| { | |
| "best_metric": 1.5448263883590698, | |
| "best_model_checkpoint": "/home/ampere/vanroy/llm-finetuning/instruct-tuning/results/falcon-7b-ft-alpaca-cleaned-dutch/checkpoint-1140", | |
| "epoch": 2.9931618365353305, | |
| "global_step": 1149, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.8571428571428575e-07, | |
| "loss": 2.0637, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.714285714285715e-07, | |
| "loss": 2.0295, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.571428571428572e-07, | |
| "loss": 1.9624, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.142857142857143e-06, | |
| "loss": 1.9473, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.4285714285714286e-06, | |
| "loss": 1.9286, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.7142857142857145e-06, | |
| "loss": 1.9895, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.9534, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.285714285714286e-06, | |
| "loss": 1.9382, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.571428571428571e-06, | |
| "loss": 1.9521, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 1.9832, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.8889312744140625, | |
| "eval_runtime": 221.7455, | |
| "eval_samples_per_second": 11.662, | |
| "eval_steps_per_second": 0.731, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.142857142857143e-06, | |
| "loss": 1.9819, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.428571428571429e-06, | |
| "loss": 1.9702, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.7142857142857146e-06, | |
| "loss": 1.9717, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.0242, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.2857142857142855e-06, | |
| "loss": 2.0544, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.571428571428572e-06, | |
| "loss": 1.8782, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.857142857142858e-06, | |
| "loss": 2.0745, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.142857142857142e-06, | |
| "loss": 1.9383, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.428571428571429e-06, | |
| "loss": 1.9806, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 1.9355, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.8833638429641724, | |
| "eval_runtime": 221.7609, | |
| "eval_samples_per_second": 11.661, | |
| "eval_steps_per_second": 0.731, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 6e-06, | |
| "loss": 1.9604, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6.285714285714286e-06, | |
| "loss": 1.8709, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6.571428571428572e-06, | |
| "loss": 1.9495, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6.857142857142858e-06, | |
| "loss": 1.9632, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 7.1428571428571436e-06, | |
| "loss": 1.9315, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 7.428571428571429e-06, | |
| "loss": 1.9402, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 7.714285714285716e-06, | |
| "loss": 1.9944, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.9004, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.285714285714287e-06, | |
| "loss": 2.0983, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 1.9694, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.8670501708984375, | |
| "eval_runtime": 221.6801, | |
| "eval_samples_per_second": 11.665, | |
| "eval_steps_per_second": 0.731, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.857142857142858e-06, | |
| "loss": 1.9217, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.142857142857144e-06, | |
| "loss": 1.878, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.42857142857143e-06, | |
| "loss": 1.9016, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.714285714285715e-06, | |
| "loss": 1.9793, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1e-05, | |
| "loss": 1.961, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.999980117587285e-06, | |
| "loss": 1.9236, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.999920470507263e-06, | |
| "loss": 1.9858, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.999821059234308e-06, | |
| "loss": 1.9147, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.999681884559027e-06, | |
| "loss": 1.8903, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.999502947588279e-06, | |
| "loss": 1.9048, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.8328224420547485, | |
| "eval_runtime": 221.7913, | |
| "eval_samples_per_second": 11.66, | |
| "eval_steps_per_second": 0.73, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.999284249745143e-06, | |
| "loss": 1.8736, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.99902579276891e-06, | |
| "loss": 1.9191, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.998727578715083e-06, | |
| "loss": 1.903, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.998389609955348e-06, | |
| "loss": 1.8531, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.998011889177558e-06, | |
| "loss": 2.0097, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.997594419385712e-06, | |
| "loss": 1.7101, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.997137203899935e-06, | |
| "loss": 1.9653, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.996640246356446e-06, | |
| "loss": 1.9002, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.996103550707528e-06, | |
| "loss": 1.9036, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.995527121221504e-06, | |
| "loss": 1.8443, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.7970249652862549, | |
| "eval_runtime": 221.713, | |
| "eval_samples_per_second": 11.664, | |
| "eval_steps_per_second": 0.731, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.9949109624827e-06, | |
| "loss": 1.9025, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.994255079391402e-06, | |
| "loss": 1.7249, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.993559477163827e-06, | |
| "loss": 1.8214, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.992824161332073e-06, | |
| "loss": 1.785, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.992049137744084e-06, | |
| "loss": 1.8474, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.991234412563594e-06, | |
| "loss": 1.8446, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.990379992270084e-06, | |
| "loss": 1.9928, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.989485883658729e-06, | |
| "loss": 1.7823, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.988552093840344e-06, | |
| "loss": 1.8821, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.987578630241326e-06, | |
| "loss": 1.7448, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.7710908651351929, | |
| "eval_runtime": 221.7207, | |
| "eval_samples_per_second": 11.663, | |
| "eval_steps_per_second": 0.731, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.986565500603598e-06, | |
| "loss": 1.8721, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.985512712984543e-06, | |
| "loss": 1.8571, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.984420275756945e-06, | |
| "loss": 1.9442, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.98328819760892e-06, | |
| "loss": 1.8412, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.982116487543844e-06, | |
| "loss": 1.9281, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.980905154880288e-06, | |
| "loss": 1.8329, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.979654209251939e-06, | |
| "loss": 1.8401, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.978363660607522e-06, | |
| "loss": 1.8755, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.977033519210725e-06, | |
| "loss": 1.8779, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.975663795640118e-06, | |
| "loss": 1.8004, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.7521506547927856, | |
| "eval_runtime": 221.7459, | |
| "eval_samples_per_second": 11.662, | |
| "eval_steps_per_second": 0.731, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.974254500789065e-06, | |
| "loss": 1.8134, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.972805645865637e-06, | |
| "loss": 1.7562, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.971317242392527e-06, | |
| "loss": 1.9037, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.969789302206957e-06, | |
| "loss": 1.7513, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.968221837460578e-06, | |
| "loss": 1.8005, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.96661486061939e-06, | |
| "loss": 1.7634, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.964968384463616e-06, | |
| "loss": 1.7449, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.963282422087628e-06, | |
| "loss": 1.8057, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.961556986899824e-06, | |
| "loss": 1.7487, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.959792092622532e-06, | |
| "loss": 1.7767, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.7370113134384155, | |
| "eval_runtime": 221.8285, | |
| "eval_samples_per_second": 11.658, | |
| "eval_steps_per_second": 0.73, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.95798775329189e-06, | |
| "loss": 1.8068, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.95614398325775e-06, | |
| "loss": 1.7506, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.95426079718355e-06, | |
| "loss": 1.814, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.952338210046202e-06, | |
| "loss": 1.7255, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.950376237135974e-06, | |
| "loss": 1.7329, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.94837489405637e-06, | |
| "loss": 1.7829, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.946334196724e-06, | |
| "loss": 1.8209, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.944254161368457e-06, | |
| "loss": 1.9201, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.942134804532194e-06, | |
| "loss": 1.7912, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.939976143070378e-06, | |
| "loss": 1.7733, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.7247874736785889, | |
| "eval_runtime": 221.7361, | |
| "eval_samples_per_second": 11.663, | |
| "eval_steps_per_second": 0.731, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.937778194150771e-06, | |
| "loss": 1.7701, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.935540975253582e-06, | |
| "loss": 1.8053, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.933264504171337e-06, | |
| "loss": 1.8445, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.930948799008728e-06, | |
| "loss": 1.7114, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.92859387818248e-06, | |
| "loss": 1.8548, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.926199760421196e-06, | |
| "loss": 1.8339, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.923766464765208e-06, | |
| "loss": 1.7359, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.921294010566434e-06, | |
| "loss": 1.8538, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.918782417488216e-06, | |
| "loss": 1.7922, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.916231705505166e-06, | |
| "loss": 1.7926, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.7149242162704468, | |
| "eval_runtime": 221.7644, | |
| "eval_samples_per_second": 11.661, | |
| "eval_steps_per_second": 0.731, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.913641894903006e-06, | |
| "loss": 1.7366, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.91101300627841e-06, | |
| "loss": 1.7165, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.908345060538838e-06, | |
| "loss": 1.7273, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.905638078902367e-06, | |
| "loss": 1.7634, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.90289208289753e-06, | |
| "loss": 1.7922, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.900107094363139e-06, | |
| "loss": 1.6726, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.897283135448106e-06, | |
| "loss": 1.9, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.89442022861128e-06, | |
| "loss": 1.8644, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.891518396621257e-06, | |
| "loss": 1.7699, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.888577662556211e-06, | |
| "loss": 1.8258, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.7066211700439453, | |
| "eval_runtime": 221.7672, | |
| "eval_samples_per_second": 11.661, | |
| "eval_steps_per_second": 0.73, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.885598049803693e-06, | |
| "loss": 1.7653, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.882579582060459e-06, | |
| "loss": 1.716, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.87952228333228e-06, | |
| "loss": 1.8161, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.876426177933743e-06, | |
| "loss": 1.6403, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.873291290488068e-06, | |
| "loss": 1.8212, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.870117645926907e-06, | |
| "loss": 1.7464, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.866905269490141e-06, | |
| "loss": 1.812, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.863654186725688e-06, | |
| "loss": 1.7119, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.860364423489299e-06, | |
| "loss": 1.7449, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.857036005944344e-06, | |
| "loss": 1.6709, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.699345588684082, | |
| "eval_runtime": 221.7101, | |
| "eval_samples_per_second": 11.664, | |
| "eval_steps_per_second": 0.731, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.853668960561611e-06, | |
| "loss": 1.8353, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.850263314119095e-06, | |
| "loss": 1.8131, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.846819093701782e-06, | |
| "loss": 1.8758, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.84333632670144e-06, | |
| "loss": 1.7605, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.839815040816391e-06, | |
| "loss": 1.8341, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.8362552640513e-06, | |
| "loss": 1.7422, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.832657024716944e-06, | |
| "loss": 1.7603, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.829020351429999e-06, | |
| "loss": 1.6797, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.825345273112796e-06, | |
| "loss": 1.778, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.82163181899311e-06, | |
| "loss": 1.6612, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.692633032798767, | |
| "eval_runtime": 221.7638, | |
| "eval_samples_per_second": 11.661, | |
| "eval_steps_per_second": 0.731, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.81788001860391e-06, | |
| "loss": 1.799, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.81408990178313e-06, | |
| "loss": 1.6594, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.810261498673441e-06, | |
| "loss": 1.8236, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.806394839722e-06, | |
| "loss": 1.8106, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.802489955680206e-06, | |
| "loss": 1.6582, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.798546877603468e-06, | |
| "loss": 1.8047, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.794565636850948e-06, | |
| "loss": 1.7607, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.790546265085317e-06, | |
| "loss": 1.7379, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.786488794272494e-06, | |
| "loss": 1.7817, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.782393256681406e-06, | |
| "loss": 1.8463, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.686733365058899, | |
| "eval_runtime": 221.7968, | |
| "eval_samples_per_second": 11.659, | |
| "eval_steps_per_second": 0.73, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.77825968488372e-06, | |
| "loss": 1.6746, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.774088111753586e-06, | |
| "loss": 1.81, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.769878570467382e-06, | |
| "loss": 1.7666, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.765631094503442e-06, | |
| "loss": 1.7299, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.761345717641794e-06, | |
| "loss": 1.6813, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.757022473963891e-06, | |
| "loss": 1.8533, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.752661397852338e-06, | |
| "loss": 1.7705, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.748262523990621e-06, | |
| "loss": 1.7602, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.743825887362832e-06, | |
| "loss": 1.8127, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.739351523253386e-06, | |
| "loss": 1.8413, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.6814411878585815, | |
| "eval_runtime": 222.7399, | |
| "eval_samples_per_second": 11.61, | |
| "eval_steps_per_second": 0.727, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.734839467246744e-06, | |
| "loss": 1.7403, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.730289755227131e-06, | |
| "loss": 1.7251, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.725702423378248e-06, | |
| "loss": 1.793, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.721077508182983e-06, | |
| "loss": 1.8803, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.716415046423126e-06, | |
| "loss": 1.877, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.711715075179075e-06, | |
| "loss": 1.7526, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.706977631829535e-06, | |
| "loss": 1.6221, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.702202754051227e-06, | |
| "loss": 1.7265, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.69739047981859e-06, | |
| "loss": 1.7845, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.692540847403468e-06, | |
| "loss": 1.7659, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.6765244007110596, | |
| "eval_runtime": 223.2206, | |
| "eval_samples_per_second": 11.585, | |
| "eval_steps_per_second": 0.726, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.687653895374824e-06, | |
| "loss": 1.7978, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.682729662598412e-06, | |
| "loss": 1.7052, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.677768188236487e-06, | |
| "loss": 1.8091, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.67276951174748e-06, | |
| "loss": 1.7734, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.667733672885688e-06, | |
| "loss": 1.7277, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.662660711700967e-06, | |
| "loss": 1.8164, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.657550668538396e-06, | |
| "loss": 1.7124, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.652403584037973e-06, | |
| "loss": 1.7963, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.647219499134278e-06, | |
| "loss": 1.6524, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.641998455056158e-06, | |
| "loss": 1.69, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.6714941263198853, | |
| "eval_runtime": 221.7019, | |
| "eval_samples_per_second": 11.664, | |
| "eval_steps_per_second": 0.731, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.636740493326398e-06, | |
| "loss": 1.7079, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.631445655761378e-06, | |
| "loss": 1.6603, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.626113984470761e-06, | |
| "loss": 1.6752, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.62074552185714e-06, | |
| "loss": 1.7644, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.615340310615713e-06, | |
| "loss": 1.6803, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.609898393733933e-06, | |
| "loss": 1.6749, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.604419814491179e-06, | |
| "loss": 1.6519, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.598904616458398e-06, | |
| "loss": 1.7138, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.593352843497768e-06, | |
| "loss": 1.6877, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.587764539762345e-06, | |
| "loss": 1.7219, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.667332410812378, | |
| "eval_runtime": 221.7085, | |
| "eval_samples_per_second": 11.664, | |
| "eval_steps_per_second": 0.731, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.582139749695713e-06, | |
| "loss": 1.7226, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.576478518031634e-06, | |
| "loss": 1.7295, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.570780889793681e-06, | |
| "loss": 1.721, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.565046910294895e-06, | |
| "loss": 1.6858, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.559276625137416e-06, | |
| "loss": 1.7445, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.553470080212122e-06, | |
| "loss": 1.6903, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.547627321698257e-06, | |
| "loss": 1.7992, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.541748396063077e-06, | |
| "loss": 1.7254, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.535833350061473e-06, | |
| "loss": 1.6893, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.5298822307356e-06, | |
| "loss": 1.6755, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.662742257118225, | |
| "eval_runtime": 221.8841, | |
| "eval_samples_per_second": 11.655, | |
| "eval_steps_per_second": 0.73, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.523895085414503e-06, | |
| "loss": 1.6372, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.517871961713736e-06, | |
| "loss": 1.8021, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.511812907534995e-06, | |
| "loss": 1.6815, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.505717971065724e-06, | |
| "loss": 1.7048, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.499587200778744e-06, | |
| "loss": 1.6524, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.493420645431853e-06, | |
| "loss": 1.6642, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.48721835406745e-06, | |
| "loss": 1.7152, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.480980376012145e-06, | |
| "loss": 1.6411, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.474706760876356e-06, | |
| "loss": 1.7822, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.468397558553928e-06, | |
| "loss": 1.7823, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.6584206819534302, | |
| "eval_runtime": 221.589, | |
| "eval_samples_per_second": 11.67, | |
| "eval_steps_per_second": 0.731, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.462052819221726e-06, | |
| "loss": 1.6793, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.455672593339241e-06, | |
| "loss": 1.7228, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.449256931648185e-06, | |
| "loss": 1.6657, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.442805885172092e-06, | |
| "loss": 1.7024, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.43631950521591e-06, | |
| "loss": 1.6369, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.429797843365594e-06, | |
| "loss": 1.7064, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.42324095148769e-06, | |
| "loss": 1.6594, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.41664888172893e-06, | |
| "loss": 1.6718, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.410021686515815e-06, | |
| "loss": 1.7348, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.4033594185542e-06, | |
| "loss": 1.7635, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.6544885635375977, | |
| "eval_runtime": 221.753, | |
| "eval_samples_per_second": 11.662, | |
| "eval_steps_per_second": 0.731, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.396662130828869e-06, | |
| "loss": 1.7155, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.389929876603112e-06, | |
| "loss": 1.6977, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.38316270941832e-06, | |
| "loss": 1.8122, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.37636068309353e-06, | |
| "loss": 1.7403, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.369523851725024e-06, | |
| "loss": 1.7272, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.362652269685881e-06, | |
| "loss": 1.6559, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.355745991625556e-06, | |
| "loss": 1.6567, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.348805072469435e-06, | |
| "loss": 1.6923, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.341829567418407e-06, | |
| "loss": 1.7745, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.334819531948418e-06, | |
| "loss": 1.7335, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.6505930423736572, | |
| "eval_runtime": 221.6702, | |
| "eval_samples_per_second": 11.666, | |
| "eval_steps_per_second": 0.731, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.327775021810037e-06, | |
| "loss": 1.6126, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.320696093028009e-06, | |
| "loss": 1.7739, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.313582801900802e-06, | |
| "loss": 1.7429, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.306435205000178e-06, | |
| "loss": 1.6804, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.299253359170722e-06, | |
| "loss": 1.731, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.292037321529404e-06, | |
| "loss": 1.6897, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.284787149465119e-06, | |
| "loss": 1.6957, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.277502900638233e-06, | |
| "loss": 1.7935, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.270184632980121e-06, | |
| "loss": 1.7074, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.262832404692714e-06, | |
| "loss": 1.7272, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.647078037261963, | |
| "eval_runtime": 221.5996, | |
| "eval_samples_per_second": 11.67, | |
| "eval_steps_per_second": 0.731, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.255446274248023e-06, | |
| "loss": 1.644, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.248026300387688e-06, | |
| "loss": 1.7362, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.240572542122502e-06, | |
| "loss": 1.6591, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.23308505873194e-06, | |
| "loss": 1.7088, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.225563909763701e-06, | |
| "loss": 1.6153, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.218009155033218e-06, | |
| "loss": 1.7105, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.210420854623191e-06, | |
| "loss": 1.7702, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.202799068883113e-06, | |
| "loss": 1.6542, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.195143858428773e-06, | |
| "loss": 1.6457, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.187455284141798e-06, | |
| "loss": 1.718, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 1.6436262130737305, | |
| "eval_runtime": 221.6177, | |
| "eval_samples_per_second": 11.669, | |
| "eval_steps_per_second": 0.731, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.179733407169146e-06, | |
| "loss": 1.7206, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.171978288922638e-06, | |
| "loss": 1.7417, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.164189991078458e-06, | |
| "loss": 1.6934, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.156368575576667e-06, | |
| "loss": 1.6417, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.148514104620711e-06, | |
| "loss": 1.6462, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.14062664067692e-06, | |
| "loss": 1.5682, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.13270624647402e-06, | |
| "loss": 1.7027, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.124752985002632e-06, | |
| "loss": 1.7179, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.116766919514765e-06, | |
| "loss": 1.7081, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.10874811352332e-06, | |
| "loss": 1.6899, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.6402881145477295, | |
| "eval_runtime": 221.6301, | |
| "eval_samples_per_second": 11.668, | |
| "eval_steps_per_second": 0.731, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.10069663080158e-06, | |
| "loss": 1.7782, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.092612535382705e-06, | |
| "loss": 1.5032, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.084495891559227e-06, | |
| "loss": 1.6477, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.076346763882529e-06, | |
| "loss": 1.6938, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.068165217162337e-06, | |
| "loss": 1.7275, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.059951316466209e-06, | |
| "loss": 1.6538, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.05170512711901e-06, | |
| "loss": 1.7431, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.043426714702398e-06, | |
| "loss": 1.7214, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.035116145054292e-06, | |
| "loss": 1.6552, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.026773484268368e-06, | |
| "loss": 1.622, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.6370071172714233, | |
| "eval_runtime": 221.6656, | |
| "eval_samples_per_second": 11.666, | |
| "eval_steps_per_second": 0.731, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.018398798693512e-06, | |
| "loss": 1.7426, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.009992154933309e-06, | |
| "loss": 1.6963, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.001553619845502e-06, | |
| "loss": 1.6488, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 8.993083260541467e-06, | |
| "loss": 1.6403, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 8.984581144385673e-06, | |
| "loss": 1.7677, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 8.976047338995156e-06, | |
| "loss": 1.7812, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 8.967481912238971e-06, | |
| "loss": 1.8025, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 8.958884932237658e-06, | |
| "loss": 1.7102, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 8.9502564673627e-06, | |
| "loss": 1.7224, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 8.941596586235972e-06, | |
| "loss": 1.6556, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.6336780786514282, | |
| "eval_runtime": 221.5029, | |
| "eval_samples_per_second": 11.675, | |
| "eval_steps_per_second": 0.731, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.932905357729213e-06, | |
| "loss": 1.6515, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.924182850963457e-06, | |
| "loss": 1.6204, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.915429135308496e-06, | |
| "loss": 1.7968, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.906644280382325e-06, | |
| "loss": 1.706, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.897828356050587e-06, | |
| "loss": 1.7528, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.88898143242602e-06, | |
| "loss": 1.6825, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.880103579867903e-06, | |
| "loss": 1.663, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.871194868981483e-06, | |
| "loss": 1.7998, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.86225537061743e-06, | |
| "loss": 1.6817, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.853285155871258e-06, | |
| "loss": 1.7912, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.6304128170013428, | |
| "eval_runtime": 221.5812, | |
| "eval_samples_per_second": 11.671, | |
| "eval_steps_per_second": 0.731, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.844284296082776e-06, | |
| "loss": 1.5936, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.835252862835508e-06, | |
| "loss": 1.7402, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.826190927956123e-06, | |
| "loss": 1.6576, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.817098563513874e-06, | |
| "loss": 1.658, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.807975841820023e-06, | |
| "loss": 1.6579, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 8.79882283542725e-06, | |
| "loss": 1.6569, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 8.7896396171291e-06, | |
| "loss": 1.7584, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 8.780426259959385e-06, | |
| "loss": 1.7632, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 8.771182837191614e-06, | |
| "loss": 1.778, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.761909422338404e-06, | |
| "loss": 1.6025, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.6273553371429443, | |
| "eval_runtime": 221.6644, | |
| "eval_samples_per_second": 11.666, | |
| "eval_steps_per_second": 0.731, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.752606089150903e-06, | |
| "loss": 1.7473, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.743272911618193e-06, | |
| "loss": 1.7449, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.733909963966709e-06, | |
| "loss": 1.6992, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.724517320659644e-06, | |
| "loss": 1.7442, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.715095056396369e-06, | |
| "loss": 1.7049, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.705643246111817e-06, | |
| "loss": 1.6719, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.696161964975907e-06, | |
| "loss": 1.6751, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 8.686651288392937e-06, | |
| "loss": 1.7948, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 8.677111292000985e-06, | |
| "loss": 1.6709, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 8.66754205167131e-06, | |
| "loss": 1.7181, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.6246178150177002, | |
| "eval_runtime": 221.5384, | |
| "eval_samples_per_second": 11.673, | |
| "eval_steps_per_second": 0.731, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 8.657943643507747e-06, | |
| "loss": 1.7374, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 8.6483161438461e-06, | |
| "loss": 1.6974, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 8.638659629253536e-06, | |
| "loss": 1.7096, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 8.628974176527982e-06, | |
| "loss": 1.7283, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 8.619259862697504e-06, | |
| "loss": 1.7745, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8.609516765019699e-06, | |
| "loss": 1.6235, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8.599744960981085e-06, | |
| "loss": 1.679, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8.589944528296476e-06, | |
| "loss": 1.7144, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8.580115544908374e-06, | |
| "loss": 1.6576, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.570258088986339e-06, | |
| "loss": 1.7452, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.6217124462127686, | |
| "eval_runtime": 221.6724, | |
| "eval_samples_per_second": 11.666, | |
| "eval_steps_per_second": 0.731, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.560372238926372e-06, | |
| "loss": 1.7452, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.550458073350296e-06, | |
| "loss": 1.7251, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.540515671105122e-06, | |
| "loss": 1.7005, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.530545111262432e-06, | |
| "loss": 1.7335, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.520546473117735e-06, | |
| "loss": 1.6461, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.510519836189853e-06, | |
| "loss": 1.7743, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.500465280220278e-06, | |
| "loss": 1.6977, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.490382885172545e-06, | |
| "loss": 1.6567, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.480272731231591e-06, | |
| "loss": 1.7074, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.470134898803113e-06, | |
| "loss": 1.5975, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 1.618903636932373, | |
| "eval_runtime": 221.623, | |
| "eval_samples_per_second": 11.668, | |
| "eval_steps_per_second": 0.731, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.459969468512943e-06, | |
| "loss": 1.7499, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.44977652120639e-06, | |
| "loss": 1.6924, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.439556137947607e-06, | |
| "loss": 1.7727, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.429308400018949e-06, | |
| "loss": 1.6344, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.419033388920315e-06, | |
| "loss": 1.689, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.40873118636851e-06, | |
| "loss": 1.6717, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.398401874296595e-06, | |
| "loss": 1.6416, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.388045534853222e-06, | |
| "loss": 1.7411, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.377662250402001e-06, | |
| "loss": 1.6613, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.36725210352083e-06, | |
| "loss": 1.5754, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 1.6161595582962036, | |
| "eval_runtime": 221.5348, | |
| "eval_samples_per_second": 11.673, | |
| "eval_steps_per_second": 0.731, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.356815177001243e-06, | |
| "loss": 1.7595, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.346351553847754e-06, | |
| "loss": 1.6056, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.33586131727719e-06, | |
| "loss": 1.7163, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.325344550718037e-06, | |
| "loss": 1.6641, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.314801337809775e-06, | |
| "loss": 1.5893, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.304231762402203e-06, | |
| "loss": 1.6807, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.29363590855479e-06, | |
| "loss": 1.6655, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.28301386053599e-06, | |
| "loss": 1.7629, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.272365702822577e-06, | |
| "loss": 1.667, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 8.261691520098985e-06, | |
| "loss": 1.7077, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 1.6135671138763428, | |
| "eval_runtime": 221.6285, | |
| "eval_samples_per_second": 11.668, | |
| "eval_steps_per_second": 0.731, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 8.250991397256609e-06, | |
| "loss": 1.6214, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 8.240265419393157e-06, | |
| "loss": 1.7911, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 8.229513671811953e-06, | |
| "loss": 1.6051, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 8.218736240021271e-06, | |
| "loss": 1.7498, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 8.207933209733654e-06, | |
| "loss": 1.6407, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 8.197104666865218e-06, | |
| "loss": 1.6836, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 8.186250697534993e-06, | |
| "loss": 1.6793, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 8.175371388064212e-06, | |
| "loss": 1.7107, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 8.164466824975648e-06, | |
| "loss": 1.6544, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 8.153537094992907e-06, | |
| "loss": 1.5848, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.6112371683120728, | |
| "eval_runtime": 221.5593, | |
| "eval_samples_per_second": 11.672, | |
| "eval_steps_per_second": 0.731, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 8.142582285039753e-06, | |
| "loss": 1.6878, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 8.131602482239405e-06, | |
| "loss": 1.7152, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 8.120597773913851e-06, | |
| "loss": 1.6608, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 8.109568247583155e-06, | |
| "loss": 1.7256, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 8.098513990964754e-06, | |
| "loss": 1.6854, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 8.087435091972762e-06, | |
| "loss": 1.6055, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 8.076331638717278e-06, | |
| "loss": 1.6369, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 8.065203719503679e-06, | |
| "loss": 1.6198, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 8.054051422831918e-06, | |
| "loss": 1.6972, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 8.042874837395816e-06, | |
| "loss": 1.7011, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 1.6087462902069092, | |
| "eval_runtime": 221.6783, | |
| "eval_samples_per_second": 11.666, | |
| "eval_steps_per_second": 0.731, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 8.031674052082372e-06, | |
| "loss": 1.699, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 8.02044915597104e-06, | |
| "loss": 1.6248, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 8.009200238333028e-06, | |
| "loss": 1.6441, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.99792738863058e-06, | |
| "loss": 1.6321, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.986630696516281e-06, | |
| "loss": 1.7742, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.975310251832328e-06, | |
| "loss": 1.5576, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.963966144609821e-06, | |
| "loss": 1.6902, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.95259846506805e-06, | |
| "loss": 1.5873, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.941207303613773e-06, | |
| "loss": 1.7496, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.929792750840499e-06, | |
| "loss": 1.6697, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.6065231561660767, | |
| "eval_runtime": 221.5733, | |
| "eval_samples_per_second": 11.671, | |
| "eval_steps_per_second": 0.731, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.918354897527767e-06, | |
| "loss": 1.6903, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.906893834640428e-06, | |
| "loss": 1.6335, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.89540965332791e-06, | |
| "loss": 1.6909, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.883902444923513e-06, | |
| "loss": 1.6651, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.872372300943657e-06, | |
| "loss": 1.7373, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.860819313087177e-06, | |
| "loss": 1.7589, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.849243573234582e-06, | |
| "loss": 1.5605, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.837645173447329e-06, | |
| "loss": 1.5867, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.826024205967084e-06, | |
| "loss": 1.6352, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.814380763214996e-06, | |
| "loss": 1.6633, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.6041749715805054, | |
| "eval_runtime": 221.6305, | |
| "eval_samples_per_second": 11.668, | |
| "eval_steps_per_second": 0.731, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.80271493779096e-06, | |
| "loss": 1.6448, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.791026822472876e-06, | |
| "loss": 1.6371, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.779316510215919e-06, | |
| "loss": 1.6645, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.767584094151793e-06, | |
| "loss": 1.757, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.755829667587993e-06, | |
| "loss": 1.7246, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 7.744053324007064e-06, | |
| "loss": 1.72, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 7.732255157065854e-06, | |
| "loss": 1.7041, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 7.720435260594774e-06, | |
| "loss": 1.7085, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 7.708593728597047e-06, | |
| "loss": 1.6751, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.696730655247963e-06, | |
| "loss": 1.6722, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 1.601514220237732, | |
| "eval_runtime": 221.608, | |
| "eval_samples_per_second": 11.669, | |
| "eval_steps_per_second": 0.731, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.684846134894133e-06, | |
| "loss": 1.6057, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.67294026205273e-06, | |
| "loss": 1.6744, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.661013131410745e-06, | |
| "loss": 1.6633, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.649064837824231e-06, | |
| "loss": 1.5247, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.637095476317553e-06, | |
| "loss": 1.7302, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.6251051420826224e-06, | |
| "loss": 1.645, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.613093930478148e-06, | |
| "loss": 1.5705, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.601061937028881e-06, | |
| "loss": 1.6186, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.58900925742484e-06, | |
| "loss": 1.6353, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.576935987520566e-06, | |
| "loss": 1.7181, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 1.5993202924728394, | |
| "eval_runtime": 221.5695, | |
| "eval_samples_per_second": 11.671, | |
| "eval_steps_per_second": 0.731, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.5648422233343564e-06, | |
| "loss": 1.7363, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.552728061047492e-06, | |
| "loss": 1.5845, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.54059359700348e-06, | |
| "loss": 1.6761, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.528438927707298e-06, | |
| "loss": 1.7179, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 7.5162641498246e-06, | |
| "loss": 1.66, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 7.504069360180971e-06, | |
| "loss": 1.5965, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 7.491854655761149e-06, | |
| "loss": 1.6249, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 7.479620133708246e-06, | |
| "loss": 1.7097, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.467365891322996e-06, | |
| "loss": 1.6683, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.455092026062955e-06, | |
| "loss": 1.6414, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.597200870513916, | |
| "eval_runtime": 221.5771, | |
| "eval_samples_per_second": 11.671, | |
| "eval_steps_per_second": 0.731, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.442798635541749e-06, | |
| "loss": 1.6526, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.430485817528281e-06, | |
| "loss": 1.7332, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.418153669945966e-06, | |
| "loss": 1.7415, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.40580229087194e-06, | |
| "loss": 1.681, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.3934317785362905e-06, | |
| "loss": 1.6391, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.381042231321269e-06, | |
| "loss": 1.6842, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7.368633747760515e-06, | |
| "loss": 1.6552, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7.356206426538262e-06, | |
| "loss": 1.5381, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7.343760366488564e-06, | |
| "loss": 1.6983, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7.3312956665945e-06, | |
| "loss": 1.6856, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 1.5951831340789795, | |
| "eval_runtime": 221.5238, | |
| "eval_samples_per_second": 11.674, | |
| "eval_steps_per_second": 0.731, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.3188124259873946e-06, | |
| "loss": 1.6686, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.306310743946024e-06, | |
| "loss": 1.7121, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.29379071989583e-06, | |
| "loss": 1.6359, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.281252453408125e-06, | |
| "loss": 1.5617, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 7.268696044199305e-06, | |
| "loss": 1.5664, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 7.2561215921300545e-06, | |
| "loss": 1.5337, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 7.243529197204552e-06, | |
| "loss": 1.6212, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 7.230918959569675e-06, | |
| "loss": 1.5584, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 7.218290979514202e-06, | |
| "loss": 1.579, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 7.205645357468016e-06, | |
| "loss": 1.6491, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 1.5929887294769287, | |
| "eval_runtime": 221.6187, | |
| "eval_samples_per_second": 11.669, | |
| "eval_steps_per_second": 0.731, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 7.192982194001312e-06, | |
| "loss": 1.6226, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 7.180301589823784e-06, | |
| "loss": 1.5809, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 7.167603645783835e-06, | |
| "loss": 1.6546, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 7.154888462867771e-06, | |
| "loss": 1.7025, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 7.142156142198997e-06, | |
| "loss": 1.7083, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 7.129406785037214e-06, | |
| "loss": 1.674, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 7.116640492777617e-06, | |
| "loss": 1.6955, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 7.103857366950081e-06, | |
| "loss": 1.5851, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 7.091057509218357e-06, | |
| "loss": 1.6826, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.078241021379272e-06, | |
| "loss": 1.6736, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 1.591227412223816, | |
| "eval_runtime": 221.512, | |
| "eval_samples_per_second": 11.674, | |
| "eval_steps_per_second": 0.731, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.065408005361902e-06, | |
| "loss": 1.5673, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.052558563226777e-06, | |
| "loss": 1.7022, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.039692797165061e-06, | |
| "loss": 1.6071, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 7.026810809497744e-06, | |
| "loss": 1.5948, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 7.013912702674821e-06, | |
| "loss": 1.5293, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 7.000998579274487e-06, | |
| "loss": 1.6306, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 6.988068542002316e-06, | |
| "loss": 1.732, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 6.9751226936904415e-06, | |
| "loss": 1.6915, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 6.9621611372967436e-06, | |
| "loss": 1.6018, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 6.949183975904027e-06, | |
| "loss": 1.619, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 1.5893467664718628, | |
| "eval_runtime": 221.6889, | |
| "eval_samples_per_second": 11.665, | |
| "eval_steps_per_second": 0.731, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 6.9361913127192026e-06, | |
| "loss": 1.6266, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 6.923183251072468e-06, | |
| "loss": 1.5814, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 6.910159894416485e-06, | |
| "loss": 1.6962, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 6.897121346325552e-06, | |
| "loss": 1.6047, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 6.884067710494788e-06, | |
| "loss": 1.6322, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 6.870999090739301e-06, | |
| "loss": 1.6904, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 6.857915590993371e-06, | |
| "loss": 1.6751, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 6.844817315309611e-06, | |
| "loss": 1.6209, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.831704367858154e-06, | |
| "loss": 1.5679, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.818576852925809e-06, | |
| "loss": 1.6452, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.5870401859283447, | |
| "eval_runtime": 221.5795, | |
| "eval_samples_per_second": 11.671, | |
| "eval_steps_per_second": 0.731, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.805434874915249e-06, | |
| "loss": 1.5774, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.792278538344161e-06, | |
| "loss": 1.5994, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 6.779107947844434e-06, | |
| "loss": 1.7274, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 6.765923208161313e-06, | |
| "loss": 1.673, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 6.752724424152575e-06, | |
| "loss": 1.5622, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 6.739511700787683e-06, | |
| "loss": 1.5549, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 6.726285143146969e-06, | |
| "loss": 1.7017, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 6.713044856420781e-06, | |
| "loss": 1.651, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 6.699790945908662e-06, | |
| "loss": 1.6616, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 6.686523517018494e-06, | |
| "loss": 1.6498, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 1.5853816270828247, | |
| "eval_runtime": 221.6093, | |
| "eval_samples_per_second": 11.669, | |
| "eval_steps_per_second": 0.731, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 6.67324267526568e-06, | |
| "loss": 1.7092, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 6.6599485262722885e-06, | |
| "loss": 1.5833, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 6.646641175766222e-06, | |
| "loss": 1.543, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 6.633320729580376e-06, | |
| "loss": 1.7974, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.6199872936517915e-06, | |
| "loss": 1.598, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.606640974020824e-06, | |
| "loss": 1.5978, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.593281876830281e-06, | |
| "loss": 1.6066, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 6.5799101083246e-06, | |
| "loss": 1.5975, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 6.566525774848988e-06, | |
| "loss": 1.6255, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 6.553128982848584e-06, | |
| "loss": 1.675, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 1.5839300155639648, | |
| "eval_runtime": 221.6131, | |
| "eval_samples_per_second": 11.669, | |
| "eval_steps_per_second": 0.731, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 6.539719838867604e-06, | |
| "loss": 1.6697, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 6.526298449548502e-06, | |
| "loss": 1.6142, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 6.512864921631121e-06, | |
| "loss": 1.5982, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 6.499419361951837e-06, | |
| "loss": 1.8056, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 6.4859618774427195e-06, | |
| "loss": 1.6077, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 6.472492575130671e-06, | |
| "loss": 1.6571, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 6.459011562136582e-06, | |
| "loss": 1.5264, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 6.44551894567448e-06, | |
| "loss": 1.6544, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 6.432014833050671e-06, | |
| "loss": 1.6281, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 6.41849933166289e-06, | |
| "loss": 1.684, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 1.5822992324829102, | |
| "eval_runtime": 221.5143, | |
| "eval_samples_per_second": 11.674, | |
| "eval_steps_per_second": 0.731, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 6.404972548999453e-06, | |
| "loss": 1.5226, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 6.3914345926383855e-06, | |
| "loss": 1.5802, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 6.3778855702465835e-06, | |
| "loss": 1.6287, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 6.364325589578948e-06, | |
| "loss": 1.5856, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 6.350754758477534e-06, | |
| "loss": 1.6461, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 6.337173184870683e-06, | |
| "loss": 1.7742, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 6.323580976772181e-06, | |
| "loss": 1.6065, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.309978242280382e-06, | |
| "loss": 1.647, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.2963650895773566e-06, | |
| "loss": 1.5884, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.282741626928036e-06, | |
| "loss": 1.6379, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 1.5801777839660645, | |
| "eval_runtime": 221.7292, | |
| "eval_samples_per_second": 11.663, | |
| "eval_steps_per_second": 0.731, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 6.269107962679344e-06, | |
| "loss": 1.633, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 6.255464205259332e-06, | |
| "loss": 1.7188, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 6.241810463176329e-06, | |
| "loss": 1.558, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 6.228146845018068e-06, | |
| "loss": 1.5924, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 6.214473459450828e-06, | |
| "loss": 1.6427, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 6.200790415218568e-06, | |
| "loss": 1.6439, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 6.187097821142061e-06, | |
| "loss": 1.6606, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 6.173395786118026e-06, | |
| "loss": 1.7101, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 6.159684419118274e-06, | |
| "loss": 1.6778, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 6.145963829188823e-06, | |
| "loss": 1.5173, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.5786410570144653, | |
| "eval_runtime": 221.549, | |
| "eval_samples_per_second": 11.672, | |
| "eval_steps_per_second": 0.731, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 6.1322341254490515e-06, | |
| "loss": 1.6827, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 6.118495417090809e-06, | |
| "loss": 1.5186, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 6.104747813377567e-06, | |
| "loss": 1.633, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 6.0909914236435355e-06, | |
| "loss": 1.6671, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 6.077226357292802e-06, | |
| "loss": 1.6258, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 6.063452723798461e-06, | |
| "loss": 1.6377, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 6.0496706327017355e-06, | |
| "loss": 1.5934, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 6.0358801936111145e-06, | |
| "loss": 1.5484, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 6.022081516201483e-06, | |
| "loss": 1.6516, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 6.008274710213235e-06, | |
| "loss": 1.6443, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 1.577327013015747, | |
| "eval_runtime": 221.6766, | |
| "eval_samples_per_second": 11.666, | |
| "eval_steps_per_second": 0.731, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 5.994459885451423e-06, | |
| "loss": 1.6277, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 5.9806371517848605e-06, | |
| "loss": 1.6301, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 5.966806619145268e-06, | |
| "loss": 1.6091, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 5.952968397526388e-06, | |
| "loss": 1.6848, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 5.9391225969831145e-06, | |
| "loss": 1.5756, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 5.925269327630615e-06, | |
| "loss": 1.6308, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 5.911408699643458e-06, | |
| "loss": 1.5454, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 5.897540823254735e-06, | |
| "loss": 1.6046, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 5.883665808755179e-06, | |
| "loss": 1.6638, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 5.8697837664923e-06, | |
| "loss": 1.5628, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 1.5755133628845215, | |
| "eval_runtime": 221.5842, | |
| "eval_samples_per_second": 11.671, | |
| "eval_steps_per_second": 0.731, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 5.855894806869493e-06, | |
| "loss": 1.6173, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5.841999040345168e-06, | |
| "loss": 1.5758, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5.828096577431874e-06, | |
| "loss": 1.6503, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5.814187528695412e-06, | |
| "loss": 1.6151, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5.800272004753961e-06, | |
| "loss": 1.5789, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 5.786350116277195e-06, | |
| "loss": 1.5589, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 5.772421973985412e-06, | |
| "loss": 1.6134, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 5.758487688648635e-06, | |
| "loss": 1.5238, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 5.744547371085752e-06, | |
| "loss": 1.6672, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 5.730601132163623e-06, | |
| "loss": 1.7287, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 1.5738086700439453, | |
| "eval_runtime": 221.6243, | |
| "eval_samples_per_second": 11.668, | |
| "eval_steps_per_second": 0.731, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 5.716649082796199e-06, | |
| "loss": 1.5054, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 5.702691333943638e-06, | |
| "loss": 1.7154, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 5.688727996611434e-06, | |
| "loss": 1.5585, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 5.6747591818495185e-06, | |
| "loss": 1.625, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 5.6607850007513876e-06, | |
| "loss": 1.6745, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 5.646805564453216e-06, | |
| "loss": 1.748, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 5.632820984132973e-06, | |
| "loss": 1.6759, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.6188313710095375e-06, | |
| "loss": 1.636, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.604836836341816e-06, | |
| "loss": 1.5845, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.5908374914278495e-06, | |
| "loss": 1.5615, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 1.5724763870239258, | |
| "eval_runtime": 221.5669, | |
| "eval_samples_per_second": 11.671, | |
| "eval_steps_per_second": 0.731, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5.576833447603943e-06, | |
| "loss": 1.5203, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5.562824816243769e-06, | |
| "loss": 1.6132, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5.5488117087574785e-06, | |
| "loss": 1.6566, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5.5347942365908315e-06, | |
| "loss": 1.6915, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.520772511224293e-06, | |
| "loss": 1.739, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.506746644172154e-06, | |
| "loss": 1.5929, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.492716746981646e-06, | |
| "loss": 1.5804, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.478682931232053e-06, | |
| "loss": 1.6294, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 5.46464530853382e-06, | |
| "loss": 1.6411, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 5.45060399052767e-06, | |
| "loss": 1.6129, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 1.5711848735809326, | |
| "eval_runtime": 221.6895, | |
| "eval_samples_per_second": 11.665, | |
| "eval_steps_per_second": 0.731, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 5.4365590888837175e-06, | |
| "loss": 1.6629, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 5.4225107153005715e-06, | |
| "loss": 1.6555, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 5.408458981504458e-06, | |
| "loss": 1.5144, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 5.394403999248327e-06, | |
| "loss": 1.5986, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 5.3803458803109606e-06, | |
| "loss": 1.6898, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 5.3662847364960855e-06, | |
| "loss": 1.6196, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.352220679631491e-06, | |
| "loss": 1.6847, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.338153821568127e-06, | |
| "loss": 1.6208, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.324084274179228e-06, | |
| "loss": 1.6083, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.310012149359411e-06, | |
| "loss": 1.6709, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 1.5699827671051025, | |
| "eval_runtime": 221.5944, | |
| "eval_samples_per_second": 11.67, | |
| "eval_steps_per_second": 0.731, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 5.295937559023794e-06, | |
| "loss": 1.565, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 5.2818606151071015e-06, | |
| "loss": 1.667, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 5.26778142956278e-06, | |
| "loss": 1.4954, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 5.253700114362096e-06, | |
| "loss": 1.5335, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 5.23961678149326e-06, | |
| "loss": 1.645, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 5.225531542960528e-06, | |
| "loss": 1.5962, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 5.211444510783309e-06, | |
| "loss": 1.6939, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 5.197355796995277e-06, | |
| "loss": 1.6092, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 5.183265513643484e-06, | |
| "loss": 1.5633, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 5.169173772787458e-06, | |
| "loss": 1.5818, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 1.5683159828186035, | |
| "eval_runtime": 221.5828, | |
| "eval_samples_per_second": 11.671, | |
| "eval_steps_per_second": 0.731, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 5.1550806864983235e-06, | |
| "loss": 1.6241, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 5.140986366857904e-06, | |
| "loss": 1.6045, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 5.126890925957832e-06, | |
| "loss": 1.6047, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 5.1127944758986545e-06, | |
| "loss": 1.6186, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 5.098697128788951e-06, | |
| "loss": 1.5565, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 5.084598996744426e-06, | |
| "loss": 1.6093, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 5.070500191887034e-06, | |
| "loss": 1.5773, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 5.056400826344078e-06, | |
| "loss": 1.6378, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 5.042301012247317e-06, | |
| "loss": 1.6531, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 5.028200861732083e-06, | |
| "loss": 1.6358, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 1.567191481590271, | |
| "eval_runtime": 221.5558, | |
| "eval_samples_per_second": 11.672, | |
| "eval_steps_per_second": 0.731, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 5.014100486936383e-06, | |
| "loss": 1.6578, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 5e-06, | |
| "loss": 1.5503, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 4.985899513063618e-06, | |
| "loss": 1.5313, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 4.971799138267918e-06, | |
| "loss": 1.5539, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 4.957698987752684e-06, | |
| "loss": 1.6979, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 4.943599173655924e-06, | |
| "loss": 1.6068, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.929499808112969e-06, | |
| "loss": 1.6521, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.915401003255577e-06, | |
| "loss": 1.6487, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.9013028712110526e-06, | |
| "loss": 1.7284, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.8872055241013455e-06, | |
| "loss": 1.6513, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 1.566185474395752, | |
| "eval_runtime": 221.56, | |
| "eval_samples_per_second": 11.672, | |
| "eval_steps_per_second": 0.731, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.873109074042169e-06, | |
| "loss": 1.541, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.859013633142096e-06, | |
| "loss": 1.6876, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.844919313501677e-06, | |
| "loss": 1.607, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.830826227212543e-06, | |
| "loss": 1.6963, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.816734486356518e-06, | |
| "loss": 1.5876, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.802644203004724e-06, | |
| "loss": 1.6434, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.788555489216692e-06, | |
| "loss": 1.678, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.7744684570394734e-06, | |
| "loss": 1.5858, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.760383218506742e-06, | |
| "loss": 1.5771, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.7462998856379065e-06, | |
| "loss": 1.5637, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 1.5654144287109375, | |
| "eval_runtime": 221.6983, | |
| "eval_samples_per_second": 11.665, | |
| "eval_steps_per_second": 0.731, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.732218570437224e-06, | |
| "loss": 1.6174, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.7181393848929e-06, | |
| "loss": 1.6466, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.704062440976209e-06, | |
| "loss": 1.5726, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.6899878506405904e-06, | |
| "loss": 1.6325, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.675915725820773e-06, | |
| "loss": 1.7229, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.661846178431873e-06, | |
| "loss": 1.5601, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.64777932036851e-06, | |
| "loss": 1.6655, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.633715263503915e-06, | |
| "loss": 1.5783, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.619654119689041e-06, | |
| "loss": 1.6456, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.6055960007516734e-06, | |
| "loss": 1.612, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 1.5643430948257446, | |
| "eval_runtime": 221.536, | |
| "eval_samples_per_second": 11.673, | |
| "eval_steps_per_second": 0.731, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.591541018495543e-06, | |
| "loss": 1.5746, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.577489284699429e-06, | |
| "loss": 1.6141, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.563440911116283e-06, | |
| "loss": 1.5741, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.549396009472331e-06, | |
| "loss": 1.6693, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.535354691466181e-06, | |
| "loss": 1.5201, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.521317068767949e-06, | |
| "loss": 1.6772, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.507283253018355e-06, | |
| "loss": 1.6413, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.493253355827846e-06, | |
| "loss": 1.6118, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.479227488775707e-06, | |
| "loss": 1.6488, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.465205763409169e-06, | |
| "loss": 1.6396, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 1.5630210638046265, | |
| "eval_runtime": 221.6501, | |
| "eval_samples_per_second": 11.667, | |
| "eval_steps_per_second": 0.731, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.4511882912425214e-06, | |
| "loss": 1.6083, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.437175183756233e-06, | |
| "loss": 1.6805, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.4231665523960574e-06, | |
| "loss": 1.6304, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.409162508572151e-06, | |
| "loss": 1.6537, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.395163163658186e-06, | |
| "loss": 1.6465, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.381168628990463e-06, | |
| "loss": 1.5872, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.367179015867028e-06, | |
| "loss": 1.6445, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.3531944355467855e-06, | |
| "loss": 1.7094, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.339214999248614e-06, | |
| "loss": 1.5845, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.325240818150485e-06, | |
| "loss": 1.6414, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 1.5620007514953613, | |
| "eval_runtime": 221.5034, | |
| "eval_samples_per_second": 11.675, | |
| "eval_steps_per_second": 0.731, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.311272003388569e-06, | |
| "loss": 1.6654, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.297308666056363e-06, | |
| "loss": 1.5831, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.283350917203802e-06, | |
| "loss": 1.6675, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.269398867836377e-06, | |
| "loss": 1.5759, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.255452628914248e-06, | |
| "loss": 1.6232, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.2415123113513665e-06, | |
| "loss": 1.6168, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.22757802601459e-06, | |
| "loss": 1.6575, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.213649883722806e-06, | |
| "loss": 1.5819, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.199727995246041e-06, | |
| "loss": 1.6676, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.185812471304589e-06, | |
| "loss": 1.6096, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 1.5610833168029785, | |
| "eval_runtime": 221.6192, | |
| "eval_samples_per_second": 11.669, | |
| "eval_steps_per_second": 0.731, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.171903422568128e-06, | |
| "loss": 1.6859, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.158000959654833e-06, | |
| "loss": 1.6561, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.1441051931305095e-06, | |
| "loss": 1.7081, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.130216233507702e-06, | |
| "loss": 1.6924, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.116334191244823e-06, | |
| "loss": 1.6573, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.102459176745267e-06, | |
| "loss": 1.5603, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.088591300356543e-06, | |
| "loss": 1.5204, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.074730672369386e-06, | |
| "loss": 1.5972, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.060877403016886e-06, | |
| "loss": 1.6257, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.047031602473613e-06, | |
| "loss": 1.6149, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 1.560268521308899, | |
| "eval_runtime": 221.5662, | |
| "eval_samples_per_second": 11.671, | |
| "eval_steps_per_second": 0.731, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.033193380854733e-06, | |
| "loss": 1.6141, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.019362848215141e-06, | |
| "loss": 1.646, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.00554011454858e-06, | |
| "loss": 1.6241, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 3.991725289786766e-06, | |
| "loss": 1.5474, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 3.977918483798519e-06, | |
| "loss": 1.6931, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 3.964119806388887e-06, | |
| "loss": 1.6239, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.950329367298268e-06, | |
| "loss": 1.716, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.936547276201542e-06, | |
| "loss": 1.5429, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.9227736427071995e-06, | |
| "loss": 1.628, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.909008576356467e-06, | |
| "loss": 1.5886, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 1.5592665672302246, | |
| "eval_runtime": 221.6247, | |
| "eval_samples_per_second": 11.668, | |
| "eval_steps_per_second": 0.731, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.895252186622433e-06, | |
| "loss": 1.7161, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.8815045829091915e-06, | |
| "loss": 1.6288, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.867765874550949e-06, | |
| "loss": 1.5689, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.854036170811176e-06, | |
| "loss": 1.6022, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.840315580881728e-06, | |
| "loss": 1.531, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.826604213881975e-06, | |
| "loss": 1.6102, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.812902178857941e-06, | |
| "loss": 1.6612, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.7992095847814337e-06, | |
| "loss": 1.6132, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.785526540549173e-06, | |
| "loss": 1.5645, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.771853154981934e-06, | |
| "loss": 1.537, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 1.5582250356674194, | |
| "eval_runtime": 221.5377, | |
| "eval_samples_per_second": 11.673, | |
| "eval_steps_per_second": 0.731, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.758189536823673e-06, | |
| "loss": 1.6137, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.7445357947406714e-06, | |
| "loss": 1.6117, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.730892037320659e-06, | |
| "loss": 1.5968, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.717258373071965e-06, | |
| "loss": 1.5811, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.7036349104226434e-06, | |
| "loss": 1.6562, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.6900217577196183e-06, | |
| "loss": 1.5226, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.67641902322782e-06, | |
| "loss": 1.641, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.662826815129317e-06, | |
| "loss": 1.5802, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.6492452415224675e-06, | |
| "loss": 1.6854, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.6356744104210528e-06, | |
| "loss": 1.5883, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 1.5573909282684326, | |
| "eval_runtime": 221.6972, | |
| "eval_samples_per_second": 11.665, | |
| "eval_steps_per_second": 0.731, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.6221144297534178e-06, | |
| "loss": 1.6555, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.608565407361615e-06, | |
| "loss": 1.5577, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.595027451000549e-06, | |
| "loss": 1.5049, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.58150066833711e-06, | |
| "loss": 1.4957, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.567985166949331e-06, | |
| "loss": 1.6509, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.554481054325522e-06, | |
| "loss": 1.6039, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.540988437863421e-06, | |
| "loss": 1.5138, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.527507424869332e-06, | |
| "loss": 1.6161, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.5140381225572826e-06, | |
| "loss": 1.6566, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.5005806380481634e-06, | |
| "loss": 1.6512, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 1.556625247001648, | |
| "eval_runtime": 221.5959, | |
| "eval_samples_per_second": 11.67, | |
| "eval_steps_per_second": 0.731, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.4871350783688795e-06, | |
| "loss": 1.5832, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.4737015504514993e-06, | |
| "loss": 1.6393, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.4602801611323977e-06, | |
| "loss": 1.5706, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.4468710171514175e-06, | |
| "loss": 1.5715, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.4334742251510127e-06, | |
| "loss": 1.5803, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.420089891675401e-06, | |
| "loss": 1.7129, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.40671812316972e-06, | |
| "loss": 1.6066, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.393359025979178e-06, | |
| "loss": 1.6188, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.3800127063482097e-06, | |
| "loss": 1.7055, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.366679270419626e-06, | |
| "loss": 1.683, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 1.5559163093566895, | |
| "eval_runtime": 221.6474, | |
| "eval_samples_per_second": 11.667, | |
| "eval_steps_per_second": 0.731, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.35335882423378e-06, | |
| "loss": 1.6224, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.3400514737277144e-06, | |
| "loss": 1.5804, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3.326757324734322e-06, | |
| "loss": 1.6535, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3.3134764829815064e-06, | |
| "loss": 1.6257, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3.300209054091339e-06, | |
| "loss": 1.6455, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.2869551435792185e-06, | |
| "loss": 1.5455, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.273714856853033e-06, | |
| "loss": 1.5906, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.260488299212319e-06, | |
| "loss": 1.5916, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.247275575847427e-06, | |
| "loss": 1.7453, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.2340767918386883e-06, | |
| "loss": 1.7059, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 1.5549125671386719, | |
| "eval_runtime": 221.5512, | |
| "eval_samples_per_second": 11.672, | |
| "eval_steps_per_second": 0.731, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.2208920521555677e-06, | |
| "loss": 1.7162, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.20772146165584e-06, | |
| "loss": 1.6342, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.194565125084753e-06, | |
| "loss": 1.6197, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.181423147074192e-06, | |
| "loss": 1.6359, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.1682956321418484e-06, | |
| "loss": 1.6265, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.15518268469039e-06, | |
| "loss": 1.4916, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.1420844090066315e-06, | |
| "loss": 1.5581, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.1290009092606988e-06, | |
| "loss": 1.6289, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.1159322895052135e-06, | |
| "loss": 1.5356, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.1028786536744495e-06, | |
| "loss": 1.5453, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 1.554166316986084, | |
| "eval_runtime": 221.6837, | |
| "eval_samples_per_second": 11.665, | |
| "eval_steps_per_second": 0.731, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.089840105583516e-06, | |
| "loss": 1.6232, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 3.0768167489275325e-06, | |
| "loss": 1.6116, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 3.0638086872807987e-06, | |
| "loss": 1.5252, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 3.050816024095975e-06, | |
| "loss": 1.6361, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 3.037838862703258e-06, | |
| "loss": 1.6747, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.0248773063095606e-06, | |
| "loss": 1.5886, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.0119314579976854e-06, | |
| "loss": 1.6214, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.9990014207255134e-06, | |
| "loss": 1.583, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.9860872973251815e-06, | |
| "loss": 1.5699, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.9731891905022593e-06, | |
| "loss": 1.5738, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 1.553594708442688, | |
| "eval_runtime": 221.5462, | |
| "eval_samples_per_second": 11.673, | |
| "eval_steps_per_second": 0.731, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.960307202834941e-06, | |
| "loss": 1.632, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.947441436773224e-06, | |
| "loss": 1.6873, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.9345919946380985e-06, | |
| "loss": 1.6665, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.9217589786207296e-06, | |
| "loss": 1.585, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.9089424907816433e-06, | |
| "loss": 1.5554, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.896142633049922e-06, | |
| "loss": 1.69, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.8833595072223842e-06, | |
| "loss": 1.5192, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.870593214962787e-06, | |
| "loss": 1.5848, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.8578438578010053e-06, | |
| "loss": 1.6617, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.8451115371322302e-06, | |
| "loss": 1.6004, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 1.5529882907867432, | |
| "eval_runtime": 221.6028, | |
| "eval_samples_per_second": 11.67, | |
| "eval_steps_per_second": 0.731, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.8323963542161665e-06, | |
| "loss": 1.6171, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.8196984101762182e-06, | |
| "loss": 1.6354, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.807017805998689e-06, | |
| "loss": 1.6368, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.7943546425319857e-06, | |
| "loss": 1.5776, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.7817090204857997e-06, | |
| "loss": 1.6396, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.7690810404303276e-06, | |
| "loss": 1.6176, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.756470802795449e-06, | |
| "loss": 1.5653, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.743878407869947e-06, | |
| "loss": 1.6045, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.7313039558006952e-06, | |
| "loss": 1.621, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.7187475465918768e-06, | |
| "loss": 1.6753, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 1.5522700548171997, | |
| "eval_runtime": 221.543, | |
| "eval_samples_per_second": 11.673, | |
| "eval_steps_per_second": 0.731, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.7062092801041717e-06, | |
| "loss": 1.5738, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.693689256053976e-06, | |
| "loss": 1.672, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.6811875740126063e-06, | |
| "loss": 1.5926, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.6687043334055017e-06, | |
| "loss": 1.5286, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.656239633511437e-06, | |
| "loss": 1.5802, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.643793573461739e-06, | |
| "loss": 1.6207, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.631366252239488e-06, | |
| "loss": 1.582, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.6189577686787317e-06, | |
| "loss": 1.6199, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.6065682214637124e-06, | |
| "loss": 1.6498, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.5941977091280614e-06, | |
| "loss": 1.6362, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 1.551666498184204, | |
| "eval_runtime": 221.6901, | |
| "eval_samples_per_second": 11.665, | |
| "eval_steps_per_second": 0.731, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.581846330054034e-06, | |
| "loss": 1.6039, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.5695141824717183e-06, | |
| "loss": 1.4543, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.557201364458252e-06, | |
| "loss": 1.5505, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.5449079739370454e-06, | |
| "loss": 1.5936, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.532634108677006e-06, | |
| "loss": 1.5993, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.5203798662917555e-06, | |
| "loss": 1.5803, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.508145344238854e-06, | |
| "loss": 1.5481, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.4959306398190304e-06, | |
| "loss": 1.5412, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.483735850175402e-06, | |
| "loss": 1.5478, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.471561072292703e-06, | |
| "loss": 1.5805, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 1.5511072874069214, | |
| "eval_runtime": 221.428, | |
| "eval_samples_per_second": 11.679, | |
| "eval_steps_per_second": 0.732, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.4594064029965197e-06, | |
| "loss": 1.6623, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.44727193895251e-06, | |
| "loss": 1.5497, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.4351577766656465e-06, | |
| "loss": 1.6082, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.4230640124794364e-06, | |
| "loss": 1.6368, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.4109907425751616e-06, | |
| "loss": 1.6386, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.3989380629711197e-06, | |
| "loss": 1.6387, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.3869060695218513e-06, | |
| "loss": 1.5591, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.3748948579173792e-06, | |
| "loss": 1.5081, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.362904523682447e-06, | |
| "loss": 1.5427, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.350935162175769e-06, | |
| "loss": 1.6416, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 1.5508249998092651, | |
| "eval_runtime": 221.6253, | |
| "eval_samples_per_second": 11.668, | |
| "eval_steps_per_second": 0.731, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.3389868685892573e-06, | |
| "loss": 1.6477, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.3270597379472713e-06, | |
| "loss": 1.5434, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.3151538651058687e-06, | |
| "loss": 1.6604, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.303269344752039e-06, | |
| "loss": 1.5617, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.2914062714029545e-06, | |
| "loss": 1.6272, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.2795647394052284e-06, | |
| "loss": 1.5248, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.267744842934147e-06, | |
| "loss": 1.7009, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.255946675992938e-06, | |
| "loss": 1.5608, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.2441703324120095e-06, | |
| "loss": 1.6098, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.2324159058482086e-06, | |
| "loss": 1.5755, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 1.5505614280700684, | |
| "eval_runtime": 221.4712, | |
| "eval_samples_per_second": 11.676, | |
| "eval_steps_per_second": 0.731, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.2206834897840814e-06, | |
| "loss": 1.5641, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.208973177527125e-06, | |
| "loss": 1.586, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.1972850622090426e-06, | |
| "loss": 1.7206, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.185619236785005e-06, | |
| "loss": 1.4538, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.1739757940329177e-06, | |
| "loss": 1.6007, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.1623548265526734e-06, | |
| "loss": 1.5956, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.1507564267654187e-06, | |
| "loss": 1.5959, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.139180686912825e-06, | |
| "loss": 1.5359, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.127627699056345e-06, | |
| "loss": 1.6186, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.11609755507649e-06, | |
| "loss": 1.5763, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 1.550114631652832, | |
| "eval_runtime": 221.6795, | |
| "eval_samples_per_second": 11.665, | |
| "eval_steps_per_second": 0.731, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.1045903466720915e-06, | |
| "loss": 1.5873, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.093106165359574e-06, | |
| "loss": 1.512, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.0816451024722344e-06, | |
| "loss": 1.5757, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.0702072491595023e-06, | |
| "loss": 1.6093, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.0587926963862287e-06, | |
| "loss": 1.628, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.0474015349319505e-06, | |
| "loss": 1.5597, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.03603385539018e-06, | |
| "loss": 1.628, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.0246897481676735e-06, | |
| "loss": 1.6856, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.013369303483719e-06, | |
| "loss": 1.5875, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 2.0020726113694204e-06, | |
| "loss": 1.7112, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 1.5496630668640137, | |
| "eval_runtime": 221.4899, | |
| "eval_samples_per_second": 11.675, | |
| "eval_steps_per_second": 0.731, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.990799761666975e-06, | |
| "loss": 1.6253, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.97955084402896e-06, | |
| "loss": 1.6424, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.9683259479176294e-06, | |
| "loss": 1.6307, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.9571251626041847e-06, | |
| "loss": 1.5608, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.945948577168086e-06, | |
| "loss": 1.5342, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.9347962804963238e-06, | |
| "loss": 1.6104, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.923668361282723e-06, | |
| "loss": 1.6282, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.9125649080272383e-06, | |
| "loss": 1.5276, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.9014860090352477e-06, | |
| "loss": 1.5614, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.8904317524168458e-06, | |
| "loss": 1.6533, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 1.5492993593215942, | |
| "eval_runtime": 221.6236, | |
| "eval_samples_per_second": 11.668, | |
| "eval_steps_per_second": 0.731, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.8794022260861483e-06, | |
| "loss": 1.5863, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.8683975177605968e-06, | |
| "loss": 1.7112, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.8574177149602496e-06, | |
| "loss": 1.601, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.8464629050070941e-06, | |
| "loss": 1.5975, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.835533175024355e-06, | |
| "loss": 1.623, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.8246286119357903e-06, | |
| "loss": 1.5591, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.8137493024650094e-06, | |
| "loss": 1.6076, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.802895333134783e-06, | |
| "loss": 1.5775, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.792066790266348e-06, | |
| "loss": 1.608, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.7812637599787298e-06, | |
| "loss": 1.6008, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_loss": 1.5489221811294556, | |
| "eval_runtime": 221.4324, | |
| "eval_samples_per_second": 11.679, | |
| "eval_steps_per_second": 0.732, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.7704863281880496e-06, | |
| "loss": 1.6018, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.759734580606845e-06, | |
| "loss": 1.6342, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.749008602743391e-06, | |
| "loss": 1.6145, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.7383084799010164e-06, | |
| "loss": 1.6211, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.7276342971774225e-06, | |
| "loss": 1.6228, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.7169861394640108e-06, | |
| "loss": 1.553, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.7063640914452113e-06, | |
| "loss": 1.5691, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.6957682375977986e-06, | |
| "loss": 1.5527, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.6851986621902267e-06, | |
| "loss": 1.5086, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.6746554492819638e-06, | |
| "loss": 1.5731, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 1.5485070943832397, | |
| "eval_runtime": 221.5833, | |
| "eval_samples_per_second": 11.671, | |
| "eval_steps_per_second": 0.731, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.6641386827228107e-06, | |
| "loss": 1.5955, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.653648446152248e-06, | |
| "loss": 1.537, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.6431848229987586e-06, | |
| "loss": 1.5893, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.6327478964791705e-06, | |
| "loss": 1.543, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.6223377495980003e-06, | |
| "loss": 1.7022, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.61195446514678e-06, | |
| "loss": 1.563, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.601598125703407e-06, | |
| "loss": 1.4853, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.5912688136314886e-06, | |
| "loss": 1.5955, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.5809666110796856e-06, | |
| "loss": 1.5711, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.570691599981053e-06, | |
| "loss": 1.4975, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 1.5480471849441528, | |
| "eval_runtime": 221.4835, | |
| "eval_samples_per_second": 11.676, | |
| "eval_steps_per_second": 0.731, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.5604438620523932e-06, | |
| "loss": 1.6568, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.550223478793612e-06, | |
| "loss": 1.6204, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.5400305314870596e-06, | |
| "loss": 1.5778, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.5298651011968868e-06, | |
| "loss": 1.5217, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.5197272687684106e-06, | |
| "loss": 1.6217, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.5096171148274546e-06, | |
| "loss": 1.6251, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.4995347197797227e-06, | |
| "loss": 1.6151, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.4894801638101502e-06, | |
| "loss": 1.6027, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.4794535268822674e-06, | |
| "loss": 1.6239, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.469454888737571e-06, | |
| "loss": 1.6158, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 1.5477726459503174, | |
| "eval_runtime": 221.5786, | |
| "eval_samples_per_second": 11.671, | |
| "eval_steps_per_second": 0.731, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.4594843288948773e-06, | |
| "loss": 1.5614, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.449541926649705e-06, | |
| "loss": 1.5896, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.4396277610736287e-06, | |
| "loss": 1.5643, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.4297419110136628e-06, | |
| "loss": 1.5279, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.419884455091628e-06, | |
| "loss": 1.5952, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.4100554717035242e-06, | |
| "loss": 1.644, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.4002550390189162e-06, | |
| "loss": 1.6332, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.3904832349803011e-06, | |
| "loss": 1.5595, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.380740137302497e-06, | |
| "loss": 1.6731, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.3710258234720191e-06, | |
| "loss": 1.6063, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 1.5473620891571045, | |
| "eval_runtime": 221.5086, | |
| "eval_samples_per_second": 11.674, | |
| "eval_steps_per_second": 0.731, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.361340370746464e-06, | |
| "loss": 1.6298, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.3516838561539019e-06, | |
| "loss": 1.6664, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.342056356492255e-06, | |
| "loss": 1.5638, | |
| "step": 883 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.332457948328691e-06, | |
| "loss": 1.6128, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.3228887079990155e-06, | |
| "loss": 1.6247, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.3133487116070643e-06, | |
| "loss": 1.5627, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.3038380350240948e-06, | |
| "loss": 1.6161, | |
| "step": 887 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.2943567538881841e-06, | |
| "loss": 1.6489, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.2849049436036325e-06, | |
| "loss": 1.5597, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.2754826793403563e-06, | |
| "loss": 1.628, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 1.5470210313796997, | |
| "eval_runtime": 221.6295, | |
| "eval_samples_per_second": 11.668, | |
| "eval_steps_per_second": 0.731, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.2660900360332927e-06, | |
| "loss": 1.6245, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.256727088381809e-06, | |
| "loss": 1.6468, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.2473939108490974e-06, | |
| "loss": 1.6272, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.238090577661596e-06, | |
| "loss": 1.6395, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.2288171628083883e-06, | |
| "loss": 1.5804, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.2195737400406165e-06, | |
| "loss": 1.6033, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.210360382870902e-06, | |
| "loss": 1.6096, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.201177164572752e-06, | |
| "loss": 1.5839, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.192024158179979e-06, | |
| "loss": 1.5953, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.1829014364861252e-06, | |
| "loss": 1.6177, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 1.546774983406067, | |
| "eval_runtime": 221.4788, | |
| "eval_samples_per_second": 11.676, | |
| "eval_steps_per_second": 0.731, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.1738090720438782e-06, | |
| "loss": 1.5881, | |
| "step": 901 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.1647471371644943e-06, | |
| "loss": 1.555, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.155715703917224e-06, | |
| "loss": 1.5393, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.1467148441287423e-06, | |
| "loss": 1.5533, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.1377446293825717e-06, | |
| "loss": 1.603, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.1288051310185182e-06, | |
| "loss": 1.5723, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.1198964201320994e-06, | |
| "loss": 1.6016, | |
| "step": 907 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.1110185675739804e-06, | |
| "loss": 1.577, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.1021716439494157e-06, | |
| "loss": 1.667, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.093355719617678e-06, | |
| "loss": 1.5646, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 1.546728491783142, | |
| "eval_runtime": 221.5999, | |
| "eval_samples_per_second": 11.67, | |
| "eval_steps_per_second": 0.731, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.0845708646915054e-06, | |
| "loss": 1.6052, | |
| "step": 911 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.0758171490365444e-06, | |
| "loss": 1.6043, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.0670946422707883e-06, | |
| "loss": 1.587, | |
| "step": 913 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.058403413764028e-06, | |
| "loss": 1.6036, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.0497435326373023e-06, | |
| "loss": 1.4276, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.0411150677623438e-06, | |
| "loss": 1.5751, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.0325180877610313e-06, | |
| "loss": 1.5523, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.023952661004845e-06, | |
| "loss": 1.6882, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.0154188556143286e-06, | |
| "loss": 1.5225, | |
| "step": 919 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.006916739458535e-06, | |
| "loss": 1.5272, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 1.5465571880340576, | |
| "eval_runtime": 221.6882, | |
| "eval_samples_per_second": 11.665, | |
| "eval_steps_per_second": 0.731, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.984463801544992e-07, | |
| "loss": 1.6817, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.900078450666929e-07, | |
| "loss": 1.5175, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.81601201306489e-07, | |
| "loss": 1.6615, | |
| "step": 923 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.732265157316344e-07, | |
| "loss": 1.6376, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.648838549457101e-07, | |
| "loss": 1.5621, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.56573285297605e-07, | |
| "loss": 1.7235, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.482948728809909e-07, | |
| "loss": 1.6235, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.400486835337913e-07, | |
| "loss": 1.68, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.318347828376639e-07, | |
| "loss": 1.6075, | |
| "step": 929 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.236532361174727e-07, | |
| "loss": 1.5402, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 1.5463948249816895, | |
| "eval_runtime": 221.5101, | |
| "eval_samples_per_second": 11.674, | |
| "eval_steps_per_second": 0.731, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 9.15504108440774e-07, | |
| "loss": 1.5344, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 9.073874646172958e-07, | |
| "loss": 1.6023, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 8.993033691984215e-07, | |
| "loss": 1.6561, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 8.912518864766817e-07, | |
| "loss": 1.5915, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.832330804852351e-07, | |
| "loss": 1.5965, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.752470149973686e-07, | |
| "loss": 1.5433, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.672937535259812e-07, | |
| "loss": 1.6243, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.593733593230813e-07, | |
| "loss": 1.5851, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 8.51485895379291e-07, | |
| "loss": 1.5311, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 8.43631424423334e-07, | |
| "loss": 1.5815, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 1.5460950136184692, | |
| "eval_runtime": 221.552, | |
| "eval_samples_per_second": 11.672, | |
| "eval_steps_per_second": 0.731, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 8.358100089215426e-07, | |
| "loss": 1.6118, | |
| "step": 941 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 8.280217110773625e-07, | |
| "loss": 1.6851, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 8.202665928308551e-07, | |
| "loss": 1.5943, | |
| "step": 943 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 8.125447158582045e-07, | |
| "loss": 1.524, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 8.048561415712269e-07, | |
| "loss": 1.6237, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.972009311168883e-07, | |
| "loss": 1.5489, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.895791453768076e-07, | |
| "loss": 1.5575, | |
| "step": 947 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.819908449667824e-07, | |
| "loss": 1.6436, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.744360902363002e-07, | |
| "loss": 1.6002, | |
| "step": 949 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.669149412680604e-07, | |
| "loss": 1.4857, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 1.545936107635498, | |
| "eval_runtime": 221.5545, | |
| "eval_samples_per_second": 11.672, | |
| "eval_steps_per_second": 0.731, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.594274578775007e-07, | |
| "loss": 1.6765, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.519736996123139e-07, | |
| "loss": 1.5792, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.445537257519775e-07, | |
| "loss": 1.677, | |
| "step": 953 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.371675953072871e-07, | |
| "loss": 1.5159, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.298153670198799e-07, | |
| "loss": 1.6549, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.224970993617685e-07, | |
| "loss": 1.619, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.152128505348821e-07, | |
| "loss": 1.6101, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.079626784705978e-07, | |
| "loss": 1.5972, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.007466408292801e-07, | |
| "loss": 1.5516, | |
| "step": 959 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.935647949998231e-07, | |
| "loss": 1.5923, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 1.5458210706710815, | |
| "eval_runtime": 221.6403, | |
| "eval_samples_per_second": 11.668, | |
| "eval_steps_per_second": 0.731, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.864171980991985e-07, | |
| "loss": 1.5649, | |
| "step": 961 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 6.793039069719925e-07, | |
| "loss": 1.6615, | |
| "step": 962 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 6.722249781899631e-07, | |
| "loss": 1.5616, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 6.651804680515828e-07, | |
| "loss": 1.5953, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 6.581704325815941e-07, | |
| "loss": 1.631, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 6.511949275305657e-07, | |
| "loss": 1.5349, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 6.442540083744453e-07, | |
| "loss": 1.5914, | |
| "step": 967 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 6.37347730314119e-07, | |
| "loss": 1.5806, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 6.304761482749777e-07, | |
| "loss": 1.6937, | |
| "step": 969 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 6.23639316906472e-07, | |
| "loss": 1.6167, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.5456454753875732, | |
| "eval_runtime": 221.6009, | |
| "eval_samples_per_second": 11.67, | |
| "eval_steps_per_second": 0.731, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 6.168372905816822e-07, | |
| "loss": 1.5585, | |
| "step": 971 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 6.100701233968876e-07, | |
| "loss": 1.6041, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 6.033378691711333e-07, | |
| "loss": 1.6218, | |
| "step": 973 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 5.966405814457999e-07, | |
| "loss": 1.619, | |
| "step": 974 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 5.899783134841846e-07, | |
| "loss": 1.48, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 5.833511182710716e-07, | |
| "loss": 1.6509, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.76759048512312e-07, | |
| "loss": 1.5868, | |
| "step": 977 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.702021566344079e-07, | |
| "loss": 1.5942, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.636804947840907e-07, | |
| "loss": 1.6148, | |
| "step": 979 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.571941148279081e-07, | |
| "loss": 1.7214, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 1.5455540418624878, | |
| "eval_runtime": 221.5314, | |
| "eval_samples_per_second": 11.673, | |
| "eval_steps_per_second": 0.731, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5.507430683518161e-07, | |
| "loss": 1.5196, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5.443274066607607e-07, | |
| "loss": 1.5658, | |
| "step": 982 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5.379471807782743e-07, | |
| "loss": 1.6647, | |
| "step": 983 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5.316024414460729e-07, | |
| "loss": 1.6552, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 5.252932391236443e-07, | |
| "loss": 1.6959, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 5.19019623987857e-07, | |
| "loss": 1.6183, | |
| "step": 986 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 5.127816459325508e-07, | |
| "loss": 1.5426, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 5.065793545681491e-07, | |
| "loss": 1.4803, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 5.00412799221257e-07, | |
| "loss": 1.663, | |
| "step": 989 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.942820289342759e-07, | |
| "loss": 1.5467, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 1.545507788658142, | |
| "eval_runtime": 221.6193, | |
| "eval_samples_per_second": 11.669, | |
| "eval_steps_per_second": 0.731, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.881870924650062e-07, | |
| "loss": 1.5791, | |
| "step": 991 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.821280382862647e-07, | |
| "loss": 1.5733, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.76104914585499e-07, | |
| "loss": 1.6028, | |
| "step": 993 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.70117769264401e-07, | |
| "loss": 1.5632, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.641666499385278e-07, | |
| "loss": 1.6126, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.582516039369245e-07, | |
| "loss": 1.5865, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.523726783017457e-07, | |
| "loss": 1.676, | |
| "step": 997 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.4652991978787975e-07, | |
| "loss": 1.4612, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.407233748625839e-07, | |
| "loss": 1.6977, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 4.3495308970510463e-07, | |
| "loss": 1.6455, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_loss": 1.5453382730484009, | |
| "eval_runtime": 221.6265, | |
| "eval_samples_per_second": 11.668, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 4.2921911020631926e-07, | |
| "loss": 1.6091, | |
| "step": 1001 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 4.235214819683681e-07, | |
| "loss": 1.644, | |
| "step": 1002 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 4.1786025030428776e-07, | |
| "loss": 1.5587, | |
| "step": 1003 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 4.1223546023765604e-07, | |
| "loss": 1.61, | |
| "step": 1004 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 4.0664715650223343e-07, | |
| "loss": 1.583, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 4.010953835416037e-07, | |
| "loss": 1.5307, | |
| "step": 1006 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.9558018550882204e-07, | |
| "loss": 1.5984, | |
| "step": 1007 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.901016062660673e-07, | |
| "loss": 1.6404, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.846596893842891e-07, | |
| "loss": 1.5449, | |
| "step": 1009 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.792544781428609e-07, | |
| "loss": 1.6137, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 1.5452983379364014, | |
| "eval_runtime": 221.4626, | |
| "eval_samples_per_second": 11.677, | |
| "eval_steps_per_second": 0.732, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.7388601552924066e-07, | |
| "loss": 1.5802, | |
| "step": 1011 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.6855434423862356e-07, | |
| "loss": 1.5109, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.6325950667360443e-07, | |
| "loss": 1.5823, | |
| "step": 1013 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.5800154494384176e-07, | |
| "loss": 1.5131, | |
| "step": 1014 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.5278050086572313e-07, | |
| "loss": 1.6175, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.4759641596202766e-07, | |
| "loss": 1.6387, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.4244933146160395e-07, | |
| "loss": 1.6567, | |
| "step": 1017 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.3733928829903396e-07, | |
| "loss": 1.5627, | |
| "step": 1018 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.322663271143112e-07, | |
| "loss": 1.7035, | |
| "step": 1019 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.2723048825252177e-07, | |
| "loss": 1.6104, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_loss": 1.5452524423599243, | |
| "eval_runtime": 221.6335, | |
| "eval_samples_per_second": 11.668, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.222318117635143e-07, | |
| "loss": 1.5946, | |
| "step": 1021 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.172703374015884e-07, | |
| "loss": 1.6396, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.12346104625178e-07, | |
| "loss": 1.5768, | |
| "step": 1023 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.0745915259653314e-07, | |
| "loss": 1.6198, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.026095201814122e-07, | |
| "loss": 1.4602, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 2.9779724594877377e-07, | |
| "loss": 1.6006, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.9302236817046636e-07, | |
| "loss": 1.6586, | |
| "step": 1027 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.8828492482092576e-07, | |
| "loss": 1.6442, | |
| "step": 1028 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.8358495357687366e-07, | |
| "loss": 1.4891, | |
| "step": 1029 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.78922491817018e-07, | |
| "loss": 1.6756, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 1.545109748840332, | |
| "eval_runtime": 221.6902, | |
| "eval_samples_per_second": 11.665, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.7429757662175316e-07, | |
| "loss": 1.6241, | |
| "step": 1031 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.6971024477287e-07, | |
| "loss": 1.5359, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.651605327532569e-07, | |
| "loss": 1.5156, | |
| "step": 1033 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.60648476746615e-07, | |
| "loss": 1.5417, | |
| "step": 1034 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.561741126371692e-07, | |
| "loss": 1.5033, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.5173747600937994e-07, | |
| "loss": 1.58, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.4733860214766315e-07, | |
| "loss": 1.5353, | |
| "step": 1037 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.429775260361106e-07, | |
| "loss": 1.5453, | |
| "step": 1038 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.3865428235820775e-07, | |
| "loss": 1.6029, | |
| "step": 1039 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.3436890549655922e-07, | |
| "loss": 1.5818, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 1.5450130701065063, | |
| "eval_runtime": 221.5386, | |
| "eval_samples_per_second": 11.673, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.301214295326193e-07, | |
| "loss": 1.5887, | |
| "step": 1041 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.2591188824641508e-07, | |
| "loss": 1.6142, | |
| "step": 1042 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.217403151162817e-07, | |
| "loss": 1.5788, | |
| "step": 1043 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.176067433185952e-07, | |
| "loss": 1.6359, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.1351120572750737e-07, | |
| "loss": 1.5598, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.0945373491468468e-07, | |
| "loss": 1.5478, | |
| "step": 1046 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.0543436314905242e-07, | |
| "loss": 1.6472, | |
| "step": 1047 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.0145312239653325e-07, | |
| "loss": 1.5053, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 1.975100443197958e-07, | |
| "loss": 1.6325, | |
| "step": 1049 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.9360516027800258e-07, | |
| "loss": 1.5829, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "eval_loss": 1.5450440645217896, | |
| "eval_runtime": 221.5885, | |
| "eval_samples_per_second": 11.67, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.8973850132655957e-07, | |
| "loss": 1.5113, | |
| "step": 1051 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.8591009821687044e-07, | |
| "loss": 1.6341, | |
| "step": 1052 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.8211998139609222e-07, | |
| "loss": 1.7143, | |
| "step": 1053 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.78368181006891e-07, | |
| "loss": 1.5249, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.7465472688720397e-07, | |
| "loss": 1.6237, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.7097964857000326e-07, | |
| "loss": 1.6128, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.6734297528305687e-07, | |
| "loss": 1.5549, | |
| "step": 1057 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.6374473594870155e-07, | |
| "loss": 1.5354, | |
| "step": 1058 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.6018495918360965e-07, | |
| "loss": 1.6438, | |
| "step": 1059 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.5666367329856046e-07, | |
| "loss": 1.5753, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 1.5450438261032104, | |
| "eval_runtime": 221.7053, | |
| "eval_samples_per_second": 11.664, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.5318090629821757e-07, | |
| "loss": 1.5775, | |
| "step": 1061 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.4973668588090572e-07, | |
| "loss": 1.5399, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.4633103943839045e-07, | |
| "loss": 1.6173, | |
| "step": 1063 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.429639940556571e-07, | |
| "loss": 1.6818, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.396355765107016e-07, | |
| "loss": 1.5952, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.363458132743123e-07, | |
| "loss": 1.6716, | |
| "step": 1066 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.3309473050986067e-07, | |
| "loss": 1.7006, | |
| "step": 1067 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.298823540730948e-07, | |
| "loss": 1.6409, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.2670870951193293e-07, | |
| "loss": 1.4846, | |
| "step": 1069 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.2357382206625802e-07, | |
| "loss": 1.6484, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 1.5450248718261719, | |
| "eval_runtime": 221.5954, | |
| "eval_samples_per_second": 11.67, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.2047771666772124e-07, | |
| "loss": 1.5518, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.1742041793954162e-07, | |
| "loss": 1.5571, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.1440195019630784e-07, | |
| "loss": 1.6202, | |
| "step": 1073 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.114223374437895e-07, | |
| "loss": 1.6521, | |
| "step": 1074 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.0848160337874225e-07, | |
| "loss": 1.596, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.0557977138872133e-07, | |
| "loss": 1.5768, | |
| "step": 1076 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.0271686455189556e-07, | |
| "loss": 1.5506, | |
| "step": 1077 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 9.989290563686305e-08, | |
| "loss": 1.6101, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 9.710791710247025e-08, | |
| "loss": 1.5509, | |
| "step": 1079 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 9.436192109763376e-08, | |
| "loss": 1.6765, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_loss": 1.5449930429458618, | |
| "eval_runtime": 221.5701, | |
| "eval_samples_per_second": 11.671, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 9.165493946116432e-08, | |
| "loss": 1.5969, | |
| "step": 1081 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 8.898699372159147e-08, | |
| "loss": 1.4659, | |
| "step": 1082 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 8.635810509699583e-08, | |
| "loss": 1.5853, | |
| "step": 1083 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 8.376829449483537e-08, | |
| "loss": 1.5234, | |
| "step": 1084 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 8.121758251178391e-08, | |
| "loss": 1.6246, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 7.870598943356622e-08, | |
| "loss": 1.5908, | |
| "step": 1086 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 7.62335352347926e-08, | |
| "loss": 1.5624, | |
| "step": 1087 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 7.380023957880511e-08, | |
| "loss": 1.6097, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 7.140612181752049e-08, | |
| "loss": 1.53, | |
| "step": 1089 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 6.905120099127249e-08, | |
| "loss": 1.623, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_loss": 1.5449092388153076, | |
| "eval_runtime": 221.6089, | |
| "eval_samples_per_second": 11.669, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 6.673549582866368e-08, | |
| "loss": 1.5162, | |
| "step": 1091 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 6.44590247464183e-08, | |
| "loss": 1.6031, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 6.222180584923021e-08, | |
| "loss": 1.6486, | |
| "step": 1093 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 6.002385692962242e-08, | |
| "loss": 1.4915, | |
| "step": 1094 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 5.7865195467807775e-08, | |
| "loss": 1.4412, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 5.5745838631544036e-08, | |
| "loss": 1.5536, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 5.3665803276002906e-08, | |
| "loss": 1.5892, | |
| "step": 1097 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 5.162510594363235e-08, | |
| "loss": 1.6356, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 4.9623762864027815e-08, | |
| "loss": 1.6506, | |
| "step": 1099 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 4.7661789953799553e-08, | |
| "loss": 1.6901, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_loss": 1.5449464321136475, | |
| "eval_runtime": 221.5857, | |
| "eval_samples_per_second": 11.67, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 4.573920281645161e-08, | |
| "loss": 1.6219, | |
| "step": 1101 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 4.385601674225082e-08, | |
| "loss": 1.6609, | |
| "step": 1102 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 4.2012246708110774e-08, | |
| "loss": 1.6263, | |
| "step": 1103 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.020790737746971e-08, | |
| "loss": 1.5852, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 3.844301310017673e-08, | |
| "loss": 1.5669, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 3.6717577912372406e-08, | |
| "loss": 1.4975, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 3.503161553638445e-08, | |
| "loss": 1.5413, | |
| "step": 1107 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.338513938061172e-08, | |
| "loss": 1.5464, | |
| "step": 1108 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.177816253942145e-08, | |
| "loss": 1.5708, | |
| "step": 1109 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.021069779304498e-08, | |
| "loss": 1.6601, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_loss": 1.5448739528656006, | |
| "eval_runtime": 221.6432, | |
| "eval_samples_per_second": 11.667, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 2.868275760747441e-08, | |
| "loss": 1.5739, | |
| "step": 1111 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.7194354134363886e-08, | |
| "loss": 1.5899, | |
| "step": 1112 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.5745499210936274e-08, | |
| "loss": 1.5463, | |
| "step": 1113 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.4336204359882153e-08, | |
| "loss": 1.5981, | |
| "step": 1114 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.2966480789275438e-08, | |
| "loss": 1.5515, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2.1636339392479553e-08, | |
| "loss": 1.6135, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2.0345790748062532e-08, | |
| "loss": 1.5344, | |
| "step": 1117 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.9094845119712603e-08, | |
| "loss": 1.6426, | |
| "step": 1118 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.788351245615716e-08, | |
| "loss": 1.5534, | |
| "step": 1119 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.6711802391081723e-08, | |
| "loss": 1.6763, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 1.5449295043945312, | |
| "eval_runtime": 221.4937, | |
| "eval_samples_per_second": 11.675, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.557972424305665e-08, | |
| "loss": 1.6222, | |
| "step": 1121 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.4487287015458872e-08, | |
| "loss": 1.5905, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.3434499396404176e-08, | |
| "loss": 1.6102, | |
| "step": 1123 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.2421369758675027e-08, | |
| "loss": 1.6438, | |
| "step": 1124 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.1447906159656741e-08, | |
| "loss": 1.5647, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.0514116341271419e-08, | |
| "loss": 1.6007, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 9.620007729916337e-09, | |
| "loss": 1.6131, | |
| "step": 1127 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 8.765587436406765e-09, | |
| "loss": 1.6681, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 7.95086225591657e-09, | |
| "loss": 1.6304, | |
| "step": 1129 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 7.175838667927149e-09, | |
| "loss": 1.6203, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 1.5448760986328125, | |
| "eval_runtime": 221.5511, | |
| "eval_samples_per_second": 11.672, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 6.440522836174135e-09, | |
| "loss": 1.5979, | |
| "step": 1131 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.744920608598547e-09, | |
| "loss": 1.4959, | |
| "step": 1132 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.089037517300721e-09, | |
| "loss": 1.553, | |
| "step": 1133 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 4.472878778495892e-09, | |
| "loss": 1.5942, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.896449292473125e-09, | |
| "loss": 1.6051, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.359753643555341e-09, | |
| "loss": 1.6249, | |
| "step": 1136 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 2.862796100065457e-09, | |
| "loss": 1.6316, | |
| "step": 1137 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 2.4055806142880835e-09, | |
| "loss": 1.6181, | |
| "step": 1138 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.988110822443434e-09, | |
| "loss": 1.5719, | |
| "step": 1139 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.6103900446534648e-09, | |
| "loss": 1.5113, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_loss": 1.5448263883590698, | |
| "eval_runtime": 221.6166, | |
| "eval_samples_per_second": 11.669, | |
| "eval_steps_per_second": 0.731, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.2724212849180019e-09, | |
| "loss": 1.6375, | |
| "step": 1141 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 9.742072310908735e-10, | |
| "loss": 1.6044, | |
| "step": 1142 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 7.157502548588158e-10, | |
| "loss": 1.5811, | |
| "step": 1143 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 4.97052411720933e-10, | |
| "loss": 1.587, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 3.181154409725995e-10, | |
| "loss": 1.702, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.7894076569435759e-10, | |
| "loss": 1.5643, | |
| "step": 1146 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 7.952949273748456e-11, | |
| "loss": 1.4459, | |
| "step": 1147 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.9882412715110932e-11, | |
| "loss": 1.4922, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.0, | |
| "loss": 1.5717, | |
| "step": 1149 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "step": 1149, | |
| "total_flos": 2.7036241629701734e+18, | |
| "train_loss": 1.6580357963464072, | |
| "train_runtime": 61956.043, | |
| "train_samples_per_second": 2.379, | |
| "train_steps_per_second": 0.019 | |
| } | |
| ], | |
| "max_steps": 1149, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.7036241629701734e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |