8:   3%|2         | 115/4000 [02:04<1:10:10,  1.08s/it, lr: 1.0e-04 loss: 3.121e-01]
my_first_lora_v8:   3%|2         | 115/4000 [02:04<1:10:10,  1.08s/it, lr: 1.0e-04 loss: 3.121e-01]
my_first_lora_v8:   3%|2         | 116/4000 [02:06<1:10:23,  1.09s/it, lr: 1.0e-04 loss: 3.142e-01]
my_first_lora_v8:   3%|2         | 116/4000 [02:06<1:10:23,  1.09s/it, lr: 1.0e-04 loss: 3.142e-01]
my_first_lora_v8:   3%|2         | 117/4000 [02:06<1:10:13,  1.09s/it, lr: 1.0e-04 loss: 5.435e-01]
my_first_lora_v8:   3%|2         | 117/4000 [02:06<1:10:13,  1.09s/it, lr: 1.0e-04 loss: 5.435e-01]
my_first_lora_v8:   3%|2         | 118/4000 [02:08<1:10:27,  1.09s/it, lr: 1.0e-04 loss: 5.710e-01]
my_first_lora_v8:   3%|2         | 118/4000 [02:08<1:10:27,  1.09s/it, lr: 1.0e-04 loss: 5.710e-01]
my_first_lora_v8:   3%|2         | 119/4000 [02:09<1:10:35,  1.09s/it, lr: 1.0e-04 loss: 7.728e-01]
my_first_lora_v8:   3%|2         | 119/4000 [02:09<1:10:35,  1.09s/it, lr: 1.0e-04 loss: 7.728e-01]
my_first_lora_v8:   3%|3         | 120/4000 [02:11<1:10:47,  1.09s/it, lr: 1.0e-04 loss: 2.985e-02]
my_first_lora_v8:   3%|3         | 120/4000 [02:11<1:10:47,  1.09s/it, lr: 1.0e-04 loss: 2.985e-02]
my_first_lora_v8:   3%|3         | 121/4000 [02:12<1:10:36,  1.09s/it, lr: 1.0e-04 loss: 8.489e-02]
my_first_lora_v8:   3%|3         | 121/4000 [02:12<1:10:36,  1.09s/it, lr: 1.0e-04 loss: 8.489e-02]
my_first_lora_v8:   3%|3         | 122/4000 [02:12<1:10:26,  1.09s/it, lr: 1.0e-04 loss: 1.323e-01]
my_first_lora_v8:   3%|3         | 122/4000 [02:12<1:10:26,  1.09s/it, lr: 1.0e-04 loss: 1.323e-01]
my_first_lora_v8:   3%|3         | 123/4000 [02:13<1:10:16,  1.09s/it, lr: 1.0e-04 loss: 7.238e-01]
my_first_lora_v8:   3%|3         | 123/4000 [02:13<1:10:16,  1.09s/it, lr: 1.0e-04 loss: 7.238e-01]
my_first_lora_v8:   3%|3         | 124/4000 [02:14<1:10:05,  1.09s/it, lr: 1.0e-04 loss: 1.588e-01]
my_first_lora_v8:   3%|3         | 124/4000 [02:14<1:10:05,  1.09s/it, lr: 1.0e-04 loss: 1.588e-01]
my_first_lora_v8:   3%|3         | 125/4000 [02:16<1:10:17,  1.09s/it, lr: 1.0e-04 loss: 2.693e-01]
my_first_lora_v8:   3%|3         | 125/4000 [02:16<1:10:17,  1.09s/it, lr: 1.0e-04 loss: 2.693e-01]
my_first_lora_v8:   3%|3         | 126/4000 [02:16<1:10:08,  1.09s/it, lr: 1.0e-04 loss: 6.026e-01]
my_first_lora_v8:   3%|3         | 126/4000 [02:16<1:10:08,  1.09s/it, lr: 1.0e-04 loss: 6.026e-01]
my_first_lora_v8:   3%|3         | 127/4000 [02:17<1:09:58,  1.08s/it, lr: 1.0e-04 loss: 6.237e-01]
my_first_lora_v8:   3%|3         | 127/4000 [02:17<1:09:58,  1.08s/it, lr: 1.0e-04 loss: 6.237e-01]
my_first_lora_v8:   3%|3         | 128/4000 [02:19<1:10:10,  1.09s/it, lr: 1.0e-04 loss: 7.205e-01]
my_first_lora_v8:   3%|3         | 128/4000 [02:19<1:10:10,  1.09s/it, lr: 1.0e-04 loss: 7.205e-01]
my_first_lora_v8:   3%|3         | 129/4000 [02:20<1:10:22,  1.09s/it, lr: 1.0e-04 loss: 1.048e-01]
my_first_lora_v8:   3%|3         | 129/4000 [02:20<1:10:22,  1.09s/it, lr: 1.0e-04 loss: 1.048e-01]
my_first_lora_v8:   3%|3         | 130/4000 [02:21<1:10:13,  1.09s/it, lr: 1.0e-04 loss: 6.800e-01]
my_first_lora_v8:   3%|3         | 130/4000 [02:21<1:10:13,  1.09s/it, lr: 1.0e-04 loss: 6.800e-01]
my_first_lora_v8:   3%|3         | 131/4000 [02:22<1:10:08,  1.09s/it, lr: 1.0e-04 loss: 6.458e-01]
my_first_lora_v8:   3%|3         | 131/4000 [02:22<1:10:08,  1.09s/it, lr: 1.0e-04 loss: 6.458e-01]
my_first_lora_v8:   3%|3         | 132/4000 [02:23<1:09:59,  1.09s/it, lr: 1.0e-04 loss: 4.421e-01]
my_first_lora_v8:   3%|3         | 132/4000 [02:23<1:09:59,  1.09s/it, lr: 1.0e-04 loss: 4.421e-01]
my_first_lora_v8:   3%|3         | 133/4000 [02:24<1:10:11,  1.09s/it, lr: 1.0e-04 loss: 6.822e-01]
my_first_lora_v8:   3%|3         | 133/4000 [02:24<1:10:11,  1.09s/it, lr: 1.0e-04 loss: 6.822e-01]
my_first_lora_v8:   3%|3         | 134/4000 [02:26<1:10:12,  1.09s/it, lr: 1.0e-04 loss: 2.414e-01]
my_first_lora_v8:   3%|3         | 134/4000 [02:26<1:10:12,  1.09s/it, lr: 1.0e-04 loss: 2.414e-01]
my_first_lora_v8:   3%|3         | 135/4000 [02:26<1:10:03,  1.09s/it, lr: 1.0e-04 loss: 7.426e-01]
my_first_lora_v8:   3%|3         | 135/4000 [02:26<1:10:03,  1.09s/it, lr: 1.0e-04 loss: 7.426e-01]
my_first_lora_v8:   3%|3         | 136/4000 [02:28<1:10:14,  1.09s/it, lr: 1.0e-04 loss: 2.861e-01]
my_first_lora_v8:   3%|3         | 136/4000 [02:28<1:10:14,  1.09s/it, lr: 1.0e-04 loss: 2.861e-01]
my_first_lora_v8:   3%|3         | 137/4000 [02:29<1:10:25,  1.09s/it, lr: 1.0e-04 loss: 2.474e-01]
my_first_lora_v8:   3%|3         | 137/4000 [02:29<1:10:25,  1.09s/it, lr: 1.0e-04 loss: 2.474e-01]
my_first_lora_v8:   3%|3         | 138/4000 [02:30<1:10:17,  1.09s/it, lr: 1.0e-04 loss: 6.962e-01]
my_first_lora_v8:   3%|3         | 138/4000 [02:30<1:10:17,  1.09s/it, lr: 1.0e-04 loss: 6.962e-01]
my_first_lora_v8:   3%|3         | 139/4000 [02:31<1:10:08,  1.09s/it, lr: 1.0e-04 loss: 3.482e-01]
my_first_lora_v8:   3%|3         | 139/4000 [02:31<1:10:08,  1.09s/it, lr: 1.0e-04 loss: 3.482e-01]
my_first_lora_v8:   4%|3         | 140/4000 [02:32<1:10:00,  1.09s/it, lr: 1.0e-04 loss: 7.002e-01]
my_first_lora_v8:   4%|3         | 140/4000 [02:32<1:10:00,  1.09s/it, lr: 1.0e-04 loss: 7.002e-01]
my_first_lora_v8:   4%|3         | 141/4000 [02:33<1:09:52,  1.09s/it, lr: 1.0e-04 loss: 2.470e-01]
my_first_lora_v8:   4%|3         | 141/4000 [02:33<1:09:52,  1.09s/it, lr: 1.0e-04 loss: 2.470e-01]
my_first_lora_v8:   4%|3         | 142/4000 [02:34<1:10:02,  1.09s/it, lr: 1.0e-04 loss: 2.359e-01]
my_first_lora_v8:   4%|3         | 142/4000 [02:34<1:10:02,  1.09s/it, lr: 1.0e-04 loss: 2.359e-01]
my_first_lora_v8:   4%|3         | 143/4000 [02:35<1:09:59,  1.09s/it, lr: 1.0e-04 loss: 2.690e-01]
my_first_lora_v8:   4%|3         | 143/4000 [02:35<1:09:59,  1.09s/it, lr: 1.0e-04 loss: 2.690e-01]
my_first_lora_v8:   4%|3         | 144/4000 [02:36<1:09:49,  1.09s/it, lr: 1.0e-04 loss: 7.200e-01]
my_first_lora_v8:   4%|3         | 144/4000 [02:36<1:09:49,  1.09s/it, lr: 1.0e-04 loss: 7.200e-01]
my_first_lora_v8:   4%|3         | 145/4000 [02:37<1:09:40,  1.08s/it, lr: 1.0e-04 loss: 6.775e-01]
my_first_lora_v8:   4%|3         | 145/4000 [02:37<1:09:40,  1.08s/it, lr: 1.0e-04 loss: 6.775e-01]
my_first_lora_v8:   4%|3         | 146/4000 [02:38<1:09:32,  1.08s/it, lr: 1.0e-04 loss: 8.453e-01]
my_first_lora_v8:   4%|3         | 146/4000 [02:38<1:09:32,  1.08s/it, lr: 1.0e-04 loss: 8.453e-01]
my_first_lora_v8:   4%|3         | 147/4000 [02:39<1:09:34,  1.08s/it, lr: 1.0e-04 loss: 7.564e-01]
my_first_lora_v8:   4%|3         | 147/4000 [02:39<1:09:34,  1.08s/it, lr: 1.0e-04 loss: 7.564e-01]
my_first_lora_v8:   4%|3         | 148/4000 [02:40<1:09:26,  1.08s/it, lr: 1.0e-04 loss: 6.264e-01]
my_first_lora_v8:   4%|3         | 148/4000 [02:40<1:09:26,  1.08s/it, lr: 1.0e-04 loss: 6.264e-01]
my_first_lora_v8:   4%|3         | 149/4000 [02:41<1:09:36,  1.08s/it, lr: 1.0e-04 loss: 7.362e-01]
my_first_lora_v8:   4%|3         | 149/4000 [02:41<1:09:36,  1.08s/it, lr: 1.0e-04 loss: 7.362e-01]
my_first_lora_v8:   4%|3         | 150/4000 [02:42<1:09:28,  1.08s/it, lr: 1.0e-04 loss: 3.790e-01]
my_first_lora_v8:   4%|3         | 150/4000 [02:42<1:09:28,  1.08s/it, lr: 1.0e-04 loss: 3.790e-01]
my_first_lora_v8:   4%|3         | 151/4000 [02:43<1:09:38,  1.09s/it, lr: 1.0e-04 loss: 6.464e-01]
my_first_lora_v8:   4%|3         | 151/4000 [02:43<1:09:38,  1.09s/it, lr: 1.0e-04 loss: 6.464e-01]
my_first_lora_v8:   4%|3         | 152/4000 [02:44<1:09:29,  1.08s/it, lr: 1.0e-04 loss: 1.521e-01]
my_first_lora_v8:   4%|3         | 152/4000 [02:44<1:09:29,  1.08s/it, lr: 1.0e-04 loss: 1.521e-01]
my_first_lora_v8:   4%|3         | 153/4000 [02:46<1:09:39,  1.09s/it, lr: 1.0e-04 loss: 4.096e-01]
my_first_lora_v8:   4%|3         | 153/4000 [02:46<1:09:39,  1.09s/it, lr: 1.0e-04 loss: 4.096e-01]
my_first_lora_v8:   4%|3         | 154/4000 [02:47<1:09:49,  1.09s/it, lr: 1.0e-04 loss: 3.197e-01]
my_first_lora_v8:   4%|3         | 154/4000 [02:47<1:09:49,  1.09s/it, lr: 1.0e-04 loss: 3.197e-01]
my_first_lora_v8:   4%|3         | 155/4000 [02:48<1:09:45,  1.09s/it, lr: 1.0e-04 loss: 7.282e-01]
my_first_lora_v8:   4%|3         | 155/4000 [02:48<1:09:45,  1.09s/it, lr: 1.0e-04 loss: 7.282e-01]
my_first_lora_v8:   4%|3         | 156/4000 [02:50<1:09:54,  1.09s/it, lr: 1.0e-04 loss: 1.614e-01]
my_first_lora_v8:   4%|3         | 156/4000 [02:50<1:09:54,  1.09s/it, lr: 1.0e-04 loss: 1.614e-01]
my_first_lora_v8:   4%|3         | 157/4000 [02:51<1:09:46,  1.09s/it, lr: 1.0e-04 loss: 7.489e-01]
my_first_lora_v8:   4%|3         | 157/4000 [02:51<1:09:46,  1.09s/it, lr: 1.0e-04 loss: 7.489e-01]
my_first_lora_v8:   4%|3         | 158/4000 [02:51<1:09:37,  1.09s/it, lr: 1.0e-04 loss: 1.863e-01]
my_first_lora_v8:   4%|3         | 158/4000 [02:51<1:09:37,  1.09s/it, lr: 1.0e-04 loss: 1.863e-01]
my_first_lora_v8:   4%|3         | 159/4000 [02:52<1:09:30,  1.09s/it, lr: 1.0e-04 loss: 5.913e-01]
my_first_lora_v8:   4%|3         | 159/4000 [02:52<1:09:30,  1.09s/it, lr: 1.0e-04 loss: 5.913e-01]
my_first_lora_v8:   4%|4         | 160/4000 [02:54<1:09:39,  1.09s/it, lr: 1.0e-04 loss: 6.771e-01]
my_first_lora_v8:   4%|4         | 160/4000 [02:54<1:09:39,  1.09s/it, lr: 1.0e-04 loss: 6.771e-01]
my_first_lora_v8:   4%|4         | 161/4000 [02:55<1:09:41,  1.09s/it, lr: 1.0e-04 loss: 8.306e-02]
my_first_lora_v8:   4%|4         | 161/4000 [02:55<1:09:41,  1.09s/it, lr: 1.0e-04 loss: 8.306e-02]
my_first_lora_v8:   4%|4         | 162/4000 [02:56<1:09:50,  1.09s/it, lr: 1.0e-04 loss: 1.452e-01]
my_first_lora_v8:   4%|4         | 162/4000 [02:56<1:09:50,  1.09s/it, lr: 1.0e-04 loss: 1.452e-01]
my_first_lora_v8:   4%|4         | 163/4000 [02:58<1:09:59,  1.09s/it, lr: 1.0e-04 loss: 1.431e-01]
my_first_lora_v8:   4%|4         | 163/4000 [02:58<1:09:59,  1.09s/it, lr: 1.0e-04 loss: 1.431e-01]
my_first_lora_v8:   4%|4         | 164/4000 [02:59<1:09:51,  1.09s/it, lr: 1.0e-04 loss: 3.712e-01]
my_first_lora_v8:   4%|4         | 164/4000 [02:59<1:09:51,  1.09s/it, lr: 1.0e-04 loss: 3.712e-01]
my_first_lora_v8:   4%|4         | 165/4000 [02:59<1:09:43,  1.09s/it, lr: 1.0e-04 loss: 3.042e-01]
my_first_lora_v8:   4%|4         | 165/4000 [02:59<1:09:43,  1.09s/it, lr: 1.0e-04 loss: 3.042e-01]
my_first_lora_v8:   4%|4         | 166/4000 [03:00<1:09:35,  1.09s/it, lr: 1.0e-04 loss: 1.195e-01]
my_first_lora_v8:   4%|4         | 166/4000 [03:00<1:09:35,  1.09s/it, lr: 1.0e-04 loss: 1.195e-01]
my_first_lora_v8:   4%|4         | 167/4000 [03:02<1:09:47,  1.09s/it, lr: 1.0e-04 loss: 5.568e-01]
my_first_lora_v8:   4%|4         | 167/4000 [03:02<1:09:47,  1.09s/it, lr: 1.0e-04 loss: 5.568e-01]
my_first_lora_v8:   4%|4         | 168/4000 [03:03<1:09:39,  1.09s/it, lr: 1.0e-04 loss: 1.652e-01]
my_first_lora_v8:   4%|4         | 168/4000 [03:03<1:09:39,  1.09s/it, lr: 1.0e-04 loss: 1.652e-01]
my_first_lora_v8:   4%|4         | 169/4000 [03:04<1:09:47,  1.09s/it, lr: 1.0e-04 loss: 4.299e-01]
my_first_lora_v8:   4%|4         | 169/4000 [03:04<1:09:47,  1.09s/it, lr: 1.0e-04 loss: 4.299e-01]
my_first_lora_v8:   4%|4         | 170/4000 [03:06<1:09:55,  1.10s/it, lr: 1.0e-04 loss: 7.448e-01]
my_first_lora_v8:   4%|4         | 170/4000 [03:06<1:09:55,  1.10s/it, lr: 1.0e-04 loss: 7.448e-01]
my_first_lora_v8:   4%|4         | 171/4000 [03:06<1:09:46,  1.09s/it, lr: 1.0e-04 loss: 5.932e-01]
my_first_lora_v8:   4%|4         | 171/4000 [03:06<1:09:46,  1.09s/it, lr: 1.0e-04 loss: 5.932e-01]
my_first_lora_v8:   4%|4         | 172/4000 [03:07<1:09:39,  1.09s/it, lr: 1.0e-04 loss: 2.371e-01]
my_first_lora_v8:   4%|4         | 172/4000 [03:07<1:09:39,  1.09s/it, lr: 1.0e-04 loss: 2.371e-01]
my_first_lora_v8:   4%|4         | 173/4000 [03:08<1:09:31,  1.09s/it, lr: 1.0e-04 loss: 3.533e-01]
my_first_lora_v8:   4%|4         | 173/4000 [03:08<1:09:31,  1.09s/it, lr: 1.0e-04 loss: 3.533e-01]
my_first_lora_v8:   4%|4         | 174/4000 [03:10<1:09:45,  1.09s/it, lr: 1.0e-04 loss: 6.864e-01]
my_first_lora_v8:   4%|4         | 174/4000 [03:10<1:09:45,  1.09s/it, lr: 1.0e-04 loss: 6.864e-01]
my_first_lora_v8:   4%|4         | 175/4000 [03:11<1:09:38,  1.09s/it, lr: 1.0e-04 loss: 6.908e-01]
my_first_lora_v8:   4%|4         | 175/4000 [03:11<1:09:38,  1.09s/it, lr: 1.0e-04 loss: 6.908e-01]
my_first_lora_v8:   4%|4         | 176/4000 [03:11<1:09:30,  1.09s/it, lr: 1.0e-04 loss: 7.036e-01]
my_first_lora_v8:   4%|4         | 176/4000 [03:11<1:09:30,  1.09s/it, lr: 1.0e-04 loss: 7.036e-01]
my_first_lora_v8:   4%|4         | 177/4000 [03:12<1:09:23,  1.09s/it, lr: 1.0e-04 loss: 6.378e-01]
my_first_lora_v8:   4%|4         | 177/4000 [03:12<1:09:23,  1.09s/it, lr: 1.0e-04 loss: 6.378e-01]
my_first_lora_v8:   4%|4         | 178/4000 [03:13<1:09:15,  1.09s/it, lr: 1.0e-04 loss: 6.186e-01]
my_first_lora_v8:   4%|4         | 178/4000 [03:13<1:09:15,  1.09s/it, lr: 1.0e-04 loss: 6.186e-01]
my_first_lora_v8:   4%|4         | 179/4000 [03:14<1:09:11,  1.09s/it, lr: 1.0e-04 loss: 7.082e-01]
my_first_lora_v8:   4%|4         | 179/4000 [03:14<1:09:11,  1.09s/it, lr: 1.0e-04 loss: 7.082e-01]
my_first_lora_v8:   4%|4         | 180/4000 [03:15<1:09:05,  1.09s/it, lr: 1.0e-04 loss: 3.507e-01]
my_first_lora_v8:   4%|4         | 180/4000 [03:15<1:09:05,  1.09s/it, lr: 1.0e-04 loss: 3.507e-01]
my_first_lora_v8:   5%|4         | 181/4000 [03:16<1:08:58,  1.08s/it, lr: 1.0e-04 loss: 2.652e-01]
my_first_lora_v8:   5%|4         | 181/4000 [03:16<1:08:58,  1.08s/it, lr: 1.0e-04 loss: 2.652e-01]
my_first_lora_v8:   5%|4         | 182/4000 [03:16<1:08:51,  1.08s/it, lr: 1.0e-04 loss: 1.599e-01]
my_first_lora_v8:   5%|4         | 182/4000 [03:16<1:08:51,  1.08s/it, lr: 1.0e-04 loss: 1.599e-01]
my_first_lora_v8:   5%|4         | 183/4000 [03:18<1:08:58,  1.08s/it, lr: 1.0e-04 loss: 7.213e-01]
my_first_lora_v8:   5%|4         | 183/4000 [03:18<1:08:58,  1.08s/it, lr: 1.0e-04 loss: 7.213e-01]
my_first_lora_v8:   5%|4         | 184/4000 [03:19<1:09:05,  1.09s/it, lr: 1.0e-04 loss: 6.475e-01]
my_first_lora_v8:   5%|4         | 184/4000 [03:19<1:09:05,  1.09s/it, lr: 1.0e-04 loss: 6.475e-01]
my_first_lora_v8:   5%|4         | 185/4000 [03:20<1:08:58,  1.08s/it, lr: 1.0e-04 loss: 4.320e-01]
my_first_lora_v8:   5%|4         | 185/4000 [03:20<1:08:58,  1.08s/it, lr: 1.0e-04 loss: 4.320e-01]
my_first_lora_v8:   5%|4         | 186/4000 [03:21<1:08:52,  1.08s/it, lr: 1.0e-04 loss: 2.375e-01]
my_first_lora_v8:   5%|4         | 186/4000 [03:21<1:08:52,  1.08s/it, lr: 1.0e-04 loss: 2.375e-01]
my_first_lora_v8:   5%|4         | 187/4000 [03:22<1:08:45,  1.08s/it, lr: 1.0e-04 loss: 7.143e-01]
my_first_lora_v8:   5%|4         | 187/4000 [03:22<1:08:45,  1.08s/it, lr: 1.0e-04 loss: 7.143e-01]
my_first_lora_v8:   5%|4         | 188/4000 [03:24<1:08:59,  1.09s/it, lr: 1.0e-04 loss: 2.655e-01]
my_first_lora_v8:   5%|4         | 188/4000 [03:24<1:08:59,  1.09s/it, lr: 1.0e-04 loss: 2.655e-01]
my_first_lora_v8:   5%|4         | 189/4000 [03:24<1:08:52,  1.08s/it, lr: 1.0e-04 loss: 2.671e-01]
my_first_lora_v8:   5%|4         | 189/4000 [03:24<1:08:52,  1.08s/it, lr: 1.0e-04 loss: 2.671e-01]
my_first_lora_v8:   5%|4         | 190/4000 [03:26<1:09:00,  1.09s/it, lr: 1.0e-04 loss: 6.535e-01]
my_first_lora_v8:   5%|4         | 190/4000 [03:26<1:09:00,  1.09s/it, lr: 1.0e-04 loss: 6.535e-01]
my_first_lora_v8:   5%|4         | 191/4000 [03:28<1:09:10,  1.09s/it, lr: 1.0e-04 loss: 1.597e-01]
my_first_lora_v8:   5%|4         | 191/4000 [03:28<1:09:10,  1.09s/it, lr: 1.0e-04 loss: 1.597e-01]
my_first_lora_v8:   5%|4         | 192/4000 [03:29<1:09:05,  1.09s/it, lr: 1.0e-04 loss: 7.107e-01]
my_first_lora_v8:   5%|4         | 192/4000 [03:29<1:09:05,  1.09s/it, lr: 1.0e-04 loss: 7.107e-01]
my_first_lora_v8:   5%|4         | 193/4000 [03:30<1:09:12,  1.09s/it, lr: 1.0e-04 loss: 2.934e-01]
my_first_lora_v8:   5%|4         | 193/4000 [03:30<1:09:12,  1.09s/it, lr: 1.0e-04 loss: 2.934e-01]
my_first_lora_v8:   5%|4         | 194/4000 [03:31<1:09:06,  1.09s/it, lr: 1.0e-04 loss: 1.278e-01]
my_first_lora_v8:   5%|4         | 194/4000 [03:31<1:09:06,  1.09s/it, lr: 1.0e-04 loss: 1.278e-01]
my_first_lora_v8:   5%|4         | 195/4000 [03:32<1:08:59,  1.09s/it, lr: 1.0e-04 loss: 8.088e-01]
my_first_lora_v8:   5%|4         | 195/4000 [03:32<1:08:59,  1.09s/it, lr: 1.0e-04 loss: 8.088e-01]
my_first_lora_v8:   5%|4         | 196/4000 [03:33<1:09:06,  1.09s/it, lr: 1.0e-04 loss: 5.411e-01]
my_first_lora_v8:   5%|4         | 196/4000 [03:33<1:09:06,  1.09s/it, lr: 1.0e-04 loss: 5.411e-01]
my_first_lora_v8:   5%|4         | 197/4000 [03:34<1:08:59,  1.09s/it, lr: 1.0e-04 loss: 1.063e-01]
my_first_lora_v8:   5%|4         | 197/4000 [03:34<1:08:59,  1.09s/it, lr: 1.0e-04 loss: 1.063e-01]
my_first_lora_v8:   5%|4         | 198/4000 [03:35<1:08:53,  1.09s/it, lr: 1.0e-04 loss: 5.162e-01]
my_first_lora_v8:   5%|4         | 198/4000 [03:35<1:08:53,  1.09s/it, lr: 1.0e-04 loss: 5.162e-01]
my_first_lora_v8:   5%|4         | 199/4000 [03:36<1:09:00,  1.09s/it, lr: 1.0e-04 loss: 6.718e-01]
my_first_lora_v8:   5%|4         | 199/4000 [03:36<1:09:00,  1.09s/it, lr: 1.0e-04 loss: 6.718e-01]
my_first_lora_v8:   5%|5         | 200/4000 [03:37<1:08:53,  1.09s/it, lr: 1.0e-04 loss: 6.649e-01]
my_first_lora_v8:   5%|5         | 200/4000 [03:37<1:08:53,  1.09s/it, lr: 1.0e-04 loss: 6.649e-01]
my_first_lora_v8:   5%|5         | 201/4000 [03:38<1:08:47,  1.09s/it, lr: 1.0e-04 loss: 7.657e-01]
my_first_lora_v8:   5%|5         | 201/4000 [03:38<1:08:47,  1.09s/it, lr: 1.0e-04 loss: 7.657e-01]
my_first_lora_v8:   5%|5         | 202/4000 [03:39<1:08:48,  1.09s/it, lr: 1.0e-04 loss: 5.083e-01]
my_first_lora_v8:   5%|5         | 202/4000 [03:39<1:08:48,  1.09s/it, lr: 1.0e-04 loss: 5.083e-01]
my_first_lora_v8:   5%|5         | 203/4000 [03:40<1:08:44,  1.09s/it, lr: 1.0e-04 loss: 2.306e-01]
my_first_lora_v8:   5%|5         | 203/4000 [03:40<1:08:44,  1.09s/it, lr: 1.0e-04 loss: 2.306e-01]
my_first_lora_v8:   5%|5         | 204/4000 [03:42<1:08:51,  1.09s/it, lr: 1.0e-04 loss: 6.810e-01]
my_first_lora_v8:   5%|5         | 204/4000 [03:42<1:08:51,  1.09s/it, lr: 1.0e-04 loss: 6.810e-01]
my_first_lora_v8:   5%|5         | 205/4000 [03:42<1:08:45,  1.09s/it, lr: 1.0e-04 loss: 6.845e-01]
my_first_lora_v8:   5%|5         | 205/4000 [03:42<1:08:45,  1.09s/it, lr: 1.0e-04 loss: 6.845e-01]
my_first_lora_v8:   5%|5         | 206/4000 [03:43<1:08:39,  1.09s/it, lr: 1.0e-04 loss: 1.408e-01]
my_first_lora_v8:   5%|5         | 206/4000 [03:43<1:08:39,  1.09s/it, lr: 1.0e-04 loss: 1.408e-01]
my_first_lora_v8:   5%|5         | 207/4000 [03:44<1:08:32,  1.08s/it, lr: 1.0e-04 loss: 6.814e-01]
my_first_lora_v8:   5%|5         | 207/4000 [03:44<1:08:32,  1.08s/it, lr: 1.0e-04 loss: 6.814e-01]
my_first_lora_v8:   5%|5         | 208/4000 [03:45<1:08:26,  1.08s/it, lr: 1.0e-04 loss: 6.371e-01]
my_first_lora_v8:   5%|5         | 208/4000 [03:45<1:08:26,  1.08s/it, lr: 1.0e-04 loss: 6.371e-01]
my_first_lora_v8:   5%|5         | 209/4000 [03:46<1:08:32,  1.08s/it, lr: 1.0e-04 loss: 2.555e-01]
my_first_lora_v8:   5%|5         | 209/4000 [03:46<1:08:32,  1.08s/it, lr: 1.0e-04 loss: 2.555e-01]
my_first_lora_v8:   5%|5         | 210/4000 [03:48<1:08:38,  1.09s/it, lr: 1.0e-04 loss: 8.141e-01]
my_first_lora_v8:   5%|5         | 210/4000 [03:48<1:08:38,  1.09s/it, lr: 1.0e-04 loss: 8.141e-01]
my_first_lora_v8:   5%|5         | 211/4000 [03:49<1:08:32,  1.09s/it, lr: 1.0e-04 loss: 2.098e-01]
my_first_lora_v8:   5%|5         | 211/4000 [03:49<1:08:32,  1.09s/it, lr: 1.0e-04 loss: 2.098e-01]
my_first_lora_v8:   5%|5         | 212/4000 [03:50<1:08:38,  1.09s/it, lr: 1.0e-04 loss: 6.997e-01]
my_first_lora_v8:   5%|5         | 212/4000 [03:50<1:08:38,  1.09s/it, lr: 1.0e-04 loss: 6.997e-01]
my_first_lora_v8:   5%|5         | 213/4000 [03:51<1:08:32,  1.09s/it, lr: 1.0e-04 loss: 3.055e-01]
my_first_lora_v8:   5%|5         | 213/4000 [03:51<1:08:32,  1.09s/it, lr: 1.0e-04 loss: 3.055e-01]
my_first_lora_v8:   5%|5         | 214/4000 [03:52<1:08:26,  1.08s/it, lr: 1.0e-04 loss: 1.091e-01]
my_first_lora_v8:   5%|5         | 214/4000 [03:52<1:08:26,  1.08s/it, lr: 1.0e-04 loss: 1.091e-01]
my_first_lora_v8:   5%|5         | 215/4000 [03:54<1:08:40,  1.09s/it, lr: 1.0e-04 loss: 8.132e-01]
my_first_lora_v8:   5%|5         | 215/4000 [03:54<1:08:40,  1.09s/it, lr: 1.0e-04 loss: 8.132e-01]
my_first_lora_v8:   5%|5         | 216/4000 [03:54<1:08:33,  1.09s/it, lr: 1.0e-04 loss: 5.008e-01]
my_first_lora_v8:   5%|5         | 216/4000 [03:54<1:08:33,  1.09s/it, lr: 1.0e-04 loss: 5.008e-01]
my_first_lora_v8:   5%|5         | 217/4000 [03:55<1:08:27,  1.09s/it, lr: 1.0e-04 loss: 5.262e-01]
my_first_lora_v8:   5%|5         | 217/4000 [03:55<1:08:27,  1.09s/it, lr: 1.0e-04 loss: 5.262e-01]
my_first_lora_v8:   5%|5         | 218/4000 [03:56<1:08:22,  1.08s/it, lr: 1.0e-04 loss: 6.811e-01]
my_first_lora_v8:   5%|5         | 218/4000 [03:56<1:08:22,  1.08s/it, lr: 1.0e-04 loss: 6.811e-01]
my_first_lora_v8:   5%|5         | 219/4000 [03:57<1:08:16,  1.08s/it, lr: 1.0e-04 loss: 6.432e-01]
my_first_lora_v8:   5%|5         | 219/4000 [03:57<1:08:16,  1.08s/it, lr: 1.0e-04 loss: 6.432e-01]
my_first_lora_v8:   6%|5         | 220/4000 [03:58<1:08:22,  1.09s/it, lr: 1.0e-04 loss: 1.342e-01]
my_first_lora_v8:   6%|5         | 220/4000 [03:58<1:08:22,  1.09s/it, lr: 1.0e-04 loss: 1.342e-01]
my_first_lora_v8:   6%|5         | 221/4000 [04:00<1:08:28,  1.09s/it, lr: 1.0e-04 loss: 4.768e-01]
my_first_lora_v8:   6%|5         | 221/4000 [04:00<1:08:28,  1.09s/it, lr: 1.0e-04 loss: 4.768e-01]
my_first_lora_v8:   6%|5         | 222/4000 [04:01<1:08:22,  1.09s/it, lr: 1.0e-04 loss: 6.793e-01]
my_first_lora_v8:   6%|5         | 222/4000 [04:01<1:08:22,  1.09s/it, lr: 1.0e-04 loss: 6.793e-01]
my_first_lora_v8:   6%|5         | 223/4000 [04:01<1:08:15,  1.08s/it, lr: 1.0e-04 loss: 5.641e-01]
my_first_lora_v8:   6%|5         | 223/4000 [04:01<1:08:15,  1.08s/it, lr: 1.0e-04 loss: 5.641e-01]
my_first_lora_v8:   6%|5         | 224/4000 [04:02<1:08:09,  1.08s/it, lr: 1.0e-04 loss: 5.284e-01]
my_first_lora_v8:   6%|5         | 224/4000 [04:02<1:08:09,  1.08s/it, lr: 1.0e-04 loss: 5.284e-01]
my_first_lora_v8:   6%|5         | 225/4000 [04:03<1:08:03,  1.08s/it, lr: 1.0e-04 loss: 2.571e-01]
my_first_lora_v8:   6%|5         | 225/4000 [04:03<1:08:03,  1.08s/it, lr: 1.0e-04 loss: 2.571e-01]
my_first_lora_v8:   6%|5         | 226/4000 [04:04<1:08:09,  1.08s/it, lr: 1.0e-04 loss: 6.738e-01]
my_first_lora_v8:   6%|5         | 226/4000 [04:04<1:08:09,  1.08s/it, lr: 1.0e-04 loss: 6.738e-01]
my_first_lora_v8:   6%|5         | 227/4000 [04:05<1:08:07,  1.08s/it, lr: 1.0e-04 loss: 4.581e-01]
my_first_lora_v8:   6%|5         | 227/4000 [04:05<1:08:07,  1.08s/it, lr: 1.0e-04 loss: 4.581e-01]
my_first_lora_v8:   6%|5         | 228/4000 [04:07<1:08:08,  1.08s/it, lr: 1.0e-04 loss: 7.002e-01]
my_first_lora_v8:   6%|5         | 228/4000 [04:07<1:08:08,  1.08s/it, lr: 1.0e-04 loss: 7.002e-01]
my_first_lora_v8:   6%|5         | 229/4000 [04:08<1:08:04,  1.08s/it, lr: 1.0e-04 loss: 6.797e-01]
my_first_lora_v8:   6%|5         | 229/4000 [04:08<1:08:04,  1.08s/it, lr: 1.0e-04 loss: 6.797e-01]
my_first_lora_v8:   6%|5         | 230/4000 [04:09<1:08:10,  1.08s/it, lr: 1.0e-04 loss: 3.435e-01]
my_first_lora_v8:   6%|5         | 230/4000 [04:09<1:08:10,  1.08s/it, lr: 1.0e-04 loss: 3.435e-01]
my_first_lora_v8:   6%|5         | 231/4000 [04:11<1:08:15,  1.09s/it, lr: 1.0e-04 loss: 2.397e-01]
my_first_lora_v8:   6%|5         | 231/4000 [04:11<1:08:15,  1.09s/it, lr: 1.0e-04 loss: 2.397e-01]
my_first_lora_v8:   6%|5         | 232/4000 [04:11<1:08:10,  1.09s/it, lr: 1.0e-04 loss: 1.405e-01]
my_first_lora_v8:   6%|5         | 232/4000 [04:11<1:08:10,  1.09s/it, lr: 1.0e-04 loss: 1.405e-01]
my_first_lora_v8:   6%|5         | 233/4000 [04:12<1:08:04,  1.08s/it, lr: 1.0e-04 loss: 2.783e-01]
my_first_lora_v8:   6%|5         | 233/4000 [04:12<1:08:04,  1.08s/it, lr: 1.0e-04 loss: 2.783e-01]
my_first_lora_v8:   6%|5         | 234/4000 [04:14<1:08:10,  1.09s/it, lr: 1.0e-04 loss: 5.431e-01]
my_first_lora_v8:   6%|5         | 234/4000 [04:14<1:08:10,  1.09s/it, lr: 1.0e-04 loss: 5.431e-01]
my_first_lora_v8:   6%|5         | 235/4000 [04:15<1:08:15,  1.09s/it, lr: 1.0e-04 loss: 5.711e-01]
my_first_lora_v8:   6%|5         | 235/4000 [04:15<1:08:15,  1.09s/it, lr: 1.0e-04 loss: 5.711e-01]
my_first_lora_v8:   6%|5         | 236/4000 [04:16<1:08:10,  1.09s/it, lr: 1.0e-04 loss: 5.237e-01]
my_first_lora_v8:   6%|5         | 236/4000 [04:16<1:08:10,  1.09s/it, lr: 1.0e-04 loss: 5.237e-01]
my_first_lora_v8:   6%|5         | 237/4000 [04:17<1:08:04,  1.09s/it, lr: 1.0e-04 loss: 2.486e-01]
my_first_lora_v8:   6%|5         | 237/4000 [04:17<1:08:04,  1.09s/it, lr: 1.0e-04 loss: 2.486e-01]
my_first_lora_v8:   6%|5         | 238/4000 [04:18<1:07:59,  1.08s/it, lr: 1.0e-04 loss: 5.187e-01]
my_first_lora_v8:   6%|5         | 238/4000 [04:18<1:07:59,  1.08s/it, lr: 1.0e-04 loss: 5.187e-01]
my_first_lora_v8:   6%|5         | 239/4000 [04:19<1:07:57,  1.08s/it, lr: 1.0e-04 loss: 1.835e-01]
my_first_lora_v8:   6%|5         | 239/4000 [04:19<1:07:57,  1.08s/it, lr: 1.0e-04 loss: 1.835e-01]
my_first_lora_v8:   6%|6         | 240/4000 [04:20<1:08:02,  1.09s/it, lr: 1.0e-04 loss: 1.693e-01]
my_first_lora_v8:   6%|6         | 240/4000 [04:20<1:08:02,  1.09s/it, lr: 1.0e-04 loss: 1.693e-01]
my_first_lora_v8:   6%|6         | 241/4000 [04:22<1:08:07,  1.09s/it, lr: 1.0e-04 loss: 9.192e-02]
my_first_lora_v8:   6%|6         | 241/4000 [04:22<1:08:07,  1.09s/it, lr: 1.0e-04 loss: 9.192e-02]
my_first_lora_v8:   6%|6         | 242/4000 [04:23<1:08:08,  1.09s/it, lr: 1.0e-04 loss: 6.201e-01]
my_first_lora_v8:   6%|6         | 242/4000 [04:23<1:08:08,  1.09s/it, lr: 1.0e-04 loss: 6.201e-01]
my_first_lora_v8:   6%|6         | 243/4000 [04:24<1:08:03,  1.09s/it, lr: 1.0e-04 loss: 5.316e-01]
my_first_lora_v8:   6%|6         | 243/4000 [04:24<1:08:03,  1.09s/it, lr: 1.0e-04 loss: 5.316e-01]
my_first_lora_v8:   6%|6         | 244/4000 [04:25<1:08:08,  1.09s/it, lr: 1.0e-04 loss: 6.515e-01]
my_first_lora_v8:   6%|6         | 244/4000 [04:25<1:08:08,  1.09s/it, lr: 1.0e-04 loss: 6.515e-01]
my_first_lora_v8:   6%|6         | 245/4000 [04:26<1:08:03,  1.09s/it, lr: 1.0e-04 loss: 8.605e-02]
my_first_lora_v8:   6%|6         | 245/4000 [04:26<1:08:03,  1.09s/it, lr: 1.0e-04 loss: 8.605e-02]
my_first_lora_v8:   6%|6         | 246/4000 [04:27<1:07:57,  1.09s/it, lr: 1.0e-04 loss: 4.219e-01]
my_first_lora_v8:   6%|6         | 246/4000 [04:27<1:07:57,  1.09s/it, lr: 1.0e-04 loss: 4.219e-01]
my_first_lora_v8:   6%|6         | 247/4000 [04:28<1:07:52,  1.09s/it, lr: 1.0e-04 loss: 2.738e-01]
my_first_lora_v8:   6%|6         | 247/4000 [04:28<1:07:52,  1.09s/it, lr: 1.0e-04 loss: 2.738e-01]
my_first_lora_v8:   6%|6         | 248/4000 [04:28<1:07:47,  1.08s/it, lr: 1.0e-04 loss: 8.311e-01]
my_first_lora_v8:   6%|6         | 248/4000 [04:28<1:07:47,  1.08s/it, lr: 1.0e-04 loss: 8.311e-01]
my_first_lora_v8:   6%|6         | 249/4000 [04:30<1:07:52,  1.09s/it, lr: 1.0e-04 loss: 4.654e-01]
my_first_lora_v8:   6%|6         | 249/4000 [04:30<1:07:52,  1.09s/it, lr: 1.0e-04 loss: 4.654e-01]
Saving at step 250
Saved checkpoint to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v8/my_first_lora_v8_000000250.safetensors
Saved optimizer to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v8/optimizer.pt
Unloading assistant lora



Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]
Generating Images:   0%|          | 0/5 [00:00<?, ?it/s]


Generating Images:  20%|##        | 1/5 [00:08<00:34,  8.61s/it]
Generating Images:  20%|##        | 1/5 [00:08<00:34,  8.61s/it]


Generating Images:  40%|####      | 2/5 [00:16<00:24,  8.29s/it]
Generating Images:  40%|####      | 2/5 [00:16<00:24,  8.29s/it]


Generating Images:  60%|######    | 3/5 [00:24<00:16,  8.05s/it]
Generating Images:  60%|######    | 3/5 [00:24<00:16,  8.05s/it]