113 lines
78 KiB
Plaintext
113 lines
78 KiB
Plaintext
📁 输出目录: /home/songsenand/Project/SUimeModelTraner/exported_models
|
||
📦 加载checkpoint: /home/songsenand/下载/20260416best_model.pt
|
||
Downloading Model from https://www.modelscope.cn to directory: /home/songsenand/.cache/modelscope/hub/models/iic/nlp_structbert_backbone_lite_std
|
||
|
||
Loading weights: 0%| | 0/103 [00:00<?, ?it/s]
|
||
Loading weights: 1%|█▏ | 1/103 [00:00<00:00, 29746.84it/s, Materializing param=embeddings.LayerNorm.bias]
|
||
Loading weights: 1%|█▏ | 1/103 [00:00<00:00, 9177.91it/s, Materializing param=embeddings.LayerNorm.bias]
|
||
Loading weights: 2%|██▎ | 2/103 [00:00<00:00, 9915.61it/s, Materializing param=embeddings.LayerNorm.weight]
|
||
Loading weights: 2%|██▎ | 2/103 [00:00<00:00, 7854.50it/s, Materializing param=embeddings.LayerNorm.weight]
|
||
Loading weights: 3%|███ | 3/103 [00:00<00:00, 9225.01it/s, Materializing param=embeddings.position_embeddings.weight]
|
||
Loading weights: 3%|███ | 3/103 [00:00<00:00, 7953.80it/s, Materializing param=embeddings.position_embeddings.weight]
|
||
Loading weights: 4%|████ | 4/103 [00:00<00:00, 8986.19it/s, Materializing param=embeddings.token_type_embeddings.weight]
|
||
Loading weights: 4%|████ | 4/103 [00:00<00:00, 8093.21it/s, Materializing param=embeddings.token_type_embeddings.weight]
|
||
Loading weights: 5%|█████▎ | 5/103 [00:00<00:00, 9023.89it/s, Materializing param=embeddings.word_embeddings.weight]
|
||
Loading weights: 5%|█████▎ | 5/103 [00:00<00:00, 8365.19it/s, Materializing param=embeddings.word_embeddings.weight]
|
||
Loading weights: 6%|█████▌ | 6/103 [00:00<00:00, 9174.56it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.bias]
|
||
Loading weights: 6%|█████▌ | 6/103 [00:00<00:00, 8589.02it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.bias]
|
||
Loading weights: 7%|██████▍ | 7/103 [00:00<00:00, 9229.84it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.weight]
|
||
Loading weights: 7%|██████▍ | 7/103 [00:00<00:00, 8722.56it/s, Materializing param=encoder.layer.0.attention.output.LayerNorm.weight]
|
||
Loading weights: 8%|███████▊ | 8/103 [00:00<00:00, 9302.59it/s, Materializing param=encoder.layer.0.attention.output.dense.bias]
|
||
Loading weights: 8%|███████▊ | 8/103 [00:00<00:00, 8862.77it/s, Materializing param=encoder.layer.0.attention.output.dense.bias]
|
||
Loading weights: 9%|████████▌ | 9/103 [00:00<00:00, 9327.58it/s, Materializing param=encoder.layer.0.attention.output.dense.weight]
|
||
Loading weights: 9%|████████▌ | 9/103 [00:00<00:00, 8921.94it/s, Materializing param=encoder.layer.0.attention.output.dense.weight]
|
||
Loading weights: 10%|██████████ | 10/103 [00:00<00:00, 9402.16it/s, Materializing param=encoder.layer.0.attention.self.key.bias]
|
||
Loading weights: 10%|██████████ | 10/103 [00:00<00:00, 9039.45it/s, Materializing param=encoder.layer.0.attention.self.key.bias]
|
||
Loading weights: 11%|██████████▊ | 11/103 [00:00<00:00, 9475.73it/s, Materializing param=encoder.layer.0.attention.self.key.weight]
|
||
Loading weights: 11%|██████████▊ | 11/103 [00:00<00:00, 9123.46it/s, Materializing param=encoder.layer.0.attention.self.key.weight]
|
||
Loading weights: 12%|███████████▊ | 12/103 [00:00<00:00, 9510.89it/s, Materializing param=encoder.layer.0.attention.self.query.bias]
|
||
Loading weights: 12%|███████████▊ | 12/103 [00:00<00:00, 9206.45it/s, Materializing param=encoder.layer.0.attention.self.query.bias]
|
||
Loading weights: 13%|████████████▍ | 13/103 [00:00<00:00, 9567.64it/s, Materializing param=encoder.layer.0.attention.self.query.weight]
|
||
Loading weights: 13%|████████████▍ | 13/103 [00:00<00:00, 9277.85it/s, Materializing param=encoder.layer.0.attention.self.query.weight]
|
||
Loading weights: 14%|█████████████▋ | 14/103 [00:00<00:00, 9548.01it/s, Materializing param=encoder.layer.0.attention.self.value.bias]
|
||
Loading weights: 14%|█████████████▋ | 14/103 [00:00<00:00, 9269.18it/s, Materializing param=encoder.layer.0.attention.self.value.bias]
|
||
Loading weights: 15%|██████████████▍ | 15/103 [00:00<00:00, 9564.39it/s, Materializing param=encoder.layer.0.attention.self.value.weight]
|
||
Loading weights: 15%|██████████████▍ | 15/103 [00:00<00:00, 9313.78it/s, Materializing param=encoder.layer.0.attention.self.value.weight]
|
||
Loading weights: 16%|███████████████▉ | 16/103 [00:00<00:00, 9617.21it/s, Materializing param=encoder.layer.0.intermediate.dense.bias]
|
||
Loading weights: 16%|███████████████▉ | 16/103 [00:00<00:00, 9383.23it/s, Materializing param=encoder.layer.0.intermediate.dense.bias]
|
||
Loading weights: 17%|████████████████▋ | 17/103 [00:00<00:00, 9669.54it/s, Materializing param=encoder.layer.0.intermediate.dense.weight]
|
||
Loading weights: 17%|████████████████▋ | 17/103 [00:00<00:00, 9434.13it/s, Materializing param=encoder.layer.0.intermediate.dense.weight]
|
||
Loading weights: 17%|██████████████████▎ | 18/103 [00:00<00:00, 9705.29it/s, Materializing param=encoder.layer.0.output.LayerNorm.bias]
|
||
Loading weights: 17%|██████████████████▎ | 18/103 [00:00<00:00, 9491.76it/s, Materializing param=encoder.layer.0.output.LayerNorm.bias]
|
||
Loading weights: 18%|███████████████████ | 19/103 [00:00<00:00, 9753.00it/s, Materializing param=encoder.layer.0.output.LayerNorm.weight]
|
||
Loading weights: 18%|███████████████████ | 19/103 [00:00<00:00, 9554.22it/s, Materializing param=encoder.layer.0.output.LayerNorm.weight]
|
||
Loading weights: 19%|█████████████████████▏ | 20/103 [00:00<00:00, 9803.21it/s, Materializing param=encoder.layer.0.output.dense.bias]
|
||
Loading weights: 19%|█████████████████████▏ | 20/103 [00:00<00:00, 9614.45it/s, Materializing param=encoder.layer.0.output.dense.bias]
|
||
Loading weights: 20%|█████████████████████▊ | 21/103 [00:00<00:00, 9852.39it/s, Materializing param=encoder.layer.0.output.dense.weight]
|
||
Loading weights: 20%|█████████████████████▊ | 21/103 [00:00<00:00, 9669.60it/s, Materializing param=encoder.layer.0.output.dense.weight]
|
||
Loading weights: 21%|████████████████████▎ | 22/103 [00:00<00:00, 9896.47it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.bias]
|
||
Loading weights: 21%|████████████████████▎ | 22/103 [00:00<00:00, 9716.19it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.bias]
|
||
Loading weights: 22%|████████████████████▊ | 23/103 [00:00<00:00, 9927.86it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.weight]
|
||
Loading weights: 22%|████████████████████▊ | 23/103 [00:00<00:00, 9756.17it/s, Materializing param=encoder.layer.1.attention.output.LayerNorm.weight]
|
||
Loading weights: 23%|███████████████████████ | 24/103 [00:00<00:00, 9956.80it/s, Materializing param=encoder.layer.1.attention.output.dense.bias]
|
||
Loading weights: 23%|███████████████████████ | 24/103 [00:00<00:00, 9762.71it/s, Materializing param=encoder.layer.1.attention.output.dense.bias]
|
||
Loading weights: 24%|███████████████████████▌ | 25/103 [00:00<00:00, 9932.52it/s, Materializing param=encoder.layer.1.attention.output.dense.weight]
|
||
Loading weights: 24%|███████████████████████▌ | 25/103 [00:00<00:00, 9767.82it/s, Materializing param=encoder.layer.1.attention.output.dense.weight]
|
||
Loading weights: 25%|██████████████████████████ | 26/103 [00:00<00:00, 9941.83it/s, Materializing param=encoder.layer.1.attention.self.key.bias]
|
||
Loading weights: 25%|██████████████████████████ | 26/103 [00:00<00:00, 9781.32it/s, Materializing param=encoder.layer.1.attention.self.key.bias]
|
||
Loading weights: 26%|██████████████████████████▍ | 27/103 [00:00<00:00, 9951.34it/s, Materializing param=encoder.layer.1.attention.self.key.weight]
|
||
Loading weights: 26%|██████████████████████████▍ | 27/103 [00:00<00:00, 9800.62it/s, Materializing param=encoder.layer.1.attention.self.key.weight]
|
||
Loading weights: 27%|███████████████████████████▍ | 28/103 [00:00<00:00, 9968.64it/s, Materializing param=encoder.layer.1.attention.self.query.bias]
|
||
Loading weights: 27%|███████████████████████████▍ | 28/103 [00:00<00:00, 9825.19it/s, Materializing param=encoder.layer.1.attention.self.query.bias]
|
||
Loading weights: 28%|███████████████████████████▊ | 29/103 [00:00<00:00, 9989.72it/s, Materializing param=encoder.layer.1.attention.self.query.weight]
|
||
Loading weights: 28%|███████████████████████████▊ | 29/103 [00:00<00:00, 9846.58it/s, Materializing param=encoder.layer.1.attention.self.query.weight]
|
||
Loading weights: 29%|█████████████████████████████▏ | 30/103 [00:00<00:00, 10007.09it/s, Materializing param=encoder.layer.1.attention.self.value.bias]
|
||
Loading weights: 29%|█████████████████████████████▍ | 30/103 [00:00<00:00, 9873.60it/s, Materializing param=encoder.layer.1.attention.self.value.bias]
|
||
Loading weights: 30%|█████████████████████████████▍ | 31/103 [00:00<00:00, 10031.12it/s, Materializing param=encoder.layer.1.attention.self.value.weight]
|
||
Loading weights: 30%|█████████████████████████████▊ | 31/103 [00:00<00:00, 9900.51it/s, Materializing param=encoder.layer.1.attention.self.value.weight]
|
||
Loading weights: 31%|███████████████████████████████▋ | 32/103 [00:00<00:00, 10054.52it/s, Materializing param=encoder.layer.1.intermediate.dense.bias]
|
||
Loading weights: 31%|███████████████████████████████▉ | 32/103 [00:00<00:00, 9921.48it/s, Materializing param=encoder.layer.1.intermediate.dense.bias]
|
||
Loading weights: 32%|████████████████████████████████ | 33/103 [00:00<00:00, 10067.79it/s, Materializing param=encoder.layer.1.intermediate.dense.weight]
|
||
Loading weights: 32%|████████████████████████████████▎ | 33/103 [00:00<00:00, 9942.68it/s, Materializing param=encoder.layer.1.intermediate.dense.weight]
|
||
Loading weights: 33%|██████████████████████████████████▎ | 34/103 [00:00<00:00, 10086.74it/s, Materializing param=encoder.layer.1.output.LayerNorm.bias]
|
||
Loading weights: 33%|██████████████████████████████████▋ | 34/103 [00:00<00:00, 9967.59it/s, Materializing param=encoder.layer.1.output.LayerNorm.bias]
|
||
Loading weights: 34%|██████████████████████████████████▋ | 35/103 [00:00<00:00, 10075.54it/s, Materializing param=encoder.layer.1.output.LayerNorm.weight]
|
||
Loading weights: 34%|███████████████████████████████████ | 35/103 [00:00<00:00, 9954.61it/s, Materializing param=encoder.layer.1.output.LayerNorm.weight]
|
||
Loading weights: 35%|█████████████████████████████████████▋ | 36/103 [00:00<00:00, 10089.87it/s, Materializing param=encoder.layer.1.output.dense.bias]
|
||
Loading weights: 35%|██████████████████████████████████████ | 36/103 [00:00<00:00, 9978.52it/s, Materializing param=encoder.layer.1.output.dense.bias]
|
||
Loading weights: 36%|██████████████████████████████████████ | 37/103 [00:00<00:00, 10110.71it/s, Materializing param=encoder.layer.1.output.dense.weight]
|
||
Loading weights: 36%|██████████████████████████████████████ | 37/103 [00:00<00:00, 10000.60it/s, Materializing param=encoder.layer.1.output.dense.weight]
|
||
Loading weights: 37%|██████████████████████████████████▋ | 38/103 [00:00<00:00, 10131.81it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.bias]
|
||
Loading weights: 37%|██████████████████████████████████▋ | 38/103 [00:00<00:00, 10020.97it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.bias]
|
||
Loading weights: 38%|██████████████████████████████████▊ | 39/103 [00:00<00:00, 10141.85it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.weight]
|
||
Loading weights: 38%|██████████████████████████████████▊ | 39/103 [00:00<00:00, 10027.45it/s, Materializing param=encoder.layer.2.attention.output.LayerNorm.weight]
|
||
Loading weights: 39%|██████████████████████████████████████ | 40/103 [00:00<00:00, 10130.56it/s, Materializing param=encoder.layer.2.attention.output.dense.bias]
|
||
Loading weights: 39%|██████████████████████████████████████ | 40/103 [00:00<00:00, 10022.83it/s, Materializing param=encoder.layer.2.attention.output.dense.bias]
|
||
Loading weights: 40%|██████████████████████████████████████▏ | 41/103 [00:00<00:00, 10131.17it/s, Materializing param=encoder.layer.2.attention.output.dense.weight]
|
||
Loading weights: 40%|██████████████████████████████████████▏ | 41/103 [00:00<00:00, 10025.45it/s, Materializing param=encoder.layer.2.attention.output.dense.weight]
|
||
Loading weights: 41%|█████████████████████████████████████████▌ | 42/103 [00:00<00:00, 10135.83it/s, Materializing param=encoder.layer.2.attention.self.key.bias]
|
||
Loading weights: 41%|█████████████████████████████████████████▌ | 42/103 [00:00<00:00, 10033.65it/s, Materializing param=encoder.layer.2.attention.self.key.bias]
|
||
Loading weights: 42%|█████████████████████████████████████████▋ | 43/103 [00:00<00:00, 10143.70it/s, Materializing param=encoder.layer.2.attention.self.key.weight]
|
||
Loading weights: 42%|█████████████████████████████████████████▋ | 43/103 [00:00<00:00, 10045.40it/s, Materializing param=encoder.layer.2.attention.self.key.weight]
|
||
Loading weights: 43%|██████████████████████████████████████████▋ | 44/103 [00:00<00:00, 10155.14it/s, Materializing param=encoder.layer.2.attention.self.query.bias]
|
||
Loading weights: 43%|██████████████████████████████████████████▋ | 44/103 [00:00<00:00, 10058.28it/s, Materializing param=encoder.layer.2.attention.self.query.bias]
|
||
Loading weights: 44%|██████████████████████████████████████████▊ | 45/103 [00:00<00:00, 10164.45it/s, Materializing param=encoder.layer.2.attention.self.query.weight]
|
||
Loading weights: 44%|██████████████████████████████████████████▊ | 45/103 [00:00<00:00, 10052.93it/s, Materializing param=encoder.layer.2.attention.self.query.weight]
|
||
Loading weights: 45%|████████████████████████████████████████████▋ | 46/103 [00:00<00:00, 10143.42it/s, Materializing param=encoder.layer.2.attention.self.value.bias]
|
||
Loading weights: 45%|████████████████████████████████████████████▋ | 46/103 [00:00<00:00, 10049.90it/s, Materializing param=encoder.layer.2.attention.self.value.bias]
|
||
Loading weights: 46%|████████████████████████████████████████████▋ | 47/103 [00:00<00:00, 10149.95it/s, Materializing param=encoder.layer.2.attention.self.value.weight]
|
||
Loading weights: 46%|████████████████████████████████████████████▋ | 47/103 [00:00<00:00, 10060.34it/s, Materializing param=encoder.layer.2.attention.self.value.weight]
|
||
Loading weights: 47%|███████████████████████████████████████████████▌ | 48/103 [00:00<00:00, 10160.83it/s, Materializing param=encoder.layer.2.intermediate.dense.bias]
|
||
Loading weights: 47%|███████████████████████████████████████████████▌ | 48/103 [00:00<00:00, 10074.89it/s, Materializing param=encoder.layer.2.intermediate.dense.bias]
|
||
Loading weights: 48%|███████████████████████████████████████████████▌ | 49/103 [00:00<00:00, 10175.31it/s, Materializing param=encoder.layer.2.intermediate.dense.weight]
|
||
Loading weights: 48%|███████████████████████████████████████████████▌ | 49/103 [00:00<00:00, 10089.39it/s, Materializing param=encoder.layer.2.intermediate.dense.weight]
|
||
Loading weights: 49%|██████████████████████████████████████████████████▍ | 50/103 [00:00<00:00, 10187.77it/s, Materializing param=encoder.layer.2.output.LayerNorm.bias]
|
||
Loading weights: 49%|██████████████████████████████████████████████████▍ | 50/103 [00:00<00:00, 10104.81it/s, Materializing param=encoder.layer.2.output.LayerNorm.bias]
|
||
Loading weights: 50%|██████████████████████████████████████████████████▌ | 51/103 [00:00<00:00, 10200.74it/s, Materializing param=encoder.layer.2.output.LayerNorm.weight]
|
||
Loading weights: 50%|██████████████████████████████████████████████████▌ | 51/103 [00:00<00:00, 10118.23it/s, Materializing param=encoder.layer.2.output.LayerNorm.weight]
|
||
Loading weights: 50%|██████████████████████████████████████████████████████▌ | 52/103 [00:00<00:00, 10211.33it/s, Materializing param=encoder.layer.2.output.dense.bias]
|
||
Loading weights: 50%|██████████████████████████████████████████████████████▌ | 52/103 [00:00<00:00, 10115.19it/s, Materializing param=encoder.layer.2.output.dense.bias]
|
||
Loading weights: 51%|██████████████████████████████████████████████████████▌ | 53/103 [00:00<00:00, 10203.71it/s, Materializing param=encoder.layer.2.output.dense.weight]
|
||
Loading weights: 51%|██████████████████████████████████████████████████████▌ | 53/103 [00:00<00:00, 10121.94it/s, Materializing param=encoder.layer.2.output.dense.weight]
|
||
Loading weights: 52%|█████████████████████████████████████████████████▎ | 54/103 [00:00<00:00, 10209.26it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.bias]
|
||
Loading weights: 52%|█████████████████████████████████████████████████▎ | 54/103 [00:00<00:00, 10128.45it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.bias]
|
||
Loading weights: 53%|█████████████████████████████████████████████████▏ | 55/103 [00:00<00:00, 10210.99it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.weight]
|
||
Loading weights: 53%|█████████████████████████████████████████████████▏ | 55/103 [00:00<00:00, 10131.17it/s, Materializing param=encoder.layer.3.attention.output.LayerNorm.weight]
|
||
Loading weights: 54%|█████████████████████████████████████████████████████▎ | 56/103 [00:00<00:00, 10194.05it/s, Materializing param=encoder.layer.3.attention.output.dense.bias]
|
||
Loading weights: 54%|█████████████████████████████████████████████████████▎ | 56/103 [00:00<00:00, 10112.41it/s, Materializing param=encoder.layer.3.attention.output.dense.bias]
|
||
Loading weights: 55%|█████████████████████████████████████████████████████▏ | 57/103 [00:00<00:00, 10190.33it/s, Materializing param=encoder.layer.3.attention.output.dense.weight]
|
||
Loading weights: 55%|█████████████████████████████████████████████████████▏ | 57/103 [00:00<00:00, 10112.31it/s, Materializing param=encoder.layer.3.attention.output.dense.weight]
|
||
Loading weights: 56%|█████████████████████████████████████████████████████████▍ | 58/103 [00:00<00:00, 10191.44it/s, Materializing param=encoder.layer.3.attention.self.key.bias]
|
||
Loading weights: 56%|█████████████████████████████████████████████████████████▍ | 58/103 [00:00<00:00, 10116.00it/s, Materializing param=encoder.layer.3.attention.self.key.bias]
|
||
Loading weights: 57%|█████████████████████████████████████████████████████████▎ | 59/103 [00:00<00:00, 10188.31it/s, Materializing param=encoder.layer.3.attention.self.key.weight]
|
||
Loading weights: 57%|█████████████████████████████████████████████████████████▎ | 59/103 [00:00<00:00, 10113.78it/s, Materializing param=encoder.layer.3.attention.self.key.weight]
|
||
Loading weights: 58%|██████████████████████████████████████████████████████████▎ | 60/103 [00:00<00:00, 10190.24it/s, Materializing param=encoder.layer.3.attention.self.query.bias]
|
||
Loading weights: 58%|██████████████████████████████████████████████████████████▎ | 60/103 [00:00<00:00, 10117.73it/s, Materializing param=encoder.layer.3.attention.self.query.bias]
|
||
Loading weights: 59%|██████████████████████████████████████████████████████████ | 61/103 [00:00<00:00, 10189.67it/s, Materializing param=encoder.layer.3.attention.self.query.weight]
|
||
Loading weights: 59%|██████████████████████████████████████████████████████████ | 61/103 [00:00<00:00, 10116.75it/s, Materializing param=encoder.layer.3.attention.self.query.weight]
|
||
Loading weights: 60%|████████████████████████████████████████████████████████████▏ | 62/103 [00:00<00:00, 10190.32it/s, Materializing param=encoder.layer.3.attention.self.value.bias]
|
||
Loading weights: 60%|████████████████████████████████████████████████████████████▏ | 62/103 [00:00<00:00, 10120.92it/s, Materializing param=encoder.layer.3.attention.self.value.bias]
|
||
Loading weights: 61%|███████████████████████████████████████████████████████████▉ | 63/103 [00:00<00:00, 10193.70it/s, Materializing param=encoder.layer.3.attention.self.value.weight]
|
||
Loading weights: 61%|███████████████████████████████████████████████████████████▉ | 63/103 [00:00<00:00, 10124.57it/s, Materializing param=encoder.layer.3.attention.self.value.weight]
|
||
Loading weights: 62%|███████████████████████████████████████████████████████████████▍ | 64/103 [00:00<00:00, 10197.37it/s, Materializing param=encoder.layer.3.intermediate.dense.bias]
|
||
Loading weights: 62%|███████████████████████████████████████████████████████████████▍ | 64/103 [00:00<00:00, 10130.02it/s, Materializing param=encoder.layer.3.intermediate.dense.bias]
|
||
Loading weights: 63%|███████████████████████████████████████████████████████████████ | 65/103 [00:00<00:00, 10198.63it/s, Materializing param=encoder.layer.3.intermediate.dense.weight]
|
||
Loading weights: 63%|███████████████████████████████████████████████████████████████ | 65/103 [00:00<00:00, 10130.79it/s, Materializing param=encoder.layer.3.intermediate.dense.weight]
|
||
Loading weights: 64%|██████████████████████████████████████████████████████████████████▋ | 66/103 [00:00<00:00, 10187.84it/s, Materializing param=encoder.layer.3.output.LayerNorm.bias]
|
||
Loading weights: 64%|██████████████████████████████████████████████████████████████████▋ | 66/103 [00:00<00:00, 10120.06it/s, Materializing param=encoder.layer.3.output.LayerNorm.bias]
|
||
Loading weights: 65%|██████████████████████████████████████████████████████████████████▎ | 67/103 [00:00<00:00, 10189.21it/s, Materializing param=encoder.layer.3.output.LayerNorm.weight]
|
||
Loading weights: 65%|██████████████████████████████████████████████████████████████████▎ | 67/103 [00:00<00:00, 10124.23it/s, Materializing param=encoder.layer.3.output.LayerNorm.weight]
|
||
Loading weights: 66%|███████████████████████████████████████████████████████████████████████▎ | 68/103 [00:00<00:00, 10192.36it/s, Materializing param=encoder.layer.3.output.dense.bias]
|
||
Loading weights: 66%|███████████████████████████████████████████████████████████████████████▎ | 68/103 [00:00<00:00, 10129.73it/s, Materializing param=encoder.layer.3.output.dense.bias]
|
||
Loading weights: 67%|███████████████████████████████████████████████████████████████████████ | 69/103 [00:00<00:00, 10198.65it/s, Materializing param=encoder.layer.3.output.dense.weight]
|
||
Loading weights: 67%|███████████████████████████████████████████████████████████████████████ | 69/103 [00:00<00:00, 10136.14it/s, Materializing param=encoder.layer.3.output.dense.weight]
|
||
Loading weights: 68%|███████████████████████████████████████████████████████████████▉ | 70/103 [00:00<00:00, 10204.41it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.bias]
|
||
Loading weights: 68%|███████████████████████████████████████████████████████████████▉ | 70/103 [00:00<00:00, 10137.82it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.bias]
|
||
Loading weights: 69%|███████████████████████████████████████████████████████████████▍ | 71/103 [00:00<00:00, 10201.27it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.weight]
|
||
Loading weights: 69%|███████████████████████████████████████████████████████████████▍ | 71/103 [00:00<00:00, 10136.69it/s, Materializing param=encoder.layer.4.attention.output.LayerNorm.weight]
|
||
Loading weights: 70%|████████████████████████████████████████████████████████████████████▌ | 72/103 [00:00<00:00, 10197.19it/s, Materializing param=encoder.layer.4.attention.output.dense.bias]
|
||
Loading weights: 70%|████████████████████████████████████████████████████████████████████▌ | 72/103 [00:00<00:00, 10136.27it/s, Materializing param=encoder.layer.4.attention.output.dense.bias]
|
||
Loading weights: 71%|████████████████████████████████████████████████████████████████████ | 73/103 [00:00<00:00, 10201.04it/s, Materializing param=encoder.layer.4.attention.output.dense.weight]
|
||
Loading weights: 71%|████████████████████████████████████████████████████████████████████ | 73/103 [00:00<00:00, 10141.91it/s, Materializing param=encoder.layer.4.attention.output.dense.weight]
|
||
Loading weights: 72%|█████████████████████████████████████████████████████████████████████████▎ | 74/103 [00:00<00:00, 10205.12it/s, Materializing param=encoder.layer.4.attention.self.key.bias]
|
||
Loading weights: 72%|█████████████████████████████████████████████████████████████████████████▎ | 74/103 [00:00<00:00, 10147.07it/s, Materializing param=encoder.layer.4.attention.self.key.bias]
|
||
Loading weights: 73%|████████████████████████████████████████████████████████████████████████▊ | 75/103 [00:00<00:00, 10210.75it/s, Materializing param=encoder.layer.4.attention.self.key.weight]
|
||
Loading weights: 73%|████████████████████████████████████████████████████████████████████████▊ | 75/103 [00:00<00:00, 10153.41it/s, Materializing param=encoder.layer.4.attention.self.key.weight]
|
||
Loading weights: 74%|█████████████████████████████████████████████████████████████████████████▊ | 76/103 [00:00<00:00, 10207.73it/s, Materializing param=encoder.layer.4.attention.self.query.bias]
|
||
Loading weights: 74%|█████████████████████████████████████████████████████████████████████████▊ | 76/103 [00:00<00:00, 10122.80it/s, Materializing param=encoder.layer.4.attention.self.query.bias]
|
||
Loading weights: 75%|█████████████████████████████████████████████████████████████████████████▎ | 77/103 [00:00<00:00, 10170.41it/s, Materializing param=encoder.layer.4.attention.self.query.weight]
|
||
Loading weights: 75%|█████████████████████████████████████████████████████████████████████████▎ | 77/103 [00:00<00:00, 10113.72it/s, Materializing param=encoder.layer.4.attention.self.query.weight]
|
||
Loading weights: 76%|███████████████████████████████████████████████████████████████████████████▋ | 78/103 [00:00<00:00, 10171.80it/s, Materializing param=encoder.layer.4.attention.self.value.bias]
|
||
Loading weights: 76%|███████████████████████████████████████████████████████████████████████████▋ | 78/103 [00:00<00:00, 10117.07it/s, Materializing param=encoder.layer.4.attention.self.value.bias]
|
||
Loading weights: 77%|███████████████████████████████████████████████████████████████████████████▏ | 79/103 [00:00<00:00, 10176.60it/s, Materializing param=encoder.layer.4.attention.self.value.weight]
|
||
Loading weights: 77%|███████████████████████████████████████████████████████████████████████████▏ | 79/103 [00:00<00:00, 10122.50it/s, Materializing param=encoder.layer.4.attention.self.value.weight]
|
||
Loading weights: 78%|███████████████████████████████████████████████████████████████████████████████▏ | 80/103 [00:00<00:00, 10181.59it/s, Materializing param=encoder.layer.4.intermediate.dense.bias]
|
||
Loading weights: 78%|███████████████████████████████████████████████████████████████████████████████▏ | 80/103 [00:00<00:00, 10128.42it/s, Materializing param=encoder.layer.4.intermediate.dense.bias]
|
||
Loading weights: 79%|██████████████████████████████████████████████████████████████████████████████▋ | 81/103 [00:00<00:00, 10187.98it/s, Materializing param=encoder.layer.4.intermediate.dense.weight]
|
||
Loading weights: 79%|██████████████████████████████████████████████████████████████████████████████▋ | 81/103 [00:00<00:00, 10135.70it/s, Materializing param=encoder.layer.4.intermediate.dense.weight]
|
||
Loading weights: 80%|██████████████████████████████████████████████████████████████████████████████████▊ | 82/103 [00:00<00:00, 10190.91it/s, Materializing param=encoder.layer.4.output.LayerNorm.bias]
|
||
Loading weights: 80%|██████████████████████████████████████████████████████████████████████████████████▊ | 82/103 [00:00<00:00, 10138.64it/s, Materializing param=encoder.layer.4.output.LayerNorm.bias]
|
||
Loading weights: 81%|██████████████████████████████████████████████████████████████████████████████████▏ | 83/103 [00:00<00:00, 10196.75it/s, Materializing param=encoder.layer.4.output.LayerNorm.weight]
|
||
Loading weights: 81%|██████████████████████████████████████████████████████████████████████████████████▏ | 83/103 [00:00<00:00, 10146.23it/s, Materializing param=encoder.layer.4.output.LayerNorm.weight]
|
||
Loading weights: 82%|████████████████████████████████████████████████████████████████████████████████████████ | 84/103 [00:00<00:00, 10204.23it/s, Materializing param=encoder.layer.4.output.dense.bias]
|
||
Loading weights: 82%|████████████████████████████████████████████████████████████████████████████████████████ | 84/103 [00:00<00:00, 10153.65it/s, Materializing param=encoder.layer.4.output.dense.bias]
|
||
Loading weights: 83%|███████████████████████████████████████████████████████████████████████████████████████▍ | 85/103 [00:00<00:00, 10210.96it/s, Materializing param=encoder.layer.4.output.dense.weight]
|
||
Loading weights: 83%|███████████████████████████████████████████████████████████████████████████████████████▍ | 85/103 [00:00<00:00, 10158.88it/s, Materializing param=encoder.layer.4.output.dense.weight]
|
||
Loading weights: 83%|██████████████████████████████████████████████████████████████████████████████▍ | 86/103 [00:00<00:00, 10214.37it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.bias]
|
||
Loading weights: 83%|██████████████████████████████████████████████████████████████████████████████▍ | 86/103 [00:00<00:00, 10156.56it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.bias]
|
||
Loading weights: 84%|█████████████████████████████████████████████████████████████████████████████▋ | 87/103 [00:00<00:00, 10202.27it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.weight]
|
||
Loading weights: 84%|█████████████████████████████████████████████████████████████████████████████▋ | 87/103 [00:00<00:00, 10151.46it/s, Materializing param=encoder.layer.5.attention.output.LayerNorm.weight]
|
||
Loading weights: 85%|███████████████████████████████████████████████████████████████████████████████████▋ | 88/103 [00:00<00:00, 10203.71it/s, Materializing param=encoder.layer.5.attention.output.dense.bias]
|
||
Loading weights: 85%|███████████████████████████████████████████████████████████████████████████████████▋ | 88/103 [00:00<00:00, 10154.58it/s, Materializing param=encoder.layer.5.attention.output.dense.bias]
|
||
Loading weights: 86%|██████████████████████████████████████████████████████████████████████████████████▉ | 89/103 [00:00<00:00, 10207.07it/s, Materializing param=encoder.layer.5.attention.output.dense.weight]
|
||
Loading weights: 86%|██████████████████████████████████████████████████████████████████████████████████▉ | 89/103 [00:00<00:00, 10154.59it/s, Materializing param=encoder.layer.5.attention.output.dense.weight]
|
||
Loading weights: 87%|█████████████████████████████████████████████████████████████████████████████████████████▏ | 90/103 [00:00<00:00, 10207.60it/s, Materializing param=encoder.layer.5.attention.self.key.bias]
|
||
Loading weights: 87%|█████████████████████████████████████████████████████████████████████████████████████████▏ | 90/103 [00:00<00:00, 10160.89it/s, Materializing param=encoder.layer.5.attention.self.key.bias]
|
||
Loading weights: 88%|████████████████████████████████████████████████████████████████████████████████████████▎ | 91/103 [00:00<00:00, 10214.13it/s, Materializing param=encoder.layer.5.attention.self.key.weight]
|
||
Loading weights: 88%|████████████████████████████████████████████████████████████████████████████████████████▎ | 91/103 [00:00<00:00, 10167.33it/s, Materializing param=encoder.layer.5.attention.self.key.weight]
|
||
Loading weights: 89%|█████████████████████████████████████████████████████████████████████████████████████████▎ | 92/103 [00:00<00:00, 10219.17it/s, Materializing param=encoder.layer.5.attention.self.query.bias]
|
||
Loading weights: 89%|█████████████████████████████████████████████████████████████████████████████████████████▎ | 92/103 [00:00<00:00, 10158.64it/s, Materializing param=encoder.layer.5.attention.self.query.bias]
|
||
Loading weights: 90%|████████████████████████████████████████████████████████████████████████████████████████▍ | 93/103 [00:00<00:00, 10209.66it/s, Materializing param=encoder.layer.5.attention.self.query.weight]
|
||
Loading weights: 90%|████████████████████████████████████████████████████████████████████████████████████████▍ | 93/103 [00:00<00:00, 10164.17it/s, Materializing param=encoder.layer.5.attention.self.query.weight]
|
||
Loading weights: 91%|███████████████████████████████████████████████████████████████████████████████████████████▎ | 94/103 [00:00<00:00, 10215.96it/s, Materializing param=encoder.layer.5.attention.self.value.bias]
|
||
Loading weights: 91%|███████████████████████████████████████████████████████████████████████████████████████████▎ | 94/103 [00:00<00:00, 10170.90it/s, Materializing param=encoder.layer.5.attention.self.value.bias]
|
||
Loading weights: 92%|██████████████████████████████████████████████████████████████████████████████████████████▍ | 95/103 [00:00<00:00, 10222.14it/s, Materializing param=encoder.layer.5.attention.self.value.weight]
|
||
Loading weights: 92%|██████████████████████████████████████████████████████████████████████████████████████████▍ | 95/103 [00:00<00:00, 10177.75it/s, Materializing param=encoder.layer.5.attention.self.value.weight]
|
||
Loading weights: 93%|███████████████████████████████████████████████████████████████████████████████████████████████ | 96/103 [00:00<00:00, 10228.19it/s, Materializing param=encoder.layer.5.intermediate.dense.bias]
|
||
Loading weights: 93%|███████████████████████████████████████████████████████████████████████████████████████████████ | 96/103 [00:00<00:00, 10184.73it/s, Materializing param=encoder.layer.5.intermediate.dense.bias]
|
||
Loading weights: 94%|██████████████████████████████████████████████████████████████████████████████████████████████▏ | 97/103 [00:00<00:00, 10213.06it/s, Materializing param=encoder.layer.5.intermediate.dense.weight]
|
||
Loading weights: 94%|██████████████████████████████████████████████████████████████████████████████████████████████▏ | 97/103 [00:00<00:00, 10165.34it/s, Materializing param=encoder.layer.5.intermediate.dense.weight]
|
||
Loading weights: 95%|██████████████████████████████████████████████████████████████████████████████████████████████████▉ | 98/103 [00:00<00:00, 10214.25it/s, Materializing param=encoder.layer.5.output.LayerNorm.bias]
|
||
Loading weights: 95%|██████████████████████████████████████████████████████████████████████████████████████████████████▉ | 98/103 [00:00<00:00, 10171.78it/s, Materializing param=encoder.layer.5.output.LayerNorm.bias]
|
||
Loading weights: 96%|██████████████████████████████████████████████████████████████████████████████████████████████████ | 99/103 [00:00<00:00, 10221.70it/s, Materializing param=encoder.layer.5.output.LayerNorm.weight]
|
||
Loading weights: 96%|██████████████████████████████████████████████████████████████████████████████████████████████████ | 99/103 [00:00<00:00, 10179.10it/s, Materializing param=encoder.layer.5.output.LayerNorm.weight]
|
||
Loading weights: 97%|███████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 100/103 [00:00<00:00, 10228.26it/s, Materializing param=encoder.layer.5.output.dense.bias]
|
||
Loading weights: 97%|███████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 100/103 [00:00<00:00, 10184.30it/s, Materializing param=encoder.layer.5.output.dense.bias]
|
||
Loading weights: 98%|██████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 101/103 [00:00<00:00, 10232.48it/s, Materializing param=encoder.layer.5.output.dense.weight]
|
||
Loading weights: 98%|██████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 101/103 [00:00<00:00, 10191.13it/s, Materializing param=encoder.layer.5.output.dense.weight]
|
||
Loading weights: 99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ | 102/103 [00:00<00:00, 10231.23it/s, Materializing param=pooler.dense.bias]
|
||
Loading weights: 99%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ | 102/103 [00:00<00:00, 10189.81it/s, Materializing param=pooler.dense.bias]
|
||
Loading weights: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 103/103 [00:00<00:00, 10238.50it/s, Materializing param=pooler.dense.weight]
|
||
Loading weights: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 103/103 [00:00<00:00, 10198.37it/s, Materializing param=pooler.dense.weight]
|
||
Loading weights: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 103/103 [00:00<00:00, 10135.69it/s, Materializing param=pooler.dense.weight]
|
||
[1mBertModel LOAD REPORT[0m from: /home/songsenand/.cache/modelscope/hub/models/iic/nlp_structbert_backbone_lite_std
|
||
Key | Status | Details
|
||
-------------------------------------------+------------+--------
|
||
cls.predictions.bias | UNEXPECTED |
|
||
cls.seq_relationship.bias | UNEXPECTED |
|
||
cls.predictions.transform.dense.weight | UNEXPECTED |
|
||
cls.predictions.decoder.bias | UNEXPECTED |
|
||
cls.seq_relationship.weight | UNEXPECTED |
|
||
cls.predictions.transform.dense.bias | UNEXPECTED |
|
||
bert.embeddings.position_ids | UNEXPECTED |
|
||
cls.predictions.transform.LayerNorm.weight | UNEXPECTED |
|
||
cls.predictions.decoder.weight | UNEXPECTED |
|
||
cls.predictions.transform.LayerNorm.bias | UNEXPECTED |
|
||
|
||
[3mNotes:
|
||
- UNEXPECTED[3m :can be ignored when loading from different task/architecture; not ok if you expect identical arch.[0m
|
||
/home/songsenand/Project/SUimeModelTraner/export_onnx.py:84: UserWarning: # 'dynamic_axes' is not recommended when dynamo=True, and may lead to 'torch._dynamo.exc.UserError: Constraints violated.' Supply the 'dynamic_shapes' argument instead if export is unsuccessful.
|
||
torch.onnx.export(
|
||
W0417 14:31:59.817000 710675 .venv/lib/python3.12/site-packages/torch/onnx/_internal/exporter/_compat.py:133] Setting ONNX exporter to use operator set version 18 because the requested opset_version 14 is a lower version than we have implementations for. Automatic version conversion will be performed, which may not be successful at converting to the requested version. If version conversion is unsuccessful, the opset version of the exported model will be kept at 18. Please consider setting opset_version >=18 to leverage latest ONNX features
|
||
W0417 14:32:00.100000 710675 .venv/lib/python3.12/site-packages/torch/onnx/_internal/exporter/_registration.py:110] torchvision is not installed. Skipping torchvision::nms
|
||
W0417 14:32:00.101000 710675 .venv/lib/python3.12/site-packages/torch/onnx/_internal/exporter/_registration.py:110] torchvision is not installed. Skipping torchvision::roi_align
|
||
W0417 14:32:00.101000 710675 .venv/lib/python3.12/site-packages/torch/onnx/_internal/exporter/_registration.py:110] torchvision is not installed. Skipping torchvision::roi_pool
|
||
/home/songsenand/.local/share/uv/python/cpython-3.12.12-linux-x86_64-gnu/lib/python3.12/contextlib.py:144: UserWarning: The tensor attributes self.pinyin_lstm._flat_weights[0], self.pinyin_lstm._flat_weights[1], self.pinyin_lstm._flat_weights[2], self.pinyin_lstm._flat_weights[3], self.pinyin_lstm._flat_weights[4], self.pinyin_lstm._flat_weights[5], self.pinyin_lstm._flat_weights[6], self.pinyin_lstm._flat_weights[7], self.pinyin_lstm._flat_weights[8], self.pinyin_lstm._flat_weights[9], self.pinyin_lstm._flat_weights[10], self.pinyin_lstm._flat_weights[11], self.pinyin_lstm._flat_weights[12], self.pinyin_lstm._flat_weights[13], self.pinyin_lstm._flat_weights[14], self.pinyin_lstm._flat_weights[15] were assigned during export. Such attributes must be registered as buffers using the `register_buffer` API (https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.register_buffer).
|
||
next(self.gen)
|
||
/home/songsenand/.local/share/uv/python/cpython-3.12.12-linux-x86_64-gnu/lib/python3.12/copyreg.py:99: FutureWarning: `isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
|
||
return cls.__new__(cls, *args)
|
||
The model version conversion is not supported by the onnxscript version converter and fallback is enabled. The model will be converted using the onnx C API (target version: 14).
|
||
Failed to convert the model to the target version 14 using the ONNX C API. The model was not modified
|
||
Traceback (most recent call last):
|
||
File "/home/songsenand/Project/SUimeModelTraner/.venv/lib/python3.12/site-packages/onnxscript/version_converter/__init__.py", line 120, in call
|
||
converted_proto = _c_api_utils.call_onnx_api(
|
||
^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||
File "/home/songsenand/Project/SUimeModelTraner/.venv/lib/python3.12/site-packages/onnxscript/version_converter/_c_api_utils.py", line 65, in call_onnx_api
|
||
result = func(proto)
|
||
^^^^^^^^^^^
|
||
File "/home/songsenand/Project/SUimeModelTraner/.venv/lib/python3.12/site-packages/onnxscript/version_converter/__init__.py", line 115, in _partial_convert_version
|
||
return onnx.version_converter.convert_version(
|
||
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||
File "/home/songsenand/Project/SUimeModelTraner/.venv/lib/python3.12/site-packages/onnx/version_converter.py", line 39, in convert_version
|
||
converted_model_str = C.convert_version(model_str, target_version)
|
||
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||
RuntimeError: /github/workspace/onnx/version_converter/adapters/no_previous_version.h:24: adapt: Assertion `false` failed: No Previous Version of LayerNormalization exists
|
||
/home/songsenand/Project/SUimeModelTraner/.venv/lib/python3.12/site-packages/torch/onnx/_internal/exporter/_onnx_program.py:487: UserWarning: # The axis name: batch_size will not be used, since it shares the same shape constraints with another axis: batch_size.
|
||
rename_mapping = _dynamic_shapes.create_rename_mapping(
|
||
/home/songsenand/Project/SUimeModelTraner/.venv/lib/python3.12/site-packages/torch/onnx/_internal/exporter/_onnx_program.py:487: UserWarning: # The axis name: seq_len will not be used, since it shares the same shape constraints with another axis: seq_len.
|
||
rename_mapping = _dynamic_shapes.create_rename_mapping(
|
||
/home/songsenand/Project/SUimeModelTraner/.venv/lib/python3.12/site-packages/torch/nn/modules/transformer.py:531: UserWarning: The PyTorch API of nested tensors is in prototype stage and will change in the near future. We recommend specifying layout=torch.jagged when constructing a nested tensor, as this layout receives active development, has better operator coverage, and works with torch.compile. (Triggered internally at /pytorch/aten/src/ATen/NestedTensorImpl.cpp:178.)
|
||
output = torch._nested_tensor_from_mask(
|
||
/home/songsenand/Project/SUimeModelTraner/export_onnx.py:155: UserWarning: # 'dynamic_axes' is not recommended when dynamo=True, and may lead to 'torch._dynamo.exc.UserError: Constraints violated.' Supply the 'dynamic_shapes' argument instead if export is unsuccessful.
|
||
torch.onnx.export(
|
||
W0417 14:32:05.304000 710675 .venv/lib/python3.12/site-packages/torch/onnx/_internal/exporter/_compat.py:133] Setting ONNX exporter to use operator set version 18 because the requested opset_version 14 is a lower version than we have implementations for. Automatic version conversion will be performed, which may not be successful at converting to the requested version. If version conversion is unsuccessful, the opset version of the exported model will be kept at 18. Please consider setting opset_version >=18 to leverage latest ONNX features
|
||
W0417 14:32:05.492000 710675 .venv/lib/python3.12/site-packages/torch/onnx/_internal/exporter/_registration.py:110] torchvision is not installed. Skipping torchvision::nms
|
||
W0417 14:32:05.492000 710675 .venv/lib/python3.12/site-packages/torch/onnx/_internal/exporter/_registration.py:110] torchvision is not installed. Skipping torchvision::roi_align
|
||
W0417 14:32:05.492000 710675 .venv/lib/python3.12/site-packages/torch/onnx/_internal/exporter/_registration.py:110] torchvision is not installed. Skipping torchvision::roi_pool
|
||
/home/songsenand/.local/share/uv/python/cpython-3.12.12-linux-x86_64-gnu/lib/python3.12/copyreg.py:99: FutureWarning: `isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
|
||
return cls.__new__(cls, *args)
|
||
The model version conversion is not supported by the onnxscript version converter and fallback is enabled. The model will be converted using the onnx C API (target version: 14).
|
||
Failed to convert the model to the target version 14 using the ONNX C API. The model was not modified
|
||
Traceback (most recent call last):
|
||
File "/home/songsenand/Project/SUimeModelTraner/.venv/lib/python3.12/site-packages/onnxscript/version_converter/__init__.py", line 120, in call
|
||
converted_proto = _c_api_utils.call_onnx_api(
|
||
^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||
File "/home/songsenand/Project/SUimeModelTraner/.venv/lib/python3.12/site-packages/onnxscript/version_converter/_c_api_utils.py", line 65, in call_onnx_api
|
||
result = func(proto)
|
||
^^^^^^^^^^^
|
||
File "/home/songsenand/Project/SUimeModelTraner/.venv/lib/python3.12/site-packages/onnxscript/version_converter/__init__.py", line 115, in _partial_convert_version
|
||
return onnx.version_converter.convert_version(
|
||
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||
File "/home/songsenand/Project/SUimeModelTraner/.venv/lib/python3.12/site-packages/onnx/version_converter.py", line 39, in convert_version
|
||
converted_model_str = C.convert_version(model_str, target_version)
|
||
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||
RuntimeError: /github/workspace/onnx/version_converter/adapters/no_previous_version.h:24: adapt: Assertion `false` failed: No Previous Version of LayerNormalization exists
|
||
/home/songsenand/Project/SUimeModelTraner/.venv/lib/python3.12/site-packages/torch/onnx/_internal/exporter/_onnx_program.py:487: UserWarning: # The axis name: batch_size will not be used, since it shares the same shape constraints with another axis: batch_size.
|
||
rename_mapping = _dynamic_shapes.create_rename_mapping(
|
||
/home/songsenand/Project/SUimeModelTraner/.venv/lib/python3.12/site-packages/torch/onnx/_internal/exporter/_onnx_program.py:487: UserWarning: # The axis name: seq_len will not be used, since it shares the same shape constraints with another axis: seq_len.
|
||
rename_mapping = _dynamic_shapes.create_rename_mapping(
|
||
📊 模型配置: {'learning_rate': 1e-06, 'weight_decay': 0.05, 'warmup_ratio': 0.1, 'label_smoothing': 0.1, 'total_steps': 781250}
|
||
正在导出上下文编码器到: exported_models/context_encoder.onnx
|
||
Applied 77 of general pattern rewrite rules.
|
||
✅ 上下文编码器导出完成
|
||
✅ ONNX模型验证通过
|
||
正在导解码器到: exported_models/decoder.onnx
|
||
Applied 21 of general pattern rewrite rules.
|
||
✅ 解码器导出完成
|
||
✅ ONNX模型验证通过
|
||
✅ 示例输入已保存到: exported_models/example_inputs.npz
|
||
✅ PyTorch示例输入已保存到: exported_models/example_inputs.pt
|
||
✅ 推理示例脚本已保存到: exported_models/inference_example.py
|
||
|
||
============================================================
|
||
🎉 ONNX导出完成！
|
||
============================================================
|
||
生成的模型文件:
|
||
- exported_models/context_encoder.onnx
|
||
- exported_models/decoder.onnx
|
||
- exported_models/example_inputs.npz
|
||
- exported_models/example_inputs.pt
|
||
- exported_models/inference_example.py
|
||
|
||
使用方法:
|
||
1. 检查模型: python -m onnx.checker exported_models/context_encoder.onnx
|
||
2. 运行推理示例: cd exported_models && python inference_example.py
|
||
3. 集成到您的应用: 参考inference_example.py中的ONNXInference类
|
||
|
||
注意:
|
||
- 请确保安装了onnxruntime: pip install onnxruntime
|
||
- GPU推理需要onnxruntime-gpu: pip install onnxruntime-gpu
|
||
- 束搜索算法需要根据实际需求进行调整
|