| { | |
| "best_metric": 0.45565962643131613, | |
| "best_model_checkpoint": "", | |
| "epoch": 4.0, | |
| "global_step": 255184, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2e-10, | |
| "loss": 0.5804, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1e-06, | |
| "loss": 0.3416, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2e-06, | |
| "loss": 0.2775, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.967635445659913e-06, | |
| "loss": 0.2661, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.9352708913198264e-06, | |
| "loss": 0.2615, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.9029063369797399e-06, | |
| "loss": 0.2637, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.870541782639653e-06, | |
| "loss": 0.2597, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.8381772282995661e-06, | |
| "loss": 0.2546, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8058126739594794e-06, | |
| "loss": 0.2593, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.7734481196193926e-06, | |
| "loss": 0.2515, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.741083565279306e-06, | |
| "loss": 0.2546, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.7087190109392193e-06, | |
| "loss": 0.2567, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.6763544565991326e-06, | |
| "loss": 0.2528, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.21571615150195908, | |
| "eval_auc": 0.9180686985375446, | |
| "eval_f1": 0.22147402418434062, | |
| "eval_loss": 1.4364598989486694, | |
| "eval_precision": 0.908817624677932, | |
| "eval_recall": 0.21571615150195908, | |
| "eval_runtime": 4.8065, | |
| "eval_samples_per_second": 955.789, | |
| "step": 63796 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.6439899022590458e-06, | |
| "loss": 0.2493, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.611625347918959e-06, | |
| "loss": 0.2448, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1.5792607935788725e-06, | |
| "loss": 0.2507, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.5468962392387856e-06, | |
| "loss": 0.2445, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.5145316848986988e-06, | |
| "loss": 0.2481, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.482167130558612e-06, | |
| "loss": 0.2452, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.4498025762185253e-06, | |
| "loss": 0.2442, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.4174380218784387e-06, | |
| "loss": 0.2443, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 1.385073467538352e-06, | |
| "loss": 0.246, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 1.3527089131982652e-06, | |
| "loss": 0.2503, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.3203443588581785e-06, | |
| "loss": 0.2492, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.2879798045180917e-06, | |
| "loss": 0.2429, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.255615250178005e-06, | |
| "loss": 0.2491, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.3243360905528951, | |
| "eval_auc": 0.9164518557207816, | |
| "eval_f1": 0.3794720254407353, | |
| "eval_loss": 1.2563140392303467, | |
| "eval_precision": 0.9077943374743213, | |
| "eval_recall": 0.3243360905528951, | |
| "eval_runtime": 4.7493, | |
| "eval_samples_per_second": 967.295, | |
| "step": 127592 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.2232506958379182e-06, | |
| "loss": 0.2508, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.1908861414978315e-06, | |
| "loss": 0.2422, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.1585215871577447e-06, | |
| "loss": 0.2404, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.126157032817658e-06, | |
| "loss": 0.2347, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.0937924784775714e-06, | |
| "loss": 0.2441, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1.0614279241374847e-06, | |
| "loss": 0.2456, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 1.029063369797398e-06, | |
| "loss": 0.2375, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 9.966988154573111e-07, | |
| "loss": 0.2441, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 9.643342611172244e-07, | |
| "loss": 0.2376, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 9.319697067771376e-07, | |
| "loss": 0.2386, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 8.996051524370509e-07, | |
| "loss": 0.2387, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 8.672405980969641e-07, | |
| "loss": 0.238, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 8.348760437568775e-07, | |
| "loss": 0.234, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.32063561166739224, | |
| "eval_auc": 0.9156791507926754, | |
| "eval_f1": 0.3746009193872616, | |
| "eval_loss": 1.388353705406189, | |
| "eval_precision": 0.9076853642985949, | |
| "eval_recall": 0.32063561166739224, | |
| "eval_runtime": 4.7646, | |
| "eval_samples_per_second": 964.188, | |
| "step": 191388 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 8.025114894167907e-07, | |
| "loss": 0.2366, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 7.70146935076704e-07, | |
| "loss": 0.2343, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 7.377823807366172e-07, | |
| "loss": 0.2353, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 7.054178263965305e-07, | |
| "loss": 0.2353, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 6.730532720564438e-07, | |
| "loss": 0.2328, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 6.40688717716357e-07, | |
| "loss": 0.2332, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 6.083241633762702e-07, | |
| "loss": 0.2374, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 5.759596090361835e-07, | |
| "loss": 0.2367, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 5.435950546960968e-07, | |
| "loss": 0.2379, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 5.112305003560101e-07, | |
| "loss": 0.2354, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 4.788659460159234e-07, | |
| "loss": 0.235, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 4.4650139167583663e-07, | |
| "loss": 0.2362, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.1413683733574987e-07, | |
| "loss": 0.24, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.38528515454941226, | |
| "eval_auc": 0.9194136352464053, | |
| "eval_f1": 0.45565962643131613, | |
| "eval_loss": 1.2999894618988037, | |
| "eval_precision": 0.9088106767314909, | |
| "eval_recall": 0.38528515454941226, | |
| "eval_runtime": 4.7332, | |
| "eval_samples_per_second": 970.591, | |
| "step": 255184 | |
| } | |
| ], | |
| "max_steps": 318980, | |
| "num_train_epochs": 5, | |
| "total_flos": 4.841807205051138e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |