| { |
| "best_global_step": 4160, |
| "best_metric": 7243.3740234375, |
| "best_model_checkpoint": "./ckpt/patchtst/output/checkpoint-4160", |
| "epoch": 14.0, |
| "eval_steps": 500, |
| "global_step": 14560, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 36713.9375, |
| "learning_rate": 4.950048076923077e-05, |
| "loss": 23563.9385, |
| "step": 1040 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 8218.5341796875, |
| "eval_runtime": 2.4942, |
| "eval_samples_per_second": 9941.052, |
| "eval_steps_per_second": 155.561, |
| "step": 1040 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 131494.859375, |
| "learning_rate": 4.9000480769230774e-05, |
| "loss": 18700.6135, |
| "step": 2080 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 7677.5400390625, |
| "eval_runtime": 2.4296, |
| "eval_samples_per_second": 10205.474, |
| "eval_steps_per_second": 159.698, |
| "step": 2080 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 43925.23046875, |
| "learning_rate": 4.850048076923077e-05, |
| "loss": 17325.0981, |
| "step": 3120 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 7396.00390625, |
| "eval_runtime": 2.4127, |
| "eval_samples_per_second": 10277.033, |
| "eval_steps_per_second": 160.818, |
| "step": 3120 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 36726.97265625, |
| "learning_rate": 4.800048076923077e-05, |
| "loss": 16331.4615, |
| "step": 4160 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 7243.3740234375, |
| "eval_runtime": 2.3967, |
| "eval_samples_per_second": 10345.543, |
| "eval_steps_per_second": 161.89, |
| "step": 4160 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 115548.1015625, |
| "learning_rate": 4.750048076923077e-05, |
| "loss": 15543.5202, |
| "step": 5200 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 7482.26904296875, |
| "eval_runtime": 2.3764, |
| "eval_samples_per_second": 10434.001, |
| "eval_steps_per_second": 163.275, |
| "step": 5200 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 51385.328125, |
| "learning_rate": 4.700048076923077e-05, |
| "loss": 14856.4, |
| "step": 6240 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 7583.52197265625, |
| "eval_runtime": 2.3809, |
| "eval_samples_per_second": 10414.132, |
| "eval_steps_per_second": 162.964, |
| "step": 6240 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 85444.8671875, |
| "learning_rate": 4.650048076923077e-05, |
| "loss": 14225.3558, |
| "step": 7280 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 7292.68701171875, |
| "eval_runtime": 2.3974, |
| "eval_samples_per_second": 10342.486, |
| "eval_steps_per_second": 161.842, |
| "step": 7280 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 78112.59375, |
| "learning_rate": 4.600048076923077e-05, |
| "loss": 13678.8481, |
| "step": 8320 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 7468.626953125, |
| "eval_runtime": 2.3943, |
| "eval_samples_per_second": 10356.058, |
| "eval_steps_per_second": 162.055, |
| "step": 8320 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 108783.96875, |
| "learning_rate": 4.550048076923077e-05, |
| "loss": 13254.4654, |
| "step": 9360 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 7322.07470703125, |
| "eval_runtime": 2.3977, |
| "eval_samples_per_second": 10341.312, |
| "eval_steps_per_second": 161.824, |
| "step": 9360 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 61333.0703125, |
| "learning_rate": 4.500048076923077e-05, |
| "loss": 12800.8865, |
| "step": 10400 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 7249.888671875, |
| "eval_runtime": 2.3836, |
| "eval_samples_per_second": 10402.213, |
| "eval_steps_per_second": 162.777, |
| "step": 10400 |
| }, |
| { |
| "epoch": 11.0, |
| "grad_norm": 61099.4765625, |
| "learning_rate": 4.450048076923077e-05, |
| "loss": 12409.2356, |
| "step": 11440 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 7354.6484375, |
| "eval_runtime": 2.3858, |
| "eval_samples_per_second": 10392.955, |
| "eval_steps_per_second": 162.632, |
| "step": 11440 |
| }, |
| { |
| "epoch": 12.0, |
| "grad_norm": 72660.046875, |
| "learning_rate": 4.4000480769230774e-05, |
| "loss": 12052.9288, |
| "step": 12480 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 7292.50048828125, |
| "eval_runtime": 2.4038, |
| "eval_samples_per_second": 10315.093, |
| "eval_steps_per_second": 161.414, |
| "step": 12480 |
| }, |
| { |
| "epoch": 13.0, |
| "grad_norm": 125435.6328125, |
| "learning_rate": 4.3500480769230775e-05, |
| "loss": 11751.2288, |
| "step": 13520 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 7339.314453125, |
| "eval_runtime": 2.3646, |
| "eval_samples_per_second": 10485.995, |
| "eval_steps_per_second": 164.088, |
| "step": 13520 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 74969.0078125, |
| "learning_rate": 4.300048076923077e-05, |
| "loss": 11451.826, |
| "step": 14560 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 7366.1162109375, |
| "eval_runtime": 2.4081, |
| "eval_samples_per_second": 10296.633, |
| "eval_steps_per_second": 161.125, |
| "step": 14560 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 104000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 100, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 10, |
| "early_stopping_threshold": 0.0001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 10 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2281399457218560.0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
