{ "best_metric": 1.374308466911316, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.10282776349614396, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002056555269922879, "grad_norm": 0.8515931367874146, "learning_rate": 5e-05, "loss": 0.7785, "step": 1 }, { "epoch": 0.002056555269922879, "eval_loss": 2.7108397483825684, "eval_runtime": 30.3275, "eval_samples_per_second": 108.021, "eval_steps_per_second": 13.519, "step": 1 }, { "epoch": 0.004113110539845758, "grad_norm": 0.8138039112091064, "learning_rate": 0.0001, "loss": 0.7817, "step": 2 }, { "epoch": 0.006169665809768638, "grad_norm": 0.8580839037895203, "learning_rate": 9.989294616193017e-05, "loss": 1.7305, "step": 3 }, { "epoch": 0.008226221079691516, "grad_norm": 0.6562185883522034, "learning_rate": 9.957224306869053e-05, "loss": 1.7627, "step": 4 }, { "epoch": 0.010282776349614395, "grad_norm": 1.5407812595367432, "learning_rate": 9.903926402016153e-05, "loss": 1.6594, "step": 5 }, { "epoch": 0.012339331619537276, "grad_norm": 1.459498405456543, "learning_rate": 9.829629131445342e-05, "loss": 1.6157, "step": 6 }, { "epoch": 0.014395886889460155, "grad_norm": 1.3394650220870972, "learning_rate": 9.73465064747553e-05, "loss": 1.5526, "step": 7 }, { "epoch": 0.016452442159383032, "grad_norm": 2.862755060195923, "learning_rate": 9.619397662556435e-05, "loss": 2.1096, "step": 8 }, { "epoch": 0.018508997429305913, "grad_norm": 2.8638174533843994, "learning_rate": 9.484363707663442e-05, "loss": 2.1911, "step": 9 }, { "epoch": 0.02056555269922879, "grad_norm": 1.9752278327941895, "learning_rate": 9.330127018922194e-05, "loss": 2.4096, "step": 10 }, { "epoch": 0.02262210796915167, "grad_norm": 10.006860733032227, "learning_rate": 9.157348061512727e-05, "loss": 4.0356, "step": 11 }, { "epoch": 0.024678663239074552, "grad_norm": 12.076238632202148, "learning_rate": 8.966766701456177e-05, "loss": 4.7412, "step": 12 }, { "epoch": 0.02673521850899743, "grad_norm": 1.0753698348999023, "learning_rate": 8.759199037394887e-05, "loss": 0.7193, "step": 13 }, { "epoch": 0.02879177377892031, "grad_norm": 0.817460834980011, "learning_rate": 8.535533905932738e-05, "loss": 0.6876, "step": 14 }, { "epoch": 0.030848329048843187, "grad_norm": 0.6857183575630188, "learning_rate": 8.296729075500344e-05, "loss": 0.9165, "step": 15 }, { "epoch": 0.032904884318766064, "grad_norm": 1.3912951946258545, "learning_rate": 8.043807145043604e-05, "loss": 1.8627, "step": 16 }, { "epoch": 0.03496143958868895, "grad_norm": 1.9995018243789673, "learning_rate": 7.777851165098012e-05, "loss": 1.3666, "step": 17 }, { "epoch": 0.037017994858611826, "grad_norm": 1.9258147478103638, "learning_rate": 7.500000000000001e-05, "loss": 1.2826, "step": 18 }, { "epoch": 0.0390745501285347, "grad_norm": 1.4042245149612427, "learning_rate": 7.211443451095007e-05, "loss": 1.1946, "step": 19 }, { "epoch": 0.04113110539845758, "grad_norm": 1.0403845310211182, "learning_rate": 6.91341716182545e-05, "loss": 1.2687, "step": 20 }, { "epoch": 0.043187660668380465, "grad_norm": 1.9604305028915405, "learning_rate": 6.607197326515808e-05, "loss": 1.7627, "step": 21 }, { "epoch": 0.04524421593830334, "grad_norm": 1.4346572160720825, "learning_rate": 6.294095225512603e-05, "loss": 1.9745, "step": 22 }, { "epoch": 0.04730077120822622, "grad_norm": 3.7036702632904053, "learning_rate": 5.9754516100806423e-05, "loss": 2.6439, "step": 23 }, { "epoch": 0.049357326478149104, "grad_norm": 6.906707286834717, "learning_rate": 5.6526309611002594e-05, "loss": 3.1967, "step": 24 }, { "epoch": 0.05141388174807198, "grad_norm": 10.569626808166504, "learning_rate": 5.327015646150716e-05, "loss": 3.5308, "step": 25 }, { "epoch": 0.05141388174807198, "eval_loss": 1.6095383167266846, "eval_runtime": 30.5808, "eval_samples_per_second": 107.126, "eval_steps_per_second": 13.407, "step": 25 }, { "epoch": 0.05347043701799486, "grad_norm": 0.6380476951599121, "learning_rate": 5e-05, "loss": 0.6109, "step": 26 }, { "epoch": 0.055526992287917736, "grad_norm": 0.5205564498901367, "learning_rate": 4.6729843538492847e-05, "loss": 0.6063, "step": 27 }, { "epoch": 0.05758354755784062, "grad_norm": 0.4885164797306061, "learning_rate": 4.347369038899744e-05, "loss": 1.6047, "step": 28 }, { "epoch": 0.0596401028277635, "grad_norm": 0.5374402403831482, "learning_rate": 4.0245483899193595e-05, "loss": 1.701, "step": 29 }, { "epoch": 0.061696658097686374, "grad_norm": 1.4350026845932007, "learning_rate": 3.705904774487396e-05, "loss": 1.1647, "step": 30 }, { "epoch": 0.06375321336760925, "grad_norm": 1.5044260025024414, "learning_rate": 3.392802673484193e-05, "loss": 1.1382, "step": 31 }, { "epoch": 0.06580976863753213, "grad_norm": 1.5621658563613892, "learning_rate": 3.086582838174551e-05, "loss": 1.0869, "step": 32 }, { "epoch": 0.067866323907455, "grad_norm": 1.0276201963424683, "learning_rate": 2.7885565489049946e-05, "loss": 1.485, "step": 33 }, { "epoch": 0.0699228791773779, "grad_norm": 1.015711784362793, "learning_rate": 2.500000000000001e-05, "loss": 1.7278, "step": 34 }, { "epoch": 0.07197943444730077, "grad_norm": 1.3744566440582275, "learning_rate": 2.2221488349019903e-05, "loss": 2.1299, "step": 35 }, { "epoch": 0.07403598971722365, "grad_norm": 5.565454959869385, "learning_rate": 1.9561928549563968e-05, "loss": 2.0742, "step": 36 }, { "epoch": 0.07609254498714653, "grad_norm": 8.212292671203613, "learning_rate": 1.703270924499656e-05, "loss": 2.5316, "step": 37 }, { "epoch": 0.0781491002570694, "grad_norm": 0.34369704127311707, "learning_rate": 1.4644660940672627e-05, "loss": 0.5871, "step": 38 }, { "epoch": 0.08020565552699228, "grad_norm": 0.3409431576728821, "learning_rate": 1.2408009626051137e-05, "loss": 0.5753, "step": 39 }, { "epoch": 0.08226221079691516, "grad_norm": 0.29858067631721497, "learning_rate": 1.0332332985438248e-05, "loss": 0.8785, "step": 40 }, { "epoch": 0.08431876606683805, "grad_norm": 0.47956377267837524, "learning_rate": 8.426519384872733e-06, "loss": 1.6915, "step": 41 }, { "epoch": 0.08637532133676093, "grad_norm": 0.5060607194900513, "learning_rate": 6.698729810778065e-06, "loss": 1.1406, "step": 42 }, { "epoch": 0.0884318766066838, "grad_norm": 0.6011289358139038, "learning_rate": 5.156362923365588e-06, "loss": 1.0699, "step": 43 }, { "epoch": 0.09048843187660668, "grad_norm": 0.6478893756866455, "learning_rate": 3.8060233744356633e-06, "loss": 1.0172, "step": 44 }, { "epoch": 0.09254498714652956, "grad_norm": 0.7206456661224365, "learning_rate": 2.653493525244721e-06, "loss": 1.1023, "step": 45 }, { "epoch": 0.09460154241645244, "grad_norm": 1.079906702041626, "learning_rate": 1.70370868554659e-06, "loss": 1.8167, "step": 46 }, { "epoch": 0.09665809768637532, "grad_norm": 1.0317572355270386, "learning_rate": 9.607359798384785e-07, "loss": 2.1526, "step": 47 }, { "epoch": 0.09871465295629821, "grad_norm": 2.9713265895843506, "learning_rate": 4.277569313094809e-07, "loss": 1.8249, "step": 48 }, { "epoch": 0.10077120822622108, "grad_norm": 4.130226135253906, "learning_rate": 1.0705383806982606e-07, "loss": 1.6247, "step": 49 }, { "epoch": 0.10282776349614396, "grad_norm": 6.861790657043457, "learning_rate": 0.0, "loss": 2.2831, "step": 50 }, { "epoch": 0.10282776349614396, "eval_loss": 1.374308466911316, "eval_runtime": 30.5227, "eval_samples_per_second": 107.33, "eval_steps_per_second": 13.433, "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": 3.813995866541261e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }