| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 20019, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9500474549178283e-05, | |
| "loss": 0.2824, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.900094909835656e-05, | |
| "loss": 0.1069, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.8501423647534843e-05, | |
| "loss": 0.0803, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.8001898196713125e-05, | |
| "loss": 0.0716, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.7502372745891407e-05, | |
| "loss": 0.0684, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.7002847295069685e-05, | |
| "loss": 0.0469, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.6503321844247966e-05, | |
| "loss": 0.0547, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.6003796393426248e-05, | |
| "loss": 0.0426, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.5504270942604526e-05, | |
| "loss": 0.04, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.5004745491782808e-05, | |
| "loss": 0.0373, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.4505220040961088e-05, | |
| "loss": 0.0346, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.400569459013937e-05, | |
| "loss": 0.0367, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.3506169139317648e-05, | |
| "loss": 0.0368, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9924870532775087, | |
| "eval_f1": 0.9475109741290744, | |
| "eval_loss": 0.03183424845337868, | |
| "eval_precision": 0.9483967467514256, | |
| "eval_recall": 0.9466268545301857, | |
| "eval_runtime": 1480.2297, | |
| "eval_samples_per_second": 4.503, | |
| "eval_steps_per_second": 0.563, | |
| "step": 6673 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.300664368849593e-05, | |
| "loss": 0.0252, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.250711823767421e-05, | |
| "loss": 0.0222, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.2007592786852491e-05, | |
| "loss": 0.0198, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.1508067336030773e-05, | |
| "loss": 0.02, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.1008541885209053e-05, | |
| "loss": 0.0232, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.0509016434387333e-05, | |
| "loss": 0.0215, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.0009490983565613e-05, | |
| "loss": 0.0196, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 9.509965532743894e-06, | |
| "loss": 0.0157, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 9.010440081922174e-06, | |
| "loss": 0.0193, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 8.510914631100456e-06, | |
| "loss": 0.0168, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.011389180278736e-06, | |
| "loss": 0.0149, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 7.511863729457016e-06, | |
| "loss": 0.0151, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 7.012338278635297e-06, | |
| "loss": 0.0205, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9948726133711071, | |
| "eval_f1": 0.9672962411611462, | |
| "eval_loss": 0.025242876261472702, | |
| "eval_precision": 0.9645143334261063, | |
| "eval_recall": 0.9700942427918261, | |
| "eval_runtime": 534.1651, | |
| "eval_samples_per_second": 12.479, | |
| "eval_steps_per_second": 1.561, | |
| "step": 13346 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 6.5128128278135775e-06, | |
| "loss": 0.0147, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 6.013287376991859e-06, | |
| "loss": 0.0089, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 5.513761926170139e-06, | |
| "loss": 0.0076, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 5.01423647534842e-06, | |
| "loss": 0.0095, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 4.5147110245267e-06, | |
| "loss": 0.0068, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.015185573704981e-06, | |
| "loss": 0.0086, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 3.515660122883261e-06, | |
| "loss": 0.0079, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 3.016134672061542e-06, | |
| "loss": 0.006, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 2.5166092212398226e-06, | |
| "loss": 0.0073, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.017083770418103e-06, | |
| "loss": 0.006, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.5175583195963836e-06, | |
| "loss": 0.0078, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.0180328687746642e-06, | |
| "loss": 0.0088, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 5.185074179529447e-07, | |
| "loss": 0.0044, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.898196713122534e-08, | |
| "loss": 0.0058, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9955338438868954, | |
| "eval_f1": 0.9709202396989827, | |
| "eval_loss": 0.02311655320227146, | |
| "eval_precision": 0.9667437557816836, | |
| "eval_recall": 0.9751329663152002, | |
| "eval_runtime": 659.1007, | |
| "eval_samples_per_second": 10.114, | |
| "eval_steps_per_second": 1.265, | |
| "step": 20019 | |
| } | |
| ], | |
| "max_steps": 20019, | |
| "num_train_epochs": 3, | |
| "total_flos": 9909919084990896.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |