| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 945, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05292405398253506, | |
| "grad_norm": 0.22462093830108643, | |
| "learning_rate": 0.00018962962962962965, | |
| "loss": 1.5354, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10584810796507012, | |
| "grad_norm": 0.2346465140581131, | |
| "learning_rate": 0.00017904761904761907, | |
| "loss": 1.4471, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15877216194760518, | |
| "grad_norm": 0.22219829261302948, | |
| "learning_rate": 0.00016846560846560849, | |
| "loss": 1.4369, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.21169621593014024, | |
| "grad_norm": 0.2058716118335724, | |
| "learning_rate": 0.0001578835978835979, | |
| "loss": 1.4188, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2646202699126753, | |
| "grad_norm": 0.24191923439502716, | |
| "learning_rate": 0.00014730158730158732, | |
| "loss": 1.4202, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.31754432389521037, | |
| "grad_norm": 0.21737360954284668, | |
| "learning_rate": 0.00013671957671957673, | |
| "loss": 1.4195, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.37046837787774545, | |
| "grad_norm": 0.22670969367027283, | |
| "learning_rate": 0.00012613756613756615, | |
| "loss": 1.4092, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.42339243186028047, | |
| "grad_norm": 0.2364790141582489, | |
| "learning_rate": 0.00011555555555555555, | |
| "loss": 1.4003, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.47631648584281555, | |
| "grad_norm": 0.23698057234287262, | |
| "learning_rate": 0.00010497354497354497, | |
| "loss": 1.4084, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5292405398253506, | |
| "grad_norm": 0.23969094455242157, | |
| "learning_rate": 9.43915343915344e-05, | |
| "loss": 1.3919, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5821645938078857, | |
| "grad_norm": 0.24043263494968414, | |
| "learning_rate": 8.380952380952382e-05, | |
| "loss": 1.3694, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6350886477904207, | |
| "grad_norm": 0.25561365485191345, | |
| "learning_rate": 7.322751322751323e-05, | |
| "loss": 1.3791, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6880127017729558, | |
| "grad_norm": 0.23547253012657166, | |
| "learning_rate": 6.264550264550265e-05, | |
| "loss": 1.3867, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.7409367557554909, | |
| "grad_norm": 0.25962698459625244, | |
| "learning_rate": 5.206349206349207e-05, | |
| "loss": 1.3826, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.793860809738026, | |
| "grad_norm": 0.24111054837703705, | |
| "learning_rate": 4.148148148148148e-05, | |
| "loss": 1.3719, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.8467848637205609, | |
| "grad_norm": 0.2652861773967743, | |
| "learning_rate": 3.08994708994709e-05, | |
| "loss": 1.3895, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.899708917703096, | |
| "grad_norm": 0.24232152104377747, | |
| "learning_rate": 2.031746031746032e-05, | |
| "loss": 1.3756, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.9526329716856311, | |
| "grad_norm": 0.2373017519712448, | |
| "learning_rate": 9.735449735449737e-06, | |
| "loss": 1.3885, | |
| "step": 900 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 945, | |
| "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": 4.175813313508147e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |