| { | |
| "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": 3.2525749891599526e-06, | |
| "loss": 1.627, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010964912280701754, | |
| "learning_rate": 4.0051499783199055e-06, | |
| "loss": 1.6081, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01644736842105263, | |
| "learning_rate": 4.445378125959108e-06, | |
| "loss": 1.587, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.021929824561403508, | |
| "learning_rate": 4.757724967479858e-06, | |
| "loss": 1.5592, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.027412280701754384, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 1.5009, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03289473684210526, | |
| "learning_rate": 4.9756410256410255e-06, | |
| "loss": 1.4438, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03837719298245614, | |
| "learning_rate": 4.95e-06, | |
| "loss": 1.3777, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.043859649122807015, | |
| "learning_rate": 4.9243589743589745e-06, | |
| "loss": 1.3215, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.049342105263157895, | |
| "learning_rate": 4.898717948717949e-06, | |
| "loss": 1.267, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.05482456140350877, | |
| "learning_rate": 4.8730769230769235e-06, | |
| "loss": 1.2095, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06030701754385965, | |
| "learning_rate": 4.847435897435897e-06, | |
| "loss": 1.1684, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.06578947368421052, | |
| "learning_rate": 4.821794871794872e-06, | |
| "loss": 1.1054, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.0712719298245614, | |
| "learning_rate": 4.796153846153846e-06, | |
| "loss": 1.0593, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.07675438596491228, | |
| "learning_rate": 4.770512820512821e-06, | |
| "loss": 1.0069, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.08223684210526316, | |
| "learning_rate": 4.744871794871795e-06, | |
| "loss": 0.9498, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.08771929824561403, | |
| "learning_rate": 4.71923076923077e-06, | |
| "loss": 0.8949, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.09320175438596491, | |
| "learning_rate": 4.693589743589744e-06, | |
| "loss": 0.8369, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.09868421052631579, | |
| "learning_rate": 4.667948717948718e-06, | |
| "loss": 0.8047, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.10416666666666667, | |
| "learning_rate": 4.642307692307692e-06, | |
| "loss": 0.781, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.10964912280701754, | |
| "learning_rate": 4.616666666666667e-06, | |
| "loss": 0.7535, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11513157894736842, | |
| "learning_rate": 4.591025641025641e-06, | |
| "loss": 0.7332, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.1206140350877193, | |
| "learning_rate": 4.565384615384616e-06, | |
| "loss": 0.7171, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.12609649122807018, | |
| "learning_rate": 4.53974358974359e-06, | |
| "loss": 0.7074, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "learning_rate": 4.514102564102564e-06, | |
| "loss": 0.6905, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.13706140350877194, | |
| "learning_rate": 4.4884615384615384e-06, | |
| "loss": 0.6812, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13706140350877194, | |
| "eval_loss": 0.6900227665901184, | |
| "eval_runtime": 7.1872, | |
| "eval_samples_per_second": 13.635, | |
| "eval_steps_per_second": 1.809, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1425438596491228, | |
| "learning_rate": 4.462820512820513e-06, | |
| "loss": 0.6753, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.14802631578947367, | |
| "learning_rate": 4.437179487179487e-06, | |
| "loss": 0.6637, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.15350877192982457, | |
| "learning_rate": 4.411538461538462e-06, | |
| "loss": 0.6615, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.15899122807017543, | |
| "learning_rate": 4.385897435897436e-06, | |
| "loss": 0.6547, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.16447368421052633, | |
| "learning_rate": 4.36025641025641e-06, | |
| "loss": 0.6487, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1699561403508772, | |
| "learning_rate": 4.3346153846153846e-06, | |
| "loss": 0.6441, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "learning_rate": 4.308974358974359e-06, | |
| "loss": 0.6358, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.18092105263157895, | |
| "learning_rate": 4.2833333333333335e-06, | |
| "loss": 0.636, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.18640350877192982, | |
| "learning_rate": 4.257692307692308e-06, | |
| "loss": 0.6326, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.19188596491228072, | |
| "learning_rate": 4.2320512820512825e-06, | |
| "loss": 0.6246, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.19736842105263158, | |
| "learning_rate": 4.206410256410256e-06, | |
| "loss": 0.6237, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.20285087719298245, | |
| "learning_rate": 4.180769230769231e-06, | |
| "loss": 0.6203, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.20833333333333334, | |
| "learning_rate": 4.155128205128205e-06, | |
| "loss": 0.6164, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.2138157894736842, | |
| "learning_rate": 4.12948717948718e-06, | |
| "loss": 0.6118, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.21929824561403508, | |
| "learning_rate": 4.103846153846154e-06, | |
| "loss": 0.6101, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.22478070175438597, | |
| "learning_rate": 4.078205128205129e-06, | |
| "loss": 0.6092, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.23026315789473684, | |
| "learning_rate": 4.052564102564102e-06, | |
| "loss": 0.6039, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.23574561403508773, | |
| "learning_rate": 4.026923076923077e-06, | |
| "loss": 0.5989, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.2412280701754386, | |
| "learning_rate": 4.001282051282051e-06, | |
| "loss": 0.5979, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.24671052631578946, | |
| "learning_rate": 3.975641025641026e-06, | |
| "loss": 0.5965, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.25219298245614036, | |
| "learning_rate": 3.95e-06, | |
| "loss": 0.5969, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.2576754385964912, | |
| "learning_rate": 3.924358974358975e-06, | |
| "loss": 0.5902, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "learning_rate": 3.8987179487179484e-06, | |
| "loss": 0.5909, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.26864035087719296, | |
| "learning_rate": 3.873076923076923e-06, | |
| "loss": 0.5914, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.2741228070175439, | |
| "learning_rate": 3.8474358974358974e-06, | |
| "loss": 0.589, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2741228070175439, | |
| "eval_loss": 0.5962496399879456, | |
| "eval_runtime": 6.5411, | |
| "eval_samples_per_second": 14.982, | |
| "eval_steps_per_second": 1.987, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.27960526315789475, | |
| "learning_rate": 3.821794871794872e-06, | |
| "loss": 0.5844, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.2850877192982456, | |
| "learning_rate": 3.7961538461538464e-06, | |
| "loss": 0.5819, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.2905701754385965, | |
| "learning_rate": 3.770512820512821e-06, | |
| "loss": 0.5828, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.29605263157894735, | |
| "learning_rate": 3.744871794871795e-06, | |
| "loss": 0.5816, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.30153508771929827, | |
| "learning_rate": 3.7192307692307695e-06, | |
| "loss": 0.5773, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.30701754385964913, | |
| "learning_rate": 3.693589743589744e-06, | |
| "loss": 0.5782, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "learning_rate": 3.6679487179487185e-06, | |
| "loss": 0.5774, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.31798245614035087, | |
| "learning_rate": 3.642307692307693e-06, | |
| "loss": 0.5733, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.32346491228070173, | |
| "learning_rate": 3.616666666666667e-06, | |
| "loss": 0.5722, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.32894736842105265, | |
| "learning_rate": 3.591025641025641e-06, | |
| "loss": 0.569, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.3344298245614035, | |
| "learning_rate": 3.5653846153846156e-06, | |
| "loss": 0.5699, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.3399122807017544, | |
| "learning_rate": 3.53974358974359e-06, | |
| "loss": 0.5691, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.34539473684210525, | |
| "learning_rate": 3.5141025641025646e-06, | |
| "loss": 0.5706, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "learning_rate": 3.488461538461539e-06, | |
| "loss": 0.565, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.35635964912280704, | |
| "learning_rate": 3.462820512820513e-06, | |
| "loss": 0.5652, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.3618421052631579, | |
| "learning_rate": 3.4371794871794873e-06, | |
| "loss": 0.5631, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.3673245614035088, | |
| "learning_rate": 3.4115384615384617e-06, | |
| "loss": 0.5652, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.37280701754385964, | |
| "learning_rate": 3.3858974358974362e-06, | |
| "loss": 0.5627, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.3782894736842105, | |
| "learning_rate": 3.3602564102564107e-06, | |
| "loss": 0.5662, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.38377192982456143, | |
| "learning_rate": 3.3346153846153852e-06, | |
| "loss": 0.5606, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.3892543859649123, | |
| "learning_rate": 3.3089743589743593e-06, | |
| "loss": 0.5616, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "learning_rate": 3.2833333333333334e-06, | |
| "loss": 0.5624, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.40021929824561403, | |
| "learning_rate": 3.257692307692308e-06, | |
| "loss": 0.5578, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.4057017543859649, | |
| "learning_rate": 3.2320512820512824e-06, | |
| "loss": 0.5577, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.41118421052631576, | |
| "learning_rate": 3.206410256410257e-06, | |
| "loss": 0.5586, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.41118421052631576, | |
| "eval_loss": 0.5718954801559448, | |
| "eval_runtime": 6.5348, | |
| "eval_samples_per_second": 14.997, | |
| "eval_steps_per_second": 1.989, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4166666666666667, | |
| "learning_rate": 3.1807692307692314e-06, | |
| "loss": 0.5603, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.42214912280701755, | |
| "learning_rate": 3.1551282051282054e-06, | |
| "loss": 0.5567, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.4276315789473684, | |
| "learning_rate": 3.1294871794871795e-06, | |
| "loss": 0.5565, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.4331140350877193, | |
| "learning_rate": 3.103846153846154e-06, | |
| "loss": 0.552, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.43859649122807015, | |
| "learning_rate": 3.0782051282051285e-06, | |
| "loss": 0.5553, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.4440789473684211, | |
| "learning_rate": 3.052564102564103e-06, | |
| "loss": 0.5528, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.44956140350877194, | |
| "learning_rate": 3.0269230769230775e-06, | |
| "loss": 0.5446, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.4550438596491228, | |
| "learning_rate": 3.0012820512820516e-06, | |
| "loss": 0.5525, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.4605263157894737, | |
| "learning_rate": 2.9756410256410256e-06, | |
| "loss": 0.5504, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.46600877192982454, | |
| "learning_rate": 2.95e-06, | |
| "loss": 0.5528, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.47149122807017546, | |
| "learning_rate": 2.9243589743589746e-06, | |
| "loss": 0.5502, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.4769736842105263, | |
| "learning_rate": 2.898717948717949e-06, | |
| "loss": 0.5512, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.4824561403508772, | |
| "learning_rate": 2.8730769230769236e-06, | |
| "loss": 0.5476, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.48793859649122806, | |
| "learning_rate": 2.8474358974358977e-06, | |
| "loss": 0.5489, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.4934210526315789, | |
| "learning_rate": 2.8217948717948718e-06, | |
| "loss": 0.5522, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.49890350877192985, | |
| "learning_rate": 2.7961538461538463e-06, | |
| "loss": 0.5463, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.5043859649122807, | |
| "learning_rate": 2.7705128205128208e-06, | |
| "loss": 0.5498, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.5098684210526315, | |
| "learning_rate": 2.7448717948717953e-06, | |
| "loss": 0.5437, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.5153508771929824, | |
| "learning_rate": 2.7192307692307697e-06, | |
| "loss": 0.5477, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.5208333333333334, | |
| "learning_rate": 2.693589743589744e-06, | |
| "loss": 0.5464, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "learning_rate": 2.667948717948718e-06, | |
| "loss": 0.5421, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.5317982456140351, | |
| "learning_rate": 2.6423076923076924e-06, | |
| "loss": 0.5451, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.5372807017543859, | |
| "learning_rate": 2.616666666666667e-06, | |
| "loss": 0.545, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.5427631578947368, | |
| "learning_rate": 2.5910256410256414e-06, | |
| "loss": 0.5416, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.5482456140350878, | |
| "learning_rate": 2.565384615384616e-06, | |
| "loss": 0.5378, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5482456140350878, | |
| "eval_loss": 0.5599762797355652, | |
| "eval_runtime": 6.5788, | |
| "eval_samples_per_second": 14.896, | |
| "eval_steps_per_second": 1.976, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 4000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 4034749748215808.0, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |