| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.9840000000000004e-05, | |
| "loss": 4.7991, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9640000000000006e-05, | |
| "loss": 4.4063, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.944e-05, | |
| "loss": 3.8331, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.924e-05, | |
| "loss": 2.8485, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9040000000000005e-05, | |
| "loss": 2.5842, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.884e-05, | |
| "loss": 2.3857, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.864e-05, | |
| "loss": 2.2079, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.8440000000000004e-05, | |
| "loss": 2.2818, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.824e-05, | |
| "loss": 2.1391, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.804e-05, | |
| "loss": 2.1858, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.784e-05, | |
| "loss": 2.1695, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.7640000000000005e-05, | |
| "loss": 2.0576, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.744e-05, | |
| "loss": 2.0989, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.724e-05, | |
| "loss": 2.0584, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.7040000000000004e-05, | |
| "loss": 2.0516, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.684e-05, | |
| "loss": 2.0031, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.664e-05, | |
| "loss": 2.0133, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.644e-05, | |
| "loss": 2.027, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.624e-05, | |
| "loss": 2.0238, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.606e-05, | |
| "loss": 2.0607, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.5860000000000005e-05, | |
| "loss": 2.1364, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.566e-05, | |
| "loss": 2.0829, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.546e-05, | |
| "loss": 2.2079, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.5260000000000004e-05, | |
| "loss": 1.9552, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.506e-05, | |
| "loss": 2.0141, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.486e-05, | |
| "loss": 1.9904, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.466e-05, | |
| "loss": 1.9627, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.4460000000000005e-05, | |
| "loss": 2.0108, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.426e-05, | |
| "loss": 1.9851, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.406e-05, | |
| "loss": 2.1354, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.3860000000000004e-05, | |
| "loss": 2.0532, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.366e-05, | |
| "loss": 2.0449, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.346e-05, | |
| "loss": 1.9925, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.326e-05, | |
| "loss": 2.0868, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.306e-05, | |
| "loss": 2.0281, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.286e-05, | |
| "loss": 1.9509, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.266e-05, | |
| "loss": 2.0431, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.246e-05, | |
| "loss": 1.917, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.226e-05, | |
| "loss": 2.0301, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.206e-05, | |
| "loss": 1.8611, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.186e-05, | |
| "loss": 1.8227, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.1660000000000004e-05, | |
| "loss": 1.9631, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.1460000000000006e-05, | |
| "loss": 1.954, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.126e-05, | |
| "loss": 1.9286, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.106e-05, | |
| "loss": 2.0062, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.0860000000000005e-05, | |
| "loss": 2.0218, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.066e-05, | |
| "loss": 2.0331, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.046e-05, | |
| "loss": 1.8572, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.0260000000000004e-05, | |
| "loss": 2.0023, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.0060000000000006e-05, | |
| "loss": 2.1018, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 9007457170046976.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |