| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7163965254768514, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.8e-05, | |
| "loss": 2.7679, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.6e-05, | |
| "loss": 2.7177, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.4e-05, | |
| "loss": 2.7222, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 2.7099, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9e-05, | |
| "loss": 2.7061, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 2.6767, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 8.6e-05, | |
| "loss": 2.6904, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.4e-05, | |
| "loss": 2.7185, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.2e-05, | |
| "loss": 2.6847, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8e-05, | |
| "loss": 2.6694, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.4485705008989588, | |
| "eval_loss": 2.9416415691375732, | |
| "eval_runtime": 57.0818, | |
| "eval_samples_per_second": 62.086, | |
| "eval_steps_per_second": 7.761, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 2.6807, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 7.6e-05, | |
| "loss": 2.6817, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 7.4e-05, | |
| "loss": 2.6816, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 7.2e-05, | |
| "loss": 2.6423, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7e-05, | |
| "loss": 2.6433, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 2.6923, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 6.6e-05, | |
| "loss": 2.665, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 2.6328, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 6.2e-05, | |
| "loss": 2.66, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 6e-05, | |
| "loss": 2.6174, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.4501928233490743, | |
| "eval_loss": 2.9311683177948, | |
| "eval_runtime": 57.1874, | |
| "eval_samples_per_second": 61.972, | |
| "eval_steps_per_second": 7.746, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5.8e-05, | |
| "loss": 2.634, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 2.6383, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 2.6367, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 2.6456, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6311, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.8e-05, | |
| "loss": 2.6221, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 2.5929, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 2.6235, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.2e-05, | |
| "loss": 2.6383, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4e-05, | |
| "loss": 2.611, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.4519195089520393, | |
| "eval_loss": 2.9166808128356934, | |
| "eval_runtime": 58.9572, | |
| "eval_samples_per_second": 60.111, | |
| "eval_steps_per_second": 7.514, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.8e-05, | |
| "loss": 2.599, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 3.6e-05, | |
| "loss": 2.6049, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 2.6246, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 2.6073, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 3e-05, | |
| "loss": 2.6135, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 2.6025, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 2.6018, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.4e-05, | |
| "loss": 2.6132, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 2.5875, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2e-05, | |
| "loss": 2.576, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.4537141134322556, | |
| "eval_loss": 2.905719757080078, | |
| "eval_runtime": 57.035, | |
| "eval_samples_per_second": 62.137, | |
| "eval_steps_per_second": 7.767, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.8e-05, | |
| "loss": 2.5963, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.5999, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 2.5973, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.5919, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1e-05, | |
| "loss": 2.5767, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.575, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6e-06, | |
| "loss": 2.5696, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.597, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.587, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0, | |
| "loss": 2.5796, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.4548206941640567, | |
| "eval_loss": 2.899137020111084, | |
| "eval_runtime": 56.9987, | |
| "eval_samples_per_second": 62.177, | |
| "eval_steps_per_second": 7.772, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "step": 1000, | |
| "total_flos": 1.7866929733632e+17, | |
| "train_loss": 2.6366955451965333, | |
| "train_runtime": 1372.8893, | |
| "train_samples_per_second": 46.617, | |
| "train_steps_per_second": 0.728 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.7866929733632e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |