| device cuda |
| dtype fp32 |
| [transformers] The fast path is not available because one of the required library is not installed. Falling back to torch implementation. To install follow https://github.com/fla-org/flash-linear-attention#installation and https://github.com/Dao-AILab/causal-conv1d |
|
Loading weights: 0%| | 0/426 [00:00<?, ?it/s]
Loading weights: 16%|█▌ | 67/426 [00:00<00:00, 665.41it/s]
Loading weights: 35%|███▍ | 147/426 [00:00<00:00, 743.19it/s]
Loading weights: 53%|█████▎ | 226/426 [00:00<00:00, 759.82it/s]
Loading weights: 72%|███████▏ | 306/426 [00:00<00:00, 766.22it/s]
Loading weights: 90%|█████████ | 385/426 [00:00<00:00, 757.81it/s]
Loading weights: 100%|██████████| 426/426 [00:00<00:00, 759.05it/s] |
| trainable 33776128 |
| train encoded 6000 skipped_over_window 0 |
| dev encoded 1000 skipped_over_window 0 |
| /root/venv/lib/python3.12/site-packages/triton/backends/nvidia/driver.c:9:10: fatal error: Python.h: No such file or directory |
| 9 | #include <Python.h> |
| | ^~~~~~~~~~ |
| compilation terminated. |
| EVAL {"epoch": 0, "dev_n": 1000, "dev_pos": 585, "auc": 0.13048295747090927, "eval_seconds": 46.3, "eval_batched": true, "tpr@0.5": 0.11282051282051282, "fpr@0.5": 0.10120481927710843, "tpr@0.9": 0.041025641025641026, "fpr@0.9": 0.021686746987951807} |
| /root/work/ft_action.py:173: UserWarning: Converting a tensor with requires_grad=True to a scalar may lead to unexpected behavior. |
| Consider using tensor.detach() first. (Triggered internally at /__w/pytorch/pytorch/torch/csrc/autograd/generated/python_variable_methods.cpp:820.) |
| (loss / nq).backward(); tot += float(loss) |
| STEP {"step": 10, "of": 188, "loss": 0.4135213174740784, "lr": 2.9997920847674955e-05, "min": 1.6161548137664794} |
| STEP {"step": 20, "of": 188, "loss": 0.211760422505904, "lr": 2.9749196553607553e-05, "min": 3.4338083108266195} |
| STEP {"step": 30, "of": 188, "loss": 0.10862454999005422, "lr": 2.909340315613169e-05, "min": 5.136755669116974} |
| STEP {"step": 40, "of": 188, "loss": 0.28800655304803513, "lr": 2.8050689290619463e-05, "min": 6.829609147707621} |
| STEP {"step": 50, "of": 188, "loss": 0.16086060367524624, "lr": 2.6653091359929564e-05, "min": 8.571347264448802} |
| STEP {"step": 60, "of": 188, "loss": 0.5306919405702502, "lr": 2.4943549246059348e-05, "min": 10.193756870428722} |
| STEP {"step": 70, "of": 188, "loss": 0.33539796170452973, "lr": 2.2974587022654817e-05, "min": 11.965876241525015} |
| STEP {"step": 80, "of": 188, "loss": 0.3669832006426077, "lr": 2.0806699202246107e-05, "min": 13.620076179504395} |
| STEP {"step": 90, "of": 188, "loss": 0.21168109775408084, "lr": 1.85064920992443e-05, "min": 15.244208375612894} |
| STEP {"step": 100, "of": 188, "loss": 0.1079174259211868, "lr": 1.614463741357356e-05, "min": 17.063996851444244} |
| STEP {"step": 110, "of": 188, "loss": 0.07926618704095745, "lr": 1.3793700909156771e-05, "min": 18.852750595410665} |
| STEP {"step": 120, "of": 188, "loss": 0.5276095138742676, "lr": 1.1525912899066204e-05, "min": 20.624580931663512} |
| STEP {"step": 130, "of": 188, "loss": 0.1399073392385617, "lr": 9.410949037086064e-06, "min": 22.431781423091888} |
| STEP {"step": 140, "of": 188, "loss": 0.08293227139620285, "lr": 7.513789598779036e-06, "min": 24.1434876203537} |
| STEP {"step": 150, "of": 188, "loss": 0.11789616077885512, "lr": 5.892723023632736e-06, "min": 25.918902285893758} |
| STEP {"step": 160, "of": 188, "loss": 0.12585554530733134, "lr": 4.5975550575759965e-06, "min": 27.720150649547577} |
| STEP {"step": 170, "of": 188, "loss": 0.05166304987301373, "lr": 3.6680785182768907e-06, "min": 29.41647714773814} |
| STEP {"step": 180, "of": 188, "loss": 0.28277575302126934, "lr": 3.1328506982444984e-06, "min": 31.251259744167328} |
| Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. |
| SAVED /root/work/ft/secjev_joint/epoch1 |
| EVAL {"epoch": 1, "dev_n": 1000, "dev_pos": 585, "auc": 0.14384512408608793, "eval_seconds": 42.0, "eval_batched": true, "tpr@0.5": 0.13675213675213677, "fpr@0.5": 0.004819277108433735, "tpr@0.9": 0.1264957264957265, "fpr@0.9": 0.0024096385542168677} |
| TRAIN_DONE |
|
|
