| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.9809417040358746, | |
| "eval_steps": 500, | |
| "global_step": 712, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14013452914798205, | |
| "grad_norm": 14.509355545043945, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 7.1534, | |
| "num_input_tokens_seen": 318240, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2802690582959641, | |
| "grad_norm": 6.642310619354248, | |
| "learning_rate": 6.533333333333334e-06, | |
| "loss": 1.9472, | |
| "num_input_tokens_seen": 636760, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4204035874439462, | |
| "grad_norm": 3.3247640132904053, | |
| "learning_rate": 9.866666666666668e-06, | |
| "loss": 1.5046, | |
| "num_input_tokens_seen": 956520, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5605381165919282, | |
| "grad_norm": 2.3405237197875977, | |
| "learning_rate": 1.3200000000000002e-05, | |
| "loss": 1.3971, | |
| "num_input_tokens_seen": 1275920, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7006726457399103, | |
| "grad_norm": 3.028830051422119, | |
| "learning_rate": 1.6533333333333333e-05, | |
| "loss": 1.3768, | |
| "num_input_tokens_seen": 1595280, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8408071748878924, | |
| "grad_norm": 1.428653597831726, | |
| "learning_rate": 1.9866666666666667e-05, | |
| "loss": 1.3278, | |
| "num_input_tokens_seen": 1914720, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9809417040358744, | |
| "grad_norm": 1.9624038934707642, | |
| "learning_rate": 1.9910139651840497e-05, | |
| "loss": 1.2927, | |
| "num_input_tokens_seen": 2233680, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.1177130044843049, | |
| "grad_norm": 1.6478056907653809, | |
| "learning_rate": 1.962720313575358e-05, | |
| "loss": 1.2029, | |
| "num_input_tokens_seen": 2544928, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.257847533632287, | |
| "grad_norm": 2.1640427112579346, | |
| "learning_rate": 1.915655103523529e-05, | |
| "loss": 1.2199, | |
| "num_input_tokens_seen": 2864008, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.397982062780269, | |
| "grad_norm": 2.563964605331421, | |
| "learning_rate": 1.8507360338956896e-05, | |
| "loss": 1.2112, | |
| "num_input_tokens_seen": 3183248, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.5381165919282511, | |
| "grad_norm": 1.9103755950927734, | |
| "learning_rate": 1.7692289262315e-05, | |
| "loss": 1.221, | |
| "num_input_tokens_seen": 3502528, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.6782511210762332, | |
| "grad_norm": 2.564152240753174, | |
| "learning_rate": 1.6727230431791816e-05, | |
| "loss": 1.1758, | |
| "num_input_tokens_seen": 3821648, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.8183856502242153, | |
| "grad_norm": 1.57261061668396, | |
| "learning_rate": 1.563100100329731e-05, | |
| "loss": 1.1828, | |
| "num_input_tokens_seen": 4140008, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.9585201793721974, | |
| "grad_norm": 1.8220309019088745, | |
| "learning_rate": 1.442497575670668e-05, | |
| "loss": 1.1948, | |
| "num_input_tokens_seen": 4458448, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.0952914798206277, | |
| "grad_norm": 2.028656005859375, | |
| "learning_rate": 1.313267032068285e-05, | |
| "loss": 1.07, | |
| "num_input_tokens_seen": 4770136, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.2354260089686098, | |
| "grad_norm": 3.713899850845337, | |
| "learning_rate": 1.1779282654255685e-05, | |
| "loss": 1.0581, | |
| "num_input_tokens_seen": 5087896, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.375560538116592, | |
| "grad_norm": 2.000035285949707, | |
| "learning_rate": 1.0391201725558842e-05, | |
| "loss": 1.048, | |
| "num_input_tokens_seen": 5407296, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.515695067264574, | |
| "grad_norm": 1.5742937326431274, | |
| "learning_rate": 8.99549296772945e-06, | |
| "loss": 1.0218, | |
| "num_input_tokens_seen": 5726896, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.655829596412556, | |
| "grad_norm": 1.7964842319488525, | |
| "learning_rate": 7.619370544785608e-06, | |
| "loss": 1.0206, | |
| "num_input_tokens_seen": 6046856, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.795964125560538, | |
| "grad_norm": 1.5667575597763062, | |
| "learning_rate": 6.289666717481497e-06, | |
| "loss": 1.0277, | |
| "num_input_tokens_seen": 6366216, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.93609865470852, | |
| "grad_norm": 1.8910105228424072, | |
| "learning_rate": 5.032308655686011e-06, | |
| "loss": 1.0494, | |
| "num_input_tokens_seen": 6685296, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 3.0728699551569507, | |
| "grad_norm": 1.1843669414520264, | |
| "learning_rate": 3.8718128986350154e-06, | |
| "loss": 0.9487, | |
| "num_input_tokens_seen": 6996704, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.213004484304933, | |
| "grad_norm": 1.5657708644866943, | |
| "learning_rate": 2.8308073203011667e-06, | |
| "loss": 0.9103, | |
| "num_input_tokens_seen": 7316144, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 3.353139013452915, | |
| "grad_norm": 1.8331918716430664, | |
| "learning_rate": 1.929589920817806e-06, | |
| "loss": 0.9102, | |
| "num_input_tokens_seen": 7635704, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.493273542600897, | |
| "grad_norm": 1.651666283607483, | |
| "learning_rate": 1.1857330468424466e-06, | |
| "loss": 0.9034, | |
| "num_input_tokens_seen": 7955304, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 3.633408071748879, | |
| "grad_norm": 1.1031330823898315, | |
| "learning_rate": 6.137407579511212e-07, | |
| "loss": 0.8949, | |
| "num_input_tokens_seen": 8274744, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.773542600896861, | |
| "grad_norm": 3.233630895614624, | |
| "learning_rate": 2.2476601988947965e-07, | |
| "loss": 0.9073, | |
| "num_input_tokens_seen": 8594304, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 3.913677130044843, | |
| "grad_norm": 1.2947144508361816, | |
| "learning_rate": 2.639323897518975e-08, | |
| "loss": 0.8967, | |
| "num_input_tokens_seen": 8913944, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.9809417040358746, | |
| "num_input_tokens_seen": 9067184, | |
| "step": 712, | |
| "total_flos": 6.151178707859082e+17, | |
| "train_loss": 1.3522842801019046, | |
| "train_runtime": 6892.301, | |
| "train_samples_per_second": 2.588, | |
| "train_steps_per_second": 0.103 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 712, | |
| "num_input_tokens_seen": 9067184, | |
| "num_train_epochs": 4, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.151178707859082e+17, | |
| "train_batch_size": 5, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |