| { | |
| "best_metric": 0.9485365152359009, | |
| "best_model_checkpoint": "../models/opt-350m_CASUAL_LM/checkpoint-560", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 560, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 9.2714, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.999246866958692e-05, | |
| "loss": 6.7036, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.985864145839845e-05, | |
| "loss": 2.5969, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.955796687186394e-05, | |
| "loss": 1.3042, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.909145108993794e-05, | |
| "loss": 1.1977, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.846065526494017e-05, | |
| "loss": 1.0884, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.766769029730238e-05, | |
| "loss": 0.9545, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.67152097716334e-05, | |
| "loss": 0.9308, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.560640107674143e-05, | |
| "loss": 0.9087, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.434497473932942e-05, | |
| "loss": 0.7838, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.29351520070574e-05, | |
| "loss": 0.8388, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.138165072252401e-05, | |
| "loss": 0.7295, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 8.968966953543851e-05, | |
| "loss": 0.763, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 8.786487050581583e-05, | |
| "loss": 0.7981, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 8.591336015641148e-05, | |
| "loss": 0.7529, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.384166903780279e-05, | |
| "loss": 0.8178, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.165672987449962e-05, | |
| "loss": 0.6486, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.936585436521707e-05, | |
| "loss": 0.7822, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 7.697670871494562e-05, | |
| "loss": 0.7186, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 7.449728798069864e-05, | |
| "loss": 0.6336, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.193588931678653e-05, | |
| "loss": 0.6833, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.930108420915009e-05, | |
| "loss": 0.6611, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 6.66016897916682e-05, | |
| "loss": 0.7151, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.384673934042714e-05, | |
| "loss": 0.6919, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.104545204468986e-05, | |
| "loss": 0.657, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 5.820720215572375e-05, | |
| "loss": 0.689, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.534148761672786e-05, | |
| "loss": 0.7398, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.2457898278836015e-05, | |
| "loss": 0.7043, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.9598486423492432, | |
| "eval_runtime": 1398.0901, | |
| "eval_samples_per_second": 0.286, | |
| "eval_steps_per_second": 0.286, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.956608380955877e-05, | |
| "loss": 0.6537, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.667572140105533e-05, | |
| "loss": 0.6571, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.379648338629646e-05, | |
| "loss": 0.627, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.093800487148857e-05, | |
| "loss": 0.6365, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.8109851493073584e-05, | |
| "loss": 0.6047, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.5321487407203e-05, | |
| "loss": 0.6789, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.258224361880657e-05, | |
| "loss": 0.7017, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.990128675623909e-05, | |
| "loss": 0.697, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.728758839599868e-05, | |
| "loss": 0.6193, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.474989504016798e-05, | |
| "loss": 0.6457, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.229669884704626e-05, | |
| "loss": 0.5986, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.9936209212919914e-05, | |
| "loss": 0.6401, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.7676325300069825e-05, | |
| "loss": 0.6171, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.5524609602948665e-05, | |
| "loss": 0.6444, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.3488262640986039e-05, | |
| "loss": 0.5864, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.1574098862709992e-05, | |
| "loss": 0.6467, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.788523841819437e-06, | |
| "loss": 0.5964, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 8.137512841518574e-06, | |
| "loss": 0.7018, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 6.626590818846162e-06, | |
| "loss": 0.6565, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 5.26081393591294e-06, | |
| "loss": 0.6369, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 4.044752639918437e-06, | |
| "loss": 0.7028, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.9824763685681766e-06, | |
| "loss": 0.5869, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.0775399320732303e-06, | |
| "loss": 0.7181, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.3329716173036078e-06, | |
| "loss": 0.6652, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 7.512630539036502e-07, | |
| "loss": 0.6402, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 3.343608762817807e-07, | |
| "loss": 0.5711, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 8.366020937677354e-08, | |
| "loss": 0.63, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.6184, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.9485365152359009, | |
| "eval_runtime": 1437.3031, | |
| "eval_samples_per_second": 0.278, | |
| "eval_steps_per_second": 0.278, | |
| "step": 560 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 560, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 134526932090880.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |