| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3453038674033149, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9884898710865566e-05, | |
| "loss": 1.8029, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.976979742173112e-05, | |
| "loss": 1.7809, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.965469613259669e-05, | |
| "loss": 1.7211, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.953959484346225e-05, | |
| "loss": 1.6942, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.942449355432781e-05, | |
| "loss": 1.7155, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.930939226519337e-05, | |
| "loss": 1.6549, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.919429097605893e-05, | |
| "loss": 1.6162, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.9079189686924495e-05, | |
| "loss": 1.6446, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.896408839779006e-05, | |
| "loss": 1.6022, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.884898710865562e-05, | |
| "loss": 1.6405, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.873388581952118e-05, | |
| "loss": 1.5943, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.861878453038674e-05, | |
| "loss": 1.6267, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.8503683241252305e-05, | |
| "loss": 1.5846, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.838858195211787e-05, | |
| "loss": 1.63, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.8273480662983425e-05, | |
| "loss": 1.5956, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.815837937384899e-05, | |
| "loss": 1.6277, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.804327808471455e-05, | |
| "loss": 1.6073, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.7928176795580114e-05, | |
| "loss": 1.6069, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.781307550644568e-05, | |
| "loss": 1.5771, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.7697974217311234e-05, | |
| "loss": 1.5908, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.75828729281768e-05, | |
| "loss": 1.6272, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.746777163904236e-05, | |
| "loss": 1.5791, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.7352670349907924e-05, | |
| "loss": 1.6181, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.723756906077349e-05, | |
| "loss": 1.5601, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.7122467771639044e-05, | |
| "loss": 1.6027, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.700736648250461e-05, | |
| "loss": 1.5406, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.6892265193370164e-05, | |
| "loss": 1.5931, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.6777163904235734e-05, | |
| "loss": 1.5754, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.666206261510129e-05, | |
| "loss": 1.6021, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.6546961325966854e-05, | |
| "loss": 1.612, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.643186003683242e-05, | |
| "loss": 1.6186, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.6316758747697973e-05, | |
| "loss": 1.5881, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.6201657458563544e-05, | |
| "loss": 1.5798, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.60865561694291e-05, | |
| "loss": 1.6227, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.597145488029466e-05, | |
| "loss": 1.5912, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.585635359116022e-05, | |
| "loss": 1.5674, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.574125230202578e-05, | |
| "loss": 1.6119, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.5626151012891346e-05, | |
| "loss": 1.6162, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.551104972375691e-05, | |
| "loss": 1.6058, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.539594843462247e-05, | |
| "loss": 1.5731, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.528084714548803e-05, | |
| "loss": 1.5954, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.516574585635359e-05, | |
| "loss": 1.6355, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.505064456721915e-05, | |
| "loss": 1.6298, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.493554327808472e-05, | |
| "loss": 1.5923, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.4820441988950276e-05, | |
| "loss": 1.5714, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.470534069981584e-05, | |
| "loss": 1.6087, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.45902394106814e-05, | |
| "loss": 1.5758, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.447513812154696e-05, | |
| "loss": 1.5886, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.436003683241253e-05, | |
| "loss": 1.583, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.4244935543278086e-05, | |
| "loss": 1.5785, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 4344, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3.1601241096192e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |