| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.8352, | |
| "eval_steps": 500, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.17174428701400757, | |
| "learning_rate": 0.0001, | |
| "loss": 1.229, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.1649257093667984, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0561, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.17078982293605804, | |
| "learning_rate": 0.0001943566591422122, | |
| "loss": 1.0143, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.17896169424057007, | |
| "learning_rate": 0.0001887133182844244, | |
| "loss": 0.9925, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.17166747152805328, | |
| "learning_rate": 0.0001830699774266366, | |
| "loss": 0.9619, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.1940702199935913, | |
| "learning_rate": 0.00017742663656884877, | |
| "loss": 0.9658, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1184, | |
| "grad_norm": 0.1746826320886612, | |
| "learning_rate": 0.00017178329571106095, | |
| "loss": 0.9479, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.2784, | |
| "grad_norm": 0.18184725940227509, | |
| "learning_rate": 0.00016613995485327313, | |
| "loss": 0.9126, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.4384000000000001, | |
| "grad_norm": 0.18270964920520782, | |
| "learning_rate": 0.00016049661399548536, | |
| "loss": 0.9387, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.5984, | |
| "grad_norm": 0.17156830430030823, | |
| "learning_rate": 0.00015485327313769753, | |
| "loss": 0.9285, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.7584, | |
| "grad_norm": 0.15996217727661133, | |
| "learning_rate": 0.0001492099322799097, | |
| "loss": 0.9388, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.9184, | |
| "grad_norm": 0.1889728307723999, | |
| "learning_rate": 0.0001435665914221219, | |
| "loss": 0.9368, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.0768, | |
| "grad_norm": 0.1747490018606186, | |
| "learning_rate": 0.0001379232505643341, | |
| "loss": 0.9214, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.2368, | |
| "grad_norm": 0.1738065481185913, | |
| "learning_rate": 0.0001322799097065463, | |
| "loss": 0.9004, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.3968, | |
| "grad_norm": 0.17394229769706726, | |
| "learning_rate": 0.00012663656884875847, | |
| "loss": 0.9218, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.5568, | |
| "grad_norm": 0.20736579596996307, | |
| "learning_rate": 0.00012099322799097066, | |
| "loss": 0.8929, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.7168, | |
| "grad_norm": 0.19318443536758423, | |
| "learning_rate": 0.00011534988713318284, | |
| "loss": 0.8941, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.8768000000000002, | |
| "grad_norm": 0.19400037825107574, | |
| "learning_rate": 0.00010970654627539505, | |
| "loss": 0.9114, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.0352, | |
| "grad_norm": 0.17894019186496735, | |
| "learning_rate": 0.00010406320541760724, | |
| "loss": 0.8913, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.1952, | |
| "grad_norm": 0.19137370586395264, | |
| "learning_rate": 9.841986455981941e-05, | |
| "loss": 0.8833, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.3552, | |
| "grad_norm": 0.2128266543149948, | |
| "learning_rate": 9.27765237020316e-05, | |
| "loss": 0.8772, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.5152, | |
| "grad_norm": 0.20723260939121246, | |
| "learning_rate": 8.71331828442438e-05, | |
| "loss": 0.8814, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.6752000000000002, | |
| "grad_norm": 0.18090017139911652, | |
| "learning_rate": 8.148984198645599e-05, | |
| "loss": 0.8719, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.8352, | |
| "grad_norm": 0.18422921001911163, | |
| "learning_rate": 7.584650112866818e-05, | |
| "loss": 0.8909, | |
| "step": 1200 | |
| } | |
| ], | |
| "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": 3.7402190332532736e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |