| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8768000000000002, | |
| "eval_steps": 500, | |
| "global_step": 900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.18150772154331207, | |
| "learning_rate": 0.0001, | |
| "loss": 1.222, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.19756411015987396, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0496, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.16334174573421478, | |
| "learning_rate": 0.0001943566591422122, | |
| "loss": 1.0084, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.1872260421514511, | |
| "learning_rate": 0.0001887133182844244, | |
| "loss": 0.9866, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.1755620241165161, | |
| "learning_rate": 0.0001830699774266366, | |
| "loss": 0.9553, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.18523474037647247, | |
| "learning_rate": 0.00017742663656884877, | |
| "loss": 0.9591, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1184, | |
| "grad_norm": 0.18473008275032043, | |
| "learning_rate": 0.00017178329571106095, | |
| "loss": 0.9414, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.2784, | |
| "grad_norm": 0.18801915645599365, | |
| "learning_rate": 0.00016613995485327313, | |
| "loss": 0.906, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.4384000000000001, | |
| "grad_norm": 0.18927383422851562, | |
| "learning_rate": 0.00016049661399548536, | |
| "loss": 0.9321, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.5984, | |
| "grad_norm": 0.1739863157272339, | |
| "learning_rate": 0.00015485327313769753, | |
| "loss": 0.9218, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.7584, | |
| "grad_norm": 0.16567449271678925, | |
| "learning_rate": 0.0001492099322799097, | |
| "loss": 0.9324, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.9184, | |
| "grad_norm": 0.17867760360240936, | |
| "learning_rate": 0.0001435665914221219, | |
| "loss": 0.9298, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.0768, | |
| "grad_norm": 0.17996446788311005, | |
| "learning_rate": 0.0001379232505643341, | |
| "loss": 0.9146, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.2368, | |
| "grad_norm": 0.17823895812034607, | |
| "learning_rate": 0.0001322799097065463, | |
| "loss": 0.8931, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.3968, | |
| "grad_norm": 0.17624235153198242, | |
| "learning_rate": 0.00012663656884875847, | |
| "loss": 0.915, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.5568, | |
| "grad_norm": 0.2087327539920807, | |
| "learning_rate": 0.00012099322799097066, | |
| "loss": 0.8858, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.7168, | |
| "grad_norm": 0.19803094863891602, | |
| "learning_rate": 0.00011534988713318284, | |
| "loss": 0.8868, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.8768000000000002, | |
| "grad_norm": 0.19719158113002777, | |
| "learning_rate": 0.00010970654627539505, | |
| "loss": 0.9044, | |
| "step": 900 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1872, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "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": 2.7986928476203008e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |