| { | |
| "best_metric": 1.1442079544067383, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.02545986888167526, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005091973776335052, | |
| "grad_norm": 0.3666571080684662, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7348, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005091973776335052, | |
| "eval_loss": 1.787514090538025, | |
| "eval_runtime": 2.4699, | |
| "eval_samples_per_second": 20.244, | |
| "eval_steps_per_second": 5.263, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010183947552670103, | |
| "grad_norm": 0.5937202572822571, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7144, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0015275921329005156, | |
| "grad_norm": 0.5567353963851929, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.7181, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0020367895105340207, | |
| "grad_norm": 0.32364699244499207, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.6458, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002545986888167526, | |
| "grad_norm": 0.396476149559021, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.5677, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003055184265801031, | |
| "grad_norm": 0.5689886212348938, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.5344, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0035643816434345363, | |
| "grad_norm": 0.2565523684024811, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.5356, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004073579021068041, | |
| "grad_norm": 0.2965347170829773, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.5614, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004582776398701547, | |
| "grad_norm": 0.37253502011299133, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.5705, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005091973776335052, | |
| "grad_norm": 0.4028000235557556, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.495, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005601171153968557, | |
| "grad_norm": 0.5303964018821716, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.5155, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006110368531602062, | |
| "grad_norm": 0.750049352645874, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.4791, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006619565909235567, | |
| "grad_norm": 0.5220856070518494, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.5254, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0071287632868690725, | |
| "grad_norm": 0.6304658651351929, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.3816, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007637960664502578, | |
| "grad_norm": 0.5773172378540039, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.2395, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008147158042136083, | |
| "grad_norm": 0.377210408449173, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.27, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008656355419769588, | |
| "grad_norm": 0.2522292733192444, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.3711, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.009165552797403094, | |
| "grad_norm": 0.2974209487438202, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2771, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009674750175036599, | |
| "grad_norm": 0.2422669380903244, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.3658, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.010183947552670105, | |
| "grad_norm": 0.3074778616428375, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.3865, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010693144930303608, | |
| "grad_norm": 0.31388193368911743, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.3699, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011202342307937114, | |
| "grad_norm": 0.34737786650657654, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.3507, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01171153968557062, | |
| "grad_norm": 0.4096006453037262, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.2984, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.012220737063204125, | |
| "grad_norm": 0.4540800154209137, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.2913, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01272993444083763, | |
| "grad_norm": 0.592296302318573, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.1759, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01272993444083763, | |
| "eval_loss": 1.1890558004379272, | |
| "eval_runtime": 1.8271, | |
| "eval_samples_per_second": 27.366, | |
| "eval_steps_per_second": 7.115, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013239131818471134, | |
| "grad_norm": 0.26080581545829773, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.42, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01374832919610464, | |
| "grad_norm": 0.3292554020881653, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.1536, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.014257526573738145, | |
| "grad_norm": 0.4155060052871704, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.8953, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01476672395137165, | |
| "grad_norm": 0.2531004548072815, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.3548, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.015275921329005156, | |
| "grad_norm": 0.23809029161930084, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.2107, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01578511870663866, | |
| "grad_norm": 0.21378874778747559, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.2265, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.016294316084272165, | |
| "grad_norm": 0.23385454714298248, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.3131, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.016803513461905673, | |
| "grad_norm": 0.24048176407814026, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.3234, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.017312710839539176, | |
| "grad_norm": 0.2692112326622009, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.2975, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01782190821717268, | |
| "grad_norm": 0.29762008786201477, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.2839, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.018331105594806187, | |
| "grad_norm": 0.327226459980011, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.2363, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01884030297243969, | |
| "grad_norm": 0.4358674883842468, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.2147, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.019349500350073198, | |
| "grad_norm": 0.34083041548728943, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.3163, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.019858697727706702, | |
| "grad_norm": 0.22418354451656342, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.3162, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02036789510534021, | |
| "grad_norm": 0.20082779228687286, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.1048, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020877092482973713, | |
| "grad_norm": 0.1930985152721405, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.2333, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.021386289860607217, | |
| "grad_norm": 0.2139016091823578, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.3156, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.021895487238240724, | |
| "grad_norm": 0.1971304565668106, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.1132, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.022404684615874228, | |
| "grad_norm": 0.20899564027786255, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.342, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.022913881993507735, | |
| "grad_norm": 0.2296018749475479, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.3284, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02342307937114124, | |
| "grad_norm": 0.2295154631137848, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.3326, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.023932276748774742, | |
| "grad_norm": 0.2735446095466614, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.2638, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02444147412640825, | |
| "grad_norm": 0.29943835735321045, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.2214, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.024950671504041753, | |
| "grad_norm": 0.37347203493118286, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.2436, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02545986888167526, | |
| "grad_norm": 0.5929493308067322, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0478, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02545986888167526, | |
| "eval_loss": 1.1442079544067383, | |
| "eval_runtime": 1.8425, | |
| "eval_samples_per_second": 27.137, | |
| "eval_steps_per_second": 7.056, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |