| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 6400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.5625e-06, | |
| "loss": 2.5618, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.125e-06, | |
| "loss": 2.4474, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.6875000000000004e-06, | |
| "loss": 2.3184, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6.25e-06, | |
| "loss": 2.2942, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.8125e-06, | |
| "loss": 2.26, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 2.2509, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.09375e-05, | |
| "loss": 2.2584, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.25e-05, | |
| "loss": 2.2217, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.4062500000000001e-05, | |
| "loss": 2.2244, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 2.181, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.71875e-05, | |
| "loss": 2.1925, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 2.1933, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.0312500000000002e-05, | |
| "loss": 2.1838, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.1875e-05, | |
| "loss": 2.1899, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2.34375e-05, | |
| "loss": 2.1938, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.1664, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.6562500000000002e-05, | |
| "loss": 2.1748, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.8125000000000003e-05, | |
| "loss": 2.184, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.96875e-05, | |
| "loss": 2.1452, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.125e-05, | |
| "loss": 2.155, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.2812500000000005e-05, | |
| "loss": 2.1591, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.4375e-05, | |
| "loss": 2.143, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.59375e-05, | |
| "loss": 2.1634, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 2.1416, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.90625e-05, | |
| "loss": 2.1293, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.0625000000000005e-05, | |
| "loss": 2.1376, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.21875e-05, | |
| "loss": 2.1396, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.375e-05, | |
| "loss": 2.1207, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.5312500000000004e-05, | |
| "loss": 2.123, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 2.1427, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.8437500000000005e-05, | |
| "loss": 2.1515, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1454, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.15625e-05, | |
| "loss": 2.1264, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.3125000000000004e-05, | |
| "loss": 2.1426, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.46875e-05, | |
| "loss": 2.105, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.6250000000000005e-05, | |
| "loss": 2.1243, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.78125e-05, | |
| "loss": 2.1041, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 5.9375e-05, | |
| "loss": 2.124, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 6.0937500000000004e-05, | |
| "loss": 2.1276, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.25e-05, | |
| "loss": 2.1318, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.40625e-05, | |
| "loss": 2.1337, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.562500000000001e-05, | |
| "loss": 2.1159, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.71875e-05, | |
| "loss": 2.1183, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.875e-05, | |
| "loss": 2.1199, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 7.031250000000001e-05, | |
| "loss": 2.1157, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 7.1875e-05, | |
| "loss": 2.09, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 7.34375e-05, | |
| "loss": 2.1108, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.0931, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 7.65625e-05, | |
| "loss": 2.1224, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 7.8125e-05, | |
| "loss": 2.0918, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 7.96875e-05, | |
| "loss": 2.1121, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.125000000000001e-05, | |
| "loss": 2.1009, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.28125e-05, | |
| "loss": 2.1047, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.4375e-05, | |
| "loss": 2.0922, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.593750000000001e-05, | |
| "loss": 2.1091, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.75e-05, | |
| "loss": 2.1061, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 8.90625e-05, | |
| "loss": 2.1206, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.062500000000001e-05, | |
| "loss": 2.0945, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 9.21875e-05, | |
| "loss": 2.0924, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.375e-05, | |
| "loss": 2.1014, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.53125e-05, | |
| "loss": 2.0984, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.687500000000001e-05, | |
| "loss": 2.0709, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.84375e-05, | |
| "loss": 2.1051, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1052, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6366426454087312, | |
| "eval_loss": 1.9433484077453613, | |
| "eval_runtime": 50910.5556, | |
| "eval_samples_per_second": 6.44, | |
| "eval_steps_per_second": 0.805, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 6400, | |
| "total_flos": 2.707934115004416e+17, | |
| "train_loss": 2.156327223777771, | |
| "train_runtime": 107381.8296, | |
| "train_samples_per_second": 3.814, | |
| "train_steps_per_second": 0.06 | |
| } | |
| ], | |
| "max_steps": 6400, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 2.707934115004416e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |