| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18795520400971102, | |
| "eval_steps": 500, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00783146683373796, | |
| "grad_norm": 4.748241901397705, | |
| "learning_rate": 5.01043841336117e-06, | |
| "loss": 14.2858, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01566293366747592, | |
| "grad_norm": 5.58024787902832, | |
| "learning_rate": 1.012526096033403e-05, | |
| "loss": 13.3814, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.023494400501213878, | |
| "grad_norm": 6.483315467834473, | |
| "learning_rate": 1.534446764091858e-05, | |
| "loss": 11.2682, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03132586733495184, | |
| "grad_norm": 8.742202758789062, | |
| "learning_rate": 2.0563674321503132e-05, | |
| "loss": 8.2763, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03915733416868979, | |
| "grad_norm": 1.6051509380340576, | |
| "learning_rate": 2.5782881002087684e-05, | |
| "loss": 5.2789, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.046988801002427756, | |
| "grad_norm": 0.4864032566547394, | |
| "learning_rate": 3.100208768267224e-05, | |
| "loss": 4.2676, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05482026783616571, | |
| "grad_norm": 0.5320207476615906, | |
| "learning_rate": 3.622129436325678e-05, | |
| "loss": 4.1722, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.06265173466990367, | |
| "grad_norm": 0.5318748950958252, | |
| "learning_rate": 4.144050104384134e-05, | |
| "loss": 4.0853, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07048320150364164, | |
| "grad_norm": 0.40588313341140747, | |
| "learning_rate": 4.6659707724425886e-05, | |
| "loss": 4.0692, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.07831466833737959, | |
| "grad_norm": 0.3184826672077179, | |
| "learning_rate": 5.187891440501044e-05, | |
| "loss": 4.024, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08614613517111755, | |
| "grad_norm": 0.43659207224845886, | |
| "learning_rate": 5.709812108559499e-05, | |
| "loss": 4.1053, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.09397760200485551, | |
| "grad_norm": 0.37201637029647827, | |
| "learning_rate": 6.231732776617955e-05, | |
| "loss": 4.0962, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.10180906883859348, | |
| "grad_norm": 0.4702536165714264, | |
| "learning_rate": 6.75365344467641e-05, | |
| "loss": 4.0553, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.10964053567233142, | |
| "grad_norm": 0.30145859718322754, | |
| "learning_rate": 7.275574112734864e-05, | |
| "loss": 3.9976, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.11747200250606939, | |
| "grad_norm": 0.3228236436843872, | |
| "learning_rate": 7.79749478079332e-05, | |
| "loss": 4.0333, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.12530346933980735, | |
| "grad_norm": 0.2818262279033661, | |
| "learning_rate": 8.319415448851775e-05, | |
| "loss": 4.0248, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.1331349361735453, | |
| "grad_norm": 0.3244370222091675, | |
| "learning_rate": 8.841336116910231e-05, | |
| "loss": 4.0115, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.14096640300728328, | |
| "grad_norm": 0.4554711580276489, | |
| "learning_rate": 9.363256784968684e-05, | |
| "loss": 4.0209, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.14879786984102122, | |
| "grad_norm": 0.3277864456176758, | |
| "learning_rate": 9.88517745302714e-05, | |
| "loss": 4.0329, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.15662933667475917, | |
| "grad_norm": 0.4635876715183258, | |
| "learning_rate": 9.999960851927063e-05, | |
| "loss": 4.039, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16446080350849715, | |
| "grad_norm": 0.3449483811855316, | |
| "learning_rate": 9.99979612742731e-05, | |
| "loss": 4.0476, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.1722922703422351, | |
| "grad_norm": 0.32321104407310486, | |
| "learning_rate": 9.999502716393e-05, | |
| "loss": 4.0361, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.18012373717597305, | |
| "grad_norm": 0.2956264615058899, | |
| "learning_rate": 9.999080626376048e-05, | |
| "loss": 4.0272, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.18795520400971102, | |
| "grad_norm": 0.3072601556777954, | |
| "learning_rate": 9.998529868240358e-05, | |
| "loss": 3.9772, | |
| "step": 1200 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 31920, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 5.125992041073869e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |