{ "best_metric": 0.025335997343063354, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.1132983996601048, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002265967993202096, "grad_norm": 18.893938064575195, "learning_rate": 5e-05, "loss": 4.8497, "step": 1 }, { "epoch": 0.002265967993202096, "eval_loss": 6.6952972412109375, "eval_runtime": 22.6932, "eval_samples_per_second": 131.009, "eval_steps_per_second": 16.393, "step": 1 }, { "epoch": 0.004531935986404192, "grad_norm": 21.686246871948242, "learning_rate": 0.0001, "loss": 5.2162, "step": 2 }, { "epoch": 0.006797903979606288, "grad_norm": 19.148719787597656, "learning_rate": 9.989294616193017e-05, "loss": 4.4352, "step": 3 }, { "epoch": 0.009063871972808384, "grad_norm": 14.298290252685547, "learning_rate": 9.957224306869053e-05, "loss": 3.0697, "step": 4 }, { "epoch": 0.01132983996601048, "grad_norm": 14.261772155761719, "learning_rate": 9.903926402016153e-05, "loss": 1.8226, "step": 5 }, { "epoch": 0.013595807959212575, "grad_norm": 11.636271476745605, "learning_rate": 9.829629131445342e-05, "loss": 0.8237, "step": 6 }, { "epoch": 0.015861775952414673, "grad_norm": 7.1677093505859375, "learning_rate": 9.73465064747553e-05, "loss": 0.3949, "step": 7 }, { "epoch": 0.018127743945616767, "grad_norm": 2.269246816635132, "learning_rate": 9.619397662556435e-05, "loss": 0.1084, "step": 8 }, { "epoch": 0.020393711938818865, "grad_norm": 2.78033185005188, "learning_rate": 9.484363707663442e-05, "loss": 0.125, "step": 9 }, { "epoch": 0.02265967993202096, "grad_norm": 1.4293838739395142, "learning_rate": 9.330127018922194e-05, "loss": 0.0661, "step": 10 }, { "epoch": 0.024925647925223057, "grad_norm": 0.876097559928894, "learning_rate": 9.157348061512727e-05, "loss": 0.0184, "step": 11 }, { "epoch": 0.02719161591842515, "grad_norm": 0.7624028325080872, "learning_rate": 8.966766701456177e-05, "loss": 0.0122, "step": 12 }, { "epoch": 0.02945758391162725, "grad_norm": 2.185802459716797, "learning_rate": 8.759199037394887e-05, "loss": 0.3498, "step": 13 }, { "epoch": 0.031723551904829346, "grad_norm": 2.4349617958068848, "learning_rate": 8.535533905932738e-05, "loss": 0.0559, "step": 14 }, { "epoch": 0.033989519898031444, "grad_norm": 1.2613362073898315, "learning_rate": 8.296729075500344e-05, "loss": 0.0509, "step": 15 }, { "epoch": 0.036255487891233534, "grad_norm": 2.2914628982543945, "learning_rate": 8.043807145043604e-05, "loss": 0.0338, "step": 16 }, { "epoch": 0.03852145588443563, "grad_norm": 0.6056019067764282, "learning_rate": 7.777851165098012e-05, "loss": 0.0089, "step": 17 }, { "epoch": 0.04078742387763773, "grad_norm": 0.7699536681175232, "learning_rate": 7.500000000000001e-05, "loss": 0.0082, "step": 18 }, { "epoch": 0.04305339187083983, "grad_norm": 0.7656072378158569, "learning_rate": 7.211443451095007e-05, "loss": 0.0115, "step": 19 }, { "epoch": 0.04531935986404192, "grad_norm": 1.9308295249938965, "learning_rate": 6.91341716182545e-05, "loss": 0.026, "step": 20 }, { "epoch": 0.047585327857244016, "grad_norm": 0.06919915974140167, "learning_rate": 6.607197326515808e-05, "loss": 0.0007, "step": 21 }, { "epoch": 0.04985129585044611, "grad_norm": 0.28471866250038147, "learning_rate": 6.294095225512603e-05, "loss": 0.0027, "step": 22 }, { "epoch": 0.05211726384364821, "grad_norm": 3.3141841888427734, "learning_rate": 5.9754516100806423e-05, "loss": 0.0042, "step": 23 }, { "epoch": 0.0543832318368503, "grad_norm": 0.5131360292434692, "learning_rate": 5.6526309611002594e-05, "loss": 0.0034, "step": 24 }, { "epoch": 0.0566491998300524, "grad_norm": 0.7339416146278381, "learning_rate": 5.327015646150716e-05, "loss": 0.008, "step": 25 }, { "epoch": 0.0566491998300524, "eval_loss": 0.03719233721494675, "eval_runtime": 22.7068, "eval_samples_per_second": 130.93, "eval_steps_per_second": 16.383, "step": 25 }, { "epoch": 0.0589151678232545, "grad_norm": 2.314321279525757, "learning_rate": 5e-05, "loss": 0.4477, "step": 26 }, { "epoch": 0.061181135816456594, "grad_norm": 0.6433771252632141, "learning_rate": 4.6729843538492847e-05, "loss": 0.0116, "step": 27 }, { "epoch": 0.06344710380965869, "grad_norm": 0.34855279326438904, "learning_rate": 4.347369038899744e-05, "loss": 0.0054, "step": 28 }, { "epoch": 0.06571307180286079, "grad_norm": 0.6224886775016785, "learning_rate": 4.0245483899193595e-05, "loss": 0.0107, "step": 29 }, { "epoch": 0.06797903979606289, "grad_norm": 0.6813771724700928, "learning_rate": 3.705904774487396e-05, "loss": 0.005, "step": 30 }, { "epoch": 0.07024500778926497, "grad_norm": 0.5452752113342285, "learning_rate": 3.392802673484193e-05, "loss": 0.0065, "step": 31 }, { "epoch": 0.07251097578246707, "grad_norm": 0.4141976237297058, "learning_rate": 3.086582838174551e-05, "loss": 0.0022, "step": 32 }, { "epoch": 0.07477694377566917, "grad_norm": 0.5566349625587463, "learning_rate": 2.7885565489049946e-05, "loss": 0.0064, "step": 33 }, { "epoch": 0.07704291176887126, "grad_norm": 0.6780135631561279, "learning_rate": 2.500000000000001e-05, "loss": 0.0079, "step": 34 }, { "epoch": 0.07930887976207336, "grad_norm": 0.04653328284621239, "learning_rate": 2.2221488349019903e-05, "loss": 0.0005, "step": 35 }, { "epoch": 0.08157484775527546, "grad_norm": 0.061018314212560654, "learning_rate": 1.9561928549563968e-05, "loss": 0.0004, "step": 36 }, { "epoch": 0.08384081574847756, "grad_norm": 0.03196936100721359, "learning_rate": 1.703270924499656e-05, "loss": 0.0003, "step": 37 }, { "epoch": 0.08610678374167965, "grad_norm": 1.5225857496261597, "learning_rate": 1.4644660940672627e-05, "loss": 0.2704, "step": 38 }, { "epoch": 0.08837275173488174, "grad_norm": 1.1271251440048218, "learning_rate": 1.2408009626051137e-05, "loss": 0.0143, "step": 39 }, { "epoch": 0.09063871972808384, "grad_norm": 0.19105099141597748, "learning_rate": 1.0332332985438248e-05, "loss": 0.0022, "step": 40 }, { "epoch": 0.09290468772128593, "grad_norm": 0.13457505404949188, "learning_rate": 8.426519384872733e-06, "loss": 0.0017, "step": 41 }, { "epoch": 0.09517065571448803, "grad_norm": 0.036084841936826706, "learning_rate": 6.698729810778065e-06, "loss": 0.0004, "step": 42 }, { "epoch": 0.09743662370769013, "grad_norm": 0.3573283851146698, "learning_rate": 5.156362923365588e-06, "loss": 0.004, "step": 43 }, { "epoch": 0.09970259170089223, "grad_norm": 0.285297155380249, "learning_rate": 3.8060233744356633e-06, "loss": 0.0023, "step": 44 }, { "epoch": 0.10196855969409432, "grad_norm": 0.13393811881542206, "learning_rate": 2.653493525244721e-06, "loss": 0.0014, "step": 45 }, { "epoch": 0.10423452768729642, "grad_norm": 0.010668603703379631, "learning_rate": 1.70370868554659e-06, "loss": 0.0001, "step": 46 }, { "epoch": 0.10650049568049852, "grad_norm": 0.04618118703365326, "learning_rate": 9.607359798384785e-07, "loss": 0.0004, "step": 47 }, { "epoch": 0.1087664636737006, "grad_norm": 0.01658078096807003, "learning_rate": 4.277569313094809e-07, "loss": 0.0002, "step": 48 }, { "epoch": 0.1110324316669027, "grad_norm": 0.06205086410045624, "learning_rate": 1.0705383806982606e-07, "loss": 0.0004, "step": 49 }, { "epoch": 0.1132983996601048, "grad_norm": 0.006261133123189211, "learning_rate": 0.0, "loss": 0.0001, "step": 50 }, { "epoch": 0.1132983996601048, "eval_loss": 0.025335997343063354, "eval_runtime": 22.8454, "eval_samples_per_second": 130.136, "eval_steps_per_second": 16.283, "step": 50 } ], "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": true }, "attributes": {} } }, "total_flos": 2.978847951683584e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }