| { | |
| "best_metric": 11.926570892333984, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.12463000467362517, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024926000934725034, | |
| "grad_norm": 0.017644137144088745, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9325, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024926000934725034, | |
| "eval_loss": 11.928278923034668, | |
| "eval_runtime": 0.2469, | |
| "eval_samples_per_second": 202.487, | |
| "eval_steps_per_second": 52.647, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004985200186945007, | |
| "grad_norm": 0.0209477748721838, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9314, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00747780028041751, | |
| "grad_norm": 0.019896268844604492, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.9318, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009970400373890013, | |
| "grad_norm": 0.018626829609274864, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9319, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012463000467362517, | |
| "grad_norm": 0.016881346702575684, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.9319, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01495560056083502, | |
| "grad_norm": 0.019356146454811096, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9306, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017448200654307525, | |
| "grad_norm": 0.01860245317220688, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.9312, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019940800747780027, | |
| "grad_norm": 0.02110034041106701, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9309, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022433400841252532, | |
| "grad_norm": 0.02060523070394993, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9304, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024926000934725034, | |
| "grad_norm": 0.02121623419225216, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.93, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02741860102819754, | |
| "grad_norm": 0.02653048373758793, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9266, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02991120112167004, | |
| "grad_norm": 0.035975076258182526, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.928, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.032403801215142546, | |
| "grad_norm": 0.021462399512529373, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9317, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03489640130861505, | |
| "grad_norm": 0.020726338028907776, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9313, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.037389001402087556, | |
| "grad_norm": 0.021755684167146683, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.9315, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.039881601495560054, | |
| "grad_norm": 0.023426685482263565, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9307, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04237420158903256, | |
| "grad_norm": 0.02306419052183628, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9308, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.044866801682505064, | |
| "grad_norm": 0.022379403933882713, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.931, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04735940177597757, | |
| "grad_norm": 0.022561531513929367, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.9304, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04985200186945007, | |
| "grad_norm": 0.0245639830827713, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9299, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05234460196292257, | |
| "grad_norm": 0.01966383121907711, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.9305, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05483720205639508, | |
| "grad_norm": 0.022959623485803604, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9298, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05732980214986758, | |
| "grad_norm": 0.026991169899702072, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9287, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05982240224334008, | |
| "grad_norm": 0.03262551128864288, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9275, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.062315002336812586, | |
| "grad_norm": 0.06274564564228058, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9246, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.062315002336812586, | |
| "eval_loss": 11.927188873291016, | |
| "eval_runtime": 0.2529, | |
| "eval_samples_per_second": 197.73, | |
| "eval_steps_per_second": 51.41, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06480760243028509, | |
| "grad_norm": 0.02988523058593273, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9308, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0673002025237576, | |
| "grad_norm": 0.026620937511324883, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.931, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0697928026172301, | |
| "grad_norm": 0.027539031580090523, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9308, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0722854027107026, | |
| "grad_norm": 0.021463748067617416, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.9308, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07477800280417511, | |
| "grad_norm": 0.029648300260305405, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.9309, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0772706028976476, | |
| "grad_norm": 0.030515654012560844, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.9309, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07976320299112011, | |
| "grad_norm": 0.037226639688014984, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.9295, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08225580308459261, | |
| "grad_norm": 0.028905542567372322, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.9293, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08474840317806512, | |
| "grad_norm": 0.027598263695836067, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.928, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08724100327153762, | |
| "grad_norm": 0.03595973178744316, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.9286, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08973360336501013, | |
| "grad_norm": 0.03301599621772766, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.9277, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09222620345848263, | |
| "grad_norm": 0.047346290200948715, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.9287, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09471880355195514, | |
| "grad_norm": 0.03353659436106682, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.9308, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09721140364542763, | |
| "grad_norm": 0.03362715244293213, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.9302, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09970400373890013, | |
| "grad_norm": 0.03183722496032715, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.9306, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10219660383237264, | |
| "grad_norm": 0.03286731615662575, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.9302, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10468920392584515, | |
| "grad_norm": 0.03750745579600334, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.9288, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10718180401931765, | |
| "grad_norm": 0.04005993530154228, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.9296, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10967440411279016, | |
| "grad_norm": 0.03339506313204765, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.929, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11216700420626266, | |
| "grad_norm": 0.03465308994054794, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.9294, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11465960429973517, | |
| "grad_norm": 0.032475683838129044, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.9286, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11715220439320767, | |
| "grad_norm": 0.029818620532751083, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.9299, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11964480448668016, | |
| "grad_norm": 0.030803250148892403, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.9282, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12213740458015267, | |
| "grad_norm": 0.04884568601846695, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.9273, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12463000467362517, | |
| "grad_norm": 0.05727693438529968, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9276, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12463000467362517, | |
| "eval_loss": 11.926570892333984, | |
| "eval_runtime": 0.2536, | |
| "eval_samples_per_second": 197.17, | |
| "eval_steps_per_second": 51.264, | |
| "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": 1042494259200.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |