| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.1642619311875695, | |
| "eval_steps": 500, | |
| "global_step": 19500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05549389567147614, | |
| "grad_norm": 5.1054205894470215, | |
| "learning_rate": 0.0009815020347761745, | |
| "loss": 2.823, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11098779134295228, | |
| "grad_norm": 5.702259540557861, | |
| "learning_rate": 0.0009630040695523493, | |
| "loss": 2.5297, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16648168701442842, | |
| "grad_norm": 2.288583278656006, | |
| "learning_rate": 0.0009445061043285239, | |
| "loss": 2.2922, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.22197558268590456, | |
| "grad_norm": 1.2640436887741089, | |
| "learning_rate": 0.0009260081391046985, | |
| "loss": 2.2693, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.27746947835738067, | |
| "grad_norm": 2.6587376594543457, | |
| "learning_rate": 0.0009075101738808731, | |
| "loss": 2.1495, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.33296337402885684, | |
| "grad_norm": 3.5381200313568115, | |
| "learning_rate": 0.0008890122086570478, | |
| "loss": 2.0572, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.38845726970033295, | |
| "grad_norm": 5.533036708831787, | |
| "learning_rate": 0.0008705142434332224, | |
| "loss": 2.0025, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.4439511653718091, | |
| "grad_norm": 5.4949541091918945, | |
| "learning_rate": 0.000852016278209397, | |
| "loss": 1.9598, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.49944506104328523, | |
| "grad_norm": 1.909883737564087, | |
| "learning_rate": 0.0008335183129855716, | |
| "loss": 1.9381, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.5549389567147613, | |
| "grad_norm": 5.691808223724365, | |
| "learning_rate": 0.0008150203477617462, | |
| "loss": 1.8509, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.6104328523862376, | |
| "grad_norm": 2.442469358444214, | |
| "learning_rate": 0.0007965223825379209, | |
| "loss": 1.7988, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.6659267480577137, | |
| "grad_norm": 2.9826149940490723, | |
| "learning_rate": 0.0007780244173140955, | |
| "loss": 1.7816, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.7214206437291898, | |
| "grad_norm": 2.3049557209014893, | |
| "learning_rate": 0.00075952645209027, | |
| "loss": 1.7736, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.7769145394006659, | |
| "grad_norm": 2.855045795440674, | |
| "learning_rate": 0.0007410284868664448, | |
| "loss": 1.7075, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.832408435072142, | |
| "grad_norm": 3.2882728576660156, | |
| "learning_rate": 0.0007225305216426194, | |
| "loss": 1.701, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.8879023307436182, | |
| "grad_norm": 2.1633858680725098, | |
| "learning_rate": 0.0007040325564187939, | |
| "loss": 1.6848, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.9433962264150944, | |
| "grad_norm": 2.723276138305664, | |
| "learning_rate": 0.0006855345911949685, | |
| "loss": 1.6152, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.9988901220865705, | |
| "grad_norm": 2.73237943649292, | |
| "learning_rate": 0.0006670366259711433, | |
| "loss": 1.5959, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.0543840177580466, | |
| "grad_norm": 2.634521007537842, | |
| "learning_rate": 0.0006485386607473178, | |
| "loss": 1.4009, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.1098779134295227, | |
| "grad_norm": 1.5136901140213013, | |
| "learning_rate": 0.0006300406955234924, | |
| "loss": 1.3877, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.1653718091009988, | |
| "grad_norm": 2.1514732837677, | |
| "learning_rate": 0.000611542730299667, | |
| "loss": 1.3724, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.220865704772475, | |
| "grad_norm": 2.6399548053741455, | |
| "learning_rate": 0.0005930447650758417, | |
| "loss": 1.335, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.2763596004439512, | |
| "grad_norm": 1.5254985094070435, | |
| "learning_rate": 0.0005745467998520163, | |
| "loss": 1.3886, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.3318534961154274, | |
| "grad_norm": 1.9089288711547852, | |
| "learning_rate": 0.0005560488346281908, | |
| "loss": 1.3439, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.3873473917869035, | |
| "grad_norm": 2.2264904975891113, | |
| "learning_rate": 0.0005375508694043655, | |
| "loss": 1.3081, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.4428412874583796, | |
| "grad_norm": 2.0363707542419434, | |
| "learning_rate": 0.0005190529041805402, | |
| "loss": 1.3539, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.4983351831298557, | |
| "grad_norm": 1.3880550861358643, | |
| "learning_rate": 0.0005005549389567147, | |
| "loss": 1.3054, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.5538290788013318, | |
| "grad_norm": 1.9909353256225586, | |
| "learning_rate": 0.00048205697373288937, | |
| "loss": 1.2664, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.609322974472808, | |
| "grad_norm": 1.8012514114379883, | |
| "learning_rate": 0.000463559008509064, | |
| "loss": 1.3344, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.6648168701442843, | |
| "grad_norm": 1.5090456008911133, | |
| "learning_rate": 0.00044506104328523863, | |
| "loss": 1.3274, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.7203107658157601, | |
| "grad_norm": 2.566316843032837, | |
| "learning_rate": 0.00042656307806141327, | |
| "loss": 1.2629, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.7758046614872365, | |
| "grad_norm": 1.7907458543777466, | |
| "learning_rate": 0.00040806511283758784, | |
| "loss": 1.3041, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.8312985571587126, | |
| "grad_norm": 1.4483698606491089, | |
| "learning_rate": 0.0003895671476137625, | |
| "loss": 1.2407, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.8867924528301887, | |
| "grad_norm": 2.474891424179077, | |
| "learning_rate": 0.0003710691823899371, | |
| "loss": 1.2555, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.9422863485016648, | |
| "grad_norm": 1.0690557956695557, | |
| "learning_rate": 0.00035257121716611174, | |
| "loss": 1.2407, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.997780244173141, | |
| "grad_norm": 1.2744386196136475, | |
| "learning_rate": 0.00033407325194228637, | |
| "loss": 1.1843, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.0532741398446173, | |
| "grad_norm": 0.9873028993606567, | |
| "learning_rate": 0.000315575286718461, | |
| "loss": 0.9438, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.108768035516093, | |
| "grad_norm": 3.0536534786224365, | |
| "learning_rate": 0.00029707732149463563, | |
| "loss": 0.918, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.1642619311875695, | |
| "grad_norm": 1.4433006048202515, | |
| "learning_rate": 0.0002785793562708102, | |
| "loss": 0.9162, | |
| "step": 19500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 27030, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.074621752888525e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |