| 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": "oxantara1", |
| "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/topa", |
| "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, |
| 1024 |
| ], |
| "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": true, |
| "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": "hoto of a nude Indian woman 21y old standing in a bedroom, facing the camera, medium wide shot, full body, black hair, dark eyes, medium breasts, slender physique, medium skin tone, brown eyes, dark eyebrows, small areola, standing with her legs together, hands at her sides, looking at the camera, natural lighting, bright and airy room, white walls, large window with sheer white curtains, white bed with a wooden frame, white bed linens, wooden floor, potted plant in the background, casual and relaxed pose, confident expression, soft shadows, high quality, jpeg artifacts, no watermark" |
| }, |
| { |
| "prompt": "Photo of a Indian 21y woman on her knees in a bathroom, giving a blowjob to a man standing in front of her. The woman has long black hair and a slender physique, with medium-sized breasts. The man is naked, with a large erect penis. The woman is performing oral sex on the man, with her eyes closed and her lips wrapped around his penis. The bathroom has a modern design, a wooden floor. The lighting is soft and warm, with a gentle glow on the woman's skin. The image is high quality and has a watermark in the bottom right corner." |
| }, |
| { |
| "prompt": "Photo of a nude woman with long black hair kneeling on a bathroom floor, facing the camera, looking directly at the camera with a neutral expression. She has a medium skin tone and a slender, toned physique. Her breasts are medium-sized with small areolas. The bathroom has gray tiled walls and a white toilet in the background. The lighting is soft and even, creating a calm and intimate atmosphere." |
| } |
| ], |
| "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: "328a8d76-cb87-47fd-b44e-19453f3c2459" |
|
|
| ############################################# |
| # Running job: my_first_lora_v2 |
| ############################################# |
|
|
|
|
| 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 [00:05<00:00, 1.98s/it]
Loading checkpoint shards: 100%|##########| 3/3 [00:05<00:00, 1.98s/it]
Loading checkpoint shards: 100%|##########| 3/3 [00:05<00:00, 1.68s/it]
Loading checkpoint shards: 100%|##########| 3/3 [00:05<00:00, 1.68s/it] |
|
|
| 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, 6.67it/s]
3%|3 | 1/30 [00:00<00:04, 6.67it/s]
7%|6 | 2/30 [00:00<00:03, 7.61it/s]
7%|6 | 2/30 [00:00<00:03, 7.61it/s]
10%|# | 3/30 [00:00<00:03, 8.06it/s]
10%|# | 3/30 [00:00<00:03, 8.06it/s]
17%|#6 | 5/30 [00:00<00:02, 9.18it/s]
17%|#6 | 5/30 [00:00<00:02, 9.18it/s]
20%|## | 6/30 [00:00<00:02, 9.06it/s]
20%|## | 6/30 [00:00<00:02, 9.06it/s]
23%|##3 | 7/30 [00:00<00:02, 9.00it/s]
23%|##3 | 7/30 [00:00<00:02, 9.00it/s]
30%|### | 9/30 [00:00<00:02, 9.59it/s]
30%|### | 9/30 [00:00<00:02, 9.59it/s]
37%|###6 | 11/30 [00:01<00:01, 9.86it/s]
37%|###6 | 11/30 [00:01<00:01, 9.86it/s]
40%|#### | 12/30 [00:01<00:01, 9.63it/s]
40%|#### | 12/30 [00:01<00:01, 9.63it/s]
43%|####3 | 13/30 [00:01<00:01, 9.46it/s]
43%|####3 | 13/30 [00:01<00:01, 9.46it/s]
47%|####6 | 14/30 [00:01<00:01, 9.28it/s]
47%|####6 | 14/30 [00:01<00:01, 9.28it/s]
50%|##### | 15/30 [00:01<00:01, 9.17it/s]
50%|##### | 15/30 [00:01<00:01, 9.17it/s]
53%|#####3 | 16/30 [00:01<00:01, 9.07it/s]
53%|#####3 | 16/30 [00:01<00:01, 9.07it/s]
57%|#####6 | 17/30 [00:01<00:01, 9.00it/s]
57%|#####6 | 17/30 [00:01<00:01, 9.00it/s]
63%|######3 | 19/30 [00:02<00:01, 9.52it/s]
63%|######3 | 19/30 [00:02<00:01, 9.52it/s]
70%|####### | 21/30 [00:02<00:00, 9.49it/s]
70%|####### | 21/30 [00:02<00:00, 9.49it/s]
73%|#######3 | 22/30 [00:02<00:00, 9.24it/s]
73%|#######3 | 22/30 [00:02<00:00, 9.24it/s]
77%|#######6 | 23/30 [00:02<00:00, 9.13it/s]
77%|#######6 | 23/30 [00:02<00:00, 9.13it/s]
83%|########3 | 25/30 [00:02<00:00, 9.57it/s]
83%|########3 | 25/30 [00:02<00:00, 9.57it/s]
90%|######### | 27/30 [00:02<00:00, 9.51it/s]
90%|######### | 27/30 [00:02<00:00, 9.51it/s]
93%|#########3| 28/30 [00:03<00:00, 9.37it/s]
93%|#########3| 28/30 [00:03<00:00, 9.37it/s]
97%|#########6| 29/30 [00:03<00:00, 9.26it/s]
97%|#########6| 29/30 [00:03<00:00, 9.26it/s]
100%|##########| 30/30 [00:03<00:00, 9.27it/s]
100%|##########| 30/30 [00:03<00:00, 9.27it/s] |
|
|
| - quantizing extras |
| Moving transformer to CPU |
| 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: 67%|######6 | 2/3 [00:00<00:00, 12.48it/s]
Loading checkpoint shards: 67%|######6 | 2/3 [00:00<00:00, 12.48it/s]
Loading checkpoint shards: 100%|##########| 3/3 [00:00<00:00, 18.41it/s]
Loading checkpoint shards: 100%|##########| 3/3 [00:00<00:00, 18.41it/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/topa |
| - Preprocessing image dimensions |
|
0%| | 0/30 [00:00<?, ?it/s]
0%| | 0/30 [00:00<?, ?it/s]
10%|# | 3/30 [00:00<00:02, 10.69it/s]
10%|# | 3/30 [00:00<00:02, 10.69it/s]
20%|## | 6/30 [00:00<00:01, 13.38it/s]
20%|## | 6/30 [00:00<00:01, 13.38it/s]
27%|##6 | 8/30 [00:00<00:02, 10.88it/s]
27%|##6 | 8/30 [00:00<00:02, 10.88it/s]
37%|###6 | 11/30 [00:00<00:01, 15.04it/s]
37%|###6 | 11/30 [00:00<00:01, 15.04it/s]
47%|####6 | 14/30 [00:01<00:01, 13.43it/s]
47%|####6 | 14/30 [00:01<00:01, 13.43it/s]
57%|#####6 | 17/30 [00:01<00:00, 16.18it/s]
57%|#####6 | 17/30 [00:01<00:00, 16.18it/s]
63%|######3 | 19/30 [00:01<00:00, 12.66it/s]
63%|######3 | 19/30 [00:01<00:00, 12.66it/s]
73%|#######3 | 22/30 [00:01<00:00, 12.33it/s]
73%|#######3 | 22/30 [00:01<00:00, 12.33it/s]
93%|#########3| 28/30 [00:01<00:00, 19.55it/s]
93%|#########3| 28/30 [00:01<00:00, 19.55it/s]
100%|##########| 30/30 [00:01<00:00, 15.92it/s]
100%|##########| 30/30 [00:01<00:00, 15.92it/s] |
|
|
| - Found 30 images |
| Bucket sizes for /teamspace/studios/this_studio/ai-toolkit/datasets/topa: |
| 352x736: 5 files |
| 384x672: 8 files |
| 448x576: 7 files |
| 416x608: 1 files |
| 512x512: 2 files |
| 416x576: 2 files |
| 448x544: 2 files |
| 384x640: 1 files |
| 320x768: 1 files |
| 480x512: 1 files |
| 10 buckets made |
| Dataset: /teamspace/studios/this_studio/ai-toolkit/datasets/topa |
| - Preprocessing image dimensions |
|
0%| | 0/30 [00:00<?, ?it/s]
0%| | 0/30 [00:00<?, ?it/s]
100%|##########| 30/30 [00:00<00:00, 39831.95it/s]
100%|##########| 30/30 [00:00<00:00, 39831.95it/s] |
|
|
| - Found 30 images |
| Bucket sizes for /teamspace/studios/this_studio/ai-toolkit/datasets/topa: |
| 704x1472: 5 files |
| 768x1344: 4 files |
| 896x1152: 5 files |
| 832x1216: 1 files |
| 704x1248: 3 files |
| 1024x1024: 1 files |
| 448x576: 1 files |
| 832x1152: 2 files |
| 896x1088: 3 files |
| 736x1312: 1 files |
| 704x704: 1 files |
| 768x1280: 1 files |
| 640x1536: 1 files |
| 960x1024: 1 files |
| 14 buckets made |
| Generating baseline samples before training |
| Unloading assistant lora |
|
Generating Images: 0%| | 0/3 [00:00<?, ?it/s]
Generating Images: 0%| | 0/3 [00:00<?, ?it/s]
Generating Images: 33%|###3 | 1/3 [00:07<00:15, 7.95s/it]
Generating Images: 33%|###3 | 1/3 [00:07<00:15, 7.95s/it]
Generating Images: 67%|######6 | 2/3 [00:15<00:07, 7.72s/it]
Generating Images: 67%|######6 | 2/3 [00:15<00:07, 7.72s/it]
Generating Images: 100%|##########| 3/3 [00:23<00:00, 7.63s/it]
Generating Images: 100%|##########| 3/3 [00:23<00:00, 7.63s/it]
Loading assistant lora |
|
my_first_lora_v2: 0%| | 0/4000 [00:00<?, ?it/s]
my_first_lora_v2: 0%| | 0/4000 [00:00<?, ?it/s]
my_first_lora_v2: 0%| | 0/4000 [00:03<?, ?it/s, lr: 1.0e-04 loss: 7.491e-01]
my_first_lora_v2: 0%| | 0/4000 [00:03<?, ?it/s, lr: 1.0e-04 loss: 7.491e-01]
my_first_lora_v2: 0%| | 0/4000 [00:03<?, ?it/s, lr: 1.0e-04 loss: 7.491e-01]
my_first_lora_v2: 0%| | 0/4000 [00:03<?, ?it/s, lr: 1.0e-04 loss: 7.491e-01]
my_first_lora_v2: 0%| | 0/4000 [00:05<?, ?it/s, lr: 1.0e-04 loss: 3.339e-01]
my_first_lora_v2: 0%| | 0/4000 [00:05<?, ?it/s, lr: 1.0e-04 loss: 3.339e-01]
my_first_lora_v2: 0%| | 1/4000 [00:08<9:40:56, 8.72s/it, lr: 1.0e-04 loss: 6.523e-01]
my_first_lora_v2: 0%| | 1/4000 [00:08<9:40:56, 8.72s/it, lr: 1.0e-04 loss: 6.523e-01]
my_first_lora_v2: 0%| | 2/4000 [00:09<5:17:22, 4.76s/it, lr: 1.0e-04 loss: 6.574e-01]
my_first_lora_v2: 0%| | 2/4000 [00:09<5:17:22, 4.76s/it, lr: 1.0e-04 loss: 6.574e-01]
my_first_lora_v2: 0%| | 3/4000 [00:12<4:35:20, 4.13s/it, lr: 1.0e-04 loss: 3.142e-01]
my_first_lora_v2: 0%| | 3/4000 [00:12<4:35:20, 4.13s/it, lr: 1.0e-04 loss: 3.142e-01]
my_first_lora_v2: 0%| | 4/4000 [00:13<3:39:59, 3.30s/it, lr: 1.0e-04 loss: 3.825e-01]
my_first_lora_v2: 0%| | 4/4000 [00:13<3:39:59, 3.30s/it, lr: 1.0e-04 loss: 3.825e-01]
my_first_lora_v2: 0%| | 5/4000 [00:16<3:34:02, 3.21s/it, lr: 1.0e-04 loss: 3.072e-01]
my_first_lora_v2: 0%| | 5/4000 [00:16<3:34:02, 3.21s/it, lr: 1.0e-04 loss: 3.072e-01]
my_first_lora_v2: 0%| | 6/4000 [00:18<3:29:58, 3.15s/it, lr: 1.0e-04 loss: 5.676e-01]
my_first_lora_v2: 0%| | 6/4000 [00:18<3:29:58, 3.15s/it, lr: 1.0e-04 loss: 5.676e-01]
my_first_lora_v2: 0%| | 7/4000 [00:19<3:07:40, 2.82s/it, lr: 1.0e-04 loss: 3.203e-01]
my_first_lora_v2: 0%| | 7/4000 [00:19<3:07:40, 2.82s/it, lr: 1.0e-04 loss: 3.203e-01]
my_first_lora_v2: 0%| | 8/4000 [00:22<3:06:16, 2.80s/it, lr: 1.0e-04 loss: 5.099e-01]
my_first_lora_v2: 0%| | 8/4000 [00:22<3:06:16, 2.80s/it, lr: 1.0e-04 loss: 5.099e-01]
my_first_lora_v2: 0%| | 9/4000 [00:25<3:06:45, 2.81s/it, lr: 1.0e-04 loss: 1.737e-01]
my_first_lora_v2: 0%| | 9/4000 [00:25<3:06:45, 2.81s/it, lr: 1.0e-04 loss: 1.737e-01]
my_first_lora_v2: 0%| | 10/4000 [00:28<3:07:11, 2.81s/it, lr: 1.0e-04 loss: 3.647e-01]
my_first_lora_v2: 0%| | 10/4000 [00:28<3:07:11, 2.81s/it, lr: 1.0e-04 loss: 3.647e-01]
my_first_lora_v2: 0%| | 11/4000 [00:28<2:54:54, 2.63s/it, lr: 1.0e-04 loss: 2.721e-01]
my_first_lora_v2: 0%| | 11/4000 [00:28<2:54:54, 2.63s/it, lr: 1.0e-04 loss: 2.721e-01]
my_first_lora_v2: 0%| | 12/4000 [00:29<2:46:09, 2.50s/it, lr: 1.0e-04 loss: 4.306e-01]
my_first_lora_v2: 0%| | 12/4000 [00:29<2:46:09, 2.50s/it, lr: 1.0e-04 loss: 4.306e-01]
my_first_lora_v2: 0%| | 13/4000 [00:32<2:48:02, 2.53s/it, lr: 1.0e-04 loss: 6.934e-01]
my_first_lora_v2: 0%| | 13/4000 [00:32<2:48:02, 2.53s/it, lr: 1.0e-04 loss: 6.934e-01]
my_first_lora_v2: 0%| | 14/4000 [00:33<2:39:51, 2.41s/it, lr: 1.0e-04 loss: 3.045e-01]
my_first_lora_v2: 0%| | 14/4000 [00:33<2:39:51, 2.41s/it, lr: 1.0e-04 loss: 3.045e-01]
my_first_lora_v2: 0%| | 15/4000 [00:34<2:32:36, 2.30s/it, lr: 1.0e-04 loss: 2.350e-01]
my_first_lora_v2: 0%| | 15/4000 [00:34<2:32:36, 2.30s/it, lr: 1.0e-04 loss: 2.350e-01]
my_first_lora_v2: 0%| | 16/4000 [00:35<2:26:18, 2.20s/it, lr: 1.0e-04 loss: 3.132e-01]
my_first_lora_v2: 0%| | 16/4000 [00:35<2:26:18, 2.20s/it, lr: 1.0e-04 loss: 3.132e-01]
my_first_lora_v2: 0%| | 17/4000 [00:38<2:28:52, 2.24s/it, lr: 1.0e-04 loss: 7.330e-01]
my_first_lora_v2: 0%| | 17/4000 [00:38<2:28:52, 2.24s/it, lr: 1.0e-04 loss: 7.330e-01]
my_first_lora_v2: 0%| | 18/4000 [00:38<2:23:41, 2.17s/it, lr: 1.0e-04 loss: 2.495e-02]
my_first_lora_v2: 0%| | 18/4000 [00:38<2:23:41, 2.17s/it, lr: 1.0e-04 loss: 2.495e-02]
my_first_lora_v2: 0%| | 19/4000 [00:41<2:26:11, 2.20s/it, lr: 1.0e-04 loss: 2.427e-01]
my_first_lora_v2: 0%| | 19/4000 [00:41<2:26:11, 2.20s/it, lr: 1.0e-04 loss: 2.427e-01]
my_first_lora_v2: 0%| | 20/4000 [00:42<2:21:31, 2.13s/it, lr: 1.0e-04 loss: 3.714e-01]
my_first_lora_v2: 0%| | 20/4000 [00:42<2:21:31, 2.13s/it, lr: 1.0e-04 loss: 3.714e-01]
my_first_lora_v2: 1%| | 21/4000 [00:43<2:18:56, 2.10s/it, lr: 1.0e-04 loss: 2.689e-01]
my_first_lora_v2: 1%| | 21/4000 [00:43<2:18:56, 2.10s/it, lr: 1.0e-04 loss: 2.689e-01]
my_first_lora_v2: 1%| | 22/4000 [00:44<2:15:01, 2.04s/it, lr: 1.0e-04 loss: 4.484e-01]
my_first_lora_v2: 1%| | 22/4000 [00:44<2:15:01, 2.04s/it, lr: 1.0e-04 loss: 4.484e-01]
my_first_lora_v2: 1%| | 23/4000 [00:47<2:17:27, 2.07s/it, lr: 1.0e-04 loss: 5.806e-01]
my_first_lora_v2: 1%| | 23/4000 [00:47<2:17:27, 2.07s/it, lr: 1.0e-04 loss: 5.806e-01]
my_first_lora_v2: 1%| | 24/4000 [00:50<2:18:17, 2.09s/it, lr: 1.0e-04 loss: 3.483e-01]
my_first_lora_v2: 1%| | 24/4000 [00:50<2:18:17, 2.09s/it, lr: 1.0e-04 loss: 3.483e-01]
my_first_lora_v2: 1%| | 25/4000 [00:50<2:14:49, 2.04s/it, lr: 1.0e-04 loss: 5.167e-01]
my_first_lora_v2: 1%| | 25/4000 [00:50<2:14:49, 2.04s/it, lr: 1.0e-04 loss: 5.167e-01]
my_first_lora_v2: 1%| | 26/4000 [00:51<2:12:23, 2.00s/it, lr: 1.0e-04 loss: 7.189e-01]
my_first_lora_v2: 1%| | 26/4000 [00:51<2:12:23, 2.00s/it, lr: 1.0e-04 loss: 7.189e-01]
my_first_lora_v2: 1%| | 27/4000 [00:52<2:09:26, 1.95s/it, lr: 1.0e-04 loss: 2.379e-01]
my_first_lora_v2: 1%| | 27/4000 [00:52<2:09:26, 1.95s/it, lr: 1.0e-04 loss: 2.379e-01]
my_first_lora_v2: 1%| | 28/4000 [00:53<2:06:43, 1.91s/it, lr: 1.0e-04 loss: 1.119e-01]
my_first_lora_v2: 1%| | 28/4000 [00:53<2:06:43, 1.91s/it, lr: 1.0e-04 loss: 1.119e-01]
my_first_lora_v2: 1%| | 29/4000 [00:54<2:04:07, 1.88s/it, lr: 1.0e-04 loss: 3.336e-01]
my_first_lora_v2: 1%| | 29/4000 [00:54<2:04:07, 1.88s/it, lr: 1.0e-04 loss: 3.336e-01]
my_first_lora_v2: 1%| | 30/4000 [00:56<2:05:10, 1.89s/it, lr: 1.0e-04 loss: 1.280e-01]
my_first_lora_v2: 1%| | 30/4000 [00:56<2:05:10, 1.89s/it, lr: 1.0e-04 loss: 1.280e-01]
my_first_lora_v2: 1%| | 31/4000 [00:59<2:06:49, 1.92s/it, lr: 1.0e-04 loss: 2.898e-01]
my_first_lora_v2: 1%| | 31/4000 [00:59<2:06:49, 1.92s/it, lr: 1.0e-04 loss: 2.898e-01]
my_first_lora_v2: 1%| | 32/4000 [01:01<2:07:46, 1.93s/it, lr: 1.0e-04 loss: 2.867e-01]
my_first_lora_v2: 1%| | 32/4000 [01:01<2:07:46, 1.93s/it, lr: 1.0e-04 loss: 2.867e-01]
my_first_lora_v2: 1%| | 33/4000 [01:02<2:05:29, 1.90s/it, lr: 1.0e-04 loss: 1.828e-01]
my_first_lora_v2: 1%| | 33/4000 [01:02<2:05:29, 1.90s/it, lr: 1.0e-04 loss: 1.828e-01]
my_first_lora_v2: 1%| | 34/4000 [01:05<2:06:56, 1.92s/it, lr: 1.0e-04 loss: 3.028e-01]
my_first_lora_v2: 1%| | 34/4000 [01:05<2:06:56, 1.92s/it, lr: 1.0e-04 loss: 3.028e-01]
my_first_lora_v2: 1%| | 35/4000 [01:06<2:04:48, 1.89s/it, lr: 1.0e-04 loss: 5.512e-01]
my_first_lora_v2: 1%| | 35/4000 [01:06<2:04:48, 1.89s/it, lr: 1.0e-04 loss: 5.512e-01]
my_first_lora_v2: 1%| | 36/4000 [01:08<2:06:37, 1.92s/it, lr: 1.0e-04 loss: 4.342e-01]
my_first_lora_v2: 1%| | 36/4000 [01:08<2:06:37, 1.92s/it, lr: 1.0e-04 loss: 4.342e-01]
my_first_lora_v2: 1%| | 37/4000 [01:11<2:08:03, 1.94s/it, lr: 1.0e-04 loss: 7.680e-01]
my_first_lora_v2: 1%| | 37/4000 [01:11<2:08:03, 1.94s/it, lr: 1.0e-04 loss: 7.680e-01]
my_first_lora_v2: 1%| | 38/4000 [01:14<2:09:41, 1.96s/it, lr: 1.0e-04 loss: 3.914e-01]
my_first_lora_v2: 1%| | 38/4000 [01:14<2:09:41, 1.96s/it, lr: 1.0e-04 loss: 3.914e-01]
my_first_lora_v2: 1%| | 39/4000 [01:15<2:07:44, 1.93s/it, lr: 1.0e-04 loss: 8.181e-01]
my_first_lora_v2: 1%| | 39/4000 [01:15<2:07:44, 1.93s/it, lr: 1.0e-04 loss: 8.181e-01]
my_first_lora_v2: 1%|1 | 40/4000 [01:16<2:06:18, 1.91s/it, lr: 1.0e-04 loss: 1.426e-01]
my_first_lora_v2: 1%|1 | 40/4000 [01:16<2:06:18, 1.91s/it, lr: 1.0e-04 loss: 1.426e-01]
my_first_lora_v2: 1%|1 | 41/4000 [01:17<2:04:28, 1.89s/it, lr: 1.0e-04 loss: 1.453e-01]
my_first_lora_v2: 1%|1 | 41/4000 [01:17<2:04:28, 1.89s/it, lr: 1.0e-04 loss: 1.453e-01]
my_first_lora_v2: 1%|1 | 42/4000 [01:18<2:02:45, 1.86s/it, lr: 1.0e-04 loss: 1.485e-01]
my_first_lora_v2: 1%|1 | 42/4000 [01:18<2:02:45, 1.86s/it, lr: 1.0e-04 loss: 1.485e-01]
my_first_lora_v2: 1%|1 | 43/4000 [01:20<2:03:58, 1.88s/it, lr: 1.0e-04 loss: 6.757e-01]
my_first_lora_v2: 1%|1 | 43/4000 [01:20<2:03:58, 1.88s/it, lr: 1.0e-04 loss: 6.757e-01]
my_first_lora_v2: 1%|1 | 44/4000 [01:21<2:02:20, 1.86s/it, lr: 1.0e-04 loss: 3.770e-01]
my_first_lora_v2: 1%|1 | 44/4000 [01:21<2:02:20, 1.86s/it, lr: 1.0e-04 loss: 3.770e-01]
my_first_lora_v2: 1%|1 | 45/4000 [01:22<2:00:48, 1.83s/it, lr: 1.0e-04 loss: 5.364e-01]
my_first_lora_v2: 1%|1 | 45/4000 [01:22<2:00:48, 1.83s/it, lr: 1.0e-04 loss: 5.364e-01]
my_first_lora_v2: 1%|1 | 46/4000 [01:23<1:59:18, 1.81s/it, lr: 1.0e-04 loss: 6.723e-01]
my_first_lora_v2: 1%|1 | 46/4000 [01:23<1:59:18, 1.81s/it, lr: 1.0e-04 loss: 6.723e-01]
my_first_lora_v2: 1%|1 | 47/4000 [01:26<2:00:44, 1.83s/it, lr: 1.0e-04 loss: 1.420e-01]
my_first_lora_v2: 1%|1 | 47/4000 [01:26<2:00:44, 1.83s/it, lr: 1.0e-04 loss: 1.420e-01]
my_first_lora_v2: 1%|1 | 48/4000 [01:29<2:02:10, 1.85s/it, lr: 1.0e-04 loss: 5.301e-01]
my_first_lora_v2: 1%|1 | 48/4000 [01:29<2:02:10, 1.85s/it, lr: 1.0e-04 loss: 5.301e-01]
my_first_lora_v2: 1%|1 | 49/4000 [01:31<2:03:11, 1.87s/it, lr: 1.0e-04 loss: 1.694e-01]
my_first_lora_v2: 1%|1 | 49/4000 [01:31<2:03:11, 1.87s/it, lr: 1.0e-04 loss: 1.694e-01]
my_first_lora_v2: 1%|1 | 50/4000 [01:32<2:01:46, 1.85s/it, lr: 1.0e-04 loss: 6.470e-01]
my_first_lora_v2: 1%|1 | 50/4000 [01:32<2:01:46, 1.85s/it, lr: 1.0e-04 loss: 6.470e-01]
my_first_lora_v2: 1%|1 | 51/4000 [01:33<2:00:23, 1.83s/it, lr: 1.0e-04 loss: 3.160e-01]
my_first_lora_v2: 1%|1 | 51/4000 [01:33<2:00:23, 1.83s/it, lr: 1.0e-04 loss: 3.160e-01]
my_first_lora_v2: 1%|1 | 52/4000 [01:34<1:59:04, 1.81s/it, lr: 1.0e-04 loss: 4.314e-01]
my_first_lora_v2: 1%|1 | 52/4000 [01:34<1:59:04, 1.81s/it, lr: 1.0e-04 loss: 4.314e-01]
my_first_lora_v2: 1%|1 | 53/4000 [01:35<1:58:09, 1.80s/it, lr: 1.0e-04 loss: 4.137e-01]
my_first_lora_v2: 1%|1 | 53/4000 [01:35<1:58:09, 1.80s/it, lr: 1.0e-04 loss: 4.137e-01]
my_first_lora_v2: 1%|1 | 54/4000 [01:36<1:56:55, 1.78s/it, lr: 1.0e-04 loss: 6.811e-01]
my_first_lora_v2: 1%|1 | 54/4000 [01:36<1:56:55, 1.78s/it, lr: 1.0e-04 loss: 6.811e-01]
my_first_lora_v2: 1%|1 | 55/4000 [01:38<1:57:55, 1.79s/it, lr: 1.0e-04 loss: 1.726e-01]
my_first_lora_v2: 1%|1 | 55/4000 [01:38<1:57:55, 1.79s/it, lr: 1.0e-04 loss: 1.726e-01]
my_first_lora_v2: 1%|1 | 56/4000 [01:41<1:59:15, 1.81s/it, lr: 1.0e-04 loss: 7.379e-01]
my_first_lora_v2: 1%|1 | 56/4000 [01:41<1:59:15, 1.81s/it, lr: 1.0e-04 loss: 7.379e-01]
my_first_lora_v2: 1%|1 | 57/4000 [01:42<1:58:07, 1.80s/it, lr: 1.0e-04 loss: 4.401e-01]
my_first_lora_v2: 1%|1 | 57/4000 [01:42<1:58:07, 1.80s/it, lr: 1.0e-04 loss: 4.401e-01]
my_first_lora_v2: 1%|1 | 58/4000 [01:45<1:59:20, 1.82s/it, lr: 1.0e-04 loss: 4.217e-01]
my_first_lora_v2: 1%|1 | 58/4000 [01:45<1:59:20, 1.82s/it, lr: 1.0e-04 loss: 4.217e-01]
my_first_lora_v2: 1%|1 | 59/4000 [01:48<2:00:44, 1.84s/it, lr: 1.0e-04 loss: 3.149e-01]
my_first_lora_v2: 1%|1 | 59/4000 [01:48<2:00:44, 1.84s/it, lr: 1.0e-04 loss: 3.149e-01]
my_first_lora_v2: 2%|1 | 60/4000 [01:49<1:59:35, 1.82s/it, lr: 1.0e-04 loss: 6.026e-01]
my_first_lora_v2: 2%|1 | 60/4000 [01:49<1:59:35, 1.82s/it, lr: 1.0e-04 loss: 6.026e-01]
my_first_lora_v2: 2%|1 | 61/4000 [01:50<1:58:28, 1.80s/it, lr: 1.0e-04 loss: 5.698e-01]
my_first_lora_v2: 2%|1 | 61/4000 [01:50<1:58:28, 1.80s/it, lr: 1.0e-04 loss: 5.698e-01]
my_first_lora_v2: 2%|1 | 62/4000 [01:53<1:59:38, 1.82s/it, lr: 1.0e-04 loss: 2.332e-01]
my_first_lora_v2: 2%|1 | 62/4000 [01:53<1:59:38, 1.82s/it, lr: 1.0e-04 loss: 2.332e-01]
my_first_lora_v2: 2%|1 | 63/4000 [01:53<1:58:32, 1.81s/it, lr: 1.0e-04 loss: 1.436e-02]
my_first_lora_v2: 2%|1 | 63/4000 [01:53<1:58:32, 1.81s/it, lr: 1.0e-04 loss: 1.436e-02]
my_first_lora_v2: 2%|1 | 64/4000 [01:54<1:57:30, 1.79s/it, lr: 1.0e-04 loss: 6.554e-01]
my_first_lora_v2: 2%|1 | 64/4000 [01:54<1:57:30, 1.79s/it, lr: 1.0e-04 loss: 6.554e-01]
my_first_lora_v2: 2%|1 | 65/4000 [01:57<1:58:22, 1.81s/it, lr: 1.0e-04 loss: 7.069e-01]
my_first_lora_v2: 2%|1 | 65/4000 [01:57<1:58:22, 1.81s/it, lr: 1.0e-04 loss: 7.069e-01]
my_first_lora_v2: 2%|1 | 66/4000 [02:00<1:59:29, 1.82s/it, lr: 1.0e-04 loss: 1.676e-01]
my_first_lora_v2: 2%|1 | 66/4000 [02:00<1:59:29, 1.82s/it, lr: 1.0e-04 loss: 1.676e-01]
my_first_lora_v2: 2%|1 | 67/4000 [02:03<2:00:31, 1.84s/it, lr: 1.0e-04 loss: 2.313e-01]
my_first_lora_v2: 2%|1 | 67/4000 [02:03<2:00:31, 1.84s/it, lr: 1.0e-04 loss: 2.313e-01]
my_first_lora_v2: 2%|1 | 68/4000 [02:05<2:01:17, 1.85s/it, lr: 1.0e-04 loss: 4.481e-01]
my_first_lora_v2: 2%|1 | 68/4000 [02:05<2:01:17, 1.85s/it, lr: 1.0e-04 loss: 4.481e-01]
my_first_lora_v2: 2%|1 | 69/4000 [02:08<2:02:16, 1.87s/it, lr: 1.0e-04 loss: 5.729e-01]
my_first_lora_v2: 2%|1 | 69/4000 [02:08<2:02:16, 1.87s/it, lr: 1.0e-04 loss: 5.729e-01]
my_first_lora_v2: 2%|1 | 70/4000 [02:09<2:01:14, 1.85s/it, lr: 1.0e-04 loss: 6.919e-01]
my_first_lora_v2: 2%|1 | 70/4000 [02:09<2:01:14, 1.85s/it, lr: 1.0e-04 loss: 6.919e-01]
my_first_lora_v2: 2%|1 | 71/4000 [02:10<2:00:16, 1.84s/it, lr: 1.0e-04 loss: 3.669e-01]
my_first_lora_v2: 2%|1 | 71/4000 [02:10<2:00:16, 1.84s/it, lr: 1.0e-04 loss: 3.669e-01]
my_first_lora_v2: 2%|1 | 72/4000 [02:11<1:59:16, 1.82s/it, lr: 1.0e-04 loss: 4.993e-01]
my_first_lora_v2: 2%|1 | 72/4000 [02:11<1:59:16, 1.82s/it, lr: 1.0e-04 loss: 4.993e-01]
my_first_lora_v2: 2%|1 | 73/4000 [02:11<1:58:17, 1.81s/it, lr: 1.0e-04 loss: 2.589e-01]
my_first_lora_v2: 2%|1 | 73/4000 [02:11<1:58:17, 1.81s/it, lr: 1.0e-04 loss: 2.589e-01]
my_first_lora_v2: 2%|1 | 74/4000 [02:14<1:59:13, 1.82s/it, lr: 1.0e-04 loss: 4.000e-01]
my_first_lora_v2: 2%|1 | 74/4000 [02:14<1:59:13, 1.82s/it, lr: 1.0e-04 loss: 4.000e-01]
my_first_lora_v2: 2%|1 | 75/4000 [02:15<1:58:18, 1.81s/it, lr: 1.0e-04 loss: 1.614e-01]
my_first_lora_v2: 2%|1 | 75/4000 [02:15<1:58:18, 1.81s/it, lr: 1.0e-04 loss: 1.614e-01]
my_first_lora_v2: 2%|1 | 76/4000 [02:16<1:57:26, 1.80s/it, lr: 1.0e-04 loss: 3.770e-01]
my_first_lora_v2: 2%|1 | 76/4000 [02:16<1:57:26, 1.80s/it, lr: 1.0e-04 loss: 3.770e-01]
my_first_lora_v2: 2%|1 | 77/4000 [02:17<1:56:33, 1.78s/it, lr: 1.0e-04 loss: 5.883e-01]
my_first_lora_v2: 2%|1 | 77/4000 [02:17<1:56:33, 1.78s/it, lr: 1.0e-04 loss: 5.883e-01]
my_first_lora_v2: 2%|1 | 78/4000 [02:18<1:55:41, 1.77s/it, lr: 1.0e-04 loss: 2.837e-01]
my_first_lora_v2: 2%|1 | 78/4000 [02:18<1:55:41, 1.77s/it, lr: 1.0e-04 loss: 2.837e-01]
my_first_lora_v2: 2%|1 | 79/4000 [02:18<1:54:50, 1.76s/it, lr: 1.0e-04 loss: 4.242e-01]
my_first_lora_v2: 2%|1 | 79/4000 [02:18<1:54:50, 1.76s/it, lr: 1.0e-04 loss: 4.242e-01]
my_first_lora_v2: 2%|2 | 80/4000 [02:21<1:55:40, 1.77s/it, lr: 1.0e-04 loss: 4.428e-01]
my_first_lora_v2: 2%|2 | 80/4000 [02:21<1:55:40, 1.77s/it, lr: 1.0e-04 loss: 4.428e-01]
my_first_lora_v2: 2%|2 | 81/4000 [02:24<1:56:32, 1.78s/it, lr: 1.0e-04 loss: 7.230e-01]
my_first_lora_v2: 2%|2 | 81/4000 [02:24<1:56:32, 1.78s/it, lr: 1.0e-04 loss: 7.230e-01]
my_first_lora_v2: 2%|2 | 82/4000 [02:25<1:56:06, 1.78s/it, lr: 1.0e-04 loss: 3.494e-01]
my_first_lora_v2: 2%|2 | 82/4000 [02:25<1:56:06, 1.78s/it, lr: 1.0e-04 loss: 3.494e-01]
my_first_lora_v2: 2%|2 | 83/4000 [02:26<1:55:17, 1.77s/it, lr: 1.0e-04 loss: 6.161e-01]
my_first_lora_v2: 2%|2 | 83/4000 [02:26<1:55:17, 1.77s/it, lr: 1.0e-04 loss: 6.161e-01]
my_first_lora_v2: 2%|2 | 84/4000 [02:29<1:56:04, 1.78s/it, lr: 1.0e-04 loss: 4.263e-01]
my_first_lora_v2: 2%|2 | 84/4000 [02:29<1:56:04, 1.78s/it, lr: 1.0e-04 loss: 4.263e-01]
my_first_lora_v2: 2%|2 | 85/4000 [02:30<1:55:16, 1.77s/it, lr: 1.0e-04 loss: 5.985e-01]
my_first_lora_v2: 2%|2 | 85/4000 [02:30<1:55:16, 1.77s/it, lr: 1.0e-04 loss: 5.985e-01]
my_first_lora_v2: 2%|2 | 86/4000 [02:33<1:56:04, 1.78s/it, lr: 1.0e-04 loss: 3.935e-01]
my_first_lora_v2: 2%|2 | 86/4000 [02:33<1:56:04, 1.78s/it, lr: 1.0e-04 loss: 3.935e-01]
my_first_lora_v2: 2%|2 | 87/4000 [02:35<1:56:29, 1.79s/it, lr: 1.0e-04 loss: 6.358e-01]
my_first_lora_v2: 2%|2 | 87/4000 [02:35<1:56:29, 1.79s/it, lr: 1.0e-04 loss: 6.358e-01]
my_first_lora_v2: 2%|2 | 88/4000 [02:36<1:55:42, 1.77s/it, lr: 1.0e-04 loss: 6.419e-01]
my_first_lora_v2: 2%|2 | 88/4000 [02:36<1:55:42, 1.77s/it, lr: 1.0e-04 loss: 6.419e-01]
my_first_lora_v2: 2%|2 | 89/4000 [02:36<1:54:56, 1.76s/it, lr: 1.0e-04 loss: 5.328e-01]
my_first_lora_v2: 2%|2 | 89/4000 [02:36<1:54:56, 1.76s/it, lr: 1.0e-04 loss: 5.328e-01]
my_first_lora_v2: 2%|2 | 90/4000 [02:39<1:55:42, 1.78s/it, lr: 1.0e-04 loss: 4.574e-01]
my_first_lora_v2: 2%|2 | 90/4000 [02:39<1:55:42, 1.78s/it, lr: 1.0e-04 loss: 4.574e-01]
my_first_lora_v2: 2%|2 | 91/4000 [02:42<1:56:07, 1.78s/it, lr: 1.0e-04 loss: 6.311e-02]
my_first_lora_v2: 2%|2 | 91/4000 [02:42<1:56:07, 1.78s/it, lr: 1.0e-04 loss: 6.311e-02]
my_first_lora_v2: 2%|2 | 92/4000 [02:43<1:55:24, 1.77s/it, lr: 1.0e-04 loss: 5.887e-01]
my_first_lora_v2: 2%|2 | 92/4000 [02:43<1:55:24, 1.77s/it, lr: 1.0e-04 loss: 5.887e-01]
my_first_lora_v2: 2%|2 | 93/4000 [02:45<1:55:59, 1.78s/it, lr: 1.0e-04 loss: 3.422e-01]
my_first_lora_v2: 2%|2 | 93/4000 [02:45<1:55:59, 1.78s/it, lr: 1.0e-04 loss: 3.422e-01]
my_first_lora_v2: 2%|2 | 94/4000 [02:46<1:55:26, 1.77s/it, lr: 1.0e-04 loss: 5.641e-01]
my_first_lora_v2: 2%|2 | 94/4000 [02:46<1:55:26, 1.77s/it, lr: 1.0e-04 loss: 5.641e-01]
my_first_lora_v2: 2%|2 | 95/4000 [02:47<1:54:43, 1.76s/it, lr: 1.0e-04 loss: 8.832e-01]
my_first_lora_v2: 2%|2 | 95/4000 [02:47<1:54:43, 1.76s/it, lr: 1.0e-04 loss: 8.832e-01]
my_first_lora_v2: 2%|2 | 96/4000 [02:50<1:55:26, 1.77s/it, lr: 1.0e-04 loss: 6.343e-01]
my_first_lora_v2: 2%|2 | 96/4000 [02:50<1:55:26, 1.77s/it, lr: 1.0e-04 loss: 6.343e-01]
my_first_lora_v2: 2%|2 | 97/4000 [02:51<1:54:46, 1.76s/it, lr: 1.0e-04 loss: 6.405e-01]
my_first_lora_v2: 2%|2 | 97/4000 [02:51<1:54:46, 1.76s/it, lr: 1.0e-04 loss: 6.405e-01]
my_first_lora_v2: 2%|2 | 98/4000 [02:51<1:54:07, 1.75s/it, lr: 1.0e-04 loss: 4.126e-01]
my_first_lora_v2: 2%|2 | 98/4000 [02:51<1:54:07, 1.75s/it, lr: 1.0e-04 loss: 4.126e-01]
my_first_lora_v2: 2%|2 | 99/4000 [02:54<1:54:30, 1.76s/it, lr: 1.0e-04 loss: 1.072e-01]
my_first_lora_v2: 2%|2 | 99/4000 [02:54<1:54:30, 1.76s/it, lr: 1.0e-04 loss: 1.072e-01]
my_first_lora_v2: 2%|2 | 100/4000 [02:57<1:55:11, 1.77s/it, lr: 1.0e-04 loss: 3.929e-01]
my_first_lora_v2: 2%|2 | 100/4000 [02:57<1:55:11, 1.77s/it, lr: 1.0e-04 loss: 3.929e-01]
my_first_lora_v2: 3%|2 | 101/4000 [02:59<1:55:42, 1.78s/it, lr: 1.0e-04 loss: 6.060e-01]
my_first_lora_v2: 3%|2 | 101/4000 [02:59<1:55:42, 1.78s/it, lr: 1.0e-04 loss: 6.060e-01]
my_first_lora_v2: 3%|2 | 102/4000 [03:02<1:56:14, 1.79s/it, lr: 1.0e-04 loss: 1.394e-01]
my_first_lora_v2: 3%|2 | 102/4000 [03:02<1:56:14, 1.79s/it, lr: 1.0e-04 loss: 1.394e-01]
my_first_lora_v2: 3%|2 | 103/4000 [03:05<1:56:53, 1.80s/it, lr: 1.0e-04 loss: 4.653e-01]
my_first_lora_v2: 3%|2 | 103/4000 [03:05<1:56:53, 1.80s/it, lr: 1.0e-04 loss: 4.653e-01]
my_first_lora_v2: 3%|2 | 104/4000 [03:06<1:56:13, 1.79s/it, lr: 1.0e-04 loss: 6.466e-01]
my_first_lora_v2: 3%|2 | 104/4000 [03:06<1:56:13, 1.79s/it, lr: 1.0e-04 loss: 6.466e-01]
my_first_lora_v2: 3%|2 | 105/4000 [03:06<1:55:33, 1.78s/it, lr: 1.0e-04 loss: 4.213e-01]
my_first_lora_v2: 3%|2 | 105/4000 [03:06<1:55:33, 1.78s/it, lr: 1.0e-04 loss: 4.213e-01]
my_first_lora_v2: 3%|2 | 106/4000 [03:07<1:54:55, 1.77s/it, lr: 1.0e-04 loss: 2.098e-01]
my_first_lora_v2: 3%|2 | 106/4000 [03:07<1:54:55, 1.77s/it, lr: 1.0e-04 loss: 2.098e-01]
my_first_lora_v2: 3%|2 | 107/4000 [03:10<1:55:33, 1.78s/it, lr: 1.0e-04 loss: 6.393e-01]
my_first_lora_v2: 3%|2 | 107/4000 [03:10<1:55:33, 1.78s/it, lr: 1.0e-04 loss: 6.393e-01]
my_first_lora_v2: 3%|2 | 108/4000 [03:11<1:54:57, 1.77s/it, lr: 1.0e-04 loss: 5.356e-01]
my_first_lora_v2: 3%|2 | 108/4000 [03:11<1:54:57, 1.77s/it, lr: 1.0e-04 loss: 5.356e-01]
my_first_lora_v2: 3%|2 | 109/4000 [03:12<1:54:21, 1.76s/it, lr: 1.0e-04 loss: 2.324e-01]
my_first_lora_v2: 3%|2 | 109/4000 [03:12<1:54:21, 1.76s/it, lr: 1.0e-04 loss: 2.324e-01]
my_first_lora_v2: 3%|2 | 110/4000 [03:12<1:53:44, 1.75s/it, lr: 1.0e-04 loss: 7.673e-01]
my_first_lora_v2: 3%|2 | 110/4000 [03:12<1:53:44, 1.75s/it, lr: 1.0e-04 loss: 7.673e-01]
my_first_lora_v2: 3%|2 | 111/4000 [03:13<1:53:10, 1.75s/it, lr: 1.0e-04 loss: 4.964e-01]
my_first_lora_v2: 3%|2 | 111/4000 [03:13<1:53:10, 1.75s/it, lr: 1.0e-04 loss: 4.964e-01]
my_first_lora_v2: 3%|2 | 112/4000 [03:16<1:53:42, 1.75s/it, lr: 1.0e-04 loss: 3.112e-01]
my_first_lora_v2: 3%|2 | 112/4000 [03:16<1:53:42, 1.75s/it, lr: 1.0e-04 loss: 3.112e-01]
my_first_lora_v2: 3%|2 | 113/4000 [03:17<1:53:08, 1.75s/it, lr: 1.0e-04 loss: 2.046e-01]
my_first_lora_v2: 3%|2 | 113/4000 [03:17<1:53:08, 1.75s/it, lr: 1.0e-04 loss: 2.046e-01]
my_first_lora_v2: 3%|2 | 114/4000 [03:20<1:53:44, 1.76s/it, lr: 1.0e-04 loss: 5.153e-01]
my_first_lora_v2: 3%|2 | 114/4000 [03:20<1:53:44, 1.76s/it, lr: 1.0e-04 loss: 5.153e-01]
my_first_lora_v2: 3%|2 | 115/4000 [03:21<1:53:11, 1.75s/it, lr: 1.0e-04 loss: 7.174e-01]
my_first_lora_v2: 3%|2 | 115/4000 [03:21<1:53:11, 1.75s/it, lr: 1.0e-04 loss: 7.174e-01]
my_first_lora_v2: 3%|2 | 116/4000 [03:23<1:53:47, 1.76s/it, lr: 1.0e-04 loss: 5.236e-01]
my_first_lora_v2: 3%|2 | 116/4000 [03:23<1:53:47, 1.76s/it, lr: 1.0e-04 loss: 5.236e-01]
my_first_lora_v2: 3%|2 | 117/4000 [03:26<1:54:22, 1.77s/it, lr: 1.0e-04 loss: 4.604e-01]
my_first_lora_v2: 3%|2 | 117/4000 [03:26<1:54:22, 1.77s/it, lr: 1.0e-04 loss: 4.604e-01]
my_first_lora_v2: 3%|2 | 118/4000 [03:29<1:54:56, 1.78s/it, lr: 1.0e-04 loss: 2.445e-01]
my_first_lora_v2: 3%|2 | 118/4000 [03:29<1:54:56, 1.78s/it, lr: 1.0e-04 loss: 2.445e-01]
my_first_lora_v2: 3%|2 | 119/4000 [03:32<1:55:29, 1.79s/it, lr: 1.0e-04 loss: 3.819e-01]
my_first_lora_v2: 3%|2 | 119/4000 [03:32<1:55:29, 1.79s/it, lr: 1.0e-04 loss: 3.819e-01]
my_first_lora_v2: 3%|3 | 120/4000 [03:33<1:55:08, 1.78s/it, lr: 1.0e-04 loss: 7.537e-01]
my_first_lora_v2: 3%|3 | 120/4000 [03:33<1:55:08, 1.78s/it, lr: 1.0e-04 loss: 7.537e-01]
my_first_lora_v2: 3%|3 | 121/4000 [03:34<1:54:36, 1.77s/it, lr: 1.0e-04 loss: 1.252e-01]
my_first_lora_v2: 3%|3 | 121/4000 [03:34<1:54:36, 1.77s/it, lr: 1.0e-04 loss: 1.252e-01]
my_first_lora_v2: 3%|3 | 122/4000 [03:37<1:55:09, 1.78s/it, lr: 1.0e-04 loss: 3.900e-01]
my_first_lora_v2: 3%|3 | 122/4000 [03:37<1:55:09, 1.78s/it, lr: 1.0e-04 loss: 3.900e-01]
my_first_lora_v2: 3%|3 | 123/4000 [03:40<1:55:42, 1.79s/it, lr: 1.0e-04 loss: 1.122e-01]
my_first_lora_v2: 3%|3 | 123/4000 [03:40<1:55:42, 1.79s/it, lr: 1.0e-04 loss: 1.122e-01]
my_first_lora_v2: 3%|3 | 124/4000 [03:43<1:56:14, 1.80s/it, lr: 1.0e-04 loss: 6.703e-01]
my_first_lora_v2: 3%|3 | 124/4000 [03:43<1:56:14, 1.80s/it, lr: 1.0e-04 loss: 6.703e-01]
my_first_lora_v2: 3%|3 | 125/4000 [03:45<1:56:45, 1.81s/it, lr: 1.0e-04 loss: 3.903e-01]
my_first_lora_v2: 3%|3 | 125/4000 [03:45<1:56:45, 1.81s/it, lr: 1.0e-04 loss: 3.903e-01]
my_first_lora_v2: 3%|3 | 126/4000 [03:48<1:57:09, 1.81s/it, lr: 1.0e-04 loss: 5.502e-01]
my_first_lora_v2: 3%|3 | 126/4000 [03:48<1:57:09, 1.81s/it, lr: 1.0e-04 loss: 5.502e-01]
my_first_lora_v2: 3%|3 | 127/4000 [03:51<1:57:41, 1.82s/it, lr: 1.0e-04 loss: 1.471e-01]
my_first_lora_v2: 3%|3 | 127/4000 [03:51<1:57:41, 1.82s/it, lr: 1.0e-04 loss: 1.471e-01]
my_first_lora_v2: 3%|3 | 128/4000 [03:52<1:57:08, 1.82s/it, lr: 1.0e-04 loss: 4.730e-01]
my_first_lora_v2: 3%|3 | 128/4000 [03:52<1:57:08, 1.82s/it, lr: 1.0e-04 loss: 4.730e-01]
my_first_lora_v2: 3%|3 | 129/4000 [03:53<1:56:35, 1.81s/it, lr: 1.0e-04 loss: 5.720e-01]
my_first_lora_v2: 3%|3 | 129/4000 [03:53<1:56:35, 1.81s/it, lr: 1.0e-04 loss: 5.720e-01]
my_first_lora_v2: 3%|3 | 130/4000 [03:55<1:56:58, 1.81s/it, lr: 1.0e-04 loss: 5.828e-01]
my_first_lora_v2: 3%|3 | 130/4000 [03:55<1:56:58, 1.81s/it, lr: 1.0e-04 loss: 5.828e-01]
my_first_lora_v2: 3%|3 | 131/4000 [03:56<1:56:26, 1.81s/it, lr: 1.0e-04 loss: 1.146e-01]
my_first_lora_v2: 3%|3 | 131/4000 [03:56<1:56:26, 1.81s/it, lr: 1.0e-04 loss: 1.146e-01]
my_first_lora_v2: 3%|3 | 132/4000 [03:57<1:55:54, 1.80s/it, lr: 1.0e-04 loss: 8.346e-01]
my_first_lora_v2: 3%|3 | 132/4000 [03:57<1:55:54, 1.80s/it, lr: 1.0e-04 loss: 8.346e-01]
my_first_lora_v2: 3%|3 | 133/4000 [04:00<1:56:18, 1.80s/it, lr: 1.0e-04 loss: 6.970e-01]
my_first_lora_v2: 3%|3 | 133/4000 [04:00<1:56:18, 1.80s/it, lr: 1.0e-04 loss: 6.970e-01]
my_first_lora_v2: 3%|3 | 134/4000 [04:03<1:56:52, 1.81s/it, lr: 1.0e-04 loss: 2.902e-01]
my_first_lora_v2: 3%|3 | 134/4000 [04:03<1:56:52, 1.81s/it, lr: 1.0e-04 loss: 2.902e-01]
my_first_lora_v2: 3%|3 | 135/4000 [04:03<1:56:21, 1.81s/it, lr: 1.0e-04 loss: 4.378e-01]
my_first_lora_v2: 3%|3 | 135/4000 [04:03<1:56:21, 1.81s/it, lr: 1.0e-04 loss: 4.378e-01]
my_first_lora_v2: 3%|3 | 136/4000 [04:04<1:55:51, 1.80s/it, lr: 1.0e-04 loss: 1.190e-01]
my_first_lora_v2: 3%|3 | 136/4000 [04:04<1:55:51, 1.80s/it, lr: 1.0e-04 loss: 1.190e-01]
my_first_lora_v2: 3%|3 | 137/4000 [04:05<1:55:20, 1.79s/it, lr: 1.0e-04 loss: 2.629e-01]
my_first_lora_v2: 3%|3 | 137/4000 [04:05<1:55:20, 1.79s/it, lr: 1.0e-04 loss: 2.629e-01]
my_first_lora_v2: 3%|3 | 138/4000 [04:06<1:54:50, 1.78s/it, lr: 1.0e-04 loss: 5.518e-01]
my_first_lora_v2: 3%|3 | 138/4000 [04:06<1:54:50, 1.78s/it, lr: 1.0e-04 loss: 5.518e-01]
my_first_lora_v2: 3%|3 | 139/4000 [04:06<1:54:19, 1.78s/it, lr: 1.0e-04 loss: 6.710e-01]
my_first_lora_v2: 3%|3 | 139/4000 [04:06<1:54:19, 1.78s/it, lr: 1.0e-04 loss: 6.710e-01]
my_first_lora_v2: 4%|3 | 140/4000 [04:07<1:53:51, 1.77s/it, lr: 1.0e-04 loss: 6.880e-01]
my_first_lora_v2: 4%|3 | 140/4000 [04:07<1:53:51, 1.77s/it, lr: 1.0e-04 loss: 6.880e-01]
my_first_lora_v2: 4%|3 | 141/4000 [04:10<1:54:06, 1.77s/it, lr: 1.0e-04 loss: 6.391e-01]
my_first_lora_v2: 4%|3 | 141/4000 [04:10<1:54:06, 1.77s/it, lr: 1.0e-04 loss: 6.391e-01]
my_first_lora_v2: 4%|3 | 142/4000 [04:13<1:54:35, 1.78s/it, lr: 1.0e-04 loss: 1.871e-01]
my_first_lora_v2: 4%|3 | 142/4000 [04:13<1:54:35, 1.78s/it, lr: 1.0e-04 loss: 1.871e-01]
my_first_lora_v2: 4%|3 | 143/4000 [04:15<1:55:03, 1.79s/it, lr: 1.0e-04 loss: 9.601e-02]
my_first_lora_v2: 4%|3 | 143/4000 [04:15<1:55:03, 1.79s/it, lr: 1.0e-04 loss: 9.601e-02]
my_first_lora_v2: 4%|3 | 144/4000 [04:16<1:54:35, 1.78s/it, lr: 1.0e-04 loss: 4.770e-01]
my_first_lora_v2: 4%|3 | 144/4000 [04:16<1:54:35, 1.78s/it, lr: 1.0e-04 loss: 4.770e-01]
my_first_lora_v2: 4%|3 | 145/4000 [04:17<1:54:08, 1.78s/it, lr: 1.0e-04 loss: 6.003e-01]
my_first_lora_v2: 4%|3 | 145/4000 [04:17<1:54:08, 1.78s/it, lr: 1.0e-04 loss: 6.003e-01]
my_first_lora_v2: 4%|3 | 146/4000 [04:20<1:54:35, 1.78s/it, lr: 1.0e-04 loss: 7.021e-01]
my_first_lora_v2: 4%|3 | 146/4000 [04:20<1:54:35, 1.78s/it, lr: 1.0e-04 loss: 7.021e-01]
my_first_lora_v2: 4%|3 | 147/4000 [04:21<1:54:08, 1.78s/it, lr: 1.0e-04 loss: 4.953e-01]
my_first_lora_v2: 4%|3 | 147/4000 [04:21<1:54:08, 1.78s/it, lr: 1.0e-04 loss: 4.953e-01]
my_first_lora_v2: 4%|3 | 148/4000 [04:22<1:53:48, 1.77s/it, lr: 1.0e-04 loss: 4.454e-01]
my_first_lora_v2: 4%|3 | 148/4000 [04:22<1:53:48, 1.77s/it, lr: 1.0e-04 loss: 4.454e-01]
my_first_lora_v2: 4%|3 | 149/4000 [04:23<1:53:21, 1.77s/it, lr: 1.0e-04 loss: 5.428e-01]
my_first_lora_v2: 4%|3 | 149/4000 [04:23<1:53:21, 1.77s/it, lr: 1.0e-04 loss: 5.428e-01]
my_first_lora_v2: 4%|3 | 150/4000 [04:25<1:53:41, 1.77s/it, lr: 1.0e-04 loss: 7.340e-01]
my_first_lora_v2: 4%|3 | 150/4000 [04:25<1:53:41, 1.77s/it, lr: 1.0e-04 loss: 7.340e-01]
my_first_lora_v2: 4%|3 | 151/4000 [04:26<1:53:16, 1.77s/it, lr: 1.0e-04 loss: 2.532e-01]
my_first_lora_v2: 4%|3 | 151/4000 [04:26<1:53:16, 1.77s/it, lr: 1.0e-04 loss: 2.532e-01]
my_first_lora_v2: 4%|3 | 152/4000 [04:29<1:53:43, 1.77s/it, lr: 1.0e-04 loss: 3.381e-01]
my_first_lora_v2: 4%|3 | 152/4000 [04:29<1:53:43, 1.77s/it, lr: 1.0e-04 loss: 3.381e-01]
my_first_lora_v2: 4%|3 | 153/4000 [04:32<1:54:03, 1.78s/it, lr: 1.0e-04 loss: 3.348e-01]
my_first_lora_v2: 4%|3 | 153/4000 [04:32<1:54:03, 1.78s/it, lr: 1.0e-04 loss: 3.348e-01]
my_first_lora_v2: 4%|3 | 154/4000 [04:33<1:53:38, 1.77s/it, lr: 1.0e-04 loss: 5.339e-01]
my_first_lora_v2: 4%|3 | 154/4000 [04:33<1:53:38, 1.77s/it, lr: 1.0e-04 loss: 5.339e-01]
my_first_lora_v2: 4%|3 | 155/4000 [04:35<1:54:03, 1.78s/it, lr: 1.0e-04 loss: 5.875e-01]
my_first_lora_v2: 4%|3 | 155/4000 [04:35<1:54:03, 1.78s/it, lr: 1.0e-04 loss: 5.875e-01]
my_first_lora_v2: 4%|3 | 156/4000 [04:38<1:54:27, 1.79s/it, lr: 1.0e-04 loss: 4.719e-01]
my_first_lora_v2: 4%|3 | 156/4000 [04:38<1:54:27, 1.79s/it, lr: 1.0e-04 loss: 4.719e-01]
my_first_lora_v2: 4%|3 | 157/4000 [04:41<1:54:49, 1.79s/it, lr: 1.0e-04 loss: 8.455e-01]
my_first_lora_v2: 4%|3 | 157/4000 [04:41<1:54:49, 1.79s/it, lr: 1.0e-04 loss: 8.455e-01]
my_first_lora_v2: 4%|3 | 158/4000 [04:42<1:54:23, 1.79s/it, lr: 1.0e-04 loss: 8.509e-01]
my_first_lora_v2: 4%|3 | 158/4000 [04:42<1:54:23, 1.79s/it, lr: 1.0e-04 loss: 8.509e-01]
my_first_lora_v2: 4%|3 | 159/4000 [04:43<1:53:58, 1.78s/it, lr: 1.0e-04 loss: 3.819e-01]
my_first_lora_v2: 4%|3 | 159/4000 [04:43<1:53:58, 1.78s/it, lr: 1.0e-04 loss: 3.819e-01]
my_first_lora_v2: 4%|4 | 160/4000 [04:45<1:54:18, 1.79s/it, lr: 1.0e-04 loss: 4.979e-01]
my_first_lora_v2: 4%|4 | 160/4000 [04:45<1:54:18, 1.79s/it, lr: 1.0e-04 loss: 4.979e-01]
my_first_lora_v2: 4%|4 | 161/4000 [04:48<1:54:38, 1.79s/it, lr: 1.0e-04 loss: 6.177e-01]
my_first_lora_v2: 4%|4 | 161/4000 [04:48<1:54:38, 1.79s/it, lr: 1.0e-04 loss: 6.177e-01]
my_first_lora_v2: 4%|4 | 162/4000 [04:49<1:54:13, 1.79s/it, lr: 1.0e-04 loss: 7.888e-02]
my_first_lora_v2: 4%|4 | 162/4000 [04:49<1:54:13, 1.79s/it, lr: 1.0e-04 loss: 7.888e-02]
my_first_lora_v2: 4%|4 | 163/4000 [04:50<1:53:48, 1.78s/it, lr: 1.0e-04 loss: 5.598e-01]
my_first_lora_v2: 4%|4 | 163/4000 [04:50<1:53:48, 1.78s/it, lr: 1.0e-04 loss: 5.598e-01]
my_first_lora_v2: 4%|4 | 164/4000 [04:50<1:53:23, 1.77s/it, lr: 1.0e-04 loss: 6.614e-01]
my_first_lora_v2: 4%|4 | 164/4000 [04:50<1:53:23, 1.77s/it, lr: 1.0e-04 loss: 6.614e-01]
my_first_lora_v2: 4%|4 | 165/4000 [04:51<1:52:59, 1.77s/it, lr: 1.0e-04 loss: 5.317e-01]
my_first_lora_v2: 4%|4 | 165/4000 [04:51<1:52:59, 1.77s/it, lr: 1.0e-04 loss: 5.317e-01]
my_first_lora_v2: 4%|4 | 166/4000 [04:52<1:52:34, 1.76s/it, lr: 1.0e-04 loss: 6.562e-01]
my_first_lora_v2: 4%|4 | 166/4000 [04:52<1:52:34, 1.76s/it, lr: 1.0e-04 loss: 6.562e-01]
my_first_lora_v2: 4%|4 | 167/4000 [04:53<1:52:12, 1.76s/it, lr: 1.0e-04 loss: 2.489e-01]
my_first_lora_v2: 4%|4 | 167/4000 [04:53<1:52:12, 1.76s/it, lr: 1.0e-04 loss: 2.489e-01]
my_first_lora_v2: 4%|4 | 168/4000 [04:54<1:51:47, 1.75s/it, lr: 1.0e-04 loss: 7.603e-01]
my_first_lora_v2: 4%|4 | 168/4000 [04:54<1:51:47, 1.75s/it, lr: 1.0e-04 loss: 7.603e-01]
my_first_lora_v2: 4%|4 | 169/4000 [04:56<1:52:00, 1.75s/it, lr: 1.0e-04 loss: 3.071e-01]
my_first_lora_v2: 4%|4 | 169/4000 [04:56<1:52:00, 1.75s/it, lr: 1.0e-04 loss: 3.071e-01]
my_first_lora_v2: 4%|4 | 170/4000 [04:59<1:52:24, 1.76s/it, lr: 1.0e-04 loss: 5.580e-01]
my_first_lora_v2: 4%|4 | 170/4000 [04:59<1:52:24, 1.76s/it, lr: 1.0e-04 loss: 5.580e-01]
my_first_lora_v2: 4%|4 | 171/4000 [05:02<1:52:43, 1.77s/it, lr: 1.0e-04 loss: 6.803e-01]
my_first_lora_v2: 4%|4 | 171/4000 [05:02<1:52:43, 1.77s/it, lr: 1.0e-04 loss: 6.803e-01]
my_first_lora_v2: 4%|4 | 172/4000 [05:02<1:52:20, 1.76s/it, lr: 1.0e-04 loss: 7.245e-01]
my_first_lora_v2: 4%|4 | 172/4000 [05:02<1:52:20, 1.76s/it, lr: 1.0e-04 loss: 7.245e-01]
my_first_lora_v2: 4%|4 | 173/4000 [05:03<1:51:58, 1.76s/it, lr: 1.0e-04 loss: 6.004e-01]
my_first_lora_v2: 4%|4 | 173/4000 [05:03<1:51:58, 1.76s/it, lr: 1.0e-04 loss: 6.004e-01]
my_first_lora_v2: 4%|4 | 174/4000 [05:06<1:52:25, 1.76s/it, lr: 1.0e-04 loss: 1.392e-01]
my_first_lora_v2: 4%|4 | 174/4000 [05:06<1:52:25, 1.76s/it, lr: 1.0e-04 loss: 1.392e-01]
my_first_lora_v2: 4%|4 | 175/4000 [05:09<1:52:49, 1.77s/it, lr: 1.0e-04 loss: 6.765e-01]
my_first_lora_v2: 4%|4 | 175/4000 [05:09<1:52:49, 1.77s/it, lr: 1.0e-04 loss: 6.765e-01]
my_first_lora_v2: 4%|4 | 176/4000 [05:10<1:52:26, 1.76s/it, lr: 1.0e-04 loss: 3.577e-01]
my_first_lora_v2: 4%|4 | 176/4000 [05:10<1:52:26, 1.76s/it, lr: 1.0e-04 loss: 3.577e-01]
my_first_lora_v2: 4%|4 | 177/4000 [05:13<1:52:50, 1.77s/it, lr: 1.0e-04 loss: 9.344e-02]
my_first_lora_v2: 4%|4 | 177/4000 [05:13<1:52:50, 1.77s/it, lr: 1.0e-04 loss: 9.344e-02]
my_first_lora_v2: 4%|4 | 178/4000 [05:14<1:52:38, 1.77s/it, lr: 1.0e-04 loss: 8.048e-01]
my_first_lora_v2: 4%|4 | 178/4000 [05:14<1:52:38, 1.77s/it, lr: 1.0e-04 loss: 8.048e-01]
my_first_lora_v2: 4%|4 | 179/4000 [05:17<1:53:00, 1.77s/it, lr: 1.0e-04 loss: 6.981e-01]
my_first_lora_v2: 4%|4 | 179/4000 [05:17<1:53:00, 1.77s/it, lr: 1.0e-04 loss: 6.981e-01]
my_first_lora_v2: 4%|4 | 180/4000 [05:18<1:52:37, 1.77s/it, lr: 1.0e-04 loss: 4.863e-01]
my_first_lora_v2: 4%|4 | 180/4000 [05:18<1:52:37, 1.77s/it, lr: 1.0e-04 loss: 4.863e-01]
my_first_lora_v2: 5%|4 | 181/4000 [05:19<1:52:15, 1.76s/it, lr: 1.0e-04 loss: 2.004e-01]
my_first_lora_v2: 5%|4 | 181/4000 [05:19<1:52:15, 1.76s/it, lr: 1.0e-04 loss: 2.004e-01]
my_first_lora_v2: 5%|4 | 182/4000 [05:22<1:52:37, 1.77s/it, lr: 1.0e-04 loss: 3.446e-01]
my_first_lora_v2: 5%|4 | 182/4000 [05:22<1:52:37, 1.77s/it, lr: 1.0e-04 loss: 3.446e-01]
my_first_lora_v2: 5%|4 | 183/4000 [05:22<1:52:15, 1.76s/it, lr: 1.0e-04 loss: 1.988e-01]
my_first_lora_v2: 5%|4 | 183/4000 [05:22<1:52:15, 1.76s/it, lr: 1.0e-04 loss: 1.988e-01]
my_first_lora_v2: 5%|4 | 184/4000 [05:23<1:51:53, 1.76s/it, lr: 1.0e-04 loss: 6.912e-01]
my_first_lora_v2: 5%|4 | 184/4000 [05:23<1:51:53, 1.76s/it, lr: 1.0e-04 loss: 6.912e-01]
my_first_lora_v2: 5%|4 | 185/4000 [05:26<1:52:10, 1.76s/it, lr: 1.0e-04 loss: 5.821e-01]
my_first_lora_v2: 5%|4 | 185/4000 [05:26<1:52:10, 1.76s/it, lr: 1.0e-04 loss: 5.821e-01]
my_first_lora_v2: 5%|4 | 186/4000 [05:29<1:52:28, 1.77s/it, lr: 1.0e-04 loss: 6.235e-01]
my_first_lora_v2: 5%|4 | 186/4000 [05:29<1:52:28, 1.77s/it, lr: 1.0e-04 loss: 6.235e-01]
my_first_lora_v2: 5%|4 | 187/4000 [05:31<1:52:49, 1.78s/it, lr: 1.0e-04 loss: 4.737e-01]
my_first_lora_v2: 5%|4 | 187/4000 [05:31<1:52:49, 1.78s/it, lr: 1.0e-04 loss: 4.737e-01]
my_first_lora_v2: 5%|4 | 188/4000 [05:32<1:52:28, 1.77s/it, lr: 1.0e-04 loss: 3.959e-01]
my_first_lora_v2: 5%|4 | 188/4000 [05:32<1:52:28, 1.77s/it, lr: 1.0e-04 loss: 3.959e-01]
my_first_lora_v2: 5%|4 | 189/4000 [05:35<1:52:53, 1.78s/it, lr: 1.0e-04 loss: 3.151e-01]
my_first_lora_v2: 5%|4 | 189/4000 [05:35<1:52:53, 1.78s/it, lr: 1.0e-04 loss: 3.151e-01]
my_first_lora_v2: 5%|4 | 190/4000 [05:36<1:52:31, 1.77s/it, lr: 1.0e-04 loss: 3.776e-01]
my_first_lora_v2: 5%|4 | 190/4000 [05:36<1:52:31, 1.77s/it, lr: 1.0e-04 loss: 3.776e-01]
my_first_lora_v2: 5%|4 | 191/4000 [05:37<1:52:10, 1.77s/it, lr: 1.0e-04 loss: 1.136e-01]
my_first_lora_v2: 5%|4 | 191/4000 [05:37<1:52:10, 1.77s/it, lr: 1.0e-04 loss: 1.136e-01]
my_first_lora_v2: 5%|4 | 192/4000 [05:40<1:52:30, 1.77s/it, lr: 1.0e-04 loss: 1.650e-01]
my_first_lora_v2: 5%|4 | 192/4000 [05:40<1:52:30, 1.77s/it, lr: 1.0e-04 loss: 1.650e-01]
my_first_lora_v2: 5%|4 | 193/4000 [05:41<1:52:10, 1.77s/it, lr: 1.0e-04 loss: 6.289e-01]
my_first_lora_v2: 5%|4 | 193/4000 [05:41<1:52:10, 1.77s/it, lr: 1.0e-04 loss: 6.289e-01]
my_first_lora_v2: 5%|4 | 194/4000 [05:44<1:52:29, 1.77s/it, lr: 1.0e-04 loss: 5.338e-01]
my_first_lora_v2: 5%|4 | 194/4000 [05:44<1:52:29, 1.77s/it, lr: 1.0e-04 loss: 5.338e-01]
my_first_lora_v2: 5%|4 | 195/4000 [05:46<1:52:40, 1.78s/it, lr: 1.0e-04 loss: 2.995e-01]
my_first_lora_v2: 5%|4 | 195/4000 [05:46<1:52:40, 1.78s/it, lr: 1.0e-04 loss: 2.995e-01]
my_first_lora_v2: 5%|4 | 196/4000 [05:49<1:52:59, 1.78s/it, lr: 1.0e-04 loss: 5.176e-01]
my_first_lora_v2: 5%|4 | 196/4000 [05:49<1:52:59, 1.78s/it, lr: 1.0e-04 loss: 5.176e-01]
my_first_lora_v2: 5%|4 | 197/4000 [05:52<1:53:15, 1.79s/it, lr: 1.0e-04 loss: 6.875e-01]
my_first_lora_v2: 5%|4 | 197/4000 [05:52<1:53:15, 1.79s/it, lr: 1.0e-04 loss: 6.875e-01]
my_first_lora_v2: 5%|4 | 198/4000 [05:54<1:53:31, 1.79s/it, lr: 1.0e-04 loss: 6.925e-01]
my_first_lora_v2: 5%|4 | 198/4000 [05:54<1:53:31, 1.79s/it, lr: 1.0e-04 loss: 6.925e-01]
my_first_lora_v2: 5%|4 | 199/4000 [05:55<1:53:10, 1.79s/it, lr: 1.0e-04 loss: 7.325e-01]
my_first_lora_v2: 5%|4 | 199/4000 [05:55<1:53:10, 1.79s/it, lr: 1.0e-04 loss: 7.325e-01]
my_first_lora_v2: 5%|5 | 200/4000 [05:56<1:52:48, 1.78s/it, lr: 1.0e-04 loss: 9.407e-02]
my_first_lora_v2: 5%|5 | 200/4000 [05:56<1:52:48, 1.78s/it, lr: 1.0e-04 loss: 9.407e-02]
my_first_lora_v2: 5%|5 | 201/4000 [05:57<1:52:28, 1.78s/it, lr: 1.0e-04 loss: 3.430e-01]
my_first_lora_v2: 5%|5 | 201/4000 [05:57<1:52:28, 1.78s/it, lr: 1.0e-04 loss: 3.430e-01]
my_first_lora_v2: 5%|5 | 202/4000 [05:59<1:52:40, 1.78s/it, lr: 1.0e-04 loss: 6.728e-01]
my_first_lora_v2: 5%|5 | 202/4000 [05:59<1:52:40, 1.78s/it, lr: 1.0e-04 loss: 6.728e-01]
my_first_lora_v2: 5%|5 | 203/4000 [06:00<1:52:21, 1.78s/it, lr: 1.0e-04 loss: 1.467e-01]
my_first_lora_v2: 5%|5 | 203/4000 [06:00<1:52:21, 1.78s/it, lr: 1.0e-04 loss: 1.467e-01]
my_first_lora_v2: 5%|5 | 204/4000 [06:03<1:52:35, 1.78s/it, lr: 1.0e-04 loss: 5.813e-01]
my_first_lora_v2: 5%|5 | 204/4000 [06:03<1:52:35, 1.78s/it, lr: 1.0e-04 loss: 5.813e-01]
my_first_lora_v2: 5%|5 | 205/4000 [06:05<1:52:53, 1.78s/it, lr: 1.0e-04 loss: 2.314e-01]
my_first_lora_v2: 5%|5 | 205/4000 [06:05<1:52:53, 1.78s/it, lr: 1.0e-04 loss: 2.314e-01]
my_first_lora_v2: 5%|5 | 206/4000 [06:06<1:52:32, 1.78s/it, lr: 1.0e-04 loss: 1.661e-01]
my_first_lora_v2: 5%|5 | 206/4000 [06:06<1:52:32, 1.78s/it, lr: 1.0e-04 loss: 1.661e-01]
my_first_lora_v2: 5%|5 | 207/4000 [06:09<1:52:52, 1.79s/it, lr: 1.0e-04 loss: 5.142e-01]
my_first_lora_v2: 5%|5 | 207/4000 [06:09<1:52:52, 1.79s/it, lr: 1.0e-04 loss: 5.142e-01]
my_first_lora_v2: 5%|5 | 208/4000 [06:10<1:52:32, 1.78s/it, lr: 1.0e-04 loss: 7.645e-01]
my_first_lora_v2: 5%|5 | 208/4000 [06:10<1:52:32, 1.78s/it, lr: 1.0e-04 loss: 7.645e-01]
my_first_lora_v2: 5%|5 | 209/4000 [06:11<1:52:12, 1.78s/it, lr: 1.0e-04 loss: 4.760e-01]
my_first_lora_v2: 5%|5 | 209/4000 [06:11<1:52:12, 1.78s/it, lr: 1.0e-04 loss: 4.760e-01]
my_first_lora_v2: 5%|5 | 210/4000 [06:14<1:52:30, 1.78s/it, lr: 1.0e-04 loss: 6.720e-01]
my_first_lora_v2: 5%|5 | 210/4000 [06:14<1:52:30, 1.78s/it, lr: 1.0e-04 loss: 6.720e-01]
my_first_lora_v2: 5%|5 | 211/4000 [06:14<1:52:10, 1.78s/it, lr: 1.0e-04 loss: 2.819e-01]
my_first_lora_v2: 5%|5 | 211/4000 [06:14<1:52:10, 1.78s/it, lr: 1.0e-04 loss: 2.819e-01]
my_first_lora_v2: 5%|5 | 212/4000 [06:15<1:51:51, 1.77s/it, lr: 1.0e-04 loss: 4.632e-01]
my_first_lora_v2: 5%|5 | 212/4000 [06:15<1:51:51, 1.77s/it, lr: 1.0e-04 loss: 4.632e-01]
my_first_lora_v2: 5%|5 | 213/4000 [06:17<1:52:00, 1.77s/it, lr: 1.0e-04 loss: 6.811e-02]
my_first_lora_v2: 5%|5 | 213/4000 [06:17<1:52:00, 1.77s/it, lr: 1.0e-04 loss: 6.811e-02]
my_first_lora_v2: 5%|5 | 214/4000 [06:20<1:52:13, 1.78s/it, lr: 1.0e-04 loss: 7.159e-01]
my_first_lora_v2: 5%|5 | 214/4000 [06:20<1:52:13, 1.78s/it, lr: 1.0e-04 loss: 7.159e-01]
my_first_lora_v2: 5%|5 | 215/4000 [06:21<1:51:54, 1.77s/it, lr: 1.0e-04 loss: 7.549e-01]
my_first_lora_v2: 5%|5 | 215/4000 [06:21<1:51:54, 1.77s/it, lr: 1.0e-04 loss: 7.549e-01]
my_first_lora_v2: 5%|5 | 216/4000 [06:22<1:51:40, 1.77s/it, lr: 1.0e-04 loss: 7.712e-01]
my_first_lora_v2: 5%|5 | 216/4000 [06:22<1:51:40, 1.77s/it, lr: 1.0e-04 loss: 7.712e-01]
my_first_lora_v2: 5%|5 | 217/4000 [06:25<1:51:53, 1.77s/it, lr: 1.0e-04 loss: 1.858e-01]
my_first_lora_v2: 5%|5 | 217/4000 [06:25<1:51:53, 1.77s/it, lr: 1.0e-04 loss: 1.858e-01]
my_first_lora_v2: 5%|5 | 218/4000 [06:25<1:51:34, 1.77s/it, lr: 1.0e-04 loss: 6.213e-01]
my_first_lora_v2: 5%|5 | 218/4000 [06:25<1:51:34, 1.77s/it, lr: 1.0e-04 loss: 6.213e-01]
my_first_lora_v2: 5%|5 | 219/4000 [06:28<1:51:48, 1.77s/it, lr: 1.0e-04 loss: 3.885e-01]
my_first_lora_v2: 5%|5 | 219/4000 [06:28<1:51:48, 1.77s/it, lr: 1.0e-04 loss: 3.885e-01]
my_first_lora_v2: 6%|5 | 220/4000 [06:31<1:52:06, 1.78s/it, lr: 1.0e-04 loss: 2.907e-01]
my_first_lora_v2: 6%|5 | 220/4000 [06:31<1:52:06, 1.78s/it, lr: 1.0e-04 loss: 2.907e-01]
my_first_lora_v2: 6%|5 | 221/4000 [06:32<1:51:48, 1.78s/it, lr: 1.0e-04 loss: 1.222e-01]
my_first_lora_v2: 6%|5 | 221/4000 [06:32<1:51:48, 1.78s/it, lr: 1.0e-04 loss: 1.222e-01]
my_first_lora_v2: 6%|5 | 222/4000 [06:33<1:51:38, 1.77s/it, lr: 1.0e-04 loss: 1.550e-01]
my_first_lora_v2: 6%|5 | 222/4000 [06:33<1:51:38, 1.77s/it, lr: 1.0e-04 loss: 1.550e-01]
my_first_lora_v2: 6%|5 | 223/4000 [06:34<1:51:20, 1.77s/it, lr: 1.0e-04 loss: 4.487e-01]
my_first_lora_v2: 6%|5 | 223/4000 [06:34<1:51:20, 1.77s/it, lr: 1.0e-04 loss: 4.487e-01]
my_first_lora_v2: 6%|5 | 224/4000 [06:35<1:51:02, 1.76s/it, lr: 1.0e-04 loss: 1.593e-01]
my_first_lora_v2: 6%|5 | 224/4000 [06:35<1:51:02, 1.76s/it, lr: 1.0e-04 loss: 1.593e-01]
my_first_lora_v2: 6%|5 | 225/4000 [06:38<1:51:19, 1.77s/it, lr: 1.0e-04 loss: 2.858e-01]
my_first_lora_v2: 6%|5 | 225/4000 [06:38<1:51:19, 1.77s/it, lr: 1.0e-04 loss: 2.858e-01]
my_first_lora_v2: 6%|5 | 226/4000 [06:38<1:51:01, 1.76s/it, lr: 1.0e-04 loss: 7.208e-01]
my_first_lora_v2: 6%|5 | 226/4000 [06:38<1:51:01, 1.76s/it, lr: 1.0e-04 loss: 7.208e-01]
my_first_lora_v2: 6%|5 | 227/4000 [06:39<1:50:43, 1.76s/it, lr: 1.0e-04 loss: 5.138e-01]
my_first_lora_v2: 6%|5 | 227/4000 [06:39<1:50:43, 1.76s/it, lr: 1.0e-04 loss: 5.138e-01]
my_first_lora_v2: 6%|5 | 228/4000 [06:40<1:50:26, 1.76s/it, lr: 1.0e-04 loss: 1.606e-01]
my_first_lora_v2: 6%|5 | 228/4000 [06:40<1:50:26, 1.76s/it, lr: 1.0e-04 loss: 1.606e-01]
my_first_lora_v2: 6%|5 | 229/4000 [06:43<1:50:45, 1.76s/it, lr: 1.0e-04 loss: 2.377e-01]
my_first_lora_v2: 6%|5 | 229/4000 [06:43<1:50:45, 1.76s/it, lr: 1.0e-04 loss: 2.377e-01]
my_first_lora_v2: 6%|5 | 230/4000 [06:44<1:50:28, 1.76s/it, lr: 1.0e-04 loss: 3.733e-01]
my_first_lora_v2: 6%|5 | 230/4000 [06:44<1:50:28, 1.76s/it, lr: 1.0e-04 loss: 3.733e-01]
my_first_lora_v2: 6%|5 | 231/4000 [06:45<1:50:10, 1.75s/it, lr: 1.0e-04 loss: 1.088e-01]
my_first_lora_v2: 6%|5 | 231/4000 [06:45<1:50:10, 1.75s/it, lr: 1.0e-04 loss: 1.088e-01]
my_first_lora_v2: 6%|5 | 232/4000 [06:48<1:50:27, 1.76s/it, lr: 1.0e-04 loss: 4.734e-01]
my_first_lora_v2: 6%|5 | 232/4000 [06:48<1:50:27, 1.76s/it, lr: 1.0e-04 loss: 4.734e-01]
my_first_lora_v2: 6%|5 | 233/4000 [06:48<1:50:09, 1.75s/it, lr: 1.0e-04 loss: 6.274e-01]
my_first_lora_v2: 6%|5 | 233/4000 [06:48<1:50:09, 1.75s/it, lr: 1.0e-04 loss: 6.274e-01]
my_first_lora_v2: 6%|5 | 234/4000 [06:49<1:49:51, 1.75s/it, lr: 1.0e-04 loss: 4.647e-01]
my_first_lora_v2: 6%|5 | 234/4000 [06:49<1:49:51, 1.75s/it, lr: 1.0e-04 loss: 4.647e-01]
my_first_lora_v2: 6%|5 | 235/4000 [06:52<1:50:08, 1.76s/it, lr: 1.0e-04 loss: 3.035e-01]
my_first_lora_v2: 6%|5 | 235/4000 [06:52<1:50:08, 1.76s/it, lr: 1.0e-04 loss: 3.035e-01]
my_first_lora_v2: 6%|5 | 236/4000 [06:53<1:49:51, 1.75s/it, lr: 1.0e-04 loss: 4.450e-01]
my_first_lora_v2: 6%|5 | 236/4000 [06:53<1:49:51, 1.75s/it, lr: 1.0e-04 loss: 4.450e-01]
my_first_lora_v2: 6%|5 | 237/4000 [06:56<1:50:07, 1.76s/it, lr: 1.0e-04 loss: 1.324e-01]
my_first_lora_v2: 6%|5 | 237/4000 [06:56<1:50:07, 1.76s/it, lr: 1.0e-04 loss: 1.324e-01]
my_first_lora_v2: 6%|5 | 238/4000 [06:59<1:50:24, 1.76s/it, lr: 1.0e-04 loss: 6.416e-01]
my_first_lora_v2: 6%|5 | 238/4000 [06:59<1:50:24, 1.76s/it, lr: 1.0e-04 loss: 6.416e-01]
my_first_lora_v2: 6%|5 | 239/4000 [07:00<1:50:10, 1.76s/it, lr: 1.0e-04 loss: 1.537e-01]
my_first_lora_v2: 6%|5 | 239/4000 [07:00<1:50:10, 1.76s/it, lr: 1.0e-04 loss: 1.537e-01]
my_first_lora_v2: 6%|6 | 240/4000 [07:02<1:50:26, 1.76s/it, lr: 1.0e-04 loss: 6.913e-01]
my_first_lora_v2: 6%|6 | 240/4000 [07:02<1:50:26, 1.76s/it, lr: 1.0e-04 loss: 6.913e-01]
my_first_lora_v2: 6%|6 | 241/4000 [07:03<1:50:10, 1.76s/it, lr: 1.0e-04 loss: 7.716e-01]
my_first_lora_v2: 6%|6 | 241/4000 [07:03<1:50:10, 1.76s/it, lr: 1.0e-04 loss: 7.716e-01]
my_first_lora_v2: 6%|6 | 242/4000 [07:06<1:50:26, 1.76s/it, lr: 1.0e-04 loss: 4.719e-01]
my_first_lora_v2: 6%|6 | 242/4000 [07:06<1:50:26, 1.76s/it, lr: 1.0e-04 loss: 4.719e-01]
my_first_lora_v2: 6%|6 | 243/4000 [07:07<1:50:14, 1.76s/it, lr: 1.0e-04 loss: 3.231e-01]
my_first_lora_v2: 6%|6 | 243/4000 [07:07<1:50:14, 1.76s/it, lr: 1.0e-04 loss: 3.231e-01]
my_first_lora_v2: 6%|6 | 244/4000 [07:10<1:50:29, 1.77s/it, lr: 1.0e-04 loss: 3.154e-01]
my_first_lora_v2: 6%|6 | 244/4000 [07:10<1:50:29, 1.77s/it, lr: 1.0e-04 loss: 3.154e-01]
my_first_lora_v2: 6%|6 | 245/4000 [07:13<1:50:45, 1.77s/it, lr: 1.0e-04 loss: 2.408e-01]
my_first_lora_v2: 6%|6 | 245/4000 [07:13<1:50:45, 1.77s/it, lr: 1.0e-04 loss: 2.408e-01]
my_first_lora_v2: 6%|6 | 246/4000 [07:16<1:50:58, 1.77s/it, lr: 1.0e-04 loss: 4.193e-01]
my_first_lora_v2: 6%|6 | 246/4000 [07:16<1:50:58, 1.77s/it, lr: 1.0e-04 loss: 4.193e-01]
my_first_lora_v2: 6%|6 | 247/4000 [07:17<1:50:41, 1.77s/it, lr: 1.0e-04 loss: 7.096e-01]
my_first_lora_v2: 6%|6 | 247/4000 [07:17<1:50:41, 1.77s/it, lr: 1.0e-04 loss: 7.096e-01]
my_first_lora_v2: 6%|6 | 248/4000 [07:19<1:50:56, 1.77s/it, lr: 1.0e-04 loss: 3.405e-01]
my_first_lora_v2: 6%|6 | 248/4000 [07:19<1:50:56, 1.77s/it, lr: 1.0e-04 loss: 3.405e-01]
my_first_lora_v2: 6%|6 | 249/4000 [07:20<1:50:40, 1.77s/it, lr: 1.0e-04 loss: 3.445e-01]
my_first_lora_v2: 6%|6 | 249/4000 [07:20<1:50:40, 1.77s/it, lr: 1.0e-04 loss: 3.445e-01] |
| Saving at step 250 |
| Saved checkpoint to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v2/my_first_lora_v2_000000250.safetensors |
| Saved optimizer to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v2/optimizer.pt |
| Unloading assistant lora |
|
|
|
|
|
Generating Images: 0%| | 0/3 [00:00<?, ?it/s]
Generating Images: 0%| | 0/3 [00:00<?, ?it/s][A[A |
|
|
|
Generating Images: 33%|###3 | 1/3 [00:07<00:15, 7.78s/it]
Generating Images: 33%|###3 | 1/3 [00:07<00:15, 7.78s/it][A[A |
|
|
|
Generating Images: 67%|######6 | 2/3 [00:15<00:07, 7.75s/it]
Generating Images: 67%|######6 | 2/3 [00:15<00:07, 7.75s/it][A[A |
|
|
|
Generating Images: 100%|##########| 3/3 [00:23<00:00, 7.71s/it]
Generating Images: 100%|##########| 3/3 [00:23<00:00, 7.71s/it][A[A |
|
|
|
[A[ALoading assistant lora |
|
my_first_lora_v2: 6%|6 | 250/4000 [07:21<1:50:27, 1.77s/it, lr: 1.0e-04 loss: 7.953e-01]
my_first_lora_v2: 6%|6 | 250/4000 [07:21<1:50:27, 1.77s/it, lr: 1.0e-04 loss: 7.953e-01]
my_first_lora_v2: 6%|6 | 251/4000 [07:22<1:50:10, 1.76s/it, lr: 1.0e-04 loss: 5.026e-01]
my_first_lora_v2: 6%|6 | 251/4000 [07:22<1:50:10, 1.76s/it, lr: 1.0e-04 loss: 5.026e-01]
my_first_lora_v2: 6%|6 | 252/4000 [07:23<1:49:54, 1.76s/it, lr: 1.0e-04 loss: 1.944e-01]
my_first_lora_v2: 6%|6 | 252/4000 [07:23<1:49:54, 1.76s/it, lr: 1.0e-04 loss: 1.944e-01]
my_first_lora_v2: 6%|6 | 253/4000 [07:25<1:50:01, 1.76s/it, lr: 1.0e-04 loss: 2.064e-01]
my_first_lora_v2: 6%|6 | 253/4000 [07:25<1:50:01, 1.76s/it, lr: 1.0e-04 loss: 2.064e-01]
my_first_lora_v2: 6%|6 | 254/4000 [07:28<1:50:13, 1.77s/it, lr: 1.0e-04 loss: 7.049e-02]
my_first_lora_v2: 6%|6 | 254/4000 [07:28<1:50:13, 1.77s/it, lr: 1.0e-04 loss: 7.049e-02]
my_first_lora_v2: 6%|6 | 255/4000 [07:29<1:49:57, 1.76s/it, lr: 1.0e-04 loss: 3.216e-01]
my_first_lora_v2: 6%|6 | 255/4000 [07:29<1:49:57, 1.76s/it, lr: 1.0e-04 loss: 3.216e-01]
my_first_lora_v2: 6%|6 | 256/4000 [07:31<1:50:09, 1.77s/it, lr: 1.0e-04 loss: 6.138e-01]
my_first_lora_v2: 6%|6 | 256/4000 [07:31<1:50:09, 1.77s/it, lr: 1.0e-04 loss: 6.138e-01]
my_first_lora_v2: 6%|6 | 257/4000 [07:34<1:50:23, 1.77s/it, lr: 1.0e-04 loss: 4.167e-01]
my_first_lora_v2: 6%|6 | 257/4000 [07:34<1:50:23, 1.77s/it, lr: 1.0e-04 loss: 4.167e-01]
my_first_lora_v2: 6%|6 | 258/4000 [07:35<1:50:08, 1.77s/it, lr: 1.0e-04 loss: 6.489e-01]
my_first_lora_v2: 6%|6 | 258/4000 [07:35<1:50:08, 1.77s/it, lr: 1.0e-04 loss: 6.489e-01]
my_first_lora_v2: 6%|6 | 259/4000 [07:38<1:50:23, 1.77s/it, lr: 1.0e-04 loss: 1.178e-01]
my_first_lora_v2: 6%|6 | 259/4000 [07:38<1:50:23, 1.77s/it, lr: 1.0e-04 loss: 1.178e-01]
my_first_lora_v2: 6%|6 | 260/4000 [07:39<1:50:08, 1.77s/it, lr: 1.0e-04 loss: 7.335e-01]
my_first_lora_v2: 6%|6 | 260/4000 [07:39<1:50:08, 1.77s/it, lr: 1.0e-04 loss: 7.335e-01]
my_first_lora_v2: 7%|6 | 261/4000 [07:41<1:50:15, 1.77s/it, lr: 1.0e-04 loss: 4.292e-01]
my_first_lora_v2: 7%|6 | 261/4000 [07:41<1:50:15, 1.77s/it, lr: 1.0e-04 loss: 4.292e-01]
my_first_lora_v2: 7%|6 | 262/4000 [07:44<1:50:31, 1.77s/it, lr: 1.0e-04 loss: 2.923e-01]
my_first_lora_v2: 7%|6 | 262/4000 [07:44<1:50:31, 1.77s/it, lr: 1.0e-04 loss: 2.923e-01]
my_first_lora_v2: 7%|6 | 263/4000 [07:47<1:50:46, 1.78s/it, lr: 1.0e-04 loss: 6.667e-01]
my_first_lora_v2: 7%|6 | 263/4000 [07:47<1:50:46, 1.78s/it, lr: 1.0e-04 loss: 6.667e-01]
my_first_lora_v2: 7%|6 | 264/4000 [07:48<1:50:30, 1.77s/it, lr: 1.0e-04 loss: 5.250e-02]
my_first_lora_v2: 7%|6 | 264/4000 [07:48<1:50:30, 1.77s/it, lr: 1.0e-04 loss: 5.250e-02]
my_first_lora_v2: 7%|6 | 265/4000 [07:49<1:50:15, 1.77s/it, lr: 1.0e-04 loss: 5.177e-01]
my_first_lora_v2: 7%|6 | 265/4000 [07:49<1:50:15, 1.77s/it, lr: 1.0e-04 loss: 5.177e-01]
my_first_lora_v2: 7%|6 | 266/4000 [07:50<1:49:59, 1.77s/it, lr: 1.0e-04 loss: 3.127e-01]
my_first_lora_v2: 7%|6 | 266/4000 [07:50<1:49:59, 1.77s/it, lr: 1.0e-04 loss: 3.127e-01]
my_first_lora_v2: 7%|6 | 267/4000 [07:50<1:49:44, 1.76s/it, lr: 1.0e-04 loss: 5.010e-01]
my_first_lora_v2: 7%|6 | 267/4000 [07:50<1:49:44, 1.76s/it, lr: 1.0e-04 loss: 5.010e-01]
my_first_lora_v2: 7%|6 | 268/4000 [07:53<1:49:58, 1.77s/it, lr: 1.0e-04 loss: 5.564e-01]
my_first_lora_v2: 7%|6 | 268/4000 [07:53<1:49:58, 1.77s/it, lr: 1.0e-04 loss: 5.564e-01]
my_first_lora_v2: 7%|6 | 269/4000 [07:54<1:49:44, 1.76s/it, lr: 1.0e-04 loss: 5.029e-01]
my_first_lora_v2: 7%|6 | 269/4000 [07:54<1:49:44, 1.76s/it, lr: 1.0e-04 loss: 5.029e-01]
my_first_lora_v2: 7%|6 | 270/4000 [07:55<1:49:28, 1.76s/it, lr: 1.0e-04 loss: 3.691e-01]
my_first_lora_v2: 7%|6 | 270/4000 [07:55<1:49:28, 1.76s/it, lr: 1.0e-04 loss: 3.691e-01]
my_first_lora_v2: 7%|6 | 271/4000 [07:56<1:49:13, 1.76s/it, lr: 1.0e-04 loss: 5.666e-01]
my_first_lora_v2: 7%|6 | 271/4000 [07:56<1:49:13, 1.76s/it, lr: 1.0e-04 loss: 5.666e-01]
my_first_lora_v2: 7%|6 | 272/4000 [07:58<1:49:24, 1.76s/it, lr: 1.0e-04 loss: 7.207e-01]
my_first_lora_v2: 7%|6 | 272/4000 [07:58<1:49:24, 1.76s/it, lr: 1.0e-04 loss: 7.207e-01]
my_first_lora_v2: 7%|6 | 273/4000 [07:59<1:49:09, 1.76s/it, lr: 1.0e-04 loss: 5.545e-01]
my_first_lora_v2: 7%|6 | 273/4000 [07:59<1:49:09, 1.76s/it, lr: 1.0e-04 loss: 5.545e-01]
my_first_lora_v2: 7%|6 | 274/4000 [08:00<1:48:55, 1.75s/it, lr: 1.0e-04 loss: 4.742e-01]
my_first_lora_v2: 7%|6 | 274/4000 [08:00<1:48:55, 1.75s/it, lr: 1.0e-04 loss: 4.742e-01]
my_first_lora_v2: 7%|6 | 275/4000 [08:01<1:48:40, 1.75s/it, lr: 1.0e-04 loss: 3.907e-01]
my_first_lora_v2: 7%|6 | 275/4000 [08:01<1:48:40, 1.75s/it, lr: 1.0e-04 loss: 3.907e-01]
my_first_lora_v2: 7%|6 | 276/4000 [08:04<1:48:56, 1.76s/it, lr: 1.0e-04 loss: 2.177e-01]
my_first_lora_v2: 7%|6 | 276/4000 [08:04<1:48:56, 1.76s/it, lr: 1.0e-04 loss: 2.177e-01]
my_first_lora_v2: 7%|6 | 277/4000 [08:05<1:48:41, 1.75s/it, lr: 1.0e-04 loss: 6.464e-01]
my_first_lora_v2: 7%|6 | 277/4000 [08:05<1:48:41, 1.75s/it, lr: 1.0e-04 loss: 6.464e-01]
my_first_lora_v2: 7%|6 | 278/4000 [08:08<1:48:55, 1.76s/it, lr: 1.0e-04 loss: 5.797e-01]
my_first_lora_v2: 7%|6 | 278/4000 [08:08<1:48:55, 1.76s/it, lr: 1.0e-04 loss: 5.797e-01]
my_first_lora_v2: 7%|6 | 279/4000 [08:10<1:49:06, 1.76s/it, lr: 1.0e-04 loss: 3.497e-01]
my_first_lora_v2: 7%|6 | 279/4000 [08:10<1:49:06, 1.76s/it, lr: 1.0e-04 loss: 3.497e-01]
my_first_lora_v2: 7%|7 | 280/4000 [08:13<1:49:17, 1.76s/it, lr: 1.0e-04 loss: 5.859e-01]
my_first_lora_v2: 7%|7 | 280/4000 [08:13<1:49:17, 1.76s/it, lr: 1.0e-04 loss: 5.859e-01]
my_first_lora_v2: 7%|7 | 281/4000 [08:16<1:49:30, 1.77s/it, lr: 1.0e-04 loss: 1.942e-01]
my_first_lora_v2: 7%|7 | 281/4000 [08:16<1:49:30, 1.77s/it, lr: 1.0e-04 loss: 1.942e-01]
my_first_lora_v2: 7%|7 | 282/4000 [08:19<1:49:41, 1.77s/it, lr: 1.0e-04 loss: 6.756e-01]
my_first_lora_v2: 7%|7 | 282/4000 [08:19<1:49:41, 1.77s/it, lr: 1.0e-04 loss: 6.756e-01]
my_first_lora_v2: 7%|7 | 283/4000 [08:19<1:49:27, 1.77s/it, lr: 1.0e-04 loss: 8.951e-02]
my_first_lora_v2: 7%|7 | 283/4000 [08:19<1:49:27, 1.77s/it, lr: 1.0e-04 loss: 8.951e-02]
my_first_lora_v2: 7%|7 | 284/4000 [08:22<1:49:40, 1.77s/it, lr: 1.0e-04 loss: 2.846e-01]
my_first_lora_v2: 7%|7 | 284/4000 [08:22<1:49:40, 1.77s/it, lr: 1.0e-04 loss: 2.846e-01]
my_first_lora_v2: 7%|7 | 285/4000 [08:23<1:49:26, 1.77s/it, lr: 1.0e-04 loss: 1.416e-01]
my_first_lora_v2: 7%|7 | 285/4000 [08:23<1:49:26, 1.77s/it, lr: 1.0e-04 loss: 1.416e-01]
my_first_lora_v2: 7%|7 | 286/4000 [08:26<1:49:32, 1.77s/it, lr: 1.0e-04 loss: 1.344e-01]
my_first_lora_v2: 7%|7 | 286/4000 [08:26<1:49:32, 1.77s/it, lr: 1.0e-04 loss: 1.344e-01]
my_first_lora_v2: 7%|7 | 287/4000 [08:26<1:49:18, 1.77s/it, lr: 1.0e-04 loss: 1.847e-01]
my_first_lora_v2: 7%|7 | 287/4000 [08:26<1:49:18, 1.77s/it, lr: 1.0e-04 loss: 1.847e-01]
my_first_lora_v2: 7%|7 | 288/4000 [08:29<1:49:28, 1.77s/it, lr: 1.0e-04 loss: 1.314e-01]
my_first_lora_v2: 7%|7 | 288/4000 [08:29<1:49:28, 1.77s/it, lr: 1.0e-04 loss: 1.314e-01]
my_first_lora_v2: 7%|7 | 289/4000 [08:30<1:49:15, 1.77s/it, lr: 1.0e-04 loss: 5.852e-01]
my_first_lora_v2: 7%|7 | 289/4000 [08:30<1:49:15, 1.77s/it, lr: 1.0e-04 loss: 5.852e-01]
my_first_lora_v2: 7%|7 | 290/4000 [08:31<1:49:04, 1.76s/it, lr: 1.0e-04 loss: 6.304e-01]
my_first_lora_v2: 7%|7 | 290/4000 [08:31<1:49:04, 1.76s/it, lr: 1.0e-04 loss: 6.304e-01]
my_first_lora_v2: 7%|7 | 291/4000 [08:32<1:48:50, 1.76s/it, lr: 1.0e-04 loss: 1.440e-01]
my_first_lora_v2: 7%|7 | 291/4000 [08:32<1:48:50, 1.76s/it, lr: 1.0e-04 loss: 1.440e-01]
my_first_lora_v2: 7%|7 | 292/4000 [08:33<1:48:43, 1.76s/it, lr: 1.0e-04 loss: 8.181e-01]
my_first_lora_v2: 7%|7 | 292/4000 [08:33<1:48:43, 1.76s/it, lr: 1.0e-04 loss: 8.181e-01]
my_first_lora_v2: 7%|7 | 293/4000 [08:36<1:48:54, 1.76s/it, lr: 1.0e-04 loss: 7.500e-01]
my_first_lora_v2: 7%|7 | 293/4000 [08:36<1:48:54, 1.76s/it, lr: 1.0e-04 loss: 7.500e-01]
my_first_lora_v2: 7%|7 | 294/4000 [08:39<1:49:06, 1.77s/it, lr: 1.0e-04 loss: 3.546e-01]
my_first_lora_v2: 7%|7 | 294/4000 [08:39<1:49:06, 1.77s/it, lr: 1.0e-04 loss: 3.546e-01]
my_first_lora_v2: 7%|7 | 295/4000 [08:40<1:48:53, 1.76s/it, lr: 1.0e-04 loss: 1.994e-01]
my_first_lora_v2: 7%|7 | 295/4000 [08:40<1:48:53, 1.76s/it, lr: 1.0e-04 loss: 1.994e-01]
my_first_lora_v2: 7%|7 | 296/4000 [08:41<1:48:39, 1.76s/it, lr: 1.0e-04 loss: 2.661e-01]
my_first_lora_v2: 7%|7 | 296/4000 [08:41<1:48:39, 1.76s/it, lr: 1.0e-04 loss: 2.661e-01]
my_first_lora_v2: 7%|7 | 297/4000 [08:41<1:48:26, 1.76s/it, lr: 1.0e-04 loss: 7.482e-01]
my_first_lora_v2: 7%|7 | 297/4000 [08:41<1:48:26, 1.76s/it, lr: 1.0e-04 loss: 7.482e-01]
my_first_lora_v2: 7%|7 | 298/4000 [08:44<1:48:39, 1.76s/it, lr: 1.0e-04 loss: 3.803e-01]
my_first_lora_v2: 7%|7 | 298/4000 [08:44<1:48:39, 1.76s/it, lr: 1.0e-04 loss: 3.803e-01]
my_first_lora_v2: 7%|7 | 299/4000 [08:46<1:48:34, 1.76s/it, lr: 1.0e-04 loss: 2.026e-01]
my_first_lora_v2: 7%|7 | 299/4000 [08:46<1:48:34, 1.76s/it, lr: 1.0e-04 loss: 2.026e-01]
my_first_lora_v2: 8%|7 | 300/4000 [08:48<1:48:40, 1.76s/it, lr: 1.0e-04 loss: 5.110e-01]
my_first_lora_v2: 8%|7 | 300/4000 [08:48<1:48:40, 1.76s/it, lr: 1.0e-04 loss: 5.110e-01]
my_first_lora_v2: 8%|7 | 301/4000 [08:49<1:48:27, 1.76s/it, lr: 1.0e-04 loss: 5.706e-01]
my_first_lora_v2: 8%|7 | 301/4000 [08:49<1:48:27, 1.76s/it, lr: 1.0e-04 loss: 5.706e-01]
my_first_lora_v2: 8%|7 | 302/4000 [08:52<1:48:36, 1.76s/it, lr: 1.0e-04 loss: 6.995e-01]
my_first_lora_v2: 8%|7 | 302/4000 [08:52<1:48:36, 1.76s/it, lr: 1.0e-04 loss: 6.995e-01]
my_first_lora_v2: 8%|7 | 303/4000 [08:55<1:48:50, 1.77s/it, lr: 1.0e-04 loss: 5.071e-01]
my_first_lora_v2: 8%|7 | 303/4000 [08:55<1:48:50, 1.77s/it, lr: 1.0e-04 loss: 5.071e-01]
my_first_lora_v2: 8%|7 | 304/4000 [08:56<1:48:36, 1.76s/it, lr: 1.0e-04 loss: 1.122e-01]
my_first_lora_v2: 8%|7 | 304/4000 [08:56<1:48:36, 1.76s/it, lr: 1.0e-04 loss: 1.122e-01]
my_first_lora_v2: 8%|7 | 305/4000 [08:58<1:48:49, 1.77s/it, lr: 1.0e-04 loss: 1.212e-01]
my_first_lora_v2: 8%|7 | 305/4000 [08:58<1:48:49, 1.77s/it, lr: 1.0e-04 loss: 1.212e-01]
my_first_lora_v2: 8%|7 | 306/4000 [08:59<1:48:36, 1.76s/it, lr: 1.0e-04 loss: 2.404e-01]
my_first_lora_v2: 8%|7 | 306/4000 [08:59<1:48:36, 1.76s/it, lr: 1.0e-04 loss: 2.404e-01]
my_first_lora_v2: 8%|7 | 307/4000 [09:02<1:48:45, 1.77s/it, lr: 1.0e-04 loss: 2.121e-01]
my_first_lora_v2: 8%|7 | 307/4000 [09:02<1:48:45, 1.77s/it, lr: 1.0e-04 loss: 2.121e-01]
my_first_lora_v2: 8%|7 | 308/4000 [09:03<1:48:31, 1.76s/it, lr: 1.0e-04 loss: 2.228e-01]
my_first_lora_v2: 8%|7 | 308/4000 [09:03<1:48:31, 1.76s/it, lr: 1.0e-04 loss: 2.228e-01]
my_first_lora_v2: 8%|7 | 309/4000 [09:06<1:48:43, 1.77s/it, lr: 1.0e-04 loss: 1.969e-01]
my_first_lora_v2: 8%|7 | 309/4000 [09:06<1:48:43, 1.77s/it, lr: 1.0e-04 loss: 1.969e-01]
my_first_lora_v2: 8%|7 | 310/4000 [09:09<1:48:55, 1.77s/it, lr: 1.0e-04 loss: 6.340e-01]
my_first_lora_v2: 8%|7 | 310/4000 [09:09<1:48:55, 1.77s/it, lr: 1.0e-04 loss: 6.340e-01]
my_first_lora_v2: 8%|7 | 311/4000 [09:11<1:49:06, 1.77s/it, lr: 1.0e-04 loss: 5.901e-01]
my_first_lora_v2: 8%|7 | 311/4000 [09:11<1:49:06, 1.77s/it, lr: 1.0e-04 loss: 5.901e-01]
my_first_lora_v2: 8%|7 | 312/4000 [09:14<1:49:18, 1.78s/it, lr: 1.0e-04 loss: 2.665e-01]
my_first_lora_v2: 8%|7 | 312/4000 [09:14<1:49:18, 1.78s/it, lr: 1.0e-04 loss: 2.665e-01]
my_first_lora_v2: 8%|7 | 313/4000 [09:15<1:49:05, 1.78s/it, lr: 1.0e-04 loss: 3.157e-01]
my_first_lora_v2: 8%|7 | 313/4000 [09:15<1:49:05, 1.78s/it, lr: 1.0e-04 loss: 3.157e-01]
my_first_lora_v2: 8%|7 | 314/4000 [09:18<1:49:16, 1.78s/it, lr: 1.0e-04 loss: 6.247e-01]
my_first_lora_v2: 8%|7 | 314/4000 [09:18<1:49:16, 1.78s/it, lr: 1.0e-04 loss: 6.247e-01]
my_first_lora_v2: 8%|7 | 315/4000 [09:19<1:49:03, 1.78s/it, lr: 1.0e-04 loss: 6.962e-01]
my_first_lora_v2: 8%|7 | 315/4000 [09:19<1:49:03, 1.78s/it, lr: 1.0e-04 loss: 6.962e-01]
my_first_lora_v2: 8%|7 | 316/4000 [09:22<1:49:16, 1.78s/it, lr: 1.0e-04 loss: 3.723e-01]
my_first_lora_v2: 8%|7 | 316/4000 [09:22<1:49:16, 1.78s/it, lr: 1.0e-04 loss: 3.723e-01]
my_first_lora_v2: 8%|7 | 317/4000 [09:25<1:49:27, 1.78s/it, lr: 1.0e-04 loss: 2.585e-01]
my_first_lora_v2: 8%|7 | 317/4000 [09:25<1:49:27, 1.78s/it, lr: 1.0e-04 loss: 2.585e-01]
my_first_lora_v2: 8%|7 | 318/4000 [09:26<1:49:14, 1.78s/it, lr: 1.0e-04 loss: 1.691e-01]
my_first_lora_v2: 8%|7 | 318/4000 [09:26<1:49:14, 1.78s/it, lr: 1.0e-04 loss: 1.691e-01]
my_first_lora_v2: 8%|7 | 319/4000 [09:26<1:49:01, 1.78s/it, lr: 1.0e-04 loss: 2.502e-01]
my_first_lora_v2: 8%|7 | 319/4000 [09:26<1:49:01, 1.78s/it, lr: 1.0e-04 loss: 2.502e-01]
my_first_lora_v2: 8%|8 | 320/4000 [09:29<1:49:13, 1.78s/it, lr: 1.0e-04 loss: 2.888e-01]
my_first_lora_v2: 8%|8 | 320/4000 [09:29<1:49:13, 1.78s/it, lr: 1.0e-04 loss: 2.888e-01]
my_first_lora_v2: 8%|8 | 321/4000 [09:30<1:49:00, 1.78s/it, lr: 1.0e-04 loss: 2.064e-01]
my_first_lora_v2: 8%|8 | 321/4000 [09:30<1:49:00, 1.78s/it, lr: 1.0e-04 loss: 2.064e-01]
my_first_lora_v2: 8%|8 | 322/4000 [09:31<1:48:47, 1.77s/it, lr: 1.0e-04 loss: 6.829e-01]
my_first_lora_v2: 8%|8 | 322/4000 [09:31<1:48:47, 1.77s/it, lr: 1.0e-04 loss: 6.829e-01]
my_first_lora_v2: 8%|8 | 323/4000 [09:34<1:48:58, 1.78s/it, lr: 1.0e-04 loss: 5.162e-01]
my_first_lora_v2: 8%|8 | 323/4000 [09:34<1:48:58, 1.78s/it, lr: 1.0e-04 loss: 5.162e-01]
my_first_lora_v2: 8%|8 | 324/4000 [09:37<1:49:09, 1.78s/it, lr: 1.0e-04 loss: 1.259e-01]
my_first_lora_v2: 8%|8 | 324/4000 [09:37<1:49:09, 1.78s/it, lr: 1.0e-04 loss: 1.259e-01]
my_first_lora_v2: 8%|8 | 325/4000 [09:38<1:48:56, 1.78s/it, lr: 1.0e-04 loss: 5.006e-01]
my_first_lora_v2: 8%|8 | 325/4000 [09:38<1:48:56, 1.78s/it, lr: 1.0e-04 loss: 5.006e-01]
my_first_lora_v2: 8%|8 | 326/4000 [09:38<1:48:43, 1.78s/it, lr: 1.0e-04 loss: 8.030e-01]
my_first_lora_v2: 8%|8 | 326/4000 [09:38<1:48:43, 1.78s/it, lr: 1.0e-04 loss: 8.030e-01]
my_first_lora_v2: 8%|8 | 327/4000 [09:41<1:48:52, 1.78s/it, lr: 1.0e-04 loss: 6.760e-01]
my_first_lora_v2: 8%|8 | 327/4000 [09:41<1:48:52, 1.78s/it, lr: 1.0e-04 loss: 6.760e-01]
my_first_lora_v2: 8%|8 | 328/4000 [09:42<1:48:39, 1.78s/it, lr: 1.0e-04 loss: 6.161e-01]
my_first_lora_v2: 8%|8 | 328/4000 [09:42<1:48:39, 1.78s/it, lr: 1.0e-04 loss: 6.161e-01]
my_first_lora_v2: 8%|8 | 329/4000 [09:44<1:48:45, 1.78s/it, lr: 1.0e-04 loss: 5.648e-01]
my_first_lora_v2: 8%|8 | 329/4000 [09:44<1:48:45, 1.78s/it, lr: 1.0e-04 loss: 5.648e-01]
my_first_lora_v2: 8%|8 | 330/4000 [09:45<1:48:36, 1.78s/it, lr: 1.0e-04 loss: 2.759e-01]
my_first_lora_v2: 8%|8 | 330/4000 [09:45<1:48:36, 1.78s/it, lr: 1.0e-04 loss: 2.759e-01]
my_first_lora_v2: 8%|8 | 331/4000 [09:46<1:48:24, 1.77s/it, lr: 1.0e-04 loss: 5.215e-01]
my_first_lora_v2: 8%|8 | 331/4000 [09:46<1:48:24, 1.77s/it, lr: 1.0e-04 loss: 5.215e-01]
my_first_lora_v2: 8%|8 | 332/4000 [09:49<1:48:32, 1.78s/it, lr: 1.0e-04 loss: 4.649e-01]
my_first_lora_v2: 8%|8 | 332/4000 [09:49<1:48:32, 1.78s/it, lr: 1.0e-04 loss: 4.649e-01]
my_first_lora_v2: 8%|8 | 333/4000 [09:50<1:48:20, 1.77s/it, lr: 1.0e-04 loss: 2.191e-01]
my_first_lora_v2: 8%|8 | 333/4000 [09:50<1:48:20, 1.77s/it, lr: 1.0e-04 loss: 2.191e-01]
my_first_lora_v2: 8%|8 | 334/4000 [09:52<1:48:26, 1.77s/it, lr: 1.0e-04 loss: 1.010e-01]
my_first_lora_v2: 8%|8 | 334/4000 [09:52<1:48:26, 1.77s/it, lr: 1.0e-04 loss: 1.010e-01]
my_first_lora_v2: 8%|8 | 335/4000 [09:53<1:48:13, 1.77s/it, lr: 1.0e-04 loss: 7.194e-01]
my_first_lora_v2: 8%|8 | 335/4000 [09:53<1:48:13, 1.77s/it, lr: 1.0e-04 loss: 7.194e-01]
my_first_lora_v2: 8%|8 | 336/4000 [09:54<1:48:01, 1.77s/it, lr: 1.0e-04 loss: 4.917e-01]
my_first_lora_v2: 8%|8 | 336/4000 [09:54<1:48:01, 1.77s/it, lr: 1.0e-04 loss: 4.917e-01]
my_first_lora_v2: 8%|8 | 337/4000 [09:55<1:47:49, 1.77s/it, lr: 1.0e-04 loss: 3.513e-01]
my_first_lora_v2: 8%|8 | 337/4000 [09:55<1:47:49, 1.77s/it, lr: 1.0e-04 loss: 3.513e-01]
my_first_lora_v2: 8%|8 | 338/4000 [09:57<1:47:57, 1.77s/it, lr: 1.0e-04 loss: 1.162e-01]
my_first_lora_v2: 8%|8 | 338/4000 [09:57<1:47:57, 1.77s/it, lr: 1.0e-04 loss: 1.162e-01]
my_first_lora_v2: 8%|8 | 339/4000 [10:00<1:48:08, 1.77s/it, lr: 1.0e-04 loss: 5.105e-01]
my_first_lora_v2: 8%|8 | 339/4000 [10:00<1:48:08, 1.77s/it, lr: 1.0e-04 loss: 5.105e-01]
my_first_lora_v2: 8%|8 | 340/4000 [10:01<1:47:56, 1.77s/it, lr: 1.0e-04 loss: 8.268e-03]
my_first_lora_v2: 8%|8 | 340/4000 [10:01<1:47:56, 1.77s/it, lr: 1.0e-04 loss: 8.268e-03]
my_first_lora_v2: 9%|8 | 341/4000 [10:02<1:47:44, 1.77s/it, lr: 1.0e-04 loss: 1.390e-01]
my_first_lora_v2: 9%|8 | 341/4000 [10:02<1:47:44, 1.77s/it, lr: 1.0e-04 loss: 1.390e-01]
my_first_lora_v2: 9%|8 | 342/4000 [10:03<1:47:32, 1.76s/it, lr: 1.0e-04 loss: 2.353e-01]
my_first_lora_v2: 9%|8 | 342/4000 [10:03<1:47:32, 1.76s/it, lr: 1.0e-04 loss: 2.353e-01]
my_first_lora_v2: 9%|8 | 343/4000 [10:05<1:47:40, 1.77s/it, lr: 1.0e-04 loss: 5.152e-01]
my_first_lora_v2: 9%|8 | 343/4000 [10:05<1:47:40, 1.77s/it, lr: 1.0e-04 loss: 5.152e-01]
my_first_lora_v2: 9%|8 | 344/4000 [10:06<1:47:31, 1.76s/it, lr: 1.0e-04 loss: 2.920e-01]
my_first_lora_v2: 9%|8 | 344/4000 [10:06<1:47:31, 1.76s/it, lr: 1.0e-04 loss: 2.920e-01]
my_first_lora_v2: 9%|8 | 345/4000 [10:09<1:47:41, 1.77s/it, lr: 1.0e-04 loss: 1.209e-01]
my_first_lora_v2: 9%|8 | 345/4000 [10:09<1:47:41, 1.77s/it, lr: 1.0e-04 loss: 1.209e-01]
my_first_lora_v2: 9%|8 | 346/4000 [10:10<1:47:29, 1.77s/it, lr: 1.0e-04 loss: 6.536e-01]
my_first_lora_v2: 9%|8 | 346/4000 [10:10<1:47:29, 1.77s/it, lr: 1.0e-04 loss: 6.536e-01]
my_first_lora_v2: 9%|8 | 347/4000 [10:11<1:47:17, 1.76s/it, lr: 1.0e-04 loss: 3.987e-01]
my_first_lora_v2: 9%|8 | 347/4000 [10:11<1:47:17, 1.76s/it, lr: 1.0e-04 loss: 3.987e-01]
my_first_lora_v2: 9%|8 | 348/4000 [10:14<1:47:28, 1.77s/it, lr: 1.0e-04 loss: 5.472e-01]
my_first_lora_v2: 9%|8 | 348/4000 [10:14<1:47:28, 1.77s/it, lr: 1.0e-04 loss: 5.472e-01]
my_first_lora_v2: 9%|8 | 349/4000 [10:17<1:47:35, 1.77s/it, lr: 1.0e-04 loss: 7.091e-01]
my_first_lora_v2: 9%|8 | 349/4000 [10:17<1:47:35, 1.77s/it, lr: 1.0e-04 loss: 7.091e-01]
my_first_lora_v2: 9%|8 | 350/4000 [10:17<1:47:23, 1.77s/it, lr: 1.0e-04 loss: 8.544e-02]
my_first_lora_v2: 9%|8 | 350/4000 [10:17<1:47:23, 1.77s/it, lr: 1.0e-04 loss: 8.544e-02]
my_first_lora_v2: 9%|8 | 351/4000 [10:18<1:47:11, 1.76s/it, lr: 1.0e-04 loss: 1.390e-01]
my_first_lora_v2: 9%|8 | 351/4000 [10:18<1:47:11, 1.76s/it, lr: 1.0e-04 loss: 1.390e-01]
my_first_lora_v2: 9%|8 | 352/4000 [10:19<1:46:59, 1.76s/it, lr: 1.0e-04 loss: 3.366e-01]
my_first_lora_v2: 9%|8 | 352/4000 [10:19<1:46:59, 1.76s/it, lr: 1.0e-04 loss: 3.366e-01]
my_first_lora_v2: 9%|8 | 353/4000 [10:22<1:47:10, 1.76s/it, lr: 1.0e-04 loss: 3.580e-01]
my_first_lora_v2: 9%|8 | 353/4000 [10:22<1:47:10, 1.76s/it, lr: 1.0e-04 loss: 3.580e-01]
my_first_lora_v2: 9%|8 | 354/4000 [10:25<1:47:19, 1.77s/it, lr: 1.0e-04 loss: 5.323e-01]
my_first_lora_v2: 9%|8 | 354/4000 [10:25<1:47:19, 1.77s/it, lr: 1.0e-04 loss: 5.323e-01]
my_first_lora_v2: 9%|8 | 355/4000 [10:27<1:47:27, 1.77s/it, lr: 1.0e-04 loss: 4.053e-01]
my_first_lora_v2: 9%|8 | 355/4000 [10:27<1:47:27, 1.77s/it, lr: 1.0e-04 loss: 4.053e-01]
my_first_lora_v2: 9%|8 | 356/4000 [10:28<1:47:16, 1.77s/it, lr: 1.0e-04 loss: 2.509e-01]
my_first_lora_v2: 9%|8 | 356/4000 [10:28<1:47:16, 1.77s/it, lr: 1.0e-04 loss: 2.509e-01]
my_first_lora_v2: 9%|8 | 357/4000 [10:29<1:47:07, 1.76s/it, lr: 1.0e-04 loss: 6.301e-01]
my_first_lora_v2: 9%|8 | 357/4000 [10:29<1:47:07, 1.76s/it, lr: 1.0e-04 loss: 6.301e-01]
my_first_lora_v2: 9%|8 | 358/4000 [10:30<1:46:56, 1.76s/it, lr: 1.0e-04 loss: 4.183e-01]
my_first_lora_v2: 9%|8 | 358/4000 [10:30<1:46:56, 1.76s/it, lr: 1.0e-04 loss: 4.183e-01]
my_first_lora_v2: 9%|8 | 359/4000 [10:33<1:47:07, 1.77s/it, lr: 1.0e-04 loss: 6.913e-01]
my_first_lora_v2: 9%|8 | 359/4000 [10:33<1:47:07, 1.77s/it, lr: 1.0e-04 loss: 6.913e-01]
my_first_lora_v2: 9%|9 | 360/4000 [10:36<1:47:14, 1.77s/it, lr: 1.0e-04 loss: 1.591e-01]
my_first_lora_v2: 9%|9 | 360/4000 [10:36<1:47:14, 1.77s/it, lr: 1.0e-04 loss: 1.591e-01]
my_first_lora_v2: 9%|9 | 361/4000 [10:39<1:47:21, 1.77s/it, lr: 1.0e-04 loss: 3.882e-01]
my_first_lora_v2: 9%|9 | 361/4000 [10:39<1:47:21, 1.77s/it, lr: 1.0e-04 loss: 3.882e-01]
my_first_lora_v2: 9%|9 | 362/4000 [10:41<1:47:26, 1.77s/it, lr: 1.0e-04 loss: 1.880e-01]
my_first_lora_v2: 9%|9 | 362/4000 [10:41<1:47:26, 1.77s/it, lr: 1.0e-04 loss: 1.880e-01]
my_first_lora_v2: 9%|9 | 363/4000 [10:42<1:47:15, 1.77s/it, lr: 1.0e-04 loss: 8.266e-01]
my_first_lora_v2: 9%|9 | 363/4000 [10:42<1:47:15, 1.77s/it, lr: 1.0e-04 loss: 8.266e-01]
my_first_lora_v2: 9%|9 | 364/4000 [10:45<1:47:24, 1.77s/it, lr: 1.0e-04 loss: 4.827e-02]
my_first_lora_v2: 9%|9 | 364/4000 [10:45<1:47:24, 1.77s/it, lr: 1.0e-04 loss: 4.827e-02]
my_first_lora_v2: 9%|9 | 365/4000 [10:47<1:47:28, 1.77s/it, lr: 1.0e-04 loss: 2.608e-01]
my_first_lora_v2: 9%|9 | 365/4000 [10:47<1:47:28, 1.77s/it, lr: 1.0e-04 loss: 2.608e-01]
my_first_lora_v2: 9%|9 | 366/4000 [10:48<1:47:17, 1.77s/it, lr: 1.0e-04 loss: 5.719e-01]
my_first_lora_v2: 9%|9 | 366/4000 [10:48<1:47:17, 1.77s/it, lr: 1.0e-04 loss: 5.719e-01]
my_first_lora_v2: 9%|9 | 367/4000 [10:49<1:47:06, 1.77s/it, lr: 1.0e-04 loss: 3.682e-01]
my_first_lora_v2: 9%|9 | 367/4000 [10:49<1:47:06, 1.77s/it, lr: 1.0e-04 loss: 3.682e-01]
my_first_lora_v2: 9%|9 | 368/4000 [10:50<1:46:55, 1.77s/it, lr: 1.0e-04 loss: 7.248e-01]
my_first_lora_v2: 9%|9 | 368/4000 [10:50<1:46:55, 1.77s/it, lr: 1.0e-04 loss: 7.248e-01]
my_first_lora_v2: 9%|9 | 369/4000 [10:52<1:47:04, 1.77s/it, lr: 1.0e-04 loss: 6.591e-01]
my_first_lora_v2: 9%|9 | 369/4000 [10:52<1:47:04, 1.77s/it, lr: 1.0e-04 loss: 6.591e-01]
my_first_lora_v2: 9%|9 | 370/4000 [10:54<1:46:57, 1.77s/it, lr: 1.0e-04 loss: 5.187e-01]
my_first_lora_v2: 9%|9 | 370/4000 [10:54<1:46:57, 1.77s/it, lr: 1.0e-04 loss: 5.187e-01]
my_first_lora_v2: 9%|9 | 371/4000 [10:54<1:46:46, 1.77s/it, lr: 1.0e-04 loss: 6.363e-01]
my_first_lora_v2: 9%|9 | 371/4000 [10:54<1:46:46, 1.77s/it, lr: 1.0e-04 loss: 6.363e-01]
my_first_lora_v2: 9%|9 | 372/4000 [10:57<1:46:55, 1.77s/it, lr: 1.0e-04 loss: 3.471e-01]
my_first_lora_v2: 9%|9 | 372/4000 [10:57<1:46:55, 1.77s/it, lr: 1.0e-04 loss: 3.471e-01]
my_first_lora_v2: 9%|9 | 373/4000 [10:58<1:46:44, 1.77s/it, lr: 1.0e-04 loss: 1.544e-01]
my_first_lora_v2: 9%|9 | 373/4000 [10:58<1:46:44, 1.77s/it, lr: 1.0e-04 loss: 1.544e-01]
my_first_lora_v2: 9%|9 | 374/4000 [11:01<1:46:53, 1.77s/it, lr: 1.0e-04 loss: 4.182e-02]
my_first_lora_v2: 9%|9 | 374/4000 [11:01<1:46:53, 1.77s/it, lr: 1.0e-04 loss: 4.182e-02]
my_first_lora_v2: 9%|9 | 375/4000 [11:04<1:47:03, 1.77s/it, lr: 1.0e-04 loss: 2.281e-01]
my_first_lora_v2: 9%|9 | 375/4000 [11:04<1:47:03, 1.77s/it, lr: 1.0e-04 loss: 2.281e-01]
my_first_lora_v2: 9%|9 | 376/4000 [11:05<1:46:51, 1.77s/it, lr: 1.0e-04 loss: 3.718e-01]
my_first_lora_v2: 9%|9 | 376/4000 [11:05<1:46:51, 1.77s/it, lr: 1.0e-04 loss: 3.718e-01]
my_first_lora_v2: 9%|9 | 377/4000 [11:06<1:46:40, 1.77s/it, lr: 1.0e-04 loss: 2.154e-01]
my_first_lora_v2: 9%|9 | 377/4000 [11:06<1:46:40, 1.77s/it, lr: 1.0e-04 loss: 2.154e-01]
my_first_lora_v2: 9%|9 | 378/4000 [11:08<1:46:48, 1.77s/it, lr: 1.0e-04 loss: 5.705e-01]
my_first_lora_v2: 9%|9 | 378/4000 [11:08<1:46:48, 1.77s/it, lr: 1.0e-04 loss: 5.705e-01]
my_first_lora_v2: 9%|9 | 379/4000 [11:11<1:46:57, 1.77s/it, lr: 1.0e-04 loss: 3.126e-01]
my_first_lora_v2: 9%|9 | 379/4000 [11:11<1:46:57, 1.77s/it, lr: 1.0e-04 loss: 3.126e-01]
my_first_lora_v2: 10%|9 | 380/4000 [11:14<1:47:03, 1.77s/it, lr: 1.0e-04 loss: 4.011e-01]
my_first_lora_v2: 10%|9 | 380/4000 [11:14<1:47:03, 1.77s/it, lr: 1.0e-04 loss: 4.011e-01]
my_first_lora_v2: 10%|9 | 381/4000 [11:16<1:47:08, 1.78s/it, lr: 1.0e-04 loss: 6.143e-01]
my_first_lora_v2: 10%|9 | 381/4000 [11:16<1:47:08, 1.78s/it, lr: 1.0e-04 loss: 6.143e-01]
my_first_lora_v2: 10%|9 | 382/4000 [11:19<1:47:17, 1.78s/it, lr: 1.0e-04 loss: 6.483e-01]
my_first_lora_v2: 10%|9 | 382/4000 [11:19<1:47:17, 1.78s/it, lr: 1.0e-04 loss: 6.483e-01]
my_first_lora_v2: 10%|9 | 383/4000 [11:20<1:47:06, 1.78s/it, lr: 1.0e-04 loss: 7.460e-01]
my_first_lora_v2: 10%|9 | 383/4000 [11:20<1:47:06, 1.78s/it, lr: 1.0e-04 loss: 7.460e-01]
my_first_lora_v2: 10%|9 | 384/4000 [11:21<1:46:58, 1.78s/it, lr: 1.0e-04 loss: 3.117e-01]
my_first_lora_v2: 10%|9 | 384/4000 [11:21<1:46:58, 1.78s/it, lr: 1.0e-04 loss: 3.117e-01]
my_first_lora_v2: 10%|9 | 385/4000 [11:22<1:46:47, 1.77s/it, lr: 1.0e-04 loss: 6.074e-01]
my_first_lora_v2: 10%|9 | 385/4000 [11:22<1:46:47, 1.77s/it, lr: 1.0e-04 loss: 6.074e-01]
my_first_lora_v2: 10%|9 | 386/4000 [11:23<1:46:36, 1.77s/it, lr: 1.0e-04 loss: 1.189e-01]
my_first_lora_v2: 10%|9 | 386/4000 [11:23<1:46:36, 1.77s/it, lr: 1.0e-04 loss: 1.189e-01]
my_first_lora_v2: 10%|9 | 387/4000 [11:24<1:46:26, 1.77s/it, lr: 1.0e-04 loss: 1.385e-01]
my_first_lora_v2: 10%|9 | 387/4000 [11:24<1:46:26, 1.77s/it, lr: 1.0e-04 loss: 1.385e-01]
my_first_lora_v2: 10%|9 | 388/4000 [11:24<1:46:15, 1.77s/it, lr: 1.0e-04 loss: 6.459e-01]
my_first_lora_v2: 10%|9 | 388/4000 [11:24<1:46:15, 1.77s/it, lr: 1.0e-04 loss: 6.459e-01]
my_first_lora_v2: 10%|9 | 389/4000 [11:25<1:46:04, 1.76s/it, lr: 1.0e-04 loss: 6.299e-01]
my_first_lora_v2: 10%|9 | 389/4000 [11:25<1:46:04, 1.76s/it, lr: 1.0e-04 loss: 6.299e-01]
my_first_lora_v2: 10%|9 | 390/4000 [11:28<1:46:14, 1.77s/it, lr: 1.0e-04 loss: 1.549e-01]
my_first_lora_v2: 10%|9 | 390/4000 [11:28<1:46:14, 1.77s/it, lr: 1.0e-04 loss: 1.549e-01]
my_first_lora_v2: 10%|9 | 391/4000 [11:29<1:46:03, 1.76s/it, lr: 1.0e-04 loss: 5.438e-01]
my_first_lora_v2: 10%|9 | 391/4000 [11:29<1:46:03, 1.76s/it, lr: 1.0e-04 loss: 5.438e-01]
my_first_lora_v2: 10%|9 | 392/4000 [11:30<1:45:57, 1.76s/it, lr: 1.0e-04 loss: 2.452e-01]
my_first_lora_v2: 10%|9 | 392/4000 [11:30<1:45:57, 1.76s/it, lr: 1.0e-04 loss: 2.452e-01]
my_first_lora_v2: 10%|9 | 393/4000 [11:33<1:46:06, 1.77s/it, lr: 1.0e-04 loss: 2.563e-01]
my_first_lora_v2: 10%|9 | 393/4000 [11:33<1:46:06, 1.77s/it, lr: 1.0e-04 loss: 2.563e-01]
my_first_lora_v2: 10%|9 | 394/4000 [11:36<1:46:16, 1.77s/it, lr: 1.0e-04 loss: 1.869e-01]
my_first_lora_v2: 10%|9 | 394/4000 [11:36<1:46:16, 1.77s/it, lr: 1.0e-04 loss: 1.869e-01]
my_first_lora_v2: 10%|9 | 395/4000 [11:37<1:46:06, 1.77s/it, lr: 1.0e-04 loss: 1.912e-01]
my_first_lora_v2: 10%|9 | 395/4000 [11:37<1:46:06, 1.77s/it, lr: 1.0e-04 loss: 1.912e-01]
my_first_lora_v2: 10%|9 | 396/4000 [11:40<1:46:14, 1.77s/it, lr: 1.0e-04 loss: 5.005e-01]
my_first_lora_v2: 10%|9 | 396/4000 [11:40<1:46:14, 1.77s/it, lr: 1.0e-04 loss: 5.005e-01]
my_first_lora_v2: 10%|9 | 397/4000 [11:41<1:46:04, 1.77s/it, lr: 1.0e-04 loss: 6.121e-01]
my_first_lora_v2: 10%|9 | 397/4000 [11:41<1:46:04, 1.77s/it, lr: 1.0e-04 loss: 6.121e-01]
my_first_lora_v2: 10%|9 | 398/4000 [11:44<1:46:14, 1.77s/it, lr: 1.0e-04 loss: 3.215e-01]
my_first_lora_v2: 10%|9 | 398/4000 [11:44<1:46:14, 1.77s/it, lr: 1.0e-04 loss: 3.215e-01]
my_first_lora_v2: 10%|9 | 399/4000 [11:45<1:46:04, 1.77s/it, lr: 1.0e-04 loss: 4.781e-01]
my_first_lora_v2: 10%|9 | 399/4000 [11:45<1:46:04, 1.77s/it, lr: 1.0e-04 loss: 4.781e-01]
my_first_lora_v2: 10%|# | 400/4000 [11:48<1:46:12, 1.77s/it, lr: 1.0e-04 loss: 5.952e-01]
my_first_lora_v2: 10%|# | 400/4000 [11:48<1:46:12, 1.77s/it, lr: 1.0e-04 loss: 5.952e-01]
my_first_lora_v2: 10%|# | 401/4000 [11:50<1:46:19, 1.77s/it, lr: 1.0e-04 loss: 6.812e-01]
my_first_lora_v2: 10%|# | 401/4000 [11:50<1:46:19, 1.77s/it, lr: 1.0e-04 loss: 6.812e-01]
my_first_lora_v2: 10%|# | 402/4000 [11:51<1:46:09, 1.77s/it, lr: 1.0e-04 loss: 4.878e-01]
my_first_lora_v2: 10%|# | 402/4000 [11:51<1:46:09, 1.77s/it, lr: 1.0e-04 loss: 4.878e-01]
my_first_lora_v2: 10%|# | 403/4000 [11:52<1:45:59, 1.77s/it, lr: 1.0e-04 loss: 3.655e-01]
my_first_lora_v2: 10%|# | 403/4000 [11:52<1:45:59, 1.77s/it, lr: 1.0e-04 loss: 3.655e-01]
my_first_lora_v2: 10%|# | 404/4000 [11:55<1:46:07, 1.77s/it, lr: 1.0e-04 loss: 1.786e-01]
my_first_lora_v2: 10%|# | 404/4000 [11:55<1:46:07, 1.77s/it, lr: 1.0e-04 loss: 1.786e-01]
my_first_lora_v2: 10%|# | 405/4000 [11:58<1:46:15, 1.77s/it, lr: 1.0e-04 loss: 7.710e-02]
my_first_lora_v2: 10%|# | 405/4000 [11:58<1:46:15, 1.77s/it, lr: 1.0e-04 loss: 7.710e-02]
my_first_lora_v2: 10%|# | 406/4000 [12:00<1:46:22, 1.78s/it, lr: 1.0e-04 loss: 1.415e-01]
my_first_lora_v2: 10%|# | 406/4000 [12:00<1:46:22, 1.78s/it, lr: 1.0e-04 loss: 1.415e-01]
my_first_lora_v2: 10%|# | 407/4000 [12:01<1:46:12, 1.77s/it, lr: 1.0e-04 loss: 1.631e-01]
my_first_lora_v2: 10%|# | 407/4000 [12:01<1:46:12, 1.77s/it, lr: 1.0e-04 loss: 1.631e-01]
my_first_lora_v2: 10%|# | 408/4000 [12:02<1:46:02, 1.77s/it, lr: 1.0e-04 loss: 5.056e-01]
my_first_lora_v2: 10%|# | 408/4000 [12:02<1:46:02, 1.77s/it, lr: 1.0e-04 loss: 5.056e-01]
my_first_lora_v2: 10%|# | 409/4000 [12:03<1:45:52, 1.77s/it, lr: 1.0e-04 loss: 4.027e-01]
my_first_lora_v2: 10%|# | 409/4000 [12:03<1:45:52, 1.77s/it, lr: 1.0e-04 loss: 4.027e-01]
my_first_lora_v2: 10%|# | 410/4000 [12:04<1:45:41, 1.77s/it, lr: 1.0e-04 loss: 4.497e-01]
my_first_lora_v2: 10%|# | 410/4000 [12:04<1:45:41, 1.77s/it, lr: 1.0e-04 loss: 4.497e-01]
my_first_lora_v2: 10%|# | 411/4000 [12:05<1:45:34, 1.77s/it, lr: 1.0e-04 loss: 6.567e-01]
my_first_lora_v2: 10%|# | 411/4000 [12:05<1:45:34, 1.77s/it, lr: 1.0e-04 loss: 6.567e-01]
my_first_lora_v2: 10%|# | 412/4000 [12:06<1:45:24, 1.76s/it, lr: 1.0e-04 loss: 4.715e-01]
my_first_lora_v2: 10%|# | 412/4000 [12:06<1:45:24, 1.76s/it, lr: 1.0e-04 loss: 4.715e-01]
my_first_lora_v2: 10%|# | 413/4000 [12:08<1:45:30, 1.76s/it, lr: 1.0e-04 loss: 6.851e-01]
my_first_lora_v2: 10%|# | 413/4000 [12:08<1:45:30, 1.76s/it, lr: 1.0e-04 loss: 6.851e-01]
my_first_lora_v2: 10%|# | 414/4000 [12:11<1:45:36, 1.77s/it, lr: 1.0e-04 loss: 7.613e-01]
my_first_lora_v2: 10%|# | 414/4000 [12:11<1:45:36, 1.77s/it, lr: 1.0e-04 loss: 7.613e-01]
my_first_lora_v2: 10%|# | 415/4000 [12:12<1:45:26, 1.76s/it, lr: 1.0e-04 loss: 3.911e-01]
my_first_lora_v2: 10%|# | 415/4000 [12:12<1:45:26, 1.76s/it, lr: 1.0e-04 loss: 3.911e-01]
my_first_lora_v2: 10%|# | 416/4000 [12:15<1:45:32, 1.77s/it, lr: 1.0e-04 loss: 6.971e-01]
my_first_lora_v2: 10%|# | 416/4000 [12:15<1:45:32, 1.77s/it, lr: 1.0e-04 loss: 6.971e-01]
my_first_lora_v2: 10%|# | 417/4000 [12:15<1:45:22, 1.76s/it, lr: 1.0e-04 loss: 5.165e-01]
my_first_lora_v2: 10%|# | 417/4000 [12:15<1:45:22, 1.76s/it, lr: 1.0e-04 loss: 5.165e-01]
my_first_lora_v2: 10%|# | 418/4000 [12:16<1:45:12, 1.76s/it, lr: 1.0e-04 loss: 6.768e-01]
my_first_lora_v2: 10%|# | 418/4000 [12:16<1:45:12, 1.76s/it, lr: 1.0e-04 loss: 6.768e-01]
my_first_lora_v2: 10%|# | 419/4000 [12:19<1:45:19, 1.76s/it, lr: 1.0e-04 loss: 5.508e-01]
my_first_lora_v2: 10%|# | 419/4000 [12:19<1:45:19, 1.76s/it, lr: 1.0e-04 loss: 5.508e-01]
my_first_lora_v2: 10%|# | 420/4000 [12:22<1:45:26, 1.77s/it, lr: 1.0e-04 loss: 5.230e-01]
my_first_lora_v2: 10%|# | 420/4000 [12:22<1:45:26, 1.77s/it, lr: 1.0e-04 loss: 5.230e-01]
my_first_lora_v2: 11%|# | 421/4000 [12:25<1:45:34, 1.77s/it, lr: 1.0e-04 loss: 8.905e-02]
my_first_lora_v2: 11%|# | 421/4000 [12:25<1:45:34, 1.77s/it, lr: 1.0e-04 loss: 8.905e-02]
my_first_lora_v2: 11%|# | 422/4000 [12:27<1:45:41, 1.77s/it, lr: 1.0e-04 loss: 4.226e-02]
my_first_lora_v2: 11%|# | 422/4000 [12:27<1:45:41, 1.77s/it, lr: 1.0e-04 loss: 4.226e-02]
my_first_lora_v2: 11%|# | 423/4000 [12:28<1:45:31, 1.77s/it, lr: 1.0e-04 loss: 1.498e-01]
my_first_lora_v2: 11%|# | 423/4000 [12:28<1:45:31, 1.77s/it, lr: 1.0e-04 loss: 1.498e-01]
my_first_lora_v2: 11%|# | 424/4000 [12:31<1:45:39, 1.77s/it, lr: 1.0e-04 loss: 4.798e-01]
my_first_lora_v2: 11%|# | 424/4000 [12:31<1:45:39, 1.77s/it, lr: 1.0e-04 loss: 4.798e-01]
my_first_lora_v2: 11%|# | 425/4000 [12:34<1:45:45, 1.78s/it, lr: 1.0e-04 loss: 8.451e-01]
my_first_lora_v2: 11%|# | 425/4000 [12:34<1:45:45, 1.78s/it, lr: 1.0e-04 loss: 8.451e-01]
my_first_lora_v2: 11%|# | 426/4000 [12:37<1:45:52, 1.78s/it, lr: 1.0e-04 loss: 3.329e-01]
my_first_lora_v2: 11%|# | 426/4000 [12:37<1:45:52, 1.78s/it, lr: 1.0e-04 loss: 3.329e-01]
my_first_lora_v2: 11%|# | 427/4000 [12:40<1:45:59, 1.78s/it, lr: 1.0e-04 loss: 6.671e-02]
my_first_lora_v2: 11%|# | 427/4000 [12:40<1:45:59, 1.78s/it, lr: 1.0e-04 loss: 6.671e-02]
my_first_lora_v2: 11%|# | 428/4000 [12:40<1:45:49, 1.78s/it, lr: 1.0e-04 loss: 5.173e-01]
my_first_lora_v2: 11%|# | 428/4000 [12:40<1:45:49, 1.78s/it, lr: 1.0e-04 loss: 5.173e-01]
my_first_lora_v2: 11%|# | 429/4000 [12:41<1:45:39, 1.78s/it, lr: 1.0e-04 loss: 1.933e-01]
my_first_lora_v2: 11%|# | 429/4000 [12:41<1:45:39, 1.78s/it, lr: 1.0e-04 loss: 1.933e-01]
my_first_lora_v2: 11%|# | 430/4000 [12:44<1:45:46, 1.78s/it, lr: 1.0e-04 loss: 4.188e-01]
my_first_lora_v2: 11%|# | 430/4000 [12:44<1:45:46, 1.78s/it, lr: 1.0e-04 loss: 4.188e-01]
my_first_lora_v2: 11%|# | 431/4000 [12:45<1:45:40, 1.78s/it, lr: 1.0e-04 loss: 7.962e-01]
my_first_lora_v2: 11%|# | 431/4000 [12:45<1:45:40, 1.78s/it, lr: 1.0e-04 loss: 7.962e-01]
my_first_lora_v2: 11%|# | 432/4000 [12:46<1:45:31, 1.77s/it, lr: 1.0e-04 loss: 4.943e-01]
my_first_lora_v2: 11%|# | 432/4000 [12:46<1:45:31, 1.77s/it, lr: 1.0e-04 loss: 4.943e-01]
my_first_lora_v2: 11%|# | 433/4000 [12:49<1:45:38, 1.78s/it, lr: 1.0e-04 loss: 7.141e-01]
my_first_lora_v2: 11%|# | 433/4000 [12:49<1:45:38, 1.78s/it, lr: 1.0e-04 loss: 7.141e-01]
my_first_lora_v2: 11%|# | 434/4000 [12:50<1:45:28, 1.77s/it, lr: 1.0e-04 loss: 2.506e-01]
my_first_lora_v2: 11%|# | 434/4000 [12:50<1:45:28, 1.77s/it, lr: 1.0e-04 loss: 2.506e-01]
my_first_lora_v2: 11%|# | 435/4000 [12:51<1:45:19, 1.77s/it, lr: 1.0e-04 loss: 4.450e-01]
my_first_lora_v2: 11%|# | 435/4000 [12:51<1:45:19, 1.77s/it, lr: 1.0e-04 loss: 4.450e-01]
my_first_lora_v2: 11%|# | 436/4000 [12:53<1:45:22, 1.77s/it, lr: 1.0e-04 loss: 1.870e-01]
my_first_lora_v2: 11%|# | 436/4000 [12:53<1:45:22, 1.77s/it, lr: 1.0e-04 loss: 1.870e-01]
my_first_lora_v2: 11%|# | 437/4000 [12:54<1:45:12, 1.77s/it, lr: 1.0e-04 loss: 1.996e-01]
my_first_lora_v2: 11%|# | 437/4000 [12:54<1:45:12, 1.77s/it, lr: 1.0e-04 loss: 1.996e-01]
my_first_lora_v2: 11%|# | 438/4000 [12:57<1:45:19, 1.77s/it, lr: 1.0e-04 loss: 3.185e-01]
my_first_lora_v2: 11%|# | 438/4000 [12:57<1:45:19, 1.77s/it, lr: 1.0e-04 loss: 3.185e-01]
my_first_lora_v2: 11%|# | 439/4000 [12:58<1:45:12, 1.77s/it, lr: 1.0e-04 loss: 3.731e-02]
my_first_lora_v2: 11%|# | 439/4000 [12:58<1:45:12, 1.77s/it, lr: 1.0e-04 loss: 3.731e-02]
my_first_lora_v2: 11%|#1 | 440/4000 [13:01<1:45:19, 1.78s/it, lr: 1.0e-04 loss: 6.117e-01]
my_first_lora_v2: 11%|#1 | 440/4000 [13:01<1:45:19, 1.78s/it, lr: 1.0e-04 loss: 6.117e-01]
my_first_lora_v2: 11%|#1 | 441/4000 [13:01<1:45:10, 1.77s/it, lr: 1.0e-04 loss: 1.543e-01]
my_first_lora_v2: 11%|#1 | 441/4000 [13:01<1:45:10, 1.77s/it, lr: 1.0e-04 loss: 1.543e-01]
my_first_lora_v2: 11%|#1 | 442/4000 [13:02<1:45:00, 1.77s/it, lr: 1.0e-04 loss: 3.246e-01]
my_first_lora_v2: 11%|#1 | 442/4000 [13:02<1:45:00, 1.77s/it, lr: 1.0e-04 loss: 3.246e-01]
my_first_lora_v2: 11%|#1 | 443/4000 [13:05<1:45:03, 1.77s/it, lr: 1.0e-04 loss: 2.330e-01]
my_first_lora_v2: 11%|#1 | 443/4000 [13:05<1:45:03, 1.77s/it, lr: 1.0e-04 loss: 2.330e-01]
my_first_lora_v2: 11%|#1 | 444/4000 [13:07<1:45:09, 1.77s/it, lr: 1.0e-04 loss: 4.055e-01]
my_first_lora_v2: 11%|#1 | 444/4000 [13:07<1:45:09, 1.77s/it, lr: 1.0e-04 loss: 4.055e-01]
my_first_lora_v2: 11%|#1 | 445/4000 [13:08<1:44:59, 1.77s/it, lr: 1.0e-04 loss: 6.200e-01]
my_first_lora_v2: 11%|#1 | 445/4000 [13:08<1:44:59, 1.77s/it, lr: 1.0e-04 loss: 6.200e-01]
my_first_lora_v2: 11%|#1 | 446/4000 [13:09<1:44:50, 1.77s/it, lr: 1.0e-04 loss: 3.488e-01]
my_first_lora_v2: 11%|#1 | 446/4000 [13:09<1:44:50, 1.77s/it, lr: 1.0e-04 loss: 3.488e-01]
my_first_lora_v2: 11%|#1 | 447/4000 [13:12<1:44:57, 1.77s/it, lr: 1.0e-04 loss: 4.962e-01]
my_first_lora_v2: 11%|#1 | 447/4000 [13:12<1:44:57, 1.77s/it, lr: 1.0e-04 loss: 4.962e-01]
my_first_lora_v2: 11%|#1 | 448/4000 [13:15<1:45:04, 1.77s/it, lr: 1.0e-04 loss: 3.123e-01]
my_first_lora_v2: 11%|#1 | 448/4000 [13:15<1:45:04, 1.77s/it, lr: 1.0e-04 loss: 3.123e-01]
my_first_lora_v2: 11%|#1 | 449/4000 [13:15<1:44:54, 1.77s/it, lr: 1.0e-04 loss: 7.718e-01]
my_first_lora_v2: 11%|#1 | 449/4000 [13:15<1:44:54, 1.77s/it, lr: 1.0e-04 loss: 7.718e-01]
my_first_lora_v2: 11%|#1 | 450/4000 [13:16<1:44:44, 1.77s/it, lr: 1.0e-04 loss: 6.958e-01]
my_first_lora_v2: 11%|#1 | 450/4000 [13:16<1:44:44, 1.77s/it, lr: 1.0e-04 loss: 6.958e-01]
my_first_lora_v2: 11%|#1 | 451/4000 [13:17<1:44:35, 1.77s/it, lr: 1.0e-04 loss: 6.092e-01]
my_first_lora_v2: 11%|#1 | 451/4000 [13:17<1:44:35, 1.77s/it, lr: 1.0e-04 loss: 6.092e-01]
my_first_lora_v2: 11%|#1 | 452/4000 [13:20<1:44:44, 1.77s/it, lr: 1.0e-04 loss: 6.750e-01]
my_first_lora_v2: 11%|#1 | 452/4000 [13:20<1:44:44, 1.77s/it, lr: 1.0e-04 loss: 6.750e-01]
my_first_lora_v2: 11%|#1 | 453/4000 [13:22<1:44:47, 1.77s/it, lr: 1.0e-04 loss: 2.280e-01]
my_first_lora_v2: 11%|#1 | 453/4000 [13:22<1:44:47, 1.77s/it, lr: 1.0e-04 loss: 2.280e-01]
my_first_lora_v2: 11%|#1 | 454/4000 [13:23<1:44:37, 1.77s/it, lr: 1.0e-04 loss: 6.857e-01]
my_first_lora_v2: 11%|#1 | 454/4000 [13:23<1:44:37, 1.77s/it, lr: 1.0e-04 loss: 6.857e-01]
my_first_lora_v2: 11%|#1 | 455/4000 [13:26<1:44:44, 1.77s/it, lr: 1.0e-04 loss: 5.007e-02]
my_first_lora_v2: 11%|#1 | 455/4000 [13:26<1:44:44, 1.77s/it, lr: 1.0e-04 loss: 5.007e-02]
my_first_lora_v2: 11%|#1 | 456/4000 [13:27<1:44:35, 1.77s/it, lr: 1.0e-04 loss: 5.454e-01]
my_first_lora_v2: 11%|#1 | 456/4000 [13:27<1:44:35, 1.77s/it, lr: 1.0e-04 loss: 5.454e-01]
my_first_lora_v2: 11%|#1 | 457/4000 [13:28<1:44:26, 1.77s/it, lr: 1.0e-04 loss: 4.723e-01]
my_first_lora_v2: 11%|#1 | 457/4000 [13:28<1:44:26, 1.77s/it, lr: 1.0e-04 loss: 4.723e-01]
my_first_lora_v2: 11%|#1 | 458/4000 [13:30<1:44:31, 1.77s/it, lr: 1.0e-04 loss: 1.523e-01]
my_first_lora_v2: 11%|#1 | 458/4000 [13:30<1:44:31, 1.77s/it, lr: 1.0e-04 loss: 1.523e-01]
my_first_lora_v2: 11%|#1 | 459/4000 [13:31<1:44:21, 1.77s/it, lr: 1.0e-04 loss: 3.266e-01]
my_first_lora_v2: 11%|#1 | 459/4000 [13:31<1:44:21, 1.77s/it, lr: 1.0e-04 loss: 3.266e-01]
my_first_lora_v2: 12%|#1 | 460/4000 [13:34<1:44:27, 1.77s/it, lr: 1.0e-04 loss: 2.066e-01]
my_first_lora_v2: 12%|#1 | 460/4000 [13:34<1:44:27, 1.77s/it, lr: 1.0e-04 loss: 2.066e-01]
my_first_lora_v2: 12%|#1 | 461/4000 [13:35<1:44:18, 1.77s/it, lr: 1.0e-04 loss: 8.103e-01]
my_first_lora_v2: 12%|#1 | 461/4000 [13:35<1:44:18, 1.77s/it, lr: 1.0e-04 loss: 8.103e-01]
my_first_lora_v2: 12%|#1 | 462/4000 [13:35<1:44:08, 1.77s/it, lr: 1.0e-04 loss: 6.875e-01]
my_first_lora_v2: 12%|#1 | 462/4000 [13:35<1:44:08, 1.77s/it, lr: 1.0e-04 loss: 6.875e-01]
my_first_lora_v2: 12%|#1 | 463/4000 [13:38<1:44:15, 1.77s/it, lr: 1.0e-04 loss: 1.134e-01]
my_first_lora_v2: 12%|#1 | 463/4000 [13:38<1:44:15, 1.77s/it, lr: 1.0e-04 loss: 1.134e-01]
my_first_lora_v2: 12%|#1 | 464/4000 [13:41<1:44:22, 1.77s/it, lr: 1.0e-04 loss: 4.826e-01]
my_first_lora_v2: 12%|#1 | 464/4000 [13:41<1:44:22, 1.77s/it, lr: 1.0e-04 loss: 4.826e-01]
my_first_lora_v2: 12%|#1 | 465/4000 [13:44<1:44:27, 1.77s/it, lr: 1.0e-04 loss: 5.896e-01]
my_first_lora_v2: 12%|#1 | 465/4000 [13:44<1:44:27, 1.77s/it, lr: 1.0e-04 loss: 5.896e-01]
my_first_lora_v2: 12%|#1 | 466/4000 [13:47<1:44:35, 1.78s/it, lr: 1.0e-04 loss: 2.074e-01]
my_first_lora_v2: 12%|#1 | 466/4000 [13:47<1:44:35, 1.78s/it, lr: 1.0e-04 loss: 2.074e-01]
my_first_lora_v2: 12%|#1 | 467/4000 [13:48<1:44:25, 1.77s/it, lr: 1.0e-04 loss: 7.994e-01]
my_first_lora_v2: 12%|#1 | 467/4000 [13:48<1:44:25, 1.77s/it, lr: 1.0e-04 loss: 7.994e-01]
my_first_lora_v2: 12%|#1 | 468/4000 [13:49<1:44:16, 1.77s/it, lr: 1.0e-04 loss: 8.766e-01]
my_first_lora_v2: 12%|#1 | 468/4000 [13:49<1:44:16, 1.77s/it, lr: 1.0e-04 loss: 8.766e-01]
my_first_lora_v2: 12%|#1 | 469/4000 [13:49<1:44:07, 1.77s/it, lr: 1.0e-04 loss: 6.572e-01]
my_first_lora_v2: 12%|#1 | 469/4000 [13:49<1:44:07, 1.77s/it, lr: 1.0e-04 loss: 6.572e-01]
my_first_lora_v2: 12%|#1 | 470/4000 [13:52<1:44:14, 1.77s/it, lr: 1.0e-04 loss: 6.164e-01]
my_first_lora_v2: 12%|#1 | 470/4000 [13:52<1:44:14, 1.77s/it, lr: 1.0e-04 loss: 6.164e-01]
my_first_lora_v2: 12%|#1 | 471/4000 [13:53<1:44:05, 1.77s/it, lr: 1.0e-04 loss: 6.358e-02]
my_first_lora_v2: 12%|#1 | 471/4000 [13:53<1:44:05, 1.77s/it, lr: 1.0e-04 loss: 6.358e-02]
my_first_lora_v2: 12%|#1 | 472/4000 [13:54<1:43:56, 1.77s/it, lr: 1.0e-04 loss: 1.752e-01]
my_first_lora_v2: 12%|#1 | 472/4000 [13:54<1:43:56, 1.77s/it, lr: 1.0e-04 loss: 1.752e-01]
my_first_lora_v2: 12%|#1 | 473/4000 [13:55<1:43:47, 1.77s/it, lr: 1.0e-04 loss: 4.776e-02]
my_first_lora_v2: 12%|#1 | 473/4000 [13:55<1:43:47, 1.77s/it, lr: 1.0e-04 loss: 4.776e-02]
my_first_lora_v2: 12%|#1 | 474/4000 [13:55<1:43:38, 1.76s/it, lr: 1.0e-04 loss: 4.751e-01]
my_first_lora_v2: 12%|#1 | 474/4000 [13:55<1:43:38, 1.76s/it, lr: 1.0e-04 loss: 4.751e-01]
my_first_lora_v2: 12%|#1 | 475/4000 [13:56<1:43:29, 1.76s/it, lr: 1.0e-04 loss: 5.160e-01]
my_first_lora_v2: 12%|#1 | 475/4000 [13:56<1:43:29, 1.76s/it, lr: 1.0e-04 loss: 5.160e-01]
my_first_lora_v2: 12%|#1 | 476/4000 [13:57<1:43:20, 1.76s/it, lr: 1.0e-04 loss: 3.539e-01]
my_first_lora_v2: 12%|#1 | 476/4000 [13:57<1:43:20, 1.76s/it, lr: 1.0e-04 loss: 3.539e-01]
my_first_lora_v2: 12%|#1 | 477/4000 [13:58<1:43:11, 1.76s/it, lr: 1.0e-04 loss: 4.569e-02]
my_first_lora_v2: 12%|#1 | 477/4000 [13:58<1:43:11, 1.76s/it, lr: 1.0e-04 loss: 4.569e-02]
my_first_lora_v2: 12%|#1 | 478/4000 [14:01<1:43:18, 1.76s/it, lr: 1.0e-04 loss: 2.159e-01]
my_first_lora_v2: 12%|#1 | 478/4000 [14:01<1:43:18, 1.76s/it, lr: 1.0e-04 loss: 2.159e-01]
my_first_lora_v2: 12%|#1 | 479/4000 [14:02<1:43:13, 1.76s/it, lr: 1.0e-04 loss: 1.656e-01]
my_first_lora_v2: 12%|#1 | 479/4000 [14:02<1:43:13, 1.76s/it, lr: 1.0e-04 loss: 1.656e-01]
my_first_lora_v2: 12%|#2 | 480/4000 [14:03<1:43:04, 1.76s/it, lr: 1.0e-04 loss: 8.100e-01]
my_first_lora_v2: 12%|#2 | 480/4000 [14:03<1:43:04, 1.76s/it, lr: 1.0e-04 loss: 8.100e-01]
my_first_lora_v2: 12%|#2 | 481/4000 [14:06<1:43:11, 1.76s/it, lr: 1.0e-04 loss: 4.715e-01]
my_first_lora_v2: 12%|#2 | 481/4000 [14:06<1:43:11, 1.76s/it, lr: 1.0e-04 loss: 4.715e-01]
my_first_lora_v2: 12%|#2 | 482/4000 [14:09<1:43:18, 1.76s/it, lr: 1.0e-04 loss: 6.751e-01]
my_first_lora_v2: 12%|#2 | 482/4000 [14:09<1:43:18, 1.76s/it, lr: 1.0e-04 loss: 6.751e-01]
my_first_lora_v2: 12%|#2 | 483/4000 [14:12<1:43:24, 1.76s/it, lr: 1.0e-04 loss: 1.999e-01]
my_first_lora_v2: 12%|#2 | 483/4000 [14:12<1:43:24, 1.76s/it, lr: 1.0e-04 loss: 1.999e-01]
my_first_lora_v2: 12%|#2 | 484/4000 [14:14<1:43:29, 1.77s/it, lr: 1.0e-04 loss: 2.023e-01]
my_first_lora_v2: 12%|#2 | 484/4000 [14:14<1:43:29, 1.77s/it, lr: 1.0e-04 loss: 2.023e-01]
my_first_lora_v2: 12%|#2 | 485/4000 [14:17<1:43:34, 1.77s/it, lr: 1.0e-04 loss: 5.400e-01]
my_first_lora_v2: 12%|#2 | 485/4000 [14:17<1:43:34, 1.77s/it, lr: 1.0e-04 loss: 5.400e-01]
my_first_lora_v2: 12%|#2 | 486/4000 [14:18<1:43:26, 1.77s/it, lr: 1.0e-04 loss: 5.631e-01]
my_first_lora_v2: 12%|#2 | 486/4000 [14:18<1:43:26, 1.77s/it, lr: 1.0e-04 loss: 5.631e-01]
my_first_lora_v2: 12%|#2 | 487/4000 [14:19<1:43:17, 1.76s/it, lr: 1.0e-04 loss: 2.593e-01]
my_first_lora_v2: 12%|#2 | 487/4000 [14:19<1:43:17, 1.76s/it, lr: 1.0e-04 loss: 2.593e-01]
my_first_lora_v2: 12%|#2 | 488/4000 [14:22<1:43:24, 1.77s/it, lr: 1.0e-04 loss: 6.429e-01]
my_first_lora_v2: 12%|#2 | 488/4000 [14:22<1:43:24, 1.77s/it, lr: 1.0e-04 loss: 6.429e-01]
my_first_lora_v2: 12%|#2 | 489/4000 [14:22<1:43:15, 1.76s/it, lr: 1.0e-04 loss: 3.795e-01]
my_first_lora_v2: 12%|#2 | 489/4000 [14:22<1:43:15, 1.76s/it, lr: 1.0e-04 loss: 3.795e-01]
my_first_lora_v2: 12%|#2 | 490/4000 [14:23<1:43:06, 1.76s/it, lr: 1.0e-04 loss: 3.679e-01]
my_first_lora_v2: 12%|#2 | 490/4000 [14:23<1:43:06, 1.76s/it, lr: 1.0e-04 loss: 3.679e-01]
my_first_lora_v2: 12%|#2 | 491/4000 [14:26<1:43:13, 1.77s/it, lr: 1.0e-04 loss: 5.670e-02]
my_first_lora_v2: 12%|#2 | 491/4000 [14:26<1:43:13, 1.77s/it, lr: 1.0e-04 loss: 5.670e-02]
my_first_lora_v2: 12%|#2 | 492/4000 [14:27<1:43:05, 1.76s/it, lr: 1.0e-04 loss: 2.607e-01]
my_first_lora_v2: 12%|#2 | 492/4000 [14:27<1:43:05, 1.76s/it, lr: 1.0e-04 loss: 2.607e-01]
my_first_lora_v2: 12%|#2 | 493/4000 [14:30<1:43:10, 1.77s/it, lr: 1.0e-04 loss: 3.423e-01]
my_first_lora_v2: 12%|#2 | 493/4000 [14:30<1:43:10, 1.77s/it, lr: 1.0e-04 loss: 3.423e-01]
my_first_lora_v2: 12%|#2 | 494/4000 [14:32<1:43:13, 1.77s/it, lr: 1.0e-04 loss: 6.501e-01]
my_first_lora_v2: 12%|#2 | 494/4000 [14:32<1:43:13, 1.77s/it, lr: 1.0e-04 loss: 6.501e-01]
my_first_lora_v2: 12%|#2 | 495/4000 [14:35<1:43:20, 1.77s/it, lr: 1.0e-04 loss: 5.828e-01]
my_first_lora_v2: 12%|#2 | 495/4000 [14:35<1:43:20, 1.77s/it, lr: 1.0e-04 loss: 5.828e-01]
my_first_lora_v2: 12%|#2 | 496/4000 [14:36<1:43:11, 1.77s/it, lr: 1.0e-04 loss: 5.937e-01]
my_first_lora_v2: 12%|#2 | 496/4000 [14:36<1:43:11, 1.77s/it, lr: 1.0e-04 loss: 5.937e-01]
my_first_lora_v2: 12%|#2 | 497/4000 [14:37<1:43:03, 1.77s/it, lr: 1.0e-04 loss: 7.481e-01]
my_first_lora_v2: 12%|#2 | 497/4000 [14:37<1:43:03, 1.77s/it, lr: 1.0e-04 loss: 7.481e-01]
my_first_lora_v2: 12%|#2 | 498/4000 [14:38<1:42:54, 1.76s/it, lr: 1.0e-04 loss: 8.247e-01]
my_first_lora_v2: 12%|#2 | 498/4000 [14:38<1:42:54, 1.76s/it, lr: 1.0e-04 loss: 8.247e-01]
my_first_lora_v2: 12%|#2 | 499/4000 [14:38<1:42:45, 1.76s/it, lr: 1.0e-04 loss: 5.894e-01]
my_first_lora_v2: 12%|#2 | 499/4000 [14:38<1:42:45, 1.76s/it, lr: 1.0e-04 loss: 5.894e-01] |
| Saving at step 500 |
| Saved checkpoint to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v2/my_first_lora_v2_000000500.safetensors |
| Saved optimizer to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v2/optimizer.pt |
| Unloading assistant lora |
|
|
|
|
|
Generating Images: 0%| | 0/3 [00:00<?, ?it/s]
Generating Images: 0%| | 0/3 [00:00<?, ?it/s][A[A |
|
|
|
Generating Images: 33%|###3 | 1/3 [00:07<00:15, 7.83s/it]
Generating Images: 33%|###3 | 1/3 [00:07<00:15, 7.83s/it][A[A |
|
|
|
Generating Images: 67%|######6 | 2/3 [00:15<00:07, 7.75s/it]
Generating Images: 67%|######6 | 2/3 [00:15<00:07, 7.75s/it][A[A |
|
|
|
Generating Images: 100%|##########| 3/3 [00:23<00:00, 7.70s/it]
Generating Images: 100%|##########| 3/3 [00:23<00:00, 7.70s/it][A[A |
|
|
|
[A[ALoading assistant lora |
|
my_first_lora_v2: 12%|#2 | 500/4000 [14:39<1:42:39, 1.76s/it, lr: 1.0e-04 loss: 3.751e-01]
my_first_lora_v2: 12%|#2 | 500/4000 [14:39<1:42:39, 1.76s/it, lr: 1.0e-04 loss: 3.751e-01]
my_first_lora_v2: 13%|#2 | 501/4000 [14:42<1:42:45, 1.76s/it, lr: 1.0e-04 loss: 3.420e-01]
my_first_lora_v2: 13%|#2 | 501/4000 [14:42<1:42:45, 1.76s/it, lr: 1.0e-04 loss: 3.420e-01]
my_first_lora_v2: 13%|#2 | 502/4000 [14:45<1:42:51, 1.76s/it, lr: 1.0e-04 loss: 7.658e-01]
my_first_lora_v2: 13%|#2 | 502/4000 [14:45<1:42:51, 1.76s/it, lr: 1.0e-04 loss: 7.658e-01]
my_first_lora_v2: 13%|#2 | 503/4000 [14:48<1:42:55, 1.77s/it, lr: 1.0e-04 loss: 1.564e-01]
my_first_lora_v2: 13%|#2 | 503/4000 [14:48<1:42:55, 1.77s/it, lr: 1.0e-04 loss: 1.564e-01]
my_first_lora_v2: 13%|#2 | 504/4000 [14:49<1:42:47, 1.76s/it, lr: 1.0e-04 loss: 2.506e-01]
my_first_lora_v2: 13%|#2 | 504/4000 [14:49<1:42:47, 1.76s/it, lr: 1.0e-04 loss: 2.506e-01]
my_first_lora_v2: 13%|#2 | 505/4000 [14:51<1:42:50, 1.77s/it, lr: 1.0e-04 loss: 4.413e-01]
my_first_lora_v2: 13%|#2 | 505/4000 [14:51<1:42:50, 1.77s/it, lr: 1.0e-04 loss: 4.413e-01]
my_first_lora_v2: 13%|#2 | 506/4000 [14:54<1:42:55, 1.77s/it, lr: 1.0e-04 loss: 1.325e-01]
my_first_lora_v2: 13%|#2 | 506/4000 [14:54<1:42:55, 1.77s/it, lr: 1.0e-04 loss: 1.325e-01]
my_first_lora_v2: 13%|#2 | 507/4000 [14:55<1:42:47, 1.77s/it, lr: 1.0e-04 loss: 5.976e-01]
my_first_lora_v2: 13%|#2 | 507/4000 [14:55<1:42:47, 1.77s/it, lr: 1.0e-04 loss: 5.976e-01]
my_first_lora_v2: 13%|#2 | 508/4000 [14:55<1:42:38, 1.76s/it, lr: 1.0e-04 loss: 5.146e-01]
my_first_lora_v2: 13%|#2 | 508/4000 [14:55<1:42:38, 1.76s/it, lr: 1.0e-04 loss: 5.146e-01]
my_first_lora_v2: 13%|#2 | 509/4000 [14:56<1:42:30, 1.76s/it, lr: 1.0e-04 loss: 3.278e-01]
my_first_lora_v2: 13%|#2 | 509/4000 [14:56<1:42:30, 1.76s/it, lr: 1.0e-04 loss: 3.278e-01]
my_first_lora_v2: 13%|#2 | 510/4000 [14:57<1:42:22, 1.76s/it, lr: 1.0e-04 loss: 7.188e-01]
my_first_lora_v2: 13%|#2 | 510/4000 [14:57<1:42:22, 1.76s/it, lr: 1.0e-04 loss: 7.188e-01]
my_first_lora_v2: 13%|#2 | 511/4000 [14:58<1:42:14, 1.76s/it, lr: 1.0e-04 loss: 2.485e-01]
my_first_lora_v2: 13%|#2 | 511/4000 [14:58<1:42:14, 1.76s/it, lr: 1.0e-04 loss: 2.485e-01]
my_first_lora_v2: 13%|#2 | 512/4000 [15:01<1:42:20, 1.76s/it, lr: 1.0e-04 loss: 8.014e-01]
my_first_lora_v2: 13%|#2 | 512/4000 [15:01<1:42:20, 1.76s/it, lr: 1.0e-04 loss: 8.014e-01]
my_first_lora_v2: 13%|#2 | 513/4000 [15:02<1:42:11, 1.76s/it, lr: 1.0e-04 loss: 3.999e-01]
my_first_lora_v2: 13%|#2 | 513/4000 [15:02<1:42:11, 1.76s/it, lr: 1.0e-04 loss: 3.999e-01]
my_first_lora_v2: 13%|#2 | 514/4000 [15:04<1:42:14, 1.76s/it, lr: 1.0e-04 loss: 4.790e-01]
my_first_lora_v2: 13%|#2 | 514/4000 [15:04<1:42:14, 1.76s/it, lr: 1.0e-04 loss: 4.790e-01]
my_first_lora_v2: 13%|#2 | 515/4000 [15:05<1:42:05, 1.76s/it, lr: 1.0e-04 loss: 7.354e-01]
my_first_lora_v2: 13%|#2 | 515/4000 [15:05<1:42:05, 1.76s/it, lr: 1.0e-04 loss: 7.354e-01]
my_first_lora_v2: 13%|#2 | 516/4000 [15:06<1:41:57, 1.76s/it, lr: 1.0e-04 loss: 4.024e-01]
my_first_lora_v2: 13%|#2 | 516/4000 [15:06<1:41:57, 1.76s/it, lr: 1.0e-04 loss: 4.024e-01]
my_first_lora_v2: 13%|#2 | 517/4000 [15:08<1:42:03, 1.76s/it, lr: 1.0e-04 loss: 5.461e-01]
my_first_lora_v2: 13%|#2 | 517/4000 [15:08<1:42:03, 1.76s/it, lr: 1.0e-04 loss: 5.461e-01]
my_first_lora_v2: 13%|#2 | 518/4000 [15:11<1:42:09, 1.76s/it, lr: 1.0e-04 loss: 2.967e-01]
my_first_lora_v2: 13%|#2 | 518/4000 [15:11<1:42:09, 1.76s/it, lr: 1.0e-04 loss: 2.967e-01]
my_first_lora_v2: 13%|#2 | 519/4000 [15:14<1:42:15, 1.76s/it, lr: 1.0e-04 loss: 6.238e-01]
my_first_lora_v2: 13%|#2 | 519/4000 [15:14<1:42:15, 1.76s/it, lr: 1.0e-04 loss: 6.238e-01]
my_first_lora_v2: 13%|#3 | 520/4000 [15:15<1:42:07, 1.76s/it, lr: 1.0e-04 loss: 1.192e-01]
my_first_lora_v2: 13%|#3 | 520/4000 [15:15<1:42:07, 1.76s/it, lr: 1.0e-04 loss: 1.192e-01]
my_first_lora_v2: 13%|#3 | 521/4000 [15:16<1:41:58, 1.76s/it, lr: 1.0e-04 loss: 5.947e-01]
my_first_lora_v2: 13%|#3 | 521/4000 [15:16<1:41:58, 1.76s/it, lr: 1.0e-04 loss: 5.947e-01]
my_first_lora_v2: 13%|#3 | 522/4000 [15:17<1:41:50, 1.76s/it, lr: 1.0e-04 loss: 6.976e-01]
my_first_lora_v2: 13%|#3 | 522/4000 [15:17<1:41:50, 1.76s/it, lr: 1.0e-04 loss: 6.976e-01]
my_first_lora_v2: 13%|#3 | 523/4000 [15:19<1:41:54, 1.76s/it, lr: 1.0e-04 loss: 6.876e-01]
my_first_lora_v2: 13%|#3 | 523/4000 [15:19<1:41:54, 1.76s/it, lr: 1.0e-04 loss: 6.876e-01]
my_first_lora_v2: 13%|#3 | 524/4000 [15:20<1:41:46, 1.76s/it, lr: 1.0e-04 loss: 4.505e-01]
my_first_lora_v2: 13%|#3 | 524/4000 [15:20<1:41:46, 1.76s/it, lr: 1.0e-04 loss: 4.505e-01]
my_first_lora_v2: 13%|#3 | 525/4000 [15:23<1:41:52, 1.76s/it, lr: 1.0e-04 loss: 2.788e-01]
my_first_lora_v2: 13%|#3 | 525/4000 [15:23<1:41:52, 1.76s/it, lr: 1.0e-04 loss: 2.788e-01]
my_first_lora_v2: 13%|#3 | 526/4000 [15:26<1:41:59, 1.76s/it, lr: 1.0e-04 loss: 4.566e-01]
my_first_lora_v2: 13%|#3 | 526/4000 [15:26<1:41:59, 1.76s/it, lr: 1.0e-04 loss: 4.566e-01]
my_first_lora_v2: 13%|#3 | 527/4000 [15:27<1:41:50, 1.76s/it, lr: 1.0e-04 loss: 7.418e-01]
my_first_lora_v2: 13%|#3 | 527/4000 [15:27<1:41:50, 1.76s/it, lr: 1.0e-04 loss: 7.418e-01]
my_first_lora_v2: 13%|#3 | 528/4000 [15:28<1:41:43, 1.76s/it, lr: 1.0e-04 loss: 7.736e-01]
my_first_lora_v2: 13%|#3 | 528/4000 [15:28<1:41:43, 1.76s/it, lr: 1.0e-04 loss: 7.736e-01]
my_first_lora_v2: 13%|#3 | 529/4000 [15:28<1:41:35, 1.76s/it, lr: 1.0e-04 loss: 3.333e-01]
my_first_lora_v2: 13%|#3 | 529/4000 [15:28<1:41:35, 1.76s/it, lr: 1.0e-04 loss: 3.333e-01]
my_first_lora_v2: 13%|#3 | 530/4000 [15:31<1:41:39, 1.76s/it, lr: 1.0e-04 loss: 4.658e-01]
my_first_lora_v2: 13%|#3 | 530/4000 [15:31<1:41:39, 1.76s/it, lr: 1.0e-04 loss: 4.658e-01]
my_first_lora_v2: 13%|#3 | 531/4000 [15:34<1:41:45, 1.76s/it, lr: 1.0e-04 loss: 1.577e-01]
my_first_lora_v2: 13%|#3 | 531/4000 [15:34<1:41:45, 1.76s/it, lr: 1.0e-04 loss: 1.577e-01]
my_first_lora_v2: 13%|#3 | 532/4000 [15:37<1:41:50, 1.76s/it, lr: 1.0e-04 loss: 1.004e-01]
my_first_lora_v2: 13%|#3 | 532/4000 [15:37<1:41:50, 1.76s/it, lr: 1.0e-04 loss: 1.004e-01]
my_first_lora_v2: 13%|#3 | 533/4000 [15:38<1:41:45, 1.76s/it, lr: 1.0e-04 loss: 3.450e-01]
my_first_lora_v2: 13%|#3 | 533/4000 [15:38<1:41:45, 1.76s/it, lr: 1.0e-04 loss: 3.450e-01]
my_first_lora_v2: 13%|#3 | 534/4000 [15:41<1:41:49, 1.76s/it, lr: 1.0e-04 loss: 3.342e-01]
my_first_lora_v2: 13%|#3 | 534/4000 [15:41<1:41:49, 1.76s/it, lr: 1.0e-04 loss: 3.342e-01]
my_first_lora_v2: 13%|#3 | 535/4000 [15:42<1:41:41, 1.76s/it, lr: 1.0e-04 loss: 2.091e-01]
my_first_lora_v2: 13%|#3 | 535/4000 [15:42<1:41:41, 1.76s/it, lr: 1.0e-04 loss: 2.091e-01]
my_first_lora_v2: 13%|#3 | 536/4000 [15:42<1:41:33, 1.76s/it, lr: 1.0e-04 loss: 2.691e-01]
my_first_lora_v2: 13%|#3 | 536/4000 [15:42<1:41:33, 1.76s/it, lr: 1.0e-04 loss: 2.691e-01]
my_first_lora_v2: 13%|#3 | 537/4000 [15:45<1:41:39, 1.76s/it, lr: 1.0e-04 loss: 4.923e-01]
my_first_lora_v2: 13%|#3 | 537/4000 [15:45<1:41:39, 1.76s/it, lr: 1.0e-04 loss: 4.923e-01]
my_first_lora_v2: 13%|#3 | 538/4000 [15:46<1:41:31, 1.76s/it, lr: 1.0e-04 loss: 6.030e-02]
my_first_lora_v2: 13%|#3 | 538/4000 [15:46<1:41:31, 1.76s/it, lr: 1.0e-04 loss: 6.030e-02]
my_first_lora_v2: 13%|#3 | 539/4000 [15:49<1:41:37, 1.76s/it, lr: 1.0e-04 loss: 2.012e-01]
my_first_lora_v2: 13%|#3 | 539/4000 [15:49<1:41:37, 1.76s/it, lr: 1.0e-04 loss: 2.012e-01]
my_first_lora_v2: 14%|#3 | 540/4000 [15:50<1:41:32, 1.76s/it, lr: 1.0e-04 loss: 2.725e-01]
my_first_lora_v2: 14%|#3 | 540/4000 [15:50<1:41:32, 1.76s/it, lr: 1.0e-04 loss: 2.725e-01]
my_first_lora_v2: 14%|#3 | 541/4000 [15:53<1:41:37, 1.76s/it, lr: 1.0e-04 loss: 6.147e-02]
my_first_lora_v2: 14%|#3 | 541/4000 [15:53<1:41:37, 1.76s/it, lr: 1.0e-04 loss: 6.147e-02]
my_first_lora_v2: 14%|#3 | 542/4000 [15:54<1:41:30, 1.76s/it, lr: 1.0e-04 loss: 8.348e-02]
my_first_lora_v2: 14%|#3 | 542/4000 [15:54<1:41:30, 1.76s/it, lr: 1.0e-04 loss: 8.348e-02]
my_first_lora_v2: 14%|#3 | 543/4000 [15:55<1:41:22, 1.76s/it, lr: 1.0e-04 loss: 2.563e-01]
my_first_lora_v2: 14%|#3 | 543/4000 [15:55<1:41:22, 1.76s/it, lr: 1.0e-04 loss: 2.563e-01]
my_first_lora_v2: 14%|#3 | 544/4000 [15:56<1:41:17, 1.76s/it, lr: 1.0e-04 loss: 3.439e-01]
my_first_lora_v2: 14%|#3 | 544/4000 [15:56<1:41:17, 1.76s/it, lr: 1.0e-04 loss: 3.439e-01]
my_first_lora_v2: 14%|#3 | 545/4000 [15:59<1:41:21, 1.76s/it, lr: 1.0e-04 loss: 8.489e-01]
my_first_lora_v2: 14%|#3 | 545/4000 [15:59<1:41:21, 1.76s/it, lr: 1.0e-04 loss: 8.489e-01]
my_first_lora_v2: 14%|#3 | 546/4000 [16:00<1:41:13, 1.76s/it, lr: 1.0e-04 loss: 1.453e-01]
my_first_lora_v2: 14%|#3 | 546/4000 [16:00<1:41:13, 1.76s/it, lr: 1.0e-04 loss: 1.453e-01]
my_first_lora_v2: 14%|#3 | 547/4000 [16:02<1:41:16, 1.76s/it, lr: 1.0e-04 loss: 3.914e-01]
my_first_lora_v2: 14%|#3 | 547/4000 [16:02<1:41:16, 1.76s/it, lr: 1.0e-04 loss: 3.914e-01]
my_first_lora_v2: 14%|#3 | 548/4000 [16:03<1:41:08, 1.76s/it, lr: 1.0e-04 loss: 3.048e-01]
my_first_lora_v2: 14%|#3 | 548/4000 [16:03<1:41:08, 1.76s/it, lr: 1.0e-04 loss: 3.048e-01]
my_first_lora_v2: 14%|#3 | 549/4000 [16:06<1:41:12, 1.76s/it, lr: 1.0e-04 loss: 5.451e-01]
my_first_lora_v2: 14%|#3 | 549/4000 [16:06<1:41:12, 1.76s/it, lr: 1.0e-04 loss: 5.451e-01]
my_first_lora_v2: 14%|#3 | 550/4000 [16:08<1:41:17, 1.76s/it, lr: 1.0e-04 loss: 4.563e-01]
my_first_lora_v2: 14%|#3 | 550/4000 [16:08<1:41:17, 1.76s/it, lr: 1.0e-04 loss: 4.563e-01]
my_first_lora_v2: 14%|#3 | 551/4000 [16:11<1:41:23, 1.76s/it, lr: 1.0e-04 loss: 3.476e-01]
my_first_lora_v2: 14%|#3 | 551/4000 [16:11<1:41:23, 1.76s/it, lr: 1.0e-04 loss: 3.476e-01]
my_first_lora_v2: 14%|#3 | 552/4000 [16:14<1:41:28, 1.77s/it, lr: 1.0e-04 loss: 2.477e-01]
my_first_lora_v2: 14%|#3 | 552/4000 [16:14<1:41:28, 1.77s/it, lr: 1.0e-04 loss: 2.477e-01]
my_first_lora_v2: 14%|#3 | 553/4000 [16:17<1:41:35, 1.77s/it, lr: 1.0e-04 loss: 1.542e-01]
my_first_lora_v2: 14%|#3 | 553/4000 [16:17<1:41:35, 1.77s/it, lr: 1.0e-04 loss: 1.542e-01]
my_first_lora_v2: 14%|#3 | 554/4000 [16:20<1:41:38, 1.77s/it, lr: 1.0e-04 loss: 7.200e-01]
my_first_lora_v2: 14%|#3 | 554/4000 [16:20<1:41:38, 1.77s/it, lr: 1.0e-04 loss: 7.200e-01]
my_first_lora_v2: 14%|#3 | 555/4000 [16:23<1:41:44, 1.77s/it, lr: 1.0e-04 loss: 4.675e-02]
my_first_lora_v2: 14%|#3 | 555/4000 [16:23<1:41:44, 1.77s/it, lr: 1.0e-04 loss: 4.675e-02]
my_first_lora_v2: 14%|#3 | 556/4000 [16:24<1:41:36, 1.77s/it, lr: 1.0e-04 loss: 1.857e-01]
my_first_lora_v2: 14%|#3 | 556/4000 [16:24<1:41:36, 1.77s/it, lr: 1.0e-04 loss: 1.857e-01]
my_first_lora_v2: 14%|#3 | 557/4000 [16:27<1:41:41, 1.77s/it, lr: 1.0e-04 loss: 6.581e-01]
my_first_lora_v2: 14%|#3 | 557/4000 [16:27<1:41:41, 1.77s/it, lr: 1.0e-04 loss: 6.581e-01]
my_first_lora_v2: 14%|#3 | 558/4000 [16:30<1:41:47, 1.77s/it, lr: 1.0e-04 loss: 2.551e-01]
my_first_lora_v2: 14%|#3 | 558/4000 [16:30<1:41:47, 1.77s/it, lr: 1.0e-04 loss: 2.551e-01]
my_first_lora_v2: 14%|#3 | 559/4000 [16:30<1:41:39, 1.77s/it, lr: 1.0e-04 loss: 6.445e-01]
my_first_lora_v2: 14%|#3 | 559/4000 [16:30<1:41:39, 1.77s/it, lr: 1.0e-04 loss: 6.445e-01]
my_first_lora_v2: 14%|#4 | 560/4000 [16:31<1:41:31, 1.77s/it, lr: 1.0e-04 loss: 7.128e-01]
my_first_lora_v2: 14%|#4 | 560/4000 [16:31<1:41:31, 1.77s/it, lr: 1.0e-04 loss: 7.128e-01]
my_first_lora_v2: 14%|#4 | 561/4000 [16:32<1:41:24, 1.77s/it, lr: 1.0e-04 loss: 6.012e-01]
my_first_lora_v2: 14%|#4 | 561/4000 [16:32<1:41:24, 1.77s/it, lr: 1.0e-04 loss: 6.012e-01]
my_first_lora_v2: 14%|#4 | 562/4000 [16:33<1:41:16, 1.77s/it, lr: 1.0e-04 loss: 9.855e-02]
my_first_lora_v2: 14%|#4 | 562/4000 [16:33<1:41:16, 1.77s/it, lr: 1.0e-04 loss: 9.855e-02]
my_first_lora_v2: 14%|#4 | 563/4000 [16:34<1:41:08, 1.77s/it, lr: 1.0e-04 loss: 2.835e-01]
my_first_lora_v2: 14%|#4 | 563/4000 [16:34<1:41:08, 1.77s/it, lr: 1.0e-04 loss: 2.835e-01]
my_first_lora_v2: 14%|#4 | 564/4000 [16:34<1:41:01, 1.76s/it, lr: 1.0e-04 loss: 6.248e-02]
my_first_lora_v2: 14%|#4 | 564/4000 [16:34<1:41:01, 1.76s/it, lr: 1.0e-04 loss: 6.248e-02]
my_first_lora_v2: 14%|#4 | 565/4000 [16:35<1:40:53, 1.76s/it, lr: 1.0e-04 loss: 5.288e-01]
my_first_lora_v2: 14%|#4 | 565/4000 [16:35<1:40:53, 1.76s/it, lr: 1.0e-04 loss: 5.288e-01]
my_first_lora_v2: 14%|#4 | 566/4000 [16:36<1:40:47, 1.76s/it, lr: 1.0e-04 loss: 7.973e-01]
my_first_lora_v2: 14%|#4 | 566/4000 [16:36<1:40:47, 1.76s/it, lr: 1.0e-04 loss: 7.973e-01]
my_first_lora_v2: 14%|#4 | 567/4000 [16:39<1:40:51, 1.76s/it, lr: 1.0e-04 loss: 2.065e-01]
my_first_lora_v2: 14%|#4 | 567/4000 [16:39<1:40:51, 1.76s/it, lr: 1.0e-04 loss: 2.065e-01]
my_first_lora_v2: 14%|#4 | 568/4000 [16:42<1:40:56, 1.76s/it, lr: 1.0e-04 loss: 4.372e-01]
my_first_lora_v2: 14%|#4 | 568/4000 [16:42<1:40:56, 1.76s/it, lr: 1.0e-04 loss: 4.372e-01]
my_first_lora_v2: 14%|#4 | 569/4000 [16:43<1:40:49, 1.76s/it, lr: 1.0e-04 loss: 4.350e-01]
my_first_lora_v2: 14%|#4 | 569/4000 [16:43<1:40:49, 1.76s/it, lr: 1.0e-04 loss: 4.350e-01]
my_first_lora_v2: 14%|#4 | 570/4000 [16:45<1:40:52, 1.76s/it, lr: 1.0e-04 loss: 1.968e-01]
my_first_lora_v2: 14%|#4 | 570/4000 [16:45<1:40:52, 1.76s/it, lr: 1.0e-04 loss: 1.968e-01]
my_first_lora_v2: 14%|#4 | 571/4000 [16:46<1:40:45, 1.76s/it, lr: 1.0e-04 loss: 1.296e-01]
my_first_lora_v2: 14%|#4 | 571/4000 [16:46<1:40:45, 1.76s/it, lr: 1.0e-04 loss: 1.296e-01]
my_first_lora_v2: 14%|#4 | 572/4000 [16:47<1:40:37, 1.76s/it, lr: 1.0e-04 loss: 7.107e-01]
my_first_lora_v2: 14%|#4 | 572/4000 [16:47<1:40:37, 1.76s/it, lr: 1.0e-04 loss: 7.107e-01]
my_first_lora_v2: 14%|#4 | 573/4000 [16:50<1:40:41, 1.76s/it, lr: 1.0e-04 loss: 6.198e-01]
my_first_lora_v2: 14%|#4 | 573/4000 [16:50<1:40:41, 1.76s/it, lr: 1.0e-04 loss: 6.198e-01]
my_first_lora_v2: 14%|#4 | 574/4000 [16:51<1:40:34, 1.76s/it, lr: 1.0e-04 loss: 6.838e-01]
my_first_lora_v2: 14%|#4 | 574/4000 [16:51<1:40:34, 1.76s/it, lr: 1.0e-04 loss: 6.838e-01]
my_first_lora_v2: 14%|#4 | 575/4000 [16:51<1:40:27, 1.76s/it, lr: 1.0e-04 loss: 3.492e-01]
my_first_lora_v2: 14%|#4 | 575/4000 [16:51<1:40:27, 1.76s/it, lr: 1.0e-04 loss: 3.492e-01]
my_first_lora_v2: 14%|#4 | 576/4000 [16:54<1:40:32, 1.76s/it, lr: 1.0e-04 loss: 1.323e-01]
my_first_lora_v2: 14%|#4 | 576/4000 [16:54<1:40:32, 1.76s/it, lr: 1.0e-04 loss: 1.323e-01]
my_first_lora_v2: 14%|#4 | 577/4000 [16:57<1:40:37, 1.76s/it, lr: 1.0e-04 loss: 3.073e-01]
my_first_lora_v2: 14%|#4 | 577/4000 [16:57<1:40:37, 1.76s/it, lr: 1.0e-04 loss: 3.073e-01]
my_first_lora_v2: 14%|#4 | 578/4000 [17:00<1:40:41, 1.77s/it, lr: 1.0e-04 loss: 2.836e-01]
my_first_lora_v2: 14%|#4 | 578/4000 [17:00<1:40:41, 1.77s/it, lr: 1.0e-04 loss: 2.836e-01]
my_first_lora_v2: 14%|#4 | 579/4000 [17:01<1:40:33, 1.76s/it, lr: 1.0e-04 loss: 4.685e-01]
my_first_lora_v2: 14%|#4 | 579/4000 [17:01<1:40:33, 1.76s/it, lr: 1.0e-04 loss: 4.685e-01]
my_first_lora_v2: 14%|#4 | 580/4000 [17:02<1:40:28, 1.76s/it, lr: 1.0e-04 loss: 7.673e-01]
my_first_lora_v2: 14%|#4 | 580/4000 [17:02<1:40:28, 1.76s/it, lr: 1.0e-04 loss: 7.673e-01]
my_first_lora_v2: 15%|#4 | 581/4000 [17:03<1:40:20, 1.76s/it, lr: 1.0e-04 loss: 7.348e-01]
my_first_lora_v2: 15%|#4 | 581/4000 [17:03<1:40:20, 1.76s/it, lr: 1.0e-04 loss: 7.348e-01]
my_first_lora_v2: 15%|#4 | 582/4000 [17:06<1:40:25, 1.76s/it, lr: 1.0e-04 loss: 1.150e-01]
my_first_lora_v2: 15%|#4 | 582/4000 [17:06<1:40:25, 1.76s/it, lr: 1.0e-04 loss: 1.150e-01]
my_first_lora_v2: 15%|#4 | 583/4000 [17:06<1:40:18, 1.76s/it, lr: 1.0e-04 loss: 5.360e-01]
my_first_lora_v2: 15%|#4 | 583/4000 [17:06<1:40:18, 1.76s/it, lr: 1.0e-04 loss: 5.360e-01]
my_first_lora_v2: 15%|#4 | 584/4000 [17:09<1:40:20, 1.76s/it, lr: 1.0e-04 loss: 3.611e-01]
my_first_lora_v2: 15%|#4 | 584/4000 [17:09<1:40:20, 1.76s/it, lr: 1.0e-04 loss: 3.611e-01]
my_first_lora_v2: 15%|#4 | 585/4000 [17:10<1:40:13, 1.76s/it, lr: 1.0e-04 loss: 8.111e-01]
my_first_lora_v2: 15%|#4 | 585/4000 [17:10<1:40:13, 1.76s/it, lr: 1.0e-04 loss: 8.111e-01]
my_first_lora_v2: 15%|#4 | 586/4000 [17:13<1:40:18, 1.76s/it, lr: 1.0e-04 loss: 1.202e-01]
my_first_lora_v2: 15%|#4 | 586/4000 [17:13<1:40:18, 1.76s/it, lr: 1.0e-04 loss: 1.202e-01]
my_first_lora_v2: 15%|#4 | 587/4000 [17:13<1:40:10, 1.76s/it, lr: 1.0e-04 loss: 6.657e-01]
my_first_lora_v2: 15%|#4 | 587/4000 [17:13<1:40:10, 1.76s/it, lr: 1.0e-04 loss: 6.657e-01]
my_first_lora_v2: 15%|#4 | 588/4000 [17:16<1:40:12, 1.76s/it, lr: 1.0e-04 loss: 4.045e-01]
my_first_lora_v2: 15%|#4 | 588/4000 [17:16<1:40:12, 1.76s/it, lr: 1.0e-04 loss: 4.045e-01]
my_first_lora_v2: 15%|#4 | 589/4000 [17:18<1:40:16, 1.76s/it, lr: 1.0e-04 loss: 6.906e-01]
my_first_lora_v2: 15%|#4 | 589/4000 [17:18<1:40:16, 1.76s/it, lr: 1.0e-04 loss: 6.906e-01]
my_first_lora_v2: 15%|#4 | 590/4000 [17:19<1:40:09, 1.76s/it, lr: 1.0e-04 loss: 8.758e-01]
my_first_lora_v2: 15%|#4 | 590/4000 [17:19<1:40:09, 1.76s/it, lr: 1.0e-04 loss: 8.758e-01]
my_first_lora_v2: 15%|#4 | 591/4000 [17:20<1:40:01, 1.76s/it, lr: 1.0e-04 loss: 7.293e-01]
my_first_lora_v2: 15%|#4 | 591/4000 [17:20<1:40:01, 1.76s/it, lr: 1.0e-04 loss: 7.293e-01]
my_first_lora_v2: 15%|#4 | 592/4000 [17:21<1:39:54, 1.76s/it, lr: 1.0e-04 loss: 3.895e-01]
my_first_lora_v2: 15%|#4 | 592/4000 [17:21<1:39:54, 1.76s/it, lr: 1.0e-04 loss: 3.895e-01]
my_first_lora_v2: 15%|#4 | 593/4000 [17:22<1:39:47, 1.76s/it, lr: 1.0e-04 loss: 2.085e-01]
my_first_lora_v2: 15%|#4 | 593/4000 [17:22<1:39:47, 1.76s/it, lr: 1.0e-04 loss: 2.085e-01]
my_first_lora_v2: 15%|#4 | 594/4000 [17:23<1:39:41, 1.76s/it, lr: 1.0e-04 loss: 6.288e-01]
my_first_lora_v2: 15%|#4 | 594/4000 [17:23<1:39:41, 1.76s/it, lr: 1.0e-04 loss: 6.288e-01]
my_first_lora_v2: 15%|#4 | 595/4000 [17:26<1:39:46, 1.76s/it, lr: 1.0e-04 loss: 3.050e-01]
my_first_lora_v2: 15%|#4 | 595/4000 [17:26<1:39:46, 1.76s/it, lr: 1.0e-04 loss: 3.050e-01]
my_first_lora_v2: 15%|#4 | 596/4000 [17:26<1:39:39, 1.76s/it, lr: 1.0e-04 loss: 6.987e-01]
my_first_lora_v2: 15%|#4 | 596/4000 [17:26<1:39:39, 1.76s/it, lr: 1.0e-04 loss: 6.987e-01]
my_first_lora_v2: 15%|#4 | 597/4000 [17:29<1:39:44, 1.76s/it, lr: 1.0e-04 loss: 4.813e-01]
my_first_lora_v2: 15%|#4 | 597/4000 [17:29<1:39:44, 1.76s/it, lr: 1.0e-04 loss: 4.813e-01]
my_first_lora_v2: 15%|#4 | 598/4000 [17:32<1:39:47, 1.76s/it, lr: 1.0e-04 loss: 4.735e-01]
my_first_lora_v2: 15%|#4 | 598/4000 [17:32<1:39:47, 1.76s/it, lr: 1.0e-04 loss: 4.735e-01]
my_first_lora_v2: 15%|#4 | 599/4000 [17:33<1:39:41, 1.76s/it, lr: 1.0e-04 loss: 4.775e-02]
my_first_lora_v2: 15%|#4 | 599/4000 [17:33<1:39:41, 1.76s/it, lr: 1.0e-04 loss: 4.775e-02]
my_first_lora_v2: 15%|#5 | 600/4000 [17:34<1:39:34, 1.76s/it, lr: 1.0e-04 loss: 6.319e-01]
my_first_lora_v2: 15%|#5 | 600/4000 [17:34<1:39:34, 1.76s/it, lr: 1.0e-04 loss: 6.319e-01]
my_first_lora_v2: 15%|#5 | 601/4000 [17:37<1:39:39, 1.76s/it, lr: 1.0e-04 loss: 1.523e-01]
my_first_lora_v2: 15%|#5 | 601/4000 [17:37<1:39:39, 1.76s/it, lr: 1.0e-04 loss: 1.523e-01]
my_first_lora_v2: 15%|#5 | 602/4000 [17:40<1:39:44, 1.76s/it, lr: 1.0e-04 loss: 5.659e-01]
my_first_lora_v2: 15%|#5 | 602/4000 [17:40<1:39:44, 1.76s/it, lr: 1.0e-04 loss: 5.659e-01]
my_first_lora_v2: 15%|#5 | 603/4000 [17:40<1:39:36, 1.76s/it, lr: 1.0e-04 loss: 1.812e-01]
my_first_lora_v2: 15%|#5 | 603/4000 [17:40<1:39:36, 1.76s/it, lr: 1.0e-04 loss: 1.812e-01]
my_first_lora_v2: 15%|#5 | 604/4000 [17:41<1:39:29, 1.76s/it, lr: 1.0e-04 loss: 2.109e-01]
my_first_lora_v2: 15%|#5 | 604/4000 [17:41<1:39:29, 1.76s/it, lr: 1.0e-04 loss: 2.109e-01]
my_first_lora_v2: 15%|#5 | 605/4000 [17:44<1:39:34, 1.76s/it, lr: 1.0e-04 loss: 3.901e-01]
my_first_lora_v2: 15%|#5 | 605/4000 [17:44<1:39:34, 1.76s/it, lr: 1.0e-04 loss: 3.901e-01]
my_first_lora_v2: 15%|#5 | 606/4000 [17:45<1:39:27, 1.76s/it, lr: 1.0e-04 loss: 5.808e-01]
my_first_lora_v2: 15%|#5 | 606/4000 [17:45<1:39:27, 1.76s/it, lr: 1.0e-04 loss: 5.808e-01]
my_first_lora_v2: 15%|#5 | 607/4000 [17:48<1:39:31, 1.76s/it, lr: 1.0e-04 loss: 3.128e-01]
my_first_lora_v2: 15%|#5 | 607/4000 [17:48<1:39:31, 1.76s/it, lr: 1.0e-04 loss: 3.128e-01]
my_first_lora_v2: 15%|#5 | 608/4000 [17:49<1:39:24, 1.76s/it, lr: 1.0e-04 loss: 2.599e-01]
my_first_lora_v2: 15%|#5 | 608/4000 [17:49<1:39:24, 1.76s/it, lr: 1.0e-04 loss: 2.599e-01]
my_first_lora_v2: 15%|#5 | 609/4000 [17:49<1:39:17, 1.76s/it, lr: 1.0e-04 loss: 3.504e-01]
my_first_lora_v2: 15%|#5 | 609/4000 [17:49<1:39:17, 1.76s/it, lr: 1.0e-04 loss: 3.504e-01]
my_first_lora_v2: 15%|#5 | 610/4000 [17:50<1:39:10, 1.76s/it, lr: 1.0e-04 loss: 3.172e-01]
my_first_lora_v2: 15%|#5 | 610/4000 [17:50<1:39:10, 1.76s/it, lr: 1.0e-04 loss: 3.172e-01]
my_first_lora_v2: 15%|#5 | 611/4000 [17:53<1:39:15, 1.76s/it, lr: 1.0e-04 loss: 7.701e-01]
my_first_lora_v2: 15%|#5 | 611/4000 [17:53<1:39:15, 1.76s/it, lr: 1.0e-04 loss: 7.701e-01]
my_first_lora_v2: 15%|#5 | 612/4000 [17:54<1:39:08, 1.76s/it, lr: 1.0e-04 loss: 3.960e-01]
my_first_lora_v2: 15%|#5 | 612/4000 [17:54<1:39:08, 1.76s/it, lr: 1.0e-04 loss: 3.960e-01]
my_first_lora_v2: 15%|#5 | 613/4000 [17:57<1:39:12, 1.76s/it, lr: 1.0e-04 loss: 4.733e-01]
my_first_lora_v2: 15%|#5 | 613/4000 [17:57<1:39:12, 1.76s/it, lr: 1.0e-04 loss: 4.733e-01]
my_first_lora_v2: 15%|#5 | 614/4000 [17:59<1:39:14, 1.76s/it, lr: 1.0e-04 loss: 1.633e-01]
my_first_lora_v2: 15%|#5 | 614/4000 [17:59<1:39:14, 1.76s/it, lr: 1.0e-04 loss: 1.633e-01]
my_first_lora_v2: 15%|#5 | 615/4000 [18:02<1:39:18, 1.76s/it, lr: 1.0e-04 loss: 5.936e-01]
my_first_lora_v2: 15%|#5 | 615/4000 [18:02<1:39:18, 1.76s/it, lr: 1.0e-04 loss: 5.936e-01]
my_first_lora_v2: 15%|#5 | 616/4000 [18:03<1:39:11, 1.76s/it, lr: 1.0e-04 loss: 4.168e-01]
my_first_lora_v2: 15%|#5 | 616/4000 [18:03<1:39:11, 1.76s/it, lr: 1.0e-04 loss: 4.168e-01]
my_first_lora_v2: 15%|#5 | 617/4000 [18:04<1:39:04, 1.76s/it, lr: 1.0e-04 loss: 7.441e-01]
my_first_lora_v2: 15%|#5 | 617/4000 [18:04<1:39:04, 1.76s/it, lr: 1.0e-04 loss: 7.441e-01]
my_first_lora_v2: 15%|#5 | 618/4000 [18:06<1:39:07, 1.76s/it, lr: 1.0e-04 loss: 2.001e-01]
my_first_lora_v2: 15%|#5 | 618/4000 [18:06<1:39:07, 1.76s/it, lr: 1.0e-04 loss: 2.001e-01]
my_first_lora_v2: 15%|#5 | 619/4000 [18:09<1:39:12, 1.76s/it, lr: 1.0e-04 loss: 5.821e-01]
my_first_lora_v2: 15%|#5 | 619/4000 [18:09<1:39:12, 1.76s/it, lr: 1.0e-04 loss: 5.821e-01]
my_first_lora_v2: 16%|#5 | 620/4000 [18:10<1:39:07, 1.76s/it, lr: 1.0e-04 loss: 1.241e-01]
my_first_lora_v2: 16%|#5 | 620/4000 [18:10<1:39:07, 1.76s/it, lr: 1.0e-04 loss: 1.241e-01]
my_first_lora_v2: 16%|#5 | 621/4000 [18:11<1:39:00, 1.76s/it, lr: 1.0e-04 loss: 5.268e-01]
my_first_lora_v2: 16%|#5 | 621/4000 [18:11<1:39:00, 1.76s/it, lr: 1.0e-04 loss: 5.268e-01]
my_first_lora_v2: 16%|#5 | 622/4000 [18:12<1:38:53, 1.76s/it, lr: 1.0e-04 loss: 5.193e-01]
my_first_lora_v2: 16%|#5 | 622/4000 [18:12<1:38:53, 1.76s/it, lr: 1.0e-04 loss: 5.193e-01]
my_first_lora_v2: 16%|#5 | 623/4000 [18:13<1:38:46, 1.76s/it, lr: 1.0e-04 loss: 1.788e-01]
my_first_lora_v2: 16%|#5 | 623/4000 [18:13<1:38:46, 1.76s/it, lr: 1.0e-04 loss: 1.788e-01]
my_first_lora_v2: 16%|#5 | 624/4000 [18:16<1:38:49, 1.76s/it, lr: 1.0e-04 loss: 7.145e-01]
my_first_lora_v2: 16%|#5 | 624/4000 [18:16<1:38:49, 1.76s/it, lr: 1.0e-04 loss: 7.145e-01]
my_first_lora_v2: 16%|#5 | 625/4000 [18:16<1:38:42, 1.75s/it, lr: 1.0e-04 loss: 5.829e-01]
my_first_lora_v2: 16%|#5 | 625/4000 [18:16<1:38:42, 1.75s/it, lr: 1.0e-04 loss: 5.829e-01]
my_first_lora_v2: 16%|#5 | 626/4000 [18:17<1:38:36, 1.75s/it, lr: 1.0e-04 loss: 5.459e-01]
my_first_lora_v2: 16%|#5 | 626/4000 [18:17<1:38:36, 1.75s/it, lr: 1.0e-04 loss: 5.459e-01]
my_first_lora_v2: 16%|#5 | 627/4000 [18:20<1:38:40, 1.76s/it, lr: 1.0e-04 loss: 3.821e-01]
my_first_lora_v2: 16%|#5 | 627/4000 [18:20<1:38:40, 1.76s/it, lr: 1.0e-04 loss: 3.821e-01]
my_first_lora_v2: 16%|#5 | 628/4000 [18:21<1:38:33, 1.75s/it, lr: 1.0e-04 loss: 3.365e-01]
my_first_lora_v2: 16%|#5 | 628/4000 [18:21<1:38:33, 1.75s/it, lr: 1.0e-04 loss: 3.365e-01]
my_first_lora_v2: 16%|#5 | 629/4000 [18:22<1:38:26, 1.75s/it, lr: 1.0e-04 loss: 5.498e-01]
my_first_lora_v2: 16%|#5 | 629/4000 [18:22<1:38:26, 1.75s/it, lr: 1.0e-04 loss: 5.498e-01]
my_first_lora_v2: 16%|#5 | 630/4000 [18:22<1:38:20, 1.75s/it, lr: 1.0e-04 loss: 8.818e-02]
my_first_lora_v2: 16%|#5 | 630/4000 [18:22<1:38:20, 1.75s/it, lr: 1.0e-04 loss: 8.818e-02]
my_first_lora_v2: 16%|#5 | 631/4000 [18:23<1:38:13, 1.75s/it, lr: 1.0e-04 loss: 2.982e-02]
my_first_lora_v2: 16%|#5 | 631/4000 [18:23<1:38:13, 1.75s/it, lr: 1.0e-04 loss: 2.982e-02]
my_first_lora_v2: 16%|#5 | 632/4000 [18:26<1:38:17, 1.75s/it, lr: 1.0e-04 loss: 2.504e-01]
my_first_lora_v2: 16%|#5 | 632/4000 [18:26<1:38:17, 1.75s/it, lr: 1.0e-04 loss: 2.504e-01]
my_first_lora_v2: 16%|#5 | 633/4000 [18:29<1:38:22, 1.75s/it, lr: 1.0e-04 loss: 6.658e-01]
my_first_lora_v2: 16%|#5 | 633/4000 [18:29<1:38:22, 1.75s/it, lr: 1.0e-04 loss: 6.658e-01]
my_first_lora_v2: 16%|#5 | 634/4000 [18:32<1:38:27, 1.75s/it, lr: 1.0e-04 loss: 4.124e-01]
my_first_lora_v2: 16%|#5 | 634/4000 [18:32<1:38:27, 1.75s/it, lr: 1.0e-04 loss: 4.124e-01]
my_first_lora_v2: 16%|#5 | 635/4000 [18:33<1:38:20, 1.75s/it, lr: 1.0e-04 loss: 5.118e-01]
my_first_lora_v2: 16%|#5 | 635/4000 [18:33<1:38:20, 1.75s/it, lr: 1.0e-04 loss: 5.118e-01]
my_first_lora_v2: 16%|#5 | 636/4000 [18:34<1:38:13, 1.75s/it, lr: 1.0e-04 loss: 8.060e-01]
my_first_lora_v2: 16%|#5 | 636/4000 [18:34<1:38:13, 1.75s/it, lr: 1.0e-04 loss: 8.060e-01]
my_first_lora_v2: 16%|#5 | 637/4000 [18:37<1:38:18, 1.75s/it, lr: 1.0e-04 loss: 4.885e-01]
my_first_lora_v2: 16%|#5 | 637/4000 [18:37<1:38:18, 1.75s/it, lr: 1.0e-04 loss: 4.885e-01]
my_first_lora_v2: 16%|#5 | 638/4000 [18:39<1:38:19, 1.75s/it, lr: 1.0e-04 loss: 2.542e-01]
my_first_lora_v2: 16%|#5 | 638/4000 [18:39<1:38:19, 1.75s/it, lr: 1.0e-04 loss: 2.542e-01]
my_first_lora_v2: 16%|#5 | 639/4000 [18:40<1:38:13, 1.75s/it, lr: 1.0e-04 loss: 7.528e-01]
my_first_lora_v2: 16%|#5 | 639/4000 [18:40<1:38:13, 1.75s/it, lr: 1.0e-04 loss: 7.528e-01]
my_first_lora_v2: 16%|#6 | 640/4000 [18:41<1:38:06, 1.75s/it, lr: 1.0e-04 loss: 6.495e-01]
my_first_lora_v2: 16%|#6 | 640/4000 [18:41<1:38:06, 1.75s/it, lr: 1.0e-04 loss: 6.495e-01]
my_first_lora_v2: 16%|#6 | 641/4000 [18:42<1:38:02, 1.75s/it, lr: 1.0e-04 loss: 2.490e-01]
my_first_lora_v2: 16%|#6 | 641/4000 [18:42<1:38:02, 1.75s/it, lr: 1.0e-04 loss: 2.490e-01]
my_first_lora_v2: 16%|#6 | 642/4000 [18:45<1:38:06, 1.75s/it, lr: 1.0e-04 loss: 6.396e-01]
my_first_lora_v2: 16%|#6 | 642/4000 [18:45<1:38:06, 1.75s/it, lr: 1.0e-04 loss: 6.396e-01]
my_first_lora_v2: 16%|#6 | 643/4000 [18:48<1:38:10, 1.75s/it, lr: 1.0e-04 loss: 5.116e-01]
my_first_lora_v2: 16%|#6 | 643/4000 [18:48<1:38:10, 1.75s/it, lr: 1.0e-04 loss: 5.116e-01]
my_first_lora_v2: 16%|#6 | 644/4000 [18:51<1:38:14, 1.76s/it, lr: 1.0e-04 loss: 6.204e-01]
my_first_lora_v2: 16%|#6 | 644/4000 [18:51<1:38:14, 1.76s/it, lr: 1.0e-04 loss: 6.204e-01]
my_first_lora_v2: 16%|#6 | 645/4000 [18:51<1:38:07, 1.75s/it, lr: 1.0e-04 loss: 3.498e-01]
my_first_lora_v2: 16%|#6 | 645/4000 [18:51<1:38:07, 1.75s/it, lr: 1.0e-04 loss: 3.498e-01]
my_first_lora_v2: 16%|#6 | 646/4000 [18:54<1:38:12, 1.76s/it, lr: 1.0e-04 loss: 3.408e-01]
my_first_lora_v2: 16%|#6 | 646/4000 [18:54<1:38:12, 1.76s/it, lr: 1.0e-04 loss: 3.408e-01]
my_first_lora_v2: 16%|#6 | 647/4000 [18:57<1:38:16, 1.76s/it, lr: 1.0e-04 loss: 4.770e-01]
my_first_lora_v2: 16%|#6 | 647/4000 [18:57<1:38:16, 1.76s/it, lr: 1.0e-04 loss: 4.770e-01]
my_first_lora_v2: 16%|#6 | 648/4000 [18:58<1:38:11, 1.76s/it, lr: 1.0e-04 loss: 7.514e-01]
my_first_lora_v2: 16%|#6 | 648/4000 [18:58<1:38:11, 1.76s/it, lr: 1.0e-04 loss: 7.514e-01]
my_first_lora_v2: 16%|#6 | 649/4000 [19:01<1:38:14, 1.76s/it, lr: 1.0e-04 loss: 5.180e-01]
my_first_lora_v2: 16%|#6 | 649/4000 [19:01<1:38:14, 1.76s/it, lr: 1.0e-04 loss: 5.180e-01]
my_first_lora_v2: 16%|#6 | 650/4000 [19:04<1:38:17, 1.76s/it, lr: 1.0e-04 loss: 7.014e-01]
my_first_lora_v2: 16%|#6 | 650/4000 [19:04<1:38:17, 1.76s/it, lr: 1.0e-04 loss: 7.014e-01]
my_first_lora_v2: 16%|#6 | 651/4000 [19:05<1:38:10, 1.76s/it, lr: 1.0e-04 loss: 4.055e-01]
my_first_lora_v2: 16%|#6 | 651/4000 [19:05<1:38:10, 1.76s/it, lr: 1.0e-04 loss: 4.055e-01]
my_first_lora_v2: 16%|#6 | 652/4000 [19:05<1:38:04, 1.76s/it, lr: 1.0e-04 loss: 1.852e-01]
my_first_lora_v2: 16%|#6 | 652/4000 [19:05<1:38:04, 1.76s/it, lr: 1.0e-04 loss: 1.852e-01]
my_first_lora_v2: 16%|#6 | 653/4000 [19:08<1:38:07, 1.76s/it, lr: 1.0e-04 loss: 3.791e-02]
my_first_lora_v2: 16%|#6 | 653/4000 [19:08<1:38:07, 1.76s/it, lr: 1.0e-04 loss: 3.791e-02]
my_first_lora_v2: 16%|#6 | 654/4000 [19:09<1:38:00, 1.76s/it, lr: 1.0e-04 loss: 2.671e-01]
my_first_lora_v2: 16%|#6 | 654/4000 [19:09<1:38:00, 1.76s/it, lr: 1.0e-04 loss: 2.671e-01]
my_first_lora_v2: 16%|#6 | 655/4000 [19:11<1:38:02, 1.76s/it, lr: 1.0e-04 loss: 1.402e-01]
my_first_lora_v2: 16%|#6 | 655/4000 [19:11<1:38:02, 1.76s/it, lr: 1.0e-04 loss: 1.402e-01]
my_first_lora_v2: 16%|#6 | 656/4000 [19:14<1:38:06, 1.76s/it, lr: 1.0e-04 loss: 5.260e-01]
my_first_lora_v2: 16%|#6 | 656/4000 [19:14<1:38:06, 1.76s/it, lr: 1.0e-04 loss: 5.260e-01]
my_first_lora_v2: 16%|#6 | 657/4000 [19:15<1:37:59, 1.76s/it, lr: 1.0e-04 loss: 6.449e-01]
my_first_lora_v2: 16%|#6 | 657/4000 [19:15<1:37:59, 1.76s/it, lr: 1.0e-04 loss: 6.449e-01]
my_first_lora_v2: 16%|#6 | 658/4000 [19:18<1:38:04, 1.76s/it, lr: 1.0e-04 loss: 4.400e-01]
my_first_lora_v2: 16%|#6 | 658/4000 [19:18<1:38:04, 1.76s/it, lr: 1.0e-04 loss: 4.400e-01]
my_first_lora_v2: 16%|#6 | 659/4000 [19:19<1:37:58, 1.76s/it, lr: 1.0e-04 loss: 5.017e-01]
my_first_lora_v2: 16%|#6 | 659/4000 [19:19<1:37:58, 1.76s/it, lr: 1.0e-04 loss: 5.017e-01]
my_first_lora_v2: 16%|#6 | 660/4000 [19:22<1:38:02, 1.76s/it, lr: 1.0e-04 loss: 4.928e-01]
my_first_lora_v2: 16%|#6 | 660/4000 [19:22<1:38:02, 1.76s/it, lr: 1.0e-04 loss: 4.928e-01]
my_first_lora_v2: 17%|#6 | 661/4000 [19:23<1:37:58, 1.76s/it, lr: 1.0e-04 loss: 5.372e-02]
my_first_lora_v2: 17%|#6 | 661/4000 [19:23<1:37:58, 1.76s/it, lr: 1.0e-04 loss: 5.372e-02]
my_first_lora_v2: 17%|#6 | 662/4000 [19:26<1:38:02, 1.76s/it, lr: 1.0e-04 loss: 9.285e-02]
my_first_lora_v2: 17%|#6 | 662/4000 [19:26<1:38:02, 1.76s/it, lr: 1.0e-04 loss: 9.285e-02]
my_first_lora_v2: 17%|#6 | 663/4000 [19:27<1:37:55, 1.76s/it, lr: 1.0e-04 loss: 1.394e-01]
my_first_lora_v2: 17%|#6 | 663/4000 [19:27<1:37:55, 1.76s/it, lr: 1.0e-04 loss: 1.394e-01]
my_first_lora_v2: 17%|#6 | 664/4000 [19:29<1:37:57, 1.76s/it, lr: 1.0e-04 loss: 1.781e-01]
my_first_lora_v2: 17%|#6 | 664/4000 [19:29<1:37:57, 1.76s/it, lr: 1.0e-04 loss: 1.781e-01]
my_first_lora_v2: 17%|#6 | 665/4000 [19:30<1:37:50, 1.76s/it, lr: 1.0e-04 loss: 8.046e-01]
my_first_lora_v2: 17%|#6 | 665/4000 [19:30<1:37:50, 1.76s/it, lr: 1.0e-04 loss: 8.046e-01]
my_first_lora_v2: 17%|#6 | 666/4000 [19:31<1:37:43, 1.76s/it, lr: 1.0e-04 loss: 1.332e-01]
my_first_lora_v2: 17%|#6 | 666/4000 [19:31<1:37:43, 1.76s/it, lr: 1.0e-04 loss: 1.332e-01]
my_first_lora_v2: 17%|#6 | 667/4000 [19:34<1:37:47, 1.76s/it, lr: 1.0e-04 loss: 1.615e-01]
my_first_lora_v2: 17%|#6 | 667/4000 [19:34<1:37:47, 1.76s/it, lr: 1.0e-04 loss: 1.615e-01]
my_first_lora_v2: 17%|#6 | 668/4000 [19:35<1:37:40, 1.76s/it, lr: 1.0e-04 loss: 5.895e-01]
my_first_lora_v2: 17%|#6 | 668/4000 [19:35<1:37:40, 1.76s/it, lr: 1.0e-04 loss: 5.895e-01]
my_first_lora_v2: 17%|#6 | 669/4000 [19:35<1:37:34, 1.76s/it, lr: 1.0e-04 loss: 6.799e-01]
my_first_lora_v2: 17%|#6 | 669/4000 [19:35<1:37:34, 1.76s/it, lr: 1.0e-04 loss: 6.799e-01]
my_first_lora_v2: 17%|#6 | 670/4000 [19:38<1:37:38, 1.76s/it, lr: 1.0e-04 loss: 4.555e-01]
my_first_lora_v2: 17%|#6 | 670/4000 [19:38<1:37:38, 1.76s/it, lr: 1.0e-04 loss: 4.555e-01]
my_first_lora_v2: 17%|#6 | 671/4000 [19:39<1:37:31, 1.76s/it, lr: 1.0e-04 loss: 3.176e-01]
my_first_lora_v2: 17%|#6 | 671/4000 [19:39<1:37:31, 1.76s/it, lr: 1.0e-04 loss: 3.176e-01]
my_first_lora_v2: 17%|#6 | 672/4000 [19:42<1:37:36, 1.76s/it, lr: 1.0e-04 loss: 6.746e-01]
my_first_lora_v2: 17%|#6 | 672/4000 [19:42<1:37:36, 1.76s/it, lr: 1.0e-04 loss: 6.746e-01]
my_first_lora_v2: 17%|#6 | 673/4000 [19:43<1:37:29, 1.76s/it, lr: 1.0e-04 loss: 2.316e-01]
my_first_lora_v2: 17%|#6 | 673/4000 [19:43<1:37:29, 1.76s/it, lr: 1.0e-04 loss: 2.316e-01]
my_first_lora_v2: 17%|#6 | 674/4000 [19:45<1:37:31, 1.76s/it, lr: 1.0e-04 loss: 1.932e-01]
my_first_lora_v2: 17%|#6 | 674/4000 [19:45<1:37:31, 1.76s/it, lr: 1.0e-04 loss: 1.932e-01]
my_first_lora_v2: 17%|#6 | 675/4000 [19:48<1:37:35, 1.76s/it, lr: 1.0e-04 loss: 2.227e-01]
my_first_lora_v2: 17%|#6 | 675/4000 [19:48<1:37:35, 1.76s/it, lr: 1.0e-04 loss: 2.227e-01]
my_first_lora_v2: 17%|#6 | 676/4000 [19:49<1:37:29, 1.76s/it, lr: 1.0e-04 loss: 6.011e-01]
my_first_lora_v2: 17%|#6 | 676/4000 [19:49<1:37:29, 1.76s/it, lr: 1.0e-04 loss: 6.011e-01]
my_first_lora_v2: 17%|#6 | 677/4000 [19:52<1:37:33, 1.76s/it, lr: 1.0e-04 loss: 5.801e-01]
my_first_lora_v2: 17%|#6 | 677/4000 [19:52<1:37:33, 1.76s/it, lr: 1.0e-04 loss: 5.801e-01]
my_first_lora_v2: 17%|#6 | 678/4000 [19:55<1:37:35, 1.76s/it, lr: 1.0e-04 loss: 6.771e-01]
my_first_lora_v2: 17%|#6 | 678/4000 [19:55<1:37:35, 1.76s/it, lr: 1.0e-04 loss: 6.771e-01]
my_first_lora_v2: 17%|#6 | 679/4000 [19:55<1:37:29, 1.76s/it, lr: 1.0e-04 loss: 3.837e-01]
my_first_lora_v2: 17%|#6 | 679/4000 [19:55<1:37:29, 1.76s/it, lr: 1.0e-04 loss: 3.837e-01]
my_first_lora_v2: 17%|#7 | 680/4000 [19:56<1:37:22, 1.76s/it, lr: 1.0e-04 loss: 6.174e-01]
my_first_lora_v2: 17%|#7 | 680/4000 [19:56<1:37:22, 1.76s/it, lr: 1.0e-04 loss: 6.174e-01]
my_first_lora_v2: 17%|#7 | 681/4000 [19:57<1:37:16, 1.76s/it, lr: 1.0e-04 loss: 5.993e-01]
my_first_lora_v2: 17%|#7 | 681/4000 [19:57<1:37:16, 1.76s/it, lr: 1.0e-04 loss: 5.993e-01]
my_first_lora_v2: 17%|#7 | 682/4000 [20:00<1:37:19, 1.76s/it, lr: 1.0e-04 loss: 2.328e-01]
my_first_lora_v2: 17%|#7 | 682/4000 [20:00<1:37:19, 1.76s/it, lr: 1.0e-04 loss: 2.328e-01]
my_first_lora_v2: 17%|#7 | 683/4000 [20:02<1:37:21, 1.76s/it, lr: 1.0e-04 loss: 6.586e-01]
my_first_lora_v2: 17%|#7 | 683/4000 [20:02<1:37:21, 1.76s/it, lr: 1.0e-04 loss: 6.586e-01]
my_first_lora_v2: 17%|#7 | 684/4000 [20:03<1:37:15, 1.76s/it, lr: 1.0e-04 loss: 2.002e-01]
my_first_lora_v2: 17%|#7 | 684/4000 [20:03<1:37:15, 1.76s/it, lr: 1.0e-04 loss: 2.002e-01]
my_first_lora_v2: 17%|#7 | 685/4000 [20:04<1:37:09, 1.76s/it, lr: 1.0e-04 loss: 1.969e-01]
my_first_lora_v2: 17%|#7 | 685/4000 [20:04<1:37:09, 1.76s/it, lr: 1.0e-04 loss: 1.969e-01]
my_first_lora_v2: 17%|#7 | 686/4000 [20:07<1:37:12, 1.76s/it, lr: 1.0e-04 loss: 1.027e-01]
my_first_lora_v2: 17%|#7 | 686/4000 [20:07<1:37:12, 1.76s/it, lr: 1.0e-04 loss: 1.027e-01]
my_first_lora_v2: 17%|#7 | 687/4000 [20:10<1:37:15, 1.76s/it, lr: 1.0e-04 loss: 5.849e-01]
my_first_lora_v2: 17%|#7 | 687/4000 [20:10<1:37:15, 1.76s/it, lr: 1.0e-04 loss: 5.849e-01]
my_first_lora_v2: 17%|#7 | 688/4000 [20:10<1:37:08, 1.76s/it, lr: 1.0e-04 loss: 3.441e-01]
my_first_lora_v2: 17%|#7 | 688/4000 [20:10<1:37:08, 1.76s/it, lr: 1.0e-04 loss: 3.441e-01]
my_first_lora_v2: 17%|#7 | 689/4000 [20:13<1:37:12, 1.76s/it, lr: 1.0e-04 loss: 5.616e-01]
my_first_lora_v2: 17%|#7 | 689/4000 [20:13<1:37:12, 1.76s/it, lr: 1.0e-04 loss: 5.616e-01]
my_first_lora_v2: 17%|#7 | 690/4000 [20:14<1:37:08, 1.76s/it, lr: 1.0e-04 loss: 2.340e-01]
my_first_lora_v2: 17%|#7 | 690/4000 [20:14<1:37:08, 1.76s/it, lr: 1.0e-04 loss: 2.340e-01]
my_first_lora_v2: 17%|#7 | 691/4000 [20:15<1:37:01, 1.76s/it, lr: 1.0e-04 loss: 6.430e-01]
my_first_lora_v2: 17%|#7 | 691/4000 [20:15<1:37:01, 1.76s/it, lr: 1.0e-04 loss: 6.430e-01]
my_first_lora_v2: 17%|#7 | 692/4000 [20:16<1:36:55, 1.76s/it, lr: 1.0e-04 loss: 1.209e-01]
my_first_lora_v2: 17%|#7 | 692/4000 [20:16<1:36:55, 1.76s/it, lr: 1.0e-04 loss: 1.209e-01]
my_first_lora_v2: 17%|#7 | 693/4000 [20:17<1:36:49, 1.76s/it, lr: 1.0e-04 loss: 6.412e-01]
my_first_lora_v2: 17%|#7 | 693/4000 [20:17<1:36:49, 1.76s/it, lr: 1.0e-04 loss: 6.412e-01]
my_first_lora_v2: 17%|#7 | 694/4000 [20:20<1:36:52, 1.76s/it, lr: 1.0e-04 loss: 6.831e-01]
my_first_lora_v2: 17%|#7 | 694/4000 [20:20<1:36:52, 1.76s/it, lr: 1.0e-04 loss: 6.831e-01]
my_first_lora_v2: 17%|#7 | 695/4000 [20:20<1:36:45, 1.76s/it, lr: 1.0e-04 loss: 7.956e-01]
my_first_lora_v2: 17%|#7 | 695/4000 [20:20<1:36:45, 1.76s/it, lr: 1.0e-04 loss: 7.956e-01]
my_first_lora_v2: 17%|#7 | 696/4000 [20:21<1:36:39, 1.76s/it, lr: 1.0e-04 loss: 5.197e-01]
my_first_lora_v2: 17%|#7 | 696/4000 [20:21<1:36:39, 1.76s/it, lr: 1.0e-04 loss: 5.197e-01]
my_first_lora_v2: 17%|#7 | 697/4000 [20:22<1:36:33, 1.75s/it, lr: 1.0e-04 loss: 5.484e-01]
my_first_lora_v2: 17%|#7 | 697/4000 [20:22<1:36:33, 1.75s/it, lr: 1.0e-04 loss: 5.484e-01]
my_first_lora_v2: 17%|#7 | 698/4000 [20:23<1:36:27, 1.75s/it, lr: 1.0e-04 loss: 4.552e-01]
my_first_lora_v2: 17%|#7 | 698/4000 [20:23<1:36:27, 1.75s/it, lr: 1.0e-04 loss: 4.552e-01]
my_first_lora_v2: 17%|#7 | 699/4000 [20:26<1:36:30, 1.75s/it, lr: 1.0e-04 loss: 1.505e-01]
my_first_lora_v2: 17%|#7 | 699/4000 [20:26<1:36:30, 1.75s/it, lr: 1.0e-04 loss: 1.505e-01]
my_first_lora_v2: 18%|#7 | 700/4000 [20:28<1:36:31, 1.76s/it, lr: 1.0e-04 loss: 4.343e-01]
my_first_lora_v2: 18%|#7 | 700/4000 [20:28<1:36:31, 1.76s/it, lr: 1.0e-04 loss: 4.343e-01]
my_first_lora_v2: 18%|#7 | 701/4000 [20:31<1:36:35, 1.76s/it, lr: 1.0e-04 loss: 6.733e-01]
my_first_lora_v2: 18%|#7 | 701/4000 [20:31<1:36:35, 1.76s/it, lr: 1.0e-04 loss: 6.733e-01]
my_first_lora_v2: 18%|#7 | 702/4000 [20:34<1:36:38, 1.76s/it, lr: 1.0e-04 loss: 3.543e-01]
my_first_lora_v2: 18%|#7 | 702/4000 [20:34<1:36:38, 1.76s/it, lr: 1.0e-04 loss: 3.543e-01]
my_first_lora_v2: 18%|#7 | 703/4000 [20:37<1:36:41, 1.76s/it, lr: 1.0e-04 loss: 3.568e-01]
my_first_lora_v2: 18%|#7 | 703/4000 [20:37<1:36:41, 1.76s/it, lr: 1.0e-04 loss: 3.568e-01]
my_first_lora_v2: 18%|#7 | 704/4000 [20:37<1:36:35, 1.76s/it, lr: 1.0e-04 loss: 6.363e-01]
my_first_lora_v2: 18%|#7 | 704/4000 [20:37<1:36:35, 1.76s/it, lr: 1.0e-04 loss: 6.363e-01]
my_first_lora_v2: 18%|#7 | 705/4000 [20:40<1:36:39, 1.76s/it, lr: 1.0e-04 loss: 6.635e-01]
my_first_lora_v2: 18%|#7 | 705/4000 [20:40<1:36:39, 1.76s/it, lr: 1.0e-04 loss: 6.635e-01]
my_first_lora_v2: 18%|#7 | 706/4000 [20:41<1:36:32, 1.76s/it, lr: 1.0e-04 loss: 3.994e-01]
my_first_lora_v2: 18%|#7 | 706/4000 [20:41<1:36:32, 1.76s/it, lr: 1.0e-04 loss: 3.994e-01]
my_first_lora_v2: 18%|#7 | 707/4000 [20:42<1:36:26, 1.76s/it, lr: 1.0e-04 loss: 7.338e-01]
my_first_lora_v2: 18%|#7 | 707/4000 [20:42<1:36:26, 1.76s/it, lr: 1.0e-04 loss: 7.338e-01]
my_first_lora_v2: 18%|#7 | 708/4000 [20:44<1:36:28, 1.76s/it, lr: 1.0e-04 loss: 5.792e-01]
my_first_lora_v2: 18%|#7 | 708/4000 [20:44<1:36:28, 1.76s/it, lr: 1.0e-04 loss: 5.792e-01]
my_first_lora_v2: 18%|#7 | 709/4000 [20:45<1:36:22, 1.76s/it, lr: 1.0e-04 loss: 3.006e-01]
my_first_lora_v2: 18%|#7 | 709/4000 [20:45<1:36:22, 1.76s/it, lr: 1.0e-04 loss: 3.006e-01]
my_first_lora_v2: 18%|#7 | 710/4000 [20:48<1:36:26, 1.76s/it, lr: 1.0e-04 loss: 3.315e-01]
my_first_lora_v2: 18%|#7 | 710/4000 [20:48<1:36:26, 1.76s/it, lr: 1.0e-04 loss: 3.315e-01]
my_first_lora_v2: 18%|#7 | 711/4000 [20:49<1:36:20, 1.76s/it, lr: 1.0e-04 loss: 5.445e-01]
my_first_lora_v2: 18%|#7 | 711/4000 [20:49<1:36:20, 1.76s/it, lr: 1.0e-04 loss: 5.445e-01]
my_first_lora_v2: 18%|#7 | 712/4000 [20:52<1:36:23, 1.76s/it, lr: 1.0e-04 loss: 9.487e-02]
my_first_lora_v2: 18%|#7 | 712/4000 [20:52<1:36:23, 1.76s/it, lr: 1.0e-04 loss: 9.487e-02]
my_first_lora_v2: 18%|#7 | 713/4000 [20:55<1:36:26, 1.76s/it, lr: 1.0e-04 loss: 6.444e-01]
my_first_lora_v2: 18%|#7 | 713/4000 [20:55<1:36:26, 1.76s/it, lr: 1.0e-04 loss: 6.444e-01]
my_first_lora_v2: 18%|#7 | 714/4000 [20:56<1:36:21, 1.76s/it, lr: 1.0e-04 loss: 5.051e-01]
my_first_lora_v2: 18%|#7 | 714/4000 [20:56<1:36:21, 1.76s/it, lr: 1.0e-04 loss: 5.051e-01]
my_first_lora_v2: 18%|#7 | 715/4000 [20:56<1:36:14, 1.76s/it, lr: 1.0e-04 loss: 1.771e-01]
my_first_lora_v2: 18%|#7 | 715/4000 [20:56<1:36:14, 1.76s/it, lr: 1.0e-04 loss: 1.771e-01]
my_first_lora_v2: 18%|#7 | 716/4000 [20:59<1:36:18, 1.76s/it, lr: 1.0e-04 loss: 3.185e-01]
my_first_lora_v2: 18%|#7 | 716/4000 [20:59<1:36:18, 1.76s/it, lr: 1.0e-04 loss: 3.185e-01]
my_first_lora_v2: 18%|#7 | 717/4000 [21:02<1:36:21, 1.76s/it, lr: 1.0e-04 loss: 6.684e-01]
my_first_lora_v2: 18%|#7 | 717/4000 [21:02<1:36:21, 1.76s/it, lr: 1.0e-04 loss: 6.684e-01]
my_first_lora_v2: 18%|#7 | 718/4000 [21:03<1:36:14, 1.76s/it, lr: 1.0e-04 loss: 2.948e-01]
my_first_lora_v2: 18%|#7 | 718/4000 [21:03<1:36:14, 1.76s/it, lr: 1.0e-04 loss: 2.948e-01]
my_first_lora_v2: 18%|#7 | 719/4000 [21:05<1:36:16, 1.76s/it, lr: 1.0e-04 loss: 5.675e-01]
my_first_lora_v2: 18%|#7 | 719/4000 [21:05<1:36:16, 1.76s/it, lr: 1.0e-04 loss: 5.675e-01]
my_first_lora_v2: 18%|#8 | 720/4000 [21:06<1:36:11, 1.76s/it, lr: 1.0e-04 loss: 1.113e-01]
my_first_lora_v2: 18%|#8 | 720/4000 [21:06<1:36:11, 1.76s/it, lr: 1.0e-04 loss: 1.113e-01]
my_first_lora_v2: 18%|#8 | 721/4000 [21:07<1:36:05, 1.76s/it, lr: 1.0e-04 loss: 3.730e-01]
my_first_lora_v2: 18%|#8 | 721/4000 [21:07<1:36:05, 1.76s/it, lr: 1.0e-04 loss: 3.730e-01]
my_first_lora_v2: 18%|#8 | 722/4000 [21:08<1:35:59, 1.76s/it, lr: 1.0e-04 loss: 6.495e-01]
my_first_lora_v2: 18%|#8 | 722/4000 [21:08<1:35:59, 1.76s/it, lr: 1.0e-04 loss: 6.495e-01]
my_first_lora_v2: 18%|#8 | 723/4000 [21:11<1:36:02, 1.76s/it, lr: 1.0e-04 loss: 6.039e-01]
my_first_lora_v2: 18%|#8 | 723/4000 [21:11<1:36:02, 1.76s/it, lr: 1.0e-04 loss: 6.039e-01]
my_first_lora_v2: 18%|#8 | 724/4000 [21:14<1:36:06, 1.76s/it, lr: 1.0e-04 loss: 5.061e-01]
my_first_lora_v2: 18%|#8 | 724/4000 [21:14<1:36:06, 1.76s/it, lr: 1.0e-04 loss: 5.061e-01]
my_first_lora_v2: 18%|#8 | 725/4000 [21:17<1:36:08, 1.76s/it, lr: 1.0e-04 loss: 4.622e-01]
my_first_lora_v2: 18%|#8 | 725/4000 [21:17<1:36:08, 1.76s/it, lr: 1.0e-04 loss: 4.622e-01]
my_first_lora_v2: 18%|#8 | 726/4000 [21:19<1:36:11, 1.76s/it, lr: 1.0e-04 loss: 4.313e-01]
my_first_lora_v2: 18%|#8 | 726/4000 [21:19<1:36:11, 1.76s/it, lr: 1.0e-04 loss: 4.313e-01]
my_first_lora_v2: 18%|#8 | 727/4000 [21:20<1:36:05, 1.76s/it, lr: 1.0e-04 loss: 7.350e-01]
my_first_lora_v2: 18%|#8 | 727/4000 [21:20<1:36:05, 1.76s/it, lr: 1.0e-04 loss: 7.350e-01]
my_first_lora_v2: 18%|#8 | 728/4000 [21:23<1:36:08, 1.76s/it, lr: 1.0e-04 loss: 2.175e-01]
my_first_lora_v2: 18%|#8 | 728/4000 [21:23<1:36:08, 1.76s/it, lr: 1.0e-04 loss: 2.175e-01]
my_first_lora_v2: 18%|#8 | 729/4000 [21:26<1:36:12, 1.76s/it, lr: 1.0e-04 loss: 6.672e-02]
my_first_lora_v2: 18%|#8 | 729/4000 [21:26<1:36:12, 1.76s/it, lr: 1.0e-04 loss: 6.672e-02]
my_first_lora_v2: 18%|#8 | 730/4000 [21:27<1:36:08, 1.76s/it, lr: 1.0e-04 loss: 7.977e-01]
my_first_lora_v2: 18%|#8 | 730/4000 [21:27<1:36:08, 1.76s/it, lr: 1.0e-04 loss: 7.977e-01]
my_first_lora_v2: 18%|#8 | 731/4000 [21:30<1:36:12, 1.77s/it, lr: 1.0e-04 loss: 4.297e-01]
my_first_lora_v2: 18%|#8 | 731/4000 [21:30<1:36:12, 1.77s/it, lr: 1.0e-04 loss: 4.297e-01]
my_first_lora_v2: 18%|#8 | 732/4000 [21:31<1:36:05, 1.76s/it, lr: 1.0e-04 loss: 6.190e-01]
my_first_lora_v2: 18%|#8 | 732/4000 [21:31<1:36:05, 1.76s/it, lr: 1.0e-04 loss: 6.190e-01]
my_first_lora_v2: 18%|#8 | 733/4000 [21:32<1:35:59, 1.76s/it, lr: 1.0e-04 loss: 6.728e-01]
my_first_lora_v2: 18%|#8 | 733/4000 [21:32<1:35:59, 1.76s/it, lr: 1.0e-04 loss: 6.728e-01]
my_first_lora_v2: 18%|#8 | 734/4000 [21:35<1:36:02, 1.76s/it, lr: 1.0e-04 loss: 6.478e-01]
my_first_lora_v2: 18%|#8 | 734/4000 [21:35<1:36:02, 1.76s/it, lr: 1.0e-04 loss: 6.478e-01]
my_first_lora_v2: 18%|#8 | 735/4000 [21:38<1:36:06, 1.77s/it, lr: 1.0e-04 loss: 6.951e-01]
my_first_lora_v2: 18%|#8 | 735/4000 [21:38<1:36:06, 1.77s/it, lr: 1.0e-04 loss: 6.951e-01]
my_first_lora_v2: 18%|#8 | 736/4000 [21:38<1:36:00, 1.76s/it, lr: 1.0e-04 loss: 1.521e-01]
my_first_lora_v2: 18%|#8 | 736/4000 [21:38<1:36:00, 1.76s/it, lr: 1.0e-04 loss: 1.521e-01]
my_first_lora_v2: 18%|#8 | 737/4000 [21:41<1:36:03, 1.77s/it, lr: 1.0e-04 loss: 3.152e-01]
my_first_lora_v2: 18%|#8 | 737/4000 [21:41<1:36:03, 1.77s/it, lr: 1.0e-04 loss: 3.152e-01]
my_first_lora_v2: 18%|#8 | 738/4000 [21:42<1:35:57, 1.77s/it, lr: 1.0e-04 loss: 2.715e-01]
my_first_lora_v2: 18%|#8 | 738/4000 [21:42<1:35:57, 1.77s/it, lr: 1.0e-04 loss: 2.715e-01]
my_first_lora_v2: 18%|#8 | 739/4000 [21:45<1:36:00, 1.77s/it, lr: 1.0e-04 loss: 5.640e-01]
my_first_lora_v2: 18%|#8 | 739/4000 [21:45<1:36:00, 1.77s/it, lr: 1.0e-04 loss: 5.640e-01]
my_first_lora_v2: 18%|#8 | 740/4000 [21:48<1:36:03, 1.77s/it, lr: 1.0e-04 loss: 4.297e-01]
my_first_lora_v2: 18%|#8 | 740/4000 [21:48<1:36:03, 1.77s/it, lr: 1.0e-04 loss: 4.297e-01]
my_first_lora_v2: 19%|#8 | 741/4000 [21:49<1:35:58, 1.77s/it, lr: 1.0e-04 loss: 4.174e-01]
my_first_lora_v2: 19%|#8 | 741/4000 [21:49<1:35:58, 1.77s/it, lr: 1.0e-04 loss: 4.174e-01]
my_first_lora_v2: 19%|#8 | 742/4000 [21:50<1:35:52, 1.77s/it, lr: 1.0e-04 loss: 6.585e-02]
my_first_lora_v2: 19%|#8 | 742/4000 [21:50<1:35:52, 1.77s/it, lr: 1.0e-04 loss: 6.585e-02]
my_first_lora_v2: 19%|#8 | 743/4000 [21:51<1:35:47, 1.76s/it, lr: 1.0e-04 loss: 3.282e-01]
my_first_lora_v2: 19%|#8 | 743/4000 [21:51<1:35:47, 1.76s/it, lr: 1.0e-04 loss: 3.282e-01]
my_first_lora_v2: 19%|#8 | 744/4000 [21:53<1:35:49, 1.77s/it, lr: 1.0e-04 loss: 5.660e-01]
my_first_lora_v2: 19%|#8 | 744/4000 [21:53<1:35:49, 1.77s/it, lr: 1.0e-04 loss: 5.660e-01]
my_first_lora_v2: 19%|#8 | 745/4000 [21:56<1:35:52, 1.77s/it, lr: 1.0e-04 loss: 6.907e-01]
my_first_lora_v2: 19%|#8 | 745/4000 [21:56<1:35:52, 1.77s/it, lr: 1.0e-04 loss: 6.907e-01]
my_first_lora_v2: 19%|#8 | 746/4000 [21:59<1:35:55, 1.77s/it, lr: 1.0e-04 loss: 5.685e-01]
my_first_lora_v2: 19%|#8 | 746/4000 [21:59<1:35:55, 1.77s/it, lr: 1.0e-04 loss: 5.685e-01]
my_first_lora_v2: 19%|#8 | 747/4000 [22:02<1:35:57, 1.77s/it, lr: 1.0e-04 loss: 4.624e-01]
my_first_lora_v2: 19%|#8 | 747/4000 [22:02<1:35:57, 1.77s/it, lr: 1.0e-04 loss: 4.624e-01]
my_first_lora_v2: 19%|#8 | 748/4000 [22:04<1:35:58, 1.77s/it, lr: 1.0e-04 loss: 1.779e-01]
my_first_lora_v2: 19%|#8 | 748/4000 [22:04<1:35:58, 1.77s/it, lr: 1.0e-04 loss: 1.779e-01]
my_first_lora_v2: 19%|#8 | 749/4000 [22:05<1:35:53, 1.77s/it, lr: 1.0e-04 loss: 7.021e-01]
my_first_lora_v2: 19%|#8 | 749/4000 [22:05<1:35:53, 1.77s/it, lr: 1.0e-04 loss: 7.021e-01] |
| Saving at step 750 |
| Saved checkpoint to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v2/my_first_lora_v2_000000750.safetensors |
| Saved optimizer to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v2/optimizer.pt |
| Unloading assistant lora |
|
|
|
|
|
Generating Images: 0%| | 0/3 [00:00<?, ?it/s]
Generating Images: 0%| | 0/3 [00:00<?, ?it/s][A[A |
|
|
|
Generating Images: 33%|###3 | 1/3 [00:07<00:15, 7.89s/it]
Generating Images: 33%|###3 | 1/3 [00:07<00:15, 7.89s/it][A[A |
|
|
|
Generating Images: 67%|######6 | 2/3 [00:15<00:07, 7.83s/it]
Generating Images: 67%|######6 | 2/3 [00:15<00:07, 7.83s/it][A[A |
|
|
|
Generating Images: 100%|##########| 3/3 [00:23<00:00, 7.79s/it]
Generating Images: 100%|##########| 3/3 [00:23<00:00, 7.79s/it][A[A |
|
|
|
[A[ALoading assistant lora |
|
my_first_lora_v2: 19%|#8 | 750/4000 [22:06<1:35:48, 1.77s/it, lr: 1.0e-04 loss: 8.394e-01]
my_first_lora_v2: 19%|#8 | 750/4000 [22:06<1:35:48, 1.77s/it, lr: 1.0e-04 loss: 8.394e-01]
my_first_lora_v2: 19%|#8 | 751/4000 [22:07<1:35:42, 1.77s/it, lr: 1.0e-04 loss: 1.746e-01]
my_first_lora_v2: 19%|#8 | 751/4000 [22:07<1:35:42, 1.77s/it, lr: 1.0e-04 loss: 1.746e-01]
my_first_lora_v2: 19%|#8 | 752/4000 [22:08<1:35:36, 1.77s/it, lr: 1.0e-04 loss: 1.277e-01]
my_first_lora_v2: 19%|#8 | 752/4000 [22:08<1:35:36, 1.77s/it, lr: 1.0e-04 loss: 1.277e-01]
my_first_lora_v2: 19%|#8 | 753/4000 [22:08<1:35:30, 1.76s/it, lr: 1.0e-04 loss: 4.612e-01]
my_first_lora_v2: 19%|#8 | 753/4000 [22:08<1:35:30, 1.76s/it, lr: 1.0e-04 loss: 4.612e-01]
my_first_lora_v2: 19%|#8 | 754/4000 [22:09<1:35:24, 1.76s/it, lr: 1.0e-04 loss: 4.419e-01]
my_first_lora_v2: 19%|#8 | 754/4000 [22:09<1:35:24, 1.76s/it, lr: 1.0e-04 loss: 4.419e-01]
my_first_lora_v2: 19%|#8 | 755/4000 [22:12<1:35:27, 1.77s/it, lr: 1.0e-04 loss: 7.345e-01]
my_first_lora_v2: 19%|#8 | 755/4000 [22:12<1:35:27, 1.77s/it, lr: 1.0e-04 loss: 7.345e-01]
my_first_lora_v2: 19%|#8 | 756/4000 [22:13<1:35:22, 1.76s/it, lr: 1.0e-04 loss: 7.684e-01]
my_first_lora_v2: 19%|#8 | 756/4000 [22:13<1:35:22, 1.76s/it, lr: 1.0e-04 loss: 7.684e-01]
my_first_lora_v2: 19%|#8 | 757/4000 [22:14<1:35:16, 1.76s/it, lr: 1.0e-04 loss: 5.880e-01]
my_first_lora_v2: 19%|#8 | 757/4000 [22:14<1:35:16, 1.76s/it, lr: 1.0e-04 loss: 5.880e-01]
my_first_lora_v2: 19%|#8 | 758/4000 [22:15<1:35:10, 1.76s/it, lr: 1.0e-04 loss: 1.154e-01]
my_first_lora_v2: 19%|#8 | 758/4000 [22:15<1:35:10, 1.76s/it, lr: 1.0e-04 loss: 1.154e-01]
my_first_lora_v2: 19%|#8 | 759/4000 [22:15<1:35:04, 1.76s/it, lr: 1.0e-04 loss: 7.416e-01]
my_first_lora_v2: 19%|#8 | 759/4000 [22:15<1:35:04, 1.76s/it, lr: 1.0e-04 loss: 7.416e-01]
my_first_lora_v2: 19%|#9 | 760/4000 [22:16<1:34:58, 1.76s/it, lr: 1.0e-04 loss: 3.980e-01]
my_first_lora_v2: 19%|#9 | 760/4000 [22:16<1:34:58, 1.76s/it, lr: 1.0e-04 loss: 3.980e-01]
my_first_lora_v2: 19%|#9 | 761/4000 [22:19<1:35:02, 1.76s/it, lr: 1.0e-04 loss: 6.617e-01]
my_first_lora_v2: 19%|#9 | 761/4000 [22:19<1:35:02, 1.76s/it, lr: 1.0e-04 loss: 6.617e-01]
my_first_lora_v2: 19%|#9 | 762/4000 [22:20<1:34:57, 1.76s/it, lr: 1.0e-04 loss: 8.342e-02]
my_first_lora_v2: 19%|#9 | 762/4000 [22:20<1:34:57, 1.76s/it, lr: 1.0e-04 loss: 8.342e-02]
my_first_lora_v2: 19%|#9 | 763/4000 [22:23<1:34:59, 1.76s/it, lr: 1.0e-04 loss: 1.581e-01]
my_first_lora_v2: 19%|#9 | 763/4000 [22:23<1:34:59, 1.76s/it, lr: 1.0e-04 loss: 1.581e-01]
my_first_lora_v2: 19%|#9 | 764/4000 [22:24<1:34:53, 1.76s/it, lr: 1.0e-04 loss: 4.835e-01]
my_first_lora_v2: 19%|#9 | 764/4000 [22:24<1:34:53, 1.76s/it, lr: 1.0e-04 loss: 4.835e-01]
my_first_lora_v2: 19%|#9 | 765/4000 [22:25<1:34:48, 1.76s/it, lr: 1.0e-04 loss: 2.759e-01]
my_first_lora_v2: 19%|#9 | 765/4000 [22:25<1:34:48, 1.76s/it, lr: 1.0e-04 loss: 2.759e-01]
my_first_lora_v2: 19%|#9 | 766/4000 [22:25<1:34:42, 1.76s/it, lr: 1.0e-04 loss: 6.038e-01]
my_first_lora_v2: 19%|#9 | 766/4000 [22:25<1:34:42, 1.76s/it, lr: 1.0e-04 loss: 6.038e-01]
my_first_lora_v2: 19%|#9 | 767/4000 [22:28<1:34:44, 1.76s/it, lr: 1.0e-04 loss: 2.490e-01]
my_first_lora_v2: 19%|#9 | 767/4000 [22:28<1:34:44, 1.76s/it, lr: 1.0e-04 loss: 2.490e-01]
my_first_lora_v2: 19%|#9 | 768/4000 [22:31<1:34:47, 1.76s/it, lr: 1.0e-04 loss: 5.861e-01]
my_first_lora_v2: 19%|#9 | 768/4000 [22:31<1:34:47, 1.76s/it, lr: 1.0e-04 loss: 5.861e-01]
my_first_lora_v2: 19%|#9 | 769/4000 [22:34<1:34:50, 1.76s/it, lr: 1.0e-04 loss: 4.847e-01]
my_first_lora_v2: 19%|#9 | 769/4000 [22:34<1:34:50, 1.76s/it, lr: 1.0e-04 loss: 4.847e-01]
my_first_lora_v2: 19%|#9 | 770/4000 [22:37<1:34:52, 1.76s/it, lr: 1.0e-04 loss: 6.200e-01]
my_first_lora_v2: 19%|#9 | 770/4000 [22:37<1:34:52, 1.76s/it, lr: 1.0e-04 loss: 6.200e-01]
my_first_lora_v2: 19%|#9 | 771/4000 [22:37<1:34:47, 1.76s/it, lr: 1.0e-04 loss: 6.057e-01]
my_first_lora_v2: 19%|#9 | 771/4000 [22:37<1:34:47, 1.76s/it, lr: 1.0e-04 loss: 6.057e-01]
my_first_lora_v2: 19%|#9 | 772/4000 [22:38<1:34:41, 1.76s/it, lr: 1.0e-04 loss: 5.891e-01]
my_first_lora_v2: 19%|#9 | 772/4000 [22:38<1:34:41, 1.76s/it, lr: 1.0e-04 loss: 5.891e-01]
my_first_lora_v2: 19%|#9 | 773/4000 [22:41<1:34:44, 1.76s/it, lr: 1.0e-04 loss: 6.597e-01]
my_first_lora_v2: 19%|#9 | 773/4000 [22:41<1:34:44, 1.76s/it, lr: 1.0e-04 loss: 6.597e-01]
my_first_lora_v2: 19%|#9 | 774/4000 [22:44<1:34:45, 1.76s/it, lr: 1.0e-04 loss: 3.247e-01]
my_first_lora_v2: 19%|#9 | 774/4000 [22:44<1:34:45, 1.76s/it, lr: 1.0e-04 loss: 3.247e-01]
my_first_lora_v2: 19%|#9 | 775/4000 [22:44<1:34:40, 1.76s/it, lr: 1.0e-04 loss: 2.363e-01]
my_first_lora_v2: 19%|#9 | 775/4000 [22:44<1:34:40, 1.76s/it, lr: 1.0e-04 loss: 2.363e-01]
my_first_lora_v2: 19%|#9 | 776/4000 [22:46<1:34:35, 1.76s/it, lr: 1.0e-04 loss: 3.992e-01]
my_first_lora_v2: 19%|#9 | 776/4000 [22:46<1:34:35, 1.76s/it, lr: 1.0e-04 loss: 3.992e-01]
my_first_lora_v2: 19%|#9 | 777/4000 [22:46<1:34:29, 1.76s/it, lr: 1.0e-04 loss: 1.299e-01]
my_first_lora_v2: 19%|#9 | 777/4000 [22:46<1:34:29, 1.76s/it, lr: 1.0e-04 loss: 1.299e-01]
my_first_lora_v2: 19%|#9 | 778/4000 [22:49<1:34:32, 1.76s/it, lr: 1.0e-04 loss: 7.012e-01]
my_first_lora_v2: 19%|#9 | 778/4000 [22:49<1:34:32, 1.76s/it, lr: 1.0e-04 loss: 7.012e-01]
my_first_lora_v2: 19%|#9 | 779/4000 [22:52<1:34:35, 1.76s/it, lr: 1.0e-04 loss: 1.243e-01]
my_first_lora_v2: 19%|#9 | 779/4000 [22:52<1:34:35, 1.76s/it, lr: 1.0e-04 loss: 1.243e-01]
my_first_lora_v2: 20%|#9 | 780/4000 [22:53<1:34:30, 1.76s/it, lr: 1.0e-04 loss: 5.217e-01]
my_first_lora_v2: 20%|#9 | 780/4000 [22:53<1:34:30, 1.76s/it, lr: 1.0e-04 loss: 5.217e-01]
my_first_lora_v2: 20%|#9 | 781/4000 [22:55<1:34:31, 1.76s/it, lr: 1.0e-04 loss: 6.420e-01]
my_first_lora_v2: 20%|#9 | 781/4000 [22:55<1:34:31, 1.76s/it, lr: 1.0e-04 loss: 6.420e-01]
my_first_lora_v2: 20%|#9 | 782/4000 [22:58<1:34:34, 1.76s/it, lr: 1.0e-04 loss: 5.023e-01]
my_first_lora_v2: 20%|#9 | 782/4000 [22:58<1:34:34, 1.76s/it, lr: 1.0e-04 loss: 5.023e-01]
my_first_lora_v2: 20%|#9 | 783/4000 [22:59<1:34:28, 1.76s/it, lr: 1.0e-04 loss: 9.178e-02]
my_first_lora_v2: 20%|#9 | 783/4000 [22:59<1:34:28, 1.76s/it, lr: 1.0e-04 loss: 9.178e-02]
my_first_lora_v2: 20%|#9 | 784/4000 [23:00<1:34:22, 1.76s/it, lr: 1.0e-04 loss: 2.365e-01]
my_first_lora_v2: 20%|#9 | 784/4000 [23:00<1:34:22, 1.76s/it, lr: 1.0e-04 loss: 2.365e-01]
my_first_lora_v2: 20%|#9 | 785/4000 [23:03<1:34:24, 1.76s/it, lr: 1.0e-04 loss: 1.570e-01]
my_first_lora_v2: 20%|#9 | 785/4000 [23:03<1:34:24, 1.76s/it, lr: 1.0e-04 loss: 1.570e-01]
my_first_lora_v2: 20%|#9 | 786/4000 [23:03<1:34:19, 1.76s/it, lr: 1.0e-04 loss: 1.649e-01]
my_first_lora_v2: 20%|#9 | 786/4000 [23:03<1:34:19, 1.76s/it, lr: 1.0e-04 loss: 1.649e-01]
my_first_lora_v2: 20%|#9 | 787/4000 [23:06<1:34:21, 1.76s/it, lr: 1.0e-04 loss: 9.563e-02]
my_first_lora_v2: 20%|#9 | 787/4000 [23:06<1:34:21, 1.76s/it, lr: 1.0e-04 loss: 9.563e-02]
my_first_lora_v2: 20%|#9 | 788/4000 [23:07<1:34:15, 1.76s/it, lr: 1.0e-04 loss: 6.175e-01]
my_first_lora_v2: 20%|#9 | 788/4000 [23:07<1:34:15, 1.76s/it, lr: 1.0e-04 loss: 6.175e-01]
my_first_lora_v2: 20%|#9 | 789/4000 [23:10<1:34:18, 1.76s/it, lr: 1.0e-04 loss: 2.055e-01]
my_first_lora_v2: 20%|#9 | 789/4000 [23:10<1:34:18, 1.76s/it, lr: 1.0e-04 loss: 2.055e-01]
my_first_lora_v2: 20%|#9 | 790/4000 [23:11<1:34:14, 1.76s/it, lr: 1.0e-04 loss: 1.102e-01]
my_first_lora_v2: 20%|#9 | 790/4000 [23:11<1:34:14, 1.76s/it, lr: 1.0e-04 loss: 1.102e-01]
my_first_lora_v2: 20%|#9 | 791/4000 [23:14<1:34:15, 1.76s/it, lr: 1.0e-04 loss: 5.792e-01]
my_first_lora_v2: 20%|#9 | 791/4000 [23:14<1:34:15, 1.76s/it, lr: 1.0e-04 loss: 5.792e-01]
my_first_lora_v2: 20%|#9 | 792/4000 [23:14<1:34:09, 1.76s/it, lr: 1.0e-04 loss: 5.791e-01]
my_first_lora_v2: 20%|#9 | 792/4000 [23:14<1:34:09, 1.76s/it, lr: 1.0e-04 loss: 5.791e-01]
my_first_lora_v2: 20%|#9 | 793/4000 [23:15<1:34:04, 1.76s/it, lr: 1.0e-04 loss: 3.925e-01]
my_first_lora_v2: 20%|#9 | 793/4000 [23:15<1:34:04, 1.76s/it, lr: 1.0e-04 loss: 3.925e-01]
my_first_lora_v2: 20%|#9 | 794/4000 [23:18<1:34:07, 1.76s/it, lr: 1.0e-04 loss: 9.869e-02]
my_first_lora_v2: 20%|#9 | 794/4000 [23:18<1:34:07, 1.76s/it, lr: 1.0e-04 loss: 9.869e-02]
my_first_lora_v2: 20%|#9 | 795/4000 [23:19<1:34:01, 1.76s/it, lr: 1.0e-04 loss: 6.943e-01]
my_first_lora_v2: 20%|#9 | 795/4000 [23:19<1:34:01, 1.76s/it, lr: 1.0e-04 loss: 6.943e-01]
my_first_lora_v2: 20%|#9 | 796/4000 [23:22<1:34:03, 1.76s/it, lr: 1.0e-04 loss: 1.040e-01]
my_first_lora_v2: 20%|#9 | 796/4000 [23:22<1:34:03, 1.76s/it, lr: 1.0e-04 loss: 1.040e-01]
my_first_lora_v2: 20%|#9 | 797/4000 [23:24<1:34:06, 1.76s/it, lr: 1.0e-04 loss: 5.603e-01]
my_first_lora_v2: 20%|#9 | 797/4000 [23:24<1:34:06, 1.76s/it, lr: 1.0e-04 loss: 5.603e-01]
my_first_lora_v2: 20%|#9 | 798/4000 [23:25<1:34:00, 1.76s/it, lr: 1.0e-04 loss: 5.318e-01]
my_first_lora_v2: 20%|#9 | 798/4000 [23:25<1:34:00, 1.76s/it, lr: 1.0e-04 loss: 5.318e-01]
my_first_lora_v2: 20%|#9 | 799/4000 [23:26<1:33:55, 1.76s/it, lr: 1.0e-04 loss: 2.546e-01]
my_first_lora_v2: 20%|#9 | 799/4000 [23:26<1:33:55, 1.76s/it, lr: 1.0e-04 loss: 2.546e-01]
my_first_lora_v2: 20%|## | 800/4000 [23:27<1:33:49, 1.76s/it, lr: 1.0e-04 loss: 1.083e-01]
my_first_lora_v2: 20%|## | 800/4000 [23:27<1:33:49, 1.76s/it, lr: 1.0e-04 loss: 1.083e-01]
my_first_lora_v2: 20%|## | 801/4000 [23:28<1:33:44, 1.76s/it, lr: 1.0e-04 loss: 4.164e-01]
my_first_lora_v2: 20%|## | 801/4000 [23:28<1:33:44, 1.76s/it, lr: 1.0e-04 loss: 4.164e-01]
my_first_lora_v2: 20%|## | 802/4000 [23:29<1:33:38, 1.76s/it, lr: 1.0e-04 loss: 2.602e-01]
my_first_lora_v2: 20%|## | 802/4000 [23:29<1:33:38, 1.76s/it, lr: 1.0e-04 loss: 2.602e-01]
my_first_lora_v2: 20%|## | 803/4000 [23:30<1:33:34, 1.76s/it, lr: 1.0e-04 loss: 2.439e-01]
my_first_lora_v2: 20%|## | 803/4000 [23:30<1:33:34, 1.76s/it, lr: 1.0e-04 loss: 2.439e-01]
my_first_lora_v2: 20%|## | 804/4000 [23:32<1:33:36, 1.76s/it, lr: 1.0e-04 loss: 3.990e-01]
my_first_lora_v2: 20%|## | 804/4000 [23:32<1:33:36, 1.76s/it, lr: 1.0e-04 loss: 3.990e-01]
my_first_lora_v2: 20%|## | 805/4000 [23:35<1:33:39, 1.76s/it, lr: 1.0e-04 loss: 2.665e-01]
my_first_lora_v2: 20%|## | 805/4000 [23:35<1:33:39, 1.76s/it, lr: 1.0e-04 loss: 2.665e-01]
my_first_lora_v2: 20%|## | 806/4000 [23:36<1:33:33, 1.76s/it, lr: 1.0e-04 loss: 2.543e-01]
my_first_lora_v2: 20%|## | 806/4000 [23:36<1:33:33, 1.76s/it, lr: 1.0e-04 loss: 2.543e-01]
my_first_lora_v2: 20%|## | 807/4000 [23:39<1:33:35, 1.76s/it, lr: 1.0e-04 loss: 4.721e-01]
my_first_lora_v2: 20%|## | 807/4000 [23:39<1:33:35, 1.76s/it, lr: 1.0e-04 loss: 4.721e-01]
my_first_lora_v2: 20%|## | 808/4000 [23:40<1:33:30, 1.76s/it, lr: 1.0e-04 loss: 5.617e-01]
my_first_lora_v2: 20%|## | 808/4000 [23:40<1:33:30, 1.76s/it, lr: 1.0e-04 loss: 5.617e-01]
my_first_lora_v2: 20%|## | 809/4000 [23:43<1:33:33, 1.76s/it, lr: 1.0e-04 loss: 2.610e-01]
my_first_lora_v2: 20%|## | 809/4000 [23:43<1:33:33, 1.76s/it, lr: 1.0e-04 loss: 2.610e-01]
my_first_lora_v2: 20%|## | 810/4000 [23:43<1:33:27, 1.76s/it, lr: 1.0e-04 loss: 4.279e-01]
my_first_lora_v2: 20%|## | 810/4000 [23:43<1:33:27, 1.76s/it, lr: 1.0e-04 loss: 4.279e-01]
my_first_lora_v2: 20%|## | 811/4000 [23:44<1:33:22, 1.76s/it, lr: 1.0e-04 loss: 1.185e-01]
my_first_lora_v2: 20%|## | 811/4000 [23:44<1:33:22, 1.76s/it, lr: 1.0e-04 loss: 1.185e-01]
my_first_lora_v2: 20%|## | 812/4000 [23:45<1:33:16, 1.76s/it, lr: 1.0e-04 loss: 2.550e-01]
my_first_lora_v2: 20%|## | 812/4000 [23:45<1:33:16, 1.76s/it, lr: 1.0e-04 loss: 2.550e-01]
my_first_lora_v2: 20%|## | 813/4000 [23:46<1:33:11, 1.75s/it, lr: 1.0e-04 loss: 2.434e-01]
my_first_lora_v2: 20%|## | 813/4000 [23:46<1:33:11, 1.75s/it, lr: 1.0e-04 loss: 2.434e-01]
my_first_lora_v2: 20%|## | 814/4000 [23:47<1:33:05, 1.75s/it, lr: 1.0e-04 loss: 7.612e-01]
my_first_lora_v2: 20%|## | 814/4000 [23:47<1:33:05, 1.75s/it, lr: 1.0e-04 loss: 7.612e-01]
my_first_lora_v2: 20%|## | 815/4000 [23:47<1:33:00, 1.75s/it, lr: 1.0e-04 loss: 5.650e-01]
my_first_lora_v2: 20%|## | 815/4000 [23:47<1:33:00, 1.75s/it, lr: 1.0e-04 loss: 5.650e-01]
my_first_lora_v2: 20%|## | 816/4000 [23:50<1:33:03, 1.75s/it, lr: 1.0e-04 loss: 1.748e-01]
my_first_lora_v2: 20%|## | 816/4000 [23:50<1:33:03, 1.75s/it, lr: 1.0e-04 loss: 1.748e-01]
my_first_lora_v2: 20%|## | 817/4000 [23:53<1:33:06, 1.76s/it, lr: 1.0e-04 loss: 5.195e-01]
my_first_lora_v2: 20%|## | 817/4000 [23:53<1:33:06, 1.76s/it, lr: 1.0e-04 loss: 5.195e-01]
my_first_lora_v2: 20%|## | 818/4000 [23:54<1:33:00, 1.75s/it, lr: 1.0e-04 loss: 6.203e-01]
my_first_lora_v2: 20%|## | 818/4000 [23:54<1:33:00, 1.75s/it, lr: 1.0e-04 loss: 6.203e-01]
my_first_lora_v2: 20%|## | 819/4000 [23:57<1:33:03, 1.76s/it, lr: 1.0e-04 loss: 6.982e-01]
my_first_lora_v2: 20%|## | 819/4000 [23:57<1:33:03, 1.76s/it, lr: 1.0e-04 loss: 6.982e-01]
my_first_lora_v2: 20%|## | 820/4000 [24:00<1:33:05, 1.76s/it, lr: 1.0e-04 loss: 5.486e-01]
my_first_lora_v2: 20%|## | 820/4000 [24:00<1:33:05, 1.76s/it, lr: 1.0e-04 loss: 5.486e-01]
my_first_lora_v2: 21%|## | 821/4000 [24:03<1:33:07, 1.76s/it, lr: 1.0e-04 loss: 7.426e-01]
my_first_lora_v2: 21%|## | 821/4000 [24:03<1:33:07, 1.76s/it, lr: 1.0e-04 loss: 7.426e-01]
my_first_lora_v2: 21%|## | 822/4000 [24:03<1:33:02, 1.76s/it, lr: 1.0e-04 loss: 1.655e-01]
my_first_lora_v2: 21%|## | 822/4000 [24:03<1:33:02, 1.76s/it, lr: 1.0e-04 loss: 1.655e-01]
my_first_lora_v2: 21%|## | 823/4000 [24:06<1:33:04, 1.76s/it, lr: 1.0e-04 loss: 5.336e-01]
my_first_lora_v2: 21%|## | 823/4000 [24:06<1:33:04, 1.76s/it, lr: 1.0e-04 loss: 5.336e-01]
my_first_lora_v2: 21%|## | 824/4000 [24:09<1:33:06, 1.76s/it, lr: 1.0e-04 loss: 1.596e-01]
my_first_lora_v2: 21%|## | 824/4000 [24:09<1:33:06, 1.76s/it, lr: 1.0e-04 loss: 1.596e-01]
my_first_lora_v2: 21%|## | 825/4000 [24:10<1:33:00, 1.76s/it, lr: 1.0e-04 loss: 7.555e-01]
my_first_lora_v2: 21%|## | 825/4000 [24:10<1:33:00, 1.76s/it, lr: 1.0e-04 loss: 7.555e-01]
my_first_lora_v2: 21%|## | 826/4000 [24:11<1:32:57, 1.76s/it, lr: 1.0e-04 loss: 6.674e-01]
my_first_lora_v2: 21%|## | 826/4000 [24:11<1:32:57, 1.76s/it, lr: 1.0e-04 loss: 6.674e-01]
my_first_lora_v2: 21%|## | 827/4000 [24:12<1:32:51, 1.76s/it, lr: 1.0e-04 loss: 5.057e-01]
my_first_lora_v2: 21%|## | 827/4000 [24:12<1:32:51, 1.76s/it, lr: 1.0e-04 loss: 5.057e-01]
my_first_lora_v2: 21%|## | 828/4000 [24:14<1:32:52, 1.76s/it, lr: 1.0e-04 loss: 6.820e-01]
my_first_lora_v2: 21%|## | 828/4000 [24:14<1:32:52, 1.76s/it, lr: 1.0e-04 loss: 6.820e-01]
my_first_lora_v2: 21%|## | 829/4000 [24:17<1:32:55, 1.76s/it, lr: 1.0e-04 loss: 1.007e-01]
my_first_lora_v2: 21%|## | 829/4000 [24:17<1:32:55, 1.76s/it, lr: 1.0e-04 loss: 1.007e-01]
my_first_lora_v2: 21%|## | 830/4000 [24:20<1:32:58, 1.76s/it, lr: 1.0e-04 loss: 2.911e-01]
my_first_lora_v2: 21%|## | 830/4000 [24:20<1:32:58, 1.76s/it, lr: 1.0e-04 loss: 2.911e-01]
my_first_lora_v2: 21%|## | 831/4000 [24:21<1:32:53, 1.76s/it, lr: 1.0e-04 loss: 1.734e-01]
my_first_lora_v2: 21%|## | 831/4000 [24:21<1:32:53, 1.76s/it, lr: 1.0e-04 loss: 1.734e-01]
my_first_lora_v2: 21%|## | 832/4000 [24:22<1:32:47, 1.76s/it, lr: 1.0e-04 loss: 6.576e-01]
my_first_lora_v2: 21%|## | 832/4000 [24:22<1:32:47, 1.76s/it, lr: 1.0e-04 loss: 6.576e-01]
my_first_lora_v2: 21%|## | 833/4000 [24:25<1:32:50, 1.76s/it, lr: 1.0e-04 loss: 7.236e-02]
my_first_lora_v2: 21%|## | 833/4000 [24:25<1:32:50, 1.76s/it, lr: 1.0e-04 loss: 7.236e-02]
my_first_lora_v2: 21%|## | 834/4000 [24:28<1:32:52, 1.76s/it, lr: 1.0e-04 loss: 4.156e-01]
my_first_lora_v2: 21%|## | 834/4000 [24:28<1:32:52, 1.76s/it, lr: 1.0e-04 loss: 4.156e-01]
my_first_lora_v2: 21%|## | 835/4000 [24:30<1:32:55, 1.76s/it, lr: 1.0e-04 loss: 5.078e-01]
my_first_lora_v2: 21%|## | 835/4000 [24:30<1:32:55, 1.76s/it, lr: 1.0e-04 loss: 5.078e-01]
my_first_lora_v2: 21%|## | 836/4000 [24:31<1:32:49, 1.76s/it, lr: 1.0e-04 loss: 4.357e-01]
my_first_lora_v2: 21%|## | 836/4000 [24:31<1:32:49, 1.76s/it, lr: 1.0e-04 loss: 4.357e-01]
my_first_lora_v2: 21%|## | 837/4000 [24:32<1:32:44, 1.76s/it, lr: 1.0e-04 loss: 6.694e-01]
my_first_lora_v2: 21%|## | 837/4000 [24:32<1:32:44, 1.76s/it, lr: 1.0e-04 loss: 6.694e-01]
my_first_lora_v2: 21%|## | 838/4000 [24:35<1:32:46, 1.76s/it, lr: 1.0e-04 loss: 7.217e-02]
my_first_lora_v2: 21%|## | 838/4000 [24:35<1:32:46, 1.76s/it, lr: 1.0e-04 loss: 7.217e-02]
my_first_lora_v2: 21%|## | 839/4000 [24:36<1:32:42, 1.76s/it, lr: 1.0e-04 loss: 2.392e-01]
my_first_lora_v2: 21%|## | 839/4000 [24:36<1:32:42, 1.76s/it, lr: 1.0e-04 loss: 2.392e-01]
my_first_lora_v2: 21%|##1 | 840/4000 [24:39<1:32:44, 1.76s/it, lr: 1.0e-04 loss: 1.939e-01]
my_first_lora_v2: 21%|##1 | 840/4000 [24:39<1:32:44, 1.76s/it, lr: 1.0e-04 loss: 1.939e-01]
my_first_lora_v2: 21%|##1 | 841/4000 [24:40<1:32:41, 1.76s/it, lr: 1.0e-04 loss: 2.521e-01]
my_first_lora_v2: 21%|##1 | 841/4000 [24:40<1:32:41, 1.76s/it, lr: 1.0e-04 loss: 2.521e-01]
my_first_lora_v2: 21%|##1 | 842/4000 [24:41<1:32:35, 1.76s/it, lr: 1.0e-04 loss: 4.722e-01]
my_first_lora_v2: 21%|##1 | 842/4000 [24:41<1:32:35, 1.76s/it, lr: 1.0e-04 loss: 4.722e-01]
my_first_lora_v2: 21%|##1 | 843/4000 [24:44<1:32:38, 1.76s/it, lr: 1.0e-04 loss: 7.680e-01]
my_first_lora_v2: 21%|##1 | 843/4000 [24:44<1:32:38, 1.76s/it, lr: 1.0e-04 loss: 7.680e-01]
my_first_lora_v2: 21%|##1 | 844/4000 [24:45<1:32:34, 1.76s/it, lr: 1.0e-04 loss: 8.024e-01]
my_first_lora_v2: 21%|##1 | 844/4000 [24:45<1:32:34, 1.76s/it, lr: 1.0e-04 loss: 8.024e-01]
my_first_lora_v2: 21%|##1 | 845/4000 [24:46<1:32:29, 1.76s/it, lr: 1.0e-04 loss: 5.947e-01]
my_first_lora_v2: 21%|##1 | 845/4000 [24:46<1:32:29, 1.76s/it, lr: 1.0e-04 loss: 5.947e-01]
my_first_lora_v2: 21%|##1 | 846/4000 [24:49<1:32:31, 1.76s/it, lr: 1.0e-04 loss: 2.705e-01]
my_first_lora_v2: 21%|##1 | 846/4000 [24:49<1:32:31, 1.76s/it, lr: 1.0e-04 loss: 2.705e-01]
my_first_lora_v2: 21%|##1 | 847/4000 [24:50<1:32:26, 1.76s/it, lr: 1.0e-04 loss: 2.364e-01]
my_first_lora_v2: 21%|##1 | 847/4000 [24:50<1:32:26, 1.76s/it, lr: 1.0e-04 loss: 2.364e-01]
my_first_lora_v2: 21%|##1 | 848/4000 [24:52<1:32:28, 1.76s/it, lr: 1.0e-04 loss: 7.024e-01]
my_first_lora_v2: 21%|##1 | 848/4000 [24:52<1:32:28, 1.76s/it, lr: 1.0e-04 loss: 7.024e-01]
my_first_lora_v2: 21%|##1 | 849/4000 [24:55<1:32:30, 1.76s/it, lr: 1.0e-04 loss: 6.396e-01]
my_first_lora_v2: 21%|##1 | 849/4000 [24:55<1:32:30, 1.76s/it, lr: 1.0e-04 loss: 6.396e-01]
my_first_lora_v2: 21%|##1 | 850/4000 [24:58<1:32:32, 1.76s/it, lr: 1.0e-04 loss: 2.961e-02]
my_first_lora_v2: 21%|##1 | 850/4000 [24:58<1:32:32, 1.76s/it, lr: 1.0e-04 loss: 2.961e-02]
my_first_lora_v2: 21%|##1 | 851/4000 [25:01<1:32:34, 1.76s/it, lr: 1.0e-04 loss: 1.809e-01]
my_first_lora_v2: 21%|##1 | 851/4000 [25:01<1:32:34, 1.76s/it, lr: 1.0e-04 loss: 1.809e-01]
my_first_lora_v2: 21%|##1 | 852/4000 [25:01<1:32:29, 1.76s/it, lr: 1.0e-04 loss: 4.043e-01]
my_first_lora_v2: 21%|##1 | 852/4000 [25:01<1:32:29, 1.76s/it, lr: 1.0e-04 loss: 4.043e-01]
my_first_lora_v2: 21%|##1 | 853/4000 [25:04<1:32:30, 1.76s/it, lr: 1.0e-04 loss: 2.902e-01]
my_first_lora_v2: 21%|##1 | 853/4000 [25:04<1:32:30, 1.76s/it, lr: 1.0e-04 loss: 2.902e-01]
my_first_lora_v2: 21%|##1 | 854/4000 [25:05<1:32:25, 1.76s/it, lr: 1.0e-04 loss: 4.998e-01]
my_first_lora_v2: 21%|##1 | 854/4000 [25:05<1:32:25, 1.76s/it, lr: 1.0e-04 loss: 4.998e-01]
my_first_lora_v2: 21%|##1 | 855/4000 [25:06<1:32:20, 1.76s/it, lr: 1.0e-04 loss: 9.082e-02]
my_first_lora_v2: 21%|##1 | 855/4000 [25:06<1:32:20, 1.76s/it, lr: 1.0e-04 loss: 9.082e-02]
my_first_lora_v2: 21%|##1 | 856/4000 [25:09<1:32:22, 1.76s/it, lr: 1.0e-04 loss: 1.228e-01]
my_first_lora_v2: 21%|##1 | 856/4000 [25:09<1:32:22, 1.76s/it, lr: 1.0e-04 loss: 1.228e-01]
my_first_lora_v2: 21%|##1 | 857/4000 [25:09<1:32:17, 1.76s/it, lr: 1.0e-04 loss: 6.864e-01]
my_first_lora_v2: 21%|##1 | 857/4000 [25:09<1:32:17, 1.76s/it, lr: 1.0e-04 loss: 6.864e-01]
my_first_lora_v2: 21%|##1 | 858/4000 [25:11<1:32:13, 1.76s/it, lr: 1.0e-04 loss: 3.817e-01]
my_first_lora_v2: 21%|##1 | 858/4000 [25:11<1:32:13, 1.76s/it, lr: 1.0e-04 loss: 3.817e-01]
my_first_lora_v2: 21%|##1 | 859/4000 [25:13<1:32:16, 1.76s/it, lr: 1.0e-04 loss: 5.274e-01]
my_first_lora_v2: 21%|##1 | 859/4000 [25:13<1:32:16, 1.76s/it, lr: 1.0e-04 loss: 5.274e-01]
my_first_lora_v2: 22%|##1 | 860/4000 [25:14<1:32:10, 1.76s/it, lr: 1.0e-04 loss: 4.372e-01]
my_first_lora_v2: 22%|##1 | 860/4000 [25:14<1:32:10, 1.76s/it, lr: 1.0e-04 loss: 4.372e-01]
my_first_lora_v2: 22%|##1 | 861/4000 [25:15<1:32:05, 1.76s/it, lr: 1.0e-04 loss: 5.484e-01]
my_first_lora_v2: 22%|##1 | 861/4000 [25:15<1:32:05, 1.76s/it, lr: 1.0e-04 loss: 5.484e-01]
my_first_lora_v2: 22%|##1 | 862/4000 [25:18<1:32:07, 1.76s/it, lr: 1.0e-04 loss: 2.262e-01]
my_first_lora_v2: 22%|##1 | 862/4000 [25:18<1:32:07, 1.76s/it, lr: 1.0e-04 loss: 2.262e-01]
my_first_lora_v2: 22%|##1 | 863/4000 [25:19<1:32:02, 1.76s/it, lr: 1.0e-04 loss: 3.569e-01]
my_first_lora_v2: 22%|##1 | 863/4000 [25:19<1:32:02, 1.76s/it, lr: 1.0e-04 loss: 3.569e-01]
my_first_lora_v2: 22%|##1 | 864/4000 [25:21<1:32:03, 1.76s/it, lr: 1.0e-04 loss: 5.233e-01]
my_first_lora_v2: 22%|##1 | 864/4000 [25:21<1:32:03, 1.76s/it, lr: 1.0e-04 loss: 5.233e-01]
my_first_lora_v2: 22%|##1 | 865/4000 [25:24<1:32:04, 1.76s/it, lr: 1.0e-04 loss: 6.566e-01]
my_first_lora_v2: 22%|##1 | 865/4000 [25:24<1:32:04, 1.76s/it, lr: 1.0e-04 loss: 6.566e-01]
my_first_lora_v2: 22%|##1 | 866/4000 [25:27<1:32:07, 1.76s/it, lr: 1.0e-04 loss: 5.719e-01]
my_first_lora_v2: 22%|##1 | 866/4000 [25:27<1:32:07, 1.76s/it, lr: 1.0e-04 loss: 5.719e-01]
my_first_lora_v2: 22%|##1 | 867/4000 [25:28<1:32:01, 1.76s/it, lr: 1.0e-04 loss: 1.484e-01]
my_first_lora_v2: 22%|##1 | 867/4000 [25:28<1:32:01, 1.76s/it, lr: 1.0e-04 loss: 1.484e-01]
my_first_lora_v2: 22%|##1 | 868/4000 [25:30<1:32:04, 1.76s/it, lr: 1.0e-04 loss: 5.602e-01]
my_first_lora_v2: 22%|##1 | 868/4000 [25:30<1:32:04, 1.76s/it, lr: 1.0e-04 loss: 5.602e-01]
my_first_lora_v2: 22%|##1 | 869/4000 [25:33<1:32:06, 1.77s/it, lr: 1.0e-04 loss: 6.576e-01]
my_first_lora_v2: 22%|##1 | 869/4000 [25:33<1:32:06, 1.77s/it, lr: 1.0e-04 loss: 6.576e-01]
my_first_lora_v2: 22%|##1 | 870/4000 [25:34<1:32:01, 1.76s/it, lr: 1.0e-04 loss: 6.684e-01]
my_first_lora_v2: 22%|##1 | 870/4000 [25:34<1:32:01, 1.76s/it, lr: 1.0e-04 loss: 6.684e-01]
my_first_lora_v2: 22%|##1 | 871/4000 [25:35<1:31:57, 1.76s/it, lr: 1.0e-04 loss: 8.141e-01]
my_first_lora_v2: 22%|##1 | 871/4000 [25:35<1:31:57, 1.76s/it, lr: 1.0e-04 loss: 8.141e-01]
my_first_lora_v2: 22%|##1 | 872/4000 [25:38<1:31:59, 1.76s/it, lr: 1.0e-04 loss: 4.870e-01]
my_first_lora_v2: 22%|##1 | 872/4000 [25:38<1:31:59, 1.76s/it, lr: 1.0e-04 loss: 4.870e-01]
my_first_lora_v2: 22%|##1 | 873/4000 [25:39<1:31:54, 1.76s/it, lr: 1.0e-04 loss: 3.795e-01]
my_first_lora_v2: 22%|##1 | 873/4000 [25:39<1:31:54, 1.76s/it, lr: 1.0e-04 loss: 3.795e-01]
my_first_lora_v2: 22%|##1 | 874/4000 [25:42<1:31:55, 1.76s/it, lr: 1.0e-04 loss: 4.310e-01]
my_first_lora_v2: 22%|##1 | 874/4000 [25:42<1:31:55, 1.76s/it, lr: 1.0e-04 loss: 4.310e-01]
my_first_lora_v2: 22%|##1 | 875/4000 [25:43<1:31:50, 1.76s/it, lr: 1.0e-04 loss: 6.096e-01]
my_first_lora_v2: 22%|##1 | 875/4000 [25:43<1:31:50, 1.76s/it, lr: 1.0e-04 loss: 6.096e-01]
my_first_lora_v2: 22%|##1 | 876/4000 [25:45<1:31:51, 1.76s/it, lr: 1.0e-04 loss: 3.898e-01]
my_first_lora_v2: 22%|##1 | 876/4000 [25:45<1:31:51, 1.76s/it, lr: 1.0e-04 loss: 3.898e-01]
my_first_lora_v2: 22%|##1 | 877/4000 [25:46<1:31:46, 1.76s/it, lr: 1.0e-04 loss: 1.952e-01]
my_first_lora_v2: 22%|##1 | 877/4000 [25:46<1:31:46, 1.76s/it, lr: 1.0e-04 loss: 1.952e-01]
my_first_lora_v2: 22%|##1 | 878/4000 [25:47<1:31:41, 1.76s/it, lr: 1.0e-04 loss: 4.583e-01]
my_first_lora_v2: 22%|##1 | 878/4000 [25:47<1:31:41, 1.76s/it, lr: 1.0e-04 loss: 4.583e-01]
my_first_lora_v2: 22%|##1 | 879/4000 [25:49<1:31:42, 1.76s/it, lr: 1.0e-04 loss: 3.356e-01]
my_first_lora_v2: 22%|##1 | 879/4000 [25:49<1:31:42, 1.76s/it, lr: 1.0e-04 loss: 3.356e-01]
my_first_lora_v2: 22%|##2 | 880/4000 [25:52<1:31:45, 1.76s/it, lr: 1.0e-04 loss: 1.136e-01]
my_first_lora_v2: 22%|##2 | 880/4000 [25:52<1:31:45, 1.76s/it, lr: 1.0e-04 loss: 1.136e-01]
my_first_lora_v2: 22%|##2 | 881/4000 [25:53<1:31:39, 1.76s/it, lr: 1.0e-04 loss: 1.522e-01]
my_first_lora_v2: 22%|##2 | 881/4000 [25:53<1:31:39, 1.76s/it, lr: 1.0e-04 loss: 1.522e-01]
my_first_lora_v2: 22%|##2 | 882/4000 [25:54<1:31:34, 1.76s/it, lr: 1.0e-04 loss: 3.231e-01]
my_first_lora_v2: 22%|##2 | 882/4000 [25:54<1:31:34, 1.76s/it, lr: 1.0e-04 loss: 3.231e-01]
my_first_lora_v2: 22%|##2 | 883/4000 [25:56<1:31:35, 1.76s/it, lr: 1.0e-04 loss: 5.178e-02]
my_first_lora_v2: 22%|##2 | 883/4000 [25:56<1:31:35, 1.76s/it, lr: 1.0e-04 loss: 5.178e-02]
my_first_lora_v2: 22%|##2 | 884/4000 [25:59<1:31:37, 1.76s/it, lr: 1.0e-04 loss: 5.598e-01]
my_first_lora_v2: 22%|##2 | 884/4000 [25:59<1:31:37, 1.76s/it, lr: 1.0e-04 loss: 5.598e-01]
my_first_lora_v2: 22%|##2 | 885/4000 [26:00<1:31:33, 1.76s/it, lr: 1.0e-04 loss: 7.746e-02]
my_first_lora_v2: 22%|##2 | 885/4000 [26:00<1:31:33, 1.76s/it, lr: 1.0e-04 loss: 7.746e-02]
my_first_lora_v2: 22%|##2 | 886/4000 [26:03<1:31:34, 1.76s/it, lr: 1.0e-04 loss: 1.797e-01]
my_first_lora_v2: 22%|##2 | 886/4000 [26:03<1:31:34, 1.76s/it, lr: 1.0e-04 loss: 1.797e-01]
my_first_lora_v2: 22%|##2 | 887/4000 [26:04<1:31:29, 1.76s/it, lr: 1.0e-04 loss: 4.404e-01]
my_first_lora_v2: 22%|##2 | 887/4000 [26:04<1:31:29, 1.76s/it, lr: 1.0e-04 loss: 4.404e-01]
my_first_lora_v2: 22%|##2 | 888/4000 [26:04<1:31:24, 1.76s/it, lr: 1.0e-04 loss: 1.047e-01]
my_first_lora_v2: 22%|##2 | 888/4000 [26:04<1:31:24, 1.76s/it, lr: 1.0e-04 loss: 1.047e-01]
my_first_lora_v2: 22%|##2 | 889/4000 [26:07<1:31:26, 1.76s/it, lr: 1.0e-04 loss: 4.863e-01]
my_first_lora_v2: 22%|##2 | 889/4000 [26:07<1:31:26, 1.76s/it, lr: 1.0e-04 loss: 4.863e-01]
my_first_lora_v2: 22%|##2 | 890/4000 [26:08<1:31:21, 1.76s/it, lr: 1.0e-04 loss: 7.201e-01]
my_first_lora_v2: 22%|##2 | 890/4000 [26:08<1:31:21, 1.76s/it, lr: 1.0e-04 loss: 7.201e-01]
my_first_lora_v2: 22%|##2 | 891/4000 [26:09<1:31:16, 1.76s/it, lr: 1.0e-04 loss: 3.153e-01]
my_first_lora_v2: 22%|##2 | 891/4000 [26:09<1:31:16, 1.76s/it, lr: 1.0e-04 loss: 3.153e-01]
my_first_lora_v2: 22%|##2 | 892/4000 [26:10<1:31:11, 1.76s/it, lr: 1.0e-04 loss: 1.398e-01]
my_first_lora_v2: 22%|##2 | 892/4000 [26:10<1:31:11, 1.76s/it, lr: 1.0e-04 loss: 1.398e-01]
my_first_lora_v2: 22%|##2 | 893/4000 [26:12<1:31:12, 1.76s/it, lr: 1.0e-04 loss: 4.476e-01]
my_first_lora_v2: 22%|##2 | 893/4000 [26:12<1:31:12, 1.76s/it, lr: 1.0e-04 loss: 4.476e-01]
my_first_lora_v2: 22%|##2 | 894/4000 [26:15<1:31:14, 1.76s/it, lr: 1.0e-04 loss: 3.725e-01]
my_first_lora_v2: 22%|##2 | 894/4000 [26:15<1:31:14, 1.76s/it, lr: 1.0e-04 loss: 3.725e-01]
my_first_lora_v2: 22%|##2 | 895/4000 [26:16<1:31:09, 1.76s/it, lr: 1.0e-04 loss: 4.092e-01]
my_first_lora_v2: 22%|##2 | 895/4000 [26:16<1:31:09, 1.76s/it, lr: 1.0e-04 loss: 4.092e-01]
my_first_lora_v2: 22%|##2 | 896/4000 [26:17<1:31:04, 1.76s/it, lr: 1.0e-04 loss: 5.364e-01]
my_first_lora_v2: 22%|##2 | 896/4000 [26:17<1:31:04, 1.76s/it, lr: 1.0e-04 loss: 5.364e-01]
my_first_lora_v2: 22%|##2 | 897/4000 [26:20<1:31:06, 1.76s/it, lr: 1.0e-04 loss: 9.721e-02]
my_first_lora_v2: 22%|##2 | 897/4000 [26:20<1:31:06, 1.76s/it, lr: 1.0e-04 loss: 9.721e-02]
my_first_lora_v2: 22%|##2 | 898/4000 [26:21<1:31:01, 1.76s/it, lr: 1.0e-04 loss: 6.109e-01]
my_first_lora_v2: 22%|##2 | 898/4000 [26:21<1:31:01, 1.76s/it, lr: 1.0e-04 loss: 6.109e-01]
my_first_lora_v2: 22%|##2 | 899/4000 [26:24<1:31:04, 1.76s/it, lr: 1.0e-04 loss: 2.188e-01]
my_first_lora_v2: 22%|##2 | 899/4000 [26:24<1:31:04, 1.76s/it, lr: 1.0e-04 loss: 2.188e-01]
my_first_lora_v2: 22%|##2 | 900/4000 [26:26<1:31:05, 1.76s/it, lr: 1.0e-04 loss: 3.205e-01]
my_first_lora_v2: 22%|##2 | 900/4000 [26:26<1:31:05, 1.76s/it, lr: 1.0e-04 loss: 3.205e-01]
my_first_lora_v2: 23%|##2 | 901/4000 [26:29<1:31:06, 1.76s/it, lr: 1.0e-04 loss: 3.957e-01]
my_first_lora_v2: 23%|##2 | 901/4000 [26:29<1:31:06, 1.76s/it, lr: 1.0e-04 loss: 3.957e-01]
my_first_lora_v2: 23%|##2 | 902/4000 [26:32<1:31:08, 1.77s/it, lr: 1.0e-04 loss: 8.426e-02]
my_first_lora_v2: 23%|##2 | 902/4000 [26:32<1:31:08, 1.77s/it, lr: 1.0e-04 loss: 8.426e-02]
my_first_lora_v2: 23%|##2 | 903/4000 [26:33<1:31:03, 1.76s/it, lr: 1.0e-04 loss: 4.036e-01]
my_first_lora_v2: 23%|##2 | 903/4000 [26:33<1:31:03, 1.76s/it, lr: 1.0e-04 loss: 4.036e-01]
my_first_lora_v2: 23%|##2 | 904/4000 [26:34<1:31:00, 1.76s/it, lr: 1.0e-04 loss: 7.502e-01]
my_first_lora_v2: 23%|##2 | 904/4000 [26:34<1:31:00, 1.76s/it, lr: 1.0e-04 loss: 7.502e-01]
my_first_lora_v2: 23%|##2 | 905/4000 [26:35<1:30:55, 1.76s/it, lr: 1.0e-04 loss: 7.333e-01]
my_first_lora_v2: 23%|##2 | 905/4000 [26:35<1:30:55, 1.76s/it, lr: 1.0e-04 loss: 7.333e-01]
my_first_lora_v2: 23%|##2 | 906/4000 [26:35<1:30:50, 1.76s/it, lr: 1.0e-04 loss: 1.586e-01]
my_first_lora_v2: 23%|##2 | 906/4000 [26:35<1:30:50, 1.76s/it, lr: 1.0e-04 loss: 1.586e-01]
my_first_lora_v2: 23%|##2 | 907/4000 [26:36<1:30:45, 1.76s/it, lr: 1.0e-04 loss: 6.675e-01]
my_first_lora_v2: 23%|##2 | 907/4000 [26:36<1:30:45, 1.76s/it, lr: 1.0e-04 loss: 6.675e-01]
my_first_lora_v2: 23%|##2 | 908/4000 [26:37<1:30:40, 1.76s/it, lr: 1.0e-04 loss: 4.154e-01]
my_first_lora_v2: 23%|##2 | 908/4000 [26:37<1:30:40, 1.76s/it, lr: 1.0e-04 loss: 4.154e-01]
my_first_lora_v2: 23%|##2 | 909/4000 [26:38<1:30:35, 1.76s/it, lr: 1.0e-04 loss: 6.859e-01]
my_first_lora_v2: 23%|##2 | 909/4000 [26:38<1:30:35, 1.76s/it, lr: 1.0e-04 loss: 6.859e-01]
my_first_lora_v2: 23%|##2 | 910/4000 [26:39<1:30:30, 1.76s/it, lr: 1.0e-04 loss: 5.601e-01]
my_first_lora_v2: 23%|##2 | 910/4000 [26:39<1:30:30, 1.76s/it, lr: 1.0e-04 loss: 5.601e-01]
my_first_lora_v2: 23%|##2 | 911/4000 [26:40<1:30:25, 1.76s/it, lr: 1.0e-04 loss: 3.145e-01]
my_first_lora_v2: 23%|##2 | 911/4000 [26:40<1:30:25, 1.76s/it, lr: 1.0e-04 loss: 3.145e-01]
my_first_lora_v2: 23%|##2 | 912/4000 [26:41<1:30:21, 1.76s/it, lr: 1.0e-04 loss: 5.083e-01]
my_first_lora_v2: 23%|##2 | 912/4000 [26:41<1:30:21, 1.76s/it, lr: 1.0e-04 loss: 5.083e-01]
my_first_lora_v2: 23%|##2 | 913/4000 [26:42<1:30:16, 1.75s/it, lr: 1.0e-04 loss: 6.259e-01]
my_first_lora_v2: 23%|##2 | 913/4000 [26:42<1:30:16, 1.75s/it, lr: 1.0e-04 loss: 6.259e-01]
my_first_lora_v2: 23%|##2 | 914/4000 [26:44<1:30:18, 1.76s/it, lr: 1.0e-04 loss: 5.863e-01]
my_first_lora_v2: 23%|##2 | 914/4000 [26:44<1:30:18, 1.76s/it, lr: 1.0e-04 loss: 5.863e-01]
my_first_lora_v2: 23%|##2 | 915/4000 [26:45<1:30:14, 1.75s/it, lr: 1.0e-04 loss: 5.168e-01]
my_first_lora_v2: 23%|##2 | 915/4000 [26:45<1:30:14, 1.75s/it, lr: 1.0e-04 loss: 5.168e-01]
my_first_lora_v2: 23%|##2 | 916/4000 [26:46<1:30:09, 1.75s/it, lr: 1.0e-04 loss: 3.496e-01]
my_first_lora_v2: 23%|##2 | 916/4000 [26:46<1:30:09, 1.75s/it, lr: 1.0e-04 loss: 3.496e-01]
my_first_lora_v2: 23%|##2 | 917/4000 [26:47<1:30:04, 1.75s/it, lr: 1.0e-04 loss: 6.754e-01]
my_first_lora_v2: 23%|##2 | 917/4000 [26:47<1:30:04, 1.75s/it, lr: 1.0e-04 loss: 6.754e-01]
my_first_lora_v2: 23%|##2 | 918/4000 [26:48<1:29:59, 1.75s/it, lr: 1.0e-04 loss: 6.618e-01]
my_first_lora_v2: 23%|##2 | 918/4000 [26:48<1:29:59, 1.75s/it, lr: 1.0e-04 loss: 6.618e-01]
my_first_lora_v2: 23%|##2 | 919/4000 [26:49<1:29:54, 1.75s/it, lr: 1.0e-04 loss: 2.099e-01]
my_first_lora_v2: 23%|##2 | 919/4000 [26:49<1:29:54, 1.75s/it, lr: 1.0e-04 loss: 2.099e-01]
my_first_lora_v2: 23%|##3 | 920/4000 [26:51<1:29:56, 1.75s/it, lr: 1.0e-04 loss: 2.096e-01]
my_first_lora_v2: 23%|##3 | 920/4000 [26:51<1:29:56, 1.75s/it, lr: 1.0e-04 loss: 2.096e-01]
my_first_lora_v2: 23%|##3 | 921/4000 [26:54<1:29:56, 1.75s/it, lr: 1.0e-04 loss: 4.353e-01]
my_first_lora_v2: 23%|##3 | 921/4000 [26:54<1:29:56, 1.75s/it, lr: 1.0e-04 loss: 4.353e-01]
my_first_lora_v2: 23%|##3 | 922/4000 [26:55<1:29:51, 1.75s/it, lr: 1.0e-04 loss: 2.024e-01]
my_first_lora_v2: 23%|##3 | 922/4000 [26:55<1:29:51, 1.75s/it, lr: 1.0e-04 loss: 2.024e-01]
my_first_lora_v2: 23%|##3 | 923/4000 [26:55<1:29:47, 1.75s/it, lr: 1.0e-04 loss: 6.085e-01]
my_first_lora_v2: 23%|##3 | 923/4000 [26:55<1:29:47, 1.75s/it, lr: 1.0e-04 loss: 6.085e-01]
my_first_lora_v2: 23%|##3 | 924/4000 [26:58<1:29:48, 1.75s/it, lr: 1.0e-04 loss: 2.366e-01]
my_first_lora_v2: 23%|##3 | 924/4000 [26:58<1:29:48, 1.75s/it, lr: 1.0e-04 loss: 2.366e-01]
my_first_lora_v2: 23%|##3 | 925/4000 [26:59<1:29:45, 1.75s/it, lr: 1.0e-04 loss: 6.706e-01]
my_first_lora_v2: 23%|##3 | 925/4000 [26:59<1:29:45, 1.75s/it, lr: 1.0e-04 loss: 6.706e-01]
my_first_lora_v2: 23%|##3 | 926/4000 [27:00<1:29:40, 1.75s/it, lr: 1.0e-04 loss: 1.931e-01]
my_first_lora_v2: 23%|##3 | 926/4000 [27:00<1:29:40, 1.75s/it, lr: 1.0e-04 loss: 1.931e-01]
my_first_lora_v2: 23%|##3 | 927/4000 [27:01<1:29:35, 1.75s/it, lr: 1.0e-04 loss: 3.252e-01]
my_first_lora_v2: 23%|##3 | 927/4000 [27:01<1:29:35, 1.75s/it, lr: 1.0e-04 loss: 3.252e-01]
my_first_lora_v2: 23%|##3 | 928/4000 [27:04<1:29:37, 1.75s/it, lr: 1.0e-04 loss: 2.947e-02]
my_first_lora_v2: 23%|##3 | 928/4000 [27:04<1:29:37, 1.75s/it, lr: 1.0e-04 loss: 2.947e-02]
my_first_lora_v2: 23%|##3 | 929/4000 [27:05<1:29:32, 1.75s/it, lr: 1.0e-04 loss: 6.340e-01]
my_first_lora_v2: 23%|##3 | 929/4000 [27:05<1:29:32, 1.75s/it, lr: 1.0e-04 loss: 6.340e-01]
my_first_lora_v2: 23%|##3 | 930/4000 [27:07<1:29:34, 1.75s/it, lr: 1.0e-04 loss: 7.192e-01]
my_first_lora_v2: 23%|##3 | 930/4000 [27:07<1:29:34, 1.75s/it, lr: 1.0e-04 loss: 7.192e-01]
my_first_lora_v2: 23%|##3 | 931/4000 [27:10<1:29:34, 1.75s/it, lr: 1.0e-04 loss: 4.707e-01]
my_first_lora_v2: 23%|##3 | 931/4000 [27:10<1:29:34, 1.75s/it, lr: 1.0e-04 loss: 4.707e-01]
my_first_lora_v2: 23%|##3 | 932/4000 [27:13<1:29:36, 1.75s/it, lr: 1.0e-04 loss: 2.261e-02]
my_first_lora_v2: 23%|##3 | 932/4000 [27:13<1:29:36, 1.75s/it, lr: 1.0e-04 loss: 2.261e-02]
my_first_lora_v2: 23%|##3 | 933/4000 [27:15<1:29:37, 1.75s/it, lr: 1.0e-04 loss: 5.781e-01]
my_first_lora_v2: 23%|##3 | 933/4000 [27:15<1:29:37, 1.75s/it, lr: 1.0e-04 loss: 5.781e-01]
my_first_lora_v2: 23%|##3 | 934/4000 [27:18<1:29:39, 1.75s/it, lr: 1.0e-04 loss: 6.460e-01]
my_first_lora_v2: 23%|##3 | 934/4000 [27:18<1:29:39, 1.75s/it, lr: 1.0e-04 loss: 6.460e-01]
my_first_lora_v2: 23%|##3 | 935/4000 [27:21<1:29:41, 1.76s/it, lr: 1.0e-04 loss: 7.003e-01]
my_first_lora_v2: 23%|##3 | 935/4000 [27:21<1:29:41, 1.76s/it, lr: 1.0e-04 loss: 7.003e-01]
my_first_lora_v2: 23%|##3 | 936/4000 [27:22<1:29:36, 1.75s/it, lr: 1.0e-04 loss: 1.006e-01]
my_first_lora_v2: 23%|##3 | 936/4000 [27:22<1:29:36, 1.75s/it, lr: 1.0e-04 loss: 1.006e-01]
my_first_lora_v2: 23%|##3 | 937/4000 [27:23<1:29:31, 1.75s/it, lr: 1.0e-04 loss: 8.016e-02]
my_first_lora_v2: 23%|##3 | 937/4000 [27:23<1:29:31, 1.75s/it, lr: 1.0e-04 loss: 8.016e-02]
my_first_lora_v2: 23%|##3 | 938/4000 [27:24<1:29:27, 1.75s/it, lr: 1.0e-04 loss: 7.074e-01]
my_first_lora_v2: 23%|##3 | 938/4000 [27:24<1:29:27, 1.75s/it, lr: 1.0e-04 loss: 7.074e-01]
my_first_lora_v2: 23%|##3 | 939/4000 [27:26<1:29:28, 1.75s/it, lr: 1.0e-04 loss: 7.285e-01]
my_first_lora_v2: 23%|##3 | 939/4000 [27:26<1:29:28, 1.75s/it, lr: 1.0e-04 loss: 7.285e-01]
my_first_lora_v2: 24%|##3 | 940/4000 [27:29<1:29:29, 1.75s/it, lr: 1.0e-04 loss: 6.853e-01]
my_first_lora_v2: 24%|##3 | 940/4000 [27:29<1:29:29, 1.75s/it, lr: 1.0e-04 loss: 6.853e-01]
my_first_lora_v2: 24%|##3 | 941/4000 [27:30<1:29:24, 1.75s/it, lr: 1.0e-04 loss: 4.109e-01]
my_first_lora_v2: 24%|##3 | 941/4000 [27:30<1:29:24, 1.75s/it, lr: 1.0e-04 loss: 4.109e-01]
my_first_lora_v2: 24%|##3 | 942/4000 [27:33<1:29:26, 1.75s/it, lr: 1.0e-04 loss: 3.492e-02]
my_first_lora_v2: 24%|##3 | 942/4000 [27:33<1:29:26, 1.75s/it, lr: 1.0e-04 loss: 3.492e-02]
my_first_lora_v2: 24%|##3 | 943/4000 [27:36<1:29:28, 1.76s/it, lr: 1.0e-04 loss: 8.863e-02]
my_first_lora_v2: 24%|##3 | 943/4000 [27:36<1:29:28, 1.76s/it, lr: 1.0e-04 loss: 8.863e-02]
my_first_lora_v2: 24%|##3 | 944/4000 [27:36<1:29:23, 1.76s/it, lr: 1.0e-04 loss: 8.125e-01]
my_first_lora_v2: 24%|##3 | 944/4000 [27:36<1:29:23, 1.76s/it, lr: 1.0e-04 loss: 8.125e-01]
my_first_lora_v2: 24%|##3 | 945/4000 [27:39<1:29:25, 1.76s/it, lr: 1.0e-04 loss: 8.715e-02]
my_first_lora_v2: 24%|##3 | 945/4000 [27:39<1:29:25, 1.76s/it, lr: 1.0e-04 loss: 8.715e-02]
my_first_lora_v2: 24%|##3 | 946/4000 [27:40<1:29:20, 1.76s/it, lr: 1.0e-04 loss: 7.143e-01]
my_first_lora_v2: 24%|##3 | 946/4000 [27:40<1:29:20, 1.76s/it, lr: 1.0e-04 loss: 7.143e-01]
my_first_lora_v2: 24%|##3 | 947/4000 [27:41<1:29:15, 1.75s/it, lr: 1.0e-04 loss: 7.679e-01]
my_first_lora_v2: 24%|##3 | 947/4000 [27:41<1:29:15, 1.75s/it, lr: 1.0e-04 loss: 7.679e-01]
my_first_lora_v2: 24%|##3 | 948/4000 [27:44<1:29:17, 1.76s/it, lr: 1.0e-04 loss: 4.316e-01]
my_first_lora_v2: 24%|##3 | 948/4000 [27:44<1:29:17, 1.76s/it, lr: 1.0e-04 loss: 4.316e-01]
my_first_lora_v2: 24%|##3 | 949/4000 [27:46<1:29:18, 1.76s/it, lr: 1.0e-04 loss: 4.240e-01]
my_first_lora_v2: 24%|##3 | 949/4000 [27:46<1:29:18, 1.76s/it, lr: 1.0e-04 loss: 4.240e-01]
my_first_lora_v2: 24%|##3 | 950/4000 [27:49<1:29:19, 1.76s/it, lr: 1.0e-04 loss: 3.500e-01]
my_first_lora_v2: 24%|##3 | 950/4000 [27:49<1:29:19, 1.76s/it, lr: 1.0e-04 loss: 3.500e-01]
my_first_lora_v2: 24%|##3 | 951/4000 [27:50<1:29:15, 1.76s/it, lr: 1.0e-04 loss: 5.510e-01]
my_first_lora_v2: 24%|##3 | 951/4000 [27:50<1:29:15, 1.76s/it, lr: 1.0e-04 loss: 5.510e-01]
my_first_lora_v2: 24%|##3 | 952/4000 [27:51<1:29:10, 1.76s/it, lr: 1.0e-04 loss: 7.029e-01]
my_first_lora_v2: 24%|##3 | 952/4000 [27:51<1:29:10, 1.76s/it, lr: 1.0e-04 loss: 7.029e-01]
my_first_lora_v2: 24%|##3 | 953/4000 [27:52<1:29:06, 1.75s/it, lr: 1.0e-04 loss: 1.357e-01]
my_first_lora_v2: 24%|##3 | 953/4000 [27:52<1:29:06, 1.75s/it, lr: 1.0e-04 loss: 1.357e-01]
my_first_lora_v2: 24%|##3 | 954/4000 [27:55<1:29:08, 1.76s/it, lr: 1.0e-04 loss: 6.685e-01]
my_first_lora_v2: 24%|##3 | 954/4000 [27:55<1:29:08, 1.76s/it, lr: 1.0e-04 loss: 6.685e-01]
my_first_lora_v2: 24%|##3 | 955/4000 [27:57<1:29:09, 1.76s/it, lr: 1.0e-04 loss: 6.201e-01]
my_first_lora_v2: 24%|##3 | 955/4000 [27:57<1:29:09, 1.76s/it, lr: 1.0e-04 loss: 6.201e-01]
my_first_lora_v2: 24%|##3 | 956/4000 [28:00<1:29:11, 1.76s/it, lr: 1.0e-04 loss: 2.358e-01]
my_first_lora_v2: 24%|##3 | 956/4000 [28:00<1:29:11, 1.76s/it, lr: 1.0e-04 loss: 2.358e-01]
my_first_lora_v2: 24%|##3 | 957/4000 [28:03<1:29:12, 1.76s/it, lr: 1.0e-04 loss: 2.473e-01]
my_first_lora_v2: 24%|##3 | 957/4000 [28:03<1:29:12, 1.76s/it, lr: 1.0e-04 loss: 2.473e-01]
my_first_lora_v2: 24%|##3 | 958/4000 [28:06<1:29:14, 1.76s/it, lr: 1.0e-04 loss: 4.956e-01]
my_first_lora_v2: 24%|##3 | 958/4000 [28:06<1:29:14, 1.76s/it, lr: 1.0e-04 loss: 4.956e-01]
my_first_lora_v2: 24%|##3 | 959/4000 [28:09<1:29:16, 1.76s/it, lr: 1.0e-04 loss: 6.793e-01]
my_first_lora_v2: 24%|##3 | 959/4000 [28:09<1:29:16, 1.76s/it, lr: 1.0e-04 loss: 6.793e-01]
my_first_lora_v2: 24%|##4 | 960/4000 [28:10<1:29:12, 1.76s/it, lr: 1.0e-04 loss: 4.018e-01]
my_first_lora_v2: 24%|##4 | 960/4000 [28:10<1:29:12, 1.76s/it, lr: 1.0e-04 loss: 4.018e-01]
my_first_lora_v2: 24%|##4 | 961/4000 [28:13<1:29:14, 1.76s/it, lr: 1.0e-04 loss: 5.879e-01]
my_first_lora_v2: 24%|##4 | 961/4000 [28:13<1:29:14, 1.76s/it, lr: 1.0e-04 loss: 5.879e-01]
my_first_lora_v2: 24%|##4 | 962/4000 [28:13<1:29:09, 1.76s/it, lr: 1.0e-04 loss: 2.488e-01]
my_first_lora_v2: 24%|##4 | 962/4000 [28:13<1:29:09, 1.76s/it, lr: 1.0e-04 loss: 2.488e-01]
my_first_lora_v2: 24%|##4 | 963/4000 [28:16<1:29:11, 1.76s/it, lr: 1.0e-04 loss: 5.870e-01]
my_first_lora_v2: 24%|##4 | 963/4000 [28:16<1:29:11, 1.76s/it, lr: 1.0e-04 loss: 5.870e-01]
my_first_lora_v2: 24%|##4 | 964/4000 [28:19<1:29:12, 1.76s/it, lr: 1.0e-04 loss: 2.065e-01]
my_first_lora_v2: 24%|##4 | 964/4000 [28:19<1:29:12, 1.76s/it, lr: 1.0e-04 loss: 2.065e-01]
my_first_lora_v2: 24%|##4 | 965/4000 [28:22<1:29:13, 1.76s/it, lr: 1.0e-04 loss: 4.472e-01]
my_first_lora_v2: 24%|##4 | 965/4000 [28:22<1:29:13, 1.76s/it, lr: 1.0e-04 loss: 4.472e-01]
my_first_lora_v2: 24%|##4 | 966/4000 [28:23<1:29:09, 1.76s/it, lr: 1.0e-04 loss: 2.613e-01]
my_first_lora_v2: 24%|##4 | 966/4000 [28:23<1:29:09, 1.76s/it, lr: 1.0e-04 loss: 2.613e-01]
my_first_lora_v2: 24%|##4 | 967/4000 [28:24<1:29:05, 1.76s/it, lr: 1.0e-04 loss: 4.862e-01]
my_first_lora_v2: 24%|##4 | 967/4000 [28:24<1:29:05, 1.76s/it, lr: 1.0e-04 loss: 4.862e-01]
my_first_lora_v2: 24%|##4 | 968/4000 [28:25<1:29:00, 1.76s/it, lr: 1.0e-04 loss: 2.168e-01]
my_first_lora_v2: 24%|##4 | 968/4000 [28:25<1:29:00, 1.76s/it, lr: 1.0e-04 loss: 2.168e-01]
my_first_lora_v2: 24%|##4 | 969/4000 [28:25<1:28:56, 1.76s/it, lr: 1.0e-04 loss: 3.268e-01]
my_first_lora_v2: 24%|##4 | 969/4000 [28:25<1:28:56, 1.76s/it, lr: 1.0e-04 loss: 3.268e-01]
my_first_lora_v2: 24%|##4 | 970/4000 [28:26<1:28:51, 1.76s/it, lr: 1.0e-04 loss: 1.760e-01]
my_first_lora_v2: 24%|##4 | 970/4000 [28:26<1:28:51, 1.76s/it, lr: 1.0e-04 loss: 1.760e-01]
my_first_lora_v2: 24%|##4 | 971/4000 [28:27<1:28:46, 1.76s/it, lr: 1.0e-04 loss: 4.351e-01]
my_first_lora_v2: 24%|##4 | 971/4000 [28:27<1:28:46, 1.76s/it, lr: 1.0e-04 loss: 4.351e-01]
my_first_lora_v2: 24%|##4 | 972/4000 [28:28<1:28:42, 1.76s/it, lr: 1.0e-04 loss: 7.394e-01]
my_first_lora_v2: 24%|##4 | 972/4000 [28:28<1:28:42, 1.76s/it, lr: 1.0e-04 loss: 7.394e-01]
my_first_lora_v2: 24%|##4 | 973/4000 [28:29<1:28:37, 1.76s/it, lr: 1.0e-04 loss: 3.595e-01]
my_first_lora_v2: 24%|##4 | 973/4000 [28:29<1:28:37, 1.76s/it, lr: 1.0e-04 loss: 3.595e-01]
my_first_lora_v2: 24%|##4 | 974/4000 [28:30<1:28:32, 1.76s/it, lr: 1.0e-04 loss: 2.632e-01]
my_first_lora_v2: 24%|##4 | 974/4000 [28:30<1:28:32, 1.76s/it, lr: 1.0e-04 loss: 2.632e-01]
my_first_lora_v2: 24%|##4 | 975/4000 [28:30<1:28:28, 1.75s/it, lr: 1.0e-04 loss: 2.612e-01]
my_first_lora_v2: 24%|##4 | 975/4000 [28:30<1:28:28, 1.75s/it, lr: 1.0e-04 loss: 2.612e-01]
my_first_lora_v2: 24%|##4 | 976/4000 [28:33<1:28:29, 1.76s/it, lr: 1.0e-04 loss: 6.755e-01]
my_first_lora_v2: 24%|##4 | 976/4000 [28:33<1:28:29, 1.76s/it, lr: 1.0e-04 loss: 6.755e-01]
my_first_lora_v2: 24%|##4 | 977/4000 [28:36<1:28:30, 1.76s/it, lr: 1.0e-04 loss: 6.803e-02]
my_first_lora_v2: 24%|##4 | 977/4000 [28:36<1:28:30, 1.76s/it, lr: 1.0e-04 loss: 6.803e-02]
my_first_lora_v2: 24%|##4 | 978/4000 [28:37<1:28:25, 1.76s/it, lr: 1.0e-04 loss: 6.837e-01]
my_first_lora_v2: 24%|##4 | 978/4000 [28:37<1:28:25, 1.76s/it, lr: 1.0e-04 loss: 6.837e-01]
my_first_lora_v2: 24%|##4 | 979/4000 [28:38<1:28:22, 1.76s/it, lr: 1.0e-04 loss: 1.902e-02]
my_first_lora_v2: 24%|##4 | 979/4000 [28:38<1:28:22, 1.76s/it, lr: 1.0e-04 loss: 1.902e-02]
my_first_lora_v2: 24%|##4 | 980/4000 [28:40<1:28:23, 1.76s/it, lr: 1.0e-04 loss: 5.648e-01]
my_first_lora_v2: 24%|##4 | 980/4000 [28:40<1:28:23, 1.76s/it, lr: 1.0e-04 loss: 5.648e-01]
my_first_lora_v2: 25%|##4 | 981/4000 [28:41<1:28:18, 1.76s/it, lr: 1.0e-04 loss: 4.335e-01]
my_first_lora_v2: 25%|##4 | 981/4000 [28:41<1:28:18, 1.76s/it, lr: 1.0e-04 loss: 4.335e-01]
my_first_lora_v2: 25%|##4 | 982/4000 [28:42<1:28:14, 1.75s/it, lr: 1.0e-04 loss: 5.360e-01]
my_first_lora_v2: 25%|##4 | 982/4000 [28:42<1:28:14, 1.75s/it, lr: 1.0e-04 loss: 5.360e-01]
my_first_lora_v2: 25%|##4 | 983/4000 [28:44<1:28:14, 1.75s/it, lr: 1.0e-04 loss: 3.261e-01]
my_first_lora_v2: 25%|##4 | 983/4000 [28:44<1:28:14, 1.75s/it, lr: 1.0e-04 loss: 3.261e-01]
my_first_lora_v2: 25%|##4 | 984/4000 [28:45<1:28:09, 1.75s/it, lr: 1.0e-04 loss: 4.408e-01]
my_first_lora_v2: 25%|##4 | 984/4000 [28:45<1:28:09, 1.75s/it, lr: 1.0e-04 loss: 4.408e-01]
my_first_lora_v2: 25%|##4 | 985/4000 [28:48<1:28:11, 1.75s/it, lr: 1.0e-04 loss: 1.662e-01]
my_first_lora_v2: 25%|##4 | 985/4000 [28:48<1:28:11, 1.75s/it, lr: 1.0e-04 loss: 1.662e-01]
my_first_lora_v2: 25%|##4 | 986/4000 [28:51<1:28:12, 1.76s/it, lr: 1.0e-04 loss: 4.396e-01]
my_first_lora_v2: 25%|##4 | 986/4000 [28:51<1:28:12, 1.76s/it, lr: 1.0e-04 loss: 4.396e-01]
my_first_lora_v2: 25%|##4 | 987/4000 [28:54<1:28:13, 1.76s/it, lr: 1.0e-04 loss: 3.545e-01]
my_first_lora_v2: 25%|##4 | 987/4000 [28:54<1:28:13, 1.76s/it, lr: 1.0e-04 loss: 3.545e-01]
my_first_lora_v2: 25%|##4 | 988/4000 [28:57<1:28:15, 1.76s/it, lr: 1.0e-04 loss: 2.862e-01]
my_first_lora_v2: 25%|##4 | 988/4000 [28:57<1:28:15, 1.76s/it, lr: 1.0e-04 loss: 2.862e-01]
my_first_lora_v2: 25%|##4 | 989/4000 [28:57<1:28:10, 1.76s/it, lr: 1.0e-04 loss: 3.163e-01]
my_first_lora_v2: 25%|##4 | 989/4000 [28:57<1:28:10, 1.76s/it, lr: 1.0e-04 loss: 3.163e-01]
my_first_lora_v2: 25%|##4 | 990/4000 [28:58<1:28:06, 1.76s/it, lr: 1.0e-04 loss: 3.932e-01]
my_first_lora_v2: 25%|##4 | 990/4000 [28:58<1:28:06, 1.76s/it, lr: 1.0e-04 loss: 3.932e-01]
my_first_lora_v2: 25%|##4 | 991/4000 [28:59<1:28:01, 1.76s/it, lr: 1.0e-04 loss: 6.081e-01]
my_first_lora_v2: 25%|##4 | 991/4000 [28:59<1:28:01, 1.76s/it, lr: 1.0e-04 loss: 6.081e-01]
my_first_lora_v2: 25%|##4 | 992/4000 [29:00<1:27:56, 1.75s/it, lr: 1.0e-04 loss: 5.886e-01]
my_first_lora_v2: 25%|##4 | 992/4000 [29:00<1:27:56, 1.75s/it, lr: 1.0e-04 loss: 5.886e-01]
my_first_lora_v2: 25%|##4 | 993/4000 [29:01<1:27:52, 1.75s/it, lr: 1.0e-04 loss: 4.995e-01]
my_first_lora_v2: 25%|##4 | 993/4000 [29:01<1:27:52, 1.75s/it, lr: 1.0e-04 loss: 4.995e-01]
my_first_lora_v2: 25%|##4 | 994/4000 [29:02<1:27:48, 1.75s/it, lr: 1.0e-04 loss: 5.258e-01]
my_first_lora_v2: 25%|##4 | 994/4000 [29:02<1:27:48, 1.75s/it, lr: 1.0e-04 loss: 5.258e-01]
my_first_lora_v2: 25%|##4 | 995/4000 [29:04<1:27:50, 1.75s/it, lr: 1.0e-04 loss: 5.022e-01]
my_first_lora_v2: 25%|##4 | 995/4000 [29:04<1:27:50, 1.75s/it, lr: 1.0e-04 loss: 5.022e-01]
my_first_lora_v2: 25%|##4 | 996/4000 [29:05<1:27:45, 1.75s/it, lr: 1.0e-04 loss: 2.995e-01]
my_first_lora_v2: 25%|##4 | 996/4000 [29:05<1:27:45, 1.75s/it, lr: 1.0e-04 loss: 2.995e-01]
my_first_lora_v2: 25%|##4 | 997/4000 [29:08<1:27:46, 1.75s/it, lr: 1.0e-04 loss: 2.841e-01]
my_first_lora_v2: 25%|##4 | 997/4000 [29:08<1:27:46, 1.75s/it, lr: 1.0e-04 loss: 2.841e-01]
my_first_lora_v2: 25%|##4 | 998/4000 [29:11<1:27:47, 1.75s/it, lr: 1.0e-04 loss: 4.944e-01]
my_first_lora_v2: 25%|##4 | 998/4000 [29:11<1:27:47, 1.75s/it, lr: 1.0e-04 loss: 4.944e-01]
my_first_lora_v2: 25%|##4 | 999/4000 [29:11<1:27:42, 1.75s/it, lr: 1.0e-04 loss: 6.844e-01]
my_first_lora_v2: 25%|##4 | 999/4000 [29:11<1:27:42, 1.75s/it, lr: 1.0e-04 loss: 6.844e-01] |
| Saving at step 1000 |
| Saved checkpoint to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v2/my_first_lora_v2_000001000.safetensors |
| Saved optimizer to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v2/optimizer.pt |
| Unloading assistant lora |
|
|
|
|
|
Generating Images: 0%| | 0/3 [00:00<?, ?it/s]
Generating Images: 0%| | 0/3 [00:00<?, ?it/s][A[A |
|
|
|
Generating Images: 33%|###3 | 1/3 [00:07<00:15, 7.79s/it]
Generating Images: 33%|###3 | 1/3 [00:07<00:15, 7.79s/it][A[A |
|
|
|
Generating Images: 67%|######6 | 2/3 [00:15<00:07, 7.73s/it]
Generating Images: 67%|######6 | 2/3 [00:15<00:07, 7.73s/it][A[A |
|
|
|
Generating Images: 100%|##########| 3/3 [00:23<00:00, 7.68s/it]
Generating Images: 100%|##########| 3/3 [00:23<00:00, 7.68s/it][A[A |
|
|
|
[A[ALoading assistant lora |
|
my_first_lora_v2: 25%|##5 | 1000/4000 [29:15<1:27:45, 1.76s/it, lr: 1.0e-04 loss: 3.343e-01]
my_first_lora_v2: 25%|##5 | 1000/4000 [29:15<1:27:45, 1.76s/it, lr: 1.0e-04 loss: 3.343e-01]
my_first_lora_v2: 25%|##5 | 1001/4000 [29:17<1:27:46, 1.76s/it, lr: 1.0e-04 loss: 3.556e-01]
my_first_lora_v2: 25%|##5 | 1001/4000 [29:17<1:27:46, 1.76s/it, lr: 1.0e-04 loss: 3.556e-01]
my_first_lora_v2: 25%|##5 | 1002/4000 [29:18<1:27:42, 1.76s/it, lr: 1.0e-04 loss: 7.267e-01]
my_first_lora_v2: 25%|##5 | 1002/4000 [29:18<1:27:42, 1.76s/it, lr: 1.0e-04 loss: 7.267e-01]
my_first_lora_v2: 25%|##5 | 1003/4000 [29:21<1:27:43, 1.76s/it, lr: 1.0e-04 loss: 7.295e-01]
my_first_lora_v2: 25%|##5 | 1003/4000 [29:21<1:27:43, 1.76s/it, lr: 1.0e-04 loss: 7.295e-01]
my_first_lora_v2: 25%|##5 | 1004/4000 [29:22<1:27:39, 1.76s/it, lr: 1.0e-04 loss: 1.818e-02]
my_first_lora_v2: 25%|##5 | 1004/4000 [29:22<1:27:39, 1.76s/it, lr: 1.0e-04 loss: 1.818e-02]
my_first_lora_v2: 25%|##5 | 1005/4000 [29:25<1:27:41, 1.76s/it, lr: 1.0e-04 loss: 3.455e-01]
my_first_lora_v2: 25%|##5 | 1005/4000 [29:25<1:27:41, 1.76s/it, lr: 1.0e-04 loss: 3.455e-01]
my_first_lora_v2: 25%|##5 | 1006/4000 [29:26<1:27:36, 1.76s/it, lr: 1.0e-04 loss: 1.301e-01]
my_first_lora_v2: 25%|##5 | 1006/4000 [29:26<1:27:36, 1.76s/it, lr: 1.0e-04 loss: 1.301e-01]
my_first_lora_v2: 25%|##5 | 1007/4000 [29:27<1:27:32, 1.75s/it, lr: 1.0e-04 loss: 7.721e-01]
my_first_lora_v2: 25%|##5 | 1007/4000 [29:27<1:27:32, 1.75s/it, lr: 1.0e-04 loss: 7.721e-01]
my_first_lora_v2: 25%|##5 | 1008/4000 [29:29<1:27:32, 1.76s/it, lr: 1.0e-04 loss: 1.889e-01]
my_first_lora_v2: 25%|##5 | 1008/4000 [29:29<1:27:32, 1.76s/it, lr: 1.0e-04 loss: 1.889e-01]
my_first_lora_v2: 25%|##5 | 1009/4000 [29:30<1:27:27, 1.75s/it, lr: 1.0e-04 loss: 6.450e-01]
my_first_lora_v2: 25%|##5 | 1009/4000 [29:30<1:27:27, 1.75s/it, lr: 1.0e-04 loss: 6.450e-01]
my_first_lora_v2: 25%|##5 | 1010/4000 [29:33<1:27:29, 1.76s/it, lr: 1.0e-04 loss: 2.625e-01]
my_first_lora_v2: 25%|##5 | 1010/4000 [29:33<1:27:29, 1.76s/it, lr: 1.0e-04 loss: 2.625e-01]
my_first_lora_v2: 25%|##5 | 1011/4000 [29:35<1:27:29, 1.76s/it, lr: 1.0e-04 loss: 1.932e-01]
my_first_lora_v2: 25%|##5 | 1011/4000 [29:35<1:27:29, 1.76s/it, lr: 1.0e-04 loss: 1.932e-01]
my_first_lora_v2: 25%|##5 | 1012/4000 [29:38<1:27:31, 1.76s/it, lr: 1.0e-04 loss: 1.542e-01]
my_first_lora_v2: 25%|##5 | 1012/4000 [29:38<1:27:31, 1.76s/it, lr: 1.0e-04 loss: 1.542e-01]
my_first_lora_v2: 25%|##5 | 1013/4000 [29:39<1:27:27, 1.76s/it, lr: 1.0e-04 loss: 2.015e-01]
my_first_lora_v2: 25%|##5 | 1013/4000 [29:39<1:27:27, 1.76s/it, lr: 1.0e-04 loss: 2.015e-01]
my_first_lora_v2: 25%|##5 | 1014/4000 [29:42<1:27:28, 1.76s/it, lr: 1.0e-04 loss: 2.305e-01]
my_first_lora_v2: 25%|##5 | 1014/4000 [29:42<1:27:28, 1.76s/it, lr: 1.0e-04 loss: 2.305e-01]
my_first_lora_v2: 25%|##5 | 1015/4000 [29:44<1:27:29, 1.76s/it, lr: 1.0e-04 loss: 3.306e-01]
my_first_lora_v2: 25%|##5 | 1015/4000 [29:44<1:27:29, 1.76s/it, lr: 1.0e-04 loss: 3.306e-01]
my_first_lora_v2: 25%|##5 | 1016/4000 [29:47<1:27:31, 1.76s/it, lr: 1.0e-04 loss: 4.735e-01]
my_first_lora_v2: 25%|##5 | 1016/4000 [29:47<1:27:31, 1.76s/it, lr: 1.0e-04 loss: 4.735e-01]
my_first_lora_v2: 25%|##5 | 1017/4000 [29:50<1:27:32, 1.76s/it, lr: 1.0e-04 loss: 6.050e-02]
my_first_lora_v2: 25%|##5 | 1017/4000 [29:50<1:27:32, 1.76s/it, lr: 1.0e-04 loss: 6.050e-02]
my_first_lora_v2: 25%|##5 | 1018/4000 [29:51<1:27:28, 1.76s/it, lr: 1.0e-04 loss: 5.539e-01]
my_first_lora_v2: 25%|##5 | 1018/4000 [29:51<1:27:28, 1.76s/it, lr: 1.0e-04 loss: 5.539e-01]
my_first_lora_v2: 25%|##5 | 1019/4000 [29:52<1:27:24, 1.76s/it, lr: 1.0e-04 loss: 8.077e-01]
my_first_lora_v2: 25%|##5 | 1019/4000 [29:52<1:27:24, 1.76s/it, lr: 1.0e-04 loss: 8.077e-01]
my_first_lora_v2: 26%|##5 | 1020/4000 [29:53<1:27:19, 1.76s/it, lr: 1.0e-04 loss: 7.291e-01]
my_first_lora_v2: 26%|##5 | 1020/4000 [29:53<1:27:19, 1.76s/it, lr: 1.0e-04 loss: 7.291e-01]
my_first_lora_v2: 26%|##5 | 1021/4000 [29:54<1:27:15, 1.76s/it, lr: 1.0e-04 loss: 5.186e-01]
my_first_lora_v2: 26%|##5 | 1021/4000 [29:54<1:27:15, 1.76s/it, lr: 1.0e-04 loss: 5.186e-01]
my_first_lora_v2: 26%|##5 | 1022/4000 [29:57<1:27:17, 1.76s/it, lr: 1.0e-04 loss: 2.485e-01]
my_first_lora_v2: 26%|##5 | 1022/4000 [29:57<1:27:17, 1.76s/it, lr: 1.0e-04 loss: 2.485e-01]
my_first_lora_v2: 26%|##5 | 1023/4000 [29:58<1:27:12, 1.76s/it, lr: 1.0e-04 loss: 1.725e-01]
my_first_lora_v2: 26%|##5 | 1023/4000 [29:58<1:27:12, 1.76s/it, lr: 1.0e-04 loss: 1.725e-01]
my_first_lora_v2: 26%|##5 | 1024/4000 [29:58<1:27:08, 1.76s/it, lr: 1.0e-04 loss: 7.764e-01]
my_first_lora_v2: 26%|##5 | 1024/4000 [29:58<1:27:08, 1.76s/it, lr: 1.0e-04 loss: 7.764e-01]
my_first_lora_v2: 26%|##5 | 1025/4000 [29:59<1:27:03, 1.76s/it, lr: 1.0e-04 loss: 7.437e-01]
my_first_lora_v2: 26%|##5 | 1025/4000 [29:59<1:27:03, 1.76s/it, lr: 1.0e-04 loss: 7.437e-01]
my_first_lora_v2: 26%|##5 | 1026/4000 [30:02<1:27:05, 1.76s/it, lr: 1.0e-04 loss: 4.669e-01]
my_first_lora_v2: 26%|##5 | 1026/4000 [30:02<1:27:05, 1.76s/it, lr: 1.0e-04 loss: 4.669e-01]
my_first_lora_v2: 26%|##5 | 1027/4000 [30:05<1:27:07, 1.76s/it, lr: 1.0e-04 loss: 4.971e-01]
my_first_lora_v2: 26%|##5 | 1027/4000 [30:05<1:27:07, 1.76s/it, lr: 1.0e-04 loss: 4.971e-01]
my_first_lora_v2: 26%|##5 | 1028/4000 [30:08<1:27:08, 1.76s/it, lr: 1.0e-04 loss: 1.160e-01]
my_first_lora_v2: 26%|##5 | 1028/4000 [30:08<1:27:08, 1.76s/it, lr: 1.0e-04 loss: 1.160e-01]
my_first_lora_v2: 26%|##5 | 1029/4000 [30:09<1:27:03, 1.76s/it, lr: 1.0e-04 loss: 2.493e-02]
my_first_lora_v2: 26%|##5 | 1029/4000 [30:09<1:27:03, 1.76s/it, lr: 1.0e-04 loss: 2.493e-02]
my_first_lora_v2: 26%|##5 | 1030/4000 [30:12<1:27:05, 1.76s/it, lr: 1.0e-04 loss: 6.484e-01]
my_first_lora_v2: 26%|##5 | 1030/4000 [30:12<1:27:05, 1.76s/it, lr: 1.0e-04 loss: 6.484e-01]
my_first_lora_v2: 26%|##5 | 1031/4000 [30:13<1:27:01, 1.76s/it, lr: 1.0e-04 loss: 5.909e-01]
my_first_lora_v2: 26%|##5 | 1031/4000 [30:13<1:27:01, 1.76s/it, lr: 1.0e-04 loss: 5.909e-01]
my_first_lora_v2: 26%|##5 | 1032/4000 [30:13<1:26:56, 1.76s/it, lr: 1.0e-04 loss: 3.128e-01]
my_first_lora_v2: 26%|##5 | 1032/4000 [30:13<1:26:56, 1.76s/it, lr: 1.0e-04 loss: 3.128e-01]
my_first_lora_v2: 26%|##5 | 1033/4000 [30:16<1:26:56, 1.76s/it, lr: 1.0e-04 loss: 1.280e-01]
my_first_lora_v2: 26%|##5 | 1033/4000 [30:16<1:26:56, 1.76s/it, lr: 1.0e-04 loss: 1.280e-01]
my_first_lora_v2: 26%|##5 | 1034/4000 [30:19<1:26:58, 1.76s/it, lr: 1.0e-04 loss: 1.757e-01]
my_first_lora_v2: 26%|##5 | 1034/4000 [30:19<1:26:58, 1.76s/it, lr: 1.0e-04 loss: 1.757e-01]
my_first_lora_v2: 26%|##5 | 1035/4000 [30:20<1:26:54, 1.76s/it, lr: 1.0e-04 loss: 5.284e-02]
my_first_lora_v2: 26%|##5 | 1035/4000 [30:20<1:26:54, 1.76s/it, lr: 1.0e-04 loss: 5.284e-02]
my_first_lora_v2: 26%|##5 | 1036/4000 [30:20<1:26:49, 1.76s/it, lr: 1.0e-04 loss: 5.599e-01]
my_first_lora_v2: 26%|##5 | 1036/4000 [30:20<1:26:49, 1.76s/it, lr: 1.0e-04 loss: 5.599e-01]
my_first_lora_v2: 26%|##5 | 1037/4000 [30:23<1:26:50, 1.76s/it, lr: 1.0e-04 loss: 7.081e-01]
my_first_lora_v2: 26%|##5 | 1037/4000 [30:23<1:26:50, 1.76s/it, lr: 1.0e-04 loss: 7.081e-01]
my_first_lora_v2: 26%|##5 | 1038/4000 [30:26<1:26:51, 1.76s/it, lr: 1.0e-04 loss: 4.837e-02]
my_first_lora_v2: 26%|##5 | 1038/4000 [30:26<1:26:51, 1.76s/it, lr: 1.0e-04 loss: 4.837e-02]
my_first_lora_v2: 26%|##5 | 1039/4000 [30:27<1:26:47, 1.76s/it, lr: 1.0e-04 loss: 1.217e-01]
my_first_lora_v2: 26%|##5 | 1039/4000 [30:27<1:26:47, 1.76s/it, lr: 1.0e-04 loss: 1.217e-01]
my_first_lora_v2: 26%|##6 | 1040/4000 [30:28<1:26:44, 1.76s/it, lr: 1.0e-04 loss: 8.073e-01]
my_first_lora_v2: 26%|##6 | 1040/4000 [30:28<1:26:44, 1.76s/it, lr: 1.0e-04 loss: 8.073e-01]
my_first_lora_v2: 26%|##6 | 1041/4000 [30:29<1:26:40, 1.76s/it, lr: 1.0e-04 loss: 1.708e-01]
my_first_lora_v2: 26%|##6 | 1041/4000 [30:29<1:26:40, 1.76s/it, lr: 1.0e-04 loss: 1.708e-01]
my_first_lora_v2: 26%|##6 | 1042/4000 [30:32<1:26:41, 1.76s/it, lr: 1.0e-04 loss: 7.808e-01]
my_first_lora_v2: 26%|##6 | 1042/4000 [30:32<1:26:41, 1.76s/it, lr: 1.0e-04 loss: 7.808e-01]
my_first_lora_v2: 26%|##6 | 1043/4000 [30:33<1:26:36, 1.76s/it, lr: 1.0e-04 loss: 7.003e-01]
my_first_lora_v2: 26%|##6 | 1043/4000 [30:33<1:26:36, 1.76s/it, lr: 1.0e-04 loss: 7.003e-01]
my_first_lora_v2: 26%|##6 | 1044/4000 [30:35<1:26:36, 1.76s/it, lr: 1.0e-04 loss: 1.997e-01]
my_first_lora_v2: 26%|##6 | 1044/4000 [30:35<1:26:36, 1.76s/it, lr: 1.0e-04 loss: 1.997e-01]
my_first_lora_v2: 26%|##6 | 1045/4000 [30:36<1:26:32, 1.76s/it, lr: 1.0e-04 loss: 5.996e-01]
my_first_lora_v2: 26%|##6 | 1045/4000 [30:36<1:26:32, 1.76s/it, lr: 1.0e-04 loss: 5.996e-01]
my_first_lora_v2: 26%|##6 | 1046/4000 [30:39<1:26:33, 1.76s/it, lr: 1.0e-04 loss: 2.169e-01]
my_first_lora_v2: 26%|##6 | 1046/4000 [30:39<1:26:33, 1.76s/it, lr: 1.0e-04 loss: 2.169e-01]
my_first_lora_v2: 26%|##6 | 1047/4000 [30:41<1:26:33, 1.76s/it, lr: 1.0e-04 loss: 6.606e-01]
my_first_lora_v2: 26%|##6 | 1047/4000 [30:41<1:26:33, 1.76s/it, lr: 1.0e-04 loss: 6.606e-01]
my_first_lora_v2: 26%|##6 | 1048/4000 [30:44<1:26:35, 1.76s/it, lr: 1.0e-04 loss: 1.639e-01]
my_first_lora_v2: 26%|##6 | 1048/4000 [30:44<1:26:35, 1.76s/it, lr: 1.0e-04 loss: 1.639e-01]
my_first_lora_v2: 26%|##6 | 1049/4000 [30:45<1:26:31, 1.76s/it, lr: 1.0e-04 loss: 6.156e-01]
my_first_lora_v2: 26%|##6 | 1049/4000 [30:45<1:26:31, 1.76s/it, lr: 1.0e-04 loss: 6.156e-01]
my_first_lora_v2: 26%|##6 | 1050/4000 [30:46<1:26:26, 1.76s/it, lr: 1.0e-04 loss: 2.748e-01]
my_first_lora_v2: 26%|##6 | 1050/4000 [30:46<1:26:26, 1.76s/it, lr: 1.0e-04 loss: 2.748e-01]
my_first_lora_v2: 26%|##6 | 1051/4000 [30:48<1:26:27, 1.76s/it, lr: 1.0e-04 loss: 4.020e-01]
my_first_lora_v2: 26%|##6 | 1051/4000 [30:48<1:26:27, 1.76s/it, lr: 1.0e-04 loss: 4.020e-01]
my_first_lora_v2: 26%|##6 | 1052/4000 [30:51<1:26:28, 1.76s/it, lr: 1.0e-04 loss: 1.364e-01]
my_first_lora_v2: 26%|##6 | 1052/4000 [30:51<1:26:28, 1.76s/it, lr: 1.0e-04 loss: 1.364e-01]
my_first_lora_v2: 26%|##6 | 1053/4000 [30:52<1:26:25, 1.76s/it, lr: 1.0e-04 loss: 5.535e-01]
my_first_lora_v2: 26%|##6 | 1053/4000 [30:52<1:26:25, 1.76s/it, lr: 1.0e-04 loss: 5.535e-01]
my_first_lora_v2: 26%|##6 | 1054/4000 [30:53<1:26:20, 1.76s/it, lr: 1.0e-04 loss: 8.029e-01]
my_first_lora_v2: 26%|##6 | 1054/4000 [30:53<1:26:20, 1.76s/it, lr: 1.0e-04 loss: 8.029e-01]
my_first_lora_v2: 26%|##6 | 1055/4000 [30:56<1:26:22, 1.76s/it, lr: 1.0e-04 loss: 1.631e-01]
my_first_lora_v2: 26%|##6 | 1055/4000 [30:56<1:26:22, 1.76s/it, lr: 1.0e-04 loss: 1.631e-01]
my_first_lora_v2: 26%|##6 | 1056/4000 [30:57<1:26:17, 1.76s/it, lr: 1.0e-04 loss: 2.855e-01]
my_first_lora_v2: 26%|##6 | 1056/4000 [30:57<1:26:17, 1.76s/it, lr: 1.0e-04 loss: 2.855e-01]
my_first_lora_v2: 26%|##6 | 1057/4000 [30:57<1:26:13, 1.76s/it, lr: 1.0e-04 loss: 2.456e-01]
my_first_lora_v2: 26%|##6 | 1057/4000 [30:57<1:26:13, 1.76s/it, lr: 1.0e-04 loss: 2.456e-01]
my_first_lora_v2: 26%|##6 | 1058/4000 [30:58<1:26:08, 1.76s/it, lr: 1.0e-04 loss: 1.583e-01]
my_first_lora_v2: 26%|##6 | 1058/4000 [30:58<1:26:08, 1.76s/it, lr: 1.0e-04 loss: 1.583e-01]
my_first_lora_v2: 26%|##6 | 1059/4000 [31:01<1:26:10, 1.76s/it, lr: 1.0e-04 loss: 8.799e-02]
my_first_lora_v2: 26%|##6 | 1059/4000 [31:01<1:26:10, 1.76s/it, lr: 1.0e-04 loss: 8.799e-02]
my_first_lora_v2: 26%|##6 | 1060/4000 [31:04<1:26:11, 1.76s/it, lr: 1.0e-04 loss: 4.999e-01]
my_first_lora_v2: 26%|##6 | 1060/4000 [31:04<1:26:11, 1.76s/it, lr: 1.0e-04 loss: 4.999e-01]
my_first_lora_v2: 27%|##6 | 1061/4000 [31:05<1:26:07, 1.76s/it, lr: 1.0e-04 loss: 4.574e-01]
my_first_lora_v2: 27%|##6 | 1061/4000 [31:05<1:26:07, 1.76s/it, lr: 1.0e-04 loss: 4.574e-01]
my_first_lora_v2: 27%|##6 | 1062/4000 [31:08<1:26:08, 1.76s/it, lr: 1.0e-04 loss: 7.018e-02]
my_first_lora_v2: 27%|##6 | 1062/4000 [31:08<1:26:08, 1.76s/it, lr: 1.0e-04 loss: 7.018e-02]
my_first_lora_v2: 27%|##6 | 1063/4000 [31:09<1:26:04, 1.76s/it, lr: 1.0e-04 loss: 5.045e-01]
my_first_lora_v2: 27%|##6 | 1063/4000 [31:09<1:26:04, 1.76s/it, lr: 1.0e-04 loss: 5.045e-01]
my_first_lora_v2: 27%|##6 | 1064/4000 [31:09<1:25:59, 1.76s/it, lr: 1.0e-04 loss: 4.044e-01]
my_first_lora_v2: 27%|##6 | 1064/4000 [31:09<1:25:59, 1.76s/it, lr: 1.0e-04 loss: 4.044e-01]
my_first_lora_v2: 27%|##6 | 1065/4000 [31:12<1:26:00, 1.76s/it, lr: 1.0e-04 loss: 5.731e-01]
my_first_lora_v2: 27%|##6 | 1065/4000 [31:12<1:26:00, 1.76s/it, lr: 1.0e-04 loss: 5.731e-01]
my_first_lora_v2: 27%|##6 | 1066/4000 [31:15<1:26:02, 1.76s/it, lr: 1.0e-04 loss: 6.596e-01]
my_first_lora_v2: 27%|##6 | 1066/4000 [31:15<1:26:02, 1.76s/it, lr: 1.0e-04 loss: 6.596e-01]
my_first_lora_v2: 27%|##6 | 1067/4000 [31:18<1:26:03, 1.76s/it, lr: 1.0e-04 loss: 2.600e-01]
my_first_lora_v2: 27%|##6 | 1067/4000 [31:18<1:26:03, 1.76s/it, lr: 1.0e-04 loss: 2.600e-01]
my_first_lora_v2: 27%|##6 | 1068/4000 [31:21<1:26:04, 1.76s/it, lr: 1.0e-04 loss: 1.016e-01]
my_first_lora_v2: 27%|##6 | 1068/4000 [31:21<1:26:04, 1.76s/it, lr: 1.0e-04 loss: 1.016e-01]
my_first_lora_v2: 27%|##6 | 1069/4000 [31:23<1:26:05, 1.76s/it, lr: 1.0e-04 loss: 6.093e-01]
my_first_lora_v2: 27%|##6 | 1069/4000 [31:23<1:26:05, 1.76s/it, lr: 1.0e-04 loss: 6.093e-01]
my_first_lora_v2: 27%|##6 | 1070/4000 [31:26<1:26:06, 1.76s/it, lr: 1.0e-04 loss: 3.401e-01]
my_first_lora_v2: 27%|##6 | 1070/4000 [31:26<1:26:06, 1.76s/it, lr: 1.0e-04 loss: 3.401e-01]
my_first_lora_v2: 27%|##6 | 1071/4000 [31:27<1:26:02, 1.76s/it, lr: 1.0e-04 loss: 7.131e-01]
my_first_lora_v2: 27%|##6 | 1071/4000 [31:27<1:26:02, 1.76s/it, lr: 1.0e-04 loss: 7.131e-01]
my_first_lora_v2: 27%|##6 | 1072/4000 [31:30<1:26:02, 1.76s/it, lr: 1.0e-04 loss: 4.756e-01]
my_first_lora_v2: 27%|##6 | 1072/4000 [31:30<1:26:02, 1.76s/it, lr: 1.0e-04 loss: 4.756e-01]
my_first_lora_v2: 27%|##6 | 1073/4000 [31:31<1:25:58, 1.76s/it, lr: 1.0e-04 loss: 2.255e-01]
my_first_lora_v2: 27%|##6 | 1073/4000 [31:31<1:25:58, 1.76s/it, lr: 1.0e-04 loss: 2.255e-01]
my_first_lora_v2: 27%|##6 | 1074/4000 [31:33<1:25:59, 1.76s/it, lr: 1.0e-04 loss: 4.599e-01]
my_first_lora_v2: 27%|##6 | 1074/4000 [31:33<1:25:59, 1.76s/it, lr: 1.0e-04 loss: 4.599e-01]
my_first_lora_v2: 27%|##6 | 1075/4000 [31:34<1:25:55, 1.76s/it, lr: 1.0e-04 loss: 5.194e-01]
my_first_lora_v2: 27%|##6 | 1075/4000 [31:34<1:25:55, 1.76s/it, lr: 1.0e-04 loss: 5.194e-01]
my_first_lora_v2: 27%|##6 | 1076/4000 [31:35<1:25:51, 1.76s/it, lr: 1.0e-04 loss: 7.158e-01]
my_first_lora_v2: 27%|##6 | 1076/4000 [31:35<1:25:51, 1.76s/it, lr: 1.0e-04 loss: 7.158e-01]
my_first_lora_v2: 27%|##6 | 1077/4000 [31:36<1:25:46, 1.76s/it, lr: 1.0e-04 loss: 5.484e-01]
my_first_lora_v2: 27%|##6 | 1077/4000 [31:36<1:25:46, 1.76s/it, lr: 1.0e-04 loss: 5.484e-01]
my_first_lora_v2: 27%|##6 | 1078/4000 [31:37<1:25:42, 1.76s/it, lr: 1.0e-04 loss: 3.587e-01]
my_first_lora_v2: 27%|##6 | 1078/4000 [31:37<1:25:42, 1.76s/it, lr: 1.0e-04 loss: 3.587e-01]
my_first_lora_v2: 27%|##6 | 1079/4000 [31:40<1:25:43, 1.76s/it, lr: 1.0e-04 loss: 4.739e-01]
my_first_lora_v2: 27%|##6 | 1079/4000 [31:40<1:25:43, 1.76s/it, lr: 1.0e-04 loss: 4.739e-01]
my_first_lora_v2: 27%|##7 | 1080/4000 [31:41<1:25:40, 1.76s/it, lr: 1.0e-04 loss: 1.964e-01]
my_first_lora_v2: 27%|##7 | 1080/4000 [31:41<1:25:40, 1.76s/it, lr: 1.0e-04 loss: 1.964e-01]
my_first_lora_v2: 27%|##7 | 1081/4000 [31:42<1:25:35, 1.76s/it, lr: 1.0e-04 loss: 7.273e-02]
my_first_lora_v2: 27%|##7 | 1081/4000 [31:42<1:25:35, 1.76s/it, lr: 1.0e-04 loss: 7.273e-02]
my_first_lora_v2: 27%|##7 | 1082/4000 [31:42<1:25:31, 1.76s/it, lr: 1.0e-04 loss: 1.682e-01]
my_first_lora_v2: 27%|##7 | 1082/4000 [31:42<1:25:31, 1.76s/it, lr: 1.0e-04 loss: 1.682e-01]
my_first_lora_v2: 27%|##7 | 1083/4000 [31:45<1:25:32, 1.76s/it, lr: 1.0e-04 loss: 5.763e-01]
my_first_lora_v2: 27%|##7 | 1083/4000 [31:45<1:25:32, 1.76s/it, lr: 1.0e-04 loss: 5.763e-01]
my_first_lora_v2: 27%|##7 | 1084/4000 [31:46<1:25:28, 1.76s/it, lr: 1.0e-04 loss: 2.911e-01]
my_first_lora_v2: 27%|##7 | 1084/4000 [31:46<1:25:28, 1.76s/it, lr: 1.0e-04 loss: 2.911e-01]
my_first_lora_v2: 27%|##7 | 1085/4000 [31:47<1:25:24, 1.76s/it, lr: 1.0e-04 loss: 1.768e-01]
my_first_lora_v2: 27%|##7 | 1085/4000 [31:47<1:25:24, 1.76s/it, lr: 1.0e-04 loss: 1.768e-01]
my_first_lora_v2: 27%|##7 | 1086/4000 [31:48<1:25:20, 1.76s/it, lr: 1.0e-04 loss: 7.330e-01]
my_first_lora_v2: 27%|##7 | 1086/4000 [31:48<1:25:20, 1.76s/it, lr: 1.0e-04 loss: 7.330e-01]
my_first_lora_v2: 27%|##7 | 1087/4000 [31:48<1:25:15, 1.76s/it, lr: 1.0e-04 loss: 4.236e-01]
my_first_lora_v2: 27%|##7 | 1087/4000 [31:48<1:25:15, 1.76s/it, lr: 1.0e-04 loss: 4.236e-01]
my_first_lora_v2: 27%|##7 | 1088/4000 [31:49<1:25:11, 1.76s/it, lr: 1.0e-04 loss: 6.089e-01]
my_first_lora_v2: 27%|##7 | 1088/4000 [31:49<1:25:11, 1.76s/it, lr: 1.0e-04 loss: 6.089e-01]
my_first_lora_v2: 27%|##7 | 1089/4000 [31:50<1:25:07, 1.75s/it, lr: 1.0e-04 loss: 7.391e-01]
my_first_lora_v2: 27%|##7 | 1089/4000 [31:50<1:25:07, 1.75s/it, lr: 1.0e-04 loss: 7.391e-01]
my_first_lora_v2: 27%|##7 | 1090/4000 [31:51<1:25:02, 1.75s/it, lr: 1.0e-04 loss: 4.554e-01]
my_first_lora_v2: 27%|##7 | 1090/4000 [31:51<1:25:02, 1.75s/it, lr: 1.0e-04 loss: 4.554e-01]
my_first_lora_v2: 27%|##7 | 1091/4000 [31:54<1:25:04, 1.75s/it, lr: 1.0e-04 loss: 4.758e-01]
my_first_lora_v2: 27%|##7 | 1091/4000 [31:54<1:25:04, 1.75s/it, lr: 1.0e-04 loss: 4.758e-01]
my_first_lora_v2: 27%|##7 | 1092/4000 [31:55<1:24:59, 1.75s/it, lr: 1.0e-04 loss: 6.879e-01]
my_first_lora_v2: 27%|##7 | 1092/4000 [31:55<1:24:59, 1.75s/it, lr: 1.0e-04 loss: 6.879e-01]
my_first_lora_v2: 27%|##7 | 1093/4000 [31:57<1:25:00, 1.75s/it, lr: 1.0e-04 loss: 1.916e-01]
my_first_lora_v2: 27%|##7 | 1093/4000 [31:57<1:25:00, 1.75s/it, lr: 1.0e-04 loss: 1.916e-01]
my_first_lora_v2: 27%|##7 | 1094/4000 [31:58<1:24:56, 1.75s/it, lr: 1.0e-04 loss: 1.737e-01]
my_first_lora_v2: 27%|##7 | 1094/4000 [31:58<1:24:56, 1.75s/it, lr: 1.0e-04 loss: 1.737e-01]
my_first_lora_v2: 27%|##7 | 1095/4000 [32:01<1:24:58, 1.75s/it, lr: 1.0e-04 loss: 5.576e-02]
my_first_lora_v2: 27%|##7 | 1095/4000 [32:01<1:24:58, 1.75s/it, lr: 1.0e-04 loss: 5.576e-02]
my_first_lora_v2: 27%|##7 | 1096/4000 [32:02<1:24:53, 1.75s/it, lr: 1.0e-04 loss: 1.485e-01]
my_first_lora_v2: 27%|##7 | 1096/4000 [32:02<1:24:53, 1.75s/it, lr: 1.0e-04 loss: 1.485e-01]
my_first_lora_v2: 27%|##7 | 1097/4000 [32:03<1:24:49, 1.75s/it, lr: 1.0e-04 loss: 5.444e-01]
my_first_lora_v2: 27%|##7 | 1097/4000 [32:03<1:24:49, 1.75s/it, lr: 1.0e-04 loss: 5.444e-01]
my_first_lora_v2: 27%|##7 | 1098/4000 [32:05<1:24:49, 1.75s/it, lr: 1.0e-04 loss: 2.001e-01]
my_first_lora_v2: 27%|##7 | 1098/4000 [32:05<1:24:49, 1.75s/it, lr: 1.0e-04 loss: 2.001e-01]
my_first_lora_v2: 27%|##7 | 1099/4000 [32:06<1:24:45, 1.75s/it, lr: 1.0e-04 loss: 4.927e-01]
my_first_lora_v2: 27%|##7 | 1099/4000 [32:06<1:24:45, 1.75s/it, lr: 1.0e-04 loss: 4.927e-01]
my_first_lora_v2: 28%|##7 | 1100/4000 [32:09<1:24:46, 1.75s/it, lr: 1.0e-04 loss: 2.496e-01]
my_first_lora_v2: 28%|##7 | 1100/4000 [32:09<1:24:46, 1.75s/it, lr: 1.0e-04 loss: 2.496e-01]
my_first_lora_v2: 28%|##7 | 1101/4000 [32:10<1:24:42, 1.75s/it, lr: 1.0e-04 loss: 5.129e-01]
my_first_lora_v2: 28%|##7 | 1101/4000 [32:10<1:24:42, 1.75s/it, lr: 1.0e-04 loss: 5.129e-01]
my_first_lora_v2: 28%|##7 | 1102/4000 [32:11<1:24:38, 1.75s/it, lr: 1.0e-04 loss: 7.804e-01]
my_first_lora_v2: 28%|##7 | 1102/4000 [32:11<1:24:38, 1.75s/it, lr: 1.0e-04 loss: 7.804e-01]
my_first_lora_v2: 28%|##7 | 1103/4000 [32:13<1:24:39, 1.75s/it, lr: 1.0e-04 loss: 5.139e-01]
my_first_lora_v2: 28%|##7 | 1103/4000 [32:13<1:24:39, 1.75s/it, lr: 1.0e-04 loss: 5.139e-01]
my_first_lora_v2: 28%|##7 | 1104/4000 [32:14<1:24:35, 1.75s/it, lr: 1.0e-04 loss: 2.949e-01]
my_first_lora_v2: 28%|##7 | 1104/4000 [32:14<1:24:35, 1.75s/it, lr: 1.0e-04 loss: 2.949e-01]
my_first_lora_v2: 28%|##7 | 1105/4000 [32:17<1:24:36, 1.75s/it, lr: 1.0e-04 loss: 6.605e-01]
my_first_lora_v2: 28%|##7 | 1105/4000 [32:17<1:24:36, 1.75s/it, lr: 1.0e-04 loss: 6.605e-01]
my_first_lora_v2: 28%|##7 | 1106/4000 [32:20<1:24:37, 1.75s/it, lr: 1.0e-04 loss: 7.117e-01]
my_first_lora_v2: 28%|##7 | 1106/4000 [32:20<1:24:37, 1.75s/it, lr: 1.0e-04 loss: 7.117e-01]
my_first_lora_v2: 28%|##7 | 1107/4000 [32:21<1:24:33, 1.75s/it, lr: 1.0e-04 loss: 2.920e-01]
my_first_lora_v2: 28%|##7 | 1107/4000 [32:21<1:24:33, 1.75s/it, lr: 1.0e-04 loss: 2.920e-01]
my_first_lora_v2: 28%|##7 | 1108/4000 [32:22<1:24:29, 1.75s/it, lr: 1.0e-04 loss: 4.680e-01]
my_first_lora_v2: 28%|##7 | 1108/4000 [32:22<1:24:29, 1.75s/it, lr: 1.0e-04 loss: 4.680e-01]
my_first_lora_v2: 28%|##7 | 1109/4000 [32:25<1:24:30, 1.75s/it, lr: 1.0e-04 loss: 5.270e-01]
my_first_lora_v2: 28%|##7 | 1109/4000 [32:25<1:24:30, 1.75s/it, lr: 1.0e-04 loss: 5.270e-01]
my_first_lora_v2: 28%|##7 | 1110/4000 [32:27<1:24:31, 1.75s/it, lr: 1.0e-04 loss: 3.323e-01]
my_first_lora_v2: 28%|##7 | 1110/4000 [32:27<1:24:31, 1.75s/it, lr: 1.0e-04 loss: 3.323e-01]
my_first_lora_v2: 28%|##7 | 1111/4000 [32:28<1:24:27, 1.75s/it, lr: 1.0e-04 loss: 6.082e-01]
my_first_lora_v2: 28%|##7 | 1111/4000 [32:28<1:24:27, 1.75s/it, lr: 1.0e-04 loss: 6.082e-01]
my_first_lora_v2: 28%|##7 | 1112/4000 [32:31<1:24:28, 1.76s/it, lr: 1.0e-04 loss: 5.862e-01]
my_first_lora_v2: 28%|##7 | 1112/4000 [32:31<1:24:28, 1.76s/it, lr: 1.0e-04 loss: 5.862e-01]
my_first_lora_v2: 28%|##7 | 1113/4000 [32:32<1:24:24, 1.75s/it, lr: 1.0e-04 loss: 7.208e-01]
my_first_lora_v2: 28%|##7 | 1113/4000 [32:32<1:24:24, 1.75s/it, lr: 1.0e-04 loss: 7.208e-01]
my_first_lora_v2: 28%|##7 | 1114/4000 [32:33<1:24:20, 1.75s/it, lr: 1.0e-04 loss: 1.593e-01]
my_first_lora_v2: 28%|##7 | 1114/4000 [32:33<1:24:20, 1.75s/it, lr: 1.0e-04 loss: 1.593e-01]
my_first_lora_v2: 28%|##7 | 1115/4000 [32:34<1:24:15, 1.75s/it, lr: 1.0e-04 loss: 2.697e-01]
my_first_lora_v2: 28%|##7 | 1115/4000 [32:34<1:24:15, 1.75s/it, lr: 1.0e-04 loss: 2.697e-01]
my_first_lora_v2: 28%|##7 | 1116/4000 [32:36<1:24:17, 1.75s/it, lr: 1.0e-04 loss: 3.168e-01]
my_first_lora_v2: 28%|##7 | 1116/4000 [32:36<1:24:17, 1.75s/it, lr: 1.0e-04 loss: 3.168e-01]
my_first_lora_v2: 28%|##7 | 1117/4000 [32:39<1:24:18, 1.75s/it, lr: 1.0e-04 loss: 3.278e-01]
my_first_lora_v2: 28%|##7 | 1117/4000 [32:39<1:24:18, 1.75s/it, lr: 1.0e-04 loss: 3.278e-01]
my_first_lora_v2: 28%|##7 | 1118/4000 [32:42<1:24:19, 1.76s/it, lr: 1.0e-04 loss: 4.730e-01]
my_first_lora_v2: 28%|##7 | 1118/4000 [32:42<1:24:19, 1.76s/it, lr: 1.0e-04 loss: 4.730e-01]
my_first_lora_v2: 28%|##7 | 1119/4000 [32:43<1:24:15, 1.75s/it, lr: 1.0e-04 loss: 6.764e-02]
my_first_lora_v2: 28%|##7 | 1119/4000 [32:43<1:24:15, 1.75s/it, lr: 1.0e-04 loss: 6.764e-02]
my_first_lora_v2: 28%|##8 | 1120/4000 [32:46<1:24:16, 1.76s/it, lr: 1.0e-04 loss: 5.365e-01]
my_first_lora_v2: 28%|##8 | 1120/4000 [32:46<1:24:16, 1.76s/it, lr: 1.0e-04 loss: 5.365e-01]
my_first_lora_v2: 28%|##8 | 1121/4000 [32:49<1:24:17, 1.76s/it, lr: 1.0e-04 loss: 4.673e-01]
my_first_lora_v2: 28%|##8 | 1121/4000 [32:49<1:24:17, 1.76s/it, lr: 1.0e-04 loss: 4.673e-01]
my_first_lora_v2: 28%|##8 | 1122/4000 [32:50<1:24:13, 1.76s/it, lr: 1.0e-04 loss: 3.474e-01]
my_first_lora_v2: 28%|##8 | 1122/4000 [32:50<1:24:13, 1.76s/it, lr: 1.0e-04 loss: 3.474e-01]
my_first_lora_v2: 28%|##8 | 1123/4000 [32:52<1:24:14, 1.76s/it, lr: 1.0e-04 loss: 6.855e-01]
my_first_lora_v2: 28%|##8 | 1123/4000 [32:52<1:24:14, 1.76s/it, lr: 1.0e-04 loss: 6.855e-01]
my_first_lora_v2: 28%|##8 | 1124/4000 [32:53<1:24:10, 1.76s/it, lr: 1.0e-04 loss: 6.670e-01]
my_first_lora_v2: 28%|##8 | 1124/4000 [32:53<1:24:10, 1.76s/it, lr: 1.0e-04 loss: 6.670e-01]
my_first_lora_v2: 28%|##8 | 1125/4000 [32:56<1:24:10, 1.76s/it, lr: 1.0e-04 loss: 5.149e-01]
my_first_lora_v2: 28%|##8 | 1125/4000 [32:56<1:24:10, 1.76s/it, lr: 1.0e-04 loss: 5.149e-01]
my_first_lora_v2: 28%|##8 | 1126/4000 [32:57<1:24:06, 1.76s/it, lr: 1.0e-04 loss: 4.317e-01]
my_first_lora_v2: 28%|##8 | 1126/4000 [32:57<1:24:06, 1.76s/it, lr: 1.0e-04 loss: 4.317e-01]
my_first_lora_v2: 28%|##8 | 1127/4000 [32:58<1:24:02, 1.76s/it, lr: 1.0e-04 loss: 5.104e-01]
my_first_lora_v2: 28%|##8 | 1127/4000 [32:58<1:24:02, 1.76s/it, lr: 1.0e-04 loss: 5.104e-01]
my_first_lora_v2: 28%|##8 | 1128/4000 [33:00<1:24:03, 1.76s/it, lr: 1.0e-04 loss: 2.099e-01]
my_first_lora_v2: 28%|##8 | 1128/4000 [33:00<1:24:03, 1.76s/it, lr: 1.0e-04 loss: 2.099e-01]
my_first_lora_v2: 28%|##8 | 1129/4000 [33:01<1:23:59, 1.76s/it, lr: 1.0e-04 loss: 6.318e-01]
my_first_lora_v2: 28%|##8 | 1129/4000 [33:01<1:23:59, 1.76s/it, lr: 1.0e-04 loss: 6.318e-01]
my_first_lora_v2: 28%|##8 | 1130/4000 [33:04<1:24:00, 1.76s/it, lr: 1.0e-04 loss: 2.921e-01]
my_first_lora_v2: 28%|##8 | 1130/4000 [33:04<1:24:00, 1.76s/it, lr: 1.0e-04 loss: 2.921e-01]
my_first_lora_v2: 28%|##8 | 1131/4000 [33:06<1:24:00, 1.76s/it, lr: 1.0e-04 loss: 5.488e-01]
my_first_lora_v2: 28%|##8 | 1131/4000 [33:06<1:24:00, 1.76s/it, lr: 1.0e-04 loss: 5.488e-01]
my_first_lora_v2: 28%|##8 | 1132/4000 [33:09<1:24:01, 1.76s/it, lr: 1.0e-04 loss: 3.286e-02]
my_first_lora_v2: 28%|##8 | 1132/4000 [33:09<1:24:01, 1.76s/it, lr: 1.0e-04 loss: 3.286e-02]
my_first_lora_v2: 28%|##8 | 1133/4000 [33:12<1:24:01, 1.76s/it, lr: 1.0e-04 loss: 5.035e-01]
my_first_lora_v2: 28%|##8 | 1133/4000 [33:12<1:24:01, 1.76s/it, lr: 1.0e-04 loss: 5.035e-01]
my_first_lora_v2: 28%|##8 | 1134/4000 [33:14<1:24:01, 1.76s/it, lr: 1.0e-04 loss: 7.366e-02]
my_first_lora_v2: 28%|##8 | 1134/4000 [33:14<1:24:01, 1.76s/it, lr: 1.0e-04 loss: 7.366e-02]
my_first_lora_v2: 28%|##8 | 1135/4000 [33:17<1:24:02, 1.76s/it, lr: 1.0e-04 loss: 4.990e-01]
my_first_lora_v2: 28%|##8 | 1135/4000 [33:17<1:24:02, 1.76s/it, lr: 1.0e-04 loss: 4.990e-01]
my_first_lora_v2: 28%|##8 | 1136/4000 [33:18<1:23:58, 1.76s/it, lr: 1.0e-04 loss: 1.364e-01]
my_first_lora_v2: 28%|##8 | 1136/4000 [33:18<1:23:58, 1.76s/it, lr: 1.0e-04 loss: 1.364e-01]
my_first_lora_v2: 28%|##8 | 1137/4000 [33:19<1:23:55, 1.76s/it, lr: 1.0e-04 loss: 3.608e-01]
my_first_lora_v2: 28%|##8 | 1137/4000 [33:19<1:23:55, 1.76s/it, lr: 1.0e-04 loss: 3.608e-01]
my_first_lora_v2: 28%|##8 | 1138/4000 [33:22<1:23:56, 1.76s/it, lr: 1.0e-04 loss: 5.174e-01]
my_first_lora_v2: 28%|##8 | 1138/4000 [33:22<1:23:56, 1.76s/it, lr: 1.0e-04 loss: 5.174e-01]
my_first_lora_v2: 28%|##8 | 1139/4000 [33:23<1:23:53, 1.76s/it, lr: 1.0e-04 loss: 4.724e-01]
my_first_lora_v2: 28%|##8 | 1139/4000 [33:23<1:23:53, 1.76s/it, lr: 1.0e-04 loss: 4.724e-01]
my_first_lora_v2: 28%|##8 | 1140/4000 [33:24<1:23:49, 1.76s/it, lr: 1.0e-04 loss: 7.488e-01]
my_first_lora_v2: 28%|##8 | 1140/4000 [33:24<1:23:49, 1.76s/it, lr: 1.0e-04 loss: 7.488e-01]
my_first_lora_v2: 29%|##8 | 1141/4000 [33:25<1:23:44, 1.76s/it, lr: 1.0e-04 loss: 6.235e-01]
my_first_lora_v2: 29%|##8 | 1141/4000 [33:25<1:23:44, 1.76s/it, lr: 1.0e-04 loss: 6.235e-01]
my_first_lora_v2: 29%|##8 | 1142/4000 [33:28<1:23:46, 1.76s/it, lr: 1.0e-04 loss: 4.457e-01]
my_first_lora_v2: 29%|##8 | 1142/4000 [33:28<1:23:46, 1.76s/it, lr: 1.0e-04 loss: 4.457e-01]
my_first_lora_v2: 29%|##8 | 1143/4000 [33:31<1:23:47, 1.76s/it, lr: 1.0e-04 loss: 4.712e-01]
my_first_lora_v2: 29%|##8 | 1143/4000 [33:31<1:23:47, 1.76s/it, lr: 1.0e-04 loss: 4.712e-01]
my_first_lora_v2: 29%|##8 | 1144/4000 [33:31<1:23:42, 1.76s/it, lr: 1.0e-04 loss: 3.215e-01]
my_first_lora_v2: 29%|##8 | 1144/4000 [33:31<1:23:42, 1.76s/it, lr: 1.0e-04 loss: 3.215e-01]
my_first_lora_v2: 29%|##8 | 1145/4000 [33:32<1:23:38, 1.76s/it, lr: 1.0e-04 loss: 6.317e-02]
my_first_lora_v2: 29%|##8 | 1145/4000 [33:32<1:23:38, 1.76s/it, lr: 1.0e-04 loss: 6.317e-02]
my_first_lora_v2: 29%|##8 | 1146/4000 [33:35<1:23:38, 1.76s/it, lr: 1.0e-04 loss: 3.389e-01]
my_first_lora_v2: 29%|##8 | 1146/4000 [33:35<1:23:38, 1.76s/it, lr: 1.0e-04 loss: 3.389e-01]
my_first_lora_v2: 29%|##8 | 1147/4000 [33:36<1:23:34, 1.76s/it, lr: 1.0e-04 loss: 4.055e-01]
my_first_lora_v2: 29%|##8 | 1147/4000 [33:36<1:23:34, 1.76s/it, lr: 1.0e-04 loss: 4.055e-01]
my_first_lora_v2: 29%|##8 | 1148/4000 [33:38<1:23:34, 1.76s/it, lr: 1.0e-04 loss: 3.896e-01]
my_first_lora_v2: 29%|##8 | 1148/4000 [33:38<1:23:34, 1.76s/it, lr: 1.0e-04 loss: 3.896e-01]
my_first_lora_v2: 29%|##8 | 1149/4000 [33:39<1:23:31, 1.76s/it, lr: 1.0e-04 loss: 7.541e-01]
my_first_lora_v2: 29%|##8 | 1149/4000 [33:39<1:23:31, 1.76s/it, lr: 1.0e-04 loss: 7.541e-01]
my_first_lora_v2: 29%|##8 | 1150/4000 [33:40<1:23:27, 1.76s/it, lr: 1.0e-04 loss: 7.763e-01]
my_first_lora_v2: 29%|##8 | 1150/4000 [33:40<1:23:27, 1.76s/it, lr: 1.0e-04 loss: 7.763e-01]
my_first_lora_v2: 29%|##8 | 1151/4000 [33:41<1:23:23, 1.76s/it, lr: 1.0e-04 loss: 2.785e-01]
my_first_lora_v2: 29%|##8 | 1151/4000 [33:41<1:23:23, 1.76s/it, lr: 1.0e-04 loss: 2.785e-01]
my_first_lora_v2: 29%|##8 | 1152/4000 [33:44<1:23:24, 1.76s/it, lr: 1.0e-04 loss: 8.377e-01]
my_first_lora_v2: 29%|##8 | 1152/4000 [33:44<1:23:24, 1.76s/it, lr: 1.0e-04 loss: 8.377e-01]
my_first_lora_v2: 29%|##8 | 1153/4000 [33:44<1:23:20, 1.76s/it, lr: 1.0e-04 loss: 3.157e-01]
my_first_lora_v2: 29%|##8 | 1153/4000 [33:44<1:23:20, 1.76s/it, lr: 1.0e-04 loss: 3.157e-01]
my_first_lora_v2: 29%|##8 | 1154/4000 [33:45<1:23:16, 1.76s/it, lr: 1.0e-04 loss: 5.942e-01]
my_first_lora_v2: 29%|##8 | 1154/4000 [33:45<1:23:16, 1.76s/it, lr: 1.0e-04 loss: 5.942e-01]
my_first_lora_v2: 29%|##8 | 1155/4000 [33:48<1:23:17, 1.76s/it, lr: 1.0e-04 loss: 5.261e-01]
my_first_lora_v2: 29%|##8 | 1155/4000 [33:48<1:23:17, 1.76s/it, lr: 1.0e-04 loss: 5.261e-01]
my_first_lora_v2: 29%|##8 | 1156/4000 [33:49<1:23:13, 1.76s/it, lr: 1.0e-04 loss: 5.062e-01]
my_first_lora_v2: 29%|##8 | 1156/4000 [33:49<1:23:13, 1.76s/it, lr: 1.0e-04 loss: 5.062e-01]
my_first_lora_v2: 29%|##8 | 1157/4000 [33:50<1:23:09, 1.75s/it, lr: 1.0e-04 loss: 1.481e-01]
my_first_lora_v2: 29%|##8 | 1157/4000 [33:50<1:23:09, 1.75s/it, lr: 1.0e-04 loss: 1.481e-01]
my_first_lora_v2: 29%|##8 | 1158/4000 [33:51<1:23:05, 1.75s/it, lr: 1.0e-04 loss: 7.262e-01]
my_first_lora_v2: 29%|##8 | 1158/4000 [33:51<1:23:05, 1.75s/it, lr: 1.0e-04 loss: 7.262e-01]
my_first_lora_v2: 29%|##8 | 1159/4000 [33:53<1:23:05, 1.75s/it, lr: 1.0e-04 loss: 2.552e-01]
my_first_lora_v2: 29%|##8 | 1159/4000 [33:53<1:23:05, 1.75s/it, lr: 1.0e-04 loss: 2.552e-01]
my_first_lora_v2: 29%|##9 | 1160/4000 [33:56<1:23:06, 1.76s/it, lr: 1.0e-04 loss: 1.447e-01]
my_first_lora_v2: 29%|##9 | 1160/4000 [33:56<1:23:06, 1.76s/it, lr: 1.0e-04 loss: 1.447e-01]
my_first_lora_v2: 29%|##9 | 1161/4000 [33:59<1:23:07, 1.76s/it, lr: 1.0e-04 loss: 6.511e-01]
my_first_lora_v2: 29%|##9 | 1161/4000 [33:59<1:23:07, 1.76s/it, lr: 1.0e-04 loss: 6.511e-01]
my_first_lora_v2: 29%|##9 | 1162/4000 [34:00<1:23:03, 1.76s/it, lr: 1.0e-04 loss: 4.709e-01]
my_first_lora_v2: 29%|##9 | 1162/4000 [34:00<1:23:03, 1.76s/it, lr: 1.0e-04 loss: 4.709e-01]
my_first_lora_v2: 29%|##9 | 1163/4000 [34:03<1:23:04, 1.76s/it, lr: 1.0e-04 loss: 1.253e-01]
my_first_lora_v2: 29%|##9 | 1163/4000 [34:03<1:23:04, 1.76s/it, lr: 1.0e-04 loss: 1.253e-01]
my_first_lora_v2: 29%|##9 | 1164/4000 [34:04<1:23:00, 1.76s/it, lr: 1.0e-04 loss: 2.483e-01]
my_first_lora_v2: 29%|##9 | 1164/4000 [34:04<1:23:00, 1.76s/it, lr: 1.0e-04 loss: 2.483e-01]
my_first_lora_v2: 29%|##9 | 1165/4000 [34:05<1:22:56, 1.76s/it, lr: 1.0e-04 loss: 5.445e-01]
my_first_lora_v2: 29%|##9 | 1165/4000 [34:05<1:22:56, 1.76s/it, lr: 1.0e-04 loss: 5.445e-01]
my_first_lora_v2: 29%|##9 | 1166/4000 [34:07<1:22:56, 1.76s/it, lr: 1.0e-04 loss: 5.563e-01]
my_first_lora_v2: 29%|##9 | 1166/4000 [34:07<1:22:56, 1.76s/it, lr: 1.0e-04 loss: 5.563e-01]
my_first_lora_v2: 29%|##9 | 1167/4000 [34:08<1:22:52, 1.76s/it, lr: 1.0e-04 loss: 5.979e-01]
my_first_lora_v2: 29%|##9 | 1167/4000 [34:08<1:22:52, 1.76s/it, lr: 1.0e-04 loss: 5.979e-01]
my_first_lora_v2: 29%|##9 | 1168/4000 [34:10<1:22:52, 1.76s/it, lr: 1.0e-04 loss: 6.262e-01]
my_first_lora_v2: 29%|##9 | 1168/4000 [34:10<1:22:52, 1.76s/it, lr: 1.0e-04 loss: 6.262e-01]
my_first_lora_v2: 29%|##9 | 1169/4000 [34:11<1:22:48, 1.76s/it, lr: 1.0e-04 loss: 2.649e-01]
my_first_lora_v2: 29%|##9 | 1169/4000 [34:11<1:22:48, 1.76s/it, lr: 1.0e-04 loss: 2.649e-01]
my_first_lora_v2: 29%|##9 | 1170/4000 [34:14<1:22:49, 1.76s/it, lr: 1.0e-04 loss: 6.480e-01]
my_first_lora_v2: 29%|##9 | 1170/4000 [34:14<1:22:49, 1.76s/it, lr: 1.0e-04 loss: 6.480e-01]
my_first_lora_v2: 29%|##9 | 1171/4000 [34:15<1:22:45, 1.76s/it, lr: 1.0e-04 loss: 5.902e-01]
my_first_lora_v2: 29%|##9 | 1171/4000 [34:15<1:22:45, 1.76s/it, lr: 1.0e-04 loss: 5.902e-01]
my_first_lora_v2: 29%|##9 | 1172/4000 [34:18<1:22:46, 1.76s/it, lr: 1.0e-04 loss: 5.180e-01]
my_first_lora_v2: 29%|##9 | 1172/4000 [34:18<1:22:46, 1.76s/it, lr: 1.0e-04 loss: 5.180e-01]
my_first_lora_v2: 29%|##9 | 1173/4000 [34:19<1:22:42, 1.76s/it, lr: 1.0e-04 loss: 3.953e-01]
my_first_lora_v2: 29%|##9 | 1173/4000 [34:19<1:22:42, 1.76s/it, lr: 1.0e-04 loss: 3.953e-01]
my_first_lora_v2: 29%|##9 | 1174/4000 [34:19<1:22:38, 1.75s/it, lr: 1.0e-04 loss: 6.073e-01]
my_first_lora_v2: 29%|##9 | 1174/4000 [34:19<1:22:38, 1.75s/it, lr: 1.0e-04 loss: 6.073e-01]
my_first_lora_v2: 29%|##9 | 1175/4000 [34:22<1:22:39, 1.76s/it, lr: 1.0e-04 loss: 1.588e-01]
my_first_lora_v2: 29%|##9 | 1175/4000 [34:22<1:22:39, 1.76s/it, lr: 1.0e-04 loss: 1.588e-01]
my_first_lora_v2: 29%|##9 | 1176/4000 [34:25<1:22:40, 1.76s/it, lr: 1.0e-04 loss: 3.515e-01]
my_first_lora_v2: 29%|##9 | 1176/4000 [34:25<1:22:40, 1.76s/it, lr: 1.0e-04 loss: 3.515e-01]
my_first_lora_v2: 29%|##9 | 1177/4000 [34:26<1:22:36, 1.76s/it, lr: 1.0e-04 loss: 6.725e-01]
my_first_lora_v2: 29%|##9 | 1177/4000 [34:26<1:22:36, 1.76s/it, lr: 1.0e-04 loss: 6.725e-01]
my_first_lora_v2: 29%|##9 | 1178/4000 [34:29<1:22:37, 1.76s/it, lr: 1.0e-04 loss: 2.902e-01]
my_first_lora_v2: 29%|##9 | 1178/4000 [34:29<1:22:37, 1.76s/it, lr: 1.0e-04 loss: 2.902e-01]
my_first_lora_v2: 29%|##9 | 1179/4000 [34:30<1:22:33, 1.76s/it, lr: 1.0e-04 loss: 5.084e-01]
my_first_lora_v2: 29%|##9 | 1179/4000 [34:30<1:22:33, 1.76s/it, lr: 1.0e-04 loss: 5.084e-01]
my_first_lora_v2: 30%|##9 | 1180/4000 [34:33<1:22:34, 1.76s/it, lr: 1.0e-04 loss: 7.520e-01]
my_first_lora_v2: 30%|##9 | 1180/4000 [34:33<1:22:34, 1.76s/it, lr: 1.0e-04 loss: 7.520e-01]
my_first_lora_v2: 30%|##9 | 1181/4000 [34:33<1:22:30, 1.76s/it, lr: 1.0e-04 loss: 6.153e-01]
my_first_lora_v2: 30%|##9 | 1181/4000 [34:33<1:22:30, 1.76s/it, lr: 1.0e-04 loss: 6.153e-01]
my_first_lora_v2: 30%|##9 | 1182/4000 [34:36<1:22:30, 1.76s/it, lr: 1.0e-04 loss: 6.384e-01]
my_first_lora_v2: 30%|##9 | 1182/4000 [34:36<1:22:30, 1.76s/it, lr: 1.0e-04 loss: 6.384e-01]
my_first_lora_v2: 30%|##9 | 1183/4000 [34:37<1:22:26, 1.76s/it, lr: 1.0e-04 loss: 4.543e-01]
my_first_lora_v2: 30%|##9 | 1183/4000 [34:37<1:22:26, 1.76s/it, lr: 1.0e-04 loss: 4.543e-01]
my_first_lora_v2: 30%|##9 | 1184/4000 [34:40<1:22:27, 1.76s/it, lr: 1.0e-04 loss: 2.582e-01]
my_first_lora_v2: 30%|##9 | 1184/4000 [34:40<1:22:27, 1.76s/it, lr: 1.0e-04 loss: 2.582e-01]
my_first_lora_v2: 30%|##9 | 1185/4000 [34:43<1:22:28, 1.76s/it, lr: 1.0e-04 loss: 3.873e-01]
my_first_lora_v2: 30%|##9 | 1185/4000 [34:43<1:22:28, 1.76s/it, lr: 1.0e-04 loss: 3.873e-01]
my_first_lora_v2: 30%|##9 | 1186/4000 [34:43<1:22:24, 1.76s/it, lr: 1.0e-04 loss: 4.735e-01]
my_first_lora_v2: 30%|##9 | 1186/4000 [34:43<1:22:24, 1.76s/it, lr: 1.0e-04 loss: 4.735e-01]
my_first_lora_v2: 30%|##9 | 1187/4000 [34:44<1:22:20, 1.76s/it, lr: 1.0e-04 loss: 7.294e-01]
my_first_lora_v2: 30%|##9 | 1187/4000 [34:44<1:22:20, 1.76s/it, lr: 1.0e-04 loss: 7.294e-01]
my_first_lora_v2: 30%|##9 | 1188/4000 [34:45<1:22:16, 1.76s/it, lr: 1.0e-04 loss: 1.836e-01]
my_first_lora_v2: 30%|##9 | 1188/4000 [34:45<1:22:16, 1.76s/it, lr: 1.0e-04 loss: 1.836e-01]
my_first_lora_v2: 30%|##9 | 1189/4000 [34:48<1:22:17, 1.76s/it, lr: 1.0e-04 loss: 6.211e-01]
my_first_lora_v2: 30%|##9 | 1189/4000 [34:48<1:22:17, 1.76s/it, lr: 1.0e-04 loss: 6.211e-01]
my_first_lora_v2: 30%|##9 | 1190/4000 [34:49<1:22:15, 1.76s/it, lr: 1.0e-04 loss: 6.628e-01]
my_first_lora_v2: 30%|##9 | 1190/4000 [34:49<1:22:15, 1.76s/it, lr: 1.0e-04 loss: 6.628e-01]
my_first_lora_v2: 30%|##9 | 1191/4000 [34:52<1:22:14, 1.76s/it, lr: 1.0e-04 loss: 4.024e-01]
my_first_lora_v2: 30%|##9 | 1191/4000 [34:52<1:22:14, 1.76s/it, lr: 1.0e-04 loss: 4.024e-01]
my_first_lora_v2: 30%|##9 | 1192/4000 [34:55<1:22:15, 1.76s/it, lr: 1.0e-04 loss: 6.034e-01]
my_first_lora_v2: 30%|##9 | 1192/4000 [34:55<1:22:15, 1.76s/it, lr: 1.0e-04 loss: 6.034e-01]
my_first_lora_v2: 30%|##9 | 1193/4000 [34:57<1:22:15, 1.76s/it, lr: 1.0e-04 loss: 6.854e-01]
my_first_lora_v2: 30%|##9 | 1193/4000 [34:57<1:22:15, 1.76s/it, lr: 1.0e-04 loss: 6.854e-01]
my_first_lora_v2: 30%|##9 | 1194/4000 [34:58<1:22:11, 1.76s/it, lr: 1.0e-04 loss: 1.577e-01]
my_first_lora_v2: 30%|##9 | 1194/4000 [34:58<1:22:11, 1.76s/it, lr: 1.0e-04 loss: 1.577e-01]
my_first_lora_v2: 30%|##9 | 1195/4000 [35:01<1:22:11, 1.76s/it, lr: 1.0e-04 loss: 3.170e-01]
my_first_lora_v2: 30%|##9 | 1195/4000 [35:01<1:22:11, 1.76s/it, lr: 1.0e-04 loss: 3.170e-01]
my_first_lora_v2: 30%|##9 | 1196/4000 [35:04<1:22:12, 1.76s/it, lr: 1.0e-04 loss: 6.197e-01]
my_first_lora_v2: 30%|##9 | 1196/4000 [35:04<1:22:12, 1.76s/it, lr: 1.0e-04 loss: 6.197e-01]
my_first_lora_v2: 30%|##9 | 1197/4000 [35:04<1:22:08, 1.76s/it, lr: 1.0e-04 loss: 5.165e-01]
my_first_lora_v2: 30%|##9 | 1197/4000 [35:04<1:22:08, 1.76s/it, lr: 1.0e-04 loss: 5.165e-01]
my_first_lora_v2: 30%|##9 | 1198/4000 [35:07<1:22:09, 1.76s/it, lr: 1.0e-04 loss: 3.578e-01]
my_first_lora_v2: 30%|##9 | 1198/4000 [35:07<1:22:09, 1.76s/it, lr: 1.0e-04 loss: 3.578e-01]
my_first_lora_v2: 30%|##9 | 1199/4000 [35:10<1:22:10, 1.76s/it, lr: 1.0e-04 loss: 1.157e-01]
my_first_lora_v2: 30%|##9 | 1199/4000 [35:10<1:22:10, 1.76s/it, lr: 1.0e-04 loss: 1.157e-01]
my_first_lora_v2: 30%|### | 1200/4000 [35:11<1:22:06, 1.76s/it, lr: 1.0e-04 loss: 1.853e-01]
my_first_lora_v2: 30%|### | 1200/4000 [35:11<1:22:06, 1.76s/it, lr: 1.0e-04 loss: 1.853e-01]
my_first_lora_v2: 30%|### | 1201/4000 [35:14<1:22:07, 1.76s/it, lr: 1.0e-04 loss: 8.828e-02]
my_first_lora_v2: 30%|### | 1201/4000 [35:14<1:22:07, 1.76s/it, lr: 1.0e-04 loss: 8.828e-02]
my_first_lora_v2: 30%|### | 1202/4000 [35:17<1:22:08, 1.76s/it, lr: 1.0e-04 loss: 4.785e-01]
my_first_lora_v2: 30%|### | 1202/4000 [35:17<1:22:08, 1.76s/it, lr: 1.0e-04 loss: 4.785e-01]
my_first_lora_v2: 30%|### | 1203/4000 [35:20<1:22:09, 1.76s/it, lr: 1.0e-04 loss: 4.999e-01]
my_first_lora_v2: 30%|### | 1203/4000 [35:20<1:22:09, 1.76s/it, lr: 1.0e-04 loss: 4.999e-01]
my_first_lora_v2: 30%|### | 1204/4000 [35:23<1:22:10, 1.76s/it, lr: 1.0e-04 loss: 1.905e-01]
my_first_lora_v2: 30%|### | 1204/4000 [35:23<1:22:10, 1.76s/it, lr: 1.0e-04 loss: 1.905e-01]
my_first_lora_v2: 30%|### | 1205/4000 [35:24<1:22:06, 1.76s/it, lr: 1.0e-04 loss: 5.272e-01]
my_first_lora_v2: 30%|### | 1205/4000 [35:24<1:22:06, 1.76s/it, lr: 1.0e-04 loss: 5.272e-01]
my_first_lora_v2: 30%|### | 1206/4000 [35:24<1:22:02, 1.76s/it, lr: 1.0e-04 loss: 3.202e-01]
my_first_lora_v2: 30%|### | 1206/4000 [35:24<1:22:02, 1.76s/it, lr: 1.0e-04 loss: 3.202e-01]
my_first_lora_v2: 30%|### | 1207/4000 [35:25<1:21:58, 1.76s/it, lr: 1.0e-04 loss: 4.373e-01]
my_first_lora_v2: 30%|### | 1207/4000 [35:25<1:21:58, 1.76s/it, lr: 1.0e-04 loss: 4.373e-01]
my_first_lora_v2: 30%|### | 1208/4000 [35:26<1:21:54, 1.76s/it, lr: 1.0e-04 loss: 7.053e-01]
my_first_lora_v2: 30%|### | 1208/4000 [35:26<1:21:54, 1.76s/it, lr: 1.0e-04 loss: 7.053e-01]
my_first_lora_v2: 30%|### | 1209/4000 [35:29<1:21:55, 1.76s/it, lr: 1.0e-04 loss: 3.189e-01]
my_first_lora_v2: 30%|### | 1209/4000 [35:29<1:21:55, 1.76s/it, lr: 1.0e-04 loss: 3.189e-01]
my_first_lora_v2: 30%|### | 1210/4000 [35:30<1:21:51, 1.76s/it, lr: 1.0e-04 loss: 3.025e-01]
my_first_lora_v2: 30%|### | 1210/4000 [35:30<1:21:51, 1.76s/it, lr: 1.0e-04 loss: 3.025e-01]
my_first_lora_v2: 30%|### | 1211/4000 [35:31<1:21:47, 1.76s/it, lr: 1.0e-04 loss: 2.749e-01]
my_first_lora_v2: 30%|### | 1211/4000 [35:31<1:21:47, 1.76s/it, lr: 1.0e-04 loss: 2.749e-01]
my_first_lora_v2: 30%|### | 1212/4000 [35:33<1:21:48, 1.76s/it, lr: 1.0e-04 loss: 4.278e-01]
my_first_lora_v2: 30%|### | 1212/4000 [35:33<1:21:48, 1.76s/it, lr: 1.0e-04 loss: 4.278e-01]
my_first_lora_v2: 30%|### | 1213/4000 [35:34<1:21:44, 1.76s/it, lr: 1.0e-04 loss: 4.747e-01]
my_first_lora_v2: 30%|### | 1213/4000 [35:34<1:21:44, 1.76s/it, lr: 1.0e-04 loss: 4.747e-01]
my_first_lora_v2: 30%|### | 1214/4000 [35:35<1:21:40, 1.76s/it, lr: 1.0e-04 loss: 1.195e-01]
my_first_lora_v2: 30%|### | 1214/4000 [35:35<1:21:40, 1.76s/it, lr: 1.0e-04 loss: 1.195e-01]
my_first_lora_v2: 30%|### | 1215/4000 [35:36<1:21:36, 1.76s/it, lr: 1.0e-04 loss: 5.318e-01]
my_first_lora_v2: 30%|### | 1215/4000 [35:36<1:21:36, 1.76s/it, lr: 1.0e-04 loss: 5.318e-01]
my_first_lora_v2: 30%|### | 1216/4000 [35:39<1:21:37, 1.76s/it, lr: 1.0e-04 loss: 3.154e-01]
my_first_lora_v2: 30%|### | 1216/4000 [35:39<1:21:37, 1.76s/it, lr: 1.0e-04 loss: 3.154e-01]
my_first_lora_v2: 30%|### | 1217/4000 [35:40<1:21:34, 1.76s/it, lr: 1.0e-04 loss: 7.067e-01]
my_first_lora_v2: 30%|### | 1217/4000 [35:40<1:21:34, 1.76s/it, lr: 1.0e-04 loss: 7.067e-01]
my_first_lora_v2: 30%|### | 1218/4000 [35:41<1:21:30, 1.76s/it, lr: 1.0e-04 loss: 4.071e-01]
my_first_lora_v2: 30%|### | 1218/4000 [35:41<1:21:30, 1.76s/it, lr: 1.0e-04 loss: 4.071e-01]
my_first_lora_v2: 30%|### | 1219/4000 [35:41<1:21:26, 1.76s/it, lr: 1.0e-04 loss: 1.768e-01]
my_first_lora_v2: 30%|### | 1219/4000 [35:41<1:21:26, 1.76s/it, lr: 1.0e-04 loss: 1.768e-01]
my_first_lora_v2: 30%|### | 1220/4000 [35:44<1:21:26, 1.76s/it, lr: 1.0e-04 loss: 2.031e-01]
my_first_lora_v2: 30%|### | 1220/4000 [35:44<1:21:26, 1.76s/it, lr: 1.0e-04 loss: 2.031e-01]
my_first_lora_v2: 31%|### | 1221/4000 [35:45<1:21:22, 1.76s/it, lr: 1.0e-04 loss: 1.952e-01]
my_first_lora_v2: 31%|### | 1221/4000 [35:45<1:21:22, 1.76s/it, lr: 1.0e-04 loss: 1.952e-01]
my_first_lora_v2: 31%|### | 1222/4000 [35:47<1:21:23, 1.76s/it, lr: 1.0e-04 loss: 1.487e-01]
my_first_lora_v2: 31%|### | 1222/4000 [35:47<1:21:23, 1.76s/it, lr: 1.0e-04 loss: 1.487e-01]
my_first_lora_v2: 31%|### | 1223/4000 [35:50<1:21:23, 1.76s/it, lr: 1.0e-04 loss: 2.554e-01]
my_first_lora_v2: 31%|### | 1223/4000 [35:50<1:21:23, 1.76s/it, lr: 1.0e-04 loss: 2.554e-01]
my_first_lora_v2: 31%|### | 1224/4000 [35:51<1:21:19, 1.76s/it, lr: 1.0e-04 loss: 4.842e-01]
my_first_lora_v2: 31%|### | 1224/4000 [35:51<1:21:19, 1.76s/it, lr: 1.0e-04 loss: 4.842e-01]
my_first_lora_v2: 31%|### | 1225/4000 [35:54<1:21:19, 1.76s/it, lr: 1.0e-04 loss: 6.218e-01]
my_first_lora_v2: 31%|### | 1225/4000 [35:54<1:21:19, 1.76s/it, lr: 1.0e-04 loss: 6.218e-01]
my_first_lora_v2: 31%|### | 1226/4000 [35:54<1:21:15, 1.76s/it, lr: 1.0e-04 loss: 6.007e-01]
my_first_lora_v2: 31%|### | 1226/4000 [35:54<1:21:15, 1.76s/it, lr: 1.0e-04 loss: 6.007e-01]
my_first_lora_v2: 31%|### | 1227/4000 [35:55<1:21:11, 1.76s/it, lr: 1.0e-04 loss: 6.228e-01]
my_first_lora_v2: 31%|### | 1227/4000 [35:55<1:21:11, 1.76s/it, lr: 1.0e-04 loss: 6.228e-01]
my_first_lora_v2: 31%|### | 1228/4000 [35:56<1:21:07, 1.76s/it, lr: 1.0e-04 loss: 7.120e-01]
my_first_lora_v2: 31%|### | 1228/4000 [35:56<1:21:07, 1.76s/it, lr: 1.0e-04 loss: 7.120e-01]
my_first_lora_v2: 31%|### | 1229/4000 [35:59<1:21:08, 1.76s/it, lr: 1.0e-04 loss: 2.857e-01]
my_first_lora_v2: 31%|### | 1229/4000 [35:59<1:21:08, 1.76s/it, lr: 1.0e-04 loss: 2.857e-01]
my_first_lora_v2: 31%|### | 1230/4000 [36:00<1:21:06, 1.76s/it, lr: 1.0e-04 loss: 7.843e-01]
my_first_lora_v2: 31%|### | 1230/4000 [36:00<1:21:06, 1.76s/it, lr: 1.0e-04 loss: 7.843e-01]
my_first_lora_v2: 31%|### | 1231/4000 [36:01<1:21:02, 1.76s/it, lr: 1.0e-04 loss: 6.281e-01]
my_first_lora_v2: 31%|### | 1231/4000 [36:01<1:21:02, 1.76s/it, lr: 1.0e-04 loss: 6.281e-01]
my_first_lora_v2: 31%|### | 1232/4000 [36:02<1:20:58, 1.76s/it, lr: 1.0e-04 loss: 2.559e-01]
my_first_lora_v2: 31%|### | 1232/4000 [36:02<1:20:58, 1.76s/it, lr: 1.0e-04 loss: 2.559e-01]
my_first_lora_v2: 31%|### | 1233/4000 [36:05<1:20:59, 1.76s/it, lr: 1.0e-04 loss: 4.198e-01]
my_first_lora_v2: 31%|### | 1233/4000 [36:05<1:20:59, 1.76s/it, lr: 1.0e-04 loss: 4.198e-01]
my_first_lora_v2: 31%|### | 1234/4000 [36:07<1:20:59, 1.76s/it, lr: 1.0e-04 loss: 2.176e-01]
my_first_lora_v2: 31%|### | 1234/4000 [36:07<1:20:59, 1.76s/it, lr: 1.0e-04 loss: 2.176e-01]
my_first_lora_v2: 31%|### | 1235/4000 [36:08<1:20:55, 1.76s/it, lr: 1.0e-04 loss: 5.086e-01]
my_first_lora_v2: 31%|### | 1235/4000 [36:08<1:20:55, 1.76s/it, lr: 1.0e-04 loss: 5.086e-01]
my_first_lora_v2: 31%|### | 1236/4000 [36:11<1:20:56, 1.76s/it, lr: 1.0e-04 loss: 5.584e-01]
my_first_lora_v2: 31%|### | 1236/4000 [36:11<1:20:56, 1.76s/it, lr: 1.0e-04 loss: 5.584e-01]
my_first_lora_v2: 31%|### | 1237/4000 [36:14<1:20:57, 1.76s/it, lr: 1.0e-04 loss: 4.528e-01]
my_first_lora_v2: 31%|### | 1237/4000 [36:14<1:20:57, 1.76s/it, lr: 1.0e-04 loss: 4.528e-01]
my_first_lora_v2: 31%|### | 1238/4000 [36:17<1:20:57, 1.76s/it, lr: 1.0e-04 loss: 3.867e-01]
my_first_lora_v2: 31%|### | 1238/4000 [36:17<1:20:57, 1.76s/it, lr: 1.0e-04 loss: 3.867e-01]
my_first_lora_v2: 31%|### | 1239/4000 [36:20<1:20:58, 1.76s/it, lr: 1.0e-04 loss: 7.142e-01]
my_first_lora_v2: 31%|### | 1239/4000 [36:20<1:20:58, 1.76s/it, lr: 1.0e-04 loss: 7.142e-01]
my_first_lora_v2: 31%|###1 | 1240/4000 [36:20<1:20:54, 1.76s/it, lr: 1.0e-04 loss: 3.830e-01]
my_first_lora_v2: 31%|###1 | 1240/4000 [36:20<1:20:54, 1.76s/it, lr: 1.0e-04 loss: 3.830e-01]
my_first_lora_v2: 31%|###1 | 1241/4000 [36:23<1:20:55, 1.76s/it, lr: 1.0e-04 loss: 6.398e-01]
my_first_lora_v2: 31%|###1 | 1241/4000 [36:23<1:20:55, 1.76s/it, lr: 1.0e-04 loss: 6.398e-01]
my_first_lora_v2: 31%|###1 | 1242/4000 [36:26<1:20:55, 1.76s/it, lr: 1.0e-04 loss: 4.128e-01]
my_first_lora_v2: 31%|###1 | 1242/4000 [36:26<1:20:55, 1.76s/it, lr: 1.0e-04 loss: 4.128e-01]
my_first_lora_v2: 31%|###1 | 1243/4000 [36:27<1:20:51, 1.76s/it, lr: 1.0e-04 loss: 1.541e-01]
my_first_lora_v2: 31%|###1 | 1243/4000 [36:27<1:20:51, 1.76s/it, lr: 1.0e-04 loss: 1.541e-01]
my_first_lora_v2: 31%|###1 | 1244/4000 [36:30<1:20:52, 1.76s/it, lr: 1.0e-04 loss: 4.961e-01]
my_first_lora_v2: 31%|###1 | 1244/4000 [36:30<1:20:52, 1.76s/it, lr: 1.0e-04 loss: 4.961e-01]
my_first_lora_v2: 31%|###1 | 1245/4000 [36:33<1:20:53, 1.76s/it, lr: 1.0e-04 loss: 4.963e-01]
my_first_lora_v2: 31%|###1 | 1245/4000 [36:33<1:20:53, 1.76s/it, lr: 1.0e-04 loss: 4.963e-01]
my_first_lora_v2: 31%|###1 | 1246/4000 [36:34<1:20:49, 1.76s/it, lr: 1.0e-04 loss: 7.919e-01]
my_first_lora_v2: 31%|###1 | 1246/4000 [36:34<1:20:49, 1.76s/it, lr: 1.0e-04 loss: 7.919e-01]
my_first_lora_v2: 31%|###1 | 1247/4000 [36:36<1:20:50, 1.76s/it, lr: 1.0e-04 loss: 5.858e-01]
my_first_lora_v2: 31%|###1 | 1247/4000 [36:36<1:20:50, 1.76s/it, lr: 1.0e-04 loss: 5.858e-01]
my_first_lora_v2: 31%|###1 | 1248/4000 [36:39<1:20:50, 1.76s/it, lr: 1.0e-04 loss: 6.626e-01]
my_first_lora_v2: 31%|###1 | 1248/4000 [36:39<1:20:50, 1.76s/it, lr: 1.0e-04 loss: 6.626e-01]
my_first_lora_v2: 31%|###1 | 1249/4000 [36:40<1:20:46, 1.76s/it, lr: 1.0e-04 loss: 5.425e-02]
my_first_lora_v2: 31%|###1 | 1249/4000 [36:40<1:20:46, 1.76s/it, lr: 1.0e-04 loss: 5.425e-02] |
| Saving at step 1250 |
| Saved checkpoint to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v2/my_first_lora_v2_000001250.safetensors |
| Saved optimizer to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v2/optimizer.pt |
| Removing old save: /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v2/my_first_lora_v2_000000250.safetensors |
| Unloading assistant lora |
|
|
|
|
|
Generating Images: 0%| | 0/3 [00:00<?, ?it/s]
Generating Images: 0%| | 0/3 [00:00<?, ?it/s][A[A |
|
|
|
Generating Images: 33%|###3 | 1/3 [00:07<00:15, 7.82s/it]
Generating Images: 33%|###3 | 1/3 [00:07<00:15, 7.82s/it][A[A |
|
|
|
Generating Images: 67%|######6 | 2/3 [00:15<00:07, 7.73s/it]
Generating Images: 67%|######6 | 2/3 [00:15<00:07, 7.73s/it][A[A |
|
|
|
Generating Images: 100%|##########| 3/3 [00:23<00:00, 7.68s/it]
Generating Images: 100%|##########| 3/3 [00:23<00:00, 7.68s/it][A[A |
|
|
|
[A[ALoading assistant lora |
|
my_first_lora_v2: 31%|###1 | 1250/4000 [36:41<1:20:43, 1.76s/it, lr: 1.0e-04 loss: 1.407e-01]
my_first_lora_v2: 31%|###1 | 1250/4000 [36:41<1:20:43, 1.76s/it, lr: 1.0e-04 loss: 1.407e-01]
my_first_lora_v2: 31%|###1 | 1251/4000 [36:44<1:20:43, 1.76s/it, lr: 1.0e-04 loss: 5.725e-02]
my_first_lora_v2: 31%|###1 | 1251/4000 [36:44<1:20:43, 1.76s/it, lr: 1.0e-04 loss: 5.725e-02]
my_first_lora_v2: 31%|###1 | 1252/4000 [36:46<1:20:43, 1.76s/it, lr: 1.0e-04 loss: 5.068e-01]
my_first_lora_v2: 31%|###1 | 1252/4000 [36:46<1:20:43, 1.76s/it, lr: 1.0e-04 loss: 5.068e-01]
my_first_lora_v2: 31%|###1 | 1253/4000 [36:47<1:20:39, 1.76s/it, lr: 1.0e-04 loss: 3.577e-01]
my_first_lora_v2: 31%|###1 | 1253/4000 [36:47<1:20:39, 1.76s/it, lr: 1.0e-04 loss: 3.577e-01]
my_first_lora_v2: 31%|###1 | 1254/4000 [36:48<1:20:35, 1.76s/it, lr: 1.0e-04 loss: 4.984e-01]
my_first_lora_v2: 31%|###1 | 1254/4000 [36:48<1:20:35, 1.76s/it, lr: 1.0e-04 loss: 4.984e-01]
my_first_lora_v2: 31%|###1 | 1255/4000 [36:49<1:20:32, 1.76s/it, lr: 1.0e-04 loss: 4.698e-01]
my_first_lora_v2: 31%|###1 | 1255/4000 [36:49<1:20:32, 1.76s/it, lr: 1.0e-04 loss: 4.698e-01]
my_first_lora_v2: 31%|###1 | 1256/4000 [36:51<1:20:31, 1.76s/it, lr: 1.0e-04 loss: 7.578e-02]
my_first_lora_v2: 31%|###1 | 1256/4000 [36:51<1:20:31, 1.76s/it, lr: 1.0e-04 loss: 7.578e-02]
my_first_lora_v2: 31%|###1 | 1257/4000 [36:52<1:20:27, 1.76s/it, lr: 1.0e-04 loss: 1.002e-01]
my_first_lora_v2: 31%|###1 | 1257/4000 [36:52<1:20:27, 1.76s/it, lr: 1.0e-04 loss: 1.002e-01]
my_first_lora_v2: 31%|###1 | 1258/4000 [36:53<1:20:24, 1.76s/it, lr: 1.0e-04 loss: 2.453e-01]
my_first_lora_v2: 31%|###1 | 1258/4000 [36:53<1:20:24, 1.76s/it, lr: 1.0e-04 loss: 2.453e-01]
my_first_lora_v2: 31%|###1 | 1259/4000 [36:56<1:20:25, 1.76s/it, lr: 1.0e-04 loss: 5.089e-01]
my_first_lora_v2: 31%|###1 | 1259/4000 [36:56<1:20:25, 1.76s/it, lr: 1.0e-04 loss: 5.089e-01]
my_first_lora_v2: 32%|###1 | 1260/4000 [36:59<1:20:25, 1.76s/it, lr: 1.0e-04 loss: 4.979e-01]
my_first_lora_v2: 32%|###1 | 1260/4000 [36:59<1:20:25, 1.76s/it, lr: 1.0e-04 loss: 4.979e-01]
my_first_lora_v2: 32%|###1 | 1261/4000 [37:00<1:20:22, 1.76s/it, lr: 1.0e-04 loss: 2.650e-01]
my_first_lora_v2: 32%|###1 | 1261/4000 [37:00<1:20:22, 1.76s/it, lr: 1.0e-04 loss: 2.650e-01]
my_first_lora_v2: 32%|###1 | 1262/4000 [37:03<1:20:23, 1.76s/it, lr: 1.0e-04 loss: 2.234e-01]
my_first_lora_v2: 32%|###1 | 1262/4000 [37:03<1:20:23, 1.76s/it, lr: 1.0e-04 loss: 2.234e-01]
my_first_lora_v2: 32%|###1 | 1263/4000 [37:03<1:20:19, 1.76s/it, lr: 1.0e-04 loss: 1.521e-02]
my_first_lora_v2: 32%|###1 | 1263/4000 [37:03<1:20:19, 1.76s/it, lr: 1.0e-04 loss: 1.521e-02]
my_first_lora_v2: 32%|###1 | 1264/4000 [37:06<1:20:20, 1.76s/it, lr: 1.0e-04 loss: 4.964e-01]
my_first_lora_v2: 32%|###1 | 1264/4000 [37:06<1:20:20, 1.76s/it, lr: 1.0e-04 loss: 4.964e-01]
my_first_lora_v2: 32%|###1 | 1265/4000 [37:07<1:20:16, 1.76s/it, lr: 1.0e-04 loss: 4.761e-01]
my_first_lora_v2: 32%|###1 | 1265/4000 [37:07<1:20:16, 1.76s/it, lr: 1.0e-04 loss: 4.761e-01]
my_first_lora_v2: 32%|###1 | 1266/4000 [37:10<1:20:17, 1.76s/it, lr: 1.0e-04 loss: 6.574e-01]
my_first_lora_v2: 32%|###1 | 1266/4000 [37:10<1:20:17, 1.76s/it, lr: 1.0e-04 loss: 6.574e-01]
my_first_lora_v2: 32%|###1 | 1267/4000 [37:13<1:20:17, 1.76s/it, lr: 1.0e-04 loss: 2.981e-01]
my_first_lora_v2: 32%|###1 | 1267/4000 [37:13<1:20:17, 1.76s/it, lr: 1.0e-04 loss: 2.981e-01]
my_first_lora_v2: 32%|###1 | 1268/4000 [37:14<1:20:13, 1.76s/it, lr: 1.0e-04 loss: 6.741e-01]
my_first_lora_v2: 32%|###1 | 1268/4000 [37:14<1:20:13, 1.76s/it, lr: 1.0e-04 loss: 6.741e-01]
my_first_lora_v2: 32%|###1 | 1269/4000 [37:16<1:20:14, 1.76s/it, lr: 1.0e-04 loss: 2.478e-01]
my_first_lora_v2: 32%|###1 | 1269/4000 [37:16<1:20:14, 1.76s/it, lr: 1.0e-04 loss: 2.478e-01]
my_first_lora_v2: 32%|###1 | 1270/4000 [37:17<1:20:10, 1.76s/it, lr: 1.0e-04 loss: 6.898e-01]
my_first_lora_v2: 32%|###1 | 1270/4000 [37:17<1:20:10, 1.76s/it, lr: 1.0e-04 loss: 6.898e-01]
my_first_lora_v2: 32%|###1 | 1271/4000 [37:20<1:20:10, 1.76s/it, lr: 1.0e-04 loss: 5.501e-01]
my_first_lora_v2: 32%|###1 | 1271/4000 [37:20<1:20:10, 1.76s/it, lr: 1.0e-04 loss: 5.501e-01]
my_first_lora_v2: 32%|###1 | 1272/4000 [37:21<1:20:06, 1.76s/it, lr: 1.0e-04 loss: 3.699e-01]
my_first_lora_v2: 32%|###1 | 1272/4000 [37:21<1:20:06, 1.76s/it, lr: 1.0e-04 loss: 3.699e-01]
my_first_lora_v2: 32%|###1 | 1273/4000 [37:23<1:20:06, 1.76s/it, lr: 1.0e-04 loss: 7.968e-01]
my_first_lora_v2: 32%|###1 | 1273/4000 [37:23<1:20:06, 1.76s/it, lr: 1.0e-04 loss: 7.968e-01]
my_first_lora_v2: 32%|###1 | 1274/4000 [37:24<1:20:03, 1.76s/it, lr: 1.0e-04 loss: 3.813e-01]
my_first_lora_v2: 32%|###1 | 1274/4000 [37:24<1:20:03, 1.76s/it, lr: 1.0e-04 loss: 3.813e-01]
my_first_lora_v2: 32%|###1 | 1275/4000 [37:25<1:19:59, 1.76s/it, lr: 1.0e-04 loss: 1.346e-01]
my_first_lora_v2: 32%|###1 | 1275/4000 [37:25<1:19:59, 1.76s/it, lr: 1.0e-04 loss: 1.346e-01]
my_first_lora_v2: 32%|###1 | 1276/4000 [37:28<1:20:00, 1.76s/it, lr: 1.0e-04 loss: 6.283e-01]
my_first_lora_v2: 32%|###1 | 1276/4000 [37:28<1:20:00, 1.76s/it, lr: 1.0e-04 loss: 6.283e-01]
my_first_lora_v2: 32%|###1 | 1277/4000 [37:29<1:19:56, 1.76s/it, lr: 1.0e-04 loss: 8.029e-01]
my_first_lora_v2: 32%|###1 | 1277/4000 [37:29<1:19:56, 1.76s/it, lr: 1.0e-04 loss: 8.029e-01]
my_first_lora_v2: 32%|###1 | 1278/4000 [37:30<1:19:52, 1.76s/it, lr: 1.0e-04 loss: 3.877e-01]
my_first_lora_v2: 32%|###1 | 1278/4000 [37:30<1:19:52, 1.76s/it, lr: 1.0e-04 loss: 3.877e-01]
my_first_lora_v2: 32%|###1 | 1279/4000 [37:31<1:19:49, 1.76s/it, lr: 1.0e-04 loss: 1.228e-01]
my_first_lora_v2: 32%|###1 | 1279/4000 [37:31<1:19:49, 1.76s/it, lr: 1.0e-04 loss: 1.228e-01]
my_first_lora_v2: 32%|###2 | 1280/4000 [37:31<1:19:45, 1.76s/it, lr: 1.0e-04 loss: 6.673e-01]
my_first_lora_v2: 32%|###2 | 1280/4000 [37:31<1:19:45, 1.76s/it, lr: 1.0e-04 loss: 6.673e-01]
my_first_lora_v2: 32%|###2 | 1281/4000 [37:32<1:19:41, 1.76s/it, lr: 1.0e-04 loss: 1.149e-01]
my_first_lora_v2: 32%|###2 | 1281/4000 [37:32<1:19:41, 1.76s/it, lr: 1.0e-04 loss: 1.149e-01]
my_first_lora_v2: 32%|###2 | 1282/4000 [37:33<1:19:37, 1.76s/it, lr: 1.0e-04 loss: 5.355e-01]
my_first_lora_v2: 32%|###2 | 1282/4000 [37:33<1:19:37, 1.76s/it, lr: 1.0e-04 loss: 5.355e-01]
my_first_lora_v2: 32%|###2 | 1283/4000 [37:34<1:19:34, 1.76s/it, lr: 1.0e-04 loss: 2.423e-02]
my_first_lora_v2: 32%|###2 | 1283/4000 [37:34<1:19:34, 1.76s/it, lr: 1.0e-04 loss: 2.423e-02]
my_first_lora_v2: 32%|###2 | 1284/4000 [37:35<1:19:30, 1.76s/it, lr: 1.0e-04 loss: 4.225e-01]
my_first_lora_v2: 32%|###2 | 1284/4000 [37:35<1:19:30, 1.76s/it, lr: 1.0e-04 loss: 4.225e-01]
my_first_lora_v2: 32%|###2 | 1285/4000 [37:36<1:19:26, 1.76s/it, lr: 1.0e-04 loss: 1.992e-01]
my_first_lora_v2: 32%|###2 | 1285/4000 [37:36<1:19:26, 1.76s/it, lr: 1.0e-04 loss: 1.992e-01]
my_first_lora_v2: 32%|###2 | 1286/4000 [37:36<1:19:22, 1.75s/it, lr: 1.0e-04 loss: 1.772e-01]
my_first_lora_v2: 32%|###2 | 1286/4000 [37:36<1:19:22, 1.75s/it, lr: 1.0e-04 loss: 1.772e-01]
my_first_lora_v2: 32%|###2 | 1287/4000 [37:39<1:19:22, 1.76s/it, lr: 1.0e-04 loss: 2.198e-01]
my_first_lora_v2: 32%|###2 | 1287/4000 [37:39<1:19:22, 1.76s/it, lr: 1.0e-04 loss: 2.198e-01]
my_first_lora_v2: 32%|###2 | 1288/4000 [37:42<1:19:23, 1.76s/it, lr: 1.0e-04 loss: 2.706e-01]
my_first_lora_v2: 32%|###2 | 1288/4000 [37:42<1:19:23, 1.76s/it, lr: 1.0e-04 loss: 2.706e-01]
my_first_lora_v2: 32%|###2 | 1289/4000 [37:45<1:19:24, 1.76s/it, lr: 1.0e-04 loss: 8.579e-02]
my_first_lora_v2: 32%|###2 | 1289/4000 [37:45<1:19:24, 1.76s/it, lr: 1.0e-04 loss: 8.579e-02]
my_first_lora_v2: 32%|###2 | 1290/4000 [37:48<1:19:24, 1.76s/it, lr: 1.0e-04 loss: 1.760e-01]
my_first_lora_v2: 32%|###2 | 1290/4000 [37:48<1:19:24, 1.76s/it, lr: 1.0e-04 loss: 1.760e-01]
my_first_lora_v2: 32%|###2 | 1291/4000 [37:51<1:19:25, 1.76s/it, lr: 1.0e-04 loss: 5.168e-01]
my_first_lora_v2: 32%|###2 | 1291/4000 [37:51<1:19:25, 1.76s/it, lr: 1.0e-04 loss: 5.168e-01]
my_first_lora_v2: 32%|###2 | 1292/4000 [37:51<1:19:21, 1.76s/it, lr: 1.0e-04 loss: 2.112e-01]
my_first_lora_v2: 32%|###2 | 1292/4000 [37:51<1:19:21, 1.76s/it, lr: 1.0e-04 loss: 2.112e-01]
my_first_lora_v2: 32%|###2 | 1293/4000 [37:54<1:19:22, 1.76s/it, lr: 1.0e-04 loss: 2.446e-01]
my_first_lora_v2: 32%|###2 | 1293/4000 [37:54<1:19:22, 1.76s/it, lr: 1.0e-04 loss: 2.446e-01]
my_first_lora_v2: 32%|###2 | 1294/4000 [37:57<1:19:22, 1.76s/it, lr: 1.0e-04 loss: 6.905e-01]
my_first_lora_v2: 32%|###2 | 1294/4000 [37:57<1:19:22, 1.76s/it, lr: 1.0e-04 loss: 6.905e-01]
my_first_lora_v2: 32%|###2 | 1295/4000 [37:58<1:19:18, 1.76s/it, lr: 1.0e-04 loss: 2.834e-01]
my_first_lora_v2: 32%|###2 | 1295/4000 [37:58<1:19:18, 1.76s/it, lr: 1.0e-04 loss: 2.834e-01]
my_first_lora_v2: 32%|###2 | 1296/4000 [38:01<1:19:19, 1.76s/it, lr: 1.0e-04 loss: 1.943e-01]
my_first_lora_v2: 32%|###2 | 1296/4000 [38:01<1:19:19, 1.76s/it, lr: 1.0e-04 loss: 1.943e-01]
my_first_lora_v2: 32%|###2 | 1297/4000 [38:03<1:19:19, 1.76s/it, lr: 1.0e-04 loss: 5.430e-01]
my_first_lora_v2: 32%|###2 | 1297/4000 [38:03<1:19:19, 1.76s/it, lr: 1.0e-04 loss: 5.430e-01]
my_first_lora_v2: 32%|###2 | 1298/4000 [38:06<1:19:20, 1.76s/it, lr: 1.0e-04 loss: 4.194e-01]
my_first_lora_v2: 32%|###2 | 1298/4000 [38:06<1:19:20, 1.76s/it, lr: 1.0e-04 loss: 4.194e-01]
my_first_lora_v2: 32%|###2 | 1299/4000 [38:07<1:19:16, 1.76s/it, lr: 1.0e-04 loss: 2.834e-01]
my_first_lora_v2: 32%|###2 | 1299/4000 [38:07<1:19:16, 1.76s/it, lr: 1.0e-04 loss: 2.834e-01]
my_first_lora_v2: 32%|###2 | 1300/4000 [38:10<1:19:17, 1.76s/it, lr: 1.0e-04 loss: 6.578e-03]
my_first_lora_v2: 32%|###2 | 1300/4000 [38:10<1:19:17, 1.76s/it, lr: 1.0e-04 loss: 6.578e-03]
my_first_lora_v2: 33%|###2 | 1301/4000 [38:11<1:19:13, 1.76s/it, lr: 1.0e-04 loss: 6.277e-01]
my_first_lora_v2: 33%|###2 | 1301/4000 [38:11<1:19:13, 1.76s/it, lr: 1.0e-04 loss: 6.277e-01]
my_first_lora_v2: 33%|###2 | 1302/4000 [38:12<1:19:09, 1.76s/it, lr: 1.0e-04 loss: 3.324e-01]
my_first_lora_v2: 33%|###2 | 1302/4000 [38:12<1:19:09, 1.76s/it, lr: 1.0e-04 loss: 3.324e-01]
my_first_lora_v2: 33%|###2 | 1303/4000 [38:13<1:19:06, 1.76s/it, lr: 1.0e-04 loss: 7.255e-01]
my_first_lora_v2: 33%|###2 | 1303/4000 [38:13<1:19:06, 1.76s/it, lr: 1.0e-04 loss: 7.255e-01]
my_first_lora_v2: 33%|###2 | 1304/4000 [38:15<1:19:06, 1.76s/it, lr: 1.0e-04 loss: 2.171e-01]
my_first_lora_v2: 33%|###2 | 1304/4000 [38:15<1:19:06, 1.76s/it, lr: 1.0e-04 loss: 2.171e-01]
my_first_lora_v2: 33%|###2 | 1305/4000 [38:17<1:19:04, 1.76s/it, lr: 1.0e-04 loss: 7.757e-01]
my_first_lora_v2: 33%|###2 | 1305/4000 [38:17<1:19:04, 1.76s/it, lr: 1.0e-04 loss: 7.757e-01]
my_first_lora_v2: 33%|###2 | 1306/4000 [38:18<1:19:00, 1.76s/it, lr: 1.0e-04 loss: 4.453e-01]
my_first_lora_v2: 33%|###2 | 1306/4000 [38:18<1:19:00, 1.76s/it, lr: 1.0e-04 loss: 4.453e-01]
my_first_lora_v2: 33%|###2 | 1307/4000 [38:19<1:18:57, 1.76s/it, lr: 1.0e-04 loss: 3.356e-01]
my_first_lora_v2: 33%|###2 | 1307/4000 [38:19<1:18:57, 1.76s/it, lr: 1.0e-04 loss: 3.356e-01]
my_first_lora_v2: 33%|###2 | 1308/4000 [38:21<1:18:56, 1.76s/it, lr: 1.0e-04 loss: 8.101e-02]
my_first_lora_v2: 33%|###2 | 1308/4000 [38:21<1:18:56, 1.76s/it, lr: 1.0e-04 loss: 8.101e-02]
my_first_lora_v2: 33%|###2 | 1309/4000 [38:24<1:18:57, 1.76s/it, lr: 1.0e-04 loss: 9.855e-02]
my_first_lora_v2: 33%|###2 | 1309/4000 [38:24<1:18:57, 1.76s/it, lr: 1.0e-04 loss: 9.855e-02]
my_first_lora_v2: 33%|###2 | 1310/4000 [38:25<1:18:53, 1.76s/it, lr: 1.0e-04 loss: 1.198e-01]
my_first_lora_v2: 33%|###2 | 1310/4000 [38:25<1:18:53, 1.76s/it, lr: 1.0e-04 loss: 1.198e-01]
my_first_lora_v2: 33%|###2 | 1311/4000 [38:26<1:18:49, 1.76s/it, lr: 1.0e-04 loss: 1.666e-01]
my_first_lora_v2: 33%|###2 | 1311/4000 [38:26<1:18:49, 1.76s/it, lr: 1.0e-04 loss: 1.666e-01]
my_first_lora_v2: 33%|###2 | 1312/4000 [38:26<1:18:46, 1.76s/it, lr: 1.0e-04 loss: 1.583e-01]
my_first_lora_v2: 33%|###2 | 1312/4000 [38:26<1:18:46, 1.76s/it, lr: 1.0e-04 loss: 1.583e-01]
my_first_lora_v2: 33%|###2 | 1313/4000 [38:27<1:18:42, 1.76s/it, lr: 1.0e-04 loss: 4.043e-01]
my_first_lora_v2: 33%|###2 | 1313/4000 [38:27<1:18:42, 1.76s/it, lr: 1.0e-04 loss: 4.043e-01]
my_first_lora_v2: 33%|###2 | 1314/4000 [38:30<1:18:43, 1.76s/it, lr: 1.0e-04 loss: 6.019e-01]
my_first_lora_v2: 33%|###2 | 1314/4000 [38:30<1:18:43, 1.76s/it, lr: 1.0e-04 loss: 6.019e-01]
my_first_lora_v2: 33%|###2 | 1315/4000 [38:31<1:18:39, 1.76s/it, lr: 1.0e-04 loss: 3.020e-01]
my_first_lora_v2: 33%|###2 | 1315/4000 [38:31<1:18:39, 1.76s/it, lr: 1.0e-04 loss: 3.020e-01]
my_first_lora_v2: 33%|###2 | 1316/4000 [38:34<1:18:39, 1.76s/it, lr: 1.0e-04 loss: 7.080e-01]
my_first_lora_v2: 33%|###2 | 1316/4000 [38:34<1:18:39, 1.76s/it, lr: 1.0e-04 loss: 7.080e-01]
my_first_lora_v2: 33%|###2 | 1317/4000 [38:36<1:18:39, 1.76s/it, lr: 1.0e-04 loss: 7.246e-01]
my_first_lora_v2: 33%|###2 | 1317/4000 [38:36<1:18:39, 1.76s/it, lr: 1.0e-04 loss: 7.246e-01]
my_first_lora_v2: 33%|###2 | 1318/4000 [38:39<1:18:40, 1.76s/it, lr: 1.0e-04 loss: 6.188e-01]
my_first_lora_v2: 33%|###2 | 1318/4000 [38:39<1:18:40, 1.76s/it, lr: 1.0e-04 loss: 6.188e-01]
my_first_lora_v2: 33%|###2 | 1319/4000 [38:40<1:18:36, 1.76s/it, lr: 1.0e-04 loss: 3.137e-01]
my_first_lora_v2: 33%|###2 | 1319/4000 [38:40<1:18:36, 1.76s/it, lr: 1.0e-04 loss: 3.137e-01]
my_first_lora_v2: 33%|###3 | 1320/4000 [38:41<1:18:33, 1.76s/it, lr: 1.0e-04 loss: 1.579e-01]
my_first_lora_v2: 33%|###3 | 1320/4000 [38:41<1:18:33, 1.76s/it, lr: 1.0e-04 loss: 1.579e-01]
my_first_lora_v2: 33%|###3 | 1321/4000 [38:44<1:18:33, 1.76s/it, lr: 1.0e-04 loss: 5.508e-01]
my_first_lora_v2: 33%|###3 | 1321/4000 [38:44<1:18:33, 1.76s/it, lr: 1.0e-04 loss: 5.508e-01]
my_first_lora_v2: 33%|###3 | 1322/4000 [38:47<1:18:34, 1.76s/it, lr: 1.0e-04 loss: 3.072e-02]
my_first_lora_v2: 33%|###3 | 1322/4000 [38:47<1:18:34, 1.76s/it, lr: 1.0e-04 loss: 3.072e-02]
my_first_lora_v2: 33%|###3 | 1323/4000 [38:48<1:18:30, 1.76s/it, lr: 1.0e-04 loss: 4.685e-01]
my_first_lora_v2: 33%|###3 | 1323/4000 [38:48<1:18:30, 1.76s/it, lr: 1.0e-04 loss: 4.685e-01]
my_first_lora_v2: 33%|###3 | 1324/4000 [38:48<1:18:26, 1.76s/it, lr: 1.0e-04 loss: 7.431e-01]
my_first_lora_v2: 33%|###3 | 1324/4000 [38:48<1:18:26, 1.76s/it, lr: 1.0e-04 loss: 7.431e-01]
my_first_lora_v2: 33%|###3 | 1325/4000 [38:50<1:18:24, 1.76s/it, lr: 1.0e-04 loss: 7.899e-01]
my_first_lora_v2: 33%|###3 | 1325/4000 [38:50<1:18:24, 1.76s/it, lr: 1.0e-04 loss: 7.899e-01]
my_first_lora_v2: 33%|###3 | 1326/4000 [38:50<1:18:20, 1.76s/it, lr: 1.0e-04 loss: 7.312e-01]
my_first_lora_v2: 33%|###3 | 1326/4000 [38:50<1:18:20, 1.76s/it, lr: 1.0e-04 loss: 7.312e-01]
my_first_lora_v2: 33%|###3 | 1327/4000 [38:51<1:18:16, 1.76s/it, lr: 1.0e-04 loss: 7.860e-02]
my_first_lora_v2: 33%|###3 | 1327/4000 [38:51<1:18:16, 1.76s/it, lr: 1.0e-04 loss: 7.860e-02]
my_first_lora_v2: 33%|###3 | 1328/4000 [38:54<1:18:16, 1.76s/it, lr: 1.0e-04 loss: 6.217e-01]
my_first_lora_v2: 33%|###3 | 1328/4000 [38:54<1:18:16, 1.76s/it, lr: 1.0e-04 loss: 6.217e-01]
my_first_lora_v2: 33%|###3 | 1329/4000 [38:57<1:18:17, 1.76s/it, lr: 1.0e-04 loss: 4.151e-01]
my_first_lora_v2: 33%|###3 | 1329/4000 [38:57<1:18:17, 1.76s/it, lr: 1.0e-04 loss: 4.151e-01]
my_first_lora_v2: 33%|###3 | 1330/4000 [38:58<1:18:13, 1.76s/it, lr: 1.0e-04 loss: 1.294e-01]
my_first_lora_v2: 33%|###3 | 1330/4000 [38:58<1:18:13, 1.76s/it, lr: 1.0e-04 loss: 1.294e-01]
my_first_lora_v2: 33%|###3 | 1331/4000 [39:00<1:18:13, 1.76s/it, lr: 1.0e-04 loss: 5.771e-01]
my_first_lora_v2: 33%|###3 | 1331/4000 [39:00<1:18:13, 1.76s/it, lr: 1.0e-04 loss: 5.771e-01]
my_first_lora_v2: 33%|###3 | 1332/4000 [39:03<1:18:13, 1.76s/it, lr: 1.0e-04 loss: 6.121e-01]
my_first_lora_v2: 33%|###3 | 1332/4000 [39:03<1:18:13, 1.76s/it, lr: 1.0e-04 loss: 6.121e-01]
my_first_lora_v2: 33%|###3 | 1333/4000 [39:06<1:18:14, 1.76s/it, lr: 1.0e-04 loss: 7.313e-01]
my_first_lora_v2: 33%|###3 | 1333/4000 [39:06<1:18:14, 1.76s/it, lr: 1.0e-04 loss: 7.313e-01]
my_first_lora_v2: 33%|###3 | 1334/4000 [39:07<1:18:10, 1.76s/it, lr: 1.0e-04 loss: 4.360e-01]
my_first_lora_v2: 33%|###3 | 1334/4000 [39:07<1:18:10, 1.76s/it, lr: 1.0e-04 loss: 4.360e-01]
my_first_lora_v2: 33%|###3 | 1335/4000 [39:07<1:18:07, 1.76s/it, lr: 1.0e-04 loss: 7.399e-01]
my_first_lora_v2: 33%|###3 | 1335/4000 [39:07<1:18:07, 1.76s/it, lr: 1.0e-04 loss: 7.399e-01]
my_first_lora_v2: 33%|###3 | 1336/4000 [39:08<1:18:03, 1.76s/it, lr: 1.0e-04 loss: 2.004e-01]
my_first_lora_v2: 33%|###3 | 1336/4000 [39:08<1:18:03, 1.76s/it, lr: 1.0e-04 loss: 2.004e-01]
my_first_lora_v2: 33%|###3 | 1337/4000 [39:09<1:17:59, 1.76s/it, lr: 1.0e-04 loss: 4.867e-01]
my_first_lora_v2: 33%|###3 | 1337/4000 [39:09<1:17:59, 1.76s/it, lr: 1.0e-04 loss: 4.867e-01]
my_first_lora_v2: 33%|###3 | 1338/4000 [39:10<1:17:56, 1.76s/it, lr: 1.0e-04 loss: 1.818e-01]
my_first_lora_v2: 33%|###3 | 1338/4000 [39:10<1:17:56, 1.76s/it, lr: 1.0e-04 loss: 1.818e-01]
my_first_lora_v2: 33%|###3 | 1339/4000 [39:12<1:17:55, 1.76s/it, lr: 1.0e-04 loss: 3.992e-01]
my_first_lora_v2: 33%|###3 | 1339/4000 [39:12<1:17:55, 1.76s/it, lr: 1.0e-04 loss: 3.992e-01]
my_first_lora_v2: 34%|###3 | 1340/4000 [39:15<1:17:56, 1.76s/it, lr: 1.0e-04 loss: 4.830e-01]
my_first_lora_v2: 34%|###3 | 1340/4000 [39:15<1:17:56, 1.76s/it, lr: 1.0e-04 loss: 4.830e-01]
my_first_lora_v2: 34%|###3 | 1341/4000 [39:18<1:17:56, 1.76s/it, lr: 1.0e-04 loss: 2.444e-01]
my_first_lora_v2: 34%|###3 | 1341/4000 [39:18<1:17:56, 1.76s/it, lr: 1.0e-04 loss: 2.444e-01]
my_first_lora_v2: 34%|###3 | 1342/4000 [39:21<1:17:56, 1.76s/it, lr: 1.0e-04 loss: 6.330e-01]
my_first_lora_v2: 34%|###3 | 1342/4000 [39:21<1:17:56, 1.76s/it, lr: 1.0e-04 loss: 6.330e-01]
my_first_lora_v2: 34%|###3 | 1343/4000 [39:24<1:17:57, 1.76s/it, lr: 1.0e-04 loss: 3.691e-01]
my_first_lora_v2: 34%|###3 | 1343/4000 [39:24<1:17:57, 1.76s/it, lr: 1.0e-04 loss: 3.691e-01]
my_first_lora_v2: 34%|###3 | 1344/4000 [39:25<1:17:53, 1.76s/it, lr: 1.0e-04 loss: 6.295e-02]
my_first_lora_v2: 34%|###3 | 1344/4000 [39:25<1:17:53, 1.76s/it, lr: 1.0e-04 loss: 6.295e-02]
my_first_lora_v2: 34%|###3 | 1345/4000 [39:27<1:17:53, 1.76s/it, lr: 1.0e-04 loss: 2.016e-01]
my_first_lora_v2: 34%|###3 | 1345/4000 [39:27<1:17:53, 1.76s/it, lr: 1.0e-04 loss: 2.016e-01]
my_first_lora_v2: 34%|###3 | 1346/4000 [39:28<1:17:50, 1.76s/it, lr: 1.0e-04 loss: 1.650e-01]
my_first_lora_v2: 34%|###3 | 1346/4000 [39:28<1:17:50, 1.76s/it, lr: 1.0e-04 loss: 1.650e-01]
my_first_lora_v2: 34%|###3 | 1347/4000 [39:31<1:17:50, 1.76s/it, lr: 1.0e-04 loss: 3.992e-01]
my_first_lora_v2: 34%|###3 | 1347/4000 [39:31<1:17:50, 1.76s/it, lr: 1.0e-04 loss: 3.992e-01]
my_first_lora_v2: 34%|###3 | 1348/4000 [39:32<1:17:46, 1.76s/it, lr: 1.0e-04 loss: 5.727e-01]
my_first_lora_v2: 34%|###3 | 1348/4000 [39:32<1:17:46, 1.76s/it, lr: 1.0e-04 loss: 5.727e-01]
my_first_lora_v2: 34%|###3 | 1349/4000 [39:33<1:17:43, 1.76s/it, lr: 1.0e-04 loss: 2.753e-01]
my_first_lora_v2: 34%|###3 | 1349/4000 [39:33<1:17:43, 1.76s/it, lr: 1.0e-04 loss: 2.753e-01]
my_first_lora_v2: 34%|###3 | 1350/4000 [39:33<1:17:39, 1.76s/it, lr: 1.0e-04 loss: 7.019e-01]
my_first_lora_v2: 34%|###3 | 1350/4000 [39:33<1:17:39, 1.76s/it, lr: 1.0e-04 loss: 7.019e-01]
my_first_lora_v2: 34%|###3 | 1351/4000 [39:34<1:17:36, 1.76s/it, lr: 1.0e-04 loss: 5.458e-01]
my_first_lora_v2: 34%|###3 | 1351/4000 [39:34<1:17:36, 1.76s/it, lr: 1.0e-04 loss: 5.458e-01]
my_first_lora_v2: 34%|###3 | 1352/4000 [39:37<1:17:36, 1.76s/it, lr: 1.0e-04 loss: 5.186e-01]
my_first_lora_v2: 34%|###3 | 1352/4000 [39:37<1:17:36, 1.76s/it, lr: 1.0e-04 loss: 5.186e-01]
my_first_lora_v2: 34%|###3 | 1353/4000 [39:38<1:17:32, 1.76s/it, lr: 1.0e-04 loss: 6.427e-01]
my_first_lora_v2: 34%|###3 | 1353/4000 [39:38<1:17:32, 1.76s/it, lr: 1.0e-04 loss: 6.427e-01]
my_first_lora_v2: 34%|###3 | 1354/4000 [39:41<1:17:33, 1.76s/it, lr: 1.0e-04 loss: 1.180e-01]
my_first_lora_v2: 34%|###3 | 1354/4000 [39:41<1:17:33, 1.76s/it, lr: 1.0e-04 loss: 1.180e-01]
my_first_lora_v2: 34%|###3 | 1355/4000 [39:43<1:17:33, 1.76s/it, lr: 1.0e-04 loss: 2.408e-01]
my_first_lora_v2: 34%|###3 | 1355/4000 [39:43<1:17:33, 1.76s/it, lr: 1.0e-04 loss: 2.408e-01]
my_first_lora_v2: 34%|###3 | 1356/4000 [39:44<1:17:29, 1.76s/it, lr: 1.0e-04 loss: 2.991e-01]
my_first_lora_v2: 34%|###3 | 1356/4000 [39:44<1:17:29, 1.76s/it, lr: 1.0e-04 loss: 2.991e-01]
my_first_lora_v2: 34%|###3 | 1357/4000 [39:47<1:17:30, 1.76s/it, lr: 1.0e-04 loss: 5.605e-01]
my_first_lora_v2: 34%|###3 | 1357/4000 [39:47<1:17:30, 1.76s/it, lr: 1.0e-04 loss: 5.605e-01]
my_first_lora_v2: 34%|###3 | 1358/4000 [39:48<1:17:26, 1.76s/it, lr: 1.0e-04 loss: 5.024e-01]
my_first_lora_v2: 34%|###3 | 1358/4000 [39:48<1:17:26, 1.76s/it, lr: 1.0e-04 loss: 5.024e-01]
my_first_lora_v2: 34%|###3 | 1359/4000 [39:49<1:17:22, 1.76s/it, lr: 1.0e-04 loss: 1.947e-01]
my_first_lora_v2: 34%|###3 | 1359/4000 [39:49<1:17:22, 1.76s/it, lr: 1.0e-04 loss: 1.947e-01]
my_first_lora_v2: 34%|###4 | 1360/4000 [39:49<1:17:19, 1.76s/it, lr: 1.0e-04 loss: 3.313e-01]
my_first_lora_v2: 34%|###4 | 1360/4000 [39:49<1:17:19, 1.76s/it, lr: 1.0e-04 loss: 3.313e-01]
my_first_lora_v2: 34%|###4 | 1361/4000 [39:52<1:17:19, 1.76s/it, lr: 1.0e-04 loss: 6.393e-01]
my_first_lora_v2: 34%|###4 | 1361/4000 [39:52<1:17:19, 1.76s/it, lr: 1.0e-04 loss: 6.393e-01]
my_first_lora_v2: 34%|###4 | 1362/4000 [39:55<1:17:19, 1.76s/it, lr: 1.0e-04 loss: 1.484e-01]
my_first_lora_v2: 34%|###4 | 1362/4000 [39:55<1:17:19, 1.76s/it, lr: 1.0e-04 loss: 1.484e-01]
my_first_lora_v2: 34%|###4 | 1363/4000 [39:56<1:17:16, 1.76s/it, lr: 1.0e-04 loss: 2.553e-01]
my_first_lora_v2: 34%|###4 | 1363/4000 [39:56<1:17:16, 1.76s/it, lr: 1.0e-04 loss: 2.553e-01]
my_first_lora_v2: 34%|###4 | 1364/4000 [39:57<1:17:12, 1.76s/it, lr: 1.0e-04 loss: 8.716e-02]
my_first_lora_v2: 34%|###4 | 1364/4000 [39:57<1:17:12, 1.76s/it, lr: 1.0e-04 loss: 8.716e-02]
my_first_lora_v2: 34%|###4 | 1365/4000 [40:00<1:17:13, 1.76s/it, lr: 1.0e-04 loss: 2.994e-01]
my_first_lora_v2: 34%|###4 | 1365/4000 [40:00<1:17:13, 1.76s/it, lr: 1.0e-04 loss: 2.994e-01]
my_first_lora_v2: 34%|###4 | 1366/4000 [40:02<1:17:12, 1.76s/it, lr: 1.0e-04 loss: 4.198e-01]
my_first_lora_v2: 34%|###4 | 1366/4000 [40:02<1:17:12, 1.76s/it, lr: 1.0e-04 loss: 4.198e-01]
my_first_lora_v2: 34%|###4 | 1367/4000 [40:03<1:17:08, 1.76s/it, lr: 1.0e-04 loss: 2.170e-01]
my_first_lora_v2: 34%|###4 | 1367/4000 [40:03<1:17:08, 1.76s/it, lr: 1.0e-04 loss: 2.170e-01]
my_first_lora_v2: 34%|###4 | 1368/4000 [40:04<1:17:05, 1.76s/it, lr: 1.0e-04 loss: 2.078e-01]
my_first_lora_v2: 34%|###4 | 1368/4000 [40:04<1:17:05, 1.76s/it, lr: 1.0e-04 loss: 2.078e-01]
my_first_lora_v2: 34%|###4 | 1369/4000 [40:06<1:17:05, 1.76s/it, lr: 1.0e-04 loss: 4.144e-01]
my_first_lora_v2: 34%|###4 | 1369/4000 [40:06<1:17:05, 1.76s/it, lr: 1.0e-04 loss: 4.144e-01]
my_first_lora_v2: 34%|###4 | 1370/4000 [40:09<1:17:06, 1.76s/it, lr: 1.0e-04 loss: 6.553e-01]
my_first_lora_v2: 34%|###4 | 1370/4000 [40:09<1:17:06, 1.76s/it, lr: 1.0e-04 loss: 6.553e-01]
my_first_lora_v2: 34%|###4 | 1371/4000 [40:10<1:17:02, 1.76s/it, lr: 1.0e-04 loss: 5.972e-01]
my_first_lora_v2: 34%|###4 | 1371/4000 [40:10<1:17:02, 1.76s/it, lr: 1.0e-04 loss: 5.972e-01]
my_first_lora_v2: 34%|###4 | 1372/4000 [40:13<1:17:02, 1.76s/it, lr: 1.0e-04 loss: 5.248e-01]
my_first_lora_v2: 34%|###4 | 1372/4000 [40:13<1:17:02, 1.76s/it, lr: 1.0e-04 loss: 5.248e-01]
my_first_lora_v2: 34%|###4 | 1373/4000 [40:14<1:16:59, 1.76s/it, lr: 1.0e-04 loss: 4.647e-01]
my_first_lora_v2: 34%|###4 | 1373/4000 [40:14<1:16:59, 1.76s/it, lr: 1.0e-04 loss: 4.647e-01]
my_first_lora_v2: 34%|###4 | 1374/4000 [40:15<1:16:55, 1.76s/it, lr: 1.0e-04 loss: 6.359e-01]
my_first_lora_v2: 34%|###4 | 1374/4000 [40:15<1:16:55, 1.76s/it, lr: 1.0e-04 loss: 6.359e-01]
my_first_lora_v2: 34%|###4 | 1375/4000 [40:17<1:16:56, 1.76s/it, lr: 1.0e-04 loss: 2.568e-01]
my_first_lora_v2: 34%|###4 | 1375/4000 [40:17<1:16:56, 1.76s/it, lr: 1.0e-04 loss: 2.568e-01]
my_first_lora_v2: 34%|###4 | 1376/4000 [40:20<1:16:56, 1.76s/it, lr: 1.0e-04 loss: 3.148e-01]
my_first_lora_v2: 34%|###4 | 1376/4000 [40:20<1:16:56, 1.76s/it, lr: 1.0e-04 loss: 3.148e-01]
my_first_lora_v2: 34%|###4 | 1377/4000 [40:21<1:16:52, 1.76s/it, lr: 1.0e-04 loss: 5.080e-01]
my_first_lora_v2: 34%|###4 | 1377/4000 [40:21<1:16:52, 1.76s/it, lr: 1.0e-04 loss: 5.080e-01]
my_first_lora_v2: 34%|###4 | 1378/4000 [40:24<1:16:53, 1.76s/it, lr: 1.0e-04 loss: 4.741e-01]
my_first_lora_v2: 34%|###4 | 1378/4000 [40:24<1:16:53, 1.76s/it, lr: 1.0e-04 loss: 4.741e-01]
my_first_lora_v2: 34%|###4 | 1379/4000 [40:25<1:16:50, 1.76s/it, lr: 1.0e-04 loss: 1.772e-01]
my_first_lora_v2: 34%|###4 | 1379/4000 [40:25<1:16:50, 1.76s/it, lr: 1.0e-04 loss: 1.772e-01]
my_first_lora_v2: 34%|###4 | 1380/4000 [40:26<1:16:46, 1.76s/it, lr: 1.0e-04 loss: 4.763e-01]
my_first_lora_v2: 34%|###4 | 1380/4000 [40:26<1:16:46, 1.76s/it, lr: 1.0e-04 loss: 4.763e-01]
my_first_lora_v2: 35%|###4 | 1381/4000 [40:27<1:16:43, 1.76s/it, lr: 1.0e-04 loss: 1.179e-01]
my_first_lora_v2: 35%|###4 | 1381/4000 [40:27<1:16:43, 1.76s/it, lr: 1.0e-04 loss: 1.179e-01]
my_first_lora_v2: 35%|###4 | 1382/4000 [40:28<1:16:39, 1.76s/it, lr: 1.0e-04 loss: 5.780e-01]
my_first_lora_v2: 35%|###4 | 1382/4000 [40:28<1:16:39, 1.76s/it, lr: 1.0e-04 loss: 5.780e-01]
my_first_lora_v2: 35%|###4 | 1383/4000 [40:29<1:16:36, 1.76s/it, lr: 1.0e-04 loss: 4.483e-01]
my_first_lora_v2: 35%|###4 | 1383/4000 [40:29<1:16:36, 1.76s/it, lr: 1.0e-04 loss: 4.483e-01]
my_first_lora_v2: 35%|###4 | 1384/4000 [40:31<1:16:36, 1.76s/it, lr: 1.0e-04 loss: 7.638e-02]
my_first_lora_v2: 35%|###4 | 1384/4000 [40:31<1:16:36, 1.76s/it, lr: 1.0e-04 loss: 7.638e-02]
my_first_lora_v2: 35%|###4 | 1385/4000 [40:34<1:16:36, 1.76s/it, lr: 1.0e-04 loss: 6.502e-01]
my_first_lora_v2: 35%|###4 | 1385/4000 [40:34<1:16:36, 1.76s/it, lr: 1.0e-04 loss: 6.502e-01]
my_first_lora_v2: 35%|###4 | 1386/4000 [40:37<1:16:37, 1.76s/it, lr: 1.0e-04 loss: 2.261e-01]
my_first_lora_v2: 35%|###4 | 1386/4000 [40:37<1:16:37, 1.76s/it, lr: 1.0e-04 loss: 2.261e-01]
my_first_lora_v2: 35%|###4 | 1387/4000 [40:40<1:16:36, 1.76s/it, lr: 1.0e-04 loss: 1.847e-01]
my_first_lora_v2: 35%|###4 | 1387/4000 [40:40<1:16:36, 1.76s/it, lr: 1.0e-04 loss: 1.847e-01]
my_first_lora_v2: 35%|###4 | 1388/4000 [40:40<1:16:33, 1.76s/it, lr: 1.0e-04 loss: 4.072e-01]
my_first_lora_v2: 35%|###4 | 1388/4000 [40:40<1:16:33, 1.76s/it, lr: 1.0e-04 loss: 4.072e-01]
my_first_lora_v2: 35%|###4 | 1389/4000 [40:41<1:16:29, 1.76s/it, lr: 1.0e-04 loss: 1.294e-01]
my_first_lora_v2: 35%|###4 | 1389/4000 [40:41<1:16:29, 1.76s/it, lr: 1.0e-04 loss: 1.294e-01]
my_first_lora_v2: 35%|###4 | 1390/4000 [40:44<1:16:30, 1.76s/it, lr: 1.0e-04 loss: 3.468e-01]
my_first_lora_v2: 35%|###4 | 1390/4000 [40:44<1:16:30, 1.76s/it, lr: 1.0e-04 loss: 3.468e-01]
my_first_lora_v2: 35%|###4 | 1391/4000 [40:47<1:16:30, 1.76s/it, lr: 1.0e-04 loss: 9.149e-02]
my_first_lora_v2: 35%|###4 | 1391/4000 [40:47<1:16:30, 1.76s/it, lr: 1.0e-04 loss: 9.149e-02]
my_first_lora_v2: 35%|###4 | 1392/4000 [40:50<1:16:30, 1.76s/it, lr: 1.0e-04 loss: 3.691e-01]
my_first_lora_v2: 35%|###4 | 1392/4000 [40:50<1:16:30, 1.76s/it, lr: 1.0e-04 loss: 3.691e-01]
my_first_lora_v2: 35%|###4 | 1393/4000 [40:51<1:16:27, 1.76s/it, lr: 1.0e-04 loss: 5.715e-01]
my_first_lora_v2: 35%|###4 | 1393/4000 [40:51<1:16:27, 1.76s/it, lr: 1.0e-04 loss: 5.715e-01]
my_first_lora_v2: 35%|###4 | 1394/4000 [40:54<1:16:27, 1.76s/it, lr: 1.0e-04 loss: 2.042e-01]
my_first_lora_v2: 35%|###4 | 1394/4000 [40:54<1:16:27, 1.76s/it, lr: 1.0e-04 loss: 2.042e-01]
my_first_lora_v2: 35%|###4 | 1395/4000 [40:54<1:16:24, 1.76s/it, lr: 1.0e-04 loss: 4.312e-01]
my_first_lora_v2: 35%|###4 | 1395/4000 [40:54<1:16:24, 1.76s/it, lr: 1.0e-04 loss: 4.312e-01]
my_first_lora_v2: 35%|###4 | 1396/4000 [40:57<1:16:24, 1.76s/it, lr: 1.0e-04 loss: 9.367e-02]
my_first_lora_v2: 35%|###4 | 1396/4000 [40:57<1:16:24, 1.76s/it, lr: 1.0e-04 loss: 9.367e-02]
my_first_lora_v2: 35%|###4 | 1397/4000 [41:00<1:16:25, 1.76s/it, lr: 1.0e-04 loss: 4.760e-01]
my_first_lora_v2: 35%|###4 | 1397/4000 [41:00<1:16:25, 1.76s/it, lr: 1.0e-04 loss: 4.760e-01]
my_first_lora_v2: 35%|###4 | 1398/4000 [41:01<1:16:21, 1.76s/it, lr: 1.0e-04 loss: 1.730e-01]
my_first_lora_v2: 35%|###4 | 1398/4000 [41:01<1:16:21, 1.76s/it, lr: 1.0e-04 loss: 1.730e-01]
my_first_lora_v2: 35%|###4 | 1399/4000 [41:04<1:16:21, 1.76s/it, lr: 1.0e-04 loss: 5.848e-01]
my_first_lora_v2: 35%|###4 | 1399/4000 [41:04<1:16:21, 1.76s/it, lr: 1.0e-04 loss: 5.848e-01]
my_first_lora_v2: 35%|###5 | 1400/4000 [41:05<1:16:18, 1.76s/it, lr: 1.0e-04 loss: 5.155e-01]
my_first_lora_v2: 35%|###5 | 1400/4000 [41:05<1:16:18, 1.76s/it, lr: 1.0e-04 loss: 5.155e-01]
my_first_lora_v2: 35%|###5 | 1401/4000 [41:07<1:16:18, 1.76s/it, lr: 1.0e-04 loss: 6.112e-01]
my_first_lora_v2: 35%|###5 | 1401/4000 [41:07<1:16:18, 1.76s/it, lr: 1.0e-04 loss: 6.112e-01]
my_first_lora_v2: 35%|###5 | 1402/4000 [41:09<1:16:15, 1.76s/it, lr: 1.0e-04 loss: 6.897e-01]
my_first_lora_v2: 35%|###5 | 1402/4000 [41:09<1:16:15, 1.76s/it, lr: 1.0e-04 loss: 6.897e-01]
my_first_lora_v2: 35%|###5 | 1403/4000 [41:11<1:16:15, 1.76s/it, lr: 1.0e-04 loss: 6.110e-01]
my_first_lora_v2: 35%|###5 | 1403/4000 [41:11<1:16:15, 1.76s/it, lr: 1.0e-04 loss: 6.110e-01]
my_first_lora_v2: 35%|###5 | 1404/4000 [41:14<1:16:15, 1.76s/it, lr: 1.0e-04 loss: 3.452e-01]
my_first_lora_v2: 35%|###5 | 1404/4000 [41:14<1:16:15, 1.76s/it, lr: 1.0e-04 loss: 3.452e-01]
my_first_lora_v2: 35%|###5 | 1405/4000 [41:17<1:16:15, 1.76s/it, lr: 1.0e-04 loss: 7.132e-01]
my_first_lora_v2: 35%|###5 | 1405/4000 [41:17<1:16:15, 1.76s/it, lr: 1.0e-04 loss: 7.132e-01]
my_first_lora_v2: 35%|###5 | 1406/4000 [41:18<1:16:11, 1.76s/it, lr: 1.0e-04 loss: 2.825e-01]
my_first_lora_v2: 35%|###5 | 1406/4000 [41:18<1:16:11, 1.76s/it, lr: 1.0e-04 loss: 2.825e-01]
my_first_lora_v2: 35%|###5 | 1407/4000 [41:18<1:16:08, 1.76s/it, lr: 1.0e-04 loss: 2.677e-01]
my_first_lora_v2: 35%|###5 | 1407/4000 [41:18<1:16:08, 1.76s/it, lr: 1.0e-04 loss: 2.677e-01]
my_first_lora_v2: 35%|###5 | 1408/4000 [41:19<1:16:04, 1.76s/it, lr: 1.0e-04 loss: 5.026e-01]
my_first_lora_v2: 35%|###5 | 1408/4000 [41:19<1:16:04, 1.76s/it, lr: 1.0e-04 loss: 5.026e-01]
my_first_lora_v2: 35%|###5 | 1409/4000 [41:20<1:16:01, 1.76s/it, lr: 1.0e-04 loss: 2.263e-01]
my_first_lora_v2: 35%|###5 | 1409/4000 [41:20<1:16:01, 1.76s/it, lr: 1.0e-04 loss: 2.263e-01]
my_first_lora_v2: 35%|###5 | 1410/4000 [41:21<1:15:57, 1.76s/it, lr: 1.0e-04 loss: 5.251e-01]
my_first_lora_v2: 35%|###5 | 1410/4000 [41:21<1:15:57, 1.76s/it, lr: 1.0e-04 loss: 5.251e-01]
my_first_lora_v2: 35%|###5 | 1411/4000 [41:24<1:15:58, 1.76s/it, lr: 1.0e-04 loss: 1.064e-01]
my_first_lora_v2: 35%|###5 | 1411/4000 [41:24<1:15:58, 1.76s/it, lr: 1.0e-04 loss: 1.064e-01]
my_first_lora_v2: 35%|###5 | 1412/4000 [41:27<1:15:58, 1.76s/it, lr: 1.0e-04 loss: 2.647e-01]
my_first_lora_v2: 35%|###5 | 1412/4000 [41:27<1:15:58, 1.76s/it, lr: 1.0e-04 loss: 2.647e-01]
my_first_lora_v2: 35%|###5 | 1413/4000 [41:28<1:15:55, 1.76s/it, lr: 1.0e-04 loss: 2.138e-01]
my_first_lora_v2: 35%|###5 | 1413/4000 [41:28<1:15:55, 1.76s/it, lr: 1.0e-04 loss: 2.138e-01]
my_first_lora_v2: 35%|###5 | 1414/4000 [41:28<1:15:51, 1.76s/it, lr: 1.0e-04 loss: 5.850e-01]
my_first_lora_v2: 35%|###5 | 1414/4000 [41:28<1:15:51, 1.76s/it, lr: 1.0e-04 loss: 5.850e-01]
my_first_lora_v2: 35%|###5 | 1415/4000 [41:31<1:15:51, 1.76s/it, lr: 1.0e-04 loss: 6.595e-01]
my_first_lora_v2: 35%|###5 | 1415/4000 [41:31<1:15:51, 1.76s/it, lr: 1.0e-04 loss: 6.595e-01]
my_first_lora_v2: 35%|###5 | 1416/4000 [41:34<1:15:51, 1.76s/it, lr: 1.0e-04 loss: 5.694e-01]
my_first_lora_v2: 35%|###5 | 1416/4000 [41:34<1:15:51, 1.76s/it, lr: 1.0e-04 loss: 5.694e-01]
my_first_lora_v2: 35%|###5 | 1417/4000 [41:34<1:15:47, 1.76s/it, lr: 1.0e-04 loss: 6.285e-01]
my_first_lora_v2: 35%|###5 | 1417/4000 [41:34<1:15:47, 1.76s/it, lr: 1.0e-04 loss: 6.285e-01]
my_first_lora_v2: 35%|###5 | 1418/4000 [41:37<1:15:48, 1.76s/it, lr: 1.0e-04 loss: 7.543e-01]
my_first_lora_v2: 35%|###5 | 1418/4000 [41:37<1:15:48, 1.76s/it, lr: 1.0e-04 loss: 7.543e-01]
my_first_lora_v2: 35%|###5 | 1419/4000 [41:38<1:15:44, 1.76s/it, lr: 1.0e-04 loss: 2.222e-01]
my_first_lora_v2: 35%|###5 | 1419/4000 [41:38<1:15:44, 1.76s/it, lr: 1.0e-04 loss: 2.222e-01]
my_first_lora_v2: 36%|###5 | 1420/4000 [41:39<1:15:41, 1.76s/it, lr: 1.0e-04 loss: 7.923e-01]
my_first_lora_v2: 36%|###5 | 1420/4000 [41:39<1:15:41, 1.76s/it, lr: 1.0e-04 loss: 7.923e-01]
my_first_lora_v2: 36%|###5 | 1421/4000 [41:42<1:15:41, 1.76s/it, lr: 1.0e-04 loss: 3.168e-01]
my_first_lora_v2: 36%|###5 | 1421/4000 [41:42<1:15:41, 1.76s/it, lr: 1.0e-04 loss: 3.168e-01]
my_first_lora_v2: 36%|###5 | 1422/4000 [41:43<1:15:38, 1.76s/it, lr: 1.0e-04 loss: 4.716e-01]
my_first_lora_v2: 36%|###5 | 1422/4000 [41:43<1:15:38, 1.76s/it, lr: 1.0e-04 loss: 4.716e-01]
my_first_lora_v2: 36%|###5 | 1423/4000 [41:46<1:15:38, 1.76s/it, lr: 1.0e-04 loss: 3.983e-01]
my_first_lora_v2: 36%|###5 | 1423/4000 [41:46<1:15:38, 1.76s/it, lr: 1.0e-04 loss: 3.983e-01]
my_first_lora_v2: 36%|###5 | 1424/4000 [41:46<1:15:35, 1.76s/it, lr: 1.0e-04 loss: 7.547e-01]
my_first_lora_v2: 36%|###5 | 1424/4000 [41:46<1:15:35, 1.76s/it, lr: 1.0e-04 loss: 7.547e-01]
my_first_lora_v2: 36%|###5 | 1425/4000 [41:48<1:15:32, 1.76s/it, lr: 1.0e-04 loss: 8.451e-01]
my_first_lora_v2: 36%|###5 | 1425/4000 [41:48<1:15:32, 1.76s/it, lr: 1.0e-04 loss: 8.451e-01]
my_first_lora_v2: 36%|###5 | 1426/4000 [41:48<1:15:28, 1.76s/it, lr: 1.0e-04 loss: 2.174e-01]
my_first_lora_v2: 36%|###5 | 1426/4000 [41:48<1:15:28, 1.76s/it, lr: 1.0e-04 loss: 2.174e-01]
my_first_lora_v2: 36%|###5 | 1427/4000 [41:51<1:15:28, 1.76s/it, lr: 1.0e-04 loss: 7.851e-02]
my_first_lora_v2: 36%|###5 | 1427/4000 [41:51<1:15:28, 1.76s/it, lr: 1.0e-04 loss: 7.851e-02]
my_first_lora_v2: 36%|###5 | 1428/4000 [41:52<1:15:25, 1.76s/it, lr: 1.0e-04 loss: 4.886e-01]
my_first_lora_v2: 36%|###5 | 1428/4000 [41:52<1:15:25, 1.76s/it, lr: 1.0e-04 loss: 4.886e-01]
my_first_lora_v2: 36%|###5 | 1429/4000 [41:55<1:15:25, 1.76s/it, lr: 1.0e-04 loss: 4.702e-01]
my_first_lora_v2: 36%|###5 | 1429/4000 [41:55<1:15:25, 1.76s/it, lr: 1.0e-04 loss: 4.702e-01]
my_first_lora_v2: 36%|###5 | 1430/4000 [41:56<1:15:21, 1.76s/it, lr: 1.0e-04 loss: 3.594e-01]
my_first_lora_v2: 36%|###5 | 1430/4000 [41:56<1:15:21, 1.76s/it, lr: 1.0e-04 loss: 3.594e-01]
my_first_lora_v2: 36%|###5 | 1431/4000 [41:56<1:15:18, 1.76s/it, lr: 1.0e-04 loss: 5.912e-01]
my_first_lora_v2: 36%|###5 | 1431/4000 [41:56<1:15:18, 1.76s/it, lr: 1.0e-04 loss: 5.912e-01]
my_first_lora_v2: 36%|###5 | 1432/4000 [41:57<1:15:14, 1.76s/it, lr: 1.0e-04 loss: 3.029e-01]
my_first_lora_v2: 36%|###5 | 1432/4000 [41:57<1:15:14, 1.76s/it, lr: 1.0e-04 loss: 3.029e-01]
my_first_lora_v2: 36%|###5 | 1433/4000 [42:00<1:15:14, 1.76s/it, lr: 1.0e-04 loss: 2.010e-01]
my_first_lora_v2: 36%|###5 | 1433/4000 [42:00<1:15:14, 1.76s/it, lr: 1.0e-04 loss: 2.010e-01]
my_first_lora_v2: 36%|###5 | 1434/4000 [42:02<1:15:14, 1.76s/it, lr: 1.0e-04 loss: 2.034e-01]
my_first_lora_v2: 36%|###5 | 1434/4000 [42:02<1:15:14, 1.76s/it, lr: 1.0e-04 loss: 2.034e-01]
my_first_lora_v2: 36%|###5 | 1435/4000 [42:03<1:15:10, 1.76s/it, lr: 1.0e-04 loss: 3.842e-01]
my_first_lora_v2: 36%|###5 | 1435/4000 [42:03<1:15:10, 1.76s/it, lr: 1.0e-04 loss: 3.842e-01]
my_first_lora_v2: 36%|###5 | 1436/4000 [42:06<1:15:11, 1.76s/it, lr: 1.0e-04 loss: 6.218e-01]
my_first_lora_v2: 36%|###5 | 1436/4000 [42:06<1:15:11, 1.76s/it, lr: 1.0e-04 loss: 6.218e-01]
my_first_lora_v2: 36%|###5 | 1437/4000 [42:09<1:15:11, 1.76s/it, lr: 1.0e-04 loss: 6.564e-01]
my_first_lora_v2: 36%|###5 | 1437/4000 [42:09<1:15:11, 1.76s/it, lr: 1.0e-04 loss: 6.564e-01]
my_first_lora_v2: 36%|###5 | 1438/4000 [42:10<1:15:08, 1.76s/it, lr: 1.0e-04 loss: 5.478e-01]
my_first_lora_v2: 36%|###5 | 1438/4000 [42:10<1:15:08, 1.76s/it, lr: 1.0e-04 loss: 5.478e-01]
my_first_lora_v2: 36%|###5 | 1439/4000 [42:13<1:15:09, 1.76s/it, lr: 1.0e-04 loss: 4.849e-01]
my_first_lora_v2: 36%|###5 | 1439/4000 [42:13<1:15:09, 1.76s/it, lr: 1.0e-04 loss: 4.849e-01]
my_first_lora_v2: 36%|###6 | 1440/4000 [42:14<1:15:05, 1.76s/it, lr: 1.0e-04 loss: 6.384e-01]
my_first_lora_v2: 36%|###6 | 1440/4000 [42:14<1:15:05, 1.76s/it, lr: 1.0e-04 loss: 6.384e-01]
my_first_lora_v2: 36%|###6 | 1441/4000 [42:17<1:15:05, 1.76s/it, lr: 1.0e-04 loss: 5.069e-01]
my_first_lora_v2: 36%|###6 | 1441/4000 [42:17<1:15:05, 1.76s/it, lr: 1.0e-04 loss: 5.069e-01]
my_first_lora_v2: 36%|###6 | 1442/4000 [42:20<1:15:06, 1.76s/it, lr: 1.0e-04 loss: 3.443e-01]
my_first_lora_v2: 36%|###6 | 1442/4000 [42:20<1:15:06, 1.76s/it, lr: 1.0e-04 loss: 3.443e-01]
my_first_lora_v2: 36%|###6 | 1443/4000 [42:23<1:15:06, 1.76s/it, lr: 1.0e-04 loss: 5.688e-01]
my_first_lora_v2: 36%|###6 | 1443/4000 [42:23<1:15:06, 1.76s/it, lr: 1.0e-04 loss: 5.688e-01]
my_first_lora_v2: 36%|###6 | 1444/4000 [42:24<1:15:03, 1.76s/it, lr: 1.0e-04 loss: 3.362e-01]
my_first_lora_v2: 36%|###6 | 1444/4000 [42:24<1:15:03, 1.76s/it, lr: 1.0e-04 loss: 3.362e-01]
my_first_lora_v2: 36%|###6 | 1445/4000 [42:27<1:15:04, 1.76s/it, lr: 1.0e-04 loss: 7.900e-01]
my_first_lora_v2: 36%|###6 | 1445/4000 [42:27<1:15:04, 1.76s/it, lr: 1.0e-04 loss: 7.900e-01]
my_first_lora_v2: 36%|###6 | 1446/4000 [42:30<1:15:03, 1.76s/it, lr: 1.0e-04 loss: 7.008e-01]
my_first_lora_v2: 36%|###6 | 1446/4000 [42:30<1:15:03, 1.76s/it, lr: 1.0e-04 loss: 7.008e-01]
my_first_lora_v2: 36%|###6 | 1447/4000 [42:30<1:15:00, 1.76s/it, lr: 1.0e-04 loss: 1.544e-02]
my_first_lora_v2: 36%|###6 | 1447/4000 [42:30<1:15:00, 1.76s/it, lr: 1.0e-04 loss: 1.544e-02]
my_first_lora_v2: 36%|###6 | 1448/4000 [42:31<1:14:57, 1.76s/it, lr: 1.0e-04 loss: 7.367e-01]
my_first_lora_v2: 36%|###6 | 1448/4000 [42:31<1:14:57, 1.76s/it, lr: 1.0e-04 loss: 7.367e-01]
my_first_lora_v2: 36%|###6 | 1449/4000 [42:32<1:14:53, 1.76s/it, lr: 1.0e-04 loss: 5.730e-01]
my_first_lora_v2: 36%|###6 | 1449/4000 [42:32<1:14:53, 1.76s/it, lr: 1.0e-04 loss: 5.730e-01]
my_first_lora_v2: 36%|###6 | 1450/4000 [42:35<1:14:53, 1.76s/it, lr: 1.0e-04 loss: 1.552e-01]
my_first_lora_v2: 36%|###6 | 1450/4000 [42:35<1:14:53, 1.76s/it, lr: 1.0e-04 loss: 1.552e-01]
my_first_lora_v2: 36%|###6 | 1451/4000 [42:36<1:14:50, 1.76s/it, lr: 1.0e-04 loss: 3.023e-01]
my_first_lora_v2: 36%|###6 | 1451/4000 [42:36<1:14:50, 1.76s/it, lr: 1.0e-04 loss: 3.023e-01]
my_first_lora_v2: 36%|###6 | 1452/4000 [42:39<1:14:50, 1.76s/it, lr: 1.0e-04 loss: 2.249e-01]
my_first_lora_v2: 36%|###6 | 1452/4000 [42:39<1:14:50, 1.76s/it, lr: 1.0e-04 loss: 2.249e-01]
my_first_lora_v2: 36%|###6 | 1453/4000 [42:40<1:14:47, 1.76s/it, lr: 1.0e-04 loss: 4.426e-01]
my_first_lora_v2: 36%|###6 | 1453/4000 [42:40<1:14:47, 1.76s/it, lr: 1.0e-04 loss: 4.426e-01]
my_first_lora_v2: 36%|###6 | 1454/4000 [42:40<1:14:44, 1.76s/it, lr: 1.0e-04 loss: 1.402e-01]
my_first_lora_v2: 36%|###6 | 1454/4000 [42:40<1:14:44, 1.76s/it, lr: 1.0e-04 loss: 1.402e-01]
my_first_lora_v2: 36%|###6 | 1455/4000 [42:41<1:14:40, 1.76s/it, lr: 1.0e-04 loss: 4.083e-01]
my_first_lora_v2: 36%|###6 | 1455/4000 [42:41<1:14:40, 1.76s/it, lr: 1.0e-04 loss: 4.083e-01]
my_first_lora_v2: 36%|###6 | 1456/4000 [42:44<1:14:40, 1.76s/it, lr: 1.0e-04 loss: 1.653e-01]
my_first_lora_v2: 36%|###6 | 1456/4000 [42:44<1:14:40, 1.76s/it, lr: 1.0e-04 loss: 1.653e-01]
my_first_lora_v2: 36%|###6 | 1457/4000 [42:47<1:14:40, 1.76s/it, lr: 1.0e-04 loss: 2.651e-01]
my_first_lora_v2: 36%|###6 | 1457/4000 [42:47<1:14:40, 1.76s/it, lr: 1.0e-04 loss: 2.651e-01]
my_first_lora_v2: 36%|###6 | 1458/4000 [42:47<1:14:36, 1.76s/it, lr: 1.0e-04 loss: 1.007e-01]
my_first_lora_v2: 36%|###6 | 1458/4000 [42:47<1:14:36, 1.76s/it, lr: 1.0e-04 loss: 1.007e-01]
my_first_lora_v2: 36%|###6 | 1459/4000 [42:48<1:14:33, 1.76s/it, lr: 1.0e-04 loss: 3.720e-01]
my_first_lora_v2: 36%|###6 | 1459/4000 [42:48<1:14:33, 1.76s/it, lr: 1.0e-04 loss: 3.720e-01]
my_first_lora_v2: 36%|###6 | 1460/4000 [42:49<1:14:30, 1.76s/it, lr: 1.0e-04 loss: 2.073e-01]
my_first_lora_v2: 36%|###6 | 1460/4000 [42:49<1:14:30, 1.76s/it, lr: 1.0e-04 loss: 2.073e-01]
my_first_lora_v2: 37%|###6 | 1461/4000 [42:50<1:14:26, 1.76s/it, lr: 1.0e-04 loss: 1.694e-01]
my_first_lora_v2: 37%|###6 | 1461/4000 [42:50<1:14:26, 1.76s/it, lr: 1.0e-04 loss: 1.694e-01]
my_first_lora_v2: 37%|###6 | 1462/4000 [42:51<1:14:23, 1.76s/it, lr: 1.0e-04 loss: 1.944e-01]
my_first_lora_v2: 37%|###6 | 1462/4000 [42:51<1:14:23, 1.76s/it, lr: 1.0e-04 loss: 1.944e-01]
my_first_lora_v2: 37%|###6 | 1463/4000 [42:53<1:14:23, 1.76s/it, lr: 1.0e-04 loss: 2.663e-01]
my_first_lora_v2: 37%|###6 | 1463/4000 [42:53<1:14:23, 1.76s/it, lr: 1.0e-04 loss: 2.663e-01]
my_first_lora_v2: 37%|###6 | 1464/4000 [42:56<1:14:23, 1.76s/it, lr: 1.0e-04 loss: 4.460e-01]
my_first_lora_v2: 37%|###6 | 1464/4000 [42:56<1:14:23, 1.76s/it, lr: 1.0e-04 loss: 4.460e-01]
my_first_lora_v2: 37%|###6 | 1465/4000 [42:59<1:14:23, 1.76s/it, lr: 1.0e-04 loss: 5.688e-01]
my_first_lora_v2: 37%|###6 | 1465/4000 [42:59<1:14:23, 1.76s/it, lr: 1.0e-04 loss: 5.688e-01]
my_first_lora_v2: 37%|###6 | 1466/4000 [43:00<1:14:20, 1.76s/it, lr: 1.0e-04 loss: 7.548e-02]
my_first_lora_v2: 37%|###6 | 1466/4000 [43:00<1:14:20, 1.76s/it, lr: 1.0e-04 loss: 7.548e-02]
my_first_lora_v2: 37%|###6 | 1467/4000 [43:03<1:14:20, 1.76s/it, lr: 1.0e-04 loss: 1.297e-01]
my_first_lora_v2: 37%|###6 | 1467/4000 [43:03<1:14:20, 1.76s/it, lr: 1.0e-04 loss: 1.297e-01]
my_first_lora_v2: 37%|###6 | 1468/4000 [43:04<1:14:17, 1.76s/it, lr: 1.0e-04 loss: 4.202e-01]
my_first_lora_v2: 37%|###6 | 1468/4000 [43:04<1:14:17, 1.76s/it, lr: 1.0e-04 loss: 4.202e-01]
my_first_lora_v2: 37%|###6 | 1469/4000 [43:07<1:14:17, 1.76s/it, lr: 1.0e-04 loss: 4.113e-01]
my_first_lora_v2: 37%|###6 | 1469/4000 [43:07<1:14:17, 1.76s/it, lr: 1.0e-04 loss: 4.113e-01]
my_first_lora_v2: 37%|###6 | 1470/4000 [43:07<1:14:13, 1.76s/it, lr: 1.0e-04 loss: 5.450e-01]
my_first_lora_v2: 37%|###6 | 1470/4000 [43:07<1:14:13, 1.76s/it, lr: 1.0e-04 loss: 5.450e-01]
my_first_lora_v2: 37%|###6 | 1471/4000 [43:08<1:14:10, 1.76s/it, lr: 1.0e-04 loss: 6.488e-01]
my_first_lora_v2: 37%|###6 | 1471/4000 [43:08<1:14:10, 1.76s/it, lr: 1.0e-04 loss: 6.488e-01]
my_first_lora_v2: 37%|###6 | 1472/4000 [43:09<1:14:07, 1.76s/it, lr: 1.0e-04 loss: 1.502e-01]
my_first_lora_v2: 37%|###6 | 1472/4000 [43:09<1:14:07, 1.76s/it, lr: 1.0e-04 loss: 1.502e-01]
my_first_lora_v2: 37%|###6 | 1473/4000 [43:10<1:14:03, 1.76s/it, lr: 1.0e-04 loss: 3.369e-01]
my_first_lora_v2: 37%|###6 | 1473/4000 [43:10<1:14:03, 1.76s/it, lr: 1.0e-04 loss: 3.369e-01]
my_first_lora_v2: 37%|###6 | 1474/4000 [43:11<1:14:00, 1.76s/it, lr: 1.0e-04 loss: 2.140e-01]
my_first_lora_v2: 37%|###6 | 1474/4000 [43:11<1:14:00, 1.76s/it, lr: 1.0e-04 loss: 2.140e-01]
my_first_lora_v2: 37%|###6 | 1475/4000 [43:13<1:14:00, 1.76s/it, lr: 1.0e-04 loss: 5.673e-01]
my_first_lora_v2: 37%|###6 | 1475/4000 [43:13<1:14:00, 1.76s/it, lr: 1.0e-04 loss: 5.673e-01]
my_first_lora_v2: 37%|###6 | 1476/4000 [43:14<1:13:57, 1.76s/it, lr: 1.0e-04 loss: 3.692e-01]
my_first_lora_v2: 37%|###6 | 1476/4000 [43:14<1:13:57, 1.76s/it, lr: 1.0e-04 loss: 3.692e-01]
my_first_lora_v2: 37%|###6 | 1477/4000 [43:15<1:13:53, 1.76s/it, lr: 1.0e-04 loss: 8.366e-01]
my_first_lora_v2: 37%|###6 | 1477/4000 [43:15<1:13:53, 1.76s/it, lr: 1.0e-04 loss: 8.366e-01]
my_first_lora_v2: 37%|###6 | 1478/4000 [43:16<1:13:50, 1.76s/it, lr: 1.0e-04 loss: 6.734e-01]
my_first_lora_v2: 37%|###6 | 1478/4000 [43:16<1:13:50, 1.76s/it, lr: 1.0e-04 loss: 6.734e-01]
my_first_lora_v2: 37%|###6 | 1479/4000 [43:17<1:13:47, 1.76s/it, lr: 1.0e-04 loss: 5.386e-01]
my_first_lora_v2: 37%|###6 | 1479/4000 [43:17<1:13:47, 1.76s/it, lr: 1.0e-04 loss: 5.386e-01]
my_first_lora_v2: 37%|###7 | 1480/4000 [43:18<1:13:44, 1.76s/it, lr: 1.0e-04 loss: 4.827e-01]
my_first_lora_v2: 37%|###7 | 1480/4000 [43:18<1:13:44, 1.76s/it, lr: 1.0e-04 loss: 4.827e-01]
my_first_lora_v2: 37%|###7 | 1481/4000 [43:19<1:13:40, 1.76s/it, lr: 1.0e-04 loss: 7.061e-01]
my_first_lora_v2: 37%|###7 | 1481/4000 [43:19<1:13:40, 1.76s/it, lr: 1.0e-04 loss: 7.061e-01]
my_first_lora_v2: 37%|###7 | 1482/4000 [43:21<1:13:40, 1.76s/it, lr: 1.0e-04 loss: 3.902e-01]
my_first_lora_v2: 37%|###7 | 1482/4000 [43:21<1:13:40, 1.76s/it, lr: 1.0e-04 loss: 3.902e-01]
my_first_lora_v2: 37%|###7 | 1483/4000 [43:24<1:13:40, 1.76s/it, lr: 1.0e-04 loss: 1.196e-01]
my_first_lora_v2: 37%|###7 | 1483/4000 [43:24<1:13:40, 1.76s/it, lr: 1.0e-04 loss: 1.196e-01]
my_first_lora_v2: 37%|###7 | 1484/4000 [43:25<1:13:37, 1.76s/it, lr: 1.0e-04 loss: 5.747e-01]
my_first_lora_v2: 37%|###7 | 1484/4000 [43:25<1:13:37, 1.76s/it, lr: 1.0e-04 loss: 5.747e-01]
my_first_lora_v2: 37%|###7 | 1485/4000 [43:26<1:13:34, 1.76s/it, lr: 1.0e-04 loss: 2.727e-01]
my_first_lora_v2: 37%|###7 | 1485/4000 [43:26<1:13:34, 1.76s/it, lr: 1.0e-04 loss: 2.727e-01]
my_first_lora_v2: 37%|###7 | 1486/4000 [43:29<1:13:34, 1.76s/it, lr: 1.0e-04 loss: 3.215e-01]
my_first_lora_v2: 37%|###7 | 1486/4000 [43:29<1:13:34, 1.76s/it, lr: 1.0e-04 loss: 3.215e-01]
my_first_lora_v2: 37%|###7 | 1487/4000 [43:29<1:13:30, 1.76s/it, lr: 1.0e-04 loss: 4.122e-01]
my_first_lora_v2: 37%|###7 | 1487/4000 [43:29<1:13:30, 1.76s/it, lr: 1.0e-04 loss: 4.122e-01]
my_first_lora_v2: 37%|###7 | 1488/4000 [43:32<1:13:30, 1.76s/it, lr: 1.0e-04 loss: 3.607e-01]
my_first_lora_v2: 37%|###7 | 1488/4000 [43:32<1:13:30, 1.76s/it, lr: 1.0e-04 loss: 3.607e-01]
my_first_lora_v2: 37%|###7 | 1489/4000 [43:35<1:13:30, 1.76s/it, lr: 1.0e-04 loss: 1.009e-01]
my_first_lora_v2: 37%|###7 | 1489/4000 [43:35<1:13:30, 1.76s/it, lr: 1.0e-04 loss: 1.009e-01]
my_first_lora_v2: 37%|###7 | 1490/4000 [43:36<1:13:27, 1.76s/it, lr: 1.0e-04 loss: 7.113e-01]
my_first_lora_v2: 37%|###7 | 1490/4000 [43:36<1:13:27, 1.76s/it, lr: 1.0e-04 loss: 7.113e-01]
my_first_lora_v2: 37%|###7 | 1491/4000 [43:37<1:13:23, 1.76s/it, lr: 1.0e-04 loss: 7.436e-02]
my_first_lora_v2: 37%|###7 | 1491/4000 [43:37<1:13:23, 1.76s/it, lr: 1.0e-04 loss: 7.436e-02]
my_first_lora_v2: 37%|###7 | 1492/4000 [43:39<1:13:23, 1.76s/it, lr: 1.0e-04 loss: 4.179e-01]
my_first_lora_v2: 37%|###7 | 1492/4000 [43:39<1:13:23, 1.76s/it, lr: 1.0e-04 loss: 4.179e-01]
my_first_lora_v2: 37%|###7 | 1493/4000 [43:42<1:13:23, 1.76s/it, lr: 1.0e-04 loss: 7.257e-01]
my_first_lora_v2: 37%|###7 | 1493/4000 [43:42<1:13:23, 1.76s/it, lr: 1.0e-04 loss: 7.257e-01]
my_first_lora_v2: 37%|###7 | 1494/4000 [43:45<1:13:23, 1.76s/it, lr: 1.0e-04 loss: 6.321e-01]
my_first_lora_v2: 37%|###7 | 1494/4000 [43:45<1:13:23, 1.76s/it, lr: 1.0e-04 loss: 6.321e-01]
my_first_lora_v2: 37%|###7 | 1495/4000 [43:48<1:13:23, 1.76s/it, lr: 1.0e-04 loss: 4.504e-01]
my_first_lora_v2: 37%|###7 | 1495/4000 [43:48<1:13:23, 1.76s/it, lr: 1.0e-04 loss: 4.504e-01]
my_first_lora_v2: 37%|###7 | 1496/4000 [43:50<1:13:23, 1.76s/it, lr: 1.0e-04 loss: 4.317e-01]
my_first_lora_v2: 37%|###7 | 1496/4000 [43:50<1:13:23, 1.76s/it, lr: 1.0e-04 loss: 4.317e-01]
my_first_lora_v2: 37%|###7 | 1497/4000 [43:53<1:13:22, 1.76s/it, lr: 1.0e-04 loss: 4.410e-01]
my_first_lora_v2: 37%|###7 | 1497/4000 [43:53<1:13:22, 1.76s/it, lr: 1.0e-04 loss: 4.410e-01]
my_first_lora_v2: 37%|###7 | 1498/4000 [43:56<1:13:22, 1.76s/it, lr: 1.0e-04 loss: 6.847e-01]
my_first_lora_v2: 37%|###7 | 1498/4000 [43:56<1:13:22, 1.76s/it, lr: 1.0e-04 loss: 6.847e-01]
my_first_lora_v2: 37%|###7 | 1499/4000 [43:57<1:13:19, 1.76s/it, lr: 1.0e-04 loss: 5.169e-01]
my_first_lora_v2: 37%|###7 | 1499/4000 [43:57<1:13:19, 1.76s/it, lr: 1.0e-04 loss: 5.169e-01] |
| Saving at step 1500 |
| Saved checkpoint to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v2/my_first_lora_v2_000001500.safetensors |
| Saved optimizer to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v2/optimizer.pt |
| Removing old save: /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v2/my_first_lora_v2_000000500.safetensors |
| Unloading assistant lora |
|
|
|
|
|
Generating Images: 0%| | 0/3 [00:00<?, ?it/s]
Generating Images: 0%| | 0/3 [00:00<?, ?it/s][A[A |
|
|
|
Generating Images: 33%|###3 | 1/3 [00:07<00:15, 7.82s/it]
Generating Images: 33%|###3 | 1/3 [00:07<00:15, 7.82s/it][A[A |
|
|
|
Generating Images: 67%|######6 | 2/3 [00:15<00:07, 7.73s/it]
Generating Images: 67%|######6 | 2/3 [00:15<00:07, 7.73s/it][A[A |
|
|
|
Generating Images: 100%|##########| 3/3 [00:23<00:00, 7.68s/it]
Generating Images: 100%|##########| 3/3 [00:23<00:00, 7.68s/it][A[A |
|
|
|
[A[ALoading assistant lora |
|
my_first_lora_v2: 38%|###7 | 1500/4000 [44:00<1:13:20, 1.76s/it, lr: 1.0e-04 loss: 3.685e-01]
my_first_lora_v2: 38%|###7 | 1500/4000 [44:00<1:13:20, 1.76s/it, lr: 1.0e-04 loss: 3.685e-01]
my_first_lora_v2: 38%|###7 | 1501/4000 [44:02<1:13:19, 1.76s/it, lr: 1.0e-04 loss: 3.496e-01]
my_first_lora_v2: 38%|###7 | 1501/4000 [44:02<1:13:19, 1.76s/it, lr: 1.0e-04 loss: 3.496e-01]
my_first_lora_v2: 38%|###7 | 1502/4000 [44:05<1:13:19, 1.76s/it, lr: 1.0e-04 loss: 2.860e-01]
my_first_lora_v2: 38%|###7 | 1502/4000 [44:05<1:13:19, 1.76s/it, lr: 1.0e-04 loss: 2.860e-01]
my_first_lora_v2: 38%|###7 | 1503/4000 [44:06<1:13:15, 1.76s/it, lr: 1.0e-04 loss: 4.472e-01]
my_first_lora_v2: 38%|###7 | 1503/4000 [44:06<1:13:15, 1.76s/it, lr: 1.0e-04 loss: 4.472e-01]
my_first_lora_v2: 38%|###7 | 1504/4000 [44:06<1:13:12, 1.76s/it, lr: 1.0e-04 loss: 6.098e-01]
my_first_lora_v2: 38%|###7 | 1504/4000 [44:06<1:13:12, 1.76s/it, lr: 1.0e-04 loss: 6.098e-01]
my_first_lora_v2: 38%|###7 | 1505/4000 [44:09<1:13:12, 1.76s/it, lr: 1.0e-04 loss: 4.131e-02]
my_first_lora_v2: 38%|###7 | 1505/4000 [44:09<1:13:12, 1.76s/it, lr: 1.0e-04 loss: 4.131e-02]
my_first_lora_v2: 38%|###7 | 1506/4000 [44:12<1:13:12, 1.76s/it, lr: 1.0e-04 loss: 8.970e-02]
my_first_lora_v2: 38%|###7 | 1506/4000 [44:12<1:13:12, 1.76s/it, lr: 1.0e-04 loss: 8.970e-02]
my_first_lora_v2: 38%|###7 | 1507/4000 [44:15<1:13:12, 1.76s/it, lr: 1.0e-04 loss: 1.685e-01]
my_first_lora_v2: 38%|###7 | 1507/4000 [44:15<1:13:12, 1.76s/it, lr: 1.0e-04 loss: 1.685e-01]
my_first_lora_v2: 38%|###7 | 1508/4000 [44:18<1:13:12, 1.76s/it, lr: 1.0e-04 loss: 3.869e-01]
my_first_lora_v2: 38%|###7 | 1508/4000 [44:18<1:13:12, 1.76s/it, lr: 1.0e-04 loss: 3.869e-01]
my_first_lora_v2: 38%|###7 | 1509/4000 [44:21<1:13:13, 1.76s/it, lr: 1.0e-04 loss: 3.792e-01]
my_first_lora_v2: 38%|###7 | 1509/4000 [44:21<1:13:13, 1.76s/it, lr: 1.0e-04 loss: 3.792e-01]
my_first_lora_v2: 38%|###7 | 1510/4000 [44:23<1:13:12, 1.76s/it, lr: 1.0e-04 loss: 7.099e-01]
my_first_lora_v2: 38%|###7 | 1510/4000 [44:23<1:13:12, 1.76s/it, lr: 1.0e-04 loss: 7.099e-01]
my_first_lora_v2: 38%|###7 | 1511/4000 [44:24<1:13:09, 1.76s/it, lr: 1.0e-04 loss: 6.422e-02]
my_first_lora_v2: 38%|###7 | 1511/4000 [44:24<1:13:09, 1.76s/it, lr: 1.0e-04 loss: 6.422e-02]
my_first_lora_v2: 38%|###7 | 1512/4000 [44:27<1:13:09, 1.76s/it, lr: 1.0e-04 loss: 5.370e-01]
my_first_lora_v2: 38%|###7 | 1512/4000 [44:27<1:13:09, 1.76s/it, lr: 1.0e-04 loss: 5.370e-01]
my_first_lora_v2: 38%|###7 | 1513/4000 [44:29<1:13:08, 1.76s/it, lr: 1.0e-04 loss: 6.547e-01]
my_first_lora_v2: 38%|###7 | 1513/4000 [44:29<1:13:08, 1.76s/it, lr: 1.0e-04 loss: 6.547e-01]
my_first_lora_v2: 38%|###7 | 1514/4000 [44:32<1:13:08, 1.77s/it, lr: 1.0e-04 loss: 1.030e-01]
my_first_lora_v2: 38%|###7 | 1514/4000 [44:32<1:13:08, 1.77s/it, lr: 1.0e-04 loss: 1.030e-01]
my_first_lora_v2: 38%|###7 | 1515/4000 [44:35<1:13:08, 1.77s/it, lr: 1.0e-04 loss: 7.566e-01]
my_first_lora_v2: 38%|###7 | 1515/4000 [44:35<1:13:08, 1.77s/it, lr: 1.0e-04 loss: 7.566e-01]
my_first_lora_v2: 38%|###7 | 1516/4000 [44:36<1:13:05, 1.77s/it, lr: 1.0e-04 loss: 3.815e-01]
my_first_lora_v2: 38%|###7 | 1516/4000 [44:36<1:13:05, 1.77s/it, lr: 1.0e-04 loss: 3.815e-01]
my_first_lora_v2: 38%|###7 | 1517/4000 [44:39<1:13:05, 1.77s/it, lr: 1.0e-04 loss: 3.594e-01]
my_first_lora_v2: 38%|###7 | 1517/4000 [44:39<1:13:05, 1.77s/it, lr: 1.0e-04 loss: 3.594e-01]
my_first_lora_v2: 38%|###7 | 1518/4000 [44:40<1:13:03, 1.77s/it, lr: 1.0e-04 loss: 6.561e-01]
my_first_lora_v2: 38%|###7 | 1518/4000 [44:40<1:13:03, 1.77s/it, lr: 1.0e-04 loss: 6.561e-01]
my_first_lora_v2: 38%|###7 | 1519/4000 [44:41<1:12:59, 1.77s/it, lr: 1.0e-04 loss: 6.451e-01]
my_first_lora_v2: 38%|###7 | 1519/4000 [44:41<1:12:59, 1.77s/it, lr: 1.0e-04 loss: 6.451e-01]
my_first_lora_v2: 38%|###8 | 1520/4000 [44:42<1:12:56, 1.76s/it, lr: 1.0e-04 loss: 2.736e-01]
my_first_lora_v2: 38%|###8 | 1520/4000 [44:42<1:12:56, 1.76s/it, lr: 1.0e-04 loss: 2.736e-01]
my_first_lora_v2: 38%|###8 | 1521/4000 [44:45<1:12:56, 1.77s/it, lr: 1.0e-04 loss: 5.153e-01]
my_first_lora_v2: 38%|###8 | 1521/4000 [44:45<1:12:56, 1.77s/it, lr: 1.0e-04 loss: 5.153e-01]
my_first_lora_v2: 38%|###8 | 1522/4000 [44:46<1:12:53, 1.76s/it, lr: 1.0e-04 loss: 1.766e-01]
my_first_lora_v2: 38%|###8 | 1522/4000 [44:46<1:12:53, 1.76s/it, lr: 1.0e-04 loss: 1.766e-01]
my_first_lora_v2: 38%|###8 | 1523/4000 [44:48<1:12:52, 1.77s/it, lr: 1.0e-04 loss: 3.226e-01]
my_first_lora_v2: 38%|###8 | 1523/4000 [44:48<1:12:52, 1.77s/it, lr: 1.0e-04 loss: 3.226e-01]
my_first_lora_v2: 38%|###8 | 1524/4000 [44:49<1:12:49, 1.76s/it, lr: 1.0e-04 loss: 3.845e-01]
my_first_lora_v2: 38%|###8 | 1524/4000 [44:49<1:12:49, 1.76s/it, lr: 1.0e-04 loss: 3.845e-01]
my_first_lora_v2: 38%|###8 | 1525/4000 [44:50<1:12:46, 1.76s/it, lr: 1.0e-04 loss: 2.844e-01]
my_first_lora_v2: 38%|###8 | 1525/4000 [44:50<1:12:46, 1.76s/it, lr: 1.0e-04 loss: 2.844e-01]
my_first_lora_v2: 38%|###8 | 1526/4000 [44:51<1:12:42, 1.76s/it, lr: 1.0e-04 loss: 4.819e-01]
my_first_lora_v2: 38%|###8 | 1526/4000 [44:51<1:12:42, 1.76s/it, lr: 1.0e-04 loss: 4.819e-01]
my_first_lora_v2: 38%|###8 | 1527/4000 [44:52<1:12:40, 1.76s/it, lr: 1.0e-04 loss: 2.087e-01]
my_first_lora_v2: 38%|###8 | 1527/4000 [44:52<1:12:40, 1.76s/it, lr: 1.0e-04 loss: 2.087e-01]
my_first_lora_v2: 38%|###8 | 1528/4000 [44:55<1:12:40, 1.76s/it, lr: 1.0e-04 loss: 6.211e-01]
my_first_lora_v2: 38%|###8 | 1528/4000 [44:55<1:12:40, 1.76s/it, lr: 1.0e-04 loss: 6.211e-01]
my_first_lora_v2: 38%|###8 | 1529/4000 [44:55<1:12:36, 1.76s/it, lr: 1.0e-04 loss: 5.572e-01]
my_first_lora_v2: 38%|###8 | 1529/4000 [44:55<1:12:36, 1.76s/it, lr: 1.0e-04 loss: 5.572e-01]
my_first_lora_v2: 38%|###8 | 1530/4000 [44:56<1:12:33, 1.76s/it, lr: 1.0e-04 loss: 2.225e-01]
my_first_lora_v2: 38%|###8 | 1530/4000 [44:56<1:12:33, 1.76s/it, lr: 1.0e-04 loss: 2.225e-01]
my_first_lora_v2: 38%|###8 | 1531/4000 [44:59<1:12:33, 1.76s/it, lr: 1.0e-04 loss: 7.777e-01]
my_first_lora_v2: 38%|###8 | 1531/4000 [44:59<1:12:33, 1.76s/it, lr: 1.0e-04 loss: 7.777e-01]
my_first_lora_v2: 38%|###8 | 1532/4000 [45:00<1:12:30, 1.76s/it, lr: 1.0e-04 loss: 1.100e-01]
my_first_lora_v2: 38%|###8 | 1532/4000 [45:00<1:12:30, 1.76s/it, lr: 1.0e-04 loss: 1.100e-01]
my_first_lora_v2: 38%|###8 | 1533/4000 [45:01<1:12:27, 1.76s/it, lr: 1.0e-04 loss: 3.562e-01]
my_first_lora_v2: 38%|###8 | 1533/4000 [45:01<1:12:27, 1.76s/it, lr: 1.0e-04 loss: 3.562e-01]
my_first_lora_v2: 38%|###8 | 1534/4000 [45:04<1:12:27, 1.76s/it, lr: 1.0e-04 loss: 3.755e-01]
my_first_lora_v2: 38%|###8 | 1534/4000 [45:04<1:12:27, 1.76s/it, lr: 1.0e-04 loss: 3.755e-01]
my_first_lora_v2: 38%|###8 | 1535/4000 [45:07<1:12:27, 1.76s/it, lr: 1.0e-04 loss: 5.736e-01]
my_first_lora_v2: 38%|###8 | 1535/4000 [45:07<1:12:27, 1.76s/it, lr: 1.0e-04 loss: 5.736e-01]
my_first_lora_v2: 38%|###8 | 1536/4000 [45:09<1:12:26, 1.76s/it, lr: 1.0e-04 loss: 6.829e-01]
my_first_lora_v2: 38%|###8 | 1536/4000 [45:09<1:12:26, 1.76s/it, lr: 1.0e-04 loss: 6.829e-01]
my_first_lora_v2: 38%|###8 | 1537/4000 [45:10<1:12:23, 1.76s/it, lr: 1.0e-04 loss: 6.262e-01]
my_first_lora_v2: 38%|###8 | 1537/4000 [45:10<1:12:23, 1.76s/it, lr: 1.0e-04 loss: 6.262e-01]
my_first_lora_v2: 38%|###8 | 1538/4000 [45:11<1:12:19, 1.76s/it, lr: 1.0e-04 loss: 1.334e-01]
my_first_lora_v2: 38%|###8 | 1538/4000 [45:11<1:12:19, 1.76s/it, lr: 1.0e-04 loss: 1.334e-01]
my_first_lora_v2: 38%|###8 | 1539/4000 [45:11<1:12:16, 1.76s/it, lr: 1.0e-04 loss: 7.584e-02]
my_first_lora_v2: 38%|###8 | 1539/4000 [45:11<1:12:16, 1.76s/it, lr: 1.0e-04 loss: 7.584e-02]
my_first_lora_v2: 38%|###8 | 1540/4000 [45:14<1:12:16, 1.76s/it, lr: 1.0e-04 loss: 7.521e-02]
my_first_lora_v2: 38%|###8 | 1540/4000 [45:14<1:12:16, 1.76s/it, lr: 1.0e-04 loss: 7.521e-02]
my_first_lora_v2: 39%|###8 | 1541/4000 [45:15<1:12:13, 1.76s/it, lr: 1.0e-04 loss: 5.767e-01]
my_first_lora_v2: 39%|###8 | 1541/4000 [45:15<1:12:13, 1.76s/it, lr: 1.0e-04 loss: 5.767e-01]
my_first_lora_v2: 39%|###8 | 1542/4000 [45:18<1:12:13, 1.76s/it, lr: 1.0e-04 loss: 2.977e-01]
my_first_lora_v2: 39%|###8 | 1542/4000 [45:18<1:12:13, 1.76s/it, lr: 1.0e-04 loss: 2.977e-01]
my_first_lora_v2: 39%|###8 | 1543/4000 [45:19<1:12:10, 1.76s/it, lr: 1.0e-04 loss: 4.596e-01]
my_first_lora_v2: 39%|###8 | 1543/4000 [45:19<1:12:10, 1.76s/it, lr: 1.0e-04 loss: 4.596e-01]
my_first_lora_v2: 39%|###8 | 1544/4000 [45:22<1:12:09, 1.76s/it, lr: 1.0e-04 loss: 6.009e-01]
my_first_lora_v2: 39%|###8 | 1544/4000 [45:22<1:12:09, 1.76s/it, lr: 1.0e-04 loss: 6.009e-01]
my_first_lora_v2: 39%|###8 | 1545/4000 [45:22<1:12:06, 1.76s/it, lr: 1.0e-04 loss: 7.883e-01]
my_first_lora_v2: 39%|###8 | 1545/4000 [45:22<1:12:06, 1.76s/it, lr: 1.0e-04 loss: 7.883e-01]
my_first_lora_v2: 39%|###8 | 1546/4000 [45:23<1:12:03, 1.76s/it, lr: 1.0e-04 loss: 3.614e-01]
my_first_lora_v2: 39%|###8 | 1546/4000 [45:23<1:12:03, 1.76s/it, lr: 1.0e-04 loss: 3.614e-01]
my_first_lora_v2: 39%|###8 | 1547/4000 [45:24<1:12:00, 1.76s/it, lr: 1.0e-04 loss: 3.798e-01]
my_first_lora_v2: 39%|###8 | 1547/4000 [45:24<1:12:00, 1.76s/it, lr: 1.0e-04 loss: 3.798e-01]
my_first_lora_v2: 39%|###8 | 1548/4000 [45:25<1:11:56, 1.76s/it, lr: 1.0e-04 loss: 4.025e-01]
my_first_lora_v2: 39%|###8 | 1548/4000 [45:25<1:11:56, 1.76s/it, lr: 1.0e-04 loss: 4.025e-01]
my_first_lora_v2: 39%|###8 | 1549/4000 [45:27<1:11:56, 1.76s/it, lr: 1.0e-04 loss: 3.313e-01]
my_first_lora_v2: 39%|###8 | 1549/4000 [45:27<1:11:56, 1.76s/it, lr: 1.0e-04 loss: 3.313e-01]
my_first_lora_v2: 39%|###8 | 1550/4000 [45:28<1:11:53, 1.76s/it, lr: 1.0e-04 loss: 7.303e-01]
my_first_lora_v2: 39%|###8 | 1550/4000 [45:28<1:11:53, 1.76s/it, lr: 1.0e-04 loss: 7.303e-01]
my_first_lora_v2: 39%|###8 | 1551/4000 [45:31<1:11:53, 1.76s/it, lr: 1.0e-04 loss: 4.644e-01]
my_first_lora_v2: 39%|###8 | 1551/4000 [45:31<1:11:53, 1.76s/it, lr: 1.0e-04 loss: 4.644e-01]
my_first_lora_v2: 39%|###8 | 1552/4000 [45:32<1:11:49, 1.76s/it, lr: 1.0e-04 loss: 7.353e-01]
my_first_lora_v2: 39%|###8 | 1552/4000 [45:32<1:11:49, 1.76s/it, lr: 1.0e-04 loss: 7.353e-01]
my_first_lora_v2: 39%|###8 | 1553/4000 [45:33<1:11:46, 1.76s/it, lr: 1.0e-04 loss: 4.734e-01]
my_first_lora_v2: 39%|###8 | 1553/4000 [45:33<1:11:46, 1.76s/it, lr: 1.0e-04 loss: 4.734e-01]
my_first_lora_v2: 39%|###8 | 1554/4000 [45:36<1:11:46, 1.76s/it, lr: 1.0e-04 loss: 6.909e-01]
my_first_lora_v2: 39%|###8 | 1554/4000 [45:36<1:11:46, 1.76s/it, lr: 1.0e-04 loss: 6.909e-01]
my_first_lora_v2: 39%|###8 | 1555/4000 [45:37<1:11:43, 1.76s/it, lr: 1.0e-04 loss: 4.974e-01]
my_first_lora_v2: 39%|###8 | 1555/4000 [45:37<1:11:43, 1.76s/it, lr: 1.0e-04 loss: 4.974e-01]
my_first_lora_v2: 39%|###8 | 1556/4000 [45:37<1:11:40, 1.76s/it, lr: 1.0e-04 loss: 2.038e-02]
my_first_lora_v2: 39%|###8 | 1556/4000 [45:37<1:11:40, 1.76s/it, lr: 1.0e-04 loss: 2.038e-02]
my_first_lora_v2: 39%|###8 | 1557/4000 [45:38<1:11:36, 1.76s/it, lr: 1.0e-04 loss: 6.880e-01]
my_first_lora_v2: 39%|###8 | 1557/4000 [45:38<1:11:36, 1.76s/it, lr: 1.0e-04 loss: 6.880e-01]
my_first_lora_v2: 39%|###8 | 1558/4000 [45:41<1:11:36, 1.76s/it, lr: 1.0e-04 loss: 4.860e-01]
my_first_lora_v2: 39%|###8 | 1558/4000 [45:41<1:11:36, 1.76s/it, lr: 1.0e-04 loss: 4.860e-01]
my_first_lora_v2: 39%|###8 | 1559/4000 [45:44<1:11:36, 1.76s/it, lr: 1.0e-04 loss: 6.814e-01]
my_first_lora_v2: 39%|###8 | 1559/4000 [45:44<1:11:36, 1.76s/it, lr: 1.0e-04 loss: 6.814e-01]
my_first_lora_v2: 39%|###9 | 1560/4000 [45:47<1:11:36, 1.76s/it, lr: 1.0e-04 loss: 6.431e-01]
my_first_lora_v2: 39%|###9 | 1560/4000 [45:47<1:11:36, 1.76s/it, lr: 1.0e-04 loss: 6.431e-01]
my_first_lora_v2: 39%|###9 | 1561/4000 [45:47<1:11:33, 1.76s/it, lr: 1.0e-04 loss: 5.725e-01]
my_first_lora_v2: 39%|###9 | 1561/4000 [45:47<1:11:33, 1.76s/it, lr: 1.0e-04 loss: 5.725e-01]
my_first_lora_v2: 39%|###9 | 1562/4000 [45:50<1:11:33, 1.76s/it, lr: 1.0e-04 loss: 4.913e-01]
my_first_lora_v2: 39%|###9 | 1562/4000 [45:50<1:11:33, 1.76s/it, lr: 1.0e-04 loss: 4.913e-01] |