| { | |
| "best_metric": 1.9625495672225952, | |
| "best_model_checkpoint": "output/lil-nas-x/checkpoint-152", | |
| "epoch": 8.0, | |
| "global_step": 152, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00011506151581352585, | |
| "loss": 3.7671, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 6.293505690059801e-05, | |
| "loss": 3.4851, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.4464961055407408e-05, | |
| "loss": 3.237, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.2925262451171875, | |
| "eval_runtime": 1.1351, | |
| "eval_samples_per_second": 22.025, | |
| "eval_steps_per_second": 3.524, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.35614586573241e-07, | |
| "loss": 3.3051, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.1079356352801514e-05, | |
| "loss": 3.2407, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 8.54403044178588e-05, | |
| "loss": 3.0887, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00012893189933276512, | |
| "loss": 3.1123, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.1396188735961914, | |
| "eval_runtime": 1.1208, | |
| "eval_samples_per_second": 22.306, | |
| "eval_steps_per_second": 3.569, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.00013348306278066356, | |
| "loss": 2.9306, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 9.615630613119375e-05, | |
| "loss": 2.8064, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 4.1043693868806304e-05, | |
| "loss": 2.7433, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.7169372193364486e-06, | |
| "loss": 2.7272, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 3.06833553314209, | |
| "eval_runtime": 1.1266, | |
| "eval_samples_per_second": 22.191, | |
| "eval_steps_per_second": 3.551, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 8.268100667234827e-06, | |
| "loss": 2.7817, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 5.175969558214116e-05, | |
| "loss": 2.5931, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 0.0001061206436471984, | |
| "loss": 2.6951, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 0.00013626438541342674, | |
| "loss": 2.4538, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 3.0064802169799805, | |
| "eval_runtime": 1.1266, | |
| "eval_samples_per_second": 22.191, | |
| "eval_steps_per_second": 3.551, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.00012273503894459262, | |
| "loss": 2.3701, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 7.426494309940199e-05, | |
| "loss": 2.2971, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 2.2138484186474223e-05, | |
| "loss": 2.4709, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.1501, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.979142665863037, | |
| "eval_runtime": 1.1215, | |
| "eval_samples_per_second": 22.292, | |
| "eval_steps_per_second": 3.567, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 2.2138484186474162e-05, | |
| "loss": 2.1304, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 7.426494309940202e-05, | |
| "loss": 2.3152, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 0.00012273503894459265, | |
| "loss": 2.3139, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.9424936771392822, | |
| "eval_runtime": 1.1322, | |
| "eval_samples_per_second": 22.081, | |
| "eval_steps_per_second": 3.533, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 0.00013626438541342677, | |
| "loss": 1.9341, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 0.00010612064364719856, | |
| "loss": 2.1993, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 5.1759695582141247e-05, | |
| "loss": 1.9984, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 8.268100667234864e-06, | |
| "loss": 2.0998, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.6141936779022217, | |
| "eval_runtime": 1.2675, | |
| "eval_samples_per_second": 22.091, | |
| "eval_steps_per_second": 3.156, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 3.716937219336464e-06, | |
| "loss": 1.9804, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 4.1043693868806114e-05, | |
| "loss": 2.296, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 9.615630613119378e-05, | |
| "loss": 2.1816, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 0.0001334830627806635, | |
| "loss": 2.0152, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.9625495672225952, | |
| "eval_runtime": 0.9643, | |
| "eval_samples_per_second": 22.814, | |
| "eval_steps_per_second": 3.111, | |
| "step": 152 | |
| } | |
| ], | |
| "max_steps": 152, | |
| "num_train_epochs": 8, | |
| "total_flos": 154684882944000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |