| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5482456140350878, | |
| "eval_steps": 500, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005482456140350877, | |
| "learning_rate": 6.505149978319905e-06, | |
| "loss": 2.1172, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010964912280701754, | |
| "learning_rate": 8.010299956639811e-06, | |
| "loss": 2.0896, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01644736842105263, | |
| "learning_rate": 8.890756251918216e-06, | |
| "loss": 2.0247, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.021929824561403508, | |
| "learning_rate": 9.515449934959717e-06, | |
| "loss": 1.9324, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.027412280701754384, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 1.8172, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03289473684210526, | |
| "learning_rate": 9.951282051282051e-06, | |
| "loss": 1.7083, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03837719298245614, | |
| "learning_rate": 9.9e-06, | |
| "loss": 1.5955, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.043859649122807015, | |
| "learning_rate": 9.848717948717949e-06, | |
| "loss": 1.506, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.049342105263157895, | |
| "learning_rate": 9.797435897435898e-06, | |
| "loss": 1.4192, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.05482456140350877, | |
| "learning_rate": 9.746153846153847e-06, | |
| "loss": 1.3436, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06030701754385965, | |
| "learning_rate": 9.694871794871794e-06, | |
| "loss": 1.2787, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.06578947368421052, | |
| "learning_rate": 9.643589743589743e-06, | |
| "loss": 1.1996, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.0712719298245614, | |
| "learning_rate": 9.592307692307692e-06, | |
| "loss": 1.1389, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.07675438596491228, | |
| "learning_rate": 9.541025641025641e-06, | |
| "loss": 1.0759, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.08223684210526316, | |
| "learning_rate": 9.48974358974359e-06, | |
| "loss": 1.0109, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.08771929824561403, | |
| "learning_rate": 9.43846153846154e-06, | |
| "loss": 0.9657, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.09320175438596491, | |
| "learning_rate": 9.387179487179488e-06, | |
| "loss": 0.9276, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.09868421052631579, | |
| "learning_rate": 9.335897435897436e-06, | |
| "loss": 0.8982, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.10416666666666667, | |
| "learning_rate": 9.284615384615385e-06, | |
| "loss": 0.8782, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.10964912280701754, | |
| "learning_rate": 9.233333333333334e-06, | |
| "loss": 0.856, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11513157894736842, | |
| "learning_rate": 9.182051282051283e-06, | |
| "loss": 0.8384, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.1206140350877193, | |
| "learning_rate": 9.130769230769232e-06, | |
| "loss": 0.8261, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.12609649122807018, | |
| "learning_rate": 9.07948717948718e-06, | |
| "loss": 0.8212, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "learning_rate": 9.028205128205128e-06, | |
| "loss": 0.8005, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.13706140350877194, | |
| "learning_rate": 8.976923076923077e-06, | |
| "loss": 0.7932, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13706140350877194, | |
| "eval_loss": 0.86247718334198, | |
| "eval_runtime": 4.0533, | |
| "eval_samples_per_second": 24.178, | |
| "eval_steps_per_second": 3.207, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1425438596491228, | |
| "learning_rate": 8.925641025641026e-06, | |
| "loss": 0.7863, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.14802631578947367, | |
| "learning_rate": 8.874358974358975e-06, | |
| "loss": 0.7758, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.15350877192982457, | |
| "learning_rate": 8.823076923076924e-06, | |
| "loss": 0.7719, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.15899122807017543, | |
| "learning_rate": 8.771794871794873e-06, | |
| "loss": 0.7642, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.16447368421052633, | |
| "learning_rate": 8.72051282051282e-06, | |
| "loss": 0.7571, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1699561403508772, | |
| "learning_rate": 8.669230769230769e-06, | |
| "loss": 0.7504, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "learning_rate": 8.617948717948718e-06, | |
| "loss": 0.7418, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.18092105263157895, | |
| "learning_rate": 8.566666666666667e-06, | |
| "loss": 0.7416, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.18640350877192982, | |
| "learning_rate": 8.515384615384616e-06, | |
| "loss": 0.7379, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.19188596491228072, | |
| "learning_rate": 8.464102564102565e-06, | |
| "loss": 0.7301, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.19736842105263158, | |
| "learning_rate": 8.412820512820512e-06, | |
| "loss": 0.728, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.20285087719298245, | |
| "learning_rate": 8.361538461538461e-06, | |
| "loss": 0.7263, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.20833333333333334, | |
| "learning_rate": 8.31025641025641e-06, | |
| "loss": 0.721, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.2138157894736842, | |
| "learning_rate": 8.25897435897436e-06, | |
| "loss": 0.7128, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.21929824561403508, | |
| "learning_rate": 8.207692307692308e-06, | |
| "loss": 0.7123, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.22478070175438597, | |
| "learning_rate": 8.156410256410257e-06, | |
| "loss": 0.7119, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.23026315789473684, | |
| "learning_rate": 8.105128205128205e-06, | |
| "loss": 0.7076, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.23574561403508773, | |
| "learning_rate": 8.053846153846154e-06, | |
| "loss": 0.7012, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.2412280701754386, | |
| "learning_rate": 8.002564102564103e-06, | |
| "loss": 0.6979, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.24671052631578946, | |
| "learning_rate": 7.951282051282052e-06, | |
| "loss": 0.6975, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.25219298245614036, | |
| "learning_rate": 7.9e-06, | |
| "loss": 0.6983, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.2576754385964912, | |
| "learning_rate": 7.84871794871795e-06, | |
| "loss": 0.692, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "learning_rate": 7.797435897435897e-06, | |
| "loss": 0.691, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.26864035087719296, | |
| "learning_rate": 7.746153846153846e-06, | |
| "loss": 0.6914, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.2741228070175439, | |
| "learning_rate": 7.694871794871795e-06, | |
| "loss": 0.6896, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2741228070175439, | |
| "eval_loss": 0.7453868389129639, | |
| "eval_runtime": 3.7352, | |
| "eval_samples_per_second": 26.237, | |
| "eval_steps_per_second": 3.48, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.27960526315789475, | |
| "learning_rate": 7.643589743589744e-06, | |
| "loss": 0.6827, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.2850877192982456, | |
| "learning_rate": 7.592307692307693e-06, | |
| "loss": 0.6818, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.2905701754385965, | |
| "learning_rate": 7.541025641025642e-06, | |
| "loss": 0.6822, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.29605263157894735, | |
| "learning_rate": 7.48974358974359e-06, | |
| "loss": 0.6798, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.30153508771929827, | |
| "learning_rate": 7.438461538461539e-06, | |
| "loss": 0.675, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.30701754385964913, | |
| "learning_rate": 7.387179487179488e-06, | |
| "loss": 0.6755, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "learning_rate": 7.335897435897437e-06, | |
| "loss": 0.6749, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.31798245614035087, | |
| "learning_rate": 7.284615384615386e-06, | |
| "loss": 0.6687, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.32346491228070173, | |
| "learning_rate": 7.233333333333334e-06, | |
| "loss": 0.6692, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.32894736842105265, | |
| "learning_rate": 7.182051282051282e-06, | |
| "loss": 0.6632, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.3344298245614035, | |
| "learning_rate": 7.130769230769231e-06, | |
| "loss": 0.6653, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.3399122807017544, | |
| "learning_rate": 7.07948717948718e-06, | |
| "loss": 0.6637, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.34539473684210525, | |
| "learning_rate": 7.028205128205129e-06, | |
| "loss": 0.6656, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "learning_rate": 6.976923076923078e-06, | |
| "loss": 0.6606, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.35635964912280704, | |
| "learning_rate": 6.925641025641026e-06, | |
| "loss": 0.66, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.3618421052631579, | |
| "learning_rate": 6.8743589743589745e-06, | |
| "loss": 0.6572, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.3673245614035088, | |
| "learning_rate": 6.8230769230769235e-06, | |
| "loss": 0.6579, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.37280701754385964, | |
| "learning_rate": 6.7717948717948725e-06, | |
| "loss": 0.6551, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.3782894736842105, | |
| "learning_rate": 6.7205128205128215e-06, | |
| "loss": 0.6577, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.38377192982456143, | |
| "learning_rate": 6.6692307692307705e-06, | |
| "loss": 0.6534, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.3892543859649123, | |
| "learning_rate": 6.617948717948719e-06, | |
| "loss": 0.6543, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "learning_rate": 6.566666666666667e-06, | |
| "loss": 0.6537, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.40021929824561403, | |
| "learning_rate": 6.515384615384616e-06, | |
| "loss": 0.6499, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.4057017543859649, | |
| "learning_rate": 6.464102564102565e-06, | |
| "loss": 0.6464, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.41118421052631576, | |
| "learning_rate": 6.412820512820514e-06, | |
| "loss": 0.65, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.41118421052631576, | |
| "eval_loss": 0.7062739133834839, | |
| "eval_runtime": 3.7117, | |
| "eval_samples_per_second": 26.403, | |
| "eval_steps_per_second": 3.502, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4166666666666667, | |
| "learning_rate": 6.361538461538463e-06, | |
| "loss": 0.6506, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.42214912280701755, | |
| "learning_rate": 6.310256410256411e-06, | |
| "loss": 0.6475, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.4276315789473684, | |
| "learning_rate": 6.258974358974359e-06, | |
| "loss": 0.6467, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.4331140350877193, | |
| "learning_rate": 6.207692307692308e-06, | |
| "loss": 0.6428, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.43859649122807015, | |
| "learning_rate": 6.156410256410257e-06, | |
| "loss": 0.6452, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.4440789473684211, | |
| "learning_rate": 6.105128205128206e-06, | |
| "loss": 0.6408, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.44956140350877194, | |
| "learning_rate": 6.053846153846155e-06, | |
| "loss": 0.634, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.4550438596491228, | |
| "learning_rate": 6.002564102564103e-06, | |
| "loss": 0.6408, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.4605263157894737, | |
| "learning_rate": 5.951282051282051e-06, | |
| "loss": 0.6393, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.46600877192982454, | |
| "learning_rate": 5.9e-06, | |
| "loss": 0.6373, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.47149122807017546, | |
| "learning_rate": 5.848717948717949e-06, | |
| "loss": 0.64, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.4769736842105263, | |
| "learning_rate": 5.797435897435898e-06, | |
| "loss": 0.6401, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.4824561403508772, | |
| "learning_rate": 5.746153846153847e-06, | |
| "loss": 0.6342, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.48793859649122806, | |
| "learning_rate": 5.694871794871795e-06, | |
| "loss": 0.6363, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.4934210526315789, | |
| "learning_rate": 5.6435897435897435e-06, | |
| "loss": 0.6394, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.49890350877192985, | |
| "learning_rate": 5.5923076923076925e-06, | |
| "loss": 0.6331, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.5043859649122807, | |
| "learning_rate": 5.5410256410256415e-06, | |
| "loss": 0.6372, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.5098684210526315, | |
| "learning_rate": 5.4897435897435905e-06, | |
| "loss": 0.6297, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.5153508771929824, | |
| "learning_rate": 5.4384615384615395e-06, | |
| "loss": 0.6333, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.5208333333333334, | |
| "learning_rate": 5.387179487179488e-06, | |
| "loss": 0.6342, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "learning_rate": 5.335897435897436e-06, | |
| "loss": 0.629, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.5317982456140351, | |
| "learning_rate": 5.284615384615385e-06, | |
| "loss": 0.6304, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.5372807017543859, | |
| "learning_rate": 5.233333333333334e-06, | |
| "loss": 0.631, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.5427631578947368, | |
| "learning_rate": 5.182051282051283e-06, | |
| "loss": 0.627, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.5482456140350878, | |
| "learning_rate": 5.130769230769232e-06, | |
| "loss": 0.6235, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5482456140350878, | |
| "eval_loss": 0.6829731464385986, | |
| "eval_runtime": 3.7134, | |
| "eval_samples_per_second": 26.391, | |
| "eval_steps_per_second": 3.501, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 4000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 1615927404658688.0, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |