| { | |
| "best_metric": 0.8798324742268041, | |
| "best_model_checkpoint": "bert_trainer/run-0/checkpoint-3000", | |
| "epoch": 3.865979381443299, | |
| "eval_steps": 250, | |
| "global_step": 3000, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.650169893369787e-06, | |
| "loss": 1.4561, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 1.2146, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 1.0949, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.9846, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.9161, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.8466, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.7954, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.7311, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.6688, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.6816, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.7857603092783505, | |
| "eval_loss": 0.6313713192939758, | |
| "eval_runtime": 78.939, | |
| "eval_samples_per_second": 39.322, | |
| "eval_steps_per_second": 9.83, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.6339, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.6102, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.6572, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.6575, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.5946, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.5779, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.5773, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.5461, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.576, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.4864, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.8176546391752577, | |
| "eval_loss": 0.5011568069458008, | |
| "eval_runtime": 78.7987, | |
| "eval_samples_per_second": 39.392, | |
| "eval_steps_per_second": 9.848, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.5618, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.5325, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.4656, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.4966, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.457, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.4715, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.4621, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.4679, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.4236, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.399, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_accuracy": 0.8443943298969072, | |
| "eval_loss": 0.4396892488002777, | |
| "eval_runtime": 78.9384, | |
| "eval_samples_per_second": 39.322, | |
| "eval_steps_per_second": 9.83, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.4321, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3953, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.379, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3415, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3705, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3612, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.4108, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.4167, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3916, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3947, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_accuracy": 0.8579252577319587, | |
| "eval_loss": 0.40539947152137756, | |
| "eval_runtime": 78.7689, | |
| "eval_samples_per_second": 39.406, | |
| "eval_steps_per_second": 9.852, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3812, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3804, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3783, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.337, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3191, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3277, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3601, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3932, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3964, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3705, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_accuracy": 0.8524484536082474, | |
| "eval_loss": 0.40534982085227966, | |
| "eval_runtime": 78.953, | |
| "eval_samples_per_second": 39.315, | |
| "eval_steps_per_second": 9.829, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.4567, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.384, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3205, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3841, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.322, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3742, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3407, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3342, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3068, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3288, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_accuracy": 0.8688788659793815, | |
| "eval_loss": 0.36364319920539856, | |
| "eval_runtime": 78.9463, | |
| "eval_samples_per_second": 39.318, | |
| "eval_steps_per_second": 9.829, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2918, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3571, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3341, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3162, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2384, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2934, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2686, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2806, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2897, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2417, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_accuracy": 0.8743556701030928, | |
| "eval_loss": 0.39001935720443726, | |
| "eval_runtime": 78.9576, | |
| "eval_samples_per_second": 39.312, | |
| "eval_steps_per_second": 9.828, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2849, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2653, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2266, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2401, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2208, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2615, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2913, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2474, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2388, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2374, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_accuracy": 0.8730670103092784, | |
| "eval_loss": 0.39385583996772766, | |
| "eval_runtime": 78.9575, | |
| "eval_samples_per_second": 39.312, | |
| "eval_steps_per_second": 9.828, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2697, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2592, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2636, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2349, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2697, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2507, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2608, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2463, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2408, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3525, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_accuracy": 0.8627577319587629, | |
| "eval_loss": 0.4113520085811615, | |
| "eval_runtime": 78.9601, | |
| "eval_samples_per_second": 39.311, | |
| "eval_steps_per_second": 9.828, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3033, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2186, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2619, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1473, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1662, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1863, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1869, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1729, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1998, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1778, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "eval_accuracy": 0.873389175257732, | |
| "eval_loss": 0.44405418634414673, | |
| "eval_runtime": 78.9751, | |
| "eval_samples_per_second": 39.304, | |
| "eval_steps_per_second": 9.826, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.171, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1642, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2303, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2194, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1756, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1956, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2669, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1514, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1263, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.259, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "eval_accuracy": 0.8566365979381443, | |
| "eval_loss": 0.4988997280597687, | |
| "eval_runtime": 78.9372, | |
| "eval_samples_per_second": 39.322, | |
| "eval_steps_per_second": 9.831, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1378, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1588, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.179, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.3413, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.169, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.208, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1602, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1406, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.1519, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 5.300339786739574e-06, | |
| "loss": 0.2028, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "eval_accuracy": 0.8798324742268041, | |
| "eval_loss": 0.46966859698295593, | |
| "eval_runtime": 78.9816, | |
| "eval_samples_per_second": 39.3, | |
| "eval_steps_per_second": 9.825, | |
| "step": 3000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 3000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 250, | |
| "total_flos": 1.2625987184277504e+16, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 5.300339786739574e-06, | |
| "per_device_eval_batch_size": 4, | |
| "per_device_train_batch_size": 16 | |
| } | |
| } | |