| { | |
| "best_metric": 0.9058130383491516, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.13175230566534915, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005270092226613966, | |
| "grad_norm": 10.324965476989746, | |
| "learning_rate": 5e-05, | |
| "loss": 20.2502, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005270092226613966, | |
| "eval_loss": 1.2747288942337036, | |
| "eval_runtime": 99.2994, | |
| "eval_samples_per_second": 12.87, | |
| "eval_steps_per_second": 1.611, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010540184453227932, | |
| "grad_norm": 9.909070014953613, | |
| "learning_rate": 0.0001, | |
| "loss": 21.298, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015810276679841896, | |
| "grad_norm": 9.973806381225586, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 21.1651, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.021080368906455864, | |
| "grad_norm": 7.567232131958008, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 20.472, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.026350461133069828, | |
| "grad_norm": 5.911794185638428, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 20.0485, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03162055335968379, | |
| "grad_norm": 5.7655205726623535, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 17.7948, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03689064558629776, | |
| "grad_norm": 5.374915599822998, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 15.4831, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04216073781291173, | |
| "grad_norm": 4.3298821449279785, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 14.8715, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04743083003952569, | |
| "grad_norm": 4.3553643226623535, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 14.4571, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.052700922266139656, | |
| "grad_norm": 4.488785266876221, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 14.4374, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.057971014492753624, | |
| "grad_norm": 5.779847621917725, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 14.4675, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06324110671936758, | |
| "grad_norm": 5.094208717346191, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 15.4172, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06851119894598155, | |
| "grad_norm": 8.054232597351074, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 15.6023, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07378129117259552, | |
| "grad_norm": 8.434983253479004, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 15.8352, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07905138339920949, | |
| "grad_norm": 5.801580429077148, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 16.2017, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08432147562582346, | |
| "grad_norm": 5.0842509269714355, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 16.3074, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08959156785243742, | |
| "grad_norm": 4.890789031982422, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 16.5253, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09486166007905138, | |
| "grad_norm": 5.724118709564209, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 16.0264, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10013175230566534, | |
| "grad_norm": 3.7091915607452393, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 14.0671, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10540184453227931, | |
| "grad_norm": 3.7077553272247314, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 13.2983, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11067193675889328, | |
| "grad_norm": 3.371248483657837, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 13.469, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11594202898550725, | |
| "grad_norm": 3.0618107318878174, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 13.3668, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 3.0709140300750732, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 13.7794, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12648221343873517, | |
| "grad_norm": 3.5011112689971924, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 13.6792, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13175230566534915, | |
| "grad_norm": 4.160451412200928, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 14.3606, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13175230566534915, | |
| "eval_loss": 0.9058130383491516, | |
| "eval_runtime": 99.7144, | |
| "eval_samples_per_second": 12.817, | |
| "eval_steps_per_second": 1.605, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.932824275748127e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |