| { | |
| "best_metric": 3.511137008666992, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.009620125302132061, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001924025060426412, | |
| "grad_norm": 17.906774520874023, | |
| "learning_rate": 5e-05, | |
| "loss": 6.0347, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001924025060426412, | |
| "eval_loss": 11.804285049438477, | |
| "eval_runtime": 3.3085, | |
| "eval_samples_per_second": 15.113, | |
| "eval_steps_per_second": 3.929, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003848050120852824, | |
| "grad_norm": 23.61397933959961, | |
| "learning_rate": 0.0001, | |
| "loss": 7.818, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005772075181279236, | |
| "grad_norm": 21.09385108947754, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.6106, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007696100241705649, | |
| "grad_norm": 6.846138954162598, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.2, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009620125302132061, | |
| "grad_norm": 6.345388889312744, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 5.8674, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011544150362558473, | |
| "grad_norm": 6.126233100891113, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 5.3815, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013468175422984884, | |
| "grad_norm": 5.865954399108887, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 5.4238, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0015392200483411297, | |
| "grad_norm": 4.0997538566589355, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 5.0759, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0017316225543837708, | |
| "grad_norm": 3.272761583328247, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 5.4185, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0019240250604264121, | |
| "grad_norm": 3.491668701171875, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 5.0995, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0021164275664690532, | |
| "grad_norm": 3.8940975666046143, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 5.8836, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0023088300725116946, | |
| "grad_norm": 4.057229042053223, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 6.0137, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002501232578554336, | |
| "grad_norm": 7.079383850097656, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 3.7789, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0026936350845969768, | |
| "grad_norm": 9.2808198928833, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 3.7065, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002886037590639618, | |
| "grad_norm": 4.389488220214844, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 3.3799, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0030784400966822594, | |
| "grad_norm": 2.8086729049682617, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.697, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0032708426027249003, | |
| "grad_norm": 3.208467483520508, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.9023, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0034632451087675416, | |
| "grad_norm": 3.1035287380218506, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.9703, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003655647614810183, | |
| "grad_norm": 3.597348213195801, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 4.1089, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0038480501208528243, | |
| "grad_norm": 3.196458578109741, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.0048, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004040452626895465, | |
| "grad_norm": 3.222419023513794, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.3464, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0042328551329381065, | |
| "grad_norm": 3.3854458332061768, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.2587, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004425257638980748, | |
| "grad_norm": 3.8163299560546875, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 4.6953, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004617660145023389, | |
| "grad_norm": 4.203793048858643, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.6006, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0048100626510660304, | |
| "grad_norm": 5.980162143707275, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 5.1432, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0048100626510660304, | |
| "eval_loss": 3.733593702316284, | |
| "eval_runtime": 3.3983, | |
| "eval_samples_per_second": 14.713, | |
| "eval_steps_per_second": 3.825, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005002465157108672, | |
| "grad_norm": 4.074855804443359, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.7415, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005194867663151312, | |
| "grad_norm": 5.183741092681885, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 3.1624, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0053872701691939535, | |
| "grad_norm": 5.362056255340576, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.3544, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.005579672675236595, | |
| "grad_norm": 4.090317726135254, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.569, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005772075181279236, | |
| "grad_norm": 3.477642297744751, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.5337, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0059644776873218775, | |
| "grad_norm": 3.0103671550750732, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.6925, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.006156880193364519, | |
| "grad_norm": 2.481553792953491, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.7062, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00634928269940716, | |
| "grad_norm": 2.371243476867676, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 3.7112, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.006541685205449801, | |
| "grad_norm": 2.5417237281799316, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 4.0359, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.006734087711492442, | |
| "grad_norm": 2.821629762649536, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 4.0407, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006926490217535083, | |
| "grad_norm": 3.3124289512634277, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 4.1073, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.007118892723577725, | |
| "grad_norm": 5.673077583312988, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 4.4741, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007311295229620366, | |
| "grad_norm": 1.9838043451309204, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.7683, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.007503697735663007, | |
| "grad_norm": 2.109670877456665, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.7531, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0076961002417056485, | |
| "grad_norm": 2.0147898197174072, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.9084, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007888502747748289, | |
| "grad_norm": 2.1483073234558105, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.1465, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.00808090525379093, | |
| "grad_norm": 1.920487403869629, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.1783, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.008273307759833572, | |
| "grad_norm": 2.0920512676239014, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.47, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.008465710265876213, | |
| "grad_norm": 2.128572940826416, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.6677, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.008658112771918854, | |
| "grad_norm": 2.0647780895233154, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.5179, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008850515277961496, | |
| "grad_norm": 2.5102503299713135, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.6965, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.009042917784004137, | |
| "grad_norm": 2.516993761062622, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.8702, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.009235320290046778, | |
| "grad_norm": 3.2718374729156494, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 4.1012, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.00942772279608942, | |
| "grad_norm": 3.6114237308502197, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 4.1246, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.009620125302132061, | |
| "grad_norm": 6.421860218048096, | |
| "learning_rate": 1e-05, | |
| "loss": 4.5367, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009620125302132061, | |
| "eval_loss": 3.511137008666992, | |
| "eval_runtime": 3.4049, | |
| "eval_samples_per_second": 14.685, | |
| "eval_steps_per_second": 3.818, | |
| "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": 6.631381723512832e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |