CoolFace
Modelpublic

Coaster41/patchtst_test

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes13downloads
trainer_state.json254 linesDownload Raw Back to root
1{2  "best_global_step": 4160,3  "best_metric": 7243.3740234375,4  "best_model_checkpoint": "./ckpt/patchtst/output/checkpoint-4160",5  "epoch": 14.0,6  "eval_steps": 500,7  "global_step": 14560,8  "is_hyper_param_search": false,9  "is_local_process_zero": true,10  "is_world_process_zero": true,11  "log_history": [12    {13      "epoch": 1.0,14      "grad_norm": 36713.9375,15      "learning_rate": 4.950048076923077e-05,16      "loss": 23563.9385,17      "step": 104018    },19    {20      "epoch": 1.0,21      "eval_loss": 8218.5341796875,22      "eval_runtime": 2.4942,23      "eval_samples_per_second": 9941.052,24      "eval_steps_per_second": 155.561,25      "step": 104026    },27    {28      "epoch": 2.0,29      "grad_norm": 131494.859375,30      "learning_rate": 4.9000480769230774e-05,31      "loss": 18700.6135,32      "step": 208033    },34    {35      "epoch": 2.0,36      "eval_loss": 7677.5400390625,37      "eval_runtime": 2.4296,38      "eval_samples_per_second": 10205.474,39      "eval_steps_per_second": 159.698,40      "step": 208041    },42    {43      "epoch": 3.0,44      "grad_norm": 43925.23046875,45      "learning_rate": 4.850048076923077e-05,46      "loss": 17325.0981,47      "step": 312048    },49    {50      "epoch": 3.0,51      "eval_loss": 7396.00390625,52      "eval_runtime": 2.4127,53      "eval_samples_per_second": 10277.033,54      "eval_steps_per_second": 160.818,55      "step": 312056    },57    {58      "epoch": 4.0,59      "grad_norm": 36726.97265625,60      "learning_rate": 4.800048076923077e-05,61      "loss": 16331.4615,62      "step": 416063    },64    {65      "epoch": 4.0,66      "eval_loss": 7243.3740234375,67      "eval_runtime": 2.3967,68      "eval_samples_per_second": 10345.543,69      "eval_steps_per_second": 161.89,70      "step": 416071    },72    {73      "epoch": 5.0,74      "grad_norm": 115548.1015625,75      "learning_rate": 4.750048076923077e-05,76      "loss": 15543.5202,77      "step": 520078    },79    {80      "epoch": 5.0,81      "eval_loss": 7482.26904296875,82      "eval_runtime": 2.3764,83      "eval_samples_per_second": 10434.001,84      "eval_steps_per_second": 163.275,85      "step": 520086    },87    {88      "epoch": 6.0,89      "grad_norm": 51385.328125,90      "learning_rate": 4.700048076923077e-05,91      "loss": 14856.4,92      "step": 624093    },94    {95      "epoch": 6.0,96      "eval_loss": 7583.52197265625,97      "eval_runtime": 2.3809,98      "eval_samples_per_second": 10414.132,99      "eval_steps_per_second": 162.964,100      "step": 6240101    },102    {103      "epoch": 7.0,104      "grad_norm": 85444.8671875,105      "learning_rate": 4.650048076923077e-05,106      "loss": 14225.3558,107      "step": 7280108    },109    {110      "epoch": 7.0,111      "eval_loss": 7292.68701171875,112      "eval_runtime": 2.3974,113      "eval_samples_per_second": 10342.486,114      "eval_steps_per_second": 161.842,115      "step": 7280116    },117    {118      "epoch": 8.0,119      "grad_norm": 78112.59375,120      "learning_rate": 4.600048076923077e-05,121      "loss": 13678.8481,122      "step": 8320123    },124    {125      "epoch": 8.0,126      "eval_loss": 7468.626953125,127      "eval_runtime": 2.3943,128      "eval_samples_per_second": 10356.058,129      "eval_steps_per_second": 162.055,130      "step": 8320131    },132    {133      "epoch": 9.0,134      "grad_norm": 108783.96875,135      "learning_rate": 4.550048076923077e-05,136      "loss": 13254.4654,137      "step": 9360138    },139    {140      "epoch": 9.0,141      "eval_loss": 7322.07470703125,142      "eval_runtime": 2.3977,143      "eval_samples_per_second": 10341.312,144      "eval_steps_per_second": 161.824,145      "step": 9360146    },147    {148      "epoch": 10.0,149      "grad_norm": 61333.0703125,150      "learning_rate": 4.500048076923077e-05,151      "loss": 12800.8865,152      "step": 10400153    },154    {155      "epoch": 10.0,156      "eval_loss": 7249.888671875,157      "eval_runtime": 2.3836,158      "eval_samples_per_second": 10402.213,159      "eval_steps_per_second": 162.777,160      "step": 10400161    },162    {163      "epoch": 11.0,164      "grad_norm": 61099.4765625,165      "learning_rate": 4.450048076923077e-05,166      "loss": 12409.2356,167      "step": 11440168    },169    {170      "epoch": 11.0,171      "eval_loss": 7354.6484375,172      "eval_runtime": 2.3858,173      "eval_samples_per_second": 10392.955,174      "eval_steps_per_second": 162.632,175      "step": 11440176    },177    {178      "epoch": 12.0,179      "grad_norm": 72660.046875,180      "learning_rate": 4.4000480769230774e-05,181      "loss": 12052.9288,182      "step": 12480183    },184    {185      "epoch": 12.0,186      "eval_loss": 7292.50048828125,187      "eval_runtime": 2.4038,188      "eval_samples_per_second": 10315.093,189      "eval_steps_per_second": 161.414,190      "step": 12480191    },192    {193      "epoch": 13.0,194      "grad_norm": 125435.6328125,195      "learning_rate": 4.3500480769230775e-05,196      "loss": 11751.2288,197      "step": 13520198    },199    {200      "epoch": 13.0,201      "eval_loss": 7339.314453125,202      "eval_runtime": 2.3646,203      "eval_samples_per_second": 10485.995,204      "eval_steps_per_second": 164.088,205      "step": 13520206    },207    {208      "epoch": 14.0,209      "grad_norm": 74969.0078125,210      "learning_rate": 4.300048076923077e-05,211      "loss": 11451.826,212      "step": 14560213    },214    {215      "epoch": 14.0,216      "eval_loss": 7366.1162109375,217      "eval_runtime": 2.4081,218      "eval_samples_per_second": 10296.633,219      "eval_steps_per_second": 161.125,220      "step": 14560221    }222  ],223  "logging_steps": 500,224  "max_steps": 104000,225  "num_input_tokens_seen": 0,226  "num_train_epochs": 100,227  "save_steps": 500,228  "stateful_callbacks": {229    "EarlyStoppingCallback": {230      "args": {231        "early_stopping_patience": 10,232        "early_stopping_threshold": 0.0001233      },234      "attributes": {235        "early_stopping_patience_counter": 10236      }237    },238    "TrainerControl": {239      "args": {240        "should_epoch_stop": false,241        "should_evaluate": false,242        "should_log": false,243        "should_save": true,244        "should_training_stop": true245      },246      "attributes": {}247    }248  },249  "total_flos": 2281399457218560.0,250  "train_batch_size": 64,251  "trial_name": null,252  "trial_params": null253}254