File size: 9,444 Bytes
64157cb | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 | train=3000 eval=30
processor_config.json: 0%| | 0.00/1.02k [00:00<?, ?B/s][A
processor_config.json: 100%|██████████| 1.02k/1.02k [00:00<00:00, 743kB/s]
chat_template.jinja: 0%| | 0.00/720 [00:00<?, ?B/s][A
chat_template.jinja: 100%|██████████| 720/720 [00:00<00:00, 4.24MB/s]
config.json: 0%| | 0.00/2.36k [00:00<?, ?B/s][A
config.json: 100%|██████████| 2.36k/2.36k [00:00<00:00, 15.0MB/s]
tokenizer_config.json: 0%| | 0.00/5.56k [00:00<?, ?B/s][A
tokenizer_config.json: 100%|██████████| 5.56k/5.56k [00:00<00:00, 31.5MB/s]
tokenizer.json: reconstructing file: 0%| | 0.00B / 11.4MB [A
tokenizer.json: downloading bytes: | 0.00B
tokenizer.json: downloading bytes: | 33.6kB
tokenizer.json: reconstructing file: 0%| | 28.5kB / 11.4MB [A
tokenizer.json: downloading bytes: ██████████| 3.40MB, 323kB/s
tokenizer.json: downloading bytes: ██████████| 3.40MB, 323kB/s
tokenizer.json: reconstructing file: 100%|██████████| 11.4MB / 11.4MB, 1.09MB/s
added_tokens.json: 0%| | 0.00/707 [00:00<?, ?B/s][A
added_tokens.json: 100%|██████████| 707/707 [00:00<00:00, 5.24MB/s]
special_tokens_map.json: 0%| | 0.00/613 [00:00<?, ?B/s][A
special_tokens_map.json: 100%|██████████| 613/613 [00:00<00:00, 3.49MB/s]
[transformers] You are using a model of type `mistral3` to instantiate a model of type `lighton_ocr`. This may be expected if you are loading a checkpoint that shares a subset of the architecture (e.g., loading a `sam2_video` checkpoint into `Sam2Model`), but is otherwise not supported and can yield errors. Please verify that the checkpoint is compatible with the model you are instantiating.
model.safetensors: reconstructing file: 0%| | 0.00B / 2.01GB [A
model.safetensors: downloading bytes: | 0.00B
model.safetensors: reconstructing file: 0%| | 39.4kB / 2.01GB [A
model.safetensors: downloading bytes: | 103kB
model.safetensors: downloading bytes: ▏ | 34.7MB, 2.41MB/s
model.safetensors: downloading bytes: ▋ | 147MB, 12.4MB/s
model.safetensors: reconstructing file: 7%|▋ | 134MB / 2.01GB, 19.1kB/s [A
model.safetensors: downloading bytes: █ | 209MB, 17.3MB/s
model.safetensors: reconstructing file: 12%|█▏ | 243MB / 2.01GB, 19.4MB/s [A
model.safetensors: downloading bytes: █▍ | 288MB, 19.9MB/s
model.safetensors: reconstructing file: 18%|█▊ | 354MB / 2.01GB, 24.1MB/s [A
model.safetensors: downloading bytes: ███▌ | 722MB, 51.3MB/s
model.safetensors: reconstructing file: 48%|████▊ | 957MB / 2.01GB, 30.1MB/s [A
model.safetensors: downloading bytes: █████▉ | 1.19GB, 84.6MB/s
model.safetensors: downloading bytes: ████████▎ | 1.68GB, 120MB/s
model.safetensors: reconstructing file: 68%|██████▊ | 1.36GB / 2.01GB, 78.8MB/s [A
model.safetensors: downloading bytes: ██████████| 1.75GB, 122MB/s
model.safetensors: downloading bytes: ██████████| 1.75GB, 122MB/s
model.safetensors: reconstructing file: 100%|██████████| 2.01GB / 2.01GB, 150MB/s
Loading weights: 0%| | 0/532 [00:00<?, ?it/s][A
Loading weights: 100%|██████████| 532/532 [00:00<00:00, 15770.96it/s]
generation_config.json: 0%| | 0.00/219 [00:00<?, ?B/s][A
generation_config.json: 100%|██████████| 219/219 [00:00<00:00, 1.62MB/s]
[eval base] 1/30 cer=0.1851
[eval base] 2/30 cer=0.2617
[eval base] 3/30 cer=0.2774
[eval base] 4/30 cer=0.2012
[eval base] 5/30 cer=0.2754
[eval base] 6/30 cer=0.4906
[eval base] 7/30 cer=0.5578
[eval base] 8/30 cer=0.4953
[eval base] 9/30 cer=0.6164
[eval base] 10/30 cer=0.6604
[eval base] 11/30 cer=0.6920
[eval base] 12/30 cer=0.6875
[eval base] 13/30 cer=0.5397
[eval base] 14/30 cer=0.5463
[eval base] 15/30 cer=0.6926
[eval base] 16/30 cer=0.3421
[eval base] 17/30 cer=0.4329
[eval base] 18/30 cer=0.4298
[eval base] 19/30 cer=0.3960
[eval base] 20/30 cer=0.3732
[eval base] 21/30 cer=0.7938
[eval base] 22/30 cer=0.7542
[eval base] 23/30 cer=0.7598
[eval base] 24/30 cer=0.8000
[eval base] 25/30 cer=1.0146
[eval base] 26/30 cer=1.1248
[eval base] 27/30 cer=1.1429
[eval base] 28/30 cer=1.1569
[eval base] 29/30 cer=1.1456
[eval base] 30/30 cer=1.4049
BASE CER mean=0.6417 median=0.6164
epoch=0 step=5/375 loss=0.1145 lr=4.54e-06
epoch=0 step=10/375 loss=0.0793 lr=9.07e-06
epoch=0 step=15/375 loss=0.0548 lr=9.96e-06
epoch=0 step=20/375 loss=0.0353 lr=9.93e-06
epoch=0 step=25/375 loss=0.0220 lr=9.89e-06
epoch=0 step=30/375 loss=0.0150 lr=9.84e-06
epoch=0 step=35/375 loss=0.0105 lr=9.79e-06
epoch=0 step=40/375 loss=0.0083 lr=9.72e-06
epoch=0 step=45/375 loss=0.0066 lr=9.65e-06
epoch=0 step=50/375 loss=0.0049 lr=9.57e-06
epoch=0 step=55/375 loss=0.0038 lr=9.48e-06
epoch=0 step=60/375 loss=0.0038 lr=9.38e-06
epoch=0 step=65/375 loss=0.0040 lr=9.28e-06
epoch=0 step=70/375 loss=0.0035 lr=9.16e-06
epoch=0 step=75/375 loss=0.0035 lr=9.05e-06
epoch=0 step=80/375 loss=0.0025 lr=8.92e-06
epoch=0 step=85/375 loss=0.0028 lr=8.78e-06
epoch=0 step=90/375 loss=0.0030 lr=8.64e-06
epoch=0 step=95/375 loss=0.0025 lr=8.50e-06
epoch=0 step=100/375 loss=0.0024 lr=8.35e-06
epoch=0 step=105/375 loss=0.0022 lr=8.19e-06
epoch=0 step=110/375 loss=0.0025 lr=8.02e-06
epoch=0 step=115/375 loss=0.0021 lr=7.85e-06
epoch=0 step=120/375 loss=0.0018 lr=7.68e-06
epoch=0 step=125/375 loss=0.0021 lr=7.50e-06
epoch=0 step=130/375 loss=0.0019 lr=7.32e-06
epoch=0 step=135/375 loss=0.0018 lr=7.13e-06
epoch=0 step=140/375 loss=0.0017 lr=6.94e-06
epoch=0 step=145/375 loss=0.0019 lr=6.74e-06
epoch=0 step=150/375 loss=0.0016 lr=6.55e-06
epoch=0 step=155/375 loss=0.0017 lr=6.34e-06
epoch=0 step=160/375 loss=0.0014 lr=6.14e-06
epoch=0 step=165/375 loss=0.0018 lr=5.94e-06
epoch=0 step=170/375 loss=0.0017 lr=5.73e-06
epoch=0 step=175/375 loss=0.0016 lr=5.52e-06
epoch=0 step=180/375 loss=0.0014 lr=5.31e-06
epoch=0 step=185/375 loss=0.0014 lr=5.10e-06
epoch=1 step=190/375 loss=0.0014 lr=4.90e-06
epoch=1 step=195/375 loss=0.0014 lr=4.69e-06
epoch=1 step=200/375 loss=0.0015 lr=4.48e-06
epoch=1 step=205/375 loss=0.0016 lr=4.27e-06
epoch=1 step=210/375 loss=0.0015 lr=4.06e-06
epoch=1 step=215/375 loss=0.0011 lr=3.86e-06
epoch=1 step=220/375 loss=0.0013 lr=3.66e-06
epoch=1 step=225/375 loss=0.0013 lr=3.45e-06
epoch=1 step=230/375 loss=0.0015 lr=3.26e-06
epoch=1 step=235/375 loss=0.0013 lr=3.06e-06
epoch=1 step=240/375 loss=0.0016 lr=2.87e-06
epoch=1 step=245/375 loss=0.0013 lr=2.68e-06
epoch=1 step=250/375 loss=0.0017 lr=2.50e-06
epoch=1 step=255/375 loss=0.0012 lr=2.32e-06
epoch=1 step=260/375 loss=0.0012 lr=2.15e-06
epoch=1 step=265/375 loss=0.0013 lr=1.98e-06
epoch=1 step=270/375 loss=0.0014 lr=1.81e-06
epoch=1 step=275/375 loss=0.0016 lr=1.65e-06
epoch=1 step=280/375 loss=0.0013 lr=1.50e-06
epoch=1 step=285/375 loss=0.0014 lr=1.36e-06
epoch=1 step=290/375 loss=0.0012 lr=1.22e-06
epoch=1 step=295/375 loss=0.0012 lr=1.08e-06
epoch=1 step=300/375 loss=0.0015 lr=1.00e-06
epoch=1 step=305/375 loss=0.0012 lr=1.00e-06
epoch=1 step=310/375 loss=0.0015 lr=1.00e-06
epoch=1 step=315/375 loss=0.0013 lr=1.00e-06
epoch=1 step=320/375 loss=0.0014 lr=1.00e-06
epoch=1 step=325/375 loss=0.0013 lr=1.00e-06
epoch=1 step=330/375 loss=0.0014 lr=1.00e-06
epoch=1 step=335/375 loss=0.0015 lr=1.00e-06
epoch=1 step=340/375 loss=0.0012 lr=1.00e-06
epoch=1 step=345/375 loss=0.0014 lr=1.00e-06
epoch=1 step=350/375 loss=0.0012 lr=1.00e-06
epoch=1 step=355/375 loss=0.0012 lr=1.00e-06
epoch=1 step=360/375 loss=0.0011 lr=1.00e-06
epoch=1 step=365/375 loss=0.0011 lr=1.00e-06
epoch=1 step=370/375 loss=0.0012 lr=1.00e-06
epoch=1 step=375/375 loss=0.0014 lr=1.00e-06
[eval finetuned] 1/30 cer=0.0007
[eval finetuned] 2/30 cer=0.0007
[eval finetuned] 3/30 cer=0.0007
[eval finetuned] 4/30 cer=0.0008
[eval finetuned] 5/30 cer=0.0007
[eval finetuned] 6/30 cer=0.0010
[eval finetuned] 7/30 cer=0.0010
[eval finetuned] 8/30 cer=0.0010
[eval finetuned] 9/30 cer=0.0011
[eval finetuned] 10/30 cer=0.0010
[eval finetuned] 11/30 cer=0.0008
[eval finetuned] 12/30 cer=0.0008
[eval finetuned] 13/30 cer=0.0009
[eval finetuned] 14/30 cer=0.0009
[eval finetuned] 15/30 cer=0.0008
[eval finetuned] 16/30 cer=0.0009
[eval finetuned] 17/30 cer=0.0008
[eval finetuned] 18/30 cer=0.0008
[eval finetuned] 19/30 cer=0.0009
[eval finetuned] 20/30 cer=0.0010
[eval finetuned] 21/30 cer=0.0019
[eval finetuned] 22/30 cer=0.0018
[eval finetuned] 23/30 cer=0.0019
[eval finetuned] 24/30 cer=0.0020
[eval finetuned] 25/30 cer=0.0018
[eval finetuned] 26/30 cer=0.0015
[eval finetuned] 27/30 cer=0.0016
[eval finetuned] 28/30 cer=0.0016
[eval finetuned] 29/30 cer=0.0016
[eval finetuned] 30/30 cer=0.0013
FINETUNED CER mean=0.0012 median=0.0010
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s][A
Writing model shards: 100%|██████████| 1/1 [00:02<00:00, 2.02s/it][A
Writing model shards: 100%|██████████| 1/1 [00:02<00:00, 2.02s/it]
SAVED /w/model
|