{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0681362725450902, "eval_steps": 100.0, "global_step": 800, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.033400133600534405, "grad_norm": 34.83279037475586, "learning_rate": 1.978638184245661e-05, "loss": 5.0239, "step": 25 }, { "epoch": 0.06680026720106881, "grad_norm": 21.53448486328125, "learning_rate": 1.956386292834891e-05, "loss": 4.5061, "step": 50 }, { "epoch": 0.10020040080160321, "grad_norm": 23.527015686035156, "learning_rate": 1.9341344014241213e-05, "loss": 4.3217, "step": 75 }, { "epoch": 0.13360053440213762, "grad_norm": 15.6005859375, "learning_rate": 1.9118825100133513e-05, "loss": 4.0712, "step": 100 }, { "epoch": 0.16700066800267202, "grad_norm": 19.26547622680664, "learning_rate": 1.8896306186025813e-05, "loss": 4.0589, "step": 125 }, { "epoch": 0.20040080160320642, "grad_norm": 23.404224395751953, "learning_rate": 1.8673787271918113e-05, "loss": 3.9447, "step": 150 }, { "epoch": 0.23380093520374082, "grad_norm": 19.686691284179688, "learning_rate": 1.8451268357810413e-05, "loss": 3.6344, "step": 175 }, { "epoch": 0.26720106880427524, "grad_norm": 20.32077407836914, "learning_rate": 1.8228749443702717e-05, "loss": 3.489, "step": 200 }, { "epoch": 0.30060120240480964, "grad_norm": 17.107595443725586, "learning_rate": 1.8006230529595017e-05, "loss": 3.4025, "step": 225 }, { "epoch": 0.33400133600534404, "grad_norm": 17.202909469604492, "learning_rate": 1.7783711615487317e-05, "loss": 3.1437, "step": 250 }, { "epoch": 0.36740146960587844, "grad_norm": 21.202510833740234, "learning_rate": 1.756119270137962e-05, "loss": 3.2257, "step": 275 }, { "epoch": 0.40080160320641284, "grad_norm": 19.31769371032715, "learning_rate": 1.733867378727192e-05, "loss": 3.1046, "step": 300 }, { "epoch": 0.43420173680694724, "grad_norm": 21.412029266357422, "learning_rate": 1.711615487316422e-05, "loss": 3.2254, "step": 325 }, { "epoch": 0.46760187040748163, "grad_norm": 23.345766067504883, "learning_rate": 1.689363595905652e-05, "loss": 3.1176, "step": 350 }, { "epoch": 0.501002004008016, "grad_norm": 21.88970375061035, "learning_rate": 1.667111704494882e-05, "loss": 2.9884, "step": 375 }, { "epoch": 0.5344021376085505, "grad_norm": 21.60796356201172, "learning_rate": 1.6448598130841123e-05, "loss": 3.1272, "step": 400 }, { "epoch": 0.5678022712090849, "grad_norm": 17.43869972229004, "learning_rate": 1.6226079216733423e-05, "loss": 2.8604, "step": 425 }, { "epoch": 0.6012024048096193, "grad_norm": 19.90398597717285, "learning_rate": 1.6003560302625723e-05, "loss": 3.0515, "step": 450 }, { "epoch": 0.6346025384101537, "grad_norm": 25.174152374267578, "learning_rate": 1.5781041388518027e-05, "loss": 2.8242, "step": 475 }, { "epoch": 0.6680026720106881, "grad_norm": 23.089248657226562, "learning_rate": 1.5558522474410327e-05, "loss": 2.7323, "step": 500 }, { "epoch": 0.7014028056112225, "grad_norm": 31.02774429321289, "learning_rate": 1.5336003560302627e-05, "loss": 2.5633, "step": 525 }, { "epoch": 0.7348029392117569, "grad_norm": 22.90081024169922, "learning_rate": 1.5113484646194927e-05, "loss": 2.5597, "step": 550 }, { "epoch": 0.7682030728122913, "grad_norm": 18.37523078918457, "learning_rate": 1.4890965732087228e-05, "loss": 2.4584, "step": 575 }, { "epoch": 0.8016032064128257, "grad_norm": 19.337141036987305, "learning_rate": 1.466844681797953e-05, "loss": 2.5439, "step": 600 }, { "epoch": 0.8350033400133601, "grad_norm": 21.656770706176758, "learning_rate": 1.444592790387183e-05, "loss": 2.4629, "step": 625 }, { "epoch": 0.8684034736138945, "grad_norm": 19.98714256286621, "learning_rate": 1.4223408989764132e-05, "loss": 2.4676, "step": 650 }, { "epoch": 0.9018036072144289, "grad_norm": 29.199106216430664, "learning_rate": 1.4000890075656433e-05, "loss": 2.2897, "step": 675 }, { "epoch": 0.9352037408149633, "grad_norm": 23.988719940185547, "learning_rate": 1.3778371161548733e-05, "loss": 2.1067, "step": 700 }, { "epoch": 0.9686038744154977, "grad_norm": 18.715688705444336, "learning_rate": 1.3555852247441033e-05, "loss": 2.3692, "step": 725 }, { "epoch": 1.0013360053440215, "grad_norm": 21.375459671020508, "learning_rate": 1.3333333333333333e-05, "loss": 2.1564, "step": 750 }, { "epoch": 1.0347361389445557, "grad_norm": 9.197733879089355, "learning_rate": 1.3110814419225635e-05, "loss": 1.3881, "step": 775 }, { "epoch": 1.0681362725450902, "grad_norm": 14.479204177856445, "learning_rate": 1.2888295505117937e-05, "loss": 1.4377, "step": 800 } ], "logging_steps": 25, "max_steps": 2247, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2.6585066994883625e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }