Download results/pendulum_multi/logs/final_A_s103.log from matCercola18/DiffusionControl: direct link, hf CLI and curl.
- Browser
- Download file 2.41 kB
-
https://huggingface.co/matCercola18/DiffusionControl/resolve/main/results/pendulum_multi/logs/final_A_s103.log
- Command line
-
hf download hf://matCercola18/DiffusionControl/results/pendulum_multi/logs/final_A_s103.log
-
curl -L -o final_A_s103.log https://huggingface.co/matCercola18/DiffusionControl/resolve/main/results/pendulum_multi/logs/final_A_s103.log
2.41 kB
| /home/cercola/matte_server/DiffusionControl/nonlinear/pendulum_multi/train_multi.py:53: UserWarning: Converting a tensor with requires_grad=True to a scalar may lead to unexpected behavior. | |
| Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/csrc/autograd/generated/python_variable_methods.cpp:836.) | |
| m, med, cov = val_metric(); log.append(dict(step=step, val=m, med=med, cov=cov, loss=float(loss), t=time.time() - t0)) | |
| {"step": 500, "val": 3.0777705879991397, "med": 0.8814744959729097, "cov": 1.0, "loss": 0.04138192906975746, "t": 160.43258953094482} | |
| {"step": 1000, "val": 0.6457873810628444, "med": 0.4453708744113861, "cov": 1.0, "loss": 0.018134387210011482, "t": 302.0306041240692} | |
| {"step": 1500, "val": 0.6073835612438419, "med": 0.3915799105186912, "cov": 1.0, "loss": 0.014142036437988281, "t": 446.61404943466187} | |
| {"step": 2000, "val": 0.48875269947373184, "med": 0.3838905667759034, "cov": 1.0, "loss": 0.01113126240670681, "t": 598.9168479442596} | |
| {"step": 2500, "val": 0.5436797010036897, "med": 0.4225180651211316, "cov": 1.0, "loss": 0.011948191560804844, "t": 739.7004780769348} | |
| {"step": 3000, "val": 0.5420743116582177, "med": 0.47085773214590104, "cov": 1.0, "loss": 0.009503159672021866, "t": 878.7929031848907} | |
| {"step": 3500, "val": 0.5510588123835142, "med": 0.4651746003272588, "cov": 1.0, "loss": 0.006830564234405756, "t": 1025.3958609104156} | |
| {"step": 4000, "val": 0.5468930372168729, "med": 0.4461596721014879, "cov": 1.0, "loss": 0.010739981196820736, "t": 1172.688584804535} | |
| {"step": 4500, "val": 0.5273761613601218, "med": 0.4704381336483857, "cov": 1.0, "loss": 0.006952967960387468, "t": 1318.8214402198792} | |
| {"step": 5000, "val": 0.520489370998997, "med": 0.46730235211195126, "cov": 1.0, "loss": 0.004291607066988945, "t": 1464.7230160236359} | |
| {"step": 5500, "val": 0.5117357281857623, "med": 0.41972756117315435, "cov": 1.0, "loss": 0.00523905036970973, "t": 1611.1928412914276} | |
| {"step": 6000, "val": 0.5451614515490856, "med": 0.44490651879342713, "cov": 1.0, "loss": 0.005097989924252033, "t": 1753.0423731803894} | |
| {"step": 6500, "val": 0.5813620501417037, "med": 0.47887181613646757, "cov": 1.0, "loss": 0.009295275434851646, "t": 1882.0969107151031} | |
| {"step": 7000, "val": 0.5672688777948622, "med": 0.4691180948698058, "cov": 1.0, "loss": 0.006978730671107769, "t": 2000.4323890209198} | |
| early stop | |
| DONE A_s103 best (0.48875269947373184, 2000) 2000s | |