| { | |
| "best_metric": 0.40978458523750305, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.045119990976001806, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000902399819520036, | |
| "grad_norm": 8.399690628051758, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6447, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000902399819520036, | |
| "eval_loss": 6.4507269859313965, | |
| "eval_runtime": 2.0204, | |
| "eval_samples_per_second": 24.748, | |
| "eval_steps_per_second": 6.434, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001804799639040072, | |
| "grad_norm": 8.699381828308105, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6436, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0027071994585601083, | |
| "grad_norm": 7.802028179168701, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.4002, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003609599278080144, | |
| "grad_norm": 5.152195453643799, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.482, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004511999097600181, | |
| "grad_norm": 3.955629825592041, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.1212, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0054143989171202165, | |
| "grad_norm": 5.4727582931518555, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.9111, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0063167987366402525, | |
| "grad_norm": 3.414292335510254, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.7738, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007219198556160288, | |
| "grad_norm": 2.2245864868164062, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.6139, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008121598375680324, | |
| "grad_norm": 1.9274322986602783, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.7081, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009023998195200361, | |
| "grad_norm": 1.8097221851348877, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.5043, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009926398014720396, | |
| "grad_norm": 1.5614923238754272, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.4841, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010828797834240433, | |
| "grad_norm": 1.6006172895431519, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.5511, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01173119765376047, | |
| "grad_norm": 1.4047011137008667, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.4716, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012633597473280505, | |
| "grad_norm": 1.4601699113845825, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.497, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013535997292800542, | |
| "grad_norm": 1.204664707183838, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.4494, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014438397112320577, | |
| "grad_norm": 1.2878624200820923, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.4607, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.015340796931840614, | |
| "grad_norm": 1.3615275621414185, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.4634, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01624319675136065, | |
| "grad_norm": 1.2070670127868652, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.4906, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.017145596570880686, | |
| "grad_norm": 1.2860541343688965, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.5256, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.018047996390400722, | |
| "grad_norm": 1.0763695240020752, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.4594, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01895039620992076, | |
| "grad_norm": 1.152286171913147, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.4526, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.019852796029440792, | |
| "grad_norm": 1.175243616104126, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.4598, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02075519584896083, | |
| "grad_norm": 1.3951351642608643, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.5541, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.021657595668480866, | |
| "grad_norm": 1.1985777616500854, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4497, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.022559995488000903, | |
| "grad_norm": 1.1992664337158203, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.5265, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022559995488000903, | |
| "eval_loss": 0.40978458523750305, | |
| "eval_runtime": 2.0218, | |
| "eval_samples_per_second": 24.73, | |
| "eval_steps_per_second": 6.43, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02346239530752094, | |
| "grad_norm": 1.0264705419540405, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.4211, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.024364795127040973, | |
| "grad_norm": 1.0953011512756348, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.4428, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02526719494656101, | |
| "grad_norm": 1.0392162799835205, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.4432, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.026169594766081047, | |
| "grad_norm": 1.050638198852539, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.4315, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.027071994585601084, | |
| "grad_norm": 1.119185447692871, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.4856, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02797439440512112, | |
| "grad_norm": 1.1340469121932983, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.4083, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.028876794224641154, | |
| "grad_norm": 1.2006741762161255, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.4851, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02977919404416119, | |
| "grad_norm": 1.2338976860046387, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.4353, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.030681593863681227, | |
| "grad_norm": 1.0770245790481567, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.4629, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.031583993683201264, | |
| "grad_norm": 1.1007499694824219, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.4546, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0324863935027213, | |
| "grad_norm": 1.0557769536972046, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.3652, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03338879332224134, | |
| "grad_norm": 1.2306406497955322, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.421, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03429119314176137, | |
| "grad_norm": 1.1832939386367798, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.3665, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.035193592961281404, | |
| "grad_norm": 1.4779810905456543, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4152, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.036095992780801445, | |
| "grad_norm": 1.2904037237167358, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4003, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03699839260032148, | |
| "grad_norm": 1.4843233823776245, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.4327, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03790079241984152, | |
| "grad_norm": 1.0545917749404907, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.4702, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03880319223936155, | |
| "grad_norm": 1.0966724157333374, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.4913, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.039705592058881585, | |
| "grad_norm": 0.8971771597862244, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.3396, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.040607991878401625, | |
| "grad_norm": 1.0624101161956787, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.4207, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04151039169792166, | |
| "grad_norm": 1.1375459432601929, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.3894, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0424127915174417, | |
| "grad_norm": 1.0266802310943604, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.3847, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04331519133696173, | |
| "grad_norm": 1.5598934888839722, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.4377, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.044217591156481766, | |
| "grad_norm": 1.8163098096847534, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.3741, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.045119990976001806, | |
| "grad_norm": 1.3753440380096436, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4274, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.045119990976001806, | |
| "eval_loss": 0.429287314414978, | |
| "eval_runtime": 2.0683, | |
| "eval_samples_per_second": 24.175, | |
| "eval_steps_per_second": 6.285, | |
| "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": 1.589463780163584e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |