| { | |
| "best_metric": 1.8553268909454346, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.29673590504451036, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011869436201780416, | |
| "grad_norm": 0.6697233319282532, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0943, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011869436201780416, | |
| "eval_loss": 2.16434907913208, | |
| "eval_runtime": 6.5003, | |
| "eval_samples_per_second": 87.381, | |
| "eval_steps_per_second": 10.923, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02373887240356083, | |
| "grad_norm": 0.7121739387512207, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0255, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03560830860534125, | |
| "grad_norm": 0.6564896702766418, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.125, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04747774480712166, | |
| "grad_norm": 0.5123652219772339, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.0523, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05934718100890208, | |
| "grad_norm": 0.5332870483398438, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.9956, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0712166172106825, | |
| "grad_norm": 0.5742672085762024, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.013, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0830860534124629, | |
| "grad_norm": 0.5574356317520142, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.9698, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09495548961424333, | |
| "grad_norm": 0.5041535496711731, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.9257, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10682492581602374, | |
| "grad_norm": 0.47685691714286804, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9255, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11869436201780416, | |
| "grad_norm": 0.46352121233940125, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.9172, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13056379821958458, | |
| "grad_norm": 0.4706200659275055, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.8964, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.142433234421365, | |
| "grad_norm": 0.47910913825035095, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.9102, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1543026706231454, | |
| "grad_norm": 0.5563710927963257, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.0062, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1661721068249258, | |
| "grad_norm": 0.6444411873817444, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8885, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17804154302670624, | |
| "grad_norm": 0.4616795778274536, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.9145, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18991097922848665, | |
| "grad_norm": 0.3399622142314911, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.8464, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.20178041543026706, | |
| "grad_norm": 0.3937033414840698, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.8395, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.21364985163204747, | |
| "grad_norm": 0.4750767946243286, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.9157, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.22551928783382788, | |
| "grad_norm": 0.47759100794792175, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.8753, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.23738872403560832, | |
| "grad_norm": 0.4606218636035919, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9086, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24925816023738873, | |
| "grad_norm": 0.4468643069267273, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.7881, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.26112759643916916, | |
| "grad_norm": 0.46788281202316284, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.8742, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.27299703264094954, | |
| "grad_norm": 0.43544918298721313, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.8698, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.28486646884273, | |
| "grad_norm": 0.4608367085456848, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.8819, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.29673590504451036, | |
| "grad_norm": 0.5243120789527893, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.9315, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.29673590504451036, | |
| "eval_loss": 1.8553268909454346, | |
| "eval_runtime": 6.4943, | |
| "eval_samples_per_second": 87.461, | |
| "eval_steps_per_second": 10.933, | |
| "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": 5.29768176943104e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |