| { | |
| "best_metric": 0.09626218676567078, | |
| "best_model_checkpoint": "checkpoint/checkpoint-300000", | |
| "epoch": 0.8551077008149176, | |
| "global_step": 300000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.942992819945672e-05, | |
| "loss": 0.0499, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8859856398913445e-05, | |
| "loss": 0.0274, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8289784598370164e-05, | |
| "loss": 0.0244, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7719712797826888e-05, | |
| "loss": 0.0218, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.714964099728361e-05, | |
| "loss": 0.0208, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.9703630265572595, | |
| "eval_f1": 0.9697362965196742, | |
| "eval_loss": 0.19255024194717407, | |
| "eval_precision": 0.9906862367555316, | |
| "eval_recall": 0.949654059527074, | |
| "eval_runtime": 7138.3308, | |
| "eval_samples_per_second": 53.13, | |
| "eval_steps_per_second": 6.641, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.657956919674033e-05, | |
| "loss": 0.018, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.600949739619705e-05, | |
| "loss": 0.0173, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5439425595653774e-05, | |
| "loss": 0.0182, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.4869353795110495e-05, | |
| "loss": 0.0168, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4299281994567218e-05, | |
| "loss": 0.0152, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.9694269833568883, | |
| "eval_f1": 0.9686356296001752, | |
| "eval_loss": 0.26416775584220886, | |
| "eval_precision": 0.9943740662782754, | |
| "eval_recall": 0.9441960048094163, | |
| "eval_runtime": 7120.7469, | |
| "eval_samples_per_second": 53.261, | |
| "eval_steps_per_second": 6.658, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.3729210194023938e-05, | |
| "loss": 0.0167, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.315913839348066e-05, | |
| "loss": 0.0143, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.2589066592937383e-05, | |
| "loss": 0.0151, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2018994792394103e-05, | |
| "loss": 0.0127, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1448922991850824e-05, | |
| "loss": 0.0129, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.9814399772185542, | |
| "eval_f1": 0.9811897565811801, | |
| "eval_loss": 0.14654095470905304, | |
| "eval_precision": 0.9945986358440376, | |
| "eval_recall": 0.9681376168076444, | |
| "eval_runtime": 7098.6821, | |
| "eval_samples_per_second": 53.426, | |
| "eval_steps_per_second": 6.678, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.0878851191307547e-05, | |
| "loss": 0.0166, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0308779390764267e-05, | |
| "loss": 0.0133, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.738707590220989e-06, | |
| "loss": 0.0117, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.168635789677712e-06, | |
| "loss": 0.0104, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.598563989134432e-06, | |
| "loss": 0.0111, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.9705159575590103, | |
| "eval_f1": 0.9696535478373199, | |
| "eval_loss": 0.31930962204933167, | |
| "eval_precision": 0.9988705619233995, | |
| "eval_recall": 0.9420971586474571, | |
| "eval_runtime": 7105.0574, | |
| "eval_samples_per_second": 53.378, | |
| "eval_steps_per_second": 6.672, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.028492188591153e-06, | |
| "loss": 0.0103, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.4584203880478754e-06, | |
| "loss": 0.0113, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.888348587504596e-06, | |
| "loss": 0.0083, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.3182767869613184e-06, | |
| "loss": 0.008, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.74820498641804e-06, | |
| "loss": 0.008, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.976308878435674, | |
| "eval_f1": 0.9758237027270649, | |
| "eval_loss": 0.20410259068012238, | |
| "eval_precision": 0.996225627276573, | |
| "eval_recall": 0.9562406395679963, | |
| "eval_runtime": 7119.7261, | |
| "eval_samples_per_second": 53.268, | |
| "eval_steps_per_second": 6.659, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.178133185874762e-06, | |
| "loss": 0.0086, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.608061385331483e-06, | |
| "loss": 0.0067, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.0379895847882044e-06, | |
| "loss": 0.007, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.467917784244926e-06, | |
| "loss": 0.0059, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.8978459837016474e-06, | |
| "loss": 0.0061, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.9880529246735714, | |
| "eval_f1": 0.9879724036876487, | |
| "eval_loss": 0.09626218676567078, | |
| "eval_precision": 0.9946763305164922, | |
| "eval_recall": 0.9813582382348598, | |
| "eval_runtime": 7136.9095, | |
| "eval_samples_per_second": 53.14, | |
| "eval_steps_per_second": 6.643, | |
| "step": 300000 | |
| } | |
| ], | |
| "max_steps": 350833, | |
| "num_train_epochs": 1, | |
| "total_flos": 2.7489826686811325e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |