| { |
| "best_metric": 0.08939466625452042, |
| "best_model_checkpoint": "./beans_outputs/checkpoint-650", |
| "epoch": 5.0, |
| "global_step": 650, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08, |
| "learning_rate": 1.9692307692307696e-05, |
| "loss": 1.0141, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 1.9384615384615386e-05, |
| "loss": 0.9846, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 1.907692307692308e-05, |
| "loss": 0.8579, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 1.876923076923077e-05, |
| "loss": 0.7665, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 1.8461538461538465e-05, |
| "loss": 0.6865, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 1.8153846153846155e-05, |
| "loss": 0.6423, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 1.784615384615385e-05, |
| "loss": 0.5619, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 1.753846153846154e-05, |
| "loss": 0.4407, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 1.7230769230769234e-05, |
| "loss": 0.3832, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 1.6923076923076924e-05, |
| "loss": 0.3293, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 1.6615384615384618e-05, |
| "loss": 0.3414, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 1.630769230769231e-05, |
| "loss": 0.2629, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.3128, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9699248120300752, |
| "eval_loss": 0.21415506303310394, |
| "eval_runtime": 4.9377, |
| "eval_samples_per_second": 26.936, |
| "eval_steps_per_second": 3.443, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 1.5692307692307693e-05, |
| "loss": 0.2952, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.2356, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 1.5076923076923078e-05, |
| "loss": 0.2324, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.31, |
| "learning_rate": 1.4769230769230772e-05, |
| "loss": 0.1496, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 1.4461538461538462e-05, |
| "loss": 0.1935, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 1.4153846153846156e-05, |
| "loss": 0.1958, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 1.3846153846153847e-05, |
| "loss": 0.1568, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 1.353846153846154e-05, |
| "loss": 0.15, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 1.3230769230769231e-05, |
| "loss": 0.1765, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 1.2923076923076925e-05, |
| "loss": 0.1893, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 1.2615384615384616e-05, |
| "loss": 0.1911, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 1.230769230769231e-05, |
| "loss": 0.2178, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 1.2e-05, |
| "loss": 0.2332, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9699248120300752, |
| "eval_loss": 0.129187673330307, |
| "eval_runtime": 6.4495, |
| "eval_samples_per_second": 20.622, |
| "eval_steps_per_second": 2.636, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.08, |
| "learning_rate": 1.1692307692307694e-05, |
| "loss": 0.1538, |
| "step": 270 |
| }, |
| { |
| "epoch": 2.15, |
| "learning_rate": 1.1384615384615385e-05, |
| "loss": 0.1763, |
| "step": 280 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 1.1076923076923079e-05, |
| "loss": 0.2192, |
| "step": 290 |
| }, |
| { |
| "epoch": 2.31, |
| "learning_rate": 1.076923076923077e-05, |
| "loss": 0.1419, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 1.0461538461538463e-05, |
| "loss": 0.2164, |
| "step": 310 |
| }, |
| { |
| "epoch": 2.46, |
| "learning_rate": 1.0153846153846154e-05, |
| "loss": 0.1575, |
| "step": 320 |
| }, |
| { |
| "epoch": 2.54, |
| "learning_rate": 9.846153846153848e-06, |
| "loss": 0.1385, |
| "step": 330 |
| }, |
| { |
| "epoch": 2.62, |
| "learning_rate": 9.53846153846154e-06, |
| "loss": 0.1707, |
| "step": 340 |
| }, |
| { |
| "epoch": 2.69, |
| "learning_rate": 9.230769230769232e-06, |
| "loss": 0.1188, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.77, |
| "learning_rate": 8.923076923076925e-06, |
| "loss": 0.1286, |
| "step": 360 |
| }, |
| { |
| "epoch": 2.85, |
| "learning_rate": 8.615384615384617e-06, |
| "loss": 0.1326, |
| "step": 370 |
| }, |
| { |
| "epoch": 2.92, |
| "learning_rate": 8.307692307692309e-06, |
| "loss": 0.102, |
| "step": 380 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.2013, |
| "step": 390 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9774436090225563, |
| "eval_loss": 0.1077343299984932, |
| "eval_runtime": 13.8689, |
| "eval_samples_per_second": 9.59, |
| "eval_steps_per_second": 1.226, |
| "step": 390 |
| }, |
| { |
| "epoch": 3.08, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.1089, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.15, |
| "learning_rate": 7.384615384615386e-06, |
| "loss": 0.1406, |
| "step": 410 |
| }, |
| { |
| "epoch": 3.23, |
| "learning_rate": 7.076923076923078e-06, |
| "loss": 0.1077, |
| "step": 420 |
| }, |
| { |
| "epoch": 3.31, |
| "learning_rate": 6.76923076923077e-06, |
| "loss": 0.1203, |
| "step": 430 |
| }, |
| { |
| "epoch": 3.38, |
| "learning_rate": 6.461538461538463e-06, |
| "loss": 0.16, |
| "step": 440 |
| }, |
| { |
| "epoch": 3.46, |
| "learning_rate": 6.153846153846155e-06, |
| "loss": 0.1014, |
| "step": 450 |
| }, |
| { |
| "epoch": 3.54, |
| "learning_rate": 5.846153846153847e-06, |
| "loss": 0.1281, |
| "step": 460 |
| }, |
| { |
| "epoch": 3.62, |
| "learning_rate": 5.538461538461539e-06, |
| "loss": 0.2122, |
| "step": 470 |
| }, |
| { |
| "epoch": 3.69, |
| "learning_rate": 5.230769230769232e-06, |
| "loss": 0.1127, |
| "step": 480 |
| }, |
| { |
| "epoch": 3.77, |
| "learning_rate": 4.923076923076924e-06, |
| "loss": 0.1156, |
| "step": 490 |
| }, |
| { |
| "epoch": 3.85, |
| "learning_rate": 4.615384615384616e-06, |
| "loss": 0.0575, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.92, |
| "learning_rate": 4.307692307692308e-06, |
| "loss": 0.1583, |
| "step": 510 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.0866, |
| "step": 520 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9774436090225563, |
| "eval_loss": 0.10892753303050995, |
| "eval_runtime": 14.1218, |
| "eval_samples_per_second": 9.418, |
| "eval_steps_per_second": 1.204, |
| "step": 520 |
| }, |
| { |
| "epoch": 4.08, |
| "learning_rate": 3.692307692307693e-06, |
| "loss": 0.1094, |
| "step": 530 |
| }, |
| { |
| "epoch": 4.15, |
| "learning_rate": 3.384615384615385e-06, |
| "loss": 0.072, |
| "step": 540 |
| }, |
| { |
| "epoch": 4.23, |
| "learning_rate": 3.0769230769230774e-06, |
| "loss": 0.1391, |
| "step": 550 |
| }, |
| { |
| "epoch": 4.31, |
| "learning_rate": 2.7692307692307697e-06, |
| "loss": 0.1309, |
| "step": 560 |
| }, |
| { |
| "epoch": 4.38, |
| "learning_rate": 2.461538461538462e-06, |
| "loss": 0.1157, |
| "step": 570 |
| }, |
| { |
| "epoch": 4.46, |
| "learning_rate": 2.153846153846154e-06, |
| "loss": 0.0687, |
| "step": 580 |
| }, |
| { |
| "epoch": 4.54, |
| "learning_rate": 1.8461538461538465e-06, |
| "loss": 0.0807, |
| "step": 590 |
| }, |
| { |
| "epoch": 4.62, |
| "learning_rate": 1.5384615384615387e-06, |
| "loss": 0.0706, |
| "step": 600 |
| }, |
| { |
| "epoch": 4.69, |
| "learning_rate": 1.230769230769231e-06, |
| "loss": 0.0906, |
| "step": 610 |
| }, |
| { |
| "epoch": 4.77, |
| "learning_rate": 9.230769230769232e-07, |
| "loss": 0.0873, |
| "step": 620 |
| }, |
| { |
| "epoch": 4.85, |
| "learning_rate": 6.153846153846155e-07, |
| "loss": 0.1316, |
| "step": 630 |
| }, |
| { |
| "epoch": 4.92, |
| "learning_rate": 3.0769230769230774e-07, |
| "loss": 0.1298, |
| "step": 640 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 0.0, |
| "loss": 0.1311, |
| "step": 650 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9774436090225563, |
| "eval_loss": 0.08939466625452042, |
| "eval_runtime": 15.1874, |
| "eval_samples_per_second": 8.757, |
| "eval_steps_per_second": 1.119, |
| "step": 650 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 650, |
| "total_flos": 4.006371770595533e+17, |
| "train_loss": 0.2342429311458881, |
| "train_runtime": 1645.9261, |
| "train_samples_per_second": 3.141, |
| "train_steps_per_second": 0.395 |
| } |
| ], |
| "max_steps": 650, |
| "num_train_epochs": 5, |
| "total_flos": 4.006371770595533e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
