| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2247, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04450378282153983, | |
| "grad_norm": 0.13366538286209106, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.4614, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08900756564307966, | |
| "grad_norm": 0.40120357275009155, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.4038, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13351134846461948, | |
| "grad_norm": 0.207975834608078, | |
| "learning_rate": 6e-06, | |
| "loss": 2.4, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1780151312861593, | |
| "grad_norm": 0.2991727888584137, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.3774, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.22251891410769917, | |
| "grad_norm": 0.3771696984767914, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3316, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.26702269692923897, | |
| "grad_norm": 0.5076782703399658, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.3049, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3115264797507788, | |
| "grad_norm": 0.46594780683517456, | |
| "learning_rate": 1.4e-05, | |
| "loss": 2.2432, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.3560302625723186, | |
| "grad_norm": 0.5553820729255676, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.2903, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.40053404539385845, | |
| "grad_norm": 0.5826830863952637, | |
| "learning_rate": 1.8e-05, | |
| "loss": 2.2219, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.44503782821539833, | |
| "grad_norm": 0.6430906057357788, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2133, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.48954161103693816, | |
| "grad_norm": 0.5223941206932068, | |
| "learning_rate": 1.9684326170007365e-05, | |
| "loss": 2.2328, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.5340453938584779, | |
| "grad_norm": 0.6351125836372375, | |
| "learning_rate": 1.8757234673417892e-05, | |
| "loss": 2.181, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.5785491766800178, | |
| "grad_norm": 0.7824538350105286, | |
| "learning_rate": 1.7277257214927987e-05, | |
| "loss": 2.1317, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6230529595015576, | |
| "grad_norm": 0.8329874277114868, | |
| "learning_rate": 1.5337831825062507e-05, | |
| "loss": 2.1331, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.6675567423230975, | |
| "grad_norm": 0.7226102352142334, | |
| "learning_rate": 1.306140367198221e-05, | |
| "loss": 2.0982, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7120605251446372, | |
| "grad_norm": 0.758540689945221, | |
| "learning_rate": 1.0591694514444284e-05, | |
| "loss": 2.1411, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.7565643079661771, | |
| "grad_norm": 0.7841065526008606, | |
| "learning_rate": 8.084628862194305e-06, | |
| "loss": 2.1329, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.8010680907877169, | |
| "grad_norm": 0.7534396648406982, | |
| "learning_rate": 5.698489718530022e-06, | |
| "loss": 2.1179, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.8455718736092568, | |
| "grad_norm": 0.809190034866333, | |
| "learning_rate": 3.583925419926607e-06, | |
| "loss": 2.132, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.8900756564307967, | |
| "grad_norm": 0.8342956304550171, | |
| "learning_rate": 1.874438488565231e-06, | |
| "loss": 2.0948, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9345794392523364, | |
| "grad_norm": 0.8505709171295166, | |
| "learning_rate": 6.779569818349296e-07, | |
| "loss": 2.1061, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.9790832220738763, | |
| "grad_norm": 0.9227008819580078, | |
| "learning_rate": 7.00204796846915e-08, | |
| "loss": 2.084, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 2247, | |
| "total_flos": 4.1045168553984e+16, | |
| "train_loss": 2.2167040354207086, | |
| "train_runtime": 618.2687, | |
| "train_samples_per_second": 7.269, | |
| "train_steps_per_second": 3.634 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2247, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.1045168553984e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |