{ "best_metric": 0.35463660955429077, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.5637773079633545, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01127554615926709, "grad_norm": 13.32147216796875, "learning_rate": 5e-05, "loss": 13.4143, "step": 1 }, { "epoch": 0.01127554615926709, "eval_loss": 11.712335586547852, "eval_runtime": 9.5509, "eval_samples_per_second": 5.235, "eval_steps_per_second": 1.361, "step": 1 }, { "epoch": 0.02255109231853418, "grad_norm": 13.4596586227417, "learning_rate": 0.0001, "loss": 13.1612, "step": 2 }, { "epoch": 0.03382663847780127, "grad_norm": 13.497325897216797, "learning_rate": 9.990365154573717e-05, "loss": 12.7211, "step": 3 }, { "epoch": 0.04510218463706836, "grad_norm": 10.264798164367676, "learning_rate": 9.961501876182148e-05, "loss": 10.5875, "step": 4 }, { "epoch": 0.05637773079633545, "grad_norm": 9.666766166687012, "learning_rate": 9.913533761814537e-05, "loss": 8.4234, "step": 5 }, { "epoch": 0.06765327695560254, "grad_norm": 15.53061580657959, "learning_rate": 9.846666218300807e-05, "loss": 5.8212, "step": 6 }, { "epoch": 0.07892882311486962, "grad_norm": 16.75433921813965, "learning_rate": 9.761185582727977e-05, "loss": 4.3371, "step": 7 }, { "epoch": 0.09020436927413672, "grad_norm": 12.84736442565918, "learning_rate": 9.657457896300791e-05, "loss": 2.9195, "step": 8 }, { "epoch": 0.1014799154334038, "grad_norm": 24.012882232666016, "learning_rate": 9.535927336897098e-05, "loss": 2.262, "step": 9 }, { "epoch": 0.1127554615926709, "grad_norm": 25.96160125732422, "learning_rate": 9.397114317029975e-05, "loss": 1.3294, "step": 10 }, { "epoch": 0.12403100775193798, "grad_norm": 6.158150672912598, "learning_rate": 9.241613255361455e-05, "loss": 0.421, "step": 11 }, { "epoch": 0.13530655391120508, "grad_norm": 7.238805770874023, "learning_rate": 9.070090031310558e-05, "loss": 0.5187, "step": 12 }, { "epoch": 0.14658210007047218, "grad_norm": 19.430675506591797, "learning_rate": 8.883279133655399e-05, "loss": 0.7906, "step": 13 }, { "epoch": 0.15785764622973925, "grad_norm": 5.920371055603027, "learning_rate": 8.681980515339464e-05, "loss": 0.4845, "step": 14 }, { "epoch": 0.16913319238900634, "grad_norm": 3.0015006065368652, "learning_rate": 8.467056167950311e-05, "loss": 0.3605, "step": 15 }, { "epoch": 0.18040873854827344, "grad_norm": 2.714553117752075, "learning_rate": 8.239426430539243e-05, "loss": 0.4047, "step": 16 }, { "epoch": 0.1916842847075405, "grad_norm": 2.455270767211914, "learning_rate": 8.000066048588211e-05, "loss": 0.377, "step": 17 }, { "epoch": 0.2029598308668076, "grad_norm": 3.998088836669922, "learning_rate": 7.75e-05, "loss": 0.3957, "step": 18 }, { "epoch": 0.2142353770260747, "grad_norm": 1.030561923980713, "learning_rate": 7.490299105985507e-05, "loss": 0.3271, "step": 19 }, { "epoch": 0.2255109231853418, "grad_norm": 4.627074241638184, "learning_rate": 7.222075445642904e-05, "loss": 0.3754, "step": 20 }, { "epoch": 0.23678646934460887, "grad_norm": 4.463960647583008, "learning_rate": 6.946477593864228e-05, "loss": 0.3941, "step": 21 }, { "epoch": 0.24806201550387597, "grad_norm": 1.6291487216949463, "learning_rate": 6.664685702961344e-05, "loss": 0.3648, "step": 22 }, { "epoch": 0.25933756166314303, "grad_norm": 6.867356777191162, "learning_rate": 6.377906449072578e-05, "loss": 0.4291, "step": 23 }, { "epoch": 0.27061310782241016, "grad_norm": 4.641796588897705, "learning_rate": 6.087367864990233e-05, "loss": 0.4116, "step": 24 }, { "epoch": 0.28188865398167723, "grad_norm": 1.0411250591278076, "learning_rate": 5.794314081535644e-05, "loss": 0.3412, "step": 25 }, { "epoch": 0.28188865398167723, "eval_loss": 0.35463660955429077, "eval_runtime": 9.57, "eval_samples_per_second": 5.225, "eval_steps_per_second": 1.358, "step": 25 }, { "epoch": 0.29316420014094435, "grad_norm": 3.1742238998413086, "learning_rate": 5.500000000000001e-05, "loss": 0.3686, "step": 26 }, { "epoch": 0.3044397463002114, "grad_norm": 1.1359697580337524, "learning_rate": 5.205685918464356e-05, "loss": 0.36, "step": 27 }, { "epoch": 0.3157152924594785, "grad_norm": 3.3203868865966797, "learning_rate": 4.912632135009769e-05, "loss": 0.3675, "step": 28 }, { "epoch": 0.3269908386187456, "grad_norm": 0.7137793302536011, "learning_rate": 4.6220935509274235e-05, "loss": 0.3569, "step": 29 }, { "epoch": 0.3382663847780127, "grad_norm": 0.9390913248062134, "learning_rate": 4.3353142970386564e-05, "loss": 0.3432, "step": 30 }, { "epoch": 0.34954193093727975, "grad_norm": 3.187091112136841, "learning_rate": 4.053522406135775e-05, "loss": 0.3686, "step": 31 }, { "epoch": 0.3608174770965469, "grad_norm": 0.7300555109977722, "learning_rate": 3.777924554357096e-05, "loss": 0.3574, "step": 32 }, { "epoch": 0.37209302325581395, "grad_norm": 1.8651896715164185, "learning_rate": 3.509700894014496e-05, "loss": 0.3528, "step": 33 }, { "epoch": 0.383368569415081, "grad_norm": 1.2698091268539429, "learning_rate": 3.250000000000001e-05, "loss": 0.3412, "step": 34 }, { "epoch": 0.39464411557434814, "grad_norm": 1.2524470090866089, "learning_rate": 2.9999339514117912e-05, "loss": 0.3498, "step": 35 }, { "epoch": 0.4059196617336152, "grad_norm": 4.981106758117676, "learning_rate": 2.760573569460757e-05, "loss": 0.3939, "step": 36 }, { "epoch": 0.41719520789288234, "grad_norm": 2.924952983856201, "learning_rate": 2.53294383204969e-05, "loss": 0.3551, "step": 37 }, { "epoch": 0.4284707540521494, "grad_norm": 1.047597885131836, "learning_rate": 2.3180194846605367e-05, "loss": 0.3458, "step": 38 }, { "epoch": 0.4397463002114165, "grad_norm": 4.389070987701416, "learning_rate": 2.1167208663446025e-05, "loss": 0.3967, "step": 39 }, { "epoch": 0.4510218463706836, "grad_norm": 4.27773380279541, "learning_rate": 1.9299099686894423e-05, "loss": 0.408, "step": 40 }, { "epoch": 0.46229739252995067, "grad_norm": 4.0992231369018555, "learning_rate": 1.758386744638546e-05, "loss": 0.4001, "step": 41 }, { "epoch": 0.47357293868921774, "grad_norm": 4.151381492614746, "learning_rate": 1.602885682970026e-05, "loss": 0.4014, "step": 42 }, { "epoch": 0.48484848484848486, "grad_norm": 3.080564260482788, "learning_rate": 1.464072663102903e-05, "loss": 0.3659, "step": 43 }, { "epoch": 0.49612403100775193, "grad_norm": 2.967905044555664, "learning_rate": 1.3425421036992098e-05, "loss": 0.3734, "step": 44 }, { "epoch": 0.507399577167019, "grad_norm": 1.1304935216903687, "learning_rate": 1.2388144172720251e-05, "loss": 0.3536, "step": 45 }, { "epoch": 0.5186751233262861, "grad_norm": 1.7547343969345093, "learning_rate": 1.1533337816991932e-05, "loss": 0.3693, "step": 46 }, { "epoch": 0.5299506694855532, "grad_norm": 0.9396548867225647, "learning_rate": 1.0864662381854632e-05, "loss": 0.3478, "step": 47 }, { "epoch": 0.5412262156448203, "grad_norm": 1.2192246913909912, "learning_rate": 1.0384981238178534e-05, "loss": 0.3545, "step": 48 }, { "epoch": 0.5525017618040874, "grad_norm": 0.6613194942474365, "learning_rate": 1.0096348454262845e-05, "loss": 0.3577, "step": 49 }, { "epoch": 0.5637773079633545, "grad_norm": 0.6536837816238403, "learning_rate": 1e-05, "loss": 0.3133, "step": 50 }, { "epoch": 0.5637773079633545, "eval_loss": 0.3638059198856354, "eval_runtime": 9.5112, "eval_samples_per_second": 5.257, "eval_steps_per_second": 1.367, "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": 1 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3.7108326150334054e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }